Sustainable Engineering of Fiber-Reinforced Coal Gangue Linking Geomechanics and Microstructure through Support Vector Machines

Sustainable Engineering of Fiber-Reinforced Coal Gangue Linking Geomechanics and Microstructure through Support Vector Machines | 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 Article Sustainable Engineering of Fiber-Reinforced Coal Gangue Linking Geomechanics and Microstructure through Support Vector Machines Mazhar Syed, Mohammed Ashfaq, Babak Jamhiri, Fazal E. Jalal, Umair Ali This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7526534/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 14 You are reading this latest preprint version Abstract The periodic variations (heave/shrink) in soft soil can lead to extensive damage to lightweight structures, resulting in an annual loss of several billion dollars. Although well-known traditional stabilizers can effectively regulate soil volumetric stability and compressibility, their production can have a massive environmental impact. This paper investigates the geomechanical efficiency of soft soil reinforced with chemically treated banana fiber (CTBF) and EnviroSafe alkaline-activated materials (AAM), which are composed of alkaline solutions and industrial waste materials. The proportions of coal gangue ash (CGA) replacement with silica fume (SF : 0–20%) were varied in the alkaline solution by maintaining a 0.4 water-to-solid ratio. A series of consolidation compressive shear, and penetration resistance tests were performed to determine the geomechanical properties, including resilient modulus ( M R ), shear strength ratio, Stereoscopic, Fourier-transform infrared (FTIR) spectroscopy, and Thermogravimetry analysis (TGA) tests at varying CTBF-SF mixture dosages. The study proposed an optimal dosage of CGA-SF in AAM-stabilized soft soil. It demonstrated a substantial improvement in California Bearing Ratio (CBR) penetration and Unconfined Compressive Strength (UCS) tests. The results of silicafume (> 10%) in CGA-based AAM stabilizer soil attained the lowest equilibrium void ratio over the unreinforced soil. Furthermore, a support vector machine (SVM) algorithm model was proposed to predict the geomechanical strength of fiber-reinforced alkaline soil, and the results showed an excellent predictor of geomechanical strength performance. Physical sciences/Engineering Earth and environmental sciences/Environmental sciences Physical sciences/Materials science Soft soil Banana Fiber reinforcement Alkaline Activated material shear strength ratio support vector model Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 Figure 15 1. Introduction Poor mechanical properties and inadequate load-bearing capacity of the infrastructure resting on soft ground are significant concerns in geotechnical engineering. Because of the swift development of infrastructure, it is extremely challenging to deal with different clays having fluctuating characteristics during the construction phase, which generally includes a variety of problematic soils (i.e., soft, swell-shrink, hydrophilic, liquefiable, acid sulfate, peaty, saline, organic, collapsible soils, among others) (Jangde et al. 2023; Luo and Zhang 2023). Of these, the soft soils generally exhibit high natural moisture content (Jiang et al. 2020), high compressibility (Nagaraj et al. 1998), strong rheological characteristics (Zhu et al. 2017), weak permeability and low shear strength (Chen and Zhang 2024; Niu et al. 2024), high natural permeability and poor load-bearing capacity (Rosli et al. 2020), which leads to a multitude of problems in the form of uncontrolled distortion as well as structural instability (Han et al. 2023; Jalal et al. 2020; Kempfert and Gebreselassie 2006; Luo and Zhang 2023; Puppala et al. 2001; Taskiran 2010). These soils are broadly distributed throughout the globe in more than 40 countries. Their properties are mainly governed by both macro-factors (i.e, surcharge, water drainage circumstances, consolidation time, and depth), as well as micro-factors, such that the complex characteristics serve as the concentrated representation of their microstructural properties (Niu et al. 2024). Such soils are detrimental to civil engineering structures and require treatment using various stabilizer materials. Nowadays, the non-traditional nano-chemical stabilization is superior to conventional stabilizing techniques owing to its cost-effectiveness and enhanced environmental conservation (Emmanuel et al. 2019; Jalal et al. 2020; Nagaraj et al. 1998; Rangaswamy and Mohan 2023). The worldwide increase in greenhouse gas emissions has been primarily attributed to the utilization of fossil fuels at the gross level for power generation and domestic purposes (Ashfaq et al., 2021; Ashfaq et al., 2020b). Within the context of coal mining wastes, coal gangue (CG) is considered a heterogeneous waste produced during the mineral processing or coal cleaning phase of the mining process. It is noteworthy to mention that millions of tonnes of CG are recorded to be stockpiled (≈ 20–40% of the entire mining waste) at different coal mines on a global scale. China's substantial coal production, reaching 4.13 billion tons in 2021, has led to a significant increase in CG production (743 million tons, representing a 5.84% rise). Additionally, the cumulative storage of CG in China approaches approximately 7 billion tons (i.e., almost 6.79% of China’s arable land) from more than 2,000 gangue hills that cover around 200,000 mu. It is also pertinent to mention that the annual growth rate exceeds 800 million tons. The substantial accumulation poses a serious environmental and land-use challenge. Note that the CG generally exists in the form of two different types: (i) nonspontaneous combustion CG (also called “fresh gangue”), and (ii) spontaneous combustion (Ashfaq et al. 2020a; Ashfaq et al. 2020c; Ashfaq et al. 2022c; Cai et al. 2023; Pang et al. 2023; Xiao et al. 2021; Yang et al. 2024). The particle size of CG is between 10 and 100 mm (equalling that of gravel and/or cobble) and is noncombustible. It exhibits a loose structure and hence has a lower value of specific gravity (G s ). It has a petrographic composition with no plastic or shrinkage properties (resembling poorly graded sand behaviour) because of insufficient surface charge as well as fines content. The inclusion of fines to CG changes its gradation from poorly graded sand to silty sand (Ashfaq et al., 2022b). Moreover, the geotechnical indices of the CG indicate its potential application as a fill material. The presence of silica and alumina imparts a pozzolanic nature to CG, whereas quartz and kaolinite render it a suitable geomaterial. In addition, its California Bearing Ratio (CBR) value as well as its collapse behaviour also guarantee that it can be employed as a subgrade material (Ashfaq et al., 2021; Ashfaq et al., 2020b). The carbon footprint assessment (CFA) on CG applications reveals a substantial reduction in carbon emissions (Ashfaq et al., 2022b). For instance, these emissions are reduced by 3210 kg CO 2 e/m 3 (in case of embankment construction in contrast to traditional fill materials), 1709 kg CO 2 e/m 3 (in case of mechanically stabilized earth wall), 1168 kg CO 2 e/m 3 (in case of plain embankments), 14.4 kg CO 2 e/m 3 (in case of reinforced earth walls), and 135.4 kg CO 2 e/m 3 (in case of subbase material) (Ashfaq et al., 2020b; Ashfaq et al., 2022a). To design Roadways, Railways, and airfields, the CBR method was formulated by the California Division of Highways in 1928 (Kamrul Alam and Shiuly 2024). The objective of carrying out the unconfined compression strength (UCS) test is to evaluate the strength properties of soft soils, which aid in soil classification, design decisions, and construction quality control (Krishna et al. 2023; McElroy et al. 2021). The UCS substantially suggests the stiffness and strength properties of soft soils in accordance with ASTM D 2166 (ASTM 2006) and the CBR test as per ASTM D1883 (ASTM 2016). In road construction, the CBR and UCS values serve as reference parameters; however, obtaining these values via tests can be time-consuming (Saputra and Putra 2020; Syed and GuhaRay 2020; Tamassoki et al. 2023). While studying the soil samples obtained from Central Kalimantan Province of Malaysia, Saputra and Putra (2020) suggested a correlation equation of UCS = 0.2416 × CBR ̶ 1.2389 (correlation coefficient R = 0.92). It is imperative to mention that various machine learning (ML) tools or AI techniques, especially in geo-environmental engineering, are found to be immensely reliable and practical tools to solve complex problems with perplexed dynamics (Gajurel et al., 2021; Krishna et al., 2023; Tamassoki et al., 2023). In this context, Taskiran (2010) investigated the applicability of AI methods for forecasting CBR soft soils in the Southeast Anatolia Region of Turkey. It was found that both artificial neural networks (ANN) and gene expression programming (GEP) accurately predicted the relation between the CBR and basic soil indices. In another study, the addition of CG to expansive black cotton (BC) soil revealed that CBR values decrease beyond 40% CG due to reduced cohesion. However, the inclusion of CaO ameliorated the CBR values, with the 6CaO and 40CG combination showing superior performance (Ashfaq & Moghal, 2021). Additionally, Iqbal et al. (2021) evaluated the strength characteristics of soft soils (CBR and UCS) by deploying an adaptive neuro fuzzy inference system (ANFIS) and an ensemble random forest (RF) regression approach. They revealed that the latter model is superior to the ANFIS model. While predicting the UCS and CBR of chemically treated CG with the help of ANN and RF approaches, Ashfaq et al. (2022c) found that the UCS of CG exhibited an increasing trend when the CaO amount, gypsum content, and CP were increased. Note that the maximum value of 1,050% was obtained for 1.5% gypsum and 6% CaO inclusion. In yet another study by Amin et al. (2022), the neural network-based models demonstrated strong performance with R values of 0.993, 0.995, and 0.997 for UCS, unsoaked CBR, and soaked CBR, respectively. Furthermore, both the CBR and UCS witnessed a significant increase when stabilizer content was incorporated, thereby surpassing those of untreated soft soil (CBR = 3.862 and UCS = 0.8097) that met the construction standards (Krishna et al., 2023). Compared to the other learners, for instance, ANNs, the support vector machine (SVM) approach provides an improvement in the functionality because it usually achieves a better learning convergence with a simpler search optimization (Syarif et al. 2016), whereas ANNs can get stuck in local extrema without a proper optimization (Ly et al. 2021; Mohamad et al. 2015). Given tree-based models, such as regression trees or Random Forests (RF), SVMs exhibit better abilities to comprehend the non-linearity among variables. Also, SVMs exhibit good generalization performance suitable for tasks where the model needs to perform well on unseen data. However, like other machine learning models, these models require hyperparameter tuning when developing predictive models. The tuning can be done manually by repeatedly changing settings. On the contrary, SVMs have shown great compatibility with hyperparameter optimization methods, which render them even more of a viable option for developing ML-based predictive models (Armaghani et al. 2020; Kurani et al. 2021; Li et al. 2021). The present study primarily focuses on utilizing residual industrial waste in alkali-activated material as a smart, sustainable, and cost-effective soil stabilizer. This study aims to improve the geomechanical behavior of soft soil through geopolymerization, utilizing chemically treated banana fiber as a reinforcement material under varying coal gang ash-silica fume proportions. The research also analyzes a series of microstructural and geotechnical behavior tests on CTBF-CGA-SF-based AAM soil. To the best of our knowledge, the existing literature does not cover the CBR and UCS of coal gangue-stabilized soft soils using the SVM method. Although past studies have utilized various AI tools for predicting CBR values, they face limitations such as sensitivity to hyperparameters and a lack of interpretability. The current study aims to overcome these constraints, thereby providing an enhanced prediction model that is essential for informed decision-making across various applications. 2. Material Properties 2.1 Soft Soil and Associated Constituents For this investigation, soft soil was taken from a site located in Telangana's Nalgonda district. The collection involved disturbed samples extracted from a shallow depth of nearly 15 centimeters below ground level. According to the classification criteria outlined in the Indian standards, the soil type is classified as Intermediate Compressible Clay (CI), containing approximately 55% fine-grained material. The acquired soil samples exhibited a semi-black appearance and contained a substantial amount of clay loam. Before use, these soil samples were pulverized and subsequently subjected to a 24-hour drying process at around 105°C. Moreover, this type of clayey soil, commonly found in Telangana, is renowned for its problematic characteristics, particularly its behavior regarding moisture content and compressibility. In-situ measurements using a rapid moisture meter revealed a high soil moisture content accompanied by low shear strength. The materials employed in this study—Coal Gangue Ash (CGA), conforming to ASTM C618-17a, and Silica Fume (SF), complying with ASTM C989—were sourced from Bhupalpally Singareni Collieries, Telangana, and Jindal South-West (JSW) Cement Limited, Vishakhapatnam, respectively. These materials were used as dry precursors in the preparation of the alkaline binder. Figure 1 illustrates the particle size distribution curves for CGA, untreated soil, and the AAM-stabilized subgrade soil. A detailed summary of the engineering properties of the constituent materials is presented in Table 1 . Table 1 Fundamental Properties of Soil and Other Constituent Materials Properties Soft Soil CGA SF Parameter UBF pH 7.9 7.18 11.5 Diameter (µm) 38 Specific gravity 2.5 2.51 2.5 Specific gravity 0.88 Swelling Index (%) 78 19 - Tensile strength (MPa) 125 Liquid limit (%) 42 28 - Elastic modulus (MPa) 3250 Dry unit weight (g/cc) 1.7 21 2.4 Cellulose (%) 58 Water content (%) 21 17.5 - Hemicellulose (%) 16 UCS (kPa) 198 - Lignin (%) 10 ITS (kPa) 24 - Ash (%) 3 Soaked CBR 2.28 - - Wax (%) 1 2.2 Fiber Reinforcement Untreated banana fibers (UBF), with lengths ranging from 20 to 30 mm and diameters less than 33 µm, were procured from Go-Green Industries, Tamil Nadu. The dimensional attributes of the fibers—particularly their length and diameter—are recognized as critical factors influencing their effectiveness in soil reinforcement applications. Many researchers have demonstrated that natural fiber lengths between 20 mm and 40 mm can effectively resist higher friction and mobilization, as well as interfacial bonding, under low desiccation and soil surface cracking conditions (Miller et al. 2015; Syed et al. 2021). Hence, in the present research, fiber lengths between 20 and 30 mm were selected as an optimum length in AAM-stabilized soil. Moreover, before reinforcing the banana fiber in the soil mixture, the fiber was chemically treated with Ca(OH) 2 to delay the degradability and serviceability. A step-by-step procedure for treating fibers is shown in Fig. 2 . Initially, the raw banana fibers were immersed in water for 24 hours, followed by boiling for 30 minutes to remove waxy coatings and reduce the presence of natural oils on the fiber surface. The dried fibers were then placed in a 1000 mL solution of Ca(OH) 2 solution (12 Molarity) for seven days, facilitating thorough absorption of the solution into the fiber matrix. After treatment, the fibers were rinsed with clean water to eliminate any remaining calcite deposits. Finally, the processed fibers were dried at a controlled temperature of 23 ± 2°C for seven days. The chemical composition of soft soil, CGA, SF, and both untreated and treated fibers is provided in Table 2 . Table 2 Chemical composition of Soil and Other Constituent Materials Elements (%) Soft Soil CGA SF UBF TBF SiO 2 23.40 51.20 85.20 1.86 1.30 Al 2 O 3 5.12 26.10 3.60 0.30 0.0 CaO 4.60 2.10 1.10 20.50 45.60 K 2 O 2.70 1.80 0.89 0.80 2.30 MgO 7.96 0.70 1.01 0.10 0.00 P 2 O 5 1.60 0.20 0.08 1.50 4.30 Na 2 O 44.65 0.14 0.81 70.20 20.10 Cl 0.60 0.06 0.65 1.30 2.40 SO 3 0.20 0.05 1.16 1.30 3.50 FE 2 O 3 4.90 2.60 0.50 0.30 7.10 2.3 Alkali-Activated Materials Alkali-activated materials (AAM) were prepared by mixing coal gangue ash (CGA) and silica fume (SF) with an aqueous alkaline activator solution. The activator was prepared by maintaining a mass ratio of 280:129.43:120:10.57 for CGA, sodium silicate (Na₂SiO₃), SF, and sodium hydroxide (NaOH), respectively. The solution was produced by combining crushed NaOH pellets with a liquid Na₂SiO 3 solution, both procured from Hychem Laboratories, Hyderabad, India. The Na₂SiO₃ solution contained around 30% silicon dioxide (SiO 2 ), 15% sodium oxide (Na 2 O), and 54% water. To obtain the optimal AAM composition, CGA and SF were blended in varying proportions, with CGA ranging from 100–80% and SF from 0–20%. Table 3 presents the dosage of alkaline binder required per cubic meter of soft soil for each CGA–SF mixture. Table 3 Required Quantities of AAM for Subgrade Soil with Varying CGA–SF Ratios Sample Mass of AAM Components per Unit Volume of Subgrade Soil (kg/m³) AAM CGA SF NaOH Na 2 SiO 3 H 2 O SA 6 C 100 F 0 102.42 62.57 0.00 1.65 20.28 17.98 SA 6 C 95 F 5 102.42 59.44 3.12 1.65 20.28 17.98 SA 6 C 90 F 10 102.42 56.31 6.25 1.65 20.28 17.98 SA 6 C 85 F 15 102.42 50.06 12.51 1.65 20.28 17.98 SA 6 C 80 F 20 102.42 43.80 18.77 1.65 20.28 17.98 2.4 Sample Preparation The alkali-activated material (AAM) paste was uniformly blended with soft soil using different combinations of coal gangue ash (CGA, 80–100%) and silica fume (SF, 0–20%), maintaining a moisture-to-solid ratio of 0.4 in the alkaline activator. AAM dosages of 1%, 3%, 6%, and 10% (based on the dry weight of soil) were initially evaluated for soil stabilization before fiber reinforcement. To minimize data clustering, a 6% AAM binder was selected as the optimal stabilizer, incorporating CGA–SF ratios of 100:0, 95:5, 90:10, 85:15, and 80:20, respectively, based on cost efficiency, workability, alkali reactivity, binding capacity, and shrinkage resistance. Various CTBF reinforcement dosages were mixed into the AAM-treated soil and covered with dampened jute sheets, allowing curing under ambient conditions for 28 days. After curing, the CTBF–AAM soil composites were subjected to detailed microstructural and geotechnical testing. Table 4 presents the terminology used for CTBF–CGA–SF -based AAM-stabilized soil. Table 4 Sample mix definition for CTBG-CGA-SF