通过蒸馏多时间步长和非保守力加速基于神经网络势的分子动力学
Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces
AI总结：
提出DMTS-NC方法，利用蒸馏多时间步长和非保守力策略，结合基础神经网络模型（如FeNNix-Bio1）加速原子分子动力学模拟，在保持精度的同时实现15-30%的额外加速，并支持氢质量再分配和氢摩擦以扩展时间步长至10 fs。
摘要：
继我们之前的工作（J. Phys. Chem. Lett., 2026, 17, 5, 1288-1295）之后，我们提出了DMTS-NC方法，这是一种使用非保守力的蒸馏多时间步长策略，用于进一步加速使用基础神经网络模型（如FeNNix-Bio1）的原子分子动力学模拟。该方法采用双层可逆参考系统传播算法（RESPA）形式，将目标精确保守势与为产生非保守力而优化的简化蒸馏表示耦合。尽管是非保守的，但蒸馏架构被设计为强制执行关键物理先验，例如旋转等变性和原子力分量的抵消。这些选择促进了蒸馏过程，从而大幅提高了模拟的鲁棒性，显著限制了两种模型之间的异常差异，从而实现了与力数据的极好一致性。总体而言，DMTS-NC方案比其保守对应方案更稳定、更高效，额外加速比DMTS达到15-30%。无需微调步骤，它更易于实现，并且可以推至系统物理共振的极限，以在保持精度的同时提供最大效率。我们通过结合氢质量再分配（HMR）和高氢摩擦（HHF）获得了额外的加速，将方案的最大时间步长进一步扩展到10 fs，同时保持稳定性和精度。与DMTS一样，DMTS-NC适用于任何神经网络势，并且可以应用于计算量比FeNNix-Bio1更大的方法。我们展示了将该方法应用于MACE-OFF23蒸馏的原理验证，与单时间步长相比，获得了3.66至5.64的加速比。
英文摘要：
Following our previous work (J. Phys. Chem. Lett., 2026, 17, 5, 1288-1295), we propose the DMTS-NC approach, a distilled multi-time-step (DMTS) strategy using non-conservative (NC) forces to further accelerate atomistic molecular dynamics simulations using foundation neural network models such as FeNNix-Bio1. There, a dual-level reversible reference system propagator algorithm (RESPA) formalism couples a target accurate conservative potential to a simplified distilled representation optimized for the production of non-conservative forces. Despite being non-conservative, the distilled architecture is designed to enforce key physical priors, such as equivariance under rotation and cancellation of atomic force components. These choices facilitate the distillation process and therefore improve drastically the robustness of simulation, significantly limiting abnormal discrepancies between the two models, thus achieving excellent agreement with the forces data. Overall, the DMTS-NC scheme is found to be more stable and efficient than its conservative counterpart with additional speedups reaching 15-30% over DMTS. Requiring no fine-tuning steps, it is easier to implement and can be pushed to the limit of the systems physical resonances to maintain accuracy while providing maximum efficiency. We obtain additional speedup by combining hydrogen mass repartitioning (HMR), High Hydrogen Friction (HHF) to further extended the largest timestep up to 10fs of our schemes while conserving stability and accuracy. As for DMTS, DMTS-NC is applicable to any neural network potential and can be applied to approaches that are computationally heavier than FeNNix-Bio1. We show a proof of principle applying the approach to the distillation of MACE-OFF23 with consequent speedups ranging from 3.66 to 5.64 compared to single timestep.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
