Use of an Artificial Neural Network and Multiple Linear Regression for the Prediction of the Asymptotic Gas Production of Agricultural By-products

Use of an Artificial Neural Network and Multiple Linear Regression for the Prediction of the Asymptotic Gas Production of Agricultural By-products | 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 Use of an Artificial Neural Network and Multiple Linear Regression for the Prediction of the Asymptotic Gas Production of Agricultural By-products S. Ghasemi, M. Behgar, M. Vatandoust, P. Vahmani This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6453740/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract This study evaluated the correlation between chemical composition and asymptotic in vitro gas production (AGP) of various agricultural by-products. In addition, it attempted to use artificial neural network (ANN) and multiple linear regression (MLR) approaches to predict AGP based on the chemical composition of these by-products. Two data sets were used in the study. The first dataset (training) consisted of published data, while the second dataset (testing) consisted of the chemical composition and asymptotic gas production of selected by-products. First, the chemical composition and AGP of the selected by-products were measured. The two data sets were then pooled and processed for cluster analysis. Multivariate cluster analysis revealed two distinct groups (A & B) with a degree of similarity among the by-products within each group exceeding 80% and 90%, respectively. The selected by-products were categorized into cluster A, so this cluster was considered for Pearson correlation and modeling analysis. Negative correlations were observed between AGP and NDF and ADF. Conversely, positive correlations were found between OM and CP of agricultural by-products and AGP. The ANN showed superior performance in predicting asymptotic gas production (b) compared to the MLR model, as indicated by lower root mean square error (RMSE) and higher r 2 . Biological sciences/Plant sciences Biological sciences/Plant sciences/Natural variation in plants Agricultural by-products gas production neural networks cluster analysis multilinear regression prediction Figures Figure 1 Figure 2 Figure 3 Introduction In recent years, researchers have shown great interest in using gas production (GP) methods instead of in situ and in vitro methods to evaluate the nutritional value of feedstuffs. This method has many advantages over other methods 1 . In addition, several equations can be used to estimate dry matter (DM) intake, metabolizable energy, organic matter (OM) digestibility 2 , and short-chain fatty acid production 1 from GP data. Several studies have reported high correlations between total gas production and feed intake 3 , digestible DM, and animal growth 4 . In addition, high correlations have been found between GP kinetics (b and k) and feed intake or DM digestibility 5 , 6 . Many studies have reported a relatively high correlation between GP kinetics and chemical fractions in oats and pasture grasses 7 – 9 . In addition, some efforts have been made to develop GP prediction equations using forage chemical fractions 9 , where linear prediction models were developed to estimate GP rate and fermented OM from forage chemical fractions. Artificial neural networks (ANNs) are computational algorithms designed to simulate the behavior of biological systems composed of "neurons". Unlike traditional regression, ANNs work well with linear and nonlinear data 10 . The use of ANNs in ruminant studies has recently gained interest, especially when the relationships between input and output variables are either unknown or highly complex 11 , 12 . It has been reported that the ANN can successfully predict the molar fraction of rumen volatile fatty acid (VFA) using milk FA profiles 13 and rumen passage rate 14 . The ANN was more accurate than multiple linear regression in predicting VFA production in the GP test using carbohydrate fractions as independent variables 15 . However, there are few studies on ANN modeling of feed GP. Therefore, this study aimed to evaluate the use of ANN and MLR for predicting GP kinetics using the chemical composition of agricultural by-products. Material and Methods Datasets Two datasets were used in the study. In the first dataset (training), a total of 64 scientific papers were identified and initially screened for acceptability by checking that all publications reported chemical composition (including organic matter: OM, crude protein: CP, neutral detergent fiber: NDF, acid detergent fiber: ADF, and hemicellulose: HemCel) and asymptotic gas production (b) of the feedstuffs/by-products. Experiments that conducted gas production tests using bovine rumen fluid instead of sheep rumen fluid were excluded from the database, as were studies that did not use the Menk and Stingase 2 method for gas production testing. After discarding 48 of the 64 papers, a baseline dataset was constructed comprising 16 articles with 42 observations (Table 1 ). Chemical compounds were converted to percentages and gas produced to ml/200 mg dry matter to harmonize the data. Table 1 Summary of the training datasets. Feedstuffs/by-products ID OM CP NDF ADF HemCel AGP References Linseed straw OB1 74.05 3.61 84.58 71.14 13.44 14.98 16 Date stone OB2 88.23 7.27 61.35 44.21 17.14 46.69 16 Sugarcane bagasse OB3 97.9 1.29 77.00 47.60 29.40 39.46 16 Dussa OB4 93.61 2.17 68.59 46.92 21.67 41.33 17 Cowpea pod OB5 92.36 12.25 71.44 52.35 19.09 34.33 17 Maize offal OB6 92.47 2.54 69.68 51.74 17.94 37.00 17 Vigna sinensis hay OB7 88.2 14.40 60.80 45.10 15.70 42.10 18 Acacia nilotica (leaves) OB8 87.6 14.50 69.50 46.80 22.70 40.90 18 Ziziphus nummularia (leaves) OB9 87.4 14.00 65.70 47.30 18.40 37.90 18 Wheat straw OB10 87.56 5.07 73.48 45.93 27.55 41.30 19 Juniperus communis OB11 94.33 5.62 56.98 34.22 22.76 51.92 20 Dillenia spp. OB12 90.14 9.59 53.33 41.70 11.63 42.03 21 Corn straw OB13 92.97 4.59 79.26 46.54 32.72 45.16 19 Pomegranate seed OB14 88.80 11.20 64.00 46.00 18.00 48.59 22 Corn cob OB15 87.70 3.00 66.50 48.80 17.70 64.60 23 Fresh pangola OB16 89.30 8.14 62.60 36.00 26.60 54.00 24 Pangola hay OB17 91.50 8.05 63.50 36.90 26.60 50.80 24 Pangola silage OB18 86.70 8.24 61.30 34.60 26.70 57.30 24 Saccharum officinarum (leaves) OB19 94.80 2.30 69.80 48.20 21.60 27.80 25 Andropogon gayanus (leaves) OB20 88.10 4.40 57.90 41.00 16.90 46.60 25 Napier grass OB21 89.60 7.60 59.60 33.10 26.50 47.30 24 Sorghum straw OB22 93.00 4.30 61.40 38.60 22.80 49.00 25 Gundelia tournefortii OB23 68.30 5.24 62.54 48.07 14.47 51.57 8 Finger millet straw OB24 92.68 3.04 65.05 38.54 26.51 53.06 26 Barley straw OB25 92.56 4.22 72.73 53.23 19.50 43.79 6 Rice straw OB26 87.34 4.56 71.45 44.65 26.80 46.74 19 Berseem hay OB27 88.80 15.32 54.90 38.31 16.59 50.92 16 Descurania Sophia OB28 81.80 11.95 49.52 39.06 10.46 44.58 8 Chick pea OB29 91.6 11.70 52.00 34.80 17.20 60.90 27 Tifton hay OB30 93.34 4.81 77.79 41.76 36.03 45.10 28 Pineapple silage OB31 93.74 8.90 59.51 38.10 21.41 24.59 28 Lemon pulp OB32 94.54 9.54 16.69 15.13 1.56 43.60 29 Grapefruit pulp OB33 94.13 9.14 16.66 13.09 3.57 44.39 29 Lime pulp OB34 91.88 8.16 17.49 14.53 2.96 44.04 29 Orange pulp OB35 94.49 8.5 14.74 11.95 2.79 40.96 29 Taraxacum officinale OB36 92.71 24.64 40.84 26.17 14.67 28.20 26 Cottonseed meal OB37 93.11 43.15 27.34 16.20 11.14 48.20 26 Groundnut meal OB38 94.10 39.09 29.87 10.92 18.95 51.20 26 Rapeseed meal OB39 91.80 37.72 27.46 15.05 12.41 48.20 26 Sesame cake OB40 87.96 29.55 32.61 17.84 14.77 45.60 26 Soybean meal OB41 92.42 47.52 22.67 11.05 11.62 59.20 26 Sunflower meal OB42 94.77 27.93 48.91 29.78 19.13 35.90 26 OM: organic matter, CP: crude protein, EE: ether extract, NDF: neutral detergent fiber, ADF: acid detergent fiber, HemCell: Hemi-cellulose. AGP: Asymptotic gas production. The second database (dataset 2) consisted of the chemical composition (OM, CP, NDF, ADF, and HemCel) and asymptotic gas production of selected agricultural by-products, including soybean hulls (SBH), soybean mill run (SBMR), cottonseed hulls (CSH), sunflower hulls (SFH), and sugar beet pulp (SBP). Samples were analyzed in duplicate for crude protein (CP), organic matter (OM), and ether extract (EE) according to AOAC 30 . Neutral detergent fiber (NDF) and acid detergent fiber (ADF) were determined according to Vansoest et al. 31 . Hemicellulose was determined by subtracting NDF from ADF. Rumen fluid was collected from the three cannulated sheep and pressed through four layers of cheesecloth. GP was measured at 2, 4, 6, 8, 12, 24, 48, 72, and 96, and a series of corresponding blanks (i.e., without samples) were included, followed by calculation of the gas produced from each treatment by subtracting the gas produced from the gas produced in control blank 2 . Statistical analysis and models The volume of GP (ml/200 mg DM) was fitted to the model using the NLIN procedure of SAS (2011): G = b × (1 - e − kt ), where G, b, and k represent the volume of GP at time t, the asymptotic GP (ml per 200 mg DM), and the rate of GP h − 1 from the slowly fermentable feed fraction b, respectively. Multivariate hierarchical cluster analysis was performed on the pooled data sets (data sets 1 and 2) using Ward's method with SAS statistical software 32 to group the feedstuff based on chemical composition and asymptotic GP (b). The graph shows the distances between the clusters. The PROC CORR statement was used in SAS 32 to display Pearson linear correlation coefficients between the variables examined in the pooled dataset. The PROC REG statement was used in SAS 32 to predict the asymptotic GP (b). Stepwise multiple regression was performed by including the most significant data sets in the model, and the significance level was set at P ≤ 0.01. The ANN modeling process was performed using RapidMiner software (version 9.3.001) with the Deep Learning operator. Deep learning is based on a multi-layer feed-forward ANN trained with stochastic gradient descent using back-propagation. The deep network used in the current study consisted of three layers of nodes: the input layer, a hidden layer, and an output layer. The number of hidden layers was determined by trial and error. For the current study, one hidden layer was used, and the Maxout activation function was implemented in each neuron of this hidden layer. Early stopping was enabled to avoid overfitting. The first data set was used for training, and the second data set was used for testing. The Performance operator was utilized to statistically evaluate the performance of the model and deliver a list of performance criteria values. Results and Discussions The chemical composition of selected feedstuff is shown in Table 2 . The CP content varied among the by-products, with SBMR having the highest values (20.49% of DM) due to a relatively high proportion of seed meat. The chemical composition of SH and SHMR was within the range reported by Ipharraguerre and Clark 33 . Higher levels of NDF were observed for GPH, SFH and CSH, while lower levels were observed for SBMR and SBP. The same pattern was observed for ADF. Table 2 Dataset 2-Chemical composition (Mean ± SD) of selected agricultural by-products (% of DM). OM CP NDF ADF HemCel SBH 99.50 ± 0.05 9.36 ± 0.10 69.45 ± 0.35 51.35 ± 0.35 18.30 ± 0.00 SBMR 93.80 ± 0.20 20.49 ± 0.54 49.65 ± 0.15 39.05 ± 0.25 10.06 ± 0.40 CSH 79.05 ± 1.75 5.50 ± 0.53 84.10 ± 0.50 69.02 ± 0.50 11.90 ± 0.00 SFH 79.95 ± 5.75 3.51 ± 0.01 88.15 ± 0.05 68.50 ± 0.90 19.65 ± 0.85 SBP 98.50 ± 0.20 9.96 ± 0.08 48.65 ± 0.05 25.95 ± 0.75 22.70 ± 0.99 GPH 95.90 ± 0.28 4.79 ± 0.08 89.15 ± 0.50 76.75 ± 0.50 12.40 ± 0.99 SD: Standard deviation, OM: