Climate Challenges with Chemistry and Materials using Open Datasets and Models

Abstract

Machine learning accelerated catalyst discovery efforts have seen much progress in the last few years. Datasets of computational calculations have improved, models to connect surface structure with electronic structure or adsorption energies have gotten more sophisticated, and active learning exploration strategies are becoming routine in discovery efforts. Large-scale data and machine learning modeling efforts like the Open Catalyst Project (https://opencatalystproject.org/, https://fair-chem.github.io) have elevated computational catalysis to a first-class problem in the broader machine learning community and led to rapid improvements in accuracy with new state-of-the-art AI/ML models appearing every 3-4 months since 2020. The resulting models are now accurate enough to assist with many day-to-day catalyst simulation efforts (CatTsunami, AdsorbML), and to share the capabilities with the community we have released an online demo (https://open-catalyst.metademolab.com/) and representative case studies. I will finally discuss current and future efforts to build similar approaches for other climate-related and materials challenges like direct air capture via the OpenDAC collaboration (https://open-dac.github.io/).

Biography

Zack Ulissi is a research scientist on the FAIR Chemistry team in Meta’s Fundamental AI Research lab and an Adjunct Professor of Chemical Engineering at Carnegie Mellon University. He has led several open science projects and community efforts, the most notable of which is the Open Catalyst Project (https://opencatalystproject.org/ ). Prior to Meta, he was an Associate Professor of Chemical Engineering. He completed his undergraduate work at the University of Delaware, M.A.St. at Cambridge, PhD at MIT on carbon nanotube devices with Michael Strano and Richard Braatz, and post-doc in catalysis at Stanford with Jens Nørskov.