Agricultural Residue Biomass Utilization for Energy Generation: A Machine Learning-Driven Approach
Keywords:
Agriculture residue, Machine Learning, Calorific value, Ash content, Biomass.Abstract
The quest for sustainable energy solutions has sparked intense research into biomass utilization, a crucial step towards mitigating climate change and weaning ourselves off fossil fuels. This study delves into the application of computational intelligence to optimize the efficiency of agriculture residual biomass for energy production. Author developed a machine
learning framework that provides Random Forest and Gradient Boosting models to predict and optimize the calorific value and ash content of biomass. To unravel the intricacies of our models, employed SHapley Additive exPlanations (SHAP) values, which revealed that the rice husk, sugarcane bagasse and wheat husk biomass to Cow Dung Ratio exerted the most profound influence on both calorific value and ash content predictions. Notably, the Gradient Boosting model underscored the significance of Biomass Type, whereas the Random Forest model emphasized the critical role of Particle Size
References
L. Chen, L. Xing, and L. Han, “Renewable energy from agro-residues in China: Solid biofuels and biomass briquetting technology,” Renew. Sustain. Energy Rev., vol. 13, no. 9, pp. 2689–2695, 2009, doi: https://doi.org/10.1016/j.rser.2009.06.025. [2] S. Magagula, J. Han, X. Liu, and B. C. Sempuga, “Targeting efficient biomass gasification,” Chinese J. Chem. Eng., vol. 33, pp. 268–278, 2021, doi: https://doi.org/10.1016/j.cjche.2020.11.027. [3] A. Kumar Sharma, P. Kumar Ghodke, N. Goyal, S. Nethaji, and W. H. Chen, “Machine learning technology in biohydrogen production from agriculture waste: Recent advances and future perspectives,” Bioresour. Technol., vol. 364, p. 128076, 2022, doi: 10.1016/j.biortech.2022.128076.
