Convenient Classification of Phyllostachys heterocycla cv. pubescens Properties Based on Growth Traits and Machine Learning Methods

Convenient Classification of Phyllostachys heterocycla cv. pubescens Properties Based on Growth Traits and Machine Learning Methods | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Convenient Classification of Phyllostachys heterocycla cv. pubescens Properties Based on Growth Traits and Machine Learning Methods Huilan XU, La HU, Shengsen TANG, Peng LI, Haibo LONG, Zhangqi YANG, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8023325/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Bamboo is widely regarded as an eco-friendly construction material due to its rapid growth cycle, strong adaptability, high productivity, and excellent mechanical properties, positioning it as one of the most promising forest-based alternatives to wood. Implementing a property-based classification system that correlat es growth traits with material properties is fundamentally important for a dvancing the rational utilization of bamboo resources. This study employed K-Means, decision tree algorithms, and regression modeling of LASSO and SVR in machine learning to categorize bamboo properties using four key growth traits: age, diameter of breast height, height, and wall thickness. The results demonstrated that growth traits serving as decision tree root nodes and intermediate nodes significantly contribute to bamboo property classification, can reflect the integrated influence of growth traits on material properties, and enable effective and convenient property classification. The material property regression model exhibited rather low fitness, indicating that growth traits alone were insufficient for developing high-accuracy predictive equations. Bamboo material properties growth traits machine learning method classification Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 1. Introduction Global forest resources have experienced significant depletion due to anthropogenic production and increased consumption. According to the “2021 China Forest and Grassland Ecological Comprehensive Monitoring and Evaluation Report (National Forestry and Grassland Administration, 2021)”, China's bamboo forest coverage reached 5.28 million hectares in 2021. Bamboo and bamboo-based products have become important raw materials for new alternative and sustainable building materials [ 1 – 3 ]. China's bamboo processing industry has witnessed remarkable growth in recent years, driven by market demands and technological progress, leading to continuous product innovation and significant economic returns. Moso bamboo( Phyllostachys heterocycla (Carr.) Mitford cv. pubescens ) is a species of large-diameter bamboo in the Poaceae family, belonging to the Phyllostachys . It is the most widely distributed and commonly utilized large-diameter bamboo in China. Bamboo is recognized as one of the most promising forest resources for wood substitution due to its short production cycle, remarkable adaptability, high productivity, and excellent material properties [ 4 – 6 ]. The investigation of bamboo's material properties forms the fundamental basis for its rational utilization. As an anisotropic biomaterial, bamboo exhibits significant variability in its material properties, with lots of influencing factors that complicate prediction and performance modeling. Many studies have established correlations between bamboo's properties and growth traits such as age, DBH (Diameter at Breast Height), height, and wall thickness [ 7 – 9 ]. However, most of the correlation analyses were based on a single indicator, for example, examining the relationship between bamboo properties and age, or studying property variations along the height. This type of approach failed to consider the combined effects of multiple growth traits on bamboo properties [ 9 – 11 ]. In practical applications, bamboo material grading relying solely on individual growth traits (e.g., age or height) demonstrated limited accuracy and reliability [ 12 ]. To improve classification accuracy, it is essential to first identify the most influential growth traits based on practical needs, followed by systematic incorporation of secondary traits for comprehensive assessment. This multivariate methodology significantly improves both the accuracy and credibility of bamboo quality evaluation. This study employed a machine learning method of decision tree algorithm for material classification, which can summarize rules from a series of feature and label data, and present the classification results guided by these rules using a tree diagram structure. The decision tree algorithm was widely used in scientific research, with a focus on identification, evaluation, and prediction in forestry [ 13 – 14 ]. However, there are not many applications in the field of bamboo properties, especially in the research of material property classification [ 15 – 17 ]. There is no consensus on whether similar methods can be applied to bamboo classification, material property evaluation, and prediction. This study comprehensively considered the correlation between four growth traits (age, DBH, height, and wall thickness) and material properties. Using the decision tree algorithm in the machine learning method, the bamboo was first classified into property grades. Secondly, the impact and trend of growth traits on material properties were analyzed, and the correlation between various properties was quantitatively analyzed; Finally, different regression methods were used to analyze the regression models between growth traits and material properties. This study attempted to classify and evaluate bamboo properties using four growth traits, effectively explored the degree of correlation of properties, diversified the application and prediction of property data, and provided a scientific basis for the rational and effective utilization of bamboo resources. 2. Materials and methods 2.1 Moso bamboo The test specimens were collected from a moso bamboo forest located in Ziyuan County, Guangxi, China (25°49´57"N, 100°34´42"E). The site exhibits a subtropical monsoon climate, with recorded mean annual values of 16.7°C air temperature, 1,736 mm precipitation, and 79% relative humidity. The bamboo forest slopes southeast at an angle of 20°, with an elevation of 600 m above sea level. Moso bamboo samples were categorized into three age groups: 2-year-old, 4-year-old, and 6-year-old. Each age group was further divided into four diameter classes: 6 cm, 8 cm, 10 cm, and 12 cm. From each of three plots, we sampled three culms representing each combination of age and diameter class. Each selected culm was felled at 8 m height and divided into four 2-meter-long segments, which were systematically labeled for identification. 2.2 Experimental methods Standard specimens were prepared and tested according to GB/T 15780 − 1995 (Testing Methods for Physical and Mechanical Properties of Bamboo). The investigation included four physical and mechanical properties: (1) air-dry density, (2) modulus of elasticity (MOE), (3) modulus of rupture (MOR), and (4) compressive strength (compression parallel to grain). Furthermore, three dry shrinkage properties were measured: (i) air-dry radial shrinkage, (ii) air-dry tangential shrinkage, and (iii) air-dry volume shrinkage. Defect-free sections with internode lengths exceeding 200 mm were selected from each 2-meter bamboo culm segment for specimen preparation. As illustrated in Fig. 1 , longitudinal strips were extracted along four cardinal orientations (east, south, west, and north) with widths of 15 mm and 30 mm. The 15 mm-wide strips were used to prepare test specimens for density, MOE, MOR, and dry shrinkage properties, while the 30 mm-wide strips were used to make compressive strength testing specimens. All bamboo strips destined for physical and mechanical characterization underwent rigorous conditioning steps: initial drying followed by controlled humidification to attain equilibrium moisture content (12 ± 1%). Specimen fabrication commenced only after mass stabilization was confirmed. For shrinkage specimens, the bamboo strips were fully immersed in distilled water until complete dimensional stabilization was achieved before specimen preparation. Table 1 provided dimensional specifications and corresponding formulas for specimens used in various property tests. Table 1 Specimen dimensions and formulas for different material properties. Properties Dimension Formulas Air-dry density 10mm × 10mm × tmm (wall thickness) \(\:{\rho\:}_{W}=\frac{{m}_{W}}{{V}_{W}}\) \(\:{\rho\:}_{12}={\rho\:}_{W}\left[1-0.01\left(1-K\right)\left(W-12\right)\right]\) \(\:K=\frac{{V}_{W}-{V}_{0}}{{V}_{0}W}\times\:100\) \(\:{\rho\:}_{w}\) : Air-dry density with a moisture content of W%, g/cm 3 \(\:{m}_{w}\) : Weight with a moisture content of W%, g \(\:{V}_{w}\) : Volume with a moisture content of W%, cm 3 \(\:{\rho\:}_{12}\) : Air-dry density with a moisture content of 12%, g/cm 3 W : Moisture content, % K : Volume shrinkage coefficient, % V 0 : Volume with a moisture content of 0%, cm 3 MOE 160mm × 10mm × tmm \(\:{{\rm\:E}}_{W}=\frac{P{L}^{3}}{4b{ℎ}^{3}f}\) E W : MOE with a moisture content of W%, MPa P : Difference between upper and lower limit loads, N L : Span between two supports, 120mm b : Wall thickness, mm h : Height, mm f : Deformation value between upper and lower limit loads, mm MOR 160mm × 10mm × tmm \(\:{\sigma\:}_{bW}=\frac{3{P}_{max}L}{2b{ℎ}^{2}}\) \(\:{{\sigma\:}}_{b12}={\sigma\:}_{bW}\left[1+0.025\left(W-12\right)\right]\) \(\:{{\sigma\:}}_{\text{b}\text{w}}\) : MOR with a moisture content of W%, MPa P max : Failure load, N \(\:{{\sigma\:}}_{b12}\) : MOR with a moisture content of 12%, MPa Compressive strength 20mm × 20mm × tmm \(\:{\sigma\:}_{W}=\frac{{P}_{max}}{bt}\) \(\:{{\sigma\:}}_{12}={\sigma\:}_{W}\left[1+0.045\left(W-12\right)\right]\) \(\:{{\sigma\:}}_{\text{w}}\) : Compressive strength with a moisture content of W%, MPa t : Width, mm \(\:{{\sigma\:}}_{12}\) : Compressive strength with a moisture content of 12%, MPa Air-dry radial /tangential shrinkage 10mm × 10mm × tmm \(\:{{\beta\:}}_{W}=\frac{{L}_{max}-{L}_{W}}{{L}_{max}}\times\:100\) β w : Air-dry radial/tangential shrinkage, % L max : Radial/tangential length with a moisture content higher than the fiber saturation point, mm L W : Radial/tangential length with a moisture content of W%, mm Air-dry volume shrinkage 10mm × 10mm × tmm \(\:{\beta\:}_{{V}_{W}}=\frac{{V}_{max}-{V}_{W}}{{V}_{max}}\times\:100\) \(\:{\beta\:}_{{V}_{W}}\) : Air-dry volume shrinkage, % \(\:{V}_{max}\) : Volume with a moisture content higher than the fiber saturation point, mm 3 \(\:{V}_{w}\) : Volume with a moisture content of W%, mm 3 2.3 Data analysis The K-means clustering algorithm, an unsupervised machine learning approach, was employed to classify bamboo material properties into distinct performance grades based on experimental results. The decision tree algorithm was employed to analyze the relationship between graded material properties and corresponding growth traits, thereby identifying the most determinant growth traits for material property classification. The regression method used decision tree algorithm, LASSO, and SVR methods to simulate material properties using growth traits, and obtain the coefficients and corresponding intercepts of the simulation function. 3. Results and discussion 3.1 Moso bamboo properties Bamboo properties were categorized according to age, DBH, height, and wall thickness, with detailed grouping results presented in Table 2 . The analysis revealed the following key findings: (1) With the exception of tangential shrinkage, all material properties exhibited consistent improvement with increasing bamboo age. While some 2-year-old bamboo specimens demonstrated superior shrinkage properties compared to 4-year-old counterparts, the trend of average values still increased with bamboo age. The tangential shrinkage was the lowest in 2-year-old bamboo. The tangential shrinkage was determined by averaging the shrinkage values from the outer(bamboo green) and inner(bamboo yellow) sides of the bamboo. The bamboo green part exhibited roughly three times greater tangential shrinkage compared to the bamboo inner. Data analysis revealed that the shrinkage proportion near the inner side of 2-year-old bamboo was smaller compared to bamboos of other ages, resulting in less overall shrinkage in 2-year-old bamboo than the others. (2) DBH and height exhibited consistent influence trends on material properties. Specifically, Specimens with DBH > 10 cm demonstrated superior material property performance compared to those with DBH < 10 cm. Similarly, height exceeding 4 m showed enhanced property performance relative to shorter culms (< 4 m). (3) Regarding physical and mechanical properties, specimens with a wall thickness 8 mm. In contrast, wall thickness showed no consistent correlation with shrinkage properties, with only minimal differences observed between mean values. The progressive enhancement of various properties with bamboo age can be primarily attributed to the lignification process. As bamboo matures, this process involves gradual enrichment, deposition, and thickening of cell walls and their contents, resulting in corresponding improvements in material properties over time. Most studies on the radial and vertical trends of bamboo properties explained their variations based on the density of vascular bundles, but the explanation for the experimental results in this article was not sufficient [ 18 – 19 ]. For example, the DBH was inversely proportional to vascular bundle density, but the bamboo properties of larger diameters were better than those of smaller diameters. In the vertical direction, the physical and mechanical properties of the tip were better than those of the base due to the density of vascular bundles. Therefore, the shrinkage performance of the base should be better than that of the tip, because the density of vascular bundles in the base was low and the shrinkage rate was small after dehydration, but the result was the opposite. These findings demonstrated that material properties require multidimensional analysis, as material properties cannot be adequately assessed through singular dominant indicators alone. From an anatomical perspective, as the DBH increases, the density of vascular bundles decreases, the tissue proportion decreases, the fiber length-diameter ratio decreases, and there is no significant change in the fiber lumen-diameter ratio; As the height increases, the density of vascular bundles increases, the tissue proportion increases, the fiber length-diameter ratio shows no significant variation pattern, and the fiber lumen-diameter ratio increases; As the wall thickness increases, the vascular bundle density decreases, the tissue proportion decreases, the fiber length-diameter ratio shows no significant change, and the fiber lumen-diameter ratio decreases [ 19 – 21 ]. The change in material properties was the result of the combined effect of different indicators mentioned above, and it also needed to be compounded by the influence of changes in chemical composition. These anatomical characteristics had varying degrees of influence on different material properties. For example, the difference in physical and mechanical properties produced by DBH was not significant and was lower than the influence of height and wall thickness. However, the impact of DBH on the properties of dry shrinkage materials was much higher than the other two factors. Table 2 Bamboo properties with different ages, DBH, heights, and wall thickness. Property Air dry density (g/cm 3 ) MOE (GPa) MOR (MPa) Compressive strength (MPa) Air dry radial shrinkage (%) Air dry tangential shrinkage (%) Air dry volume shrinkage (%) Age 2 4 6 2 4 6 2 4 6 2 4 6 2 4 6 2 4 6 2 4 6 Sample size 151 159 195 158 192 213 158 192 213 170 180 171 151 159 195 151 159 195 151 159 195 DBH < 10cm 0.57 ± 0.07 0.66 ± 0.07 0.74 ± 0.07 11.42 ± 1.74 13.32 ± 1.59 13.82 ± 1.59 101.45 ± 19.90 129.88 ± 23.27 141.08 ± 17.25 44.34 ± 8.21 52.83 ± 7.98 65.21 ± 7.83 6.32 ± 2.52 3.90 ± 1.67 2.80 ± 1.00 2.47 ± 0.65 2.68 ± 0.70 2.50 ± 0.37 9.24 ± 2.80 7.46 ± 1.74 6.19 ± 1.24 Sample size 176 184 229 243 211 239 243 211 239 227 204 212 176 184 229 176 184 229 176 184 229 DBH > 10cm 0.65 ± 0.09 0.66 ± 0.07 0.75 ± 0.07 12.63 ± 2.05 12.86 ± 1.60 13.19 ± 1.49 121.53 ± 24.88 126.37 ± 18.14 136.64 ± 16.32 55.11 ± 10.22 56.20 ± 7.54 67.97 ± 8.96 3.26 ± 1.32 3.68 ± 1.86 2.53 ± 0.61 2.36 ± 0.45 2.76 ± 0.58 2.51 ± 0.58 6.15 ± 1.46 7.16 ± 2.19 5.92 ± 1.07 Sample size 228 256 334 294 321 370 294 321 370 280 296 287 228 256 334 228 256 334 228 256 334 Height < 4m 0.58 ± 0.07 0.64 ± 0.07 0.74 ± 0.06 11.34 ± 1.58 12.78 ± 1.53 13.27 ± 1.51 105.04 ± 19.84 124.62 ± 20.35 137.13 ± 16.13 46.26 ± 8.78 52.93 ± 7.08 65.14 ± 7.48 5.33 ± 2.64 4.02 ± 1.93 2.68 ± 0.87 2.43 ± 0.60 2.72 ± 0.64 2.52 ± 0.44 8.28 ± 2.82 7.58 ± 2.12 6.12 ± 1.18 Sample size 99 87 90 107 82 82 107 82 82 117 88 96 99 87 90 99 87 90 99 87 90 Height > 4m 0.69 ± 0.07 0.70 ± 0.07 0.77 ± 0.09 14.39 ± 1.28 14.25 ± 1.40 14.46 ± 1.46 137.18 ± 22.65 141.44 ± 16.78 145.99 ± 18.39 60.62 ± 8.17 60.32 ± 7.94 71.50 ± 9.82 3.16 ± 1.09 3.08 ± 0.89 2.56 ± 0.61 2.37 ± 0.43 2.72 ± 0.62 2.46 ± 0.67 5.96 ± 1.22 6.46 ± 1.22 5.75 ± 1.02 Sample size 199 190 232 210 212 216 210 212 216 233 199 200 199 190 232 199 190 232 199 190 232 Wall thick < 8mm 0.62 ± 0.10 0.69 ± 0.07 0.76 ± 0.08 12.64 ± 2.32 14.05 ± 1.41 14.14 ± 1.74 115.75 ± 29.75 138.73 ± 19.70 143.75 ± 18.96 51.46 ± 12.36 57.93 ± 7.76 67.56 ± 9.64 4.93 ± 2.45 3.56 ± 1.46 2.72 ± 0.90 2.47 ± 