Presenter: Qiang Zhu （UNLV, Dept. of Physics and Astronomy, High-Pressure Sci. & Eng. Center）
Topic: Machine Learning on the Interatomic Potentials
Time: 2:00 PM, Jun. 24th(Wednesday)
Zoom Meeting ID: 456 862 1540
Zoom Meeting Link:
I will present PyXtal_FF, a package based on Python programming language, for developing machine learning potentials (MLPs). The aim of PyXtal_FF is to promote the application of atomistic simulations by providing several choices of structural descriptors and machine learning regressions in one platform. Based on the given choice of structural descriptors (including the atom-centered symmetry functions, embedded atom density, SO4 bispectrum, and smooth SO3 power spectrum), PyXtal_FF can train the MLPs with either the linear regression and neural networks model, by simultaneously minimizing the errors of energy/forces/stress tensors in comparison with the data from the ab-initio simulation. The trained MLP model from PyXtal_FF is interfaced with the Atomic Simulation Environment (ASE) package, which allows different types of light-weight simulations such as geometry optimization, molecular dynamics, and physical properties prediction. Finally, we will illustrate the performance of PyXtal_FF by applying it to investigate several material systems. Full documentation of PyXtal\_FF is available at http://pyxtal-ff.readthedocs.io.
Qiang Zhu is an Assistant Professor in the Department of Physics and Astronomy at the University of Nevada, Las Vegas. He is also a faculty member in the High-Pressure Science and Engineering Center in UNLV. Qiang holds a Ph.D. in Mineral Physics from the State University of New York at Stony Brook, as well as a B.S in Materials Science and Engineering from Beijing University of Aeronautics and Astronautics in China. He joined UNLV in October 2016.
Professor Qiang Zhu is mainly engaged in the prediction of new organic polycrystalline materials, the prediction of structures under extreme conditions, the study of the relationship between material defects and properties, and the exploration of the phase transition mechanism of materials. Professor Qiang Zhu is one of the main developers of the world-renowned crystal structure prediction program—USPEX. He has published more than 60 research papers in top journals such as Nature series, Science, Phys. Rev. Lett., JACS, within more than 3,000 citations.
Contanct：Prof. Tao Cheng