organic matter, CP: crude protein, EE: ether extract, NDF: neutral detergent fiber, ADF: acid detergent fiber, HemCell: Hemi-cellulose. SBH: soybean hull, SBMR: soybean mill run, CSH: cottonseed hull, SFH: sunflower hull, SBP: sugar beet pulp, GPH: ground peanut hull. Gas production assay The GP trend of the agricultural by-products (Dataset 2) is shown in Fig. 1 . The agricultural by-products also behaved differently regarding the rate at which they produced gas. Table 3 shows the total gas produced by the incubation of selected agricultural by-products at different times and the corresponding GP kinetics (b and k). In the present study, selected agricultural by-products had a wide range of produced gas from 26.10 to 107.29 ml after incubation for 96 h. Soybean hulls and SBMR had the highest values of produced gas at 96 h, but GPH, SFH, and CSH had the lower produced gas. The same trends were observed for incubation at 24 and 72 hours. Table 3 Gas volume and gas production kinetics (mean ± sd) of selected agricultural by-products. Agricultural by-products SBH SBMR CSH SFH SBP GPH Gas volume (ml/200 mg DM) 24 h 85.21 ± 12.63 79.75 ± 7.86 22.50 ± 2.65 22.06 ± 2.16 86.93 ± 10.27 17.75 ± 5.74 72 h 105.29 ± 15.45 100.85 ± 6.06 52.10 ± 3.63 32.50 ± 3.78 105.63 ± 11.03 24.58 ± 6.86 96 h 107.29 ± 15.42 102.90 ± 5.66 57.5 ± 6.15 33.6 ± 3.59 108.25 ± 11.00 26.1 ± 6.89 Gas production kinetics (96 h) AGP (ml) 107.01 ± 18.80 102.38 ± 5.85 76.30 ± 15.20 33.40 ± 4.41 104.41 ± 11.22 25.01 ± 6.07 k (% h − 1 ) 0.069 ± 0.020 0.063 ± 0.010 0.017 ± 0.005 0.047 ± 0.005 0.092 ± 0.010 0.060 ± 0.020 SBH: soybean hull, SBMR: soybean mill run, CSH: cottonseed hull, SFH: sunflower hull, BP: pistachio by-product, SBP: sugar beet pulp, GPH: ground peanut hull. Cluster Analysis The results of the cluster analysis on the pooled data sets (1 & 2) are shown in Fig. 2 . The graph shows that the samples were grouped into two clusters (A & B), with the degree of similarity among the by-products within each group being greater than 80% and 90% for clusters A and B, respectively. Group (A) included OB1-31; and SBH, SBMR, CSH, SFH, SBP, GPH (data set 2). Cluster B grouped OB32-44. Cluster A discriminated from Group B with a similarity of 55%. Group B included lemon pulp, grapefruit pulp, lime pulp, orange pulp, Taraxacum officinale, cottonseed meal, peanut meal, rapeseed meal, sesame cake, soybean meal, sunflower meal, and chickpea. It has been shown that cluster analysis can successfully classify agricultural by-products based on their chemical composition and fermentation characteristics 34 . In the present study, cluster B consisted of feeds with low cell wall content or, in the case of meals, high protein content. Group A included dataset 2 and the rest of the by-products from dataset 1. Bizzuti et al. 35 classified agricultural by-products into a clear cluster with 3 distinct groups based on chemical composition, in vitro gas production, organic matter degradability, and ruminal fermentation kinetics. Table 4 shows the correlation coefficients of chemical composition with produced gas potential (b) on cluster A. Negative correlations (P < 0.01) were observed between asymptotic gas production (b) with NDF and ADF. The negative correlation between AGP and cell wall components (NDF and ADF; 0.47 and 0.41, respectively) in the present study is consistent with previous studies 8 ,34 . Kafilzadeh and Heidary 7 examined 18 different oat cultivars and found a significant negative correlation between NDF (r = 0.48) and ADF (r = 0.83) with AGP or gas production rate. Although lignin was not examined in this study, much of the adverse effect of cell wall components on gas production may be due to the presence of lignin in NDF and ADF. Lignin forms a physical barrier that reduces the access of rumen microbes to fermentable cell wall components. Studies have shown a powerful and negative correlation between GP kinetics and ADL content of agricultural co-products 9 , 36 . Table 4 Correlation of chemical composition with AGP. AGP OM 0.32* CP 0.37* NDF -0.47** ADF -0.41** HemCell -0.04 OM: organic matter, CP: crud protein, NDF: Neutral detergent fiber, ADF: acid detergent fiber, HemCel: hemi-cellulose, AGP: Asymptotic gas production. * P < 0.0, **P < 0.01 It has been reported that cumulative in vitro gas production after 12–48 h of fall-oat diets was negatively correlated with NDF, hemicellulose, lignin, and ash 37 . These findings are further supported by the data from the present study, which indicates that by-products with the highest levels of cell wall content exhibited the lowest gas production. (see Tables 2 and 3 ). There were positive correlations (P < 0.05) between OM and CP of agricultural by-products and asymptotic gas production (b). Similarly, the results of Kulivand and Kafilzadeh 8 showed a positive correlation between the CP content of pasture grasses with asymptotic GP and the rate of GP after 96 h of incubation. Similarly, Nherera et al. 35 observed a positive and significant correlation between the nitrogen content of some diets and GP kinetics (b and k) after 96 h of incubation. It has been reported that the minimum CP concentration to support microbial activity is %7 of DM 38 . Interestingly, in the present study, co-products with CP content below this level (i.e., CSH, SFH, and GPH) had the lowest cumulative GP. Model Development The input data utilized for the MLR and ANN modeling were confined to cluster A. The multiple linear regression (MLR) model for AGP and the statistical parameters for the ANN and MLR models are summarized in Table 5 . Asymptotic gas production (AGP) was explained by multiple regression equations using OM, CP, and NDF as independent variables (r 2 = 0.23). The r 2 and RMSE for predicting b using ANN were 0.70 and 5.39, respectively. Based on the comparison of the results of the ANN with those of the MLR model, the ANN performed better with lower RMSE and higher r 2 . Table 5 Statistics and information of ANN and MLR models for asymptotic gas production. Model b = 26.06 + OM0.62 + CP0.78-NDF0.57 - Root Mean Squared Error 18.36 5.39 R 2 0.23 0.70 When the number of nodes in the hidden layer was set to 13 and b was treated as a single output variable in the model, the lower RMSE and higher r 2 for predicting b were observed. Dong and Zhao 15 concluded that the number of neurons in the hidden layer affected the performance of ANN models for predicting ruminal VFA production. In the present study, the number of neurons was selected by trial and error, and the model with the lowest RMSE and highest R 2 was chosen as the best model. Fadare and Babayemi 39 reported a higher R value with a lower standard deviation in neural network models with one hidden layer compared to two. In the current study, the number of hidden layers was set to one because a single hidden layer ANN can approximate any function as long as enough neurons are used. MLR modeling is an ideal tool for identifying linear relationships between different parameters. Nherera et al. 35 found a higher correlation of dietary NDF and nitrogen with in vitro AGP at 24 h than at 96 h. They used simple and multiple linear equations to predict in vitro AGP based on dietary chemical composition, and they reported a higher R for predicting gas at 24 h than at 96 h (0.90 and 0.80, respectively). Similarly, Marcos et al. 9 reported that carbohydrates (sugars and NDF) could be used to predict in vitro ruminal GP and OM fermentation of olive cake. MLR modeling is based on the assumption of a linear relationship between dependent and independent variables. However, in most cases, the data is complex and not linear 15 . For this reason, in some cases, models developed using ANN perform better than MLR models, as seen in the present study. It has been reported that CNCPS carbohydrate fractions can be effectively utilized as inputs to predict in vitro rumen gas production (GP) using MLR, as well as for estimating acetate, propionate, butyrate, and total VFA production through both MLR and ANN approaches 15 . In this study, ANN models performed better than MLR models. The superior performance of ANN models over MLR has also been documented in estimating milk production 40 , goat body weight gain 41 , and nutrient content of dairy manure 42 . Conclusion The results of the present study indicated that the feedstuff's chemical composition was suitable for predicting in vitro AGP. Based on the results of the present study, deep learning models showed better performance for predicting AGP than MLR models. Further studies are needed to improve the prediction accuracy and to apply this prediction model to a wider range of samples and feedstuffs. Declarations Author Contribution S.G. and M.B. wrote the main manuscript text.M.V. Analyzed the data and prepared Tables and Figs.P.V. Revised the final draft of the manuscript.All authors reviewed the final manuscript. Data Availability The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request. References Getachew, G., Blummel, M., Makkar, H. P. S. & Becker, K. In vitro gas measuring techniques for assessment of nutritional quality of feeds: a review. Anim Feed Sci Technol. 72 , 261-281 (1998). Menke, K.H. and Steingass, H. Estimation of the energetic feed value from chemical analysis and in vitro gas production using rumen fluid. Anim Res Dev. 28 , 7-55 (1988). Hetta, M., Cone, J. W., Bernes, G., Gustavsson, A-M. & Martinsson, K. Voluntary intake of silages in dairy cows depending on chemical composition and in vitro gas production characteristics. Livest Sci. 106 , 47-56 (2007). Blummel, M., Ørskov, E. R. Comparison of in vitro gas production and nylon bag degradability of roughages in predicting feed intake in cattle. Anim Feed Sci Tech. 40 , 109-119 (1993). Rodrigues, M. A. M., Fonseca, A. J. M., Sequeira, C. A. & Dias-da-Silva, A. A. Digestion kinetic parameters from an in vitro gas production method as predictors of voluntary intake of forage by mature ewes. Anim Feed Sci Tech. 95 , 133-142 (2002). Kamalak, A., Canbolat, O., Gurbuz, Y. & Ozay, O. Comparison of in vitro gas production technique with in situ nylon bag technique to estimate dry matter degradation. Czech J. Anim Sci. 50 , 60-67 (2005). Kafilzadeh, F. & Heidary N. Chemical composition, in vitro digestibility and kinetics of fermentation of whole-crop forage from 18 different varieties of oat (Avena sativa L.). J. Applied Anim Res. 41 , 1, 61-68 (2013). Kulivand, M. & Kafilzadeh F. Correlation between chemical composition, kinetics of fermentation and methane production of eight pasture grasses. Acta Sci., Anim. Sci. 37 , 9-14 (2015). Marcos, C. N., García-Rebollar, P, de Blas, C. & Carro, M. D. Variability in the Chemical Composition and In Vitro Ruminal Fermentation of Olive Cake By-Products. Animal. 9 , 109; 10.3390/ani9030109 (2019). Haykin, S. Neural networks: A comprehensive foundation (Macmillan, 1998). Ganesan, R., Dhanavanthan, P., Kiruthika, C., Kumarasamy, P. & Balasubramanyam, D. Comparative study of linear mixed-effects and artificial neural network models for longitudinal unbalanced growth data of madras red sheep. Vet World. 7 , 52-58 (2014). Adebayo, R. A., Moyo, M., Gueguim Kana, E. B. & Nsahlai, I. V. The use of artificial neural networks for modelling rumen fill. Can J. Anim Sci. 101 , 427-437 (2020). Craninx, M., Fievez, Vlaeminck, V. B., De Baets, B. Artificial neural network models of the rumen fermentation pattern in dairy cattle. Comput Electron Agric. 