In a recent study published in Scientific Reports, Zaher Mundher Yaseen and Farah Loui Alhalimi explored the use of ensemble machine learning models to predict the adsorption efficiency of heavy metals. The research highlighted the potential of these models to improve heavy metal removal strategies.  

The authors applied several ensemble machine learning models, including Random Forest Regressor, Adaptive Boosting, Gradient Boosting, HistGradient Boosting, Extreme Gradient Boosting (XGBoost), and Light Gradient-Boosting Machine, to predict the adsorption efficiency of heavy metals like lead, cadmium, nickel, copper, and zinc. The models considered factors such as temperature, 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, and 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 characteristics. The data, consisting of 353 samples, were collected from open-source literature.  

The study revealed that the XGBoost model achieved the highest accuracy, with a determination coefficient of 0.92. Further analysis identified the initial concentration ratio of metals to biochar and pH as the most influential factors affecting adsorption efficiency. In contrast, physical properties like surface area and pore structure of biochar had minimal impact on efficiency.  

The researchers concluded that ensemble machine learning models, particularly XGBoost, can effectively predict heavy metal adsorption. These models offer a promising tool for developing efficient and targeted solutions for heavy metal removal in environmental applications.  

SOURCE: Yaseen, Z. M., & Alhalimi, F. L. (2025). Heavy metal adsorption efficiency prediction using biochar properties: a comparative analysis for ensemble machine learning models. Scientific Reports, 15(1), 13434.