Search
Recently, the research team led by Professor Xu Zhenli from the School of Mathematical Sciences at Shanghai Jiao Tong University has achieved a significant breakthrough in the realm of machine learning force fields. Their groundbreaking study, entitled "Machine-learning interatomic potentials for long-range systems," has been published in the prestigious international journal Physical Review Letters and has been highlighted as an Editors’ Suggestion article. This innovative research introduces a novel neural network framework known as SOG-Net (Sum-of-Gaussians Network). This framework successfully tackles the computational accuracy issues that have long plagued machine learning potential functions in systems with long-range interactions. By doing so, it provides vital algorithmic support for conducting high-precision molecular dynamics simulations in complex systems.
-
C114 Communication Network -
Communication Home