60 , 226-238 (2008). Moyo, M. Gueguim Kana E. B. & Nsahlai I. V. Modelling of digesta passage rates in grazing and browsing domestic and wild ruminant herbivores. S Afr J. Anim Sci. 47 , 362-377 (2017). Dong, R. L. & Zhao, G. Y. Relationship between the methane production and the CNCPS carbohydrate fractions of rations with various concentrate/roughage ratios evaluated using in vitro incubation technique. Asian-Australas J. Anim Sci. 26 , 1708-1716 (2013). Sallam, S. M. A., Nasser, M. E. A., El-Waziry, A. M., Bueno, I. C. S. & Abdalla, A. L. Use of an in vitro Rumen Gas Production Technique to Evaluate Some Ruminant Feedstuffs. J. Applied Sci Res. 3 , 34-41 (2007). Akinfemi, A., Adua, M. M. & Adu, O. A. Evaluation of nutritive values of tropical feed sources and by-products using in vitro gas production technique in ruminant animals. Emir J. Food Agric. 24 , 348-353 (2012). Aderao, et al. In vitro rumen fermentation kinetics, metabolite production, methane and substrate degradability of polyphenol rich plant leaves and their component complete feed blocks. J. Anim Sci Technol. 60 , 26; 10.1186/s40781-018-0184-6 (2018). He, L. W., Meng, Q. X., Li, D. Y., Wang, F. & Ren, L. P. Effect of Steam Explosion on In Vitro Gas Production Kinetics and Rumen Fermentation Profiles of Three Common Straws. Ital J. Anim Sci. 14 , 4076;10.4081/ijas.2015 (2015). Kamalak, A. et al. Chemical composition and in vitro gas production characteristics of several tannin containing tree leaves. Livestock Research for Rural Development, 16 (6). 2004 Giridhar, K. S. Nutritional potentialities of some tree leaves based on polyphenols and rumen in vitro gas production. Vet. World. 23 , 1479-1485 (2018). Delavar, M. H., Tahmasbi, A. M., Danesh-Mesgaran, M. & Valizadeh, R. In vitro Rumen Fermentation and Gas Production: Influence of Different by-product Feedstuffs. Annu. res. rev. biol. 4 ; 1121-1128 (2014). Chanthakhoun, V. & Wanapat, M. The in vitro gas Production and Ruminal Fermentation of Various Feeds using Rumen Liquor from Swamp Buffalo and Cattle. Asian J Anim Vet Adv , 7 ,54-60 (2012). Tikam, K. et al. In vitro gas production, in vivo nutrient digestibilities, and metabolisable energy concentrations for sheep of fresh and conserved pangola grass. Small Rum Res. 128 , 34-40 (2015). Elghandour, M.M.Y. et al. Effects of exogenous enzymes on in vitro gas production kinetics and ruminal fermentation of four fibrous feeds. Anim Feed Sci Technol. 179 , 46-53 (2013). Kiran, D. & Krishnamoorthy, U. Rumen fermentation and microbial biomass synthesis indices of tropical feedstuffs determined by the in vitro gas production technique. Anim Feed Sci Technol. 134 , 170-179 (2007). Karabulut, A. et al. Comparison of In vitro Gas Production, Metabolizable Energy, Organic Matter Digestibility and Microbial Protein Production of Some Legume Hays. Asian-Aust J. Anim Sci. 20, 517-522 (2007). Baffa, D. F. et al. Evaluation of Associative Effects of In Vitro Gas Production and Fermentation Profile Caused by Variation in Ruminant Diet Constituents. Methane . 2 , 344-360. (2023). Lashkari, S. & Taghizadeh, A. Digestion kinetics of carbohydrate fractions of citrus by-products. Vet Res Forum . 6, 41-48 (2015). AOAC (Association of Official Analytical Chemists), Official methods of analysis (15th Edn) (AOAC Inc., Arlington, 1990). Van soest, P. J., Robertson, J. B. & Lewis, B. A. Methods for dietary fiber, neutral detergent fiber and non-starch polysaccharides in ration to animal nutrition. J. Dairy Sci . 74 , 3583-3597 (1991). SAS Ipharraguerre, I. R. & Clark, J. H. Soyhulls as an Alternative Feed for Lactating Dairy Cows: A Review. J. Dairy Sci . 86 , 1052-1073 (2003). García-Rodríguez, J. et al. Chemical Composition, In Vitro Digestibility and Rumen Fermentation Kinetics of Agro-Industrial By-Products. Animals. 9 , 861; 10.3390/ani9110861 (2019). Bizzuti, B. E. et al. In Vitro Degradability and Methane Production from By-Products Fed to Ruminants. Agronomy . 13 , 1043; 10.3390/ agronomy13041043 (2023). Haddi, M. L., Filacorda, S., Meniai, K. Rollin, F. & Susmel, P. In vitro fermentation kinetics of some halophyte shrubs sampled at three stages of maturity . Anim Feed Sci Tech. 104 , 215-225 (2003). Nherera, F. V., Ndlovu, L. R. & Dzowela, B. H. Relationships between in vitro gas production characteristics, chemical composition and in vivo quality measures in goats fed tree fodder supplements. Small Rum. Res . 31 , 117-126 (1999). He, Y., Mouthier, T. M. B., Kabel, M. A, Dijkstra, J., Hendriks, W. H., Struik, P. C. and Cone, J.W. (2018). Lignin composition is more important than content for maize stem cell wall degradation . J. Sci Food Agric. 98 , 384-390. Coblentz, W.K. et al. Unique interrelationships between fiber composition, water-soluble carbohydrates, and in vitro gas production for fall-grown oat forages, J. of Dairy Sci. 96 , 7195-7209 (2013). Hariadi, B. T. & Santoso, B. Evaluation of tropical plants containing tannin on in vitro methanogenesis and fermentation parameters using rumen fluid. J. Sci. Food Agric. 90 , 456-461 (2010). Fadare, D. A. & Babayemi, O. J. Modelling the association between in vitro gas production and chemical composition of some lesser known tropical browse forages using artificial neural network. Afr. J. Biotechnol. 6 , 2184-2192 (2007). Sanzogni, L. & Kerr, D. Milk production estimates using feed forward artificial neural networks. Comput Electron Agr. 32 , 21-30 (2001). Chen, L. J., Cui, L.Y., Xing, L. & Han, L. J. Prediction of the nutrient content in dairy manure using artificial neural network modeling. J. Dairy Sci . 91 , 4822–4829 (2008). Njubi. D., Wakhungu, J. & Badamana, M. Use of test-day records to predict first lactation 305-day milk yield using artificial neural network in Kenyan Holstein–Friesian dairy cows. Trop Anim Health Prod. 42 , 639–644 (2010). Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6453740","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":452149613,"identity":"984883d5-b1b9-45f7-bbd6-65114a08f720","order_by":0,"name":"S. Ghasemi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIiWNgGAWjYPCCAwwMEgzsHz5UMDAYkKKFjXHGGVK1MPO2EaFFvv104ueCijsM8tENbI955x2WN2dvPsDwo2IbTi0GZ3I3S88484zB8M4BdsO52w4b7uw5lsDYc+Y2bi0MuRukedsOMxjOSGCQeLvtMOOGGzkGzIxtuLXI97/d/Jv3H1QL75zD9gS1MNzI3SbN23CYQV4igU0SyEgkqMXgxttt1jzHDjMYSCQwG844lp684cyxhIP4/CLfn7v5Nk8N0JYZCYwPPtRY22443nzwwY8KPA6DgvoNB/g/AOlmMO8AQfVg6xrAVB1RikfBKBgFo2BkAQBv51919HFHcAAAAABJRU5ErkJggg==","orcid":"","institution":"national university of skills (NUS)","correspondingAuthor":true,"prefix":"","firstName":"S.","middleName":"","lastName":"Ghasemi","suffix":""},{"id":452149617,"identity":"856941f3-5311-4d40-bac0-79c585604d63","order_by":1,"name":"M. Behgar","email":"","orcid":"","institution":"Nuclear Science and Technology Research Institute","correspondingAuthor":false,"prefix":"","firstName":"M.","middleName":"","lastName":"Behgar","suffix":""},{"id":452149619,"identity":"f8577ee4-6ba0-4cce-a345-9bd296008a4c","order_by":2,"name":"M. Vatandoust","email":"","orcid":"","institution":"Payame Noor Department of Agriculture","correspondingAuthor":false,"prefix":"","firstName":"M.","middleName":"","lastName":"Vatandoust","suffix":""},{"id":452149620,"identity":"2d704019-57d3-4773-996c-88a814644f2f","order_by":3,"name":"P. Vahmani","email":"","orcid":"","institution":"University of California, Davis","correspondingAuthor":false,"prefix":"","firstName":"P.","middleName":"","lastName":"Vahmani","suffix":""}],"badges":[],"createdAt":"2025-04-15 10:23:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6453740/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6453740/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82080903,"identity":"e18ddc6d-777c-466e-b8dc-64426092b3a8","added_by":"auto","created_at":"2025-05-06 14:25:25","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":105808,"visible":true,"origin":"","legend":"\u003cp\u003eEvolution of gas production from agricultural by-products. Notes. SBH: soybean hulls, SBMR: soybean meal residue, CSH: cottonseed hulls, SFH: sunflower hulls, SBP: sugar beet pulp, GPH: ground peanut hulls.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6453740/v1/6a581f8af74c1e8869d62b6c.png"},{"id":82079707,"identity":"ca13dcf0-5147-4df4-a028-fdf7f9c7fdad","added_by":"auto","created_at":"2025-05-06 14:17:25","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":145303,"visible":true,"origin":"","legend":"\u003cp\u003eMultivariate cluster analysis plot showing groups of different feedstuffs/by-products based on similarities in chemical composition and asymptotic gas production (\u003cem\u003eb\u003c/em\u003e).\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6453740/v1/93f23c1999349973217cb46c.png"},{"id":82079710,"identity":"52659722-f68c-4d5e-ae51-2f1cd861d0ee","added_by":"auto","created_at":"2025-05-06 14:17:25","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":48588,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003ePredicted vs. observed asymptotic gas production (AGP) after 96 h for ANN (A) and MLR (B) models.\u003c/strong\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6453740/v1/e386110d536cb3c4b5e044fd.png"},{"id":90790198,"identity":"00e0352c-c230-405c-986f-9ab2ea763d9a","added_by":"auto","created_at":"2025-09-08 08:09:52","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1150151,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6453740/v1/6581711a-08d9-4de6-b87b-6c1f8d4852dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Use of an Artificial Neural Network and Multiple Linear Regression for the Prediction of the Asymptotic Gas Production of Agricultural By-products","fulltext":[{"header":"Introduction","content":"\u003cp\u003eIn recent years, researchers have shown great interest in using gas production (GP) methods instead of in situ and in vitro methods to evaluate the nutritional value of feedstuffs. This method has many advantages over other methods\u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e. In addition, several equations can be used to estimate dry matter (DM) intake, metabolizable energy, organic matter (OM) digestibility\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e, and short-chain fatty acid production \u003csup\u003e\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u003c/sup\u003e from GP data.\u003c/p\u003e \u003cp\u003eSeveral studies have reported high correlations between total gas production and feed intake \u003csup\u003e\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e\u003c/sup\u003e, digestible DM, and animal growth\u003csup\u003e\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u003c/sup\u003e. In addition, high correlations have been found between GP kinetics (b and k) and feed intake or DM digestibility\u003csup\u003e\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e,\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eMany studies have reported a relatively high correlation between GP kinetics and chemical fractions in oats and pasture grasses\u003csup\u003e\u003cspan additionalcitationids=\"CR8\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e. In addition, some efforts have been made to develop GP prediction equations using forage chemical fractions\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e, where linear prediction models were developed to estimate GP rate and fermented OM from forage chemical fractions.