Brook Wander, Muhammed Shuaibi, John R. Kitchin, Zachary W. Ulissi, C. Lawrence Zitnick
{"title":"CatTSunami: Accelerating Transition State Energy Calculations with Pretrained Graph Neural Networks","authors":"Brook Wander, Muhammed Shuaibi, John R. Kitchin, Zachary W. Ulissi, C. Lawrence Zitnick","doi":"10.1021/acscatal.4c04272","DOIUrl":null,"url":null,"abstract":"Direct access to transition state energies at low computational cost unlocks the possibility of accelerating catalyst discovery. We show that the top performing graph neural network potential trained on the OC20 data set, a related but different task, is able to find transition states energetically similar (within 0.1 eV) to density functional theory (DFT) 91% of the time with a 28× speedup. This speaks to the generalizability of the models, having never been explicitly trained on reactions, the machine learned potential approximates the potential energy surface well enough to be performant for this auxiliary task. We introduce the Open Catalyst 2020 Nudged Elastic Band (OC20NEB) data set, which is made of 932 DFT nudged elastic band calculations, to benchmark machine learned model performance on transition state energies. To demonstrate the efficacy of this approach, we for the first time explicitly treated a large reaction network with 61 intermediates and 174 dissociation reactions at DFT resolution (40 meV). To find low energy transition states we densely enumerate many possible NEBs. Using DFT this would have taken 52 GPU years. With ML we realized a 1500× speedup for dense enumerations, using just 12 GPU days of compute. Similar searches for complete reaction networks could become routine using the approach presented here. Finally, we constructed an ammonia synthesis activity volcano and systematically found lower energy configurations of the transition states and intermediates on six stepped unary surfaces than had previously been reported. This scalable approach offers a more complete treatment of configurational space to improve and accelerate catalyst discovery.","PeriodicalId":9,"journal":{"name":"ACS Catalysis ","volume":"18 1","pages":""},"PeriodicalIF":11.3000,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Catalysis ","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1021/acscatal.4c04272","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Direct access to transition state energies at low computational cost unlocks the possibility of accelerating catalyst discovery. We show that the top performing graph neural network potential trained on the OC20 data set, a related but different task, is able to find transition states energetically similar (within 0.1 eV) to density functional theory (DFT) 91% of the time with a 28× speedup. This speaks to the generalizability of the models, having never been explicitly trained on reactions, the machine learned potential approximates the potential energy surface well enough to be performant for this auxiliary task. We introduce the Open Catalyst 2020 Nudged Elastic Band (OC20NEB) data set, which is made of 932 DFT nudged elastic band calculations, to benchmark machine learned model performance on transition state energies. To demonstrate the efficacy of this approach, we for the first time explicitly treated a large reaction network with 61 intermediates and 174 dissociation reactions at DFT resolution (40 meV). To find low energy transition states we densely enumerate many possible NEBs. Using DFT this would have taken 52 GPU years. With ML we realized a 1500× speedup for dense enumerations, using just 12 GPU days of compute. Similar searches for complete reaction networks could become routine using the approach presented here. Finally, we constructed an ammonia synthesis activity volcano and systematically found lower energy configurations of the transition states and intermediates on six stepped unary surfaces than had previously been reported. This scalable approach offers a more complete treatment of configurational space to improve and accelerate catalyst discovery.
期刊介绍:
ACS Catalysis is an esteemed journal that publishes original research in the fields of heterogeneous catalysis, molecular catalysis, and biocatalysis. It offers broad coverage across diverse areas such as life sciences, organometallics and synthesis, photochemistry and electrochemistry, drug discovery and synthesis, materials science, environmental protection, polymer discovery and synthesis, and energy and fuels.
The scope of the journal is to showcase innovative work in various aspects of catalysis. This includes new reactions and novel synthetic approaches utilizing known catalysts, the discovery or modification of new catalysts, elucidation of catalytic mechanisms through cutting-edge investigations, practical enhancements of existing processes, as well as conceptual advances in the field. Contributions to ACS Catalysis can encompass both experimental and theoretical research focused on catalytic molecules, macromolecules, and materials that exhibit catalytic turnover.