Liu et al., in npj Clean Water, presented a machine learning (ML) approach to predict the ammonia nitrogen adsorption capacity of 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 and identify optimal conditions for maximizing its removal from aquatic systems. The study evaluated twelve ML models, including tree-based ensembles, kernel-based methods, and deep learning, using Bayesian optimization and cross-validation.

The results showed that tree-based ensemble models excelled, with CatBoost performing best (R2 = 0.9329, RMSE = 0.5378) and demonstrating strong generalization.  The study found that experimental conditions (67.2%) and biochar’s chemical properties (18.2%) most influenced adsorption capacity. Under specific experimental conditions (C0 > 50 mg/L and pHpH is a measure of how acidic or alkaline a substance is. A pH of 7 is neutral, while lower pH values indicate acidity and higher values indicate alkalinity. Biochars are normally alkaline and can influence soil pH, often increasing it, which can be beneficial More 6–9), a higher adsorption capacity could be achieved. A Python-based GUI incorporating CatBoost was developed to facilitate practical applications in designing efficient biochar adsorption systems.  

SOURCE: Liu, C., Balasubramanian, P., An, J., & Li, F. (2025). Machine learning prediction of ammonia nitrogen adsorption on biochar with model evaluation and optimization. npj Clean Water, 8(1), Article 13. https://doi.org/10.1038/s41545-024-00429-z