\u003c/p\u003e \u003cp\u003eArtificial neural networks (ANNs) are computational algorithms designed to simulate the behavior of biological systems composed of \"neurons\". Unlike traditional regression, ANNs work well with linear and nonlinear data\u003csup\u003e\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003cp\u003eThe use of ANNs in ruminant studies has recently gained interest, especially when the relationships between input and output variables are either unknown or highly complex\u003csup\u003e\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e,\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e\u003c/sup\u003e. It has been reported that the ANN can successfully predict the molar fraction of rumen volatile fatty acid (VFA) using milk FA profiles\u003csup\u003e\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u003c/sup\u003e and rumen passage rate\u003csup\u003e\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e\u003c/sup\u003e. The ANN was more accurate than multiple linear regression in predicting VFA production in the GP test using carbohydrate fractions as independent variables\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. However, there are few studies on ANN modeling of feed GP. Therefore, this study aimed to evaluate the use of ANN and MLR for predicting GP kinetics using the chemical composition of agricultural by-products.\u003c/p\u003e"},{"header":"Material and Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eDatasets\u003c/h2\u003e \u003cp\u003eTwo datasets were used in the study. In the first dataset (training), a total of 64 scientific papers were identified and initially screened for acceptability by checking that all publications reported chemical composition (including organic matter: OM, crude protein: CP, neutral detergent fiber: NDF, acid detergent fiber: ADF, and hemicellulose: HemCel) and asymptotic gas production (b) of the feedstuffs/by-products. Experiments that conducted gas production tests using bovine rumen fluid instead of sheep rumen fluid were excluded from the database, as were studies that did not use the Menk and Stingase\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e method for gas production testing. After discarding 48 of the 64 papers, a baseline dataset was constructed comprising 16 articles with 42 observations (Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Chemical compounds were converted to percentages and gas produced to ml/200 mg dry matter to harmonize the data.\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\u003eSummary of the training datasets.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"9\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c9\" colnum=\"9\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFeedstuffs/by-products\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eID\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOM\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNDF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eADF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHemCel\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c8\"\u003e \u003cp\u003eAGP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c9\"\u003e \u003cp\u003eReferences\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLinseed straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e74.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e84.58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e71.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e13.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e14.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDate stone\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e61.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e44.21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e17.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e46.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSugarcane bagasse\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e97.9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e77.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e47.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e29.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e39.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDussa\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e68.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e46.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e21.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e41.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCowpea pod\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e12.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e71.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e52.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e19.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e34.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMaize offal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e69.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e51.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e17.94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e37.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVigna sinensis hay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e60.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e45.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e15.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e42.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcacia nilotica (leaves)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e69.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e46.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e22.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e40.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZiziphus nummularia (leaves)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e14.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e65.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e47.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e18.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e37.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWheat straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e73.48\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e45.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e27.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e41.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eJuniperus communis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e56.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e34.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e22.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e51.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDillenia spp.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB12\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e90.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e53.33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e41.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e11.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e42.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e21\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCorn straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e79.26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e46.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e32.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e45.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePomegranate seed\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e64.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e46.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e18.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e48.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e22\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCorn cob\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e66.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e48.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e17.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e64.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e23\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFresh pangola\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e62.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e36.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e54.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePangola hay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e63.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e36.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e50.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePangola silage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e86.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e61.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e34.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e57.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSaccharum officinarum (leaves)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB19\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e2.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e69.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e48.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e21.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e27.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAndropogon gayanus (leaves)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e57.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e41.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e16.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e46.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNapier grass\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB21\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e89.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e7.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e59.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e33.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e47.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e24\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSorghum straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e61.40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e22.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e49.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e25\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGundelia tournefortii\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e68.30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e62.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e48.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e14.47\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e51.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFinger millet straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB24\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.68\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e3.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e65.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e53.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBarley straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e72.73\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e53.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e19.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e43.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e6\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRice straw\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB26\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e71.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e44.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e46.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e19\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBerseem hay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e88.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e15.32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e54.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38.31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e16.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e50.