Skip to main content

Abstract: We’ll present several theories, methods, and engineering efforts that integrate physical models with artificial intelligence (AI) and high-performance computing (HPC) for molecular simulations. Examples include AI-assisted electronic structure models, AI-assisted molecular dynamics models, as well as AI-assisted enhanced sampling schemes. Particularly, we’ll show our recent efforts on developing related open-source software packages and high-performance computing schemes, which have now been widely used worldwide by experts and practitioners in the molecular and materials simulation community. Finally, we’ll envision how the field proceeds in the era of cloud-native infrastructures and data-driven science.

Bio: Linfeng Zhang is the founder and chief scientist of DP Technology and a researcher at the AI for Science Institute. In 2020, he graduated from the PhD Program in Applied and Computational Mathematics at Princeton University, working with Profs. Weinan E and Roberto Car. Linfeng has been focusing on developing machine-learning based physical models for electronic structures, molecular dynamics, and enhanced sampling. He’s one of the main developers of DeePMD-kit, a popular deep learning-based open-source software for molecular simulation in physics, chemistry, and materials science. He is a recipient of the 2020 ACM Gordon Bell Prize.