Open challenges in developing generalizable large-scale machine-learning models for catalyst discovery
Published in ACS Catalysis, 2022
Citation: Adeesh Kolluru, Muhammed Shuaibi, Aini Palizhati, Nima Shoghi, Abhishek Das, Brandon Wood, C Lawrence Zitnick, John R Kitchin, Zachary W Ulissi, ACS Catalysis 12 (14), 8572-8581, 2022 https://pubs.acs.org/doi/abs/10.1021/acscatal.2c02291
This paper discusses the challenges in developing generalizable machine learning models for catalyst discovery. While current approaches are effective for specific chemistries and compositions, they struggle to generalize across diverse chemical spaces. The paper highlights the potential of large-scale catalyst datasets like the Open Catalyst 2020 Data set (OC20) to enable the development of universal machine learning potentials that could accelerate catalyst discovery across various applications without requiring specialized training efforts.