Predicting Heavy Metal Adsorption on Soil with Machine Learning and Mapping Global Distribution of Soil Adsorption Capacities

This study explores the use of machine learning models, specifically Random Forest, to predict the adsorption capacity of various heavy metals (Cd, Cu, Pb, Zn) on soil. By leveraging a comprehensive dataset of soil properties and adsorption experimental data, the research develops predictive models that can accurately estimate heavy metal retention. Furthermore, it aims to map the global distribution of soil adsorption capacities, providing valuable insights for environmental management and pollution control strategies. The findings highlight the potential of data-driven approaches in understanding and mitigating soil contamination.