stabilized soil Combination Sample definition All percentages of Coal Gangue ash and Silica fume were kept at 100% in the AAM paste. SA 6 C x F y : Binder prepared with various %age of AAM Mixing of AAM paste into the soil at 1, 3, 6, and 10% S = Soft soil F = Silica fume A = AAM C = Coal Gangue ash x=% of coal gangue ash (100, 95, 90, 85, and 80%) y=% of Silica fume (0, 5, 10, 15, and 20%) AAM-treated soil cured for 28 28-day curing period SA 6 C 100 F 0 SA 6 C 95 F 5 SA 6 C 90 F 10 SA 6 C 85 F 15 SA 6 C 80 F 20 3. Methodology 3.1 Microstructural characterization Microstructural investigations—including stereomicroscopy, Fourier-transform infrared (FTIR) spectroscopy, and thermogravimetric analysis (TGA)—were performed on untreated banana fiber, chemically treated banana fiber, and soft soil stabilized with CGA–SF-based alkali-activated mixtures. Surface topography of the soil was examined using a stereo microscope (Olympus SXZ7) operated at various magnifications (1×, 2.5×, 4.5×, and 5.6×), with a resolution capability of up to 20 µm. Molecular bond transmittance was analyzed using a potassium bromide (KBr) pellet-based FTIR spectrometer (JASCO-4200). Spectral data were recorded across a wavenumber range of 4000–500 cm⁻¹ for both fiber and AAM-stabilized soil matrices. In addition, thermal degradation behavior was evaluated through thermogravimetric analysis using a Shimadzu DTG-60 analyzer, applying a controlled heating rate of 10°C/min to approximately 15 mg of sample under a nitrogen atmosphere, with temperature reaching up to 800°C. 3.2 Geotechnical Testing A series of soil behaviour and mechanical strength testing, including consolidation, compression, and penetration resistance, was performed on AAM-stabilized soil, and CTBF-reinforced AAM composites containing varying proportions of SF-CGA. The relationship between void ratio (e) and effective stress (σ) was examined using a 3-cell consolidometer setup in accordance with ASTM D2435. Both untreated and treated specimens were sandwiched between porous stone in a consolidation ring of 6 cm diameter and 2 cm thickness. Measurements of sample height and percentage swelling were recorded at 24-hour intervals under a preload of 6.5 kPa, with loading continued until a peak effective stress of 800 kPa was achieved. The unconfined compressive strength (UCS) of the soil was evaluated by preparing soil–fiber composite specimens within cylindrical molds of 3.8 cm diameter and 7.6 cm height. Load was applied using a strain-controlled compression testing apparatus with a maximum capacity of 20 kN, operated at a constant strain rate of 1.25 mm/min. The improvement in shear strength due to fiber addition was quantified using the shear strength ratio (SSR), expressed in Eq. ( 1 ), which represents the ratio of UCS for fiber-reinforced (CTBF) soil to that of unreinforced soil. $$\:SSR=\frac{{UCS}_{(CTBF=0.25,\:\:\:0.5,\:\:\:0.75,\:\:\:1\%)}}{{UCS}_{\:ZeroCTBF}}$$ 1 Penetration resistance of CTBF-AAM stabilized soil containing SF and CGA was evaluated using the California Bearing Ratio (CBR) method under a 15 cm diameter cylindrical mold. The compacted CTBF-soil composite specimens were submerged in water for 4 days, and penetration was applied using a 5 cm diameter plunger at a constant strain rate of 1.25 mm/min. Additionally, the subgrade resilient modulus (M R ) was determined from the corresponding CBR values using Eq. ( 2 ), in accordance with the guidelines provided in IRC:37-2018: $$\:{M}_{R}=17.6\times\:{\left(CBR\right)}^{0.64}$$ 2 3.3 Support Vector-based modelling Support Vector Machines (SVMs) have demonstrated strong effectiveness in addressing high-dimensional problems involving function approximation, feature selection, classification, and predictive modeling. It is pertinent to mention that SVMs are advantageous due to their efficacy in high-dimensional spaces, robustness in dealing with the problem of overfitting, adaptable kernel functions, and improved performance in cases of small datasets. However, some of their main limitations include being computationally expensive, sensitivity to parameter tuning, lower transparency, and limited efficiency with noisy datasets. It is essential to recognize that the benefits and drawbacks of SVMs can vary depending on the specifics of the challenge and the dataset available when employing SVM-based modeling to evaluate the strength characteristics of fiber-reinforced coal gangue. As a result, it is highly recommended to conduct extensive testing with various algorithms and evaluate their performance before deciding on the best strategy for a given scenario. Furthermore, leveraging its kernel type, the SVM approach proves to be a powerful machine learning model that can effectively substitute traditional regression analyses. The SVM model can be mathematically represented as Eq. 3 . $$\:{\stackrel{̑}{y}}_{i}={w}^{T}\psi\:\left({x}_{i}\right)+b$$ 3 where ψ (x i ) stands for a kernel function that maps the input data to a desired linear or nonlinear feature space, w T denotes the weight vector, and b refers to the intermediary coordinate of the regression hyperplane. Although SVMs can classify and predict based on the predictive model, the type of kernel functions, as well as their hyperparameters, both affect the final accuracy. Therefore, it is important to develop predictive models by incorporating the optimized hyperparameters. Note that there are several optimization methods, such as (i) search-based methods (i.e., random search and grid search) (Syarif et al., 2016), and (ii) (meta)heuristic methods (i.e., evolutionary and population-based methods) (Armaghani et al., 2020). Further details about the evolutionary hyperparameter optimization of ML methods can be found in Chen et al. (2021). This study employs three types of baseline models: the plain SVM with manual settings, Grid search-based SVM (GS-SVM), and genetic algorithm-optimized SVM (GA-SVM), to ensure the validity of predictions. Hence, a variety of hyperparameter optimizations are employed, which also allows for the comparison of the prediction power of the developed models. Moreover, it is imperative to effectively refine the experimental observations of bias, missing observations, and multicollinearity before developing the predictive models. Accordingly, three predictive input parameters, namely, CGA, SF, and BF, were adopted to predict the response behaviour of two output variables (i.e., UCS and CBR). Consequently, Figs. 3 and 4 illustrate the pairwise relationships among variables, along with their statistical distributions. These pairplots are effective for exploring the relationships between variables in the dataset and identifying trends in variables. As shown in the figure, the diagonal histograms display the marginal distributions, and the remaining graphs illustrate the pairwise correlations. Based on the experimental observations, these figures suggest that, with increasing BF and SF, the strength characteristics (CBR and UCS) decrease. In contrast, the CGA increases, leading to reduced UCS and CBR values. Considering the pairs of variables, the experimental observations also suggest the existence of a negative correlation between SF and CGA. Hence, SF is inversely related to CGA. However, there is no tangible correlation between the three input attributes. These observations indicate that the effects of SF and CGA can be correlated, while BF does not correlate with other input variables. Noticeably, the effects of input variables on the predicted strength characteristics can be identified later based on the predictive SVM models. Noticeably, 225 entries of experimental observations have been incorporated into two portions to formulate the SVM-based models. After splitting the data randomly, 80% of the entries were used for training the models, whereas the remaining portion was used to test the predictions. These predictive models help to identify the influential variables on the prediction outputs (i.e., UCS and CBR). 4. Results and Analysis 4.1 Microstructural characterization 4.1.1 Stereomicroscopic Images A series of microscopic surface images of soft soil is collected by using a stereomicroscope under varying magnifications. Figure 5 (a-d) illustrates the typical stereomicroscopic images for untreated soft soil, soil mixed with an alkaline binder, and AAM soil reinforced with fibers at varying CGA-SF content. Figure 5 a illustrates areas of yellowish and light brown pigmentation in the untreated soft soil, which may be interpreted due to the presence of illite-smectite and iron groups. Additionally, irregular surface cracks are visible on the untreated soil, which will significantly impact the volumetric behavior when the water level fluctuates. Figure 5 (b) shows a thin layer of hardened AAM paste deposition around the cracks of the clay matrix. The bright and shiny regions may be due to the presence of mica from the silica fume. In contrast, the dark black colored patches are voids caused by early moisture evaporation from the solidified alkaline binder. The randomly distributed CTBF in the CGA-based AAM soil combination at 0 and 20% silica fume content is depicted in Figs. 5 (c-d). Moreover, the morphology of CTBF reinforcement in the soil matrix has formed a spatially grooved network, which relatively enhances interlocking friction by restricting the clay. particles during load application. Adding CTBF is beneficial as it strengthens the interfacial bonding, resulting in higher tensile and frictional resistance. As a result, the combined action of CTBF, CGA, and SF improves the load-bearing capacity and stiffness of AAM-stabilized soil, attributed to the development of an active pozzolanic matrix 4.1.2 Fourier Transform Infrared (FTIR) spectroscopy FTIR spectra for banana fiber before and after chemical treatment, untreated soft soil, and AAM stabilized soil at various coal gangue and silica fume dosages are shown in Figs. 6 (a-b). The molecular bonding curves of untreated banana fibers (Fig. 6 a) are characterized by hydroxyl O-H stretching at around 3300 cm − 1 , mostly due to the presence of cellulose and water. Moreover, the untreated soil in Fig. 6 (b) shows a sharp band of Portlandite [Ca (OH) 2 ] at 3600 cm − 1 . The broadband of O-H water stretching (3600 cm − 1 ) and C-H alcohol (3400 cm − 1 ) was reduced in both coal gangue (100%) and silica fume (20%) based AAM treated soil relative to untreated soil. Also, the C-H methyl group at around 2950 cm − 1 showed the same peaks before and after chemical treatment of fibers (Mir et al. 2012). The C = O carbonyl functional group is not apparent at 2900 cm-1 as the replacement of coal gangue with silica fume increases in the AAM mixed soil. The pozzolanic reaction in silica-rich soil roughly characterizes this spectrum. The transmittance spectra for AAM-treated soil containing high coal gangue ash (100%) show the marginal peak of the = CH2 bond compared to silica fume (20%) based AAM-treated soil. These modifications in soil chemical structures due to carbonation may be associated with minimal chemical weathering reactions on the clay surfaces (Syed et al. 2022). Interestingly, the symmetric stretching vibration of Si-O at 1030 cm − 1 remains identifiable even after the chemical treatment of fibers (Cesar dos Santos et al. 2016). A sharp characteristic band of Si-Al-O at 800 cm − 1 was observed in the untreated soil and the AAM mixed soil. Apart from that, the Si-O plane stretching vibration was identified in the range of wavenumbers around 580 cm − 1 . Thus, with a chemical shift of roughly 10–20 cm − 1 , the transmittance peaks from untreated fibers and AAM-treated soil reveal identical linkages. 4.1.3 Thermogravimetric analysis (TGA) Thermogravimetric (TG) and derivative thermogravimetric (DTG) analysis are used to calculate the stability of compounds and mass fractions against temperature. Figure 7 displays the TGA/DTG profiles of UBF and CTBF, focusing on mass reduction and its first derivative. An initial drop in mass was observed for both UBF and CTBF samples between 100–150ºC, likely resulting from rapid evaporation of free water within the fiber matrix (Komal et al. 2020). The mass loss in UBF was found to be relatively higher (4–5%) than in CTBF, which may be attributed to a greater decomposition rate of volatile components in the untreated fibers. Additionally, the TG/DTG trends for both UBF and CTBF overlapped due to cyclic thermal fluctuations. A second notable weight loss phase in UBF, occurring around 375–400°C, is predominantly linked to thermal degradation of biomass, including the breakdown of hemicellulose and cellulose structures (Ferreira et al. 2015). Moreover, the substantial alterations in the thermal peak positions of CTBF indicate restructuring in the fiber surface chemistry, likely due to the formation of new chemical phases induced by Ca (OH) 2 treatment. Also, the minimized thermal degradation of CTBF is attributed to the encapsulation of fibers with calcium hydroxide on the surface (Varma and Mondal 2016). Beyond 500°C, TGA curves indicate negligible mass change and tend to exhibit asymptotic behavior. 4.2 Geotechnical characterization A series of geotechnical tests was performed on AAM-stabilized soil incorporating various CGA–SF blend ratios. The corresponding geotechnical properties are presented in Table 5 . Table 5 Geotechnical results of AAM-soil at varying CGA-SF content Properties S.A 6 (C 100 F 0 ) (C 95 F 5 ) (C 90 F 10 ) (C 85 F 15 ) (C 80 F 20 ) Dry density (kN/m³) 16.75 17.5 17.8 18.0 18.3 Moisture content (%) 19.5 18.5 18.3 18.1 18.0 Linear shrinkage (%) 6.35 6.24 6.39 6.59 6.85 Plasticity index(%) 19.1 18.6 17.9 17.4 16.9 Swell index (%) 30.4 28.1 27.9 26.5 25.1 Swell Pressure (kPa) 46.2 41.4 34.1 31.2 27.5 4.2.1 Consolidation Soil compressibility (relative to equilibrium void ratio) for soft soil, coal gangue ash-silica fume-based alkaline stabilized soil, is plotted against effective stress. The variance in initial void ratio curves for both untreated soil and AAM stabilized soils is presented graphically in Fig. 8 . The trend of the void ratio plots illustrates the relationship between soil swelling behavior and the rate of applied seating load. During the early phase, untreated soft soil demonstrates a greater final void ratio compared to the alkaline-treated soil, as indicated by the e–log(σ) response. This is due to the existence of active moisture retention around the clay matrix and also being rich in silica and iron-illite compounds, effectively delaying the moisture infiltration, thus requiring a longer time to reach an equilibrium swelling stage (Kayabali and Yaldiz 2012; Soltani et al. 2018). The addition of CGA-SF-based AAM stabilized soil aids in restricting the rate of void ratio effects (from 0.92 to 0.54); this marginal reduction may be due to the activation of the geopolymerization reaction in the clay composition, which adversely impacts the mineralogy. As the proportion of SF increases in place of CGA within the AAM blend, a significant reduction in volumetric expansion is observed. Notably, the combined incorporation of 20% SF and 80% CGA in the alkaline matrix results in a marked decrease in both void ratio and swelling across all AAM-stabilized soil compositions. Moreover, the drastic changes in and around the clay structure can also be substantially responsible for the drop in void ratio from 0.72 to 0.47 (20% SF-based AAM-soil). Through pozzolanic-ion consumption during active cementing gel formation, silica fume-based AAM stabilized surface particles may improve the interlocking bonding capacity of clay at low-effective stress applications (Chittoori et al., 2017; Meisina, 2007). Thus, in AAM mixed soil, creating consistent cementitious coatings with a new morphology reduces compressible behavior and the rate of void ratio reduction. 4.2.2 Unconfined compressive strength (UCS) The UCS measurements of AAM-stabilized soil incorporating varying dosages of pozzolanic materials within the alkaline binder are illustrated in Fig. 9 , which highlights the combined influence of fiber, coal gangue ash (CGA), and silica fume (SF) on strength enhancement in soft soil. A partial replacement of CGA (100–90%) with SF (0–10%) initially slows the development of compressive strength, which may be attributed to the low pozzolanic activity of silica and alumina present in CGA-based systems. As the content of SF and CTBF increases, the strength performance of AAM-treated soil improves progressively. This strength gain (from 620 kPa to 1260 kPa) is linked to the active geopolymerization reaction between clay particles and pozzolanic products in the alkaline matrix, leading to the formation of a denser microstructure (Ahmad et al., 2024; Alsafi et al., 2017; Syed et al., 2023a). The results also show that increasing the CTBF (0–1%) improves soil shear strength from 1280 kPa (SA 6 C 100 F 0 ) to 2160 kPa (SA 6 C 80 F 20 ). The increasing UCS trends reveal strong interlock particle bonding between the fiber matrix and clay structures that indirectly benefit from the geopozzolanic reaction. Therefore, the cohesive strength of the AAM-stabilized soil is directly influenced by the combined presence of silica fume and CTBF Figure 9 (b) illustrates the shear strength ratio (SSR) behavior of AAM soil reinforced with CTBF across different CGA–SF mix proportions. The SSR-based compressive strength analysis highlights the role of CTBF in enhancing confinement effects, primarily through increased interparticle friction and improved bonding within the alkaline-treated matrix, resulting in greater density and stiffness. When the soil matrix is stabilized using 100% CGA (with no SF), the CTBF–AAM system attains an SSR range of approximately 2.0–2.5. Similar SSR values (2.2–3.0) have been reported by Park (2011) and Bekhiti et al. (2019) for waste rubber fiber-reinforced cementitious materials. In comparison, for kaolinite clay treated with 1% glass fiber and 1% polypropylene fiber, Maher and Ho (1995) and Rios et al. (2017) reported a maximum SSR of 1.2. As SF partially replaces CGA (up to 20%) in the mix, the SSR of the CTBF–AAM system tends to align with the corresponding compressive strength, showing a value around 1.65. It is important to note that increasing CTBF dosage beyond 0.6% and SF content above 10% results in a modest improvement in the shear strength ratio. The increased dosage of the silica fume in the alkaline binder compound actively enhances the soil interbonding density between CTBF-AAM soils. Additionally, the addition of SF is beneficial to CGA-based AAM soil, as it actively produces calcium silicate gel from its available silica-calcium compounds, resulting in low soil moisture attraction around the CTBF-clay particles. This forms a dense bridge effect, characterized by strong particle-holding efficiency, and enhances the compressive shear resistance during geopolymerization. The rough surface of CTBF strongly holds the pozzolanic encapsulated clay particles, which are difficult to reorient, and can improve interlocking friction resistance against loading (Mazhar & Guharay, 2020; Tang et al., 2007). Thus, the active formation of geopolymerization in the SF-based CTBF-AAM soil can strengthen the ultimate pulling stress under strong linkage effects. 