The Open Catalyst 2020 (OC20) Dataset and Community Challenges
| Autor: | Brandon Wood, Lowik Chanussot, Weihua Hu, Zachary W. Ulissi, Muhammed Shuaibi, Siddharth Goyal, Devi Parikh, Morgane Riviere, Thibaut Lavril, Anuroop Sriram, C. Lawrence Zitnick, Kevin Tran, Aini Palizhati, Javier Heras-Domingo, Junwoong Yoon, Caleb Ho, Abhishek Das |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Condensed Matter - Materials Science Computer Science - Machine Learning ComputingMilieux_THECOMPUTINGPROFESSION 010405 organic chemistry business.industry Materials Science (cond-mat.mtrl-sci) FOS: Physical sciences General Chemistry Environmental economics 010402 general chemistry Solar fuel 01 natural sciences Catalysis Energy storage 0104 chemical sciences Renewable energy Machine Learning (cs.LG) Production (economics) business |
| Popis: | Catalyst discovery and optimization is key to solving many societal and energy challenges including solar fuels 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 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 pre-defined 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, 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. 37 pages, 11 figures, submitted to ACS Catalysis |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|