国家(计算机科学)
人工智能
计算机科学
曲面(拓扑)
物理
过渡(遗传学)
机器学习
催化作用
特征(语言学)
数学
统计物理学
理论物理学
化学
算法
理论(学习稳定性)
作者
Raffaele Cheula,Mie Andersen,John R. Kitchin
标识
DOI:10.1038/s41524-026-02228-1
摘要
Determining transition states (TSs) of surface reactions is central to understanding and designing heterogeneous catalysts but remains computationally prohibitive with density functional theory (DFT). While machine learning potentials (MLPs) offer significant speedups, task-specific models have limited transferability across catalytic systems, and universal MLPs (uMLPs) lack the accuracy needed for reactive configurations. Here, we present a workflow based on active learning to iteratively fine-tune uMLPs for DFT-quality TS search. Using 250 TSs from the CO 2 hydrogenation reaction network on metal and single-atom alloy surfaces, we first benchmark TS search algorithms, identifying the Sella algorithm as most robust, and propose a modification (Bond-Aware Sella) that substantially improves its success rate. We then explore sequential and batch active-learning strategies for fine-tuning and show that DFT-quality TS structures can be found using only 8 DFT single-point calculations on average per structure. This demonstrates the viability of fine-tuned uMLPs for high-throughput catalyst screening.
科研通智能强力驱动
Strongly Powered by AbleSci AI