4.2.3 California Bearing Ratio (CBR) The influence of pozzolanic precursors and alkaline activators on the performance enhancement of subgrade soil was analyzed through penetration resistance measurements. The soaked CBR tests will indirectly provide a clue to the efficiency of subgrade geomaterials under the long-term effect at different CTBF-CGA-SF proportions in the AAM-soil mixture. Figures 10 a shows the variation in soaking CBR values for untreated soil and CTBF-reinforced AAM mixed soil under CGA replacement with SF proportionsAAM addition improved the penetration resistance of the soil from 2.28–5.87%. The substantial improvement in CBR value achieved may be due to geopozzolanic activation during soaking (Syed et al., 2023b). The synthesis of silica fume between the CGA-fiber matrices induces an active multivalent cationic growth that minimizes clay compressibility (Moghal et al., 2018; Pourakbar & Huat, 2017; Priyadharshini et al., 2017; Shahbazi et al., 2017). Moreover, the formation of dense pozzolanic compounds within the silica-rich matrix significantly enhances the bonding of flocculated particles, leading to greater penetration-locking density. It is important to highlight that the combined use of 20% SF and 80% CGA in the alkaline binder results in a substantial improvement in penetration resistance, along with minimal swelling across all AAM-based CGA/SF mixtures. Additionally, Fig. 10 (b) presents the soaked CBR-derived resilient modulus values, which serve as a reliable indicator of subgrade soil stiffness. To minimize data clustering, only selected results for CTBF–AAM-stabilized soil with CGA:SF ratios of 100:0, 90:10, and 80:20 are shown. The resilient modulus outcomes highlight the interaction between soil penetration resistance and specific slag content, particularly under higher PLF dosages in the treated soil. It reveals that the CTBF and SF proportions in CGA-based AAM composites play a key role in increasing subgrade strength and bearing resistance under regulated swell-shrinkage behavior. The resilient modulus trend of soil is similar to that of CBR penetration with the addition of binder and fiber to the soil. A significant increase in the CBR-based resilient modulus of AAM-stabilized subgrade soils was observed beyond 0.5% CTBF reinforcement, particularly within the 0.2–0.4% PLF range when silica fume content exceeded 10% in the alkaline binder. Hence, geopolymerization driven by pozzolanic gels contributes to the formation of a bonded network around the CTBF–AAM–soil matrix, improving penetration resistance. 4.3 Comparative efficiency of SVM-based predictive models Figures 11 and 12 illustrate the regression plot between the experimental observations and forecasted outputs, showcasing the predictive outcomes of SVM-based modeling. Accordingly, two error measurement initiatives, namely residual error and training-testing errors, are also visualized to determine the robustness of the SVM-based models. Upon comparing the prediction results, it is evident that the SVM optimization has a substantial impact on the predicted outputs. The testing R 2 values yielded from the SVM approach in the case of UCS and CBR models are improved by 270% and 220%, respectively, when optimized through grid search methods. These improvements are also achieved by attaining R 2 of 0.95 (for UCS) and 0.965 (for CBR) in the GA approach, which corroborates the immense capabilities of both these optimization methods. Error area analysis : Error areas are another type of visual measurement of the uncertainty in the case of predicted data. The difference between error area analysis and prediction error analysis (shown in Fig. 10 and Fig. 11 , respectively) lies in the type of associated uncertainty. By propagating uncertainty through the input data and then performing predictions, error areas are determined. In contrast, the prediction error results in Figs. 10 and 11 only show the yielded error after prediction using the developed model, or how well the developed model can predict the outputs from the original data. As a result, this uncertainty analysis adds variability to the dataset, aiding in the assessment of how well the developed models generalize to unseen data. To carry out error area analysis, the standard deviation of the input entries is extended using a 95% confidence interval (CI), represented by the shaded regions. Broader error areas indicate less prediction certainty, while narrower areas imply more certainty. Moreover, Fig. 12 and Fig. 13 depict the error area analysis during training and testing of GS-SVM and GA-SVM models predicting CBR and UCS, respectively. Evidently, the training of the models with deviated inputs is more certain, whereas testing is significantly sensitive to inputs having high standard deviation. Noticeably, the regression fit results of training for both GS-SVM and GA-SVM were R 2 of 0.9728 and 0.973, respectively. However, the testing results were slightly higher in the case of GA-SVM during testing, with an increase from R 2 of 0.9601 for GS-SVM to R 2 of 0.9645 for GA-SVM. These marginal differences, although not clearly visible in Figs. 10 and 11 imply the effect of the optimization using the Genetic algorithm. Hence, the presence of such error area analysis can better highlight the importance of such tasks. As can be seen in Figs. 10 and 11 , the encircled areas in the testing plots of each figure indicate noticeable differences between the two different algorithms, as well as different predicted outputs. This observation further underscores the importance of error analysis with confidence intervals (CIs) compared to common regression plots, enabling the identification of models with robust performance more easily. 4.4 Comparative effects of input variables on the predicted output One of the key advantages of predictive models is their ability to identify how input variables influence output parameters. However, earlier studies often failed to represent the significance and ranking of these variables clearly. The magnitude of these influences can be accurately evaluated only through sensitivity analysis techniques, such as feature importance or explainable AI approaches. SHAP (SHapley Additive exPlanations) is a modern sensitivity analysis method that enables the evaluation of individual variable effects on model predictions. This technique offers both global insights—comparable to those provided by Sobol sensitivity analysis—and local interpretability. SHAP values quantify the relative impact of each input feature on the predicted output, supporting a deeper understanding of both local and global prediction behaviors. The SHAP-based sensitivity results for outputs predicted by the optimized SVM models are illustrated in Fig. 14 . It should be noted that despite the previous model analysis, the sensitivity results obtained via both GA-SVM and GS-SVM were almost identical. For the sake of brevity, only the results of GA-SVM are reported herein. It can be seen that BF is the governing input parameter affecting the output more than twice as much as the remaining variables. However, the predictive impacts of both CGA and SF on the predicted outcomes are almost identical. As shown earlier (in the preprocessing of the datasets via pair plots, i.e., Figs. 2 and 3 ), it is pertinent to mention that CGA and SF exhibit a strong negative relationship. As a result, the consequent effects are also somewhat similar. On the contrary, BF has no significant correlation with the remaining variables. These observations suggest that the variation would significantly alter the final strength values, given the current dosage and experimental plan. Furthermore, the effect of variables on the prediction of each distinct output is almost similar. Nevertheless, it is noteworthy to mention that each point in the SHAP plot represents the effect of variables on a set of data entries. Although the order of variable importance can be put as BF > CGA ≥ SF, during the prediction of CBR values, the SHAP values are observed to be more scattered. This observation indicates that the inputs affect the prediction course of CBR comparatively more than the UCS. Hence, data measurement and preprocessing of CBR values require relatively more precision to prevent data measurement uncertainty. 5. Summary and Conclusions This research investigates the combined influence of CTBF reinforcement on soft soil stabilized with coal gangue ash and silica fume-based alkali-activated materials. The influence of CGA-SF proportions on consolidation and CTBF reinforcement on geomechanical strength performance indicators (compressive strength, shear strength ratio, CBR, and resilient modulus) of AAM stabilized soft soil was investigated. Furthermore, an optimal SVM model was developed to analyze the geomechanical strength behavior, including compressive shear and penetration resistance, of CTBF-AAM soil at various CGA-SF dosages. The key findings of this research are outlined in the conclusion section that follows. The growth of geopolymeric cementitious gel around the CTBF-clay matrices is observed after AAM treatment (soil surface cracks and pores filling and forming a hardened AAM thin layer). Moreover, the addition of discrete CTBF alkaline soil has formed a spatial groove clay network structure, enhancing the soil-tensile interfacial density under strong interlocking friction. The growth of new molecular bonds (Si-O-Si and Si-O-Al) linked to activating geopolymerization reactions. Also, in the CTBF, the C = O and –CH2 alkene-lignin group is identified, corresponding to the carbonation reaction. In TGA/DTG measurement, the mass loss fraction of CTBF decreases compared to UBF, overcoming the early biodegradability of the material. At an optimal blend ratio of 80:20 (CGA to SF), the AAM-treated soil demonstrates improved volumetric stability by reducing the equilibrium void ratio by up to 68%. CTBF–AAM composites also show enhanced penetration resistance and subgrade resilient modulus, achieving a 68% increase in CBR strength at the ideal fiber reinforcement level of 1%. The shear strength ratio of AAM-treated soil decreases significantly when CGA is partially replaced with SF in the alkaline binder. Moreover, CTBF enhances the confinement bonding with dense cementitious layers surrounding it, achieving higher durability by preventing early biodegradation. The improvement in unconfined compressive strength (UCS) was notable when CTBF, CGA, and SF were combined in the alkaline soil stabilizer. Additionally, the proposed SV model for geomechanical strength, in terms of UCS and CBR, exhibits the lowest error percentages (< 10%) regardless of CGA: SF content. The regression fit results of training for both GS-SVM and GA-SVM were R2 of 0.9728 and 0.973, 536, respectively. However, the testing results were slightly higher in the case of GA-SVM during testing, with a 537 increase from R2 of 0.9601 for GS-SVM to R2 of 0.9645 for GA-SVM. According to SHAP analysis, the order of variable importance can be put as BF > CGA ≥ SF; however, 539 during the prediction of CBR values, the SHAP values are observed to be more scattered. This observation 540 indicates that the inputs affect the prediction course of CBR comparatively more than the UCS. Declarations Credit authorship contribution statement Mazhar Syed : Methodological Framework, Research Execution, and Writing – Original Draft Mohammed Ashfaq : Idea Development, Supervision, and Critical Review of the Manuscript Babak Jamhiri : Conceptualization, Software Implementation, Analytical Modeling. Fazal E. Jalal: Conceptualization, Review & editing. Umair Ali: Conceptualization, Project administration, Resources, Supervision, Review, and editing. Data Avaialability: The datasets used and/or analysed during the current study available from the corresponding author on reasonable request. Conflicts of interest/Competing interests (include appropriate disclosures): No conflict of interest Acknowledgments: The authors gratefully acknowledge the support provided by the Deanship of Research at King Fahd University of Petroleum and Minerals (KFUPM) for facilitating this study. Special thanks are also extended to the Interdisciplinary Research Center for Construction and Building Materials for their valuable contribution toward the successful completion of this work. Author Contribution M.S, M.A, and B.J wrote the main manuscript text and F.J prepared figures. U.A reviewed, edited and wrote. All authors reviewed the manuscript. References Ahmad, S., M. Shah Alam Ghazi, M. Syed, and M. A. Al-Osta. 2024. “Utilization of fly ash with and without secondary additives for stabilizing expansive soils: A review.” Results Eng. , 22 (April): 102079. Elsevier B.V. https://doi.org/10.1016/j.rineng.2024.102079. Alsafi, S., N. Farzadnia, A. Asadi, and B. K. Huat. 2017. “Collapsibility potential of gypseous soil stabilized with fly ash geopolymer; characterization and assessment.” Constr. Build. Mater. , 137: 390–409. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2017.01.079. Bekhiti, M., H. Trouzine, and M. Rabehi. 2019. “Influence of waste tire rubber fibers on swelling behavior, unconfined compressive strength and ductility of cement stabilized bentonite clay soil.” Constr. Build. Mater. , 208: 304–313. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2019.03.011. Cesar dos Santos, J., T. H. Panzera, K. Strecker, A. Caldas, J. C. dos Santos, T. H. Panzera, and K. Strecker. 2016. MECHANICAL PROPERTIES OF EPOXY BANANA FIBRE COMPOSITE TRATED WITH SODIUM CARBONATE . Chittoori, B. C. S. Moghal, A. A. B. Pedarla, A. Al-Mahbashi, A. M. 2017. “Effect of Unit Weight on Porosity and Consolidation Characteristics of Expansive Clays.” J. Test. Eval. , 45 (1): 94–104. https://doi.org/https://doi.org/10.1520/JTE20160451. Ferreira, S. R., F. D. A. Silva, P. R. L. Lima, and R. D. Toledo Filho. 2015. “Effect of fiber treatments on the sisal fiber properties and fiber-matrix bond in cement based systems.” Constr. Build. Mater. , 101: 730–740. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2015.10.120. IRC:37-2018. 2018. “Guidelines for the design of flexible pavements (Fourth Revision). IRC 37-2018. New Delhi, India.” 2018 , 1–94. Jangde, H., F. Khan, and A. Ghaffar. 2023. “Exploring the Correlation Between Compressive Strength and Hydraulic Conductivity in Soft Soil with Metakaolin as a Stabilizing Agent: An Experimental Study.” Int. Conf. Interdiscip. Approaches Civ. Eng. Sustain. Dev. , 79–89. Springer. Kayabali, K., and Ö. Yaldiz. 2012. “Investigation of the relationship between swell pressure and shrinkage limit.” Electron. J. Geotech. Eng. , 17 P (May): 2313–2325. Komal, U. K., V. Verma, T. Ashwani, N. Verma, and I. Singh. 2020. “Effect of Chemical Treatment on Thermal, Mechanical and Degradation Behavior of Banana Fiber Reinforced Polymer Composites.” J. Nat. Fibers , 17 (7): 1026–1038. Taylor and Francis Inc. https://doi.org/10.1080/15440478.2018.1550461. Luo, Z., and B. Zhang. 2023. “Effect of humic acid and fulvic acid on mechanical and durability properties of geopolymer stabilized soft soil.” Constr. Build. Mater. , 409: 133875. Elsevier. Maher, M. H., and Y. C. Ho. 1995. “Mechanical Properties of Kaolinite/Fiber Soil Composite.” J. Geotech. Eng. , 120 (8): 1381–1393. Mazhar, S., and A. Guharay. 2020. “Stabilization of expansive clay by fibre-reinforced alkali-activated binder : an experimental investigation and prediction modelling.” Int. J. Geotech. Eng. , 15 (2020): 1–17. https://doi.org/10.1080/19386362.2020.1775358. Meisina, C. 2007. “Swelling-shrinking properties of weathered clayey soils associated with shallow landslides.” Q. J. Eng. Geol. Hydrogeol. , 37 (2): 77–94. https://doi.org/10.1144/1470-9236/03-044. Miller, S. A., W. V. Srubar, S. L. Billington, and M. D. Lepech. 2015. “Integrating durability-based service-life predictions with environmental impact assessments of natural fiber-reinforced composite materials.” Resour. Conserv. Recycl. , 99: 72–83. https://doi.org/10.1016/j.resconrec.2015.04.004. Mir, S. S., S. M. N. Hasan, M. J. Hossain, and M. Hasan. 2012. “Chemical modification effect on the mechanical properties of coir fiber.” Eng. J. , 16 (2): 73–83. https://doi.org/10.4186/ej.2012.16.2.73. Moghal, A. A. B., B. C. S. Chittoori, and B. M. Basha. 2018. “Effect of fibre reinforcement on CBR behaviour of lime-blended expansive soils: reliability approach.” Road Mater. Pavement Des. , 19 (3): 690–709. Taylor & Francis. https://doi.org/10.1080/14680629.2016.1272479. Park, S. S. 2011. “Unconfined compressive strength and ductility of fiber-reinforced cemented sand.” Constr. Build. Mater. , 25 (2): 1134–1138. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2010.07.017. Pourakbar, S., and B. K. Huat. 2017. “A review of alternatives traditional cementitious binders for engineering improvement of soils.” Int. J. Geotech. Eng. , 11 (2): 206–216. https://doi.org/10.1080/19386362.2016.1207042. Priyadharshini, P., K. Ramamurthy, and R. G. Robinson. 2017. “Excavated soil waste as fine aggregate in fly ash based geopolymer mortar.” Appl. Clay Sci. Rios, S., C. Ramos, and C. Viana da Fonseca, António Cruz, Nuno. & Rodrigues. 2017. “Mechanical and durability properties of a soil stabilised with an alkali-activated cement.” Eur. J. Environ. Civ. Eng. , 8189 (January): 1–23. Taylor & Francis. https://doi.org/10.1080/19648189.2016.1275987. Shahbazi, M., M. Rowshanzamir, S. M. Abtahi, and S. M. Hejazi. 2017. “Optimization of carpet waste fibers and steel slag particles to reinforce expansive soil using response surface methodology.” Appl. Clay Sci. https://doi.org/10.1016/j.clay.2016.11.027. Soltani, A., A. Deng, and A. Taheri. 2018. “Swell–compression characteristics of a fiber–reinforced expansive soil.” Geotext. Geomembranes , 46 (2): 183–189. Elsevier. https://doi.org/10.1016/j.geotexmem.2017.11.009. Syed, M., M. Ahuja, A. R. Jambholkar, and A. GuhaRay. 2022. “Laboratory Investigation on Fiber-Reinforced Expansive Subgrade Soil Stabilized with Alkali Activated Binder: A Reliability-Based Perspective.” Geo-Congress 2022 , 241–250. Syed, M., A. GuhaRay, S. K. Chukka, and S. Ahmad. 2024. “A laboratory investigation and numerical modeling on fiber reinforced lime and alkaline binder stabilized pavement subgrade soil.” Case Stud. Constr. Mater. , 20 (January): e03000. Elsevier Ltd. https://doi.org/10.1016/j.cscm.2024.e03000. Syed, M., A. GuhaRay, and A. Garg. 2021. “Performance evaluation of lime, cement and alkali-activated binder in fiber-reinforced expansive subgrade soil: A comparative study.” J. Test. Eval. , 51 (1). https://doi.org/10.1520/JTE20210054. Syed, M., A. GuhaRay, and S. Raju. 2023a. “Subgrade Strength Performance Behavior of Alkali-Activated Binder and Cement Stabilized Expansive Soil: A Semifield Study.” J. Mater. Civ. Eng. , 35 (10): 1–11. https://doi.org/10.1061/jmcee7.mteng-15580. Syed, M., A. A. B. Moghal, and B. Chittoori. 