0.60 2.68 ± 0.72 2.47 ± 0.51 7.81 ± 2.74 7.01 ± 1.60 6.03 ± 1.22 Sample size 128 153 192 191 191 236 191 191 236 164 185 183 128 153 192 128 153 192 128 153 192 Wall thick > 8mm 0.60 ± 0.07 0.63 ± 0.06 0.72 ± 0.05 11.61 ± 1.46 12.01 ± 1.03 12.89 ± 1.09 111.27 ± 18.31 116.17 ± 14.63 134.14 ± 13.21 49.12 ± 7.95 51.06 ± 6.42 65.85 ± 7.15 4.27 ± 2.51 4.05 ± 2.08 2.58 ± 0.72 2.31 ± 0.45 2.77 ± 0.52 2.55 ± 0.47 7.22 ± 2.53 7.64 ± 2.36 6.06 ± 1.08 3.2 Classification 3.2.1 K-Means classification of properties The K-Means algorithm was implemented to classify material properties and establish corresponding quality grades [ 22 ]. As an unsupervised learning approach, the clustering performance is evaluated using two principal criteria: (1) minimization of intra-cluster variation and (2) maximization of inter-cluster separation. The silhouette coefficient, ranging from − 1 to 1, serves as the primary evaluation metric. Values approaching 1 indicate an optimal clustering configuration, where samples demonstrate strong intra-cluster homogeneity and clear inter-cluster distinction. As shown in Table 3 , the clustering analysis of material properties yielded two distinct quality categories: "excellent" and "fine," determined through silhouette coefficient optimization and practical implementation considerations. Cluster center averages exhibited strong agreement with average experimental value for most properties, with the exception of radial and volume shrinkage values that displayed noticeable deviations. Taking density as an example, specimens clustered around center 0.76 were categorized as “excellent”, specimens near center 0.60 were classified as “fine” (Table 3 ). Table 3 Comparison of Silhouette coefficient and cluster centers for 2 and 3 clusters. Age Properties Air dry density (g/cm 3 ) MOE (GPa) MOR (MPa) Compressive strength (MPa) Air dry radial shrinkage (%) Air dry tangential shrinkage (%) Air dry volume shrinkage (%) 2 + 4 + 6 2 clusters Silhouette coef. 0.60 0.54 0.57 0.57 0.72 0.53 0.66 Cluster centers 0.60/0.76 11.47/14.33 143.92/105.65 48.63/67.45 7.00/2.81 2.21/3.06 10.25/6.02 3 clusters Silhouette coef. 0.51 0.54 0.55 0.56 0.61 0.52 0.57 Cluster centers 0.56/0.79/0.67 12.80/15.06/10.43 130.46/99.62/156.79 55.24/69.77/41.86 4.79/2.56/8.29 2.07/3.63/2.72 7.78/5.55/11.39 Experimental average 0.68 12.93 127.28 57.20 3.61 2.55 6.89 2 + 4 2 clusters Silhouette coef. 0.55 0.54 0.56 0.53 0.67 0.51 0.62 Cluster centers 0.72/0.58 14.27/11.28 104.98/144.47 45.10/60.44 3.09/7.26 3.06/2.14 6.21/10.53 3 clusters Silhouette coef. 0.55 0.54 0.54 0.55 0.59 0.52 0.56 Cluster centers 0.74/0.54/0.64 12.62/10.32/15.08 124.46/156.99/96.25 52.79/65.09/40.56 2.77/5.25/8.58 2.57/3.47/1.82 5.61/8.07/11.59 Experimental average 0.64 12.62 120.85 52.52 4.22 2.57 7.43 Table 4 presented the material classification scheme. The data included four growth traits of the specimen (input variables), the first one was bamboo age, with three characteristic values: 2-year-old, 4-year-old, and 6-year-old; The second trait was DBH, with two characteristic values: above 10 cm and below; The third trait was height, with two characteristic values: above 4 m and below; The fourth one was wall thickness, which had two characteristic values: above 8 mm and below. The last column consisted of two grades of material quality (output variables): excellent and fine. Table 4 Representative examples of material property categorization. ID Age DBH Height Wall thick Property category 1 2 < 10 cm (10-) < 4 m (4-) 10 cm (10+) 8 mm (8+) Fine 3 4 4 m (4+) > 8 mm (8+) Excellent … 6 4 m (4+) < 8 mm (8-) Excellent 3.2.2 Decision tree classification Decision trees employ a hierarchical branching structure to analyze feature variables, identify optimal predictive features, and partition datasets accordingly to achieve data classification [ 23 ]. The methodology involves two fundamental considerations: (1) optimal node selection and (2) pruning techniques. By identifying the feature corresponding to the optimal nodes, the priority order of multiple factors that affect material properties can be determined. 3.2.2.1 Ternary decision tree Since age was categorized into three characteristics of 2, 4, and 6-year-olds, ternary decision tree classification was calculated using the C4.5 algorithm [ 24 – 25 ]. Figure 2 showed the classification results of the ternary decision tree. In the figures, the circles represented the root node or middle node, which served as the classification basis; the box represented the leaf node, which indicated the excellent or fine grade label, and the numerical value represented the accuracy of classification. Each path from the root to a leaf node corresponds to a classification rule, which can be expressed as an IF-THEN statement. Taking air-dry density as an example, bamboo age served as the root node of the decision tree, indicating that among the four input variables-age, DBH, height, and wall thickness, age exhibited the highest information gain ratio. Consequently, the decision tree was partitioned into three subsets based on age. Within these subsets, 82% of the 6-year-old specimens were classified as "excellent" and require no further subdivision. For the 2-year-old specimens, height served as the second node, forming the classification criterion at this level. Among these, 88% of specimens with a height below 4 m were classified as "fine." For those exceeding 4 m in height, wall thickness was used as the subsequent splitting attribute, 66% of specimens with a wall thickness below 8 mm were categorized as "excellent," while 83% of those exceeding 8 mm were assigned to the "fine" category. For 4-year-old specimens, wall thickness served as the second node. Among these, 79% of specimens with a wall thickness exceeding 8 mm were classified as "fine." For specimens with a wall thickness below 8 mm, height was used as the subsequent splitting criterion. Among these bamboo properties, only the root node of MOE was the height. Specimens exceeding 4 m in height 87% exhibited "excellent" MOR performance. For specimens below 4 m, age served as the second node: 85% of 2-year-old specimens were categorized as "fine," while 4 and 6-year-old specimens underwent further classification based on wall thickness and DBH. The decision tree structures for air-dry density and compressive strength exhibited identical root and intermediate nodes. Similarly, air-dry radial shrinkage and volume shrinkage shared the same node configuration in their respective decision trees. The ternary decision tree was optimized for training data fitting by maximizing the information gain ratio, without considering potential issues of model complexity or overfitting. Analysis of the classification results revealed that 6-year-old bamboo specimens achieved the highest classification accuracy, with nearly all being categorized as "excellent." The predominance of 6-year-old bamboo in the 'excellent' category disproportionately influenced the model, artificially elevated classification accuracy, and systematically favored age-based splits in root node selection. 2-year-old bamboo specimens showed relatively good classification performance, predominantly falling into the "fine" category. The classification of 4-year-old bamboo required more intermediate nodes in the decision tree, increased model complexity, and susceptibility to overfitting, which consequently resulted in relatively lower classification accuracy. The results indicated that 4-year-old bamboo exhibited comparable proportions of excellent and fine categories, suggesting that classification based solely on growth data has limited effectiveness for quality grade. Some studies have shown that, incorporating density alongside growth traits could significantly improve classification accuracy for material properties [ 26 – 27 ]. The classification accuracy for the dry shrinkage properties was consistently lower than that achieved for physical and mechanical properties, reflecting the higher CV (coefficient of variation) in shrinkage measurements. Some of the accuracy rate for tangential shrinkage prediction was merely 51%, statistically indistinguishable from random guessing. In the ternary decision tree analysis, age and height emerged as the primary decision nodes for physical and mechanical properties, while age and DBH served as the key classification nodes for dry shrinkage properties. 3.2.2.2 Binary decision tree Bamboo age classification was established as follows: 2 and 4-year-old specimens were categorized as mature bamboo, while those 6-year-old specimens were classified as old bamboo [ 28 ]. The binary decision tree excluded the old bamboo and only analyzed the mature bamboo. After removing the 6-year-old part, two remaining characteristics were used for analysis using the binary decision tree in Scikit-learn. Figure 3 presented the classification results of various material properties using binary decision trees. Unlike the ternary decision tree model, height demonstrated greater classification importance than age for mature bamboo categorization. Each material property may have multiple decision trees, but the ones displayed in the figures were the most frequently occurring models with higher classification accuracy. Radial and volume shrinkage were listed as two decision trees with high frequency of occurrence, with a ratio of 8:5 and 7:5. In the binary decision tree model, bamboo age no longer served as the root node, allowing other traits to demonstrate their predictive importance. Among physical-mechanical properties, height emerged as the most influential factor, particularly for mechanical properties. Specimens exceeding 4 meters in height were consistently classified as 'excellent' with relatively high accuracy. While DBH showed no significant contribution to the classification of physical-mechanical properties. The incorporation of both height and wall thickness parameters led to a measurable enhancement in prediction accuracy. In the shrinkage property analysis, DBH demonstrated significant predictive importance in the binary decision tree model, with every tree participating in the classification process and even serving as root nodes in some cases. However, the overall accuracy improvement of the binary tree model compared to the ternary tree model was relatively marginal, which can be primarily attributed to the inherent characteristics of the dataset itself. 3.2.2.3 Single-feature binary decision tree root nodes and accuracy To observe the root nodes under different conditions, the decision root nodes and accuracy of various bamboo ages, different DBH, heights, and wall thicknesses were analyzed. The root nodes obtained from the analysis were not singular, and Table 5 showed the root nodes with the highest frequency of occurrence. The DBH, height, and wall thickness were the data analysis results of mature bamboo. If 6-year-old bamboo was added, almost all root nodes were of bamboo age. Table 5 Decision tree root nodes and accuracy for each characteristic. Property 2-year-old 4-year-old 6-year-old 10 cm 4 m 8 mm Air-dry density Height/73% Thick/65% Height/84% Age/68% Thick/69% Age/64% Thick/79% DBH/77% DBH/57% MOE Height/84% Height/78% Height/79% Age/77% Height/87% Age/80% Age/91% Age/83% Height/80% MOR Height/77% Thick/75% Height/87% Age/78% Thick/74% Thick/75% Age/72% Age/77% Height/75% Compressive strength Height/78% Height/62% Thick/85% Age/72% Thick/68% Age/64% Thick/87% Height/78% DBH/63% Air-dry radial shrinkage DBH/78% Height/83% DBH/98% Age/74% Height/88% DBH/74% Age/96% Height/84% Age/74% Air-dry tangential shrinkage DBH/75% DBH/52% Thick/64% Age/64% Age/69% Age/63% Age/66% Age/62% Age/65% Air-dry volume shrinkage DBH/76% Height/78% DBH/97% Age/67% Height/86% Age/70% Thick/96% Height/82% Age/71% The results of physical and mechanical properties showed that the root nodes of different bamboo ages were mostly height without DBH. Furthermore, bamboo age frequently served as the root node in classifications based on DBH, height, and wall thickness. The analysis of dry shrinkage properties revealed that age exerted the most significant influence. For the same age, DBH was the dominant factor, whereas wall thickness contributed minimally to shrinkage classification. Analysis across all bamboo ages (2-, 4-, and 6-year-old), mature bamboo (2- and 4-year-old), and individual indicators demonstrated consistent root nodes among the three analytical approaches. Specifically, physical and mechanical properties were primarily determined by age, and height; dry shrinkage properties were predominantly influenced by age and DBH. These findings indicated that while decision trees are subject to data structure constraints and inherent decision limitations, their root nodes maintain significant reference value. In accordance with the principles of optimizing the loss function while minimizing decision tree model complexity, field applications should prioritize root nodes as classification indicators. 3.3 Material properties’ correlation The decision tree can quantify the relative importance of independent variables on the dependent variable using feature importances, enabling a quantitative analysis of their interaction effects. Figure 4 presented a percentage correlation matrix among various indicators derived from decision tree analysis, representing the average importance of each indicator (only for mature bamboo). The circled areas in the figure represented regions of high correlation, demonstrating significant interaction effects among growth traits, physical-mechanical properties, and dry shrinkage properties. The percentage of correlation between each indicator can be sorted, making it a relatively reliable method to predict or judge the quality of other material indicators using known indicators. Taking density as an example, the horizontal summation of values equals 100%. The indicator most strongly correlated with density was MOE, followed by compressive strength and MOR (Fig. 4 ). The growth traits (DBH, height, and wall thickness) exhibited moderate positive correlations, resulting in relatively high correlation percentages between them. Notably, both height and wall thickness had the strongest correlation with MOE, underscoring the significance of these traits, particularly height, as key determinants of MOE. The physical-mechanical property analysis revealed significant interactions among the four properties, with MOE being additionally influenced by height. The shrinkage property analysis revealed the strongest mutual influence between radial and volume shrinkage. In contrast, radial and tangential shrinkage remained largely independent with limited interaction. Matrix longitudinal analysis revealed that each indicator contributed most significantly to MOE property, followed by compressive strength and density, with age contributing the least. 3.4 Regression Multiple regression models were undertaken to predict material properties by using age, DBH, height, and wall thickness. The purpose of undertaking regression analysis is to establish whether some growth traits can be used to infer properties that are normally measured destructively [ 26 , 29 ]. Multivariate linear regression models were considered using the Machine Learning method, such as Decision Tree, LASSO [ 30 ], and SVR [ 31 ]. ŷ = ω 0 + ω 1 x 1 + ω 2 x 2 + … + ω n x n (1) where ŷ means material property, x means traits, like age, DBH, height, and wall thickness, and the size of x depends on the number of traits considered. ω 0 is the intercept, ω n is the regression coefficient of each trait. Table 6 presented the detailed regression outputs, including: (i) feature importances from decision tree analysis, (ii) regression coefficients and intercepts for both LASSO and SVR models, along with (iii) model performance metrics (MSE, R², and Score). Model evaluation revealed the highest accuracy for MOE regression and the lowest for tangential air-dried shrinkage. Figure 5 compared regression model performances for these two properties. Regression modeling using only four growth traits demonstrated limited accuracy in predicting material properties. Although model optimization slightly improved performance metrics, the enhancements remained marginal, as the predictive capacity was fundamentally constrained by the inherent limitations of the input data. Table 6 Feature importances for the decision tree and the regression coefficient for Lasso and SVR. Property Traits Age DBH Height Thick Intercept MSE R 2 Score Air dry density Decision Tree 0.192 0.325 0.460 0.022 - 0.004 0.518 0.518 Lasso 0.029 0.006 0.012 -0.012 0.550 0.005 0.330 0.344 SVR 0.036 0.005 0.017 -0.008 0.504 0.005 - 0.342 MOE Decision Tree 0.179 0.347 0.403 0.071 - 1.343 0.630 0.630 Lasso 0.502 -0.162 0.620 -0.113 12.196 1.908 0.452 0.551 SVR 0.441 0.065 0.370 -0.369 12.684 1.703 - 0.533 MOR Decision Tree 0.220 0.359 0.306 0.115 - 269.887 0.573 0.573 Lasso 7.575 -2.173 7.696 0.762 95.365 392.054 0.307 0.401 SVR 7.861 1.019 4.503 -2.046 90.113 349.629 - 0.395 Compressive strength Decision Tree 0.141 0.238 0.538 0.083 - 50.318 0.482 0.482 Lasso 2.644 1.323 1.690 -1.497 38.893 57.658 0.372 0.379 SVR 2.786 2.034 0.356 -2.387 41.365 57.176 - 0.361 Air dry radial shrinkage Decision Tree 0.336 0.447 0.111 0.106 - 2.963 0.419 0.419 Lasso -0.421 0.156 -0.727 -0.567 10.394 3.675 0.216 0.296 SVR -0.317 0.141 -0.639 -0.575 9.663 3.532 - 0.272 Air dry tangential shrinkage Decision Tree 0.342 0.369 0.129 0.160 - 0.333 0.186 0.186 Lasso 0.175 -0.002 -0.022 -0.043 2.469 0.358 0.045 0.017 SVR 0.168 -0.015 -0.022 -0.045 2.586 0.307 - 0.025 Air dry volume shrinkage Decision Tree 0.031 0.472 0.304 