In the quest for sustainable energy solutions, converting waste to energy through a process called pyrolysisPyrolysis is a thermochemical process that converts waste biomass into bio-char, bio-oil, and pyro-gas. It offers significant advantages in waste valorization, turning low-value materials into economically valuable resources. Its versatility allows for tailored products based on operational conditions, presenting itself as a cost-effective and efficient More has gained significant attention. Among the products of pyrolysis, biocharBiochar is a carbon-rich material created from biomass decomposition in low-oxygen conditions. It has important applications in environmental remediation, soil improvement, agriculture, carbon sequestration, energy storage, and sustainable materials, promoting efficiency and reducing waste in various contexts while addressing climate change challenges. More stands out for its versatility and potential benefits in various applications, including soil improvement and carbon sequestration. The yield of biochar, however, is influenced by various factors, making it challenging to predict and optimize production.   In a recent study published in Scientific Reports, Uppalapati et al. (2025) employed machine learning techniques to develop a predictive model for biochar yield. The researchers utilized a dataset of 134 samples, encompassing different biomassBiomass is a complex biological organic or non-organic solid product derived from living or recently living organism and available naturally. Various types of wastes such as animal manure, waste paper, sludge and many industrial wastes are also treated as biomass because like natural biomass these More types and pyrolysis conditionsThe conditions under which pyrolysis takes place, such as temperature, heating rate, and residence time, can significantly affect the properties of the biochar produced.   More, to train and evaluate five machine learning models: Lasso regression, Tweedie regression, random forest, XGBoost, and Gradient boosting regression.  

Among these models, XGBoost emerged as the superior performer, achieving a remarkable accuracy in predicting biochar yield. The model demonstrated an R-squared value of 0.9739 for the training data and 0.8875 for the test data, indicating its ability to explain a significant portion of the variability in biochar yield. The mean absolute percentage error (MAPE) was also impressively low, at 2.14% for training and 3.8% for testing, further confirming the model’s accuracy. The researchers also employed SHAP (SHapley Additive exPlanations) analysis to interpret the XGBoost model and identify the key factors influencing biochar yield. They found that ashAsh is the non-combustible inorganic residue that remains after organic matter, like wood or biomass, is completely burned. It consists mainly of minerals and is different from biochar, which is produced through incomplete combustion.   Ash Ash is the residue that remains after the complete More content and moisture negatively impacted biochar yield, while factors such as final pyrolysis temperature (FPT), nitrogen content, and carbon content had a significant positive influence.  

This study highlights the potential of machine learning in predicting and optimizing biochar production. The XGBoost model developed by Uppalapati et al. (2025) offers a valuable tool for researchers and practitioners in the field of biochar, enabling them to make informed decisions regarding feedstockFeedstock refers to the raw organic material used to produce biochar. This can include a wide range of materials, such as wood chips, agricultural residues, and animal manure. More selection and pyrolysis conditions to maximize biochar yield and its associated benefits.  

Source: Uppalapati, S., Paramasivam, P., Kilari, N., Chohan, J. S., Kanti, P. K., Vemanaboina, H., Dabelo, L. H., & Gupta, R. (2025). Precision biochar yield forecasting employing random forest and XGBoost with Taylor diagram visualization. Scientific Reports, 15(1), Article 7105. https://doi.org/10.1038/s41598-025-91450-w