2023b. “Reliability Analysis of Polyvinyl Alcohol Fiber-Reinforced Soft Subgrade Soil Treated with Lime and Alkali Activated Stabilizer: A Comparative Study.” Geo-Congress 2023 , 422–432. ASCE. Tang, C., B. Shi, W. Gao, F. Chen, and Y. Cai. 2007. “Strength and mechanical behavior of short polypropylene fiber reinforced and cement stabilized clayey soil.” Geotext. Geomembranes , 25 (3): 194–202. https://doi.org/10.1016/j.geotexmem.2006.11.002. Varma, A. K., and P. Mondal. 2016. “Physicochemical Characterization and Pyrolysis Kinetic Study of Sugarcane Bagasse Using Thermogravimetric Analysis.” J. Energy Resour. Technol. , 138 (5): 1–11. https://doi.org/10.1115/1.4032729. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 23 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 09 Oct, 2025 Reviews received at journal 09 Oct, 2025 Reviews received at journal 06 Oct, 2025 Reviews received at journal 26 Sep, 2025 Reviewers agreed at journal 25 Sep, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviews received at journal 18 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers invited by journal 10 Sep, 2025 Editor assigned by journal 10 Sep, 2025 Editor invited by journal 10 Sep, 2025 Submission checks completed at journal 07 Sep, 2025 First submitted to journal 07 Sep, 2025 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-7526534","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":514381341,"identity":"32fb92d9-84ec-44ec-a5bc-d3b0affab048","order_by":0,"name":"Mazhar Syed","email":"","orcid":"","institution":"King Fahd University of Petroleum and Minerals","correspondingAuthor":false,"prefix":"","firstName":"Mazhar","middleName":"","lastName":"Syed","suffix":""},{"id":514381342,"identity":"3e46d9eb-4e75-4bee-a206-65268862f831","order_by":1,"name":"Mohammed Ashfaq","email":"","orcid":"","institution":"Technical Manager, Osaimi Geotechnic Company","correspondingAuthor":false,"prefix":"","firstName":"Mohammed","middleName":"","lastName":"Ashfaq","suffix":""},{"id":514381343,"identity":"07d2ed9a-b46e-4f23-90b9-ef6a050ca570","order_by":2,"name":"Babak Jamhiri","email":"","orcid":"","institution":"Loughborough University","correspondingAuthor":false,"prefix":"","firstName":"Babak","middleName":"","lastName":"Jamhiri","suffix":""},{"id":514381344,"identity":"93a300d8-5317-4962-aaae-35c29ebdb522","order_by":3,"name":"Fazal E. Jalal","email":"","orcid":"","institution":"King Fahd University of Petroleum and Minerals","correspondingAuthor":false,"prefix":"","firstName":"Fazal","middleName":"E.","lastName":"Jalal","suffix":""},{"id":514381348,"identity":"bfadb37b-617b-4451-9499-d7140a31ec36","order_by":4,"name":"Umair Ali","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYJACCTDJzHyYoQIiYECsFrZkhjOkaWHgMSZOi/yM5IM3GHfYyW44zvPZ4GDbnWgG9uZtEgx/7HBqMbiRlmzBeCbZeMNh3s0JB9ue5TbwHCuTYGxLxq1FIscMqIA5cWYz7+bDH9sO5zaARRqY8Tgs/xtQSz1QC8/jAwdBWuTfmAEdVo/bMzdy2IBaDif2M/MwJ4C1SPAAtbAdxu2wM8+MLRLbjhv3M7MZGxw49yy3jSetGCSC22HtyQ9vfGyrlm3jP/xY4kDZndx+9sMbb3z4U43bYQIJDAxAxNgA4R5gYANRCbg1MDDwHwBTCC2jYBSMglEwCtABACWJV4VUaYnxAAAAAElFTkSuQmCC","orcid":"","institution":"King Fahd University of Petroleum and Minerals","correspondingAuthor":true,"prefix":"","firstName":"Umair","middleName":"","lastName":"Ali","suffix":""}],"badges":[],"createdAt":"2025-09-03 11:38:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7526534/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7526534/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-28438-z","type":"published","date":"2025-12-23T15:57:04+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91517019,"identity":"798ed952-2fef-4fbc-b222-dbea144fc8d5","added_by":"auto","created_at":"2025-09-17 09:28:06","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":90808,"visible":true,"origin":"","legend":"\u003cp\u003eParticle size analysis of materials\u003c/p\u003e","description":"","filename":"1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/c2dac4bdc7c69a8b8e0d89f0.jpg"},{"id":91517022,"identity":"f3d1e57c-05c3-4858-8fbe-764aa358699e","added_by":"auto","created_at":"2025-09-17 09:28:06","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":254864,"visible":true,"origin":"","legend":"\u003cp\u003eChemical treatment process of banana fiber\u003c/p\u003e","description":"","filename":"2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/56f81573dd51a55c5fe0edae.jpg"},{"id":91519829,"identity":"cfb7c1da-1a45-4ae4-a03c-7ebbe918ec02","added_by":"auto","created_at":"2025-09-17 10:00:07","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":84266,"visible":true,"origin":"","legend":"\u003cp\u003ePair plots of statistics, correlation among input/output variables while processing the UCS dataset.\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/845e0e687cb324c987b277e9.png"},{"id":91518878,"identity":"285beffb-c154-4fdd-bbc6-60d4dce76d7b","added_by":"auto","created_at":"2025-09-17 09:52:06","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":76849,"visible":true,"origin":"","legend":"\u003cp\u003ePair plots of statistics, correlation among input/output variables while processing the CBR dataset.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/733a08f97077fb2c11094b83.png"},{"id":91518493,"identity":"4109ca30-86ce-4ae9-aaa1-44986ec79c16","added_by":"auto","created_at":"2025-09-17 09:44:07","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":1386113,"visible":true,"origin":"","legend":"\u003cp\u003eStereomicroscopic images of a) untreated soil, b) AAM-soil, c) CGA-based AAM-CTBF soil, d) SF-CGA-based AAM-CTBF reinforced soil\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/ba7b9dfaeec151fe52e3f81e.png"},{"id":91517028,"identity":"205e842a-0b67-4b61-a829-62a3a96a7e87","added_by":"auto","created_at":"2025-09-17 09:28:06","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":439917,"visible":true,"origin":"","legend":"\u003cp\u003eFTIR curve of UBF and CTBF \u003cstrong\u003eb)\u003c/strong\u003e Raw and AAM-treated soil\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/37709801459f39b04d5fc610.png"},{"id":91517481,"identity":"a73e87dc-5f28-4864-a1d6-2251641fa079","added_by":"auto","created_at":"2025-09-17 09:36:06","extension":"jpg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":79357,"visible":true,"origin":"","legend":"\u003cp\u003eTGA-DTG curves of untreated and chemically treated banana fiber\u003c/p\u003e","description":"","filename":"7.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/feb1423d484d3f054e591be7.jpg"},{"id":91518488,"identity":"41b4aae5-54ce-477e-aa7e-6bb55b269fc9","added_by":"auto","created_at":"2025-09-17 09:44:06","extension":"jpg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":101641,"visible":true,"origin":"","legend":"\u003cp\u003eVoid ratio variations at different effective stresses for untreated and AAM-treated soils under varying CGA-SF dosages.\u003c/p\u003e","description":"","filename":"8.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/36d7c43019b5ceab054d3b9e.jpg"},{"id":91517037,"identity":"c0e1c8cd-75f3-4fdd-baa3-a25d848d8ee9","added_by":"auto","created_at":"2025-09-17 09:28:07","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":461400,"visible":true,"origin":"","legend":"\u003cp\u003eVariation of a) UCS and b) shear strength ratio of AAM-CTBF-reinforced soil at varying CGA-SF dosage\u003c/p\u003e","description":"","filename":"9.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/e03eb1129a59465d300f0840.png"},{"id":91517492,"identity":"e3090737-2fe4-49d9-9d26-848eee4ada24","added_by":"auto","created_at":"2025-09-17 09:36:07","extension":"png","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":565821,"visible":true,"origin":"","legend":"\u003cp\u003eEffect of CGA–SF proportions on a) soaked CBR values and b) resilient modulus of CTBF-reinforced AAM soil.\u003c/p\u003e","description":"","filename":"10.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/30149204b7beea07f46e1f2a.png"},{"id":91517491,"identity":"44f502ce-d35c-40c5-b378-bc630e8a4242","added_by":"auto","created_at":"2025-09-17 09:36:07","extension":"png","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":592972,"visible":true,"origin":"","legend":"\u003cp\u003ePrediction results of UCS corresponding to: a) SVM, b) GS-SVM, and c) GA-SVM approaches, along with the error measurements\u003c/p\u003e","description":"","filename":"11.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/0e5c737159dbc3ffb58e9d2e.png"},{"id":91517038,"identity":"eae22514-82ea-4a6e-9b66-28bb533d645d","added_by":"auto","created_at":"2025-09-17 09:28:07","extension":"png","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":607454,"visible":true,"origin":"","legend":"\u003cp\u003ePrediction results of CBR corresponding to a) SVM, b) GS-SVM, and c) GA-SVM, along with the error measurements\u003c/p\u003e","description":"","filename":"12.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/31c6f1c8d559c9edd18d81c3.png"},{"id":91517054,"identity":"90531a74-4039-4091-a199-55beb3dbca41","added_by":"auto","created_at":"2025-09-17 09:28:07","extension":"png","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":1596006,"visible":true,"origin":"","legend":"\u003cp\u003eFig. 12 Error area analysis during training and testing of GA-SVM and GS-SVM for predicting CBR with a 95% confidence interval\u003c/p\u003e","description":"","filename":"121.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/5af27ded6520778aeb666b94.png"},{"id":91517052,"identity":"ad1d7ae5-b3bb-4447-9ef6-62be77dd54a0","added_by":"auto","created_at":"2025-09-17 09:28:07","extension":"png","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":1757701,"visible":true,"origin":"","legend":"\u003cp\u003eFig. 13: Error area analysis during training and testing of GA-SVM and GS-SVM for predicting UCS with a 95% confidence interval\u003c/p\u003e","description":"","filename":"13.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/ab77608916894560b7b1e575.png"},{"id":91517041,"identity":"d01b8c7d-51e6-484c-8f04-fcb1798b1d9f","added_by":"auto","created_at":"2025-09-17 09:28:07","extension":"png","order_by":15,"title":"Figure 15","display":"","copyAsset":false,"role":"figure","size":111085,"visible":true,"origin":"","legend":"\u003cp\u003eFig.14: Variable importance analysis in the prediction of UCS and CBR\u003c/p\u003e","description":"","filename":"14.png","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/96f699f65b58bfcda01db3c1.png"},{"id":99172222,"identity":"eb9f00a4-34a7-4660-b2b5-83d7aea5bd71","added_by":"auto","created_at":"2025-12-29 16:03:59","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":9196077,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7526534/v1/2d24deec-a175-4467-a75a-34f907c4792e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Sustainable Engineering of Fiber-Reinforced Coal Gangue Linking Geomechanics and Microstructure through Support Vector Machines","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003ePoor mechanical properties and inadequate load-bearing capacity of the infrastructure resting on soft ground are significant concerns in geotechnical engineering. Because of the swift development of infrastructure, it is extremely challenging to deal with different clays having fluctuating characteristics during the construction phase, which generally includes a variety of problematic soils (i.e., soft, swell-shrink, hydrophilic, liquefiable, acid sulfate, peaty, saline, organic, collapsible soils, among others) (Jangde et al. 2023; Luo and Zhang 2023). Of these, the soft soils generally exhibit high natural moisture content (Jiang et al. 2020), high compressibility (Nagaraj et al. 1998), strong rheological characteristics (Zhu et al. 2017), weak permeability and low shear strength (Chen and Zhang 2024; Niu et al. 2024), high natural permeability and poor load-bearing capacity (Rosli et al. 2020), which leads to a multitude of problems in the form of uncontrolled distortion as well as structural instability (Han et al. 2023; Jalal et al. 2020; Kempfert and Gebreselassie 2006; Luo and Zhang 2023; Puppala et al. 2001; Taskiran 2010). These soils are broadly distributed throughout the globe in more than 40 countries. Their properties are mainly governed by both macro-factors (i.e, surcharge, water drainage circumstances, consolidation time, and depth), as well as micro-factors, such that the complex characteristics serve as the concentrated representation of their microstructural properties (Niu et al. 2024). Such soils are detrimental to civil engineering structures and require treatment using various stabilizer materials. Nowadays, the non-traditional nano-chemical stabilization is superior to conventional stabilizing techniques owing to its cost-effectiveness and enhanced environmental conservation (Emmanuel et al. 2019; Jalal et al. 2020; Nagaraj et al. 1998; Rangaswamy and Mohan 2023).\u003c/p\u003e\u003cp\u003eThe worldwide increase in greenhouse gas emissions has been primarily attributed to the utilization of fossil fuels at the gross level for power generation and domestic purposes (Ashfaq et al., 2021; Ashfaq et al., 2020b). Within the context of coal mining wastes, coal gangue (CG) is considered a heterogeneous waste produced during the mineral processing or coal cleaning phase of the mining process. It is noteworthy to mention that millions of tonnes of CG are recorded to be stockpiled (\u0026asymp;\u0026thinsp;20\u0026ndash;40% of the entire mining waste) at different coal mines on a global scale. China's substantial coal production, reaching 4.13\u0026nbsp;billion tons in 2021, has led to a significant increase in CG production (743\u0026nbsp;million tons, representing a 5.84% rise). Additionally, the cumulative storage of CG in China approaches approximately 7\u0026nbsp;billion tons (i.e., almost 6.79% of China\u0026rsquo;s arable land) from more than 2,000 gangue hills that cover around 200,000 mu. It is also pertinent to mention that the annual growth rate exceeds 800\u0026nbsp;million tons. The substantial accumulation poses a serious environmental and land-use challenge. Note that the CG generally exists in the form of two different types: (i) nonspontaneous combustion CG (also called \u0026ldquo;fresh gangue\u0026rdquo;), and (ii) spontaneous combustion (Ashfaq et al. 2020a; Ashfaq et al. 2020c; Ashfaq et al. 2022c; Cai et al. 2023; Pang et al. 2023; Xiao et al. 2021; Yang et al. 2024). The particle size of CG is between 10 and 100 mm (equalling that of gravel and/or cobble) and is noncombustible. It exhibits a loose structure and hence has a lower value of specific gravity (G\u003csub\u003es\u003c/sub\u003e). It has a petrographic composition with no plastic or shrinkage properties (resembling poorly graded sand behaviour) because of insufficient surface charge as well as fines content. The inclusion of fines to CG changes its gradation from poorly graded sand to silty sand (Ashfaq et al., 2022b). Moreover, the geotechnical indices of the CG indicate its potential application as a fill material. The presence of silica and alumina imparts a pozzolanic nature to CG, whereas quartz and kaolinite render it a suitable geomaterial. In addition, its California Bearing Ratio (CBR) value as well as its collapse behaviour also guarantee that it can be employed as a subgrade material (Ashfaq et al., 2021; Ashfaq et al., 2020b). The carbon footprint assessment (CFA) on CG applications reveals a substantial reduction in carbon emissions (Ashfaq et al., 2022b). For instance, these emissions are reduced by 3210 kg CO\u003csub\u003e2\u003c/sub\u003ee/m\u003csup\u003e3\u003c/sup\u003e (in case of embankment construction in contrast to traditional fill materials), 1709 kg CO\u003csub\u003e2\u003c/sub\u003ee/m\u003csup\u003e3\u003c/sup\u003e (in case of mechanically stabilized earth wall), 1168 kg CO\u003csub\u003e2\u003c/sub\u003ee/m\u003csup\u003e3\u003c/sup\u003e (in case of plain embankments), 14.4 kg CO\u003csub\u003e2\u003c/sub\u003ee/m\u003csup\u003e3\u003c/sup\u003e (in case of reinforced earth walls), and 135.4 kg CO\u003csub\u003e2\u003c/sub\u003ee/m\u003csup\u003e3\u003c/sup\u003e (in case of subbase material) (Ashfaq et al., 2020b; Ashfaq et al., 2022a).\u003c/p\u003e\u003cp\u003eTo design Roadways, Railways, and airfields, the CBR method was formulated by the California Division of Highways in 1928 (Kamrul Alam and Shiuly 2024). The objective of carrying out the unconfined compression strength (UCS) test is to evaluate the strength properties of soft soils, which aid in soil classification, design decisions, and construction quality control (Krishna et al. 2023; McElroy et al. 2021). The UCS substantially suggests the stiffness and strength properties of soft soils in accordance with ASTM D 2166 (ASTM 2006) and the CBR test as per ASTM D1883 (ASTM 2016). In road construction, the CBR and UCS values serve as reference parameters; however, obtaining these values via tests can be time-consuming (Saputra and Putra 2020; Syed and GuhaRay 2020; Tamassoki et al. 2023). While studying the soil samples obtained from Central Kalimantan Province of Malaysia, Saputra and Putra (2020) suggested a correlation equation of UCS\u0026thinsp;=\u0026thinsp;0.2416 \u0026times; CBR ̶ 1.2389 (correlation coefficient \u003cem\u003eR\u003c/em\u003e\u0026thinsp;=\u0026thinsp;0.92).\u003c/p\u003e\u003cp\u003eIt is imperative to mention that various machine learning (ML) tools or AI techniques, especially in geo-environmental engineering, are found to be immensely reliable and practical tools to solve complex problems with perplexed dynamics (Gajurel et al., 2021; Krishna et al., 2023; Tamassoki et al., 2023). In this context, Taskiran (2010) investigated the applicability of AI methods for forecasting CBR soft soils in the Southeast Anatolia Region of Turkey. It was found that both artificial neural networks (ANN) and gene expression programming (GEP) accurately predicted the relation between the CBR and basic soil indices. In another study, the addition of CG to expansive black cotton (BC) soil revealed that CBR values decrease beyond 40% CG due to reduced cohesion. However, the inclusion of CaO ameliorated the CBR values, with the 6CaO and 40CG combination showing superior performance (Ashfaq \u0026amp; Moghal, 2021). Additionally, Iqbal et al. (2021) evaluated the strength characteristics of soft soils (CBR and UCS) by deploying an adaptive neuro fuzzy inference system (ANFIS) and an ensemble random forest (RF) regression approach. They revealed that the latter model is superior to the ANFIS model. While predicting the UCS and CBR of chemically treated CG with the help of ANN and RF approaches, Ashfaq et al. (2022c) found that the UCS of CG exhibited an increasing trend when the CaO amount, gypsum content, and CP were increased. Note that the maximum value of 1,050% was obtained for 1.5% gypsum and 6% CaO inclusion. In yet another study by Amin et al. (2022), the neural network-based models demonstrated strong performance with \u003cem\u003eR\u003c/em\u003e values of 0.993, 0.995, and 0.997 for UCS, unsoaked CBR, and soaked CBR, respectively. Furthermore, both the CBR and UCS witnessed a significant increase when stabilizer content was incorporated, thereby surpassing those of untreated soft soil (CBR\u0026thinsp;=\u0026thinsp;3.862 and UCS\u0026thinsp;=\u0026thinsp;0.8097) that met the construction standards (Krishna et al., 2023).