0.193 - 4.135 0.289 0.289 Lasso -0.101 0.083 -0.695 -0.498 12.770 4.486 0.163 0.239 SVR -0.076 0.077 -0.672 -0.570 12.889 4.247 - 0.237 4. Conclusions The material properties of Moso bamboo were investigated using samples collected from Ziyuan County, Guangxi, China. Seven material properties were experimentally determined: air-dry density, MOE, MOR, compressive strength, and air-dry shrinkage properties (radial, tangential, and volumetric). These datasets were analyzed using machine learning approaches, yielding three principal outcomes: (a) identification of critical classification indicators through decision tree root node analysis, (b) quantitative evaluation of inter-parameter correlations, and (c) development of growth traits-based regression models for property prediction. The study's major findings lead to the following conclusions: (1) With the exception of tangential shrinkage, all material properties exhibited consistent improvement with increasing bamboo age. Specimens with DBH exceeding 10 cm exhibited superior material properties compared to those under 10 cm; similarly, bamboo height taller than 4 m showed enhanced properties relative to shorter ones. Specimens with a wall thickness of 8 mm. Excluded the factor of bamboo age, height had a significant impact on the physical and mechanical properties of bamboo, while DBH had a significant impact on the dry shrinkage properties. (2) There was a certain degree of uncertainty in using four growth traits to classify wood properties in decision trees, which was affected by data structure and was a limitation of statistical analysis. The accuracy of the physical mechanical properties’ decision tree in this study was around 75%, with the two main traits being age and height. When it comes to mature bamboo or single bamboo age, height was the most important trait for classification. The accuracy of the decision tree for the dry shrinkage properties was around 67%, and the two main traits were age and DBH. When it came to mature bamboo or single bamboo age, DBH was the most important classification trait. The influence of wall thickness difference was far less than that of age and height, but it could serve as a reference for a secondary selection trait in terms of physical and mechanical properties. Therefore, when classifying materials, different classification traits should be selected according to the actual situation to effectively improve classification accuracy. (3) Correlation analysis showed each indicator had a corresponding maximum proportion indicator, which can be used to determine the trend of unknown indicators through sorting and known indicator information. Matrix longitudinal analysis showed that each indicator contributed the most to MOE, while age contributed the least to other material properties. (4) The regression results showed that simulating material properties based on four growth traits had low accuracy. Especially, the accuracy at both ends of the value range was very low. The regression coefficients of the model indirectly reflect the influence of different growth traits on material properties. Declarations The authors have no relevant financial or non-financial interests to disclose. The authors have no conflicts of interest to declare that are relevant to the content of this article. All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript. The authors have no financial or proprietary interests in any material discussed in this article. Author Contribution Huilan XU and La HU wrote the main manuscript text. The experiments were conducted by Shengsen TANG and Peng LI. The manuscript was polished by Haibo LONG, and the bamboo planting experiment was designed by Zhangqi YANGand Guiping YANG. All authors have reviewed and approved the final manuscript. Acknowledgements This research was financially supported by the Bagui Scholars Program of Guangxi (2019A26), and Science and Technology Major Project of Guangxi (Guike AA 24263024). References A. Bala, S. Gupta. Engineered bamboo and bamboo-reinforced concrete elements as sustainable building materials: A review. Construction and Building Materials. 2023, 394, 132116. Z. Lou, Z. Zheng, N. Yan, X. Jiang, X. Zhang, S. Chen, R. Xu, C. Liu, L. Xu. Modification and Application of Bamboo-Based Materials: A Review-Part II: Application of Bamboo-Based Materials. Forests. 2023, 14, 2266. H. Du, B. Chen, Z. Chen, Y. Wei, X. Hu. Study on flexural performance of glued laminated bamboo and timber-concrete composite beams. Construction and Building Materials. 2025, 492, 142986. P.G.Dixon, L.J.Gibson. The Structure and mechanics of Moso bamboo material. Journal of the Royal Society Interface. 2014, 11, 20140321. H. Sun, H. Li, A. Dauletbet, R. Lorenzo, I. Corbi, O. Corbi, M. Ashraf. Review of materials and structure inspired by bamboo. Construction and Building Materials. 2022, 325, 126656. C. Hong, H. Li, Z. Xiong, R. Lorenzo, I. Corbi, O. Corbi, D. Wei, C. Yuan, D. Yang, H. Zhang. Review of connections for engineered bamboo structures. Journal of Building Engineering. 2020, 30, 101324. S. MEI, D. Zhao, X. Meng, H. Qi, Y. Gao. Experimental study on tensile properties of the arc outer green skin of bamboo. Journal of Forestry Engineering. 2022, 7(3): 60-66. S.P. Sylvayanti, N. Nugroho, E.T. Bahtiar. Bamboo Scrimber’s Physical and Mechanical Properties in Comparison to Four Structural Timber Species. Forests. 2023, 14(1): 146. Nurmadina, N. Nugroho, E.T. Bahtiar. Structural grading of Gigantochloa apus bamboo based on its flexural properties. Construction and Building Materials. 2017, 157: 1173-1189. X. Wang, Y. Zhong, X. Luo, H. Ren. Compressive Failure Mechanism of Structural Bamboo Scrimber. Polymers. 2021, 13(23): 4223. M.F.V. Adier, M.E.P. Sevilla, D.N.R. Valerio, J.M.C. Ongpeng. Bamboo as Sustainable Building Materials: A Systematic Review of Properties, Treatment Methods, and Standards. Buildings. 2023, 13, 2449. S. Qin, Y. ZONG, A. HUANG, X. Zhang, H. Liu. Research Progress and Prospects of Bamboo Grading. China Forest Products Industry. 2022, 59(03): 49-54. Y. Feng, S. Mekhilef, D. Hui, C.L.Chow, D. Lau. Machine learning-assisted wood materials: Applications and future prospects. Extreme Mechanics Letters. 2024, 71: 102209. S.Dubey, D. Gupta, M. Mallik. Foretelling the compressive strength of bamboo using machine learning techniques. Engineering Computations. 2024, 41(8-9): 2251-2288. J.F. Correal, A.F. Calvo, D.J.A. Trhjillo, J.S. Echeverry. Inference of mechanical properties and structural grades of bamboo by machine learning methods. Construction and Building Materials. 2022, 354, 129116. L. Tong, B. Li, Y. Geng, L. Chen, Y. Li, R. Cao. Spectrometric Classification of Bamboo Shoot Species by Comparison of Different Machine Learning Methods. Food Analytical Methods. 2021, 14: 300-306. J. Li, H. Xu, Y, Zhang, T. Zhong, K. Semple, V. Nasir, H. Wang, C. Dai. Radial distribution of vascular bundle morphology in Chinese bamboos: machine learning methodology for rapid sampling and classification. Holzforschung. 2023, 77(6): 468-483. L. Mao, X. Kong, P. Liang, J. Fu, J. Xu. Research Progress in Factors Influencing Physical and Mechanical properties of Bamboo. World Bamboo and Rattan. 2024, 22(2): 91-97. W. Fang, Y. Gui, L. Ma, A. Jin, X. Xin, X. Yu, L. Ma, J. Q. Chinese Economic Bamboo. Beijing: Science Press. 2015. C. Chang, F. Chang. Comprehensive review of the elastic constants of bamboo. Eur. J. Wood Prod. 2024, 82: 1793-1754. F. Rusch, A.D. Wastowski, T.S. de Lira, et al . Description of the component properties of species of bamboo: a review. Biomass Conv. Bioref. 2023, 13:2478-2495. A. Pérez-Suárez, J.F. Martínez-Trinidad, J.A. Carrasco-Ochoa. A review of conceptual clustering algorithms. Artificial Intelligence Review. 2019, 52, 1267-1296. R.A. Olshen，J.R. Quinlan. Induction of decision trees. Machine Learning. 1986, 1(1): 81-106. R.A. Olshen, J.R. Quinlan. C4.5: Programs for machine learning. San Mateo, CA: Morgan Kaufmann Publishers. 1992. Li Hang. Statistical Learning Method. Beijing: Tsinghua University Press. 2019. S. Chen, R. Shiina, K. Nakia, T. Awano, A. Yoshinaga, J. Sugiyama. Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction. Journal of Wood Science. 2023, 69: 22. S. Chen, T. Awano, A, Yoshinaga, J, Sugiyama. Flexural behavior of wood in the transverse direction investigated using novel computer vision and machine learning approach. Holzforschung. 2022, 79(10): 875-885. National Forestry and Grassland Administration. Forestry Industry Standard of Peoples’s Republic of China, LY/T 2908-2017, Regulations for age-class and age-group division of main tree-species. 2017. E.T. Bahtiar, A.P. Imanullah, D. Hermawan, N. Nugroho. Structural grading of three sympodial bamboo culms (Hitam, Andong, and Tali) subjected to axial compressive Load. Engineering Structures. 2019, 181, 233-245. E.T. Bahtiar, D. Trujillo, N. Nugroho. Compression resistance of short members as the basis for structural grading of Guadua angustifolia. Construction and Building Materials. 2020, 249, 118759. R.Tibshirani. Regression shrinkage and selection via the lasso. The Journal of the Royal Statistical Society: Series B (methodological). 1996, 58(1): 267-288. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8023325","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":539497487,"identity":"753d7903-aa64-4de3-b9a2-427820d147ae","order_by":0,"name":"Huilan XU","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYBACfvbmAwYfKv4x8zMzHyBOi2TPsYTCGWcOsEu2tyUQp8Xgho/BZ86WA/wGPWcMiHTZDbbEzYwNd6QNJHI+3njDYCen20BAB+Ps5sPGhTueGZtL5G62nMOQbGx2gIAWZpljacYzzzAnW87I3SbNw3AgcRshLWwSOea/eduY6zfcyHlGnBYeiRwDY962w8wGZ86wEadFgudYguGMM2nMwEA2tpxjQIRf7I+Do9IGFJUPb7ypsJMjqAXNSmKjBkkLqTpGwSgYBaNgRAAAMxNHzTlxl4oAAAAASUVORK5CYII=","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":true,"prefix":"","firstName":"Huilan","middleName":"","lastName":"XU","suffix":""},{"id":539497488,"identity":"ec425acb-acac-4445-b502-9415d4583851","order_by":1,"name":"La HU","email":"","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":false,"prefix":"","firstName":"La","middleName":"","lastName":"HU","suffix":""},{"id":539497489,"identity":"ab279bff-7558-4d30-9704-087c7c376d1e","order_by":2,"name":"Shengsen TANG","email":"","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Shengsen","middleName":"","lastName":"TANG","suffix":""},{"id":539497490,"identity":"7c29e6af-8996-428e-9940-12a6015582d9","order_by":3,"name":"Peng LI","email":"","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Peng","middleName":"","lastName":"LI","suffix":""},{"id":539497491,"identity":"6c0c2ff6-199f-4f14-9802-e722f66ea98e","order_by":4,"name":"Haibo LONG","email":"","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Haibo","middleName":"","lastName":"LONG","suffix":""},{"id":539497492,"identity":"14ae2240-4930-4a81-8557-24d3e1c14dc3","order_by":5,"name":"Zhangqi YANG","email":"","orcid":"","institution":"Guangxi Forestry Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Zhangqi","middleName":"","lastName":"YANG","suffix":""},{"id":539497493,"identity":"65d494bf-5f1c-4a53-8532-8472ebe9b2ee","order_by":6,"name":"Guiping YANG","email":"","orcid":"","institution":"Ziyuan Forest Farm","correspondingAuthor":false,"prefix":"","firstName":"Guiping","middleName":"","lastName":"YANG","suffix":""}],"badges":[],"createdAt":"2025-11-04 01:53:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8023325/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8023325/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95704381,"identity":"1065d191-fdf3-4f63-b3e4-91f2a3b40302","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1011350,"visible":true,"origin":"","legend":"","description":"","filename":"ConvenientClassificationofPhyllostachysheterocyclacv.pubescensPropertiesBasedonGrowthTraitsandMachineLearningMethods.docx","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/3a2273db0d8a58cb27e3a586.docx"},{"id":95704377,"identity":"ff4d4039-8817-4bab-8d91-bcbdd81a9672","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7586,"visible":true,"origin":"","legend":"","description":"","filename":"2fe11487f9264833a96bd2644c73a28e.json","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/2bba7b4a014c41189bc5489c.json"},{"id":95704386,"identity":"1c4ad517-bf39-42e5-ab37-de0b8a14444f","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":150371,"visible":true,"origin":"","legend":"","description":"","filename":"2fe11487f9264833a96bd2644c73a28e1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/67b984b18aa31aacb7b53068.xml"},{"id":95704376,"identity":"ac0b5362-61dd-4555-a9b2-7f2b96600444","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":56104,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/33cd547ef68b2dd38724d56b.jpeg"},{"id":95704385,"identity":"bb0dfb98-6379-4461-b408-f9cdf3915da4","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":636438,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/0eb50bee14b28fca466e49f1.jpeg"},{"id":95799066,"identity":"2fb6f27d-84af-491a-a026-45fff9a0d9dc","added_by":"auto","created_at":"2025-11-13 08:18:36","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":587517,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/06754f8631b076d4df41a102.jpeg"},{"id":95800827,"identity":"8f06c5c4-c5fc-44fc-b120-b8dc4c9859ae","added_by":"auto","created_at":"2025-11-13 08:23:41","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":248713,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/776468e73380abe21b7ef2e9.jpeg"},{"id":95704388,"identity":"0947c22e-3072-49e7-ac3e-f6eff8694251","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":117687,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/8d65004d3c195c4a0aa07a55.jpeg"},{"id":95704383,"identity":"c6d74ea8-6158-4ac8-98d8-b02f39becd7d","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17678,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/992925da97bf94cddc895fed.png"},{"id":95704389,"identity":"e24db86b-1937-4a3e-b12c-3c5642724561","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148691,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/6c11274106a0b2190b025e61.png"},{"id":95704391,"identity":"c62271df-c0d8-40ff-b6f6-e2dfdb6539d0","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":136518,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/9321bcfd6984a8856ac5c5bb.png"},{"id":95704390,"identity":"531adc65-99ba-4a44-a6b4-d1a13e636b2a","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":58440,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/b40d0c3581749f922f33ca03.png"},{"id":95704384,"identity":"8a7b7f36-7036-4614-a924-43f1d5270c97","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27497,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/48f566c998473a4413473476.png"},{"id":95704392,"identity":"8b7df66f-a75f-47be-ae08-ad4d8179fc8b","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"xml","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":152307,"visible":true,"origin":"","legend":"","description":"","filename":"2fe11487f9264833a96bd2644c73a28e1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/feb7bd73f7e5807197aaa83a.xml"},{"id":95704393,"identity":"50e0d681-6583-4947-a9c8-4ba9983a84b7","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"html","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":158231,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/04b72d6b127cb8a19219e0be.html"},{"id":95704374,"identity":"5a66d9d8-dfb1-43f9-9a7d-fb9bda2e44a5","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":20292,"visible":true,"origin":"","legend":"\u003cp\u003eMethod for extracting test specimens.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/b9e0b57e0be3d7faa9ebf752.png"},{"id":95704375,"identity":"41449d9f-40a0-4e3b-91ef-b2d2fcf5d0dd","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":167595,"visible":true,"origin":"","legend":"\u003cp\u003eTernary decision tree and accuracy. (a)air dry density; (b)MOE; (c)MOR; \u0026nbsp;\u0026nbsp;(d)compressive strength; (e)air dry radial shrinkage; (f)air dry tangential \u0026nbsp;\u0026nbsp;shrinkage; (g)air dry volume shrinkage.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/76660c70b7d040e3ca24da68.png"},{"id":95799108,"identity":"16d44341-d6a7-43c2-9c64-d32de2bc612f","added_by":"auto","created_at":"2025-11-13 08:18:49","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":151346,"visible":true,"origin":"","legend":"\u003cp\u003eBinary decision tree and accuracy. (a)air dry density; (b)MOE; (c)MOR; \u0026nbsp;\u0026nbsp;(d)compressive strength; (e)air dry radial shrinkage; (f)air dry tangential \u0026nbsp;\u0026nbsp;shrinkage; (g)air dry volume shrinkage.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/321cbdb7921daaa828169d9d.png"},{"id":95800160,"identity":"bcc09c89-60bb-4a5f-9452-5d8513e5e0c0","added_by":"auto","created_at":"2025-11-13 08:21:44","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":75143,"visible":true,"origin":"","legend":"\u003cp\u003eConfusion matrix of property importances.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/27c3d9655e45815c0bc1e43b.png"},{"id":95704378,"identity":"d651eff7-a022-42f8-b3f5-9becb04dc07f","added_by":"auto","created_at":"2025-11-12 06:23:07","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":30361,"visible":true,"origin":"","legend":"\u003cp\u003eDifferent regression models (a)MOE; (b)air-dry tangential shrinkage.\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/2b075bfc9e3a37271f0b9dbd.png"},{"id":108718032,"identity":"68a52f80-9ece-437d-85f1-7dcd9f9ae606","added_by":"auto","created_at":"2026-05-07 15:26:47","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1055672,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8023325/v1/0f62e8c9-4479-4223-82d4-2e8727e22f55.