physics.chem-phNov 17, 2026

Neural Network Path Optimization for Finding Transition States on a Machine Learned Potential

Authors: Kareem Hegazy, Eric C-Y Yuan, Anup Kumar, Dmitriy Morozov, Daniel Barter, Michael W Mahoney, Teresa Head-Gordon, Samuel M Blau

Organizations: Department of Statistics, University of California, Berkeley, 94720, CA, USA. · International Computer Science Institute, Berkeley, 94704, CA, USA. · Kenneth S. Pitzer Theory Center and Department of Chemistry, University of California, Berkeley, 94720, CA, USA. · Chemical Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, 94720, CA, USA. · 

Abstract

Transition states govern chemical reaction rates and outcomes, yet locating them remains a central challenge in computational chemistry. Double-ended search methods find transition states given reactant and product structures, but generally rely on discretized path representations developed for density functional theory, where potential energy surface evaluations are expensive. Machine learned interatomic potentials (MLIPs) dramatically reduce this cost and leverage automatic differentiation to access higher-order derivatives efficiently. We introduce Popcornn, a framework to find transition states by optimizing continuous neural network paths atop an MLIP with a parallelized adaptive numerical integrator. This combination eliminates path discretization artifacts, reduces hyperparameter sensitivity, and enables non-local optimization to overcome local features using second-order potential-energy-surface information. Popcornn consistently recovers more correct transition states than standard methods such as nudged elastic band and growing string, across MLIPs on thousands of organic reactions, establishing it as a robust, automation-ready method for high-throughput transition state search. Popcornn's infrastructure is flexible in path objective, integration strategy, and optimization algorithm, making it a practical tool and platform for investigating open questions in MLIP-based path optimization.

Explore similar work

CardsList
  1. A Priori Sampling of Transition States with Guided Diffusion

    Mar 26, 2026Hyukjun Lim, Soojung Yang, Lucas Pinède +3Diffusion Model GuidanceDiffusion Sampling

  2. Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials

    Jul 2, 2026Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng +4Machine Learning Interatomic PotentialsNeural Network Optimization

  3. All Paths All at Once: A Quantum Monte Carlo and Neural Committor Approach to Reaction Pathway Search

    Oct 29, 2026Chien-Chai ChangChemical Reaction Prediction