\u003c/p\u003e\u003cp\u003eCompared to the other learners, for instance, ANNs, the support vector machine (SVM) approach provides an improvement in the functionality because it usually achieves a better learning convergence with a simpler search optimization (Syarif et al. 2016), whereas ANNs can get stuck in local extrema without a proper optimization (Ly et al. 2021; Mohamad et al. 2015). Given tree-based models, such as regression trees or Random Forests (RF), SVMs exhibit better abilities to comprehend the non-linearity among variables. Also, SVMs exhibit good generalization performance suitable for tasks where the model needs to perform well on unseen data. However, like other machine learning models, these models require hyperparameter tuning when developing predictive models. The tuning can be done manually by repeatedly changing settings. On the contrary, SVMs have shown great compatibility with hyperparameter optimization methods, which render them even more of a viable option for developing ML-based predictive models (Armaghani et al. 2020; Kurani et al. 2021; Li et al. 2021).\u003c/p\u003e\u003cp\u003eThe present study primarily focuses on utilizing residual industrial waste in alkali-activated material as a smart, sustainable, and cost-effective soil stabilizer. This study aims to improve the geomechanical behavior of soft soil through geopolymerization, utilizing chemically treated banana fiber as a reinforcement material under varying coal gang ash-silica fume proportions. The research also analyzes a series of microstructural and geotechnical behavior tests on CTBF-CGA-SF-based AAM soil. To the best of our knowledge, the existing literature does not cover the CBR and UCS of coal gangue-stabilized soft soils using the SVM method. Although past studies have utilized various AI tools for predicting CBR values, they face limitations such as sensitivity to hyperparameters and a lack of interpretability. The current study aims to overcome these constraints, thereby providing an enhanced prediction model that is essential for informed decision-making across various applications.\u003c/p\u003e"},{"header":"2. Material Properties","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Soft Soil and Associated Constituents\u003c/h2\u003e\u003cp\u003eFor this investigation, soft soil was taken from a site located in Telangana's Nalgonda district. The collection involved disturbed samples extracted from a shallow depth of nearly 15 centimeters below ground level. According to the classification criteria outlined in the Indian standards, the soil type is classified as Intermediate Compressible Clay (CI), containing approximately 55% fine-grained material. The acquired soil samples exhibited a semi-black appearance and contained a substantial amount of clay loam. Before use, these soil samples were pulverized and subsequently subjected to a 24-hour drying process at around 105\u0026deg;C. Moreover, this type of clayey soil, commonly found in Telangana, is renowned for its problematic characteristics, particularly its behavior regarding moisture content and compressibility. In-situ measurements using a rapid moisture meter revealed a high soil moisture content accompanied by low shear strength. The materials employed in this study\u0026mdash;Coal Gangue Ash (CGA), conforming to ASTM C618-17a, and Silica Fume (SF), complying with ASTM C989\u0026mdash;were sourced from Bhupalpally Singareni Collieries, Telangana, and Jindal South-West (JSW) Cement Limited, Vishakhapatnam, respectively. These materials were used as dry precursors in the preparation of the alkaline binder. Figure\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates the particle size distribution curves for CGA, untreated soil, and the AAM-stabilized subgrade soil. A detailed summary of the engineering properties of the constituent materials is presented in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\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\u003eFundamental Properties of Soil and Other Constituent Materials\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\u003eProperties\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSoft Soil\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCGA\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eParameter\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eUBF\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003epH\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e7.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e7.18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e11.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eDiameter (\u0026micro;m)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e38\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSpecific gravity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e2.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eSpecific gravity\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e0.88\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSwelling Index (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e78\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eTensile strength (MPa)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e125\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLiquid limit (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eElastic modulus (MPa)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3250\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDry unit weight (g/cc)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e1.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e2.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eCellulose (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e58\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWater content (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e17.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eHemicellulose (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eUCS (kPa)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e198\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eLignin (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eITS (kPa)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eAsh (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSoaked CBR\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e-\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003eWax (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e1\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=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Fiber Reinforcement\u003c/h2\u003e\u003cp\u003eUntreated banana fibers (UBF), with lengths ranging from 20 to 30 mm and diameters less than 33 \u0026micro;m, were procured from Go-Green Industries, Tamil Nadu. The dimensional attributes of the fibers\u0026mdash;particularly their length and diameter\u0026mdash;are recognized as critical factors influencing their effectiveness in soil reinforcement applications. Many researchers have demonstrated that natural fiber lengths between 20 mm and 40 mm can effectively resist higher friction and mobilization, as well as interfacial bonding, under low desiccation and soil surface cracking conditions (Miller et al. 2015; Syed et al. 2021). Hence, in the present research, fiber lengths between 20 and 30 mm were selected as an optimum length in AAM-stabilized soil. Moreover, before reinforcing the banana fiber in the soil mixture, the fiber was chemically treated with Ca(OH)\u003csub\u003e2\u003c/sub\u003e to delay the degradability and serviceability. A step-by-step procedure for treating fibers is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. Initially, the raw banana fibers were immersed in water for 24 hours, followed by boiling for 30 minutes to remove waxy coatings and reduce the presence of natural oils on the fiber surface. The dried fibers were then placed in a 1000 mL solution of Ca(OH)\u003csub\u003e2\u003c/sub\u003e solution (12 Molarity) for seven days, facilitating thorough absorption of the solution into the fiber matrix. After treatment, the fibers were rinsed with clean water to eliminate any remaining calcite deposits. Finally, the processed fibers were dried at a controlled temperature of 23\u0026thinsp;\u0026plusmn;\u0026thinsp;2\u0026deg;C for seven days. The chemical composition of soft soil, CGA, SF, and both untreated and treated fibers is provided in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\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\u003eChemical composition of Soil and Other Constituent Materials\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=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eElements (%)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSoft Soil\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCGA\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eUBF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eTBF\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSiO\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e23.40\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e51.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e85.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.86\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e1.30\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAl\u003csub\u003e2\u003c/sub\u003eO\u003csub\u003e3\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e5.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e26.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCaO\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e20.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e45.60\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eK\u003csub\u003e2\u003c/sub\u003eO\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e2.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.89\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2.30\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMgO\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7.96\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.70\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.01\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eP\u003csub\u003e2\u003c/sub\u003eO\u003csub\u003e5\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e1.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.08\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e4.30\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eNa\u003csub\u003e2\u003c/sub\u003eO\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e44.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.14\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.81\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e70.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.10\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCl\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e2.40\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSO\u003csub\u003e3\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e0.20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e0.05\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1.16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e3.50\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eFE\u003csub\u003e2\u003c/sub\u003eO\u003csub\u003e3\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e4.90\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e2.60\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.50\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e0.30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e7.10\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\u003cdiv id=\"Sec5\" class=\"Section2\"\u003e\u003ch2\u003e2.3 Alkali-Activated Materials\u003c/h2\u003e\u003cp\u003eAlkali-activated materials (AAM) were prepared by mixing coal gangue ash (CGA) and silica fume (SF) with an aqueous alkaline activator solution. The activator was prepared by maintaining a mass ratio of 280:129.43:120:10.57 for CGA, sodium silicate (Na₂SiO₃), SF, and sodium hydroxide (NaOH), respectively. The solution was produced by combining crushed NaOH pellets with a liquid Na₂SiO\u003csub\u003e3\u003c/sub\u003e solution, both procured from Hychem Laboratories, Hyderabad, India. The Na₂SiO₃ solution contained around 30% silicon dioxide (SiO\u003csub\u003e2\u003c/sub\u003e), 15% sodium oxide (Na\u003csub\u003e2\u003c/sub\u003eO), and 54% water. To obtain the optimal AAM composition, CGA and SF were blended in varying proportions, with CGA ranging from 100\u0026ndash;80% and SF from 0\u0026ndash;20%. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e presents the dosage of alkaline binder required per cubic meter of soft soil for each CGA\u0026ndash;SF mixture.\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\u003eRequired Quantities of AAM for Subgrade Soil with Varying CGA\u0026ndash;SF Ratios\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"8\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eSample\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"7\" nameend=\"c8\" namest=\"c2\"\u003e\u003cp\u003eMass of AAM Components per Unit Volume of Subgrade Soil (kg/m\u0026sup3;)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAAM\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eCGA\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eSF\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eNaOH\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNa\u003csub\u003e2\u003c/sub\u003eSiO\u003csub\u003e3\u003c/sub\u003e\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003eH\u003csub\u003e2\u003c/sub\u003eO\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSA\u003c/b\u003e\u003csub\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sub\u003e \u003cb\u003eC\u003c/b\u003e\u003csub\u003e\u003cb\u003e100\u003c/b\u003e\u003c/sub\u003e\u003cb\u003eF\u003c/b\u003e\u003csub\u003e\u003cb\u003e0\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e62.57\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e0.00\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e17.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSA\u003c/b\u003e\u003csub\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sub\u003e \u003cb\u003eC\u003c/b\u003e\u003csub\u003e\u003cb\u003e95\u003c/b\u003e\u003c/sub\u003e\u003cb\u003eF\u003c/b\u003e\u003csub\u003e\u003cb\u003e5\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e59.44\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3.12\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e17.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSA\u003c/b\u003e\u003csub\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sub\u003e \u003cb\u003eC\u003c/b\u003e\u003csub\u003e\u003cb\u003e90\u003c/b\u003e\u003c/sub\u003e\u003cb\u003eF\u003c/b\u003e\u003csub\u003e\u003cb\u003e10\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e56.31\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e17.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSA\u003c/b\u003e\u003csub\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sub\u003e \u003cb\u003eC\u003c/b\u003e\u003csub\u003e\u003cb\u003e85\u003c/b\u003e\u003c/sub\u003e\u003cb\u003eF\u003c/b\u003e\u003csub\u003e\u003cb\u003e15\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e50.06\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e12.51\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e17.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSA\u003c/b\u003e\u003csub\u003e\u003cb\u003e6\u003c/b\u003e\u003c/sub\u003e \u003cb\u003eC\u003c/b\u003e\u003csub\u003e\u003cb\u003e80\u003c/b\u003e\u003c/sub\u003e\u003cb\u003eF\u003c/b\u003e\u003csub\u003e\u003cb\u003e20\u003c/b\u003e\u003c/sub\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e102.42\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e43.80\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e18.77\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e1.65\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20.28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e17.98\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colspan=\"1\" nameend=\"c8\" namest=\"c8\"\u003e\u0026nbsp;\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=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e2.4 Sample Preparation\u003c/h2\u003e\u003cp\u003eThe alkali-activated material (AAM) paste was uniformly blended with soft soil using different combinations of coal gangue ash (CGA, 80\u0026ndash;100%) and silica fume (SF, 0\u0026ndash;20%), maintaining a moisture-to-solid ratio of 0.4 in the alkaline activator. AAM dosages of 1%, 3%, 6%, and 10% (based on the dry weight of soil) were initially evaluated for soil stabilization before fiber reinforcement. To minimize data clustering, a 6% AAM binder was selected as the optimal stabilizer, incorporating CGA\u0026ndash;SF ratios of 100:0, 95:5, 90:10, 85:15, and 80:20, respectively, based on cost efficiency, workability, alkali reactivity, binding capacity, and shrinkage resistance. Various CTBF reinforcement dosages were mixed into the AAM-treated soil and covered with dampened jute sheets, allowing curing under ambient conditions for 28 days. After curing, the CTBF\u0026ndash;AAM soil composites were subjected to detailed microstructural and geotechnical testing. Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e presents the terminology used for CTBF\u0026ndash;CGA\u0026ndash;SF -based AAM-stabilized soil.\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\u003eSample mix definition for CTBG-CGA-SF stabilized soil\u003c/p\u003e\u003c/div\u003e\u003c/caption\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\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCombination\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSample definition\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAll percentages of Coal Gangue ash and Silica fume were kept at 100% in the AAM paste.