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Convenient Classification of Phyllostachys heterocycla cv. pubescens Properties Based on Growth Traits and Machine Learning Methods","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eGlobal forest resources have experienced significant depletion due to anthropogenic production and increased consumption. According to the \u0026ldquo;2021 China Forest and Grassland Ecological Comprehensive Monitoring and Evaluation Report (National Forestry and Grassland Administration, 2021)\u0026rdquo;, China's bamboo forest coverage reached 5.28\u0026nbsp;million hectares in 2021. Bamboo and bamboo-based products have become important raw materials for new alternative and sustainable building materials [\u003cspan additionalcitationids=\"CR2\" citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. China's bamboo processing industry has witnessed remarkable growth in recent years, driven by market demands and technological progress, leading to continuous product innovation and significant economic returns. Moso bamboo(\u003cem\u003ePhyllostachys heterocycla (Carr.) Mitford cv. pubescens\u003c/em\u003e) is a species of large-diameter bamboo in the \u003cem\u003ePoaceae\u003c/em\u003e family, belonging to the \u003cem\u003ePhyllostachys\u003c/em\u003e. It is the most widely distributed and commonly utilized large-diameter bamboo in China. Bamboo is recognized as one of the most promising forest resources for wood substitution due to its short production cycle, remarkable adaptability, high productivity, and excellent material properties [\u003cspan additionalcitationids=\"CR5\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The investigation of bamboo's material properties forms the fundamental basis for its rational utilization. As an anisotropic biomaterial, bamboo exhibits significant variability in its material properties, with lots of influencing factors that complicate prediction and performance modeling. Many studies have established correlations between bamboo's properties and growth traits such as age, DBH (Diameter at Breast Height), height, and wall thickness [\u003cspan additionalcitationids=\"CR8\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. However, most of the correlation analyses were based on a single indicator, for example, examining the relationship between bamboo properties and age, or studying property variations along the height. This type of approach failed to consider the combined effects of multiple growth traits on bamboo properties [\u003cspan additionalcitationids=\"CR10\" citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. In practical applications, bamboo material grading relying solely on individual growth traits (e.g., age or height) demonstrated limited accuracy and reliability [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. To improve classification accuracy, it is essential to first identify the most influential growth traits based on practical needs, followed by systematic incorporation of secondary traits for comprehensive assessment. This multivariate methodology significantly improves both the accuracy and credibility of bamboo quality evaluation.\u003c/p\u003e\u003cp\u003eThis study employed a machine learning method of decision tree algorithm for material classification, which can summarize rules from a series of feature and label data, and present the classification results guided by these rules using a tree diagram structure. The decision tree algorithm was widely used in scientific research, with a focus on identification, evaluation, and prediction in forestry [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. However, there are not many applications in the field of bamboo properties, especially in the research of material property classification [\u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. There is no consensus on whether similar methods can be applied to bamboo classification, material property evaluation, and prediction.\u003c/p\u003e\u003cp\u003eThis study comprehensively considered the correlation between four growth traits (age, DBH, height, and wall thickness) and material properties. Using the decision tree algorithm in the machine learning method, the bamboo was first classified into property grades. Secondly, the impact and trend of growth traits on material properties were analyzed, and the correlation between various properties was quantitatively analyzed; Finally, different regression methods were used to analyze the regression models between growth traits and material properties. This study attempted to classify and evaluate bamboo properties using four growth traits, effectively explored the degree of correlation of properties, diversified the application and prediction of property data, and provided a scientific basis for the rational and effective utilization of bamboo resources.\u003c/p\u003e"},{"header":"2. Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Moso bamboo\u003c/h2\u003e\u003cp\u003eThe test specimens were collected from a moso bamboo forest located in Ziyuan County, Guangxi, China (25\u0026deg;49\u0026acute;57\"N, 100\u0026deg;34\u0026acute;42\"E). The site exhibits a subtropical monsoon climate, with recorded mean annual values of 16.7\u0026deg;C air temperature, 1,736 mm precipitation, and 79% relative humidity. The bamboo forest slopes southeast at an angle of 20\u0026deg;, with an elevation of 600 m above sea level. Moso bamboo samples were categorized into three age groups: 2-year-old, 4-year-old, and 6-year-old. Each age group was further divided into four diameter classes: 6 cm, 8 cm, 10 cm, and 12 cm. From each of three plots, we sampled three culms representing each combination of age and diameter class. Each selected culm was felled at 8 m height and divided into four 2-meter-long segments, which were systematically labeled for identification.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Experimental methods\u003c/h2\u003e\u003cp\u003eStandard specimens were prepared and tested according to GB/T 15780\u0026thinsp;\u0026minus;\u0026thinsp;1995 (Testing Methods for Physical and Mechanical Properties of Bamboo). The investigation included four physical and mechanical properties: (1) air-dry density, (2) modulus of elasticity (MOE), (3) modulus of rupture (MOR), and (4) compressive strength (compression parallel to grain). Furthermore, three dry shrinkage properties were measured: (i) air-dry radial shrinkage, (ii) air-dry tangential shrinkage, and (iii) air-dry volume shrinkage.\u003c/p\u003e\u003cp\u003eDefect-free sections with internode lengths exceeding 200 mm were selected from each 2-meter bamboo culm segment for specimen preparation. As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, longitudinal strips were extracted along four cardinal orientations (east, south, west, and north) with widths of 15 mm and 30 mm. The 15 mm-wide strips were used to prepare test specimens for density, MOE, MOR, and dry shrinkage properties, while the 30 mm-wide strips were used to make compressive strength testing specimens. All bamboo strips destined for physical and mechanical characterization underwent rigorous conditioning steps: initial drying followed by controlled humidification to attain equilibrium moisture content (12\u0026thinsp;\u0026plusmn;\u0026thinsp;1%). Specimen fabrication commenced only after mass stabilization was confirmed. For shrinkage specimens, the bamboo strips were fully immersed in distilled water until complete dimensional stabilization was achieved before specimen preparation. Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e provided dimensional specifications and corresponding formulas for specimens used in various property tests.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSpecimen dimensions and formulas for different material properties.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"4\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProperties\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDimension\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c4\" namest=\"c3\"\u003e\u003cp\u003eFormulas\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry density\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e10mm \u0026times; 10mm \u0026times; tmm\u003c/p\u003e\u003cp\u003e(wall thickness)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\rho\\:}_{W}=\\frac{{m}_{W}}{{V}_{W}}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\rho\\:}_{12}={\\rho\\:}_{W}\\left[1-0.01\\left(1-K\\right)\\left(W-12\\right)\\right]\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:K=\\frac{{V}_{W}-{V}_{0}}{{V}_{0}W}\\times\\:100\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\rho\\:}_{w}\\)\u003c/span\u003e\u003c/span\u003e: Air-dry density with a moisture content of W%, g/cm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{m}_{w}\\)\u003c/span\u003e\u003c/span\u003e: Weight with a moisture content of W%, g\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{V}_{w}\\)\u003c/span\u003e\u003c/span\u003e: Volume with a moisture content of W%, cm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\rho\\:}_{12}\\)\u003c/span\u003e\u003c/span\u003e: Air-dry density with a moisture content of 12%, g/cm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003eW\u003c/em\u003e: Moisture content, %\u003c/p\u003e\u003cp\u003e\u003cem\u003eK\u003c/em\u003e: Volume shrinkage coefficient, %\u003c/p\u003e\u003cp\u003e\u003cem\u003eV\u003c/em\u003e\u003csub\u003e\u003cem\u003e0\u003c/em\u003e\u003c/sub\u003e: Volume with a moisture content of 0%, cm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMOE\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e160mm \u0026times; 10mm \u0026times; tmm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\rm\\:E}}_{W}=\\frac{P{L}^{3}}{4b{ℎ}^{3}f}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cem\u003eE\u003c/em\u003e\u003csub\u003e\u003cem\u003eW\u003c/em\u003e\u003c/sub\u003e: MOE with a moisture content of W%, MPa\u003c/p\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e: Difference between upper and lower limit loads, N\u003c/p\u003e\u003cp\u003e\u003cem\u003eL\u003c/em\u003e: Span between two supports, 120mm\u003c/p\u003e\u003cp\u003e\u003cem\u003eb\u003c/em\u003e: Wall thickness, mm\u003c/p\u003e\u003cp\u003e\u003cem\u003eh\u003c/em\u003e: Height, mm\u003c/p\u003e\u003cp\u003e\u003cem\u003ef\u003c/em\u003e: Deformation value between upper and lower limit loads, mm\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMOR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e160mm \u0026times; 10mm \u0026times; tmm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\sigma\\:}_{bW}=\\frac{3{P}_{max}L}{2b{ℎ}^{2}}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{b12}={\\sigma\\:}_{bW}\\left[1+0.025\\left(W-12\\right)\\right]\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{\\text{b}\\text{w}}\\)\u003c/span\u003e\u003c/span\u003e: MOR with a moisture content of W%, MPa\u003c/p\u003e\u003cp\u003e\u003cem\u003eP\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e: Failure load, N\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{b12}\\)\u003c/span\u003e\u003c/span\u003e: MOR with a moisture content of 12%, MPa\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCompressive strength\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e20mm \u0026times; 20mm \u0026times; tmm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\sigma\\:}_{W}=\\frac{{P}_{max}}{bt}\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{12}={\\sigma\\:}_{W}\\left[1+0.045\\left(W-12\\right)\\right]\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{\\text{w}}\\)\u003c/span\u003e\u003c/span\u003e: Compressive strength with a moisture content of W%, MPa\u003c/p\u003e\u003cp\u003e\u003cem\u003et\u003c/em\u003e: Width, mm\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\sigma\\:}}_{12}\\)\u003c/span\u003e\u003c/span\u003e: Compressive strength with a moisture content of 12%, MPa\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry radial /tangential shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e10mm \u0026times; 10mm \u0026times; tmm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{{\\beta\\:}}_{W}=\\frac{{L}_{max}-{L}_{W}}{{L}_{max}}\\times\\:100\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eβ\u003csub\u003ew\u003c/sub\u003e: Air-dry radial/tangential shrinkage, %\u003c/p\u003e\u003cp\u003e\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003emax\u003c/em\u003e\u003c/sub\u003e: Radial/tangential length with a moisture content higher than the fiber saturation point, mm\u003c/p\u003e\u003cp\u003e\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003eW\u003c/em\u003e\u003c/sub\u003e: Radial/tangential length with a moisture content of W%, mm\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry volume shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e10mm \u0026times; 10mm \u0026times; tmm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\beta\\:}_{{V}_{W}}=\\frac{{V}_{max}-{V}_{W}}{{V}_{max}}\\times\\:100\\)\u003c/span\u003e\u003c/span\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{\\beta\\:}_{{V}_{W}}\\)\u003c/span\u003e\u003c/span\u003e: Air-dry volume shrinkage, %\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{V}_{max}\\)\u003c/span\u003e\u003c/span\u003e: Volume with a moisture content higher than the fiber saturation point, mm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003cp\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\\:{V}_{w}\\)\u003c/span\u003e\u003c/span\u003e: Volume with a moisture content of W%, mm\u003csup\u003e3\u003c/sup\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3 Data analysis\u003c/h2\u003e\u003cp\u003eThe K-means clustering algorithm, an unsupervised machine learning approach, was employed to classify bamboo material properties into distinct performance grades based on experimental results. The decision tree algorithm was employed to analyze the relationship between graded material properties and corresponding growth traits, thereby identifying the most determinant growth traits for material property classification. The regression method used decision tree algorithm, LASSO, and SVR methods to simulate material properties using growth traits, and obtain the coefficients and corresponding intercepts of the simulation function.\u003c/p\u003e\u003c/div\u003e"},{"header":"3. Results and discussion","content":"\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Moso bamboo properties\u003c/h2\u003e\u003cp\u003eBamboo properties were categorized according to age, DBH, height, and wall thickness, with detailed grouping results presented in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The analysis revealed the following key findings: (1) With the exception of tangential shrinkage, all material properties exhibited consistent improvement with increasing bamboo age. While some 2-year-old bamboo specimens demonstrated superior shrinkage properties compared to 4-year-old counterparts, the trend of average values still increased with bamboo age. The tangential shrinkage was the lowest in 2-year-old bamboo. The tangential shrinkage was determined by averaging the shrinkage values from the outer(bamboo green) and inner(bamboo yellow) sides of the bamboo. The bamboo green part exhibited roughly three times greater tangential shrinkage compared to the bamboo inner. Data analysis revealed that the shrinkage proportion near the inner side of 2-year-old bamboo was smaller compared to bamboos of other ages, resulting in less overall shrinkage in 2-year-old bamboo than the others. (2) DBH and height exhibited consistent influence trends on material properties. Specifically, Specimens with DBH\u0026thinsp;\u0026gt;\u0026thinsp;10 cm demonstrated superior material property performance compared to those with DBH\u0026thinsp;\u0026lt;\u0026thinsp;10 cm. Similarly, height exceeding 4 m showed enhanced property performance relative to shorter culms (\u0026lt;\u0026thinsp;4 m). (3) Regarding physical and mechanical properties, specimens with a wall thickness\u0026thinsp;\u0026lt;\u0026thinsp;8 mm exhibited superior material performance compared to those\u0026thinsp;\u0026gt;\u0026thinsp;8 mm. In contrast, wall thickness showed no consistent correlation with shrinkage properties, with only minimal differences observed between mean values.