报告题目：Modeling the interatomic potential by deep learning
报告地点：腾讯会议ID: 582 466 169
In silico design of materials requires an accurate description of the interatomic potential energy surface (PES). However, in the context of molecular simulation, one usually faces the dilemma that the first principle PESs are accurate but computationally expensive, while the empirical PESs (force fields) are efficient but of limited accuracy. We discuss the solution 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. We briefly introduce the open-source implementations of DP and DP-GEN and then debut the DP library that provides the platform for openly sharing DP models and data in the community. In the last part of the talk, we briefly introduce the optimization of DeePMD-kit on Summit supercomputer, which wins the 2020 ACM Gordon Bell prize for its unprecedented power of simulating 100M atoms with the first-principle accuracy in one day.