Computation has emerged as a powerful tool for accelerating the discovery of new materials and molecules: first through first-principles simulation in high throughput screening and very recently even further with machine learning (ML). Unique challenges remain for the accelerated discovery and design of inorganic complexes, despite the highly tunable electronic structure properties that make these materials so compelling for applications in energy storage and catalysis. Density functional theory (DFT) is the method of choice in most computational screening, but DFT is simultaneously too computationally costly and inaccurate for the predictive design of open-shell transition metal complex properties. I will describe our recent efforts to overcome both of these challenges through developing ML models (e.g., artificial neural networks and kernel ridge regression) that predict key first-principles energetic (e.g., spin-state ordering and redox potential) and geometric properties to within the accuracy of the underlying simulation method that provides the training data. I will describe our efforts to use these ML models for extrapolative applications (i.e., design) by incorporating heuristics for ML model uncertainty in a genetic algorithm to discover new inorganic compounds. I will present our recent efforts to further unify ML and first-principles simulation models by developing ML classifiers that predict simulation "promise" in a data driven fashion, both with respect to methodology choice (i.e., when beyond DFT is needed) and with respect to whether materials are expected to be computationally stable. Finally, I will describe how we have incorporated all of these advances into open source codes disseminated in a user-friendly format for the broader scientific community.

Accelerating inorganic discovery with machine learning and automation

256th National Meeting (2018)

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.