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDescurania Sophia\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e81.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e49.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e39.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e10.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e44.58\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChick pea\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB29\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.6\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e11.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e52.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e34.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e17.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e60.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e27\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTifton hay\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB30\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e4.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e77.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e41.76\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e36.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e45.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePineapple silage\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB31\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e59.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e38.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e21.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e24.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e28\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLemon pulp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB32\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e16.69\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e15.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e1.56\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e43.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGrapefruit pulp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB33\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e9.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e16.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e13.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e3.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e44.39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLime pulp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.88\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e17.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e14.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e44.04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOrange pulp\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.49\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e8.5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e14.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e11.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e2.79\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e40.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e29\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTaraxacum officinale\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.71\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e24.64\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e40.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e26.17\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e14.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e28.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCottonseed meal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB37\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e93.11\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e43.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27.34\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e16.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e11.14\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e48.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGroundnut meal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB38\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e39.09\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e29.87\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e10.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e18.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e51.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRapeseed meal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB39\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e91.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e37.72\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e27.46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e15.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e12.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e48.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSesame cake\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB40\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e87.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e29.55\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e32.61\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e17.84\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e14.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e45.60\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSoybean meal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e92.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e47.52\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e22.67\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e11.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e11.62\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e59.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSunflower meal\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOB42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e94.77\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e27.93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e48.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e29.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e19.13\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e \u003cp\u003e35.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c9\"\u003e \u003cp\u003e26\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"9\" nameend=\"c9\" namest=\"c1\"\u003e \u003cp\u003eOM: organic matter, CP: crude protein, EE: ether extract, NDF: neutral detergent fiber, ADF: acid detergent fiber, HemCell: Hemi-cellulose. AGP: Asymptotic gas production.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe second database (dataset 2) consisted of the chemical composition (OM, CP, NDF, ADF, and HemCel) and asymptotic gas production of selected agricultural by-products, including soybean hulls (SBH), soybean mill run (SBMR), cottonseed hulls (CSH), sunflower hulls (SFH), and sugar beet pulp (SBP). Samples were analyzed in duplicate for crude protein (CP), organic matter (OM), and ether extract (EE) according to AOAC\u003csup\u003e\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e30\u003c/span\u003e\u003c/sup\u003e. Neutral detergent fiber (NDF) and acid detergent fiber (ADF) were determined according to Vansoest et al.\u003csup\u003e\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u003c/sup\u003e. Hemicellulose was determined by subtracting NDF from ADF.\u003c/p\u003e \u003cp\u003eRumen fluid was collected from the three cannulated sheep and pressed through four layers of cheesecloth. GP was measured at 2, 4, 6, 8, 12, 24, 48, 72, and 96, and a series of corresponding blanks (i.e., without samples) were included, followed by calculation of the gas produced from each treatment by subtracting the gas produced from the gas produced in control blank\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eStatistical analysis and models\u003c/h3\u003e\n\u003cp\u003eThe volume of GP (ml/200 mg DM) was fitted to the model using the NLIN procedure of SAS (2011): G\u0026thinsp;=\u0026thinsp;b \u0026times; (1 - e\u003csup\u003e\u0026minus;\u0026thinsp;kt\u003c/sup\u003e), where G, b, and k represent the volume of GP at time t, the asymptotic GP (ml per 200 mg DM), and the rate of GP h\u003csup\u003e\u0026minus;\u0026thinsp;1\u003c/sup\u003e from the slowly fermentable feed fraction b, respectively.\u003c/p\u003e \u003cp\u003eMultivariate hierarchical cluster analysis was performed on the pooled data sets (data sets 1 and 2) using Ward's method with SAS statistical software\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e to group the feedstuff based on chemical composition and asymptotic GP (b). The graph shows the distances between the clusters.\u003c/p\u003e \u003cp\u003eThe PROC CORR statement was used in SAS\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e to display Pearson linear correlation coefficients between the variables examined in the pooled dataset.\u003c/p\u003e \u003cp\u003eThe PROC REG statement was used in SAS\u003csup\u003e\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u003c/sup\u003e to predict the asymptotic GP (b). Stepwise multiple regression was performed by including the most significant data sets in the model, and the significance level was set at P\u0026thinsp;\u0026le;\u0026thinsp;0.01.\u003c/p\u003e \u003cp\u003eThe ANN modeling process was performed using RapidMiner software (version 9.3.001) with the Deep Learning operator. Deep learning is based on a multi-layer feed-forward ANN trained with stochastic gradient descent using back-propagation. The deep network used in the current study consisted of three layers of nodes: the input layer, a hidden layer, and an output layer. The number of hidden layers was determined by trial and error. For the current study, one hidden layer was used, and the Maxout activation function was implemented in each neuron of this hidden layer. Early stopping was enabled to avoid overfitting. The first data set was used for training, and the second data set was used for testing. The Performance operator was utilized to statistically evaluate the performance of the model and deliver a list of performance criteria values.\u003c/p\u003e"},{"header":"Results and Discussions","content":"\u003cp\u003eThe chemical composition of selected feedstuff is shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The CP content varied among the by-products, with SBMR having the highest values (20.49% of DM) due to a relatively high proportion of seed meat. The chemical composition of SH and SHMR was within the range reported by Ipharraguerre and Clark\u003csup\u003e\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e\u003c/sup\u003e. Higher levels of NDF were observed for GPH, SFH and CSH, while lower levels were observed for SBMR and SBP. The same pattern was observed for ADF.\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\u003eDataset 2-Chemical composition (Mean\u0026thinsp;\u0026plusmn;\u0026thinsp;SD) of selected agricultural by-products (% of DM).\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\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOM\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCP\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNDF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eADF\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eHemCel\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSBH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e99.50\u0026thinsp;\u0026plusmn;\u0026thinsp;0.