logo

Dongsun Yoo and Jisu Jung (Ph.D. and Ph.D. Candidate from Prof. Seungwu Han group) has recently reported ‘Metadynamics sampling in atomic environment space for collecting training data for machine learning potentials’. They suggest the novel sampling method utilizing the metadynamics on the atomic environment space, which drives the system into unvisited configuration automatically, resulting in diverse and reasonable training set for machine learning potential. Their method would expedite the development of machine learning potentials. This research has posted online on npj Computational Materials, August 16

▲ (왼쪽부터) 유동선 박사, 정지수 연구원