\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003ex\u003c/sub\u003eF\u003csub\u003ey\u003c/sub\u003e: Binder prepared with various %age of AAM\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMixing of AAM paste into the soil at 1, 3, 6, and 10%\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eS\u0026thinsp;=\u0026thinsp;Soft soil F\u0026thinsp;=\u0026thinsp;Silica fume A\u0026thinsp;=\u0026thinsp;AAM C\u0026thinsp;=\u0026thinsp;Coal Gangue ash\u003c/p\u003e\u003cp\u003ex=% of coal gangue ash (100, 95, 90, 85, and 80%)\u003c/p\u003e\u003cp\u003ey=% of Silica fume (0, 5, 10, 15, and 20%)\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAAM-treated soil cured for 28 28-day curing period\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003e100\u003c/sub\u003eF\u003csub\u003e0\u003c/sub\u003e SA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003e95\u003c/sub\u003eF\u003csub\u003e5\u003c/sub\u003e\u003c/p\u003e\u003cp\u003eSA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003e90\u003c/sub\u003eF\u003csub\u003e10\u003c/sub\u003e SA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003e85\u003c/sub\u003eF\u003csub\u003e15\u003c/sub\u003e SA\u003csub\u003e6\u003c/sub\u003e C\u003csub\u003e80\u003c/sub\u003eF\u003csub\u003e20\u003c/sub\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"},{"header":"3. Methodology","content":"\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Microstructural characterization\u003c/h2\u003e\u003cp\u003eMicrostructural investigations\u0026mdash;including stereomicroscopy, Fourier-transform infrared (FTIR) spectroscopy, and thermogravimetric analysis (TGA)\u0026mdash;were performed on untreated banana fiber, chemically treated banana fiber, and soft soil stabilized with CGA\u0026ndash;SF-based alkali-activated mixtures. Surface topography of the soil was examined using a stereo microscope (Olympus SXZ7) operated at various magnifications (1\u0026times;, 2.5\u0026times;, 4.5\u0026times;, and 5.6\u0026times;), with a resolution capability of up to 20 \u0026micro;m. Molecular bond transmittance was analyzed using a potassium bromide (KBr) pellet-based FTIR spectrometer (JASCO-4200). Spectral data were recorded across a wavenumber range of 4000\u0026ndash;500 cm⁻\u0026sup1; for both fiber and AAM-stabilized soil matrices. In addition, thermal degradation behavior was evaluated through thermogravimetric analysis using a Shimadzu DTG-60 analyzer, applying a controlled heating rate of 10\u0026deg;C/min to approximately 15 mg of sample under a nitrogen atmosphere, with temperature reaching up to 800\u0026deg;C.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Geotechnical Testing\u003c/h2\u003e\u003cp\u003eA series of soil behaviour and mechanical strength testing, including consolidation, compression, and penetration resistance, was performed on AAM-stabilized soil, and CTBF-reinforced AAM composites containing varying proportions of SF-CGA. The relationship between void ratio (e) and effective stress (σ) was examined using a 3-cell consolidometer setup in accordance with ASTM D2435. Both untreated and treated specimens were sandwiched between porous stone in a consolidation ring of 6 cm diameter and 2 cm thickness. Measurements of sample height and percentage swelling were recorded at 24-hour intervals under a preload of 6.5 kPa, with loading continued until a peak effective stress of 800 kPa was achieved.\u003c/p\u003e\u003cp\u003eThe unconfined compressive strength (UCS) of the soil was evaluated by preparing soil\u0026ndash;fiber composite specimens within cylindrical molds of 3.8 cm diameter and 7.6 cm height. Load was applied using a strain-controlled compression testing apparatus with a maximum capacity of 20 kN, operated at a constant strain rate of 1.25 mm/min. The improvement in shear strength due to fiber addition was quantified using the shear strength ratio (SSR), expressed in Eq.\u0026nbsp;(\u003cspan refid=\"Equ1\" class=\"InternalRef\"\u003e1\u003c/span\u003e), which represents the ratio of UCS for fiber-reinforced (CTBF) soil to that of unreinforced soil.\u003cdiv id=\"Equ1\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ1\" name=\"EquationSource\"\u003e\n$$\\:SSR=\\frac{{UCS}_{(CTBF=0.25,\\:\\:\\:0.5,\\:\\:\\:0.75,\\:\\:\\:1\\%)}}{{UCS}_{\\:ZeroCTBF}}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e1\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ePenetration resistance of CTBF-AAM stabilized soil containing SF and CGA was evaluated using the California Bearing Ratio (CBR) method under a 15 cm diameter cylindrical mold. The compacted CTBF-soil composite specimens were submerged in water for 4 days, and penetration was applied using a 5 cm diameter plunger at a constant strain rate of 1.25 mm/min. Additionally, the subgrade resilient modulus (M\u003csub\u003eR\u003c/sub\u003e) was determined from the corresponding CBR values using Eq.\u0026nbsp;(\u003cspan refid=\"Equ2\" class=\"InternalRef\"\u003e2\u003c/span\u003e), in accordance with the guidelines provided in IRC:37-2018:\u003cdiv id=\"Equ2\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ2\" name=\"EquationSource\"\u003e\n$$\\:{M}_{R}=17.6\\times\\:{\\left(CBR\\right)}^{0.64}$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e2\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Support Vector-based modelling\u003c/h2\u003e\u003cp\u003eSupport Vector Machines (SVMs) have demonstrated strong effectiveness in addressing high-dimensional problems involving function approximation, feature selection, classification, and predictive modeling. It is pertinent to mention that SVMs are advantageous due to their efficacy in high-dimensional spaces, robustness in dealing with the problem of overfitting, adaptable kernel functions, and improved performance in cases of small datasets. However, some of their main limitations include being computationally expensive, sensitivity to parameter tuning, lower transparency, and limited efficiency with noisy datasets. It is essential to recognize that the benefits and drawbacks of SVMs can vary depending on the specifics of the challenge and the dataset available when employing SVM-based modeling to evaluate the strength characteristics of fiber-reinforced coal gangue. As a result, it is highly recommended to conduct extensive testing with various algorithms and evaluate their performance before deciding on the best strategy for a given scenario. Furthermore, leveraging its kernel type, the SVM approach proves to be a powerful machine learning model that can effectively substitute traditional regression analyses. The SVM model can be mathematically represented as Eq.\u0026nbsp;\u003cspan refid=\"Equ3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003cdiv id=\"Equ3\" class=\"Equation\"\u003e\u003cdiv format=\"TEX\" class=\"mathdisplay\" id=\"FileID_Equ3\" name=\"EquationSource\"\u003e\n$$\\:{\\stackrel{̑}{y}}_{i}={w}^{T}\\psi\\:\\left({x}_{i}\\right)+b$$\u003c/div\u003e\u003cdiv class=\"EquationNumber\"\u003e3\u003c/div\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003ewhere \u003cem\u003eψ\u003c/em\u003e(x\u003csub\u003ei\u003c/sub\u003e) stands for a kernel function that maps the input data to a desired linear or nonlinear feature space, \u003cem\u003ew\u003c/em\u003e\u003csup\u003e\u003cem\u003eT\u003c/em\u003e\u003c/sup\u003e denotes the weight vector, and \u003cem\u003eb\u003c/em\u003e refers to the intermediary coordinate of the regression hyperplane. Although SVMs can classify and predict based on the predictive model, the type of kernel functions, as well as their hyperparameters, both affect the final accuracy. Therefore, it is important to develop predictive models by incorporating the optimized hyperparameters. Note that there are several optimization methods, such as (i) search-based methods (i.e., random search and grid search) (Syarif et al., 2016), and (ii) (meta)heuristic methods (i.e., evolutionary and population-based methods) (Armaghani et al., 2020). Further details about the evolutionary hyperparameter optimization of ML methods can be found in Chen et al. (2021).\u003c/p\u003e\u003cp\u003eThis study employs three types of baseline models: the plain SVM with manual settings, Grid search-based SVM (GS-SVM), and genetic algorithm-optimized SVM (GA-SVM), to ensure the validity of predictions. Hence, a variety of hyperparameter optimizations are employed, which also allows for the comparison of the prediction power of the developed models. Moreover, it is imperative to effectively refine the experimental observations of bias, missing observations, and multicollinearity before developing the predictive models. Accordingly, three predictive input parameters, namely, CGA, SF, and BF, were adopted to predict the response behaviour of two output variables (i.e., UCS and CBR). Consequently, Figs.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e and \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e illustrate the pairwise relationships among variables, along with their statistical distributions. These pairplots are effective for exploring the relationships between variables in the dataset and identifying trends in variables. As shown in the figure, the diagonal histograms display the marginal distributions, and the remaining graphs illustrate the pairwise correlations. Based on the experimental observations, these figures suggest that, with increasing BF and SF, the strength characteristics (CBR and UCS) decrease. In contrast, the CGA increases, leading to reduced UCS and CBR values. Considering the pairs of variables, the experimental observations also suggest the existence of a negative correlation between SF and CGA. Hence, SF is inversely related to CGA. However, there is no tangible correlation between the three input attributes. These observations indicate that the effects of SF and CGA can be correlated, while BF does not correlate with other input variables. Noticeably, the effects of input variables on the predicted strength characteristics can be identified later based on the predictive SVM models. Noticeably, 225 entries of experimental observations have been incorporated into two portions to formulate the SVM-based models. After splitting the data randomly, 80% of the entries were used for training the models, whereas the remaining portion was used to test the predictions. These predictive models help to identify the influential variables on the prediction outputs (i.e., UCS and CBR).\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4. Results and Analysis","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e4.1 Microstructural characterization\u003c/h2\u003e\u003cdiv id=\"Sec13\" class=\"Section3\"\u003e\u003ch2\u003e4.1.1 Stereomicroscopic Images\u003c/h2\u003e\u003cp\u003eA series of microscopic surface images of soft soil is collected by using a stereomicroscope under varying magnifications. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e(a-d) illustrates the typical stereomicroscopic images for untreated soft soil, soil mixed with an alkaline binder, and AAM soil reinforced with fibers at varying CGA-SF content. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003ea illustrates areas of yellowish and light brown pigmentation in the untreated soft soil, which may be interpreted due to the presence of illite-smectite and iron groups. Additionally, irregular surface cracks are visible on the untreated soil, which will significantly impact the volumetric behavior when the water level fluctuates. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e(b) shows a thin layer of hardened AAM paste deposition around the cracks of the clay matrix. The bright and shiny regions may be due to the presence of mica from the silica fume. In contrast, the dark black colored patches are voids caused by early moisture evaporation from the solidified alkaline binder. The randomly distributed CTBF in the CGA-based AAM soil combination at 0 and 20% silica fume content is depicted in Figs.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e(c-d). Moreover, the morphology of CTBF reinforcement in the soil matrix has formed a spatially grooved network, which relatively enhances interlocking friction by restricting the clay. particles during load application. Adding CTBF is beneficial as it strengthens the interfacial bonding,\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eresulting in higher tensile and frictional resistance. As a result, the combined action of CTBF, CGA, and SF improves the load-bearing capacity and stiffness of AAM-stabilized soil, attributed to the development of an active pozzolanic matrix\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec14\" class=\"Section3\"\u003e\u003ch2\u003e4.1.2 Fourier Transform Infrared (FTIR) spectroscopy\u003c/h2\u003e\u003cp\u003eFTIR spectra for banana fiber before and after chemical treatment, untreated soft soil, and AAM stabilized soil at various coal gangue and silica fume dosages are shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e(a-b). The molecular bonding curves of untreated banana fibers (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003ea) are characterized by hydroxyl O-H stretching at around 3300 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e, mostly due to the presence of cellulose and water. Moreover, the untreated soil in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e(b) shows a sharp band of Portlandite [Ca (OH)\u003csub\u003e2\u003c/sub\u003e] at 3600 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e. The broadband of O-H water stretching (3600 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e) and C-H alcohol (3400 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e) was reduced in both coal gangue (100%) and silica fume (20%) based AAM treated soil relative to untreated soil. Also, the C-H methyl group at around 2950 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e showed the same peaks before and after chemical treatment of fibers (Mir et al. 2012). The C\u0026thinsp;=\u0026thinsp;O carbonyl functional group is not apparent at 2900 cm-1 as the replacement of coal gangue with silica fume increases in the AAM mixed soil. The pozzolanic reaction in silica-rich soil roughly characterizes this spectrum. The transmittance spectra for AAM-treated soil containing high coal gangue ash (100%) show the marginal peak of the =\u0026thinsp;CH2 bond compared to silica fume (20%) based AAM-treated soil. These modifications in soil chemical structures due to carbonation may be associated with minimal chemical weathering reactions on the clay surfaces (Syed et al. 2022). Interestingly, the symmetric stretching vibration of Si-O at 1030 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e remains identifiable even after the chemical treatment of fibers (Cesar dos Santos et al. 2016). A sharp characteristic band of Si-Al-O at 800 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e was observed in the untreated soil and the AAM mixed soil. Apart from that, the Si-O plane stretching vibration was identified in the range of wavenumbers around 580 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e. Thus, with a chemical shift of roughly 10\u0026ndash;20 cm\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e, the transmittance peaks from untreated fibers and AAM-treated soil reveal identical linkages.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec15\" class=\"Section3\"\u003e\u003ch2\u003e4.1.3 Thermogravimetric analysis (TGA)\u003c/h2\u003e\u003cp\u003eThermogravimetric (TG) and derivative thermogravimetric (DTG) analysis are used to calculate the stability of compounds and mass fractions against temperature. Figure\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e displays the TGA/DTG profiles of UBF and CTBF, focusing on mass reduction and its first derivative. An initial drop in mass was observed for both UBF and CTBF samples between 100\u0026ndash;150\u0026ordm;C, likely resulting from rapid evaporation of free water within the fiber matrix (Komal et al. 2020). The mass loss in UBF was found to be relatively higher (4\u0026ndash;5%) than in CTBF, which may be attributed to a greater decomposition rate of volatile components in the untreated fibers. Additionally, the TG/DTG trends for both UBF and CTBF overlapped due to cyclic thermal fluctuations. A second notable weight loss phase in UBF, occurring around 375\u0026ndash;400\u0026deg;C, is predominantly linked to thermal degradation of biomass, including the breakdown of hemicellulose and cellulose structures (Ferreira et al. 2015). Moreover, the substantial alterations in the thermal peak positions of CTBF indicate restructuring in the fiber surface chemistry, likely due to the formation of new chemical phases induced by Ca (OH)\u003csub\u003e2\u003c/sub\u003e treatment. Also, the minimized thermal degradation of CTBF is attributed to the encapsulation of fibers with calcium hydroxide on the surface (Varma and Mondal 2016). Beyond 500\u0026deg;C, TGA curves indicate negligible mass change and tend to exhibit asymptotic behavior.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003e4.2 Geotechnical characterization\u003c/h2\u003e\u003cp\u003eA series of geotechnical tests was performed on AAM-stabilized soil incorporating various CGA\u0026ndash;SF blend ratios. The corresponding geotechnical properties are presented in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\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\u003eGeotechnical results of AAM-soil at varying CGA-SF content\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=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\" morerows=\"1\" rowspan=\"2\"\u003e\u003cp\u003eProperties\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colspan=\"5\" nameend=\"c6\" namest=\"c2\"\u003e\u003cp\u003eS.A\u003csub\u003e6\u003c/sub\u003e\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e(C\u003csub\u003e100\u003c/sub\u003eF\u003csub\u003e0\u003c/sub\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003e(C\u003csub\u003e95\u003c/sub\u003eF\u003csub\u003e5\u003c/sub\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003e(C\u003csub\u003e90\u003c/sub\u003eF\u003csub\u003e10\u003c/sub\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e(C\u003csub\u003e85\u003c/sub\u003eF\u003csub\u003e15\u003c/sub\u003e)\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003e(C\u003csub\u003e80\u003c/sub\u003eF\u003csub\u003e20\u003c/sub\u003e)\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDry density (kN/m\u0026sup3;)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e16.75\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e17.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18.0\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e18.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMoisture content (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e18.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e18.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e18.0\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLinear shrinkage (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6.35\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e6.24\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6.39\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e6.59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e6.85\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003ePlasticity index(%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e19.