The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts

Abstract

The development of machine learning models for electrocatalysts requires a broad set of training data to enable their use across a wide variety of materials. One class of materials that currently lacks sufficient training data is oxides, which are critical for the development of OER catalysts. To address this, we developed the OC22 dataset, consisting of 62,331 DFT relaxations (~9,854,504 single point calculations) across a range of oxide materials, coverages, and adsorbates. We define generalized total energy tasks that enable property prediction beyond adsorption energies; we test baseline performance of several graph neural networks; and we provide pre-defined dataset splits to establish clear benchmarks for future efforts. In the most general task, GemNet-OC sees a ~36% improvement in energy predictions when combining the chemically dissimilar OC20 and OC22 datasets via fine-tuning. Similarly, we achieved a ~19% improvement in total energy predictions on OC20 and a ~9% improvement in force predictions in OC22 when using joint training. We demonstrate the practical utility of a top performing model by capturing literature adsorption energies and important OER scaling relationships. We expect OC22 to provide an important benchmark for models seeking to incorporate intricate long-range electrostatic and magnetic interactions in oxide surfaces. Dataset and baseline models are open sourced, and a public leaderboard is available to encourage continued community developments on the total energy tasks and data.

50 pages, 14 figures

References in corpus (3)

• Rotation Invariant Graph Neural Networks using Spin Convolutions
• Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
• Two Wrongs Can Make a Right: A Transfer Learning Approach for Chemical Discovery with Chemical Accuracy

Cited by in corpus (22)

• AdsorbML: A Leap in Efficiency for Adsorption Energy Calculations using Generalizable Machine Learning Potentials
• On the redundancy in large material datasets: efficient and robust learning with less data
• Probing out-of-distribution generalization in machine learning for materials
• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• A reactive neural network framework for water-loaded acidic zeolites
• DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
• Machine Learning and Data-Driven Methods in Computational Surface and Interface Science
• Navigating chemical reaction space with a steering wheel
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO${}_2$ to Methanol Conversion
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Generator of Neural Network Potential for Molecular Dynamics: Constructing Robust and Accurate Potentials with Active Learning for Nanosecond-scale Simulations
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Scalable Training of Trustworthy and Energy-Efficient Predictive Graph Foundation Models for Atomistic Materials Modeling: A Case Study with HydraGNN
• Towards Foundation Models for Materials Science: The Open MatSci ML Toolkit
• $\Delta$-model correction of Foundation Model based on the models own understanding
• Rational design of nanoscale stabilized oxide catalysts for OER with OC22
• Machine-Learned Potentials for Solvation Modeling
• CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning
• FIRE-GNN: Force-informed, Relaxed Equivariance Graph Neural Network for Rapid and Accurate Prediction of Surface Properties
• Accelerating point defect simulations using data-driven and machine learning approaches
• Bridging Text and Crystal Structures: Literature-driven Contrastive Learning for Materials Science