Experimentally validated inverse design of multi-property Fe-Co-Ni alloys.

This study presents a machine learning (ML) framework aimed at accelerating the discovery of multi-property optimized Fe-Ni-Co alloys, addressing the time-consuming, expensive, and inefficient nature of traditional methods of material discovery, development, and deployment. We compiled a detailed heterogeneous database of the magnetic, electrical, and mechanical properties of Fe-Co-Ni alloys, employing a novel ML-based imputation strategy to address gaps in property data. Leveraging this comprehensive database, we developed predictive ML models using tree-based and neural network approaches for optimizing multiple properties simultaneously. An inverse design strategy, utilizing multi-objective Bayesian optimization (MOBO), enabled the identification of promising alloy compositions. This approach was experimentally validated using high-throughput methodology, highlighting alloys such as Fe66.8Co28Ni5.2 and Fe61.9Co22.8Ni15.3, which demonstrated superior properties. The predicted properties data closely matched experimental data within 14% accuracy. Our approach can be extended to a broad range of materials systems to predict novel materials with an optimized set of properties.

Machine-Learning-Assisted Discovery of Mechanosynthesized Lead-Free Metal Halide Perovskites for the Oxidative Photocatalytic Cleavage of Alkenes.

Lead-free metal halide perovskites can potentially be air- and water-stable photocatalysts for organic synthesis, but there are limited studies on them for this application. Separately, machine learning (ML), a critical subfield of artificial intelligence, has played a pivotal role in identifying correlations and formulating predictions based on extensive datasets. Herein, an iterative workflow by incorporating high-throughput experimental data with ML to discover new lead-free metal halide perovskite photocatalysts for the aerobic oxidation of styrene is described. Through six rounds of ML optimization guided by SHapley Additive exPlanations (SHAP) analysis, BA2CsAg0.95Na0.05BiBr7 as a photocatalyst that afforded an 80% yield of benzoic acid under the standard conditions is identified, which is a 13-fold improvement compared to the 6% with when using Cs2AgBiBr6 as the initial photocatalyst benchmark that is started. BA2CsAg0.95Na0.05BiBr7 can tolerate various functional groups with 22 styrene derivatives, highlighting the generality of the photocatalytic properties demonstrated. Radical scavenging studies and density functional theory calculations revealed that the formation of the reactive oxygen species superoxide and singlet oxygen in the presence of BA2CsAg0.95Na0.05BiBr7 are critical for photocatalysis.