Data-Driven Insights into Rare Earth Mineralization: Machine Learning Applications Using Functional Material Synthesis Data

Abstract

Quantitative understanding of rare earth element (REE) mineralization mechanisms, crucial for improving industrial separation, remains limited. This study leverages 1239 hydrothermal synthesis datapoints from material science as a surrogate for natural REE mineralization. We trained machine learning models (KNN, RF, XGBoost) using precursor, additive, and reaction data to predict product elements and phases, validating predictions with new experiments. XGBoost exhibited the highest accuracy, with feature importance analysis indicating thermodynamic properties were critical for predictions. Observed correlations among reaction parameters aligned with classical crystallization theory. Further XGBoost models successfully predicted reaction temperature and pH from precursor/product data. Our findings demonstrate the cross-disciplinary utility of material science data for geochemical understanding, underscore the need for research on less-studied REE minerals (e.g., carbonates, heavy REEs), and suggest potential to accelerate REE resource development.