Integrating Experimental Pyrolysis and Machine Learning for Sustainable Biochar Yield Prediction from Lignocellulosic Waste

Abstract

Biochar production from lignocellulosic waste represents a sustainable route for biomass valorization and carbon management within circular bioeconomy frameworks. In this study, biochar was produced from two abundant agricultural wastes in T & uuml;rkiye-tea-brewing residues and almond husks-via controlled non-isothermal pyrolysis, and biochar yield was modeled using data-driven machine learning approaches. The effects of key process parameters, including carbonization temperature (37-850 degrees C covering drying/pre-pyrolysis and pyrolysis regions), residence time (1-150 min), and heating rate (10-60 degrees C min(-1)), were evaluated using regression-based, ensemble, and deep learning models. Model performance was evaluated using cross-validation on training and testing datasets. The results showed that linear models exhibited limited predictive capability (R-2 < 0.95), while regularized and ensemble models improved performance (R-2 approximate to 0.97-0.99). Among all approaches, Gaussian Process Regression (GPR) achieved the highest predictive performance (R-2 approximate to 0.99, RMSE approximate to 0.06), indicating its superior ability to capture nonlinear relationships, particularly for limited datasets. Sensitivity and partial dependence analyses identified carbonization temperature as the dominant factor controlling biochar yield, with sharp declines observed above 600 degrees C. Optimal yields of 52-55% were obtained at 400-500 degrees C and residence times of 10-15 min, while lower heating rates enhanced yield stability. Overall, the results demonstrate that advanced machine learning models provide reliable tools for optimizing biochar production and supporting sustainable thermochemical conversion of lignocellulosic waste for energy and carbon-oriented sustainability applications.