Zero-valent iron based materials selection for permeable reactive barrier using machine learning.

The zero-valent iron (ZVI) based reactive materials are potential remediation reagents in permeable reactive barriers (PRB). Considering that reactive materials is the essential to determining the long-term stability of PRB and the emergence of a large number of new iron-based materials. Here, we present a new approach using machine learning to screen PRB reactive materials, which proposes to improve the efficiency and practicality of selection of ZVI-based materials. To compensate for the insufficient amount of existing machine learning source data and the real-world implementation, machine learning combines evaluation index (EI) and reactive material experimental evaluations. XGboost model is applied to estimate the kinetic data and SHAP is used to improve the accuracy of model. Batch and column tests were conducted to investigate the geochemical characteristics of groundwater. The study find that specific surface area is a fundamental factor correlated with the kinetic constants of ZVI-based materials, according to SHAP analysis. Reclassifying the data with specific surface area significantly improved prediction accuracy (reducing RMSE from 1.84 to 0.6). Experimental evaluation results showed that ZVI had 3.2 times higher anaerobic corrosion reaction kinetic constants and 3.8 times lower selectivity than AC-ZVI. Mechanistic studies revealed the transformation pathways and endpoint products of iron compounds. Overall, this study is a successful initial attempt to use machine learning for selecting reactive materials.