No abstract

No abstract

Catalyst discovery and optimization is key to solving many societal and energy challenges including solar fuel synthesis, long-term energy storage, and renewable fertilizer production. Despite considerable effort by the catalysis community to apply machine learning models to the computational catalyst discovery process, it remains an open challenge to build models that can generalize across both elemental compositions of surfaces and adsorbate identity/configurations, perhaps because datasets have been smaller in catalysis than in related fields. To address this, we developed the OC20 dataset, consisting of 1,281,040 density functional theory (DFT) relaxations (∼264,890,000 single-point evaluations) across a wide swath of materials, surfaces, and adsorbates (nitrogen, carbon, and oxygen chemistries). We supplemented this dataset with randomly perturbed structures, short timescale molecular dynamics, and electronic structure analyses. The dataset comprises three central tasks indicative of day-to-day catalyst modeling and comes with predefined train/validation/test splits to facilitate direct comparisons with future model development efforts. We applied three state-of-the-art graph neural network models (CGCNN, SchNet, and DimeNet++) to each of these tasks as baseline demonstrations for the community to build on. In almost every task, no upper limit on model size was identified, suggesting that even larger models are likely to improve on initial results. The dataset and baseline models are both provided as open resources as well as a public leader board to encourage community contributions to solve these important tasks.

Developing active and stable oxygen evolution catalysts is a key to enabling various future energy technologies and the state-of-the-art catalyst is Ir-containing oxide materials. Understanding oxygen chemistry on oxide materials is significantly more complicated than studying transition metal catalysts for two reasons: the most stable surface coverage under reaction conditions is extremely important but difficult to understand without many detailed calculations, and there are many possible active sites and configurations on O* or OH* covered surfaces. We have developed an automated and high-throughput approach to solve this problem and predict OER overpotentials for arbitrary oxide surfaces. We demonstrate this for a number of previously-unstudied IrO2 and IrO3 polymorphs and their facets. We discovered that low index surfaces of IrO2 other than rutile (110) are more active than the most stable rutile (110), and we identified promising active sites of IrO2 and IrO3 that outperform rutile (110) by 0.2 V in theoretical overpotential. Based on findings from DFT calculations, we pro-vide catalyst design strategies to improve catalytic activity of Ir based catalysts and demonstrate a machine learning model capable of predicting surface coverages and site activity. This work highlights the importance of investigating unexplored chemical space to design promising catalysts. File list (2)download file view on ChemRxiv oxide_manuscript.pdf (16.03 MiB) download file view on ChemRxiv oxide_supporting_information.pdf (7.81 MiB)

Data science and informatics tools have been proliferating recently within the computational materials science and catalysis fields. This proliferation has spurned the creation of various frameworks for automated materials screening, discovery, and design. Underpinning these frameworks are surrogate models with uncertainty estimates on their predictions. These uncertainty estimates are instrumental for determining which materials to screen next, but the computational catalysis field does not yet have a standard procedure for judging the quality of such uncertainty estimates. Here we present a suite of figures and performance metrics derived from the machine learning community that can be used to judge the quality of such uncertainty estimates.This suite probes the accuracy, calibration, and sharpness of a model quantitatively.We then show a case study where we judge various methods for predicting densityfunctional-theory-calculated adsorption energies. Of the methods studied here, we find that the best performer is a model where a convolutional neural network is used 1 arXiv:1912.10066v2 [cond-mat.mtrl-sci] to supply features to a Gaussian process regressor, which then makes predictions of adsorption energies along with corresponding uncertainty estimates.