\u003c/p\u003e\u003cp\u003eThe progressive enhancement of various properties with bamboo age can be primarily attributed to the lignification process. As bamboo matures, this process involves gradual enrichment, deposition, and thickening of cell walls and their contents, resulting in corresponding improvements in material properties over time. Most studies on the radial and vertical trends of bamboo properties explained their variations based on the density of vascular bundles, but the explanation for the experimental results in this article was not sufficient [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. For example, the DBH was inversely proportional to vascular bundle density, but the bamboo properties of larger diameters were better than those of smaller diameters. In the vertical direction, the physical and mechanical properties of the tip were better than those of the base due to the density of vascular bundles. Therefore, the shrinkage performance of the base should be better than that of the tip, because the density of vascular bundles in the base was low and the shrinkage rate was small after dehydration, but the result was the opposite. These findings demonstrated that material properties require multidimensional analysis, as material properties cannot be adequately assessed through singular dominant indicators alone. From an anatomical perspective, as the DBH increases, the density of vascular bundles decreases, the tissue proportion decreases, the fiber length-diameter ratio decreases, and there is no significant change in the fiber lumen-diameter ratio; As the height increases, the density of vascular bundles increases, the tissue proportion increases, the fiber length-diameter ratio shows no significant variation pattern, and the fiber lumen-diameter ratio increases; As the wall thickness increases, the vascular bundle density decreases, the tissue proportion decreases, the fiber length-diameter ratio shows no significant change, and the fiber lumen-diameter ratio decreases [\u003cspan additionalcitationids=\"CR20\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. The change in material properties was the result of the combined effect of different indicators mentioned above, and it also needed to be compounded by the influence of changes in chemical composition. These anatomical characteristics had varying degrees of influence on different material properties. For example, the difference in physical and mechanical properties produced by DBH was not significant and was lower than the influence of height and wall thickness. However, the impact of DBH on the properties of dry shrinkage materials was much higher than the other two factors.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eBamboo properties with different ages, DBH, heights, and wall thickness.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"22\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c11\" colnum=\"11\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c12\" colnum=\"12\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c13\" colnum=\"13\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c14\" colnum=\"14\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c15\" colnum=\"15\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c16\" colnum=\"16\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c17\" colnum=\"17\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c18\" colnum=\"18\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c19\" colnum=\"19\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c20\" colnum=\"20\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c21\" colnum=\"21\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c22\" colnum=\"22\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProperty\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e\u003cp\u003eAir dry density (g/cm\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c7\" namest=\"c5\"\u003e\u003cp\u003eMOE (GPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c10\" namest=\"c8\"\u003e\u003cp\u003eMOR (MPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c13\" namest=\"c11\"\u003e\u003cp\u003eCompressive strength (MPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c16\" namest=\"c14\"\u003e\u003cp\u003eAir dry radial shrinkage (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c19\" namest=\"c17\"\u003e\u003cp\u003eAir dry\u003c/p\u003e\u003cp\u003etangential shrinkage (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"3\" nameend=\"c22\" namest=\"c20\"\u003e\u003cp\u003eAir dry volume shrinkage (%)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e195\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e158\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e213\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e158\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e213\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e170\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e180\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e171\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e195\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e195\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e159\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e195\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDBH\u0026thinsp;\u0026lt;\u0026thinsp;10cm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.66\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.74\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.42\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e13.32\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e13.82\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e101.45\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;19.90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e129.88\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;23.27\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e141.08\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;17.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e44.34\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;8.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e52.83\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e65.21\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.83\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e6.32\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e3.90\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.80\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.47\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.68\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.50\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.37\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e9.24\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e7.46\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e6.19\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.24\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e176\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e229\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e243\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e211\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e239\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e243\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e211\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e239\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e227\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e204\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e212\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e176\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e229\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e176\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e229\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e176\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e184\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e229\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDBH\u0026thinsp;\u0026gt;\u0026thinsp;10cm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.65\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.66\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.75\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.63\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12.86\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e13.19\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.49\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e121.53\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;24.88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e126.37\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;18.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e136.64\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;16.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e55.11\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;10.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e56.20\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e67.97\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;8.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e3.26\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e3.68\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.53\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.36\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.76\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.51\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e6.15\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e7.16\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e5.92\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.07\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e228\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e334\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e294\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e321\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e370\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e294\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e321\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e370\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e280\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e296\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e287\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e228\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e334\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e228\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e334\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e228\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e256\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e334\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHeight\u0026thinsp;\u0026lt;\u0026thinsp;4m\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.58\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.74\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.34\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12.78\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e13.27\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e105.04\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;19.84\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e124.62\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;20.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e137.13\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;16.13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e46.26\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;8.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e52.93\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e65.14\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.48\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e5.33\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e4.02\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.68\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.43\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.72\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.52\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e8.28\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e7.58\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e6.12\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.18\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e107\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e107\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e117\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e88\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e99\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e87\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e90\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHeight\u0026thinsp;\u0026gt;\u0026thinsp;4m\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.69\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.70\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.77\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14.39\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e14.25\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.40\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e14.46\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e137.18\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;22.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e141.44\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;16.78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e145.99\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;18.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e60.62\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;8.17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e60.32\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.94\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e71.50\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;9.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e3.16\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e3.08\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.56\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.37\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.72\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.46\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e5.96\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e6.46\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e5.75\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e199\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e232\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e210\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e212\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e216\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e210\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e212\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e216\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e233\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e199\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e200\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e199\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e232\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e199\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e232\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e199\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e190\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e232\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWall thick\u0026thinsp;\u0026lt;\u0026thinsp;8mm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.62\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.69\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.76\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.64\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e14.05\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.41\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e14.14\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e115.75\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;29.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e138.73\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;19.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e143.75\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;18.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e51.46\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;12.36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e57.93\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e67.56\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;9.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e4.93\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e3.56\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.72\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.47\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.68\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.47\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e7.81\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.74\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e7.01\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e6.03\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.22\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSample size\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e153\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e191\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e191\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e236\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e191\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e191\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e236\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e164\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e185\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e183\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e153\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e153\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e128\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e153\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e192\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWall thick\u0026thinsp;\u0026gt;\u0026thinsp;8mm\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e0.60\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.07\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.63\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.61\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.46\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12.01\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.03\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12.89\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.09\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e111.27\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;18.