Modeling the interatomic potential by deep learning
报告题目(Title)：Modeling the interatomic potential by deep learning
报告人(Speaker)：王涵（北京应用物理与计算数学研究所）
地点(Place)：后主楼1124
时间(Time)：12月25日（星期五），15:00-16:00
邀请人(Inviter)：蔡勇勇
报告摘要
An accurate description of the interatomic potential energy surface (PES) is one of the central problems in molecular simulations. For a long time, one has to choose between the first principle PESs that are accurate but computationally expensive and the empirical PESs (force fields) that are efficient but of limited accuracy. We discuss the solution to this dilemma in two aspects: PES construction and data generation. In terms of PES construction, we introduce the Deep Potential (DP) method, which faithfully represents the first principle PES by a symmetry-preserving deep neural network. In terms of data generation, we present a new concurrent learning scheme named Deep Potential Generator (DP-GEN). This approach automatically generates the most compact training dataset that enables the training of DP with uniform accuracy. By contrast to the empirical PESs, the DP-GEN opens the opportunity of continuously improving the quality of DP by exploring the chemical and configurational space of the system. After a few examples of DP and DP-GEN, we introduce the open-source implementations of DP named DeePMD-kit, and a recent GPU optimization of DeePMD-kit for the world's fastest supercomputer, which makes possible nanosecond simulation of 100 million atoms with ab initio accuracy in a day.
主讲人简介
王涵，现为北京应用物理与计算数学研究所副研究员，2002年进入北京大学数学科学学院学习，2006年获学士学位，2011年获博士学位，师从张平文院士。主要研究兴趣为分子模拟中的多尺度建模与计算方法，以及基于深度学习的分子建模。曾获中国数学会计算数学分会第五届青年创新奖。2020年与合作者共同推动完成的工作成果—“Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning”获得国际高性能计算应用领域最高奖—戈登贝尔奖（ACM Gordon Bell Prize）。
