用时间序列预测加速分子动力学，几分钟跑几千步
Accelerating Long-Term Molecular Dynamics with Physics-Informed Time-Series Forecasting
- 将分子轨迹预测转为位移序列建模，提升稳定性
- 结合物理约束损失，避免原子非法重叠，精度超越基线
- 适合需要长期模拟的材料与生物体系研究者
高效的分子动力学（MD）模拟对理解材料科学和生物物理中的原子尺度过程至关重要。传统密度泛函理论（DFT）方法计算成本高，限制了长期模拟的可行性。本文提出一种新方法，将MD模拟建模为时间序列预测问题，通过预测原子位移而非绝对位置实现轨迹外推。引入基于DFT参数化双体Morse势函数的物理信息损失与推理机制，惩罚不合理的原子近距离以保证物理合理性。该方法在多种材料上均显著优于标准基线，在模拟精度上持续领先。结果表明，融合物理知识可有效提升原子轨迹预测的可靠性与精度。尤为关键的是，该方法可在数分钟内稳定模拟数千个MD步，提供一种可扩展的替代方案，取代昂贵的DFT模拟。
原文摘要 · Abstract (English)
Efficient molecular dynamics (MD) simulation is vital for understanding atomic-scale processes in materials science and biophysics. Traditional density functional theory (DFT) methods are computationally expensive, which limits the feasibility of long-term simulations. We propose a novel approach that formulates MD simulation as a time-series forecasting problem, enabling advanced forecasting models to predict atomic trajectories via displacements rather than absolute positions. We incorporate a physics-informed loss and inference mechanism based on DFT-parametrised pair-wise Morse potential functions that penalize unphysical atomic proximity to enforce physical plausibility. Our method consistently surpasses standard baselines in simulation accuracy across diverse materials. The results highlight the importance of incorporating physics knowledge to enhance the reliability and precision of atomic trajectory forecasting. Remarkably, it enables stable modeling of thousands of MD steps in minutes, offering a scalable alternative to costly DFT simulations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。