推广含显式高阶多体关联的Abell-Tersoff键级势，用于势能面的鲁棒外推
Generalizing Abell-Tersoff bond-order potential with explicit high-order many-body correlations for robust extrapolation of potential energy surfaces
浏览论文内容
中文总结 AI 辅助
该研究推广Abell-Tersoff键级势并引入显式高阶多体关联，构建半参数原子间势，在多数据集上实现与现有MLIP相当的插值精度，且外推性能更优，为优化MLIP外推能力提供了思路。
中文摘要 AI 辅助
机器学习原子间势（MLIP）可实现准确高效的原子模拟，但其在训练域之外的分布外构型上的可靠性仍是重大挑战。为解决该问题，本文提出一种基于Abell-Tersoff键级势推广的半参数原子间势，具有化学信息感知的函数形式和显式高阶多体关联。模型在硅、碳、水及小分子等多种数据集上训练与评估，插值精度与现有MLIP模型相当，且对未见过的构型（包括高压、高温条件下的构型）展现出更优外推性能。这些结果表明，函数形式中融入物理动机约束可改善原子间势的外推行为，为控制机器学习原子间势外推的归纳偏置提供了见解。
英文摘要
Machine-learning interatomic potentials enable accurate and efficient atomistic simulations, yet their reliability for out-of-distribution configurations far beyond the training domain remains a significant challenge. Here, we introduce a semiparametric interatomic potential based on a generalization of the Abell--Tersoff bond-order potential, incorporating a chemically informed functional form and explicit high-order many-body correlations to address this challenge. The model is trained and evaluated on various datasets of silicon, carbon, water, and small molecules, achieving interpolation accuracy comparable to existing MLIP models while exhibiting improved extrapolation to unseen configurations, including those at high pressures and temperatures. These results provide insights into the design of specific inductive biases for reliable extrapolation in interatomic potentials. inductive biases that can be used to control extrapolation in machine-learning interatomic potentials.
