Open Catalyst Project
Join us for the live webinars on:
April 26*, 27, and 28
The Open Catalyst Project is a collaborative research effort between Facebook AI Research (FAIR) and Carnegie Mellon University’s (CMU) Department of Chemical Engineering, and aims to develop new ML methods and models to accelerate the catalyst simulation process for renewable energy technologies and improve our ability to predict activity/selectivity across catalyst composition.
To achieve that in the short term, we need participation from the ML community in solving key challenges in catalysis. In this talk, we will first describe the OC20 dataset – a dataset of 134M training points coming from ~1.5M DFT relaxations across 53 elements and their binary/ternary materials, various low-index facets, and adsorbates spanning 56 common reaction intermediates with relevance to carbon, oxygen, and nitrogen thermal and electrochemical reactions. We will then describe some of our most recent modeling improvements on the OC20 dataset, specifically Graph Parallel (published at ICLR 2022) and GemNet-OC (under review), which are the current state-of-the-art on this dataset.