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e17.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e17.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e16.9\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSwell index (%)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e30.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e28.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e27.9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e26.5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e25.1\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eSwell Pressure (kPa)\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e46.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e41.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e34.1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e31.2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e27.5\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cdiv id=\"Sec17\" class=\"Section3\"\u003e\u003ch2\u003e4.2.1 Consolidation\u003c/h2\u003e\u003cp\u003eSoil compressibility (relative to equilibrium void ratio) for soft soil, coal gangue ash-silica fume-based alkaline stabilized soil, is plotted against effective stress. The variance in initial void ratio curves for both untreated soil and AAM stabilized soils is presented graphically in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e. The trend of the void ratio plots illustrates the relationship between soil swelling behavior and the rate of applied seating load. During the early phase, untreated soft soil demonstrates a greater final void ratio compared to the alkaline-treated soil, as indicated by the e\u0026ndash;log(σ) response. This is due to the existence of active moisture retention around the clay matrix and also being rich in silica and iron-illite compounds, effectively delaying the moisture infiltration, thus requiring a longer time to reach an equilibrium swelling stage (Kayabali and Yaldiz 2012; Soltani et al. 2018). The addition of CGA-SF-based AAM stabilized soil aids in restricting the rate of void ratio effects (from 0.92 to 0.54); this marginal reduction may be due to the activation of the geopolymerization reaction in the clay composition, which adversely impacts the mineralogy. As the proportion of SF increases in place of CGA within the AAM blend, a significant reduction in volumetric expansion is observed. Notably, the combined incorporation of 20% SF and 80% CGA in the alkaline matrix results in a marked decrease in both void ratio and swelling across all AAM-stabilized soil compositions. Moreover, the drastic changes in and around the clay structure can also be substantially responsible for the drop in void ratio from 0.72 to 0.47 (20% SF-based AAM-soil). Through pozzolanic-ion consumption during active cementing gel formation, silica fume-based AAM stabilized surface particles may improve the interlocking bonding capacity of clay at low-effective stress applications (Chittoori et al., 2017; Meisina, 2007). Thus, in AAM mixed soil, creating consistent cementitious coatings with a new morphology reduces compressible behavior and the rate of void ratio reduction.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec18\" class=\"Section3\"\u003e\u003ch2\u003e\u003cb\u003e4.2.2 Unconfined compressive strength (UCS)\u003c/b\u003e\u003c/h2\u003e\u003cp\u003eThe UCS measurements of AAM-stabilized soil incorporating varying dosages of pozzolanic materials within the alkaline binder are illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e, which highlights the combined influence of fiber, coal gangue ash (CGA), and silica fume (SF) on strength enhancement in soft soil. A partial replacement of CGA (100\u0026ndash;90%) with SF (0\u0026ndash;10%) initially slows the development of compressive strength, which may be attributed to the low pozzolanic activity of silica and alumina present in CGA-based systems. As the content of SF and CTBF increases, the strength performance of AAM-treated soil improves progressively. This strength gain (from 620 kPa to 1260 kPa) is linked to the active geopolymerization reaction between clay particles and pozzolanic products in the alkaline matrix, leading to the formation of a denser microstructure (Ahmad et al., 2024; Alsafi et al., 2017; Syed et al., 2023a). The results also show that increasing the CTBF (0\u0026ndash;1%) improves soil shear strength from 1280 kPa (SA\u003csub\u003e6\u003c/sub\u003eC\u003csub\u003e100\u003c/sub\u003eF\u003csub\u003e0\u003c/sub\u003e) to 2160 kPa (SA\u003csub\u003e6\u003c/sub\u003eC\u003csub\u003e80\u003c/sub\u003eF\u003csub\u003e20\u003c/sub\u003e). The increasing UCS trends reveal strong interlock particle bonding between the fiber matrix and clay structures that indirectly benefit from the geopozzolanic reaction. Therefore, the cohesive strength of the AAM-stabilized soil is directly influenced by the combined presence of silica fume and CTBF\u003c/p\u003e\u003cp\u003eFigure \u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e(b) illustrates the shear strength ratio (SSR) behavior of AAM soil reinforced with CTBF across different CGA\u0026ndash;SF mix proportions. The SSR-based compressive strength analysis highlights the role of CTBF in enhancing confinement effects, primarily through increased interparticle friction and improved bonding within the alkaline-treated matrix, resulting in greater density and stiffness. When the soil matrix is stabilized using 100% CGA (with no SF), the CTBF\u0026ndash;AAM system attains an SSR range of approximately 2.0\u0026ndash;2.5. Similar SSR values (2.2\u0026ndash;3.0) have been reported by Park (2011) and Bekhiti et al. (2019) for waste rubber fiber-reinforced cementitious materials. In comparison, for kaolinite clay treated with 1% glass fiber and 1% polypropylene fiber, Maher and Ho (1995) and Rios et al. (2017) reported a maximum SSR of 1.2. As SF partially replaces CGA (up to 20%) in the mix, the SSR of the CTBF\u0026ndash;AAM system tends to align with the corresponding compressive strength, showing a value around 1.65. It is important to note that increasing CTBF dosage beyond 0.6% and SF content above 10% results in a modest improvement in the shear strength ratio. The increased dosage of the silica fume in the alkaline binder compound actively enhances the soil interbonding density between CTBF-AAM soils. Additionally, the addition of SF is beneficial to CGA-based AAM soil, as it actively produces calcium silicate gel from its available silica-calcium compounds, resulting in low soil moisture attraction around the CTBF-clay particles. This forms a dense bridge effect, characterized by strong particle-holding efficiency, and enhances the compressive shear resistance during geopolymerization. The rough surface of CTBF strongly holds the pozzolanic encapsulated clay particles, which are difficult to reorient, and can improve interlocking friction resistance against loading (Mazhar \u0026amp; Guharay, 2020; Tang et al., 2007). Thus, the active formation of geopolymerization in the SF-based CTBF-AAM soil can strengthen the ultimate pulling stress under strong linkage effects.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec19\" class=\"Section3\"\u003e\u003ch2\u003e\u003cb\u003e4.2.3 California Bearing Ratio (CBR)\u003c/b\u003e\u003c/h2\u003e\u003cp\u003eThe influence of pozzolanic precursors and alkaline activators on the performance enhancement of subgrade soil was analyzed through penetration resistance measurements. The soaked CBR tests will indirectly\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eprovide a clue to the efficiency of subgrade geomaterials under the long-term effect at different CTBF-CGA-SF proportions in the AAM-soil mixture. Figures\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003ea shows the variation in soaking CBR values for untreated soil and CTBF-reinforced AAM mixed soil under CGA replacement with SF proportionsAAM addition improved the penetration resistance of the soil from 2.28\u0026ndash;5.87%. The substantial improvement in CBR value achieved may be due to geopozzolanic activation during soaking (Syed et al., 2023b). The synthesis of silica fume between the CGA-fiber matrices induces an active multivalent cationic growth that minimizes clay compressibility (Moghal et al., 2018; Pourakbar \u0026amp; Huat, 2017; Priyadharshini et al., 2017; Shahbazi et al., 2017). Moreover, the formation of dense pozzolanic compounds within the silica-rich matrix significantly enhances the bonding of flocculated particles, leading to greater penetration-locking density. It is important to highlight that the combined use of 20% SF and 80% CGA in the alkaline binder results in a substantial improvement in penetration resistance, along with minimal swelling across all AAM-based CGA/SF mixtures. Additionally, Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e(b) presents the soaked CBR-derived resilient modulus values, which serve as a reliable indicator of subgrade soil stiffness. To minimize data clustering, only selected results for CTBF\u0026ndash;AAM-stabilized soil with CGA:SF ratios of 100:0, 90:10, and 80:20 are shown. The resilient modulus outcomes highlight the interaction between soil penetration resistance and specific slag content, particularly under higher PLF dosages in the treated soil. It reveals that the CTBF and SF proportions in CGA-based AAM composites play a key role in increasing subgrade strength and bearing resistance under regulated swell-shrinkage behavior. The resilient modulus trend of soil is similar to that of CBR penetration with the addition of binder and fiber to the soil. A significant increase in the CBR-based resilient modulus of AAM-stabilized subgrade soils was observed beyond 0.5% CTBF reinforcement, particularly within the 0.2\u0026ndash;0.4% PLF range when silica fume content exceeded 10% in the alkaline binder. Hence, geopolymerization driven by pozzolanic gels contributes to the formation of a bonded network around the CTBF\u0026ndash;AAM\u0026ndash;soil matrix, improving penetration resistance.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section2\"\u003e\u003ch2\u003e\u003cb\u003e4.3 Comparative efficiency of SVM-based predictive models\u003c/b\u003e\u003c/h2\u003e\u003cp\u003eFigures \u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e and \u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e12\u003c/span\u003e illustrate the regression plot between the experimental observations and forecasted outputs, showcasing the predictive outcomes of SVM-based modeling. Accordingly, two error measurement initiatives, namely residual error and training-testing errors, are also visualized to determine\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003ethe robustness of the SVM-based models. Upon comparing the prediction results, it is evident that the SVM optimization has a substantial impact on the predicted outputs. The testing R\u003csup\u003e2\u003c/sup\u003e values yielded from the SVM approach in the case of UCS and CBR models are improved by 270% and 220%, respectively, when optimized through grid search methods.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eThese improvements are also achieved by attaining R\u003csup\u003e2\u003c/sup\u003e of 0.95 (for UCS) and 0.965 (for CBR) in the GA approach, which corroborates the immense capabilities of both these optimization methods.\u003c/p\u003e\u003cp\u003e\u003cb\u003eError area analysis\u003c/b\u003e:\u003c/p\u003e\u003cp\u003eError areas are another type of visual measurement of the uncertainty in the case of predicted data. The difference between error area analysis and prediction error analysis (shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e, respectively) lies in the type of associated uncertainty. By propagating uncertainty through the input data and then performing predictions, error areas are determined. In contrast, the prediction error results in Figs.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e and \u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e only show the yielded error after prediction using the developed model, or how well the developed model can predict the outputs from the original data. As a result, this uncertainty analysis adds variability to the dataset, aiding in the assessment of how well the developed models generalize to unseen data.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTo carry out error area analysis, the standard deviation of the input entries is extended using a 95% confidence interval (CI), represented by the shaded regions. Broader error areas indicate less prediction certainty, while narrower areas imply more certainty. Moreover, Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e12\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e13\u003c/span\u003e depict the error area analysis during training and testing of GS-SVM and GA-SVM models predicting CBR and UCS, respectively. Evidently, the training of the models with deviated inputs is more certain, whereas testing is significantly sensitive to inputs having high standard deviation. Noticeably, the regression fit results of training for both GS-SVM and GA-SVM were R\u003csup\u003e2\u003c/sup\u003e of 0.9728 and 0.973, respectively. However, the testing results were slightly higher in the case of GA-SVM during testing, with an increase from R\u003csup\u003e2\u003c/sup\u003e of 0.9601 for GS-SVM to R\u003csup\u003e2\u003c/sup\u003e of 0.9645 for GA-SVM. These marginal differences, although not clearly visible in Figs.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e and \u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e imply the effect of the optimization using the Genetic algorithm.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eHence, the presence of such error area analysis can better highlight the importance of such tasks. As can be seen in Figs.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e and \u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e, the encircled areas in the testing plots of each figure indicate noticeable differences between the two different algorithms, as well as different predicted outputs. This observation further underscores the importance of error analysis with confidence intervals (CIs) compared to common regression plots, enabling the identification of models with robust performance more easily.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section2\"\u003e\u003ch2\u003e4.4 Comparative effects of input variables on the predicted output\u003c/h2\u003e\u003cp\u003eOne of the key advantages of predictive models is their ability to identify how input variables influence output parameters. However, earlier studies often failed to represent the significance and ranking of these variables clearly. The magnitude of these influences can be accurately evaluated only through sensitivity analysis techniques, such as feature importance or explainable AI approaches. SHAP (SHapley Additive exPlanations) is a modern sensitivity analysis method that enables the evaluation of individual variable effects on model predictions. This technique offers both global insights\u0026mdash;comparable to those provided by Sobol sensitivity analysis\u0026mdash;and local interpretability. SHAP values quantify the relative impact of each input feature on the predicted output, supporting a deeper understanding of both local and global prediction behaviors. The SHAP-based sensitivity results for outputs predicted by the optimized SVM models are illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e14\u003c/span\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eIt should be noted that despite the previous model analysis, the sensitivity results obtained via both GA-SVM and GS-SVM were almost identical. For the sake of brevity, only the results of GA-SVM are reported herein. It can be seen that BF is the governing input parameter affecting the output more than twice as much as the remaining variables. However, the predictive impacts of both CGA and SF on the predicted outcomes are almost identical. As shown earlier (in the preprocessing of the datasets via pair plots, i.e., Figs.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e), it is pertinent to mention that CGA and SF exhibit a strong negative relationship. As a result, the consequent effects are also somewhat similar. On the contrary, BF has no significant correlation with the remaining variables. These observations suggest that the variation would significantly alter the final strength values, given the current dosage and experimental plan. Furthermore, the effect of variables on the prediction of each distinct output is almost similar. Nevertheless, it is noteworthy to mention that each point in the SHAP plot represents the effect of variables on a set of data entries. Although the order of variable importance can be put as BF\u0026thinsp;\u0026gt;\u0026thinsp;CGA\u0026thinsp;\u0026ge;\u0026thinsp;SF, during the prediction of CBR values, the SHAP values are observed to be more scattered. This observation indicates that the inputs affect the prediction course of CBR comparatively more than the UCS. Hence, data measurement and preprocessing of CBR values require relatively more precision to prevent data measurement uncertainty.\u003c/p\u003e\u003c/div\u003e"},{"header":"5. Summary and Conclusions","content":"\u003cp\u003eThis research investigates the combined influence of CTBF reinforcement on soft soil stabilized with coal gangue ash and silica fume-based alkali-activated materials. The influence of CGA-SF proportions on consolidation and CTBF reinforcement on geomechanical strength performance indicators (compressive strength, shear strength ratio, CBR, and resilient modulus) of AAM stabilized soft soil was investigated. Furthermore, an optimal SVM model was developed to analyze the geomechanical strength behavior, including compressive shear and penetration resistance, of CTBF-AAM soil at various CGA-SF dosages. The key findings of this research are outlined in the conclusion section that follows.\u003c/p\u003e\u003cp\u003e\u003cul\u003e\u003cli\u003e\u003cp\u003eThe growth of geopolymeric cementitious gel around the CTBF-clay matrices is observed after AAM treatment (soil surface cracks and pores filling and forming a hardened AAM thin layer). Moreover, the addition of discrete CTBF alkaline soil has formed a spatial groove clay network structure, enhancing the soil-tensile interfacial density under strong interlocking friction.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe growth of new molecular bonds (Si-O-Si and Si-O-Al) linked to activating geopolymerization reactions. Also, in the CTBF, the C\u0026thinsp;=\u0026thinsp;O and \u0026ndash;CH2 alkene-lignin group is identified, corresponding to the carbonation reaction. In TGA/DTG measurement, the mass loss fraction of CTBF decreases compared to UBF, overcoming the early biodegradability of the material.