Data-driven transfer learning across MOF-derived zirconia polymorphs

Abstract

Despite extensive investigation of metal-organic framework (MOF) derived materials over the last 20 years, no systematic approach to predict the structural properties of the derived metal oxides is available. We present an integrated machine learning (ML) approach leveraging Smooth Overlap of Atomic Positions (SOAP) and multiple ML models, including Kernel Ridge Regression (KRR), to predict thermally derived zirconium dioxide (ZrO2) polymorph from diverse Zr-based precursors. By a systematic experimental dataset of calcination parameters, we train the ML model to quantitatively forecast material properties and the weight fraction of crystalline phases of the resulting ZrO2. Experimental validation of model predictions confirms that the chemical composition of precursors and calcination parameters have a profound influence on the crystallinity of MOF-derived ZrO2 polymorph. Our findings demonstrate the utility of small-data-driven predictive ML modeling and transfer learning for guiding the synthesis of advanced oxide materials providing a blueprint for accelerated discovery of MOF-derived nanomaterials.