The Open Catalyst 2020 (OC20) Dataset and Community Challenges

By Lowik Chanussot, Abhishek Das, Siddharth Goyal, Thibaut Lavril, Muhammed Shuaibi, Morgane Rivière, Kevin Tran, Javier Heras-Domingo, Caleb Ho, Weihua Hu and 7 more. ACS Catalysis, 2020

822 citations recorded by the source corpus.

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 1,281,121 Density Functional Theory (DFT) relaxations (264,900,500 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 (SchNet, Dimenet, CGCNN) 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.

Subfields: Materials Chemistry, Renewable Energy, Sustainability and the Environment

View Paper: https://www.semanticscholar.org/paper/966ea7df97a5c38d04710dd4bb393b8acaef4d9a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

Citations in the corpus

An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage (2020, background): “The inputs to the OC20 tasks include the atoms, catalyst and adsorbate information.”
Large-Scale Representation Learning on Graphs via Bootstrapping (2021, neutral): “Graphs provide a powerful abstraction for complex datasets that arise in a variety of applications such as social networks, transportation networks, and biological sciences (Hamilton et al., 2017; Derrow-Pinion et al., 2021; Zitnik & Leskovec, 2017; Chanussot et al., 2021).”
Geometric and Physical Quantities improve E(3) Equivariant Message Passing (2021, methodology): “Table 4 shows SEGNN results on the OC20 dataset and comparisons with existing methods.”
EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations (2023, positive): “However, the memory complexity of triplet and quadruplet representations of atoms do not scale well with the number of atoms, and this requires additional modifications like interaction hierarchy used by GemNet-OC [51] for large datasets like OC20 [30].”
Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements (2021, methodology): “See the original reference [1] for the definition of the tasks.”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “The OC20 dataset has been recently introduced, containing 200+ million samples from quantum chemistry simulations relevant to the discovery of new catalysts for renewable energy storage and other energy applications (Becke, 2014; Chanussot et al., 2020; Zitnick et al., 2020).”
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs (2022, background): “0 license), and ocp [10] (MIT license).”
Crystal Diffusion Variational Autoencoder for Periodic Material Generation (2021, background): “The Open Catalyst Project (OCP) provides a platform for comparing different architectures by predicting energies and forces from the periodic structure of catalytic surfaces (Chanussot et al., 2021).”
GemNet: Universal Directional Graph Neural Networks for Molecules (2021, methodology): “The open catalyst (OC20) dataset [8, CC-BY 4.0] consists of energy relaxation trajectories of solid catalysts with adsorbate molecules.”
OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs (2021, background): “…(Ying et al., 2018), hyperlinked Web documents (Kleinberg, 1999), knowledge graphs (KGs) (Bollacker et al., 2008; Vrandečić and Krötzsch, 2014), as well as the molecule simulation data generated by the ever-increasing scientific computation (Nakata and Shimazaki, 2017; Chanussot et al., 2021).”