Open Catalyst 2020 (OC20) Dataset and Community Challenges

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.

Identifying Outstanding Transition-Metal-Alloy Heterogeneous Catalysts for the Oxygen Reduction and Evolution Reactions via Subgroup Discovery

“…This is addressed in reference [ 8 ] by using the sure-independence-screening-and-sparsifying-operator approach [ 32 ]. Similarly, we note that other AI strategies have been developed and applied for the accurate estimation of adsorption energies [ 33 , 34 ]. Contrary to such global approaches, however, SGD provides a local description focused only on specific desired behaviors.…”

Dynamics of Heterogeneous Catalytic Processes at Operando Conditions

“… 244 The currently available data sets include the Catalysis Hub, Open Catalyst 2020 (OC20) Data set, CMR project, etc. 244 − 247 Except for the limited number of data sets, the data set’s chemical diversity also limits the generalizability of ML predictions. 248 One more thing to take care of is the inconsistency of data sets, as they may obtain from different levels of theory.…”

Towards Universal Neural Network Potential for Material Discovery Applicable to Arbitrary Combination of 45 Elements

“…First, we demonstrate the performance of PFP architecture on the Structure to Energy and Forces (S2EF) task [20]. We used the S2EF 2M dataset as training data, which is a sub-dataset two orders of magnitude smaller than the largest dataset provided by OC20.…”

“…The Open Catalyst Project, which targets molecular adsorption in catalytic reactions, has constructed a massive surface adsorption structure dataset known as the Open Catalyst 2020 (OC20) dataset. [19,20] In this way, the area covered by NNPs has gradually expanded.…”

“…For PFP, the validation dataset is used instead. See original reference [20] for the definition of tasks.…”