Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery

arXiv:2404.10003v1 Announce Type: cross
Abstract: New technology for energy storage is necessary for the large-scale adoption of renewable energy sources like wind and solar. The ability to discover suitable catalysts is crucial for making energy storage more cost-effective and scalable. The Open Catalyst Project aims to apply advances in graph neural networks (GNNs) to accelerate progress in catalyst discovery, replacing Density Functional Theory-based (DFT) approaches that are computationally burdensome. Current approaches involve scaling GNNs to over 1 billion parameters, pushing …

abstract adoption advances apply arxiv catalyst cost cs.lg deep learning discovery energy energy storage graph making modelling new technology open catalyst physics.chem-ph project renewable scalable scale solar storage technology type wind