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e116.17\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;14.63\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e134.14\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;13.21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c11\"\u003e\u003cp\u003e49.12\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.95\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c12\"\u003e\u003cp\u003e51.06\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;6.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c13\"\u003e\u003cp\u003e65.85\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;7.15\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c14\"\u003e\u003cp\u003e4.27\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c15\"\u003e\u003cp\u003e4.05\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c16\"\u003e\u003cp\u003e2.58\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c17\"\u003e\u003cp\u003e2.31\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c18\"\u003e\u003cp\u003e2.77\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c19\"\u003e\u003cp\u003e2.55\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;0.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c20\"\u003e\u003cp\u003e7.22\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c21\"\u003e\u003cp\u003e7.64\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;2.36\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c22\"\u003e\u003cp\u003e6.06\u003c/p\u003e\u003cp\u003e\u0026plusmn;\u0026thinsp;1.08\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Classification\u003c/h2\u003e\u003cdiv id=\"Sec9\" class=\"Section3\"\u003e\u003ch2\u003e3.2.1 K-Means classification of properties\u003c/h2\u003e\u003cp\u003eThe K-Means algorithm was implemented to classify material properties and establish corresponding quality grades [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. As an unsupervised learning approach, the clustering performance is evaluated using two principal criteria: (1) minimization of intra-cluster variation and (2) maximization of inter-cluster separation. The silhouette coefficient, ranging from \u0026minus;\u0026thinsp;1 to 1, serves as the primary evaluation metric. Values approaching 1 indicate an optimal clustering configuration, where samples demonstrate strong intra-cluster homogeneity and clear inter-cluster distinction. As shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e, the clustering analysis of material properties yielded two distinct quality categories: \"excellent\" and \"fine,\" determined through silhouette coefficient optimization and practical implementation considerations. Cluster center averages exhibited strong agreement with average experimental value for most properties, with the exception of radial and volume shrinkage values that displayed noticeable deviations. Taking density as an example, specimens clustered around center 0.76 were categorized as \u0026ldquo;excellent\u0026rdquo;, specimens near center 0.60 were classified as \u0026ldquo;fine\u0026rdquo; (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eComparison of Silhouette coefficient and cluster centers for 2 and 3 clusters.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eProperties\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eAir dry density\u003c/p\u003e\u003cp\u003e(g/cm\u003csup\u003e3\u003c/sup\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eMOE\u003c/p\u003e\u003cp\u003e(GPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eMOR\u003c/p\u003e\u003cp\u003e(MPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eCompressive strength (MPa)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAir dry radial shrinkage\u003c/p\u003e\u003cp\u003e(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAir dry tangential shrinkage\u003c/p\u003e\u003cp\u003e(%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAir dry volume shrinkage\u003c/p\u003e\u003cp\u003e(%)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e\u003cp\u003e2\u003c/p\u003e\u003cp\u003e+\u003c/p\u003e\u003cp\u003e4\u003c/p\u003e\u003cp\u003e+\u003c/p\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e2 clusters\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSilhouette coef.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.66\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCluster centers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.60/0.76\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e11.47/14.33\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e143.92/105.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e48.63/67.45\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e7.00/2.81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2.21/3.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e10.25/6.02\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e3 clusters\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSilhouette coef.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.57\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCluster centers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.56/0.79/0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.80/15.06/10.43\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e130.46/99.62/156.79\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e55.24/69.77/41.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4.79/2.56/8.29\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2.07/3.63/2.72\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e7.78/5.55/11.39\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eExperimental average\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.68\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.93\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e127.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e57.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e3.61\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6.89\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"4\" rowspan=\"5\"\u003e\u003cp\u003e2\u003c/p\u003e\u003cp\u003e+\u003c/p\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e2 clusters\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSilhouette coef.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.53\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.67\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.62\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCluster centers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.72/0.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14.27/11.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e104.98/144.47\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e45.10/60.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e3.09/7.26\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e3.06/2.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e6.21/10.53\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003e3 clusters\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSilhouette coef.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.54\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.55\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.56\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCluster centers\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.74/0.54/0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.62/10.32/15.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e124.46/156.99/96.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e52.79/65.09/40.56\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e2.77/5.25/8.58\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2.57/3.47/1.82\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e5.61/8.07/11.59\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colspan=\"2\" nameend=\"c3\" namest=\"c2\"\u003e\u003cp\u003eExperimental average\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.64\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e12.62\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e120.85\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e52.52\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4.22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e2.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e7.43\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e presented the material classification scheme. The data included four growth traits of the specimen (input variables), the first one was bamboo age, with three characteristic values: 2-year-old, 4-year-old, and 6-year-old; The second trait was DBH, with two characteristic values: above 10 cm and below; The third trait was height, with two characteristic values: above 4 m and below; The fourth one was wall thickness, which had two characteristic values: above 8 mm and below. The last column consisted of two grades of material quality (output variables): excellent and fine.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eRepresentative examples of material property categorization.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eID\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDBH\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHeight\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eWall thick\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eProperty category\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;10 cm (10-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;4 m (4-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;8 mm (8-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eFine\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;10 cm (10+)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;4 m (4-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;8 mm (8+)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eFine\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;10 cm (10-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;4 m (4+)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;8 mm (8+)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eExcellent\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u0026hellip;\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;10 cm (10-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;4 m (4+)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;8 mm (8-)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eExcellent\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section3\"\u003e\u003ch2\u003e3.2.2 Decision tree classification\u003c/h2\u003e\u003cp\u003eDecision trees employ a hierarchical branching structure to analyze feature variables, identify optimal predictive features, and partition datasets accordingly to achieve data classification [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. The methodology involves two fundamental considerations: (1) optimal node selection and (2) pruning techniques. By identifying the feature corresponding to the optimal nodes, the priority order of multiple factors that affect material properties can be determined.\u003c/p\u003e\u003cdiv id=\"Sec11\" class=\"Section4\"\u003e\u003ch2\u003e3.2.2.1 Ternary decision tree\u003c/h2\u003e\u003cp\u003eSince age was categorized into three characteristics of 2, 4, and 6-year-olds, ternary decision tree classification was calculated using the C4.5 algorithm [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e showed the classification results of the ternary decision tree. In the figures, the circles represented the root node or middle node, which served as the classification basis; the box represented the leaf node, which indicated the excellent or fine grade label, and the numerical value represented the accuracy of classification. Each path from the root to a leaf node corresponds to a classification rule, which can be expressed as an IF-THEN statement.\u003c/p\u003e\u003cp\u003eTaking air-dry density as an example, bamboo age served as the root node of the decision tree, indicating that among the four input variables-age, DBH, height, and wall thickness, age exhibited the highest information gain ratio. Consequently, the decision tree was partitioned into three subsets based on age. Within these subsets, 82% of the 6-year-old specimens were classified as \"excellent\" and require no further subdivision. For the 2-year-old specimens, height served as the second node, forming the classification criterion at this level. Among these, 88% of specimens with a height below 4 m were classified as \"fine.\" For those exceeding 4 m in height, wall thickness was used as the subsequent splitting attribute, 66% of specimens with a wall thickness below 8 mm were categorized as \"excellent,\" while 83% of those exceeding 8 mm were assigned to the \"fine\" category. For 4-year-old specimens, wall thickness served as the second node. Among these, 79% of specimens with a wall thickness exceeding 8 mm were classified as \"fine.\" For specimens with a wall thickness below 8 mm, height was used as the subsequent splitting criterion.\u003c/p\u003e\u003cp\u003eAmong these bamboo properties, only the root node of MOE was the height. Specimens exceeding 4 m in height 87% exhibited \"excellent\" MOR performance. For specimens below 4 m, age served as the second node: 85% of 2-year-old specimens were categorized as \"fine,\" while 4 and 6-year-old specimens underwent further classification based on wall thickness and DBH. The decision tree structures for air-dry density and compressive strength exhibited identical root and intermediate nodes. Similarly, air-dry radial shrinkage and volume shrinkage shared the same node configuration in their respective decision trees.\u003c/p\u003e\u003cp\u003eThe ternary decision tree was optimized for training data fitting by maximizing the information gain ratio, without considering potential issues of model complexity or overfitting. Analysis of the classification results revealed that 6-year-old bamboo specimens achieved the highest classification accuracy, with nearly all being categorized as \"excellent.\" The predominance of 6-year-old bamboo in the 'excellent' category disproportionately influenced the model, artificially elevated classification accuracy, and systematically favored age-based splits in root node selection. 2-year-old bamboo specimens showed relatively good classification performance, predominantly falling into the \"fine\" category. The classification of 4-year-old bamboo required more intermediate nodes in the decision tree, increased model complexity, and susceptibility to overfitting, which consequently resulted in relatively lower classification accuracy. The results indicated that 4-year-old bamboo exhibited comparable proportions of excellent and fine categories, suggesting that classification based solely on growth data has limited effectiveness for quality grade. Some studies have shown that, incorporating density alongside growth traits could significantly improve classification accuracy for material properties [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. The classification accuracy for the dry shrinkage properties was consistently lower than that achieved for physical and mechanical properties, reflecting the higher CV (coefficient of variation) in shrinkage measurements. Some of the accuracy rate for tangential shrinkage prediction was merely 51%, statistically indistinguishable from random guessing. In the ternary decision tree analysis, age and height emerged as the primary decision nodes for physical and mechanical properties, while age and DBH served as the key classification nodes for dry shrinkage properties.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section4\"\u003e\u003ch2\u003e3.2.2.2 Binary decision tree\u003c/h2\u003e\u003cp\u003eBamboo age classification was established as follows: 2 and 4-year-old specimens were categorized as mature bamboo, while those 6-year-old specimens were classified as old bamboo [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. The binary decision tree excluded the old bamboo and only analyzed the mature bamboo.\u003c/p\u003e\u003cp\u003eAfter removing the 6-year-old part, two remaining characteristics were used for analysis using the binary decision tree in Scikit-learn. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e presented the classification results of various material properties using binary decision trees. Unlike the ternary decision tree model, height demonstrated greater classification importance than age for mature bamboo categorization. Each material property may have multiple decision trees, but the ones displayed in the figures were the most frequently occurring models with higher classification accuracy. Radial and volume shrinkage were listed as two decision trees with high frequency of occurrence, with a ratio of 8:5 and 7:5.\u003c/p\u003e\u003cp\u003eIn the binary decision tree model, bamboo age no longer served as the root node, allowing other traits to demonstrate their predictive importance. Among physical-mechanical properties, height emerged as the most influential factor, particularly for mechanical properties. Specimens exceeding 4 meters in height were consistently classified as 'excellent' with relatively high accuracy. While DBH showed no significant contribution to the classification of physical-mechanical properties. The incorporation of both height and wall thickness parameters led to a measurable enhancement in prediction accuracy. In the shrinkage property analysis, DBH demonstrated significant predictive importance in the binary decision tree model, with every tree participating in the classification process and even serving as root nodes in some cases. However, the overall accuracy improvement of the binary tree model compared to the ternary tree model was relatively marginal, which can be primarily attributed to the inherent characteristics of the dataset itself.