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.36\u0026thinsp;\u0026plusmn;\u0026thinsp;0.10\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e69.45\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e51.35\u0026thinsp;\u0026plusmn;\u0026thinsp;0.35\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e18.30\u0026thinsp;\u0026plusmn;\u0026thinsp;0.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSBMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e93.80\u0026thinsp;\u0026plusmn;\u0026thinsp;0.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e20.49\u0026thinsp;\u0026plusmn;\u0026thinsp;0.54\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e49.65\u0026thinsp;\u0026plusmn;\u0026thinsp;0.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e39.05\u0026thinsp;\u0026plusmn;\u0026thinsp;0.25\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e10.06\u0026thinsp;\u0026plusmn;\u0026thinsp;0.40\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCSH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e79.05\u0026thinsp;\u0026plusmn;\u0026thinsp;1.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e5.50\u0026thinsp;\u0026plusmn;\u0026thinsp;0.53\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e84.10\u0026thinsp;\u0026plusmn;\u0026thinsp;0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e69.02\u0026thinsp;\u0026plusmn;\u0026thinsp;0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e11.90\u0026thinsp;\u0026plusmn;\u0026thinsp;0.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSFH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e79.95\u0026thinsp;\u0026plusmn;\u0026thinsp;5.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e3.51\u0026thinsp;\u0026plusmn;\u0026thinsp;0.01\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e88.15\u0026thinsp;\u0026plusmn;\u0026thinsp;0.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e68.50\u0026thinsp;\u0026plusmn;\u0026thinsp;0.90\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e19.65\u0026thinsp;\u0026plusmn;\u0026thinsp;0.85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSBP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e98.50\u0026thinsp;\u0026plusmn;\u0026thinsp;0.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e9.96\u0026thinsp;\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e48.65\u0026thinsp;\u0026plusmn;\u0026thinsp;0.05\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e25.95\u0026thinsp;\u0026plusmn;\u0026thinsp;0.75\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e22.70\u0026thinsp;\u0026plusmn;\u0026thinsp;0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGPH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e95.90\u0026thinsp;\u0026plusmn;\u0026thinsp;0.28\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e4.79\u0026thinsp;\u0026plusmn;\u0026thinsp;0.08\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e89.15\u0026thinsp;\u0026plusmn;\u0026thinsp;0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e76.75\u0026thinsp;\u0026plusmn;\u0026thinsp;0.50\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e12.40\u0026thinsp;\u0026plusmn;\u0026thinsp;0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"6\" nameend=\"c6\" namest=\"c1\"\u003e \u003cp\u003eSD: Standard deviation, OM: organic matter, CP: crude protein, EE: ether extract, NDF: neutral detergent fiber, ADF: acid detergent fiber, HemCell: Hemi-cellulose. SBH: soybean hull, SBMR: soybean mill run, CSH: cottonseed hull, SFH: sunflower hull, SBP: sugar beet pulp, GPH: ground peanut hull.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003eGas production assay\u003c/h3\u003e\n\u003cp\u003eThe GP trend of the agricultural by-products (Dataset 2) is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. The agricultural by-products also behaved differently regarding the rate at which they produced gas. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the total gas produced by the incubation of selected agricultural by-products at different times and the corresponding GP kinetics (b and k). In the present study, selected agricultural by-products had a wide range of produced gas from 26.10 to 107.29 ml after incubation for 96 h. Soybean hulls and SBMR had the highest values of produced gas at 96 h, but GPH, SFH, and CSH had the lower produced gas. The same trends were observed for incubation at 24 and 72 hours.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eGas volume and gas production kinetics (mean\u0026thinsp;\u0026plusmn;\u0026thinsp;sd) of selected agricultural by-products.\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=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c8\" colnum=\"8\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colspan=\"7\" nameend=\"c8\" namest=\"c2\"\u003e \u003cp\u003eAgricultural by-products\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSBH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSBMR\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCSH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSFH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eSBP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eGPH\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGas volume\u003c/p\u003e \u003cp\u003e(ml/200 mg DM)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e24 h\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e85.21\u0026thinsp;\u0026plusmn;\u0026thinsp;12.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e79.75\u0026thinsp;\u0026plusmn;\u0026thinsp;7.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e22.50\u0026thinsp;\u0026plusmn;\u0026thinsp;2.65\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e22.06\u0026thinsp;\u0026plusmn;\u0026thinsp;2.16\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e86.93\u0026thinsp;\u0026plusmn;\u0026thinsp;10.27\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e17.75\u0026thinsp;\u0026plusmn;\u0026thinsp;5.74\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e72 h\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e105.29\u0026thinsp;\u0026plusmn;\u0026thinsp;15.45\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e100.85\u0026thinsp;\u0026plusmn;\u0026thinsp;6.06\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e52.10\u0026thinsp;\u0026plusmn;\u0026thinsp;3.63\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e32.50\u0026thinsp;\u0026plusmn;\u0026thinsp;3.78\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e105.63\u0026thinsp;\u0026plusmn;\u0026thinsp;11.03\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e24.58\u0026thinsp;\u0026plusmn;\u0026thinsp;6.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003e96 h\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e107.29\u0026thinsp;\u0026plusmn;\u0026thinsp;15.42\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e102.90\u0026thinsp;\u0026plusmn;\u0026thinsp;5.66\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e57.5\u0026thinsp;\u0026plusmn;\u0026thinsp;6.15\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e33.6\u0026thinsp;\u0026plusmn;\u0026thinsp;3.59\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e108.25\u0026thinsp;\u0026plusmn;\u0026thinsp;11.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e26.1\u0026thinsp;\u0026plusmn;\u0026thinsp;6.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003eGas production kinetics\u003c/p\u003e \u003cp\u003e(96 h)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAGP \u003cem\u003e(ml)\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e107.01\u0026thinsp;\u0026plusmn;\u0026thinsp;18.80\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e102.38\u0026thinsp;\u0026plusmn;\u0026thinsp;5.85\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e76.30\u0026thinsp;\u0026plusmn;\u0026thinsp;15.20\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e33.40\u0026thinsp;\u0026plusmn;\u0026thinsp;4.41\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e104.41\u0026thinsp;\u0026plusmn;\u0026thinsp;11.22\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e25.01\u0026thinsp;\u0026plusmn;\u0026thinsp;6.07\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cem\u003ek (% h\u003c/em\u003e\u003csup\u003e\u003cem\u003e\u0026minus;\u0026thinsp;1\u003c/em\u003e\u003c/sup\u003e\u003cem\u003e)\u003c/em\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.069\u0026thinsp;\u0026plusmn;\u0026thinsp;0.020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.063\u0026thinsp;\u0026plusmn;\u0026thinsp;0.010\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.017\u0026thinsp;\u0026plusmn;\u0026thinsp;0.005\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.047\u0026thinsp;\u0026plusmn;\u0026thinsp;0.005\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003e0.092\u0026thinsp;\u0026plusmn;\u0026thinsp;0.010\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003e0.060\u0026thinsp;\u0026plusmn;\u0026thinsp;0.020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c8\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"8\" nameend=\"c8\" namest=\"c1\"\u003e \u003cp\u003eSBH: soybean hull, SBMR: soybean mill run, CSH: cottonseed hull, SFH: sunflower hull, BP: pistachio by-product, SBP: sugar beet pulp, GPH: ground peanut hull.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e\n\u003ch3\u003eCluster Analysis\u003c/h3\u003e\n\u003cp\u003eThe results of the cluster analysis on the pooled data sets (1 \u0026amp; 2) are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The graph shows that the samples were grouped into two clusters (A \u0026amp; B), with the degree of similarity among the by-products within each group being greater than 80% and 90% for clusters A and B, respectively. Group (A) included OB1-31; and SBH, SBMR, CSH, SFH, SBP, GPH (data set 2). Cluster B grouped OB32-44. Cluster A discriminated from Group B with a similarity of 55%. Group B included lemon pulp, grapefruit pulp, lime pulp, orange pulp, Taraxacum officinale, cottonseed meal, peanut meal, rapeseed meal, sesame cake, soybean meal, sunflower meal, and chickpea.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIt has been shown that cluster analysis can successfully classify agricultural by-products based on their chemical composition and fermentation characteristics\u003csup\u003e34\u003c/sup\u003e. In the present study, cluster B consisted of feeds with low cell wall content or, in the case of meals, high protein content. Group A included dataset 2 and the rest of the by-products from dataset 1. Bizzuti et al.\u003csup\u003e35\u003c/sup\u003e classified agricultural by-products into a clear cluster with 3 distinct groups based on chemical composition, in vitro gas production, organic matter degradability, and ruminal fermentation kinetics.\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e shows the correlation coefficients of chemical composition with produced gas potential (b) on cluster A. Negative correlations (P\u0026thinsp;\u0026lt;\u0026thinsp;0.01) were observed between asymptotic gas production (b) with NDF and ADF. The negative correlation between AGP and cell wall components (NDF and ADF; 0.47 and 0.41, respectively) in the present study is consistent with previous studies\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e,34\u003c/sup\u003e. Kafilzadeh and Heidary\u003csup\u003e\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u003c/sup\u003e examined 18 different oat cultivars and found a significant negative correlation between NDF (r\u0026thinsp;=\u0026thinsp;0.48) and ADF (r\u0026thinsp;=\u0026thinsp;0.83) with AGP or gas production rate. Although lignin was not examined in this study, much of the adverse effect of cell wall components on gas production may be due to the presence of lignin in NDF and ADF. Lignin forms a physical barrier that reduces the access of rumen microbes to fermentable cell wall components. Studies have shown a powerful and negative correlation between GP kinetics and ADL content of agricultural co-products\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e,\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u003c/sup\u003e.