Machine learning predicts heavy metal adsorption on iron (oxyhydr)oxides: A combined insight into the adsorption efficiency and binding configuration.

ABSTRACT

The adsorption of heavy metal on iron (oxyhydr)oxides is one of the most vital geochemical/chemical processes controlling the environmental fate of these contaminants in natural and engineered systems. Traditional experimental methods to investigate this process are often time-consuming and labor-intensive due to the complexity of influencing factors. Herein, a comprehensive database containing the adsorption data of 11 heavy metals on 7 iron (oxyhydr)oxides was constructed, and the machine learning models was successfully developed to predict the adsorption efficiency. The random forest (RF) models achieved high prediction performance (R2 > 0.9, RMSE < 0.1, and MAE < 0.07) and interpretability. Key factors influencing heavy metal adsorption efficiency were identified as mineral surface area, solution pH, metal concentration, and mineral concentration. Additionally, by integrating our previous binding configuration models, we elucidated the simultaneous effects of input features on adsorption efficiency and binding configuration through partial dependence analysis. Higher pH simultaneously enhanced adsorption efficiency and affinity for cations, whereas lower pH benefited that for oxyanions. While higher mineral surface area improved the metal adsorption efficiency, the adsorption affinity could be weakened. This work presents a data-driven approach for investigating metal adsorption behavior and elucidating the influencing mechanisms from macroscopic to microcosmic scale, thereby offering comprehensive guidance for predicting and managing the environmental behavior of heavy metals.