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section4\"\u003e\u003ch2\u003e3.2.2.3 Single-feature binary decision tree root nodes and accuracy\u003c/h2\u003e\u003cp\u003eTo observe the root nodes under different conditions, the decision root nodes and accuracy of various bamboo ages, different DBH, heights, and wall thicknesses were analyzed. The root nodes obtained from the analysis were not singular, and Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e showed the root nodes with the highest frequency of occurrence. The DBH, height, and wall thickness were the data analysis results of mature bamboo. If 6-year-old bamboo was added, almost all root nodes were of bamboo age.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eDecision tree root nodes and accuracy for each characteristic.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProperty\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2-year-old\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e4-year-old\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e6-year-old\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;10 cm\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;10 cm\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;4 m\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;4 m\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003e\u0026lt;\u0026thinsp;8 mm\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003e\u0026gt;\u0026thinsp;8 mm\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry density\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHeight/73%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eThick/65%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHeight/84%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/68%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eThick/69%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAge/64%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eThick/79%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eDBH/77%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDBH/57%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMOE\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHeight/84%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHeight/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHeight/79%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/77%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eHeight/87%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAge/80%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAge/91%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAge/83%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eHeight/80%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMOR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHeight/77%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eThick/75%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eHeight/87%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eThick/74%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eThick/75%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAge/72%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAge/77%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eHeight/75%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCompressive strength\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHeight/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHeight/62%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eThick/85%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/72%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eThick/68%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAge/64%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eThick/87%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eHeight/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eDBH/63%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry radial shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDBH/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHeight/83%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDBH/98%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/74%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eHeight/88%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eDBH/74%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAge/96%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eHeight/84%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAge/74%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry tangential shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDBH/75%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eDBH/52%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eThick/64%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/64%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eAge/69%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAge/63%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eAge/66%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eAge/62%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAge/65%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAir-dry volume shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDBH/76%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eHeight/78%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDBH/97%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAge/67%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003eHeight/86%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003eAge/70%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003eThick/96%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003eHeight/82%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003eAge/71%\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eThe results of physical and mechanical properties showed that the root nodes of different bamboo ages were mostly height without DBH. Furthermore, bamboo age frequently served as the root node in classifications based on DBH, height, and wall thickness. The analysis of dry shrinkage properties revealed that age exerted the most significant influence. For the same age, DBH was the dominant factor, whereas wall thickness contributed minimally to shrinkage classification.\u003c/p\u003e\u003cp\u003eAnalysis across all bamboo ages (2-, 4-, and 6-year-old), mature bamboo (2- and 4-year-old), and individual indicators demonstrated consistent root nodes among the three analytical approaches. Specifically, physical and mechanical properties were primarily determined by age, and height; dry shrinkage properties were predominantly influenced by age and DBH. These findings indicated that while decision trees are subject to data structure constraints and inherent decision limitations, their root nodes maintain significant reference value. In accordance with the principles of optimizing the loss function while minimizing decision tree model complexity, field applications should prioritize root nodes as classification indicators.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Material properties\u0026rsquo; correlation\u003c/h2\u003e\u003cp\u003eThe decision tree can quantify the relative importance of independent variables on the dependent variable using feature importances, enabling a quantitative analysis of their interaction effects. Figure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e presented a percentage correlation matrix among various indicators derived from decision tree analysis, representing the average importance of each indicator (only for mature bamboo). The circled areas in the figure represented regions of high correlation, demonstrating significant interaction effects among growth traits, physical-mechanical properties, and dry shrinkage properties. The percentage of correlation between each indicator can be sorted, making it a relatively reliable method to predict or judge the quality of other material indicators using known indicators. Taking density as an example, the horizontal summation of values equals 100%. The indicator most strongly correlated with density was MOE, followed by compressive strength and MOR (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e\u003cp\u003eThe growth traits (DBH, height, and wall thickness) exhibited moderate positive correlations, resulting in relatively high correlation percentages between them. Notably, both height and wall thickness had the strongest correlation with MOE, underscoring the significance of these traits, particularly height, as key determinants of MOE. The physical-mechanical property analysis revealed significant interactions among the four properties, with MOE being additionally influenced by height. The shrinkage property analysis revealed the strongest mutual influence between radial and volume shrinkage. In contrast, radial and tangential shrinkage remained largely independent with limited interaction. Matrix longitudinal analysis revealed that each indicator contributed most significantly to MOE property, followed by compressive strength and density, with age contributing the least.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003e3.4 Regression\u003c/h2\u003e\u003cp\u003eMultiple regression models were undertaken to predict material properties by using age, DBH, height, and wall thickness. The purpose of undertaking regression analysis is to establish whether some growth traits can be used to infer properties that are normally measured destructively [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Multivariate linear regression models were considered using the Machine Learning method, such as Decision Tree, LASSO [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e], and SVR [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e].\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"No\" id=\"Taba\" border=\"1\"\u003e\u003ccolgroup cols=\"2\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eŷ = ω\u003csub\u003e0 +\u003c/sub\u003e ω\u003csub\u003e1\u003c/sub\u003ex\u003csub\u003e1 +\u003c/sub\u003e ω\u003csub\u003e2\u003c/sub\u003ex\u003csub\u003e2 + \u0026hellip; +\u003c/sub\u003e ω\u003csub\u003en\u003c/sub\u003ex\u003csub\u003en\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e(1)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ewhere ŷ means material property, x means traits, like age, DBH, height, and wall thickness, and the size of x depends on the number of traits considered. ω\u003csub\u003e0\u003c/sub\u003e is the intercept, ω\u003csub\u003en\u003c/sub\u003e is the regression coefficient of each trait.\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e presented the detailed regression outputs, including: (i) feature importances from decision tree analysis, (ii) regression coefficients and intercepts for both LASSO and SVR models, along with (iii) model performance metrics (MSE, R\u0026sup2;, and Score). Model evaluation revealed the highest accuracy for MOE regression and the lowest for tangential air-dried shrinkage. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e compared regression model performances for these two properties. Regression modeling using only four growth traits demonstrated limited accuracy in predicting material properties. Although model optimization slightly improved performance metrics, the enhancements remained marginal, as the predictive capacity was fundamentally constrained by the inherent limitations of the input data.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eFeature importances for the decision tree and the regression coefficient for Lasso and SVR.\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"10\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c10\" colnum=\"10\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eProperty\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eTraits\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eAge\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eDBH\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eHeight\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eThick\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eIntercept\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c8\"\u003e\u003cp\u003eMSE\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c9\"\u003e\u003cp\u003eR\u003csup\u003e2\u003c/sup\u003e\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c10\"\u003e\u003cp\u003eScore\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAir dry density\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.192\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.325\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.460\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.004\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.518\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.518\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.029\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.006\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.012\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.550\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.330\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.344\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.036\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.008\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e0.504\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.005\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.342\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eMOE\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.179\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.347\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.403\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.071\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.343\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.630\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.630\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.502\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-0.162\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.620\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.113\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12.196\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.908\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.452\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.551\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.441\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.065\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.370\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.369\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12.684\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e1.703\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.533\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eMOR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.220\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.359\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.306\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.115\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e269.887\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.573\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.573\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7.575\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-2.173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e7.696\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.762\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e95.365\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e392.054\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.307\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.401\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7.861\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.019\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e4.503\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-2.046\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e90.113\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e349.629\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.395\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eCompressive strength\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.141\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.238\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.538\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.083\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e50.318\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.482\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.482\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.644\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.323\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e1.690\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-1.497\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e38.893\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e57.658\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.372\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.379\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.786\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.034\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.356\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-2.387\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e41.365\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e57.176\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.361\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAir