Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations.

ABSTRACT: Recent developments in computational chemistry facilitate the automated quantum chemical exploration of chemical reaction networks for the in-silico prediction of synthesis pathways, yield, and selectivity. However, the underlying quantum chemical energy calculations require vast computational resources, limiting these explorations severely in practice. Machine learning potentials (MLPs) offer a solution to increase computational efficiency, while retaining the accuracy of reliable first-principles data used for their training. Unfortunately, MLPs will be limited in their generalization ability within chemical (reaction) space, if the underlying training data are not representative for a given application. Within the framework of automated reaction network exploration, where new reactants

SUBMITTER: Eckhoff M 

PROVIDER: S-EPMC12529901 | biostudies-literature | 2025 Oct

REPOSITORIES: biostudies-literature