物理化学学报 >> 2026, Vol. 42 >> Issue (6): 100235.doi: 10.1016/j.actphy.2025.100235

所属专题： AI化学

论文 上一篇    下一篇

LASPAI：人工智能驱动的未来原子模拟平台

罗涵之1, 梁琦茗1, 郭子兴1, 谢忻恬1, 唐锦朋1, 管曈1, 李晔飞1, 马思聪2, 许颖忱1, 王振雄1,*(), 商城1,*(), 刘智攀1,2,*()   

  1. 1 复旦大学化学系, 计算物质科学教育部重点实验室, 上海市分子催化与功能材料重点实验室, 能源材料化学协同创新中心, 多孔材料分离与转化国家重点实验室, 上海 200433
    2 中国科学院上海有机化学研究所金属有机化学国家重点实验室, 上海 200032
  • 收稿日期:2025-11-17 修回日期:2025-12-30 录用日期:2025-12-30 发布日期:2026-04-21
  • 通讯作者: Email: wangzhenxiong@fudan.edu.cn (王振雄)cshang@fudan.edu.cn (商城)zpliu@fudan.edu.cn (刘智攀)

LASPAI: AI-powered platform for the future atomic simulation

Han-Zhi Luo1, Qi-Ming Liang1, Zi-Xing Guo1, Xin-Tian Xie1, Jin-Peng Tang1, Tong Guan1, Ye-Fei Li1, Si-Cong Ma2, Ying-Chen Xu1, Zhen-Xiong Wang1,*(), Cheng Shang1,*(), Zhi-Pan Liu1,2,*()   

  1. 1 State Key Laboratory of Porous Materials for Separation and Conversion, Collaborative Innovation Center of Chemistry for Energy Material, Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials, Key Laboratory of Computational Physical Science, Department of Chemistry, Fudan University, Shanghai 200433, China
    2 State Key Laboratory of Metal Organic Chemistry, Shanghai Institute of Organic Chemistry, Chinese Academy of Sciences, Shanghai 200032, China
  • Received:2025-11-17 Revised:2025-12-30 Accepted:2025-12-30 Published:2026-04-21
  • Contact: Email: wangzhenxiong@fudan.edu.cn (Zhen-Xiong Wang)cshang@fudan.edu.cn (Cheng Shang)zpliu@fudan.edu.cn (Zhi-Pan Liu)

RichHTML

19

PDF

490

赞

摘要：

原子模拟正成为现代科学的重要工具，架起了理论与实验之间的桥梁。自20世纪50年代诞生以来，精度与速度的平衡始终是原子模拟的核心命题。近年来，基于机器学习势函数的方法崭露头角，成为探索复杂势能面(PES)时密度泛函理论计算的有力替代方案。本文报道了我们开发的LASPAI平台(www.laspai.com)，这是一个面向未来原子模拟的云端平台。该平台采用LASP软件中实现的广义全局神经网络势函数进行快速PES评估，同时整合了一系列通用扩散生成模型、随机表面行走(SSW)全局优化算法及其他PES探索工具。LASPAI平台通过任务导向、用户友好的网页图形界面(GUI)，能大幅简化和加速从分子材料结构预测到气-固、液-固界面识别、固-固界面判定及反应路径模拟等广泛科学领域的原子模拟工作，旨在为科学家设计新材料和反应提供快速的化学知识支持。

关键词: 原子模拟, 生成模型, 全局机器学习势, LASPAI平台

Abstract:

Atomic simulation is becoming a vital tool in modern science, bridging the gap between theory and experiments. Since its birth in 1950s, the balance between accuracy and speed has been the main theme in simulating atomic world and in recent years machine learning potential based methods emerged as a promising alternative to density functional theory calculations for exploring complex potential energy surface (PES). Here we report our implementation of LASPAI (www.laspai.com), a web-based platform for future atomic simulations, which is built using the generalized global neural network potential for fast PES evaluation as implemented in LASP software, together with a series of general diffusion generative models, stochastic surface walking (SSW) global optimization, and other common simulation tools for the PES exploration of molecules and materials. We show that LASPAI platform offers a task-orientated, user-friendly, web-based graphical user interface (GUI) to greatly simplify and speed-up atomic simulations for a wide range of scientific areas, ranging from molecule and material structure prediction to solid-gas, solid-liquid, solid-solid interface identification, and reaction pathway simulations. It aims to provide a fast chemical knowledge delivery for scientists to design new materials and reactions.

Key words: Atomic simulation, Generative model, Global machine learning potential, LASPAI platform