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAt an optimal blend ratio of 80:20 (CGA to SF), the AAM-treated soil demonstrates improved volumetric stability by reducing the equilibrium void ratio by up to 68%. CTBF\u0026ndash;AAM composites also show enhanced penetration resistance and subgrade resilient modulus, achieving a 68% increase in CBR strength at the ideal fiber reinforcement level of 1%.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe shear strength ratio of AAM-treated soil decreases significantly when CGA is partially replaced with SF in the alkaline binder. Moreover, CTBF enhances the confinement bonding with dense cementitious layers surrounding it, achieving higher durability by preventing early biodegradation.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe improvement in unconfined compressive strength (UCS) was notable when CTBF, CGA, and SF were combined in the alkaline soil stabilizer. Additionally, the proposed SV model for geomechanical strength, in terms of UCS and CBR, exhibits the lowest error percentages (\u0026lt;\u0026thinsp;10%) regardless of CGA: SF content.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eThe regression fit results of training for both GS-SVM and GA-SVM were R2 of 0.9728 and 0.973, 536, respectively. However, the testing results were slightly higher in the case of GA-SVM during testing, with a 537 increase from R2 of 0.9601 for GS-SVM to R2 of 0.9645 for GA-SVM.\u003c/p\u003e\u003c/li\u003e\u003cli\u003e\u003cp\u003eAccording to SHAP analysis, the order of variable importance can be put as BF\u0026thinsp;\u0026gt;\u0026thinsp;CGA\u0026thinsp;\u0026ge;\u0026thinsp;SF; however, 539 during the prediction of CBR values, the SHAP values are observed to be more scattered. This observation 540 indicates that the inputs affect the prediction course of CBR comparatively more than the UCS.\u003c/p\u003e\u003c/li\u003e\u003c/ul\u003e\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCredit authorship contribution statement\u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp; \u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMazhar Syed\u003c/strong\u003e: Methodological Framework, Research Execution, and Writing \u0026ndash; Original Draft\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMohammed Ashfaq\u003c/strong\u003e: Idea Development, Supervision, and Critical Review of the Manuscript\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eBabak Jamhiri\u003c/strong\u003e: Conceptualization, Software Implementation, Analytical Modeling.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFazal E. Jalal:\u0026nbsp;\u003c/strong\u003eConceptualization, Review \u0026amp; editing.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eUmair Ali:\u003c/strong\u003e Conceptualization, Project administration, Resources, Supervision, Review, and editing.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Avaialability:\u003c/strong\u003e The datasets used and/or analysed during the current study available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConflicts of interest/Competing interests (include appropriate disclosures):\u0026nbsp;\u003c/strong\u003eNo conflict of interest\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgments:\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors gratefully acknowledge the support provided by the Deanship of Research at King Fahd University of Petroleum and Minerals (KFUPM) for facilitating this study. Special thanks are also extended to the Interdisciplinary Research Center for Construction and Building Materials for their valuable contribution toward the successful completion of this work.\u003c/p\u003e\n\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\n\u003cp\u003eM.S, M.A, and B.J wrote the main manuscript text and F.J prepared figures. U.A reviewed, edited and wrote. All authors reviewed the manuscript.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eAhmad, S., M. Shah Alam Ghazi, M. Syed, and M. A. Al-Osta. 2024. \u0026ldquo;Utilization of fly ash with and without secondary additives for stabilizing expansive soils: A review.\u0026rdquo; \u003cem\u003eResults Eng.\u003c/em\u003e, 22 (April): 102079. Elsevier B.V. https://doi.org/10.1016/j.rineng.2024.102079.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eAlsafi, S., N. Farzadnia, A. Asadi, and B. K. Huat. 2017. \u0026ldquo;Collapsibility potential of gypseous soil stabilized with fly ash geopolymer; characterization and assessment.\u0026rdquo; \u003cem\u003eConstr. Build. Mater.\u003c/em\u003e, 137: 390\u0026ndash;409. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2017.01.079.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eBekhiti, M., H. Trouzine, and M. Rabehi. 2019. \u0026ldquo;Influence of waste tire rubber fibers on swelling behavior, unconfined compressive strength and ductility of cement stabilized bentonite clay soil.\u0026rdquo; \u003cem\u003eConstr. Build. Mater.\u003c/em\u003e, 208: 304\u0026ndash;313. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2019.03.011.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eCesar dos Santos, J., T. H. Panzera, K. Strecker, A. Caldas, J. C. dos Santos, T. H. Panzera, and K. Strecker. 2016. \u003cem\u003eMECHANICAL PROPERTIES OF EPOXY BANANA FIBRE COMPOSITE TRATED WITH SODIUM CARBONATE\u003c/em\u003e.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eChittoori, B. C. S. Moghal, A. A. B. Pedarla, A. Al-Mahbashi, A. M. 2017. \u0026ldquo;Effect of Unit Weight on Porosity and Consolidation Characteristics of Expansive Clays.\u0026rdquo; \u003cem\u003eJ. Test. Eval.\u003c/em\u003e, 45 (1): 94\u0026ndash;104. https://doi.org/https://doi.org/10.1520/JTE20160451.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eFerreira, S. R., F. D. A. Silva, P. R. L. Lima, and R. D. Toledo Filho. 2015. \u0026ldquo;Effect of fiber treatments on the sisal fiber properties and fiber-matrix bond in cement based systems.\u0026rdquo; \u003cem\u003eConstr. Build. Mater.\u003c/em\u003e, 101: 730\u0026ndash;740. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2015.10.120.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eIRC:37-2018. 2018. \u0026ldquo;Guidelines for the design of flexible pavements (Fourth Revision). IRC 37-2018. New Delhi, India.\u0026rdquo; \u003cem\u003e2018\u003c/em\u003e, 1\u0026ndash;94.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eJangde, H., F. Khan, and A. Ghaffar. 2023. \u0026ldquo;Exploring the Correlation Between Compressive Strength and Hydraulic Conductivity in Soft Soil with Metakaolin as a Stabilizing Agent: An Experimental Study.\u0026rdquo; \u003cem\u003eInt. Conf. Interdiscip. Approaches Civ. Eng. Sustain. Dev.\u003c/em\u003e, 79\u0026ndash;89. Springer.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKayabali, K., and \u0026Ouml;. Yaldiz. 2012. \u0026ldquo;Investigation of the relationship between swell pressure and shrinkage limit.\u0026rdquo; \u003cem\u003eElectron. J. Geotech. Eng.\u003c/em\u003e, 17 P (May): 2313\u0026ndash;2325.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eKomal, U. K., V. Verma, T. Ashwani, N. Verma, and I. Singh. 2020. \u0026ldquo;Effect of Chemical Treatment on Thermal, Mechanical and Degradation Behavior of Banana Fiber Reinforced Polymer Composites.\u0026rdquo; \u003cem\u003eJ. Nat. Fibers\u003c/em\u003e, 17 (7): 1026\u0026ndash;1038. Taylor and Francis Inc. https://doi.org/10.1080/15440478.2018.1550461.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eLuo, Z., and B. Zhang. 2023. \u0026ldquo;Effect of humic acid and fulvic acid on mechanical and durability properties of geopolymer stabilized soft soil.\u0026rdquo; \u003cem\u003eConstr. Build. Mater.\u003c/em\u003e, 409: 133875. Elsevier.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMaher, M. H., and Y. C. Ho. 1995. \u0026ldquo;Mechanical Properties of Kaolinite/Fiber Soil Composite.\u0026rdquo; \u003cem\u003eJ. Geotech. Eng.\u003c/em\u003e, 120 (8): 1381\u0026ndash;1393.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMazhar, S., and A. Guharay. 2020. \u0026ldquo;Stabilization of expansive clay by fibre-reinforced alkali-activated binder : an experimental investigation and prediction modelling.\u0026rdquo; \u003cem\u003eInt. J. Geotech. Eng.\u003c/em\u003e, 15 (2020): 1\u0026ndash;17. https://doi.org/10.1080/19386362.2020.1775358.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMeisina, C. 2007. \u0026ldquo;Swelling-shrinking properties of weathered clayey soils associated with shallow landslides.\u0026rdquo; \u003cem\u003eQ. J. Eng. Geol. Hydrogeol.\u003c/em\u003e, 37 (2): 77\u0026ndash;94. https://doi.org/10.1144/1470-9236/03-044.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMiller, S. A., W. V. Srubar, S. L. Billington, and M. D. Lepech. 2015. \u0026ldquo;Integrating durability-based service-life predictions with environmental impact assessments of natural fiber-reinforced composite materials.\u0026rdquo; \u003cem\u003eResour. Conserv. Recycl.\u003c/em\u003e, 99: 72\u0026ndash;83. https://doi.org/10.1016/j.resconrec.2015.04.004.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMir, S. S., S. M. N. Hasan, M. J. Hossain, and M. Hasan. 2012. \u0026ldquo;Chemical modification effect on the mechanical properties of coir fiber.\u0026rdquo; \u003cem\u003eEng. J.\u003c/em\u003e, 16 (2): 73\u0026ndash;83. https://doi.org/10.4186/ej.2012.16.2.73.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eMoghal, A. A. B., B. C. S. Chittoori, and B. M. Basha. 2018. \u0026ldquo;Effect of fibre reinforcement on CBR behaviour of lime-blended expansive soils: reliability approach.\u0026rdquo; \u003cem\u003eRoad Mater. Pavement Des.\u003c/em\u003e, 19 (3): 690\u0026ndash;709. Taylor \u0026amp; Francis. https://doi.org/10.1080/14680629.2016.1272479.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePark, S. S. 2011. \u0026ldquo;Unconfined compressive strength and ductility of fiber-reinforced cemented sand.\u0026rdquo; \u003cem\u003eConstr. Build. Mater.\u003c/em\u003e, 25 (2): 1134\u0026ndash;1138. Elsevier Ltd. https://doi.org/10.1016/j.conbuildmat.2010.07.017.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePourakbar, S., and B. K. Huat. 2017. \u0026ldquo;A review of alternatives traditional cementitious binders for engineering improvement of soils.\u0026rdquo; \u003cem\u003eInt. J. Geotech. Eng.\u003c/em\u003e, 11 (2): 206\u0026ndash;216. https://doi.org/10.1080/19386362.2016.1207042.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003ePriyadharshini, P., K. Ramamurthy, and R. G. Robinson. 2017. \u0026ldquo;Excavated soil waste as fine aggregate in fly ash based geopolymer mortar.\u0026rdquo; \u003cem\u003eAppl. Clay Sci.\u003c/em\u003e\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eRios, S., C. Ramos, and C. Viana da Fonseca, Ant\u0026oacute;nio Cruz, Nuno. \u0026amp; Rodrigues. 2017. \u0026ldquo;Mechanical and durability properties of a soil stabilised with an alkali-activated cement.\u0026rdquo; \u003cem\u003eEur. J. Environ. Civ. Eng.\u003c/em\u003e, 8189 (January): 1\u0026ndash;23. Taylor \u0026amp; Francis. https://doi.org/10.1080/19648189.2016.1275987.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eShahbazi, M., M. Rowshanzamir, S. M. Abtahi, and S. M. Hejazi. 2017. \u0026ldquo;Optimization of carpet waste fibers and steel slag particles to reinforce expansive soil using response surface methodology.\u0026rdquo; \u003cem\u003eAppl. Clay Sci.\u003c/em\u003e https://doi.org/10.1016/j.clay.2016.11.027.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSoltani, A., A. Deng, and A. Taheri. 2018. \u0026ldquo;Swell\u0026ndash;compression characteristics of a fiber\u0026ndash;reinforced expansive soil.\u0026rdquo; \u003cem\u003eGeotext. Geomembranes\u003c/em\u003e, 46 (2): 183\u0026ndash;189. Elsevier. https://doi.org/10.1016/j.geotexmem.2017.11.009.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSyed, M., M. Ahuja, A. R. Jambholkar, and A. GuhaRay. 2022. \u0026ldquo;Laboratory Investigation on Fiber-Reinforced Expansive Subgrade Soil Stabilized with Alkali Activated Binder: A Reliability-Based Perspective.\u0026rdquo; \u003cem\u003eGeo-Congress 2022\u003c/em\u003e, 241\u0026ndash;250.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSyed, M., A. GuhaRay, S. K. Chukka, and S. Ahmad. 2024. \u0026ldquo;A laboratory investigation and numerical modeling on fiber reinforced lime and alkaline binder stabilized pavement subgrade soil.\u0026rdquo; \u003cem\u003eCase Stud. Constr. Mater.\u003c/em\u003e, 20 (January): e03000. Elsevier Ltd. https://doi.org/10.1016/j.cscm.2024.e03000.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSyed, M., A. GuhaRay, and A. Garg. 2021. \u0026ldquo;Performance evaluation of lime, cement and alkali-activated binder in fiber-reinforced expansive subgrade soil: A comparative study.\u0026rdquo; \u003cem\u003eJ. Test. Eval.\u003c/em\u003e, 51 (1). https://doi.org/10.1520/JTE20210054.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSyed, M., A. GuhaRay, and S. Raju. 2023a. \u0026ldquo;Subgrade Strength Performance Behavior of Alkali-Activated Binder and Cement Stabilized Expansive Soil: A Semifield Study.\u0026rdquo; \u003cem\u003eJ. Mater. Civ. Eng.\u003c/em\u003e, 35 (10): 1\u0026ndash;11. https://doi.org/10.1061/jmcee7.mteng-15580.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eSyed, M., A. A. B. Moghal, and B. Chittoori. 2023b. \u0026ldquo;Reliability Analysis of Polyvinyl Alcohol Fiber-Reinforced Soft Subgrade Soil Treated with Lime and Alkali Activated Stabilizer: A Comparative Study.\u0026rdquo; \u003cem\u003eGeo-Congress 2023\u003c/em\u003e, 422\u0026ndash;432. ASCE.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eTang, C., B. Shi, W. Gao, F. Chen, and Y. Cai. 2007. \u0026ldquo;Strength and mechanical behavior of short polypropylene fiber reinforced and cement stabilized clayey soil.\u0026rdquo; \u003cem\u003eGeotext. Geomembranes\u003c/em\u003e, 25 (3): 194\u0026ndash;202. https://doi.org/10.1016/j.geotexmem.2006.11.002.\u003c/span\u003e\u003c/li\u003e\u003cli\u003e\u003cspan\u003eVarma, A. K., and P. Mondal. 2016. \u0026ldquo;Physicochemical Characterization and Pyrolysis Kinetic Study of Sugarcane Bagasse Using Thermogravimetric Analysis.\u0026rdquo; \u003cem\u003eJ. Energy Resour. Technol.\u003c/em\u003e, 138 (5): 1\u0026ndash;11. https://doi.org/10.1115/1.4032729.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Soft soil, Banana Fiber reinforcement, Alkaline Activated material, shear strength ratio, support vector model","lastPublishedDoi":"10.21203/rs.3.rs-7526534/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7526534/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe periodic variations (heave/shrink) in soft soil can lead to extensive damage to lightweight structures, resulting in an annual loss of several billion dollars. Although well-known traditional stabilizers can effectively regulate soil volumetric stability and compressibility, their production can have a massive environmental impact. This paper investigates the geomechanical efficiency of soft soil reinforced with chemically treated banana fiber (CTBF) and EnviroSafe alkaline-activated materials (AAM), which are composed of alkaline solutions and industrial waste materials. The proportions of coal gangue ash (CGA) replacement with silica fume (SF : 0\u0026ndash;20%) were varied in the alkaline solution by maintaining a 0.4 water-to-solid ratio. A series of consolidation compressive shear, and penetration resistance tests were performed to determine the geomechanical properties, including resilient modulus (\u003cem\u003eM\u003c/em\u003e\u003csub\u003e\u003cem\u003eR\u003c/em\u003e\u003c/sub\u003e), shear strength ratio, Stereoscopic, Fourier-transform infrared (FTIR) spectroscopy, and Thermogravimetry analysis (TGA) tests at varying CTBF-SF mixture dosages. The study proposed an optimal dosage of CGA-SF in AAM-stabilized soft soil. It demonstrated a substantial improvement in California Bearing Ratio (CBR) penetration and Unconfined Compressive Strength (UCS) tests. The results of silicafume (\u0026gt;\u0026thinsp;10%) in CGA-based AAM stabilizer soil attained the lowest equilibrium void ratio over the unreinforced soil. Furthermore, a support vector machine (SVM) algorithm model was proposed to predict the geomechanical strength of fiber-reinforced alkaline soil, and the results showed an excellent predictor of geomechanical strength performance.\u003c/p\u003e","manuscriptTitle":"Sustainable Engineering of Fiber-Reinforced Coal Gangue Linking Geomechanics and Microstructure through Support Vector Machines","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 09:28:02","doi":"10.21203/rs.3.rs-7526534/v1","editorialEvents":[{"type":"communityComments","content":1},{"type":"decision","content":"Revision requested","date":"2025-10-09T07:37:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-09T06:46:29+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-06T06:58:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-26T14:33:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"98663724707523226855003281605828489624","date":"2025-09-25T06:59:07+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"37444994955605414816721628209417519487","date":"2025-09-21T06:04:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"181317946579775184350829532365873133363","date":"2025-09-21T06:04:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-19T02:31:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"194838716310395693138977594990751391721","date":"2025-09-10T13:01:48+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-10T07:16:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-10T07:15:43+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-10T04:17:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-07T06:22:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-07T06:19:36+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1f0f7826-863b-463d-8d23-10df536ff315","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54651485,"name":"Physical sciences/Engineering"},{"id":54651486,"name":"Earth and environmental sciences/Environmental sciences"},{"id":54651487,"name":"Physical sciences/Materials science"}],"tags":[],"updatedAt":"2025-12-29T15:59:10+00:00","versionOfRecord":{"articleIdentity":"rs-7526534","link":"https://doi.org/10.1038/s41598-025-28438-z","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-23 15:57:04","publishedOnDateReadable":"December 23rd, 2025"},"versionCreatedAt":"2025-09-17 09:28:02","video":"","vorDoi":"10.1038/s41598-025-28438-z","vorDoiUrl":"https://doi.org/10.1038/s41598-025-28438-z","workflowStages":[]},"version":"v1","identity":"rs-7526534","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7526534","identity":"rs-7526534","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}