arXiv cs.AI· Kareem Hegazy, Eric C-Y Yuan, Anup Kumar, Dmitriy Morozov, Daniel Barter, Michael W Mahoney, Teresa Head-Gordon, Samuel M Blau·· 4 小时前AI 评分29
Popcornn:在机器学习势能面上用神经网络路径优化寻找过渡态
Neural Network Path Optimization for Finding Transition States on a Machine Learned Potential
AI 导读
Popcornn 框架通过在机器学习原子间势(MLIP)上优化连续神经网络路径并结合并行自适应数值积分器来寻找过渡态,消除了路径离散化伪影并降低超参数敏感性。在数千个有机反应的多种 MLIP 上,它比 nudged elastic band 和 growing string 等标准方法稳定找回更多正确过渡态。该框架在路径目标、积分策略和优化算法上均可灵活替换,适合高通量过渡态搜索。
正文 · 原文
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.
| Subjects: | Chemical Physics (physics.chem-ph); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22272 [physics.chem-ph] |
| (or arXiv:2611.22272v1 [physics.chem-ph] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22272 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kareem Hegazy [view email]
[v1]
Tue, 17 Nov 2026 06:18:18 UTC (25,394 KB)
来源:arXiv cs.AI · arxiv.org