\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\u003e Correlation of chemical composition with AGP.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003e\u003cem\u003eAGP\u003c/em\u003e\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.32*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCP\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.37*\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNDF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-0.47**\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eADF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-0.41**\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemCell\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-0.04\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"4\" nameend=\"c4\" namest=\"c1\"\u003e \u003cp\u003eOM: organic matter, CP: crud protein, NDF: Neutral detergent fiber, ADF: acid detergent fiber, HemCel: hemi-cellulose, AGP: Asymptotic gas production. * P\u0026thinsp;\u0026lt;\u0026thinsp;0.0, **P\u0026thinsp;\u0026lt;\u0026thinsp;0.01\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\u003eIt has been reported that cumulative \u003cem\u003ein vitro\u003c/em\u003e gas production after 12\u0026ndash;48 h of fall-oat diets was negatively correlated with NDF, hemicellulose, lignin, and ash\u003csup\u003e\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u003c/sup\u003e. These findings are further supported by the data from the present study, which indicates that by-products with the highest levels of cell wall content exhibited the lowest gas production. (see Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThere were positive correlations (P\u0026thinsp;\u0026lt;\u0026thinsp;0.05) between OM and CP of agricultural by-products and asymptotic gas production (b). Similarly, the results of Kulivand and Kafilzadeh\u003csup\u003e\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e\u003c/sup\u003e showed a positive correlation between the CP content of pasture grasses with asymptotic GP and the rate of GP after 96 h of incubation. Similarly, Nherera et al.\u003csup\u003e35\u003c/sup\u003e observed a positive and significant correlation between the nitrogen content of some diets and GP kinetics (b and k) after 96 h of incubation. It has been reported that the minimum CP concentration to support microbial activity is %7 of DM\u003csup\u003e38\u003c/sup\u003e. Interestingly, in the present study, co-products with CP content below this level (i.e., CSH, SFH, and GPH) had the lowest cumulative GP.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eModel Development\u003c/h2\u003e \u003cp\u003eThe input data utilized for the MLR and ANN modeling were confined to cluster A. The multiple linear regression (MLR) model for AGP and the statistical parameters for the ANN and MLR models are summarized in Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e. Asymptotic gas production (AGP) was explained by multiple regression equations using OM, CP, and NDF as independent variables (r\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;0.23). The r\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e and RMSE for predicting b using ANN were 0.70 and 5.39, respectively. Based on the comparison of the results of the ANN with those of the MLR model, the ANN performed better with lower RMSE and higher r\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\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\u003eStatistics and information of ANN and MLR models for asymptotic gas production.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eModel\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e\u003cem\u003eb\u003c/em\u003e\u0026thinsp;=\u0026thinsp;26.06\u0026thinsp;+\u0026thinsp;OM0.62\u0026thinsp;+\u0026thinsp;CP0.78-NDF0.57\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e-\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRoot Mean Squared Error\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e18.36\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e5.39\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eR\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.23\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.70\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\u003eWhen the number of nodes in the hidden layer was set to 13 and b was treated as a single output variable in the model, the lower RMSE and higher r\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e for predicting b were observed.\u003c/p\u003e \u003cp\u003eDong and Zhao\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e concluded that the number of neurons in the hidden layer affected the performance of ANN models for predicting ruminal VFA production. In the present study, the number of neurons was selected by trial and error, and the model with the lowest RMSE and highest R\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e was chosen as the best model. Fadare and Babayemi\u003csup\u003e39\u003c/sup\u003e reported a higher R value with a lower standard deviation in neural network models with one hidden layer compared to two. In the current study, the number of hidden layers was set to one because a single hidden layer ANN can approximate any function as long as enough neurons are used.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eMLR modeling is an ideal tool for identifying linear relationships between different parameters. Nherera et al.\u003csup\u003e35\u003c/sup\u003e found a higher correlation of dietary NDF and nitrogen with in vitro AGP at 24 h than at 96 h. They used simple and multiple linear equations to predict in vitro AGP based on dietary chemical composition, and they reported a higher R for predicting gas at 24 h than at 96 h (0.90 and 0.80, respectively). Similarly, Marcos et al.\u003csup\u003e\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e\u003c/sup\u003e reported that carbohydrates (sugars and NDF) could be used to predict in vitro ruminal GP and OM fermentation of olive cake. MLR modeling is based on the assumption of a linear relationship between dependent and independent variables. However, in most cases, the data is complex and not linear\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. For this reason, in some cases, models developed using ANN perform better than MLR models, as seen in the present study.\u003c/p\u003e \u003cp\u003eIt has been reported that CNCPS carbohydrate fractions can be effectively utilized as inputs to predict in vitro rumen gas production (GP) using MLR, as well as for estimating acetate, propionate, butyrate, and total VFA production through both MLR and ANN approaches\u003csup\u003e\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u003c/sup\u003e. In this study, ANN models performed better than MLR models. The superior performance of ANN models over MLR has also been documented in estimating milk production\u003csup\u003e\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e\u003c/sup\u003e, goat body weight gain\u003csup\u003e\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u003c/sup\u003e, and nutrient content of dairy manure\u003csup\u003e\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThe results of the present study indicated that the feedstuff's chemical composition was suitable for predicting \u003cem\u003ein vitro\u003c/em\u003e AGP. Based on the results of the present study, deep learning models showed better performance for predicting AGP than MLR models. Further studies are needed to improve the prediction accuracy and to apply this prediction model to a wider range of samples and feedstuffs.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eS.G. and M.B. wrote the main manuscript text.M.V. Analyzed the data and prepared Tables and Figs.P.V. Revised the final draft of the manuscript.All authors reviewed the final manuscript.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eGetachew, G., Blummel, M., Makkar, H. P. S. \u0026amp; Becker, K. In vitro gas measuring techniques for assessment of nutritional quality of feeds: a review. \u003cem\u003eAnim Feed Sci Technol.\u003c/em\u003e \u003cstrong\u003e72\u003c/strong\u003e, 261-281 (1998).\u003c/li\u003e\n\u003cli\u003eMenke, K.H. and Steingass, H. Estimation of the energetic feed value from chemical analysis and in vitro gas production using rumen fluid. \u003cem\u003eAnim Res Dev.\u003c/em\u003e \u003cstrong\u003e28\u003c/strong\u003e, 7-55 (1988). \u003c/li\u003e\n\u003cli\u003eHetta, M., Cone, J. W., Bernes, G., Gustavsson, A-M. \u0026amp; Martinsson, K. Voluntary intake of silages in dairy cows depending on chemical composition and in vitro gas production characteristics. \u003cem\u003eLivest Sci.\u003c/em\u003e \u003cstrong\u003e106\u003c/strong\u003e, 47-56 (2007).\u003c/li\u003e\n\u003cli\u003eBlummel, M., \u0026Oslash;rskov, E. R. Comparison of in vitro gas production and nylon bag degradability of roughages in predicting feed intake in cattle. \u003cem\u003eAnim Feed Sci Tech. \u003c/em\u003e\u003cstrong\u003e40\u003c/strong\u003e, 109-119 (1993).\u003c/li\u003e\n\u003cli\u003eRodrigues, M. A. M., Fonseca, A. J. M., Sequeira, C. A. \u0026amp; Dias-da-Silva, A. A. Digestion kinetic parameters from an in vitro gas production method as predictors of voluntary intake of forage by mature ewes. \u003cem\u003eAnim Feed Sci Tech. \u003c/em\u003e\u003cstrong\u003e95\u003c/strong\u003e, 133-142 (2002). \u003c/li\u003e\n\u003cli\u003eKamalak, A., Canbolat, O., Gurbuz, Y. \u0026amp; Ozay, O. Comparison of \u003cem\u003ein vitro\u003c/em\u003e gas production technique with in situ nylon bag technique to estimate dry matter degradation. Czech J. Anim Sci. \u003cstrong\u003e50\u003c/strong\u003e, 60-67 (2005).\u003c/li\u003e\n\u003cli\u003eKafilzadeh, F. \u0026amp; Heidary N. Chemical composition, in vitro digestibility and kinetics of fermentation of whole-crop forage from 18 different varieties of oat (Avena sativa L.). \u003cem\u003eJ. Applied Anim Res.\u003c/em\u003e \u003cstrong\u003e41\u003c/strong\u003e, 1, 61-68 (2013).\u003c/li\u003e\n\u003cli\u003eKulivand, M. \u0026amp; Kafilzadeh F. Correlation between chemical composition, kinetics of fermentation and methane production of eight pasture grasses. \u003cem\u003eActa Sci., Anim. Sci.\u003c/em\u003e \u003cstrong\u003e37\u003c/strong\u003e, 9-14 (2015). \u003c/li\u003e\n\u003cli\u003eMarcos, C. N., Garc\u0026iacute;a-Rebollar, P, de Blas, C. \u0026amp; Carro, M. D. Variability in the Chemical Composition and In Vitro Ruminal Fermentation of Olive Cake By-Products. \u003cem\u003eAnimal.\u003c/em\u003e \u003cstrong\u003e9\u003c/strong\u003e, 109; 10.3390/ani9030109 (2019).\u003c/li\u003e\n\u003cli\u003eHaykin, S. Neural networks: A comprehensive foundation (Macmillan, 1998).\u003c/li\u003e\n\u003cli\u003eGanesan, R., Dhanavanthan, P., Kiruthika, C., Kumarasamy, P. \u0026amp; Balasubramanyam, D. Comparative study of linear mixed-effects and artificial neural network models for longitudinal unbalanced growth data of madras red sheep. \u003cem\u003eVet World.\u003c/em\u003e \u003cstrong\u003e7\u003c/strong\u003e, 52-58 (2014). \u003c/li\u003e\n\u003cli\u003eAdebayo, R. A., Moyo, M., Gueguim Kana, E. B. \u0026amp; Nsahlai, I. V. The use of artificial neural networks for modelling rumen fill. \u003cem\u003eCan J. Anim Sci.