Shahid Bahonar University of Kerman and Iranian Society of Animal Science Journal of Livestock Science and Technologies 2322-3553 15 1 2027 07 01 Application of artificial neural networks and multiple linear regression for predicting asymptotic gas production of agricultural by-products 15 23 5319 10.22103/jlst.2026.26196.1690 EN Samaneh Ghasemi Department of Agricultural Engineering, National University of Skills (NUS), Tehran, Iran Mehdi Behgar Nuclear Agriculture Research School, Nuclear Science and Technology Research Institute. P.O. Box 31485498, Tehran, Iran Moosa Vatandoust Department of Agriculture, Payame Noor University, Tehran, Iran, P. O. Box 19395-3697. Tehran, Iran Payam Vahmani Department of Animal Science, University of California, Davis, One Shields Avenue, Davis, CA 95616 Journal Article 2025 10 27 This research explored the correlation between the chemical composition and asymptotic <em>in vitro</em> gas production (AGP) of diverse agricultural by-products, intending to develop predictive models for AGP using advanced computational methods. The research employed two complementary analytical approaches: artificial neural networks (ANN) and multiple linear regression (MLR), to assess their efficacy in forecasting AGP based on compositional parameters. Two datasets were utilized: a training dataset compiled from previously published literature and a testing dataset comprising experimentally derived chemical profiles and AGP measurements of selected by-products. Following the determination of chemical constituents (e.g., neutral detergent fiber [NDF], acid detergent fiber [ADF], organic matter [OM], and crude protein [CP]) and AGP values, the datasets were merged and subjected to multivariate cluster analysis. This analysis revealed two statistically distinct clusters (A and B), with intra-group similarity thresholds exceeding 80% for Cluster A and 90% for Cluster B. The study focused on Cluster A, which encompassed the selected by-products, for subsequent Pearson correlation and predictive modeling. Key findings included significant inverse relationships between AGP and fiber components (NDF: r=−0.65; ADF: r=−0.72), whereas positive correlations emerged with OM (r=0.58) and CP (r=0.49). Comparative model performance demonstrated ANN’s superiority (r²=0.78, RMSE=5.39) over MLR (r²=0.24, RMSE=18.36), highlighting its potential for accurate AGP prediction in agricultural by-products. https://lst.uk.ac.ir/article_5319_b472c886a57aeb0c21821e0d01fb0131.pdf