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

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.

Predicting the binding configuration and release potential of heavy metals on iron (oxyhydr)oxides: A machine learning study on EXAFS.

Heavy metals raise a global concern and can be easily retained by ubiquitous iron (oxyhydr)oxides in natural and engineered systems. The complex interaction between iron (oxyhydr)oxides and heavy metals results in various mineral-metal binding configurations, such as outer-sphere complexes and edge-sharing inner-sphere complexes, which determine the accumulation and release of heavy metals in the environment. However, traditional experimental approaches are time-consuming and inadequate to elucidate the complex binding relationships and configurations between iron (oxyhydr)oxides and heavy metals. Herein, a workflow that integrates the binding configuration data of 11 heavy metals on 7 iron (oxyhydr)oxides and then trains machine learning models to predict unknown binding configurations was proposed. The well-trained multi-grained cascade forest models exhibited high accuracy (> 90%) and predictive performance (R2 ∼ 0.75). The underlying effects of mineral properties, metal ion species, and environmental conditions on mineral-metal binding configurations were fully interpreted with data mining. Moreover, the metal release rate was further successfully predicted based on mineral-metal binding configurations. This work provides a method to accurately and quickly predict the binding configuration of heavy metals on iron (oxyhydr)oxides, which would provide guidance for estimating the potential release behavior of heavy metals and remediating heavy metal pollution in natural and engineered environments.