\u003c/em\u003e \u003cstrong\u003e101\u003c/strong\u003e, 427-437 (2020). \u003c/li\u003e\n\u003cli\u003eCraninx, M., Fievez, Vlaeminck, V. B., De Baets, B. Artificial neural network models of the rumen fermentation pattern in dairy cattle. \u003cem\u003eComput Electron Agric. \u003c/em\u003e\u003cstrong\u003e60\u003c/strong\u003e, 226-238 (2008).\u003c/li\u003e\n\u003cli\u003eMoyo, M. Gueguim Kana E. B. \u0026amp; Nsahlai I. V. Modelling of digesta passage rates in grazing and browsing domestic and wild ruminant herbivores. \u003cem\u003eS Afr J. Anim Sci.\u003c/em\u003e \u003cstrong\u003e47\u003c/strong\u003e, 362-377 (2017).\u003c/li\u003e\n\u003cli\u003eDong, R. L. \u0026amp; Zhao, G. Y. Relationship between the methane production and the CNCPS carbohydrate fractions of rations with various concentrate/roughage ratios evaluated using in vitro incubation technique. \u003cem\u003eAsian-Australas J. Anim Sci.\u003c/em\u003e \u003cstrong\u003e26\u003c/strong\u003e, 1708-1716 (2013).\u003c/li\u003e\n\u003cli\u003eSallam, S. M. A., Nasser, M. E. A., El-Waziry, A. M., Bueno, I. C. S. \u0026amp; Abdalla, A. L. Use of an in vitro Rumen Gas Production Technique to Evaluate Some Ruminant Feedstuffs. J. Applied Sci Res. \u003cstrong\u003e3\u003c/strong\u003e, 34-41 (2007). \u003c/li\u003e\n\u003cli\u003eAkinfemi, A., Adua, M. M. \u0026amp; Adu, O. A. Evaluation of nutritive values of tropical feed sources and by-products using in vitro gas production technique in ruminant animals. Emir J. Food Agric. \u003cstrong\u003e24\u003c/strong\u003e, 348-353 (2012).\u003c/li\u003e\n\u003cli\u003eAderao, et al. In vitro rumen fermentation kinetics, metabolite production, methane and substrate degradability of polyphenol rich plant leaves and their component complete feed blocks. \u003cem\u003eJ. Anim Sci Technol.\u003c/em\u003e \u003cstrong\u003e60\u003c/strong\u003e, 26; 10.1186/s40781-018-0184-6 (2018). \u003c/li\u003e\n\u003cli\u003eHe, L. W., Meng, Q. X., Li, D. Y., Wang, F. \u0026amp; Ren, L. P. Effect of Steam Explosion on In Vitro Gas Production Kinetics and Rumen Fermentation Profiles of Three Common Straws. \u003cem\u003eItal J. Anim Sci.\u003c/em\u003e \u003cstrong\u003e14\u003c/strong\u003e, 4076;10.4081/ijas.2015 (2015). \u003c/li\u003e\n\u003cli\u003eKamalak, A. et al. Chemical composition and in vitro gas production characteristics of several tannin containing tree leaves. Livestock Research for Rural Development, \u003cstrong\u003e16\u003c/strong\u003e (6). 2004\u003c/li\u003e\n\u003cli\u003eGiridhar, K. S. Nutritional potentialities of some tree leaves based on polyphenols and rumen in vitro gas production. \u003cem\u003eVet. World.\u003c/em\u003e \u003cstrong\u003e23\u003c/strong\u003e, 1479-1485 (2018).\u003c/li\u003e\n\u003cli\u003eDelavar, M. H., Tahmasbi, A. M., Danesh-Mesgaran, M. \u0026amp; Valizadeh, R. In vitro Rumen Fermentation and Gas Production: Influence of Different by-product Feedstuffs. \u003cem\u003eAnnu. res. rev. biol. \u003c/em\u003e\u003cstrong\u003e4\u003c/strong\u003e; 1121-1128 (2014).\u003c/li\u003e\n\u003cli\u003eChanthakhoun, V. \u0026amp; Wanapat, M. The in vitro gas Production and Ruminal Fermentation of Various Feeds using Rumen Liquor from Swamp Buffalo and Cattle. \u003cem\u003eAsian J Anim Vet Adv\u003c/em\u003e, \u003cstrong\u003e7\u003c/strong\u003e,54-60 (2012).\u003c/li\u003e\n\u003cli\u003eTikam, K. et al. In vitro gas production, in vivo nutrient digestibilities, and metabolisable energy concentrations for sheep of fresh and conserved pangola grass. \u003cem\u003eSmall Rum Res.\u003c/em\u003e \u003cstrong\u003e128\u003c/strong\u003e, 34-40 (2015).\u003c/li\u003e\n\u003cli\u003eElghandour, M.M.Y. et al. Effects of exogenous enzymes on in vitro gas production kinetics and ruminal fermentation of four fibrous feeds. \u003cem\u003eAnim Feed Sci Technol.\u003c/em\u003e \u003cstrong\u003e179\u003c/strong\u003e, 46-53 (2013). \u003c/li\u003e\n\u003cli\u003eKiran, D. \u0026amp; Krishnamoorthy, U. Rumen fermentation and microbial biomass synthesis indices of tropical feedstuffs determined by the in vitro gas production technique. \u003cem\u003eAnim Feed Sci Technol.\u003c/em\u003e \u003cstrong\u003e134\u003c/strong\u003e, 170-179 (2007). \u003c/li\u003e\n\u003cli\u003eKarabulut, A. et al. Comparison of In vitro Gas Production, Metabolizable Energy, Organic Matter Digestibility and Microbial Protein Production of Some Legume Hays. \u003cem\u003eAsian-Aust J. Anim Sci.\u003c/em\u003e 20, 517-522 (2007).\u003c/li\u003e\n\u003cli\u003eBaffa, D. F. et al. Evaluation of Associative Effects of In Vitro Gas Production and Fermentation Profile Caused by Variation in Ruminant Diet Constituents. \u003cem\u003eMethane\u003c/em\u003e. \u003cstrong\u003e2\u003c/strong\u003e, 344-360. (2023).\u003c/li\u003e\n\u003cli\u003eLashkari, S. \u0026amp; Taghizadeh, A. Digestion kinetics of carbohydrate fractions of citrus by-products. \u003cem\u003eVet Res Forum\u003c/em\u003e. 6, 41-48 (2015).\u003c/li\u003e\n\u003cli\u003eAOAC (Association of Official Analytical Chemists), Official methods of analysis (15th Edn) (AOAC Inc., Arlington, 1990).\u003c/li\u003e\n\u003cli\u003eVan soest, P. J., Robertson, J. B. \u0026amp; Lewis, B. A. Methods for dietary fiber, neutral detergent fiber and non-starch polysaccharides in ration to animal nutrition. \u003cem\u003eJ. Dairy Sci\u003c/em\u003e\u003cem\u003e.\u003c/em\u003e \u003cstrong\u003e74\u003c/strong\u003e, 3583-3597 (1991). \u003c/li\u003e\n\u003cli\u003eSAS\u003c/li\u003e\n\u003cli\u003eIpharraguerre, I. R. \u0026amp; Clark, J. H. Soyhulls as an Alternative Feed for Lactating Dairy Cows: A Review. \u003cem\u003eJ. Dairy Sci\u003c/em\u003e\u003cem\u003e.\u003c/em\u003e \u003cstrong\u003e86\u003c/strong\u003e, 1052-1073 (2003).\u003c/li\u003e\n\u003cli\u003eGarc\u0026iacute;a-Rodr\u0026iacute;guez, J. et al. Chemical Composition, In Vitro Digestibility and Rumen Fermentation Kinetics of Agro-Industrial By-Products. \u003cem\u003eAnimals.\u003c/em\u003e \u003cstrong\u003e9\u003c/strong\u003e, 861; 10.3390/ani9110861 (2019).\u003c/li\u003e\n\u003cli\u003eBizzuti, B. E. et al. \u003cem\u003eIn Vitro\u003c/em\u003e Degradability and Methane Production from By-Products Fed to Ruminants. \u003cem\u003eAgronomy\u003c/em\u003e. \u003cstrong\u003e13\u003c/strong\u003e, 1043; 10.3390/ agronomy13041043 (2023).\u003c/li\u003e\n\u003cli\u003eHaddi, M. L., Filacorda, S., Meniai, K. Rollin, F. \u0026amp; Susmel, P. In vitro fermentation kinetics of some halophyte shrubs sampled at three stages of maturity\u003cem\u003e. Anim Feed Sci Tech. \u003c/em\u003e\u003cstrong\u003e104\u003c/strong\u003e, 215-225 (2003). \u003c/li\u003e\n\u003cli\u003eNherera, F. V., Ndlovu, L. R. \u0026amp; Dzowela, B. H. Relationships between in vitro gas production characteristics, chemical composition and in vivo quality measures in goats fed tree fodder supplements. \u003cem\u003eSmall Rum. Res\u003c/em\u003e. \u003cstrong\u003e31\u003c/strong\u003e, 117-126 (1999). \u003c/li\u003e\n\u003cli\u003eHe, Y., Mouthier, T. M. B., Kabel, M. A, Dijkstra, J., Hendriks, W. H., Struik, P. C. and Cone, J.W. (2018). Lignin composition is more important than content for maize stem cell wall degradation\u003cem\u003e. J. Sci Food Agric.\u003c/em\u003e \u003cstrong\u003e98\u003c/strong\u003e, 384-390. \u003c/li\u003e\n\u003cli\u003eCoblentz, W.K. et al. Unique interrelationships between fiber composition, water-soluble carbohydrates, and in vitro gas production for fall-grown oat forages, \u003cem\u003eJ. of Dairy Sci.\u003c/em\u003e \u003cstrong\u003e96\u003c/strong\u003e, 7195-7209 (2013).\u003c/li\u003e\n\u003cli\u003eHariadi, B. T. \u0026amp; Santoso, B. Evaluation of tropical plants containing tannin on in vitro methanogenesis and fermentation parameters using rumen fluid. \u003cem\u003eJ. Sci. Food Agric.\u003c/em\u003e \u003cstrong\u003e90\u003c/strong\u003e, 456-461 (2010).\u003c/li\u003e\n\u003cli\u003eFadare, D. A. \u0026amp; Babayemi, O. J. Modelling the association between in vitro gas production and chemical composition of some lesser known tropical browse forages using artificial neural network. \u003cem\u003eAfr. J. Biotechnol.\u003c/em\u003e\u003cstrong\u003e 6\u003c/strong\u003e, 2184-2192 (2007).\u003c/li\u003e\n\u003cli\u003eSanzogni, L. \u0026amp; Kerr, D. Milk production estimates using feed forward artificial neural networks. \u003cem\u003eComput Electron Agr.\u003c/em\u003e \u003cstrong\u003e32\u003c/strong\u003e, 21-30 (2001).\u003c/li\u003e\n\u003cli\u003eChen, L. J., Cui, L.Y., Xing, L. \u0026amp; Han, L. J. Prediction of the nutrient content in dairy manure using artificial neural network modeling. \u003cem\u003eJ. Dairy Sci\u003c/em\u003e\u003cem\u003e.\u003c/em\u003e \u003cstrong\u003e91\u003c/strong\u003e, 4822\u0026ndash;4829 (2008).\u003c/li\u003e\n\u003cli\u003eNjubi. D., Wakhungu, J. \u0026amp; Badamana, M. Use of test-day records to predict first lactation 305-day milk yield using artificial neural network in Kenyan Holstein\u0026ndash;Friesian dairy cows. \u003cem\u003eTrop Anim Health Prod. \u003c/em\u003e\u003cstrong\u003e42\u003c/strong\u003e, 639\u0026ndash;644 (2010).\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Agricultural by-products, gas production, neural networks, cluster analysis, multilinear regression, prediction","lastPublishedDoi":"10.21203/rs.3.rs-6453740/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6453740/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study evaluated the correlation between chemical composition and asymptotic in vitro gas production (AGP) of various agricultural by-products. In addition, it attempted to use artificial neural network (ANN) and multiple linear regression (MLR) approaches to predict AGP based on the chemical composition of these by-products. Two data sets were used in the study. The first dataset (training) consisted of published data, while the second dataset (testing) consisted of the chemical composition and asymptotic gas production of selected by-products. First, the chemical composition and AGP of the selected by-products were measured. The two data sets were then pooled and processed for cluster analysis. Multivariate cluster analysis revealed two distinct groups (A \u0026amp; B) with a degree of similarity among the by-products within each group exceeding 80% and 90%, respectively. The selected by-products were categorized into cluster A, so this cluster was considered for Pearson correlation and modeling analysis. Negative correlations were observed between AGP and NDF and ADF. Conversely, positive correlations were found between OM and CP of agricultural by-products and AGP. The ANN showed superior performance in predicting asymptotic gas production (b) compared to the MLR model, as indicated by lower root mean square error (RMSE) and higher r\u003csup\u003e\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e\u003c/sup\u003e.\u003c/p\u003e","manuscriptTitle":"Use of an Artificial Neural Network and Multiple Linear Regression for the Prediction of the Asymptotic Gas Production of Agricultural By-products","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 14:17:20","doi":"10.21203/rs.3.rs-6453740/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"300ec2ab-a2f7-482a-bac5-0013a309bada","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48086253,"name":"Biological sciences/Plant sciences"},{"id":48086254,"name":"Biological sciences/Plant sciences/Natural variation in plants"}],"tags":[],"updatedAt":"2025-09-08T08:09:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-06 14:17:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6453740","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6453740","identity":"rs-6453740","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}