dry radial shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.336\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.447\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.111\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.106\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e2.963\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.419\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.419\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.421\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.156\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.727\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.567\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e10.394\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e3.675\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.216\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.296\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.317\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.141\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.639\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.575\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e9.663\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e3.532\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.272\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAir dry tangential shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.342\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.369\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.129\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.160\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.333\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.186\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.186\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.175\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-0.002\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.043\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e2.469\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.358\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.045\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.017\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.168\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-0.015\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.022\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.045\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e2.586\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e0.307\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.025\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\" morerows=\"2\" rowspan=\"3\"\u003e\u003cp\u003eAir dry volume shrinkage\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eDecision\u003c/p\u003e\u003cp\u003eTree\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e0.031\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.472\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e0.304\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.193\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4.135\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.289\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.289\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eLasso\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.101\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.083\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.695\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.498\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12.770\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4.486\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e0.163\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.239\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSVR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-0.076\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e0.077\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e-0.672\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e-0.570\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c7\"\u003e\u003cp\u003e12.889\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c8\"\u003e\u003cp\u003e4.247\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c9\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c10\"\u003e\u003cp\u003e0.237\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Conclusions","content":"\u003cp\u003eThe material properties of Moso bamboo were investigated using samples collected from Ziyuan County, Guangxi, China. Seven material properties were experimentally determined: air-dry density, MOE, MOR, compressive strength, and air-dry shrinkage properties (radial, tangential, and volumetric). These datasets were analyzed using machine learning approaches, yielding three principal outcomes: (a) identification of critical classification indicators through decision tree root node analysis, (b) quantitative evaluation of inter-parameter correlations, and (c) development of growth traits-based regression models for property prediction. The study's major findings lead to the following conclusions:\u003c/p\u003e\u003cp\u003e(1) With the exception of tangential shrinkage, all material properties exhibited consistent improvement with increasing bamboo age. Specimens with DBH exceeding 10 cm exhibited superior material properties compared to those under 10 cm; similarly, bamboo height taller than 4 m showed enhanced properties relative to shorter ones. Specimens with a wall thickness of \u0026lt;\u0026thinsp;8 mm demonstrated superior performance of physical and mechanical properties relative to those of \u0026gt;\u0026thinsp;8 mm. Excluded the factor of bamboo age, height had a significant impact on the physical and mechanical properties of bamboo, while DBH had a significant impact on the dry shrinkage properties.\u003c/p\u003e\u003cp\u003e(2) There was a certain degree of uncertainty in using four growth traits to classify wood properties in decision trees, which was affected by data structure and was a limitation of statistical analysis. The accuracy of the physical mechanical properties\u0026rsquo; decision tree in this study was around 75%, with the two main traits being age and height. When it comes to mature bamboo or single bamboo age, height was the most important trait for classification. The accuracy of the decision tree for the dry shrinkage properties was around 67%, and the two main traits were age and DBH. When it came to mature bamboo or single bamboo age, DBH was the most important classification trait. The influence of wall thickness difference was far less than that of age and height, but it could serve as a reference for a secondary selection trait in terms of physical and mechanical properties. Therefore, when classifying materials, different classification traits should be selected according to the actual situation to effectively improve classification accuracy.\u003c/p\u003e\u003cp\u003e(3) Correlation analysis showed each indicator had a corresponding maximum proportion indicator, which can be used to determine the trend of unknown indicators through sorting and known indicator information. Matrix longitudinal analysis showed that each indicator contributed the most to MOE, while age contributed the least to other material properties.\u003c/p\u003e\u003cp\u003e(4) The regression results showed that simulating material properties based on four growth traits had low accuracy. Especially, the accuracy at both ends of the value range was very low. The regression coefficients of the model indirectly reflect the influence of different growth traits on material properties.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cem\u003eThe authors have no relevant financial or non-financial interests to disclose.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eThe authors have no conflicts of interest to declare that are relevant to the content of this article.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAll authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eThe authors have no financial or proprietary interests in any material discussed in this article.\u003c/em\u003e\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eHuilan XU and La HU wrote the main manuscript text. The experiments were conducted by Shengsen TANG and Peng LI. The manuscript was polished by Haibo LONG, and the bamboo planting experiment was designed by Zhangqi YANGand Guiping YANG. All authors have reviewed and approved the final manuscript.\u003c/p\u003e\u003ch2\u003eAcknowledgements\u003c/h2\u003e\u003cp\u003eThis research was financially supported by the Bagui Scholars Program of Guangxi (2019A26), and Science and Technology Major Project of Guangxi (Guike AA 24263024).\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eA. Bala, S. Gupta. Engineered bamboo and bamboo-reinforced concrete elements as sustainable building materials: A review. Construction and Building Materials. 2023, 394, 132116.\u003c/li\u003e\n\u003cli\u003eZ. Lou, Z. Zheng, N. Yan, X. Jiang, X. Zhang, S. Chen, R. Xu, C. Liu, L. Xu. Modification and Application of Bamboo-Based Materials: A Review-Part II: Application of Bamboo-Based Materials. Forests. 2023, 14, 2266.\u003c/li\u003e\n\u003cli\u003eH. Du, B. Chen, Z. Chen, Y. Wei, X. Hu. Study on flexural performance of glued laminated bamboo and timber-concrete composite beams. Construction and Building Materials. 2025, 492, 142986.\u003c/li\u003e\n\u003cli\u003eP.G.Dixon, L.J.Gibson. The Structure and mechanics of Moso bamboo material. Journal of the Royal Society Interface. 2014, 11, 20140321.\u003c/li\u003e\n\u003cli\u003eH. Sun, H. Li, A. Dauletbet, R. Lorenzo, I. Corbi, O. Corbi, M. Ashraf. Review of materials and structure inspired by bamboo. Construction and Building Materials. 2022, 325, 126656.\u003c/li\u003e\n\u003cli\u003eC. Hong, H. Li, Z. Xiong, R. Lorenzo, I. Corbi, O. Corbi, D. Wei, C. Yuan, D. Yang, H. Zhang. Review of connections for engineered bamboo structures. Journal of Building Engineering. 2020, 30, 101324.\u003c/li\u003e\n\u003cli\u003eS. MEI, D. Zhao, X. Meng, H. Qi, Y. Gao. Experimental study on tensile properties of the arc outer green skin of bamboo. Journal of Forestry Engineering. 2022, 7(3): 60-66.\u003c/li\u003e\n\u003cli\u003eS.P. Sylvayanti, N. Nugroho, E.T. Bahtiar. Bamboo Scrimber\u0026rsquo;s Physical and Mechanical Properties in Comparison to Four Structural Timber Species. Forests. 2023, 14(1): 146.\u003c/li\u003e\n\u003cli\u003eNurmadina, N. Nugroho, E.T. Bahtiar. Structural grading of Gigantochloa apus bamboo based on its flexural properties. Construction and Building Materials. 2017, 157: 1173-1189.\u003c/li\u003e\n\u003cli\u003eX. Wang, Y. Zhong, X. Luo, H. Ren. Compressive Failure Mechanism of Structural Bamboo Scrimber. Polymers. 2021, 13(23): 4223.\u003c/li\u003e\n\u003cli\u003eM.F.V. Adier, M.E.P. Sevilla, D.N.R. Valerio, J.M.C. Ongpeng. Bamboo as Sustainable Building Materials: A Systematic Review of Properties, Treatment Methods, and Standards. Buildings. 2023, 13, 2449.\u003c/li\u003e\n\u003cli\u003eS. Qin, Y. ZONG, A. HUANG, X. Zhang, H. Liu. Research Progress and Prospects of Bamboo Grading. China Forest Products Industry. 2022, 59(03): 49-54.\u003c/li\u003e\n\u003cli\u003eY. Feng, S. Mekhilef, D. Hui, C.L.Chow, D. Lau. Machine learning-assisted wood materials: Applications and future prospects. Extreme Mechanics Letters. 2024, 71: 102209.\u003c/li\u003e\n\u003cli\u003eS.Dubey, D. Gupta, M. Mallik. Foretelling the compressive strength of bamboo using machine learning techniques. Engineering Computations. 2024, 41(8-9): 2251-2288.\u003c/li\u003e\n\u003cli\u003eJ.F. Correal, A.F. Calvo, D.J.A. Trhjillo, J.S. Echeverry. Inference of mechanical properties and structural grades of bamboo by machine learning methods. Construction and Building Materials. 2022, 354, 129116.\u003c/li\u003e\n\u003cli\u003eL. Tong, B. Li, Y. Geng, L. Chen, Y. Li, R. Cao. Spectrometric Classification of Bamboo Shoot Species by Comparison of Different Machine Learning Methods. Food Analytical Methods. 2021, 14: 300-306.\u003c/li\u003e\n\u003cli\u003eJ. Li, H. Xu, Y, Zhang, T. Zhong, K. Semple, V. Nasir, H. Wang, C. Dai. Radial distribution of vascular bundle morphology in Chinese bamboos: machine learning methodology for rapid sampling and classification. Holzforschung. 2023, 77(6): 468-483.\u003c/li\u003e\n\u003cli\u003eL. Mao, X. Kong, P. Liang, J. Fu, J. Xu. Research Progress in Factors Influencing Physical and Mechanical properties of Bamboo. World Bamboo and Rattan. 2024, 22(2): 91-97.\u003c/li\u003e\n\u003cli\u003eW. Fang, Y. Gui, L. Ma, A. Jin, X. Xin, X. Yu, L. Ma, J. Q. Chinese Economic Bamboo. Beijing: Science Press. 2015.\u003c/li\u003e\n\u003cli\u003eC. Chang, F. Chang. Comprehensive review of the elastic constants of bamboo. Eur. J. Wood Prod. 2024, 82: 1793-1754. \u003c/li\u003e\n\u003cli\u003eF. Rusch, A.D. Wastowski, T.S. de Lira, \u003cem\u003eet al\u003c/em\u003e. Description of the component properties of species of bamboo: a review. Biomass Conv. Bioref. 2023, 13:2478-2495. \u003c/li\u003e\n\u003cli\u003eA. P\u0026eacute;rez-Su\u0026aacute;rez, J.F. Mart\u0026iacute;nez-Trinidad, J.A. Carrasco-Ochoa. A review of conceptual clustering algorithms. Artificial Intelligence Review. 2019, 52, 1267-1296.\u003c/li\u003e\n\u003cli\u003eR.A. Olshen，J.R. Quinlan. Induction of decision trees. Machine Learning. 1986, 1(1): 81-106.\u003c/li\u003e\n\u003cli\u003eR.A. Olshen, J.R. Quinlan. C4.5: Programs for machine learning. San Mateo, CA: Morgan Kaufmann Publishers. 1992. \u003c/li\u003e\n\u003cli\u003eLi Hang. Statistical Learning Method. Beijing: Tsinghua University Press. 2019. \u003c/li\u003e\n\u003cli\u003eS. Chen, R. Shiina, K. Nakia, T. Awano, A. Yoshinaga, J. Sugiyama. Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction. Journal of Wood Science. 2023, 69: 22.\u003c/li\u003e\n\u003cli\u003eS. Chen, T. Awano, A, Yoshinaga, J, Sugiyama. Flexural behavior of wood in the transverse direction investigated using novel computer vision and machine learning approach. Holzforschung. 2022, 79(10): 875-885.\u003c/li\u003e\n\u003cli\u003eNational Forestry and Grassland Administration. Forestry Industry Standard of Peoples\u0026rsquo;s Republic of China, LY/T 2908-2017, Regulations for age-class and age-group division of main tree-species. 2017. \u003c/li\u003e\n\u003cli\u003eE.T. Bahtiar, A.P. Imanullah, D. Hermawan, N. Nugroho. Structural grading of three sympodial bamboo culms (Hitam, Andong, and Tali) subjected to axial compressive Load. Engineering Structures. 2019, 181, 233-245.\u003c/li\u003e\n\u003cli\u003eE.T. Bahtiar, D. Trujillo, N. Nugroho. Compression resistance of short members as the basis for structural grading of Guadua angustifolia. Construction and Building Materials. 2020, 249, 118759.\u003c/li\u003e\n\u003cli\u003eR.Tibshirani. Regression shrinkage and selection via the lasso. The Journal of the Royal Statistical Society: Series B (methodological). 1996, 58(1): 267-288.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Bamboo, material properties, growth traits, machine learning method, classification","lastPublishedDoi":"10.21203/rs.3.rs-8023325/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8023325/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBamboo is widely regarded as an eco-friendly construction material due to its rapid growth cycle, strong adaptability, high productivity, and excellent mechanical properties, positioning it as one of the most promising forest-based alternatives to wood. Implementing a property-based classification system that correlat\u003cem\u003ees growth traits with material properties is fundamentally important for a\u003c/em\u003edvancing the rational utilization of bamboo resources. \u003cem\u003eThis study employed K-Means, decision tree algorithms, and regression modeling of LASSO and SVR in machine learning to categorize bamboo properties using four key growth traits: age, diameter of breast height, height, and wall thickness. \u003c/em\u003eThe results demonstrated that growth traits serving as decision tree root nodes and intermediate nodes significantly contribute to bamboo property classification, can reflect the integrated influence of growth traits on material properties, and enable effective and convenient property classification. The material property regression model exhibited rather low fitness, indicating that growth traits alone were insufficient for developing high-accuracy predictive equations.\u003c/p\u003e","manuscriptTitle":"Convenient Classification of Phyllostachys heterocycla cv. pubescens Properties Based on Growth Traits and Machine Learning Methods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-12 06:23:02","doi":"10.21203/rs.3.rs-8023325/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"43c543e1-c5a1-4716-9652-681f5ea7db75","owner":[],"postedDate":"November 12th, 2025","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-07T15:08:10+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T15:25:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-12 06:23:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8023325","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8023325","identity":"rs-8023325","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}