首页|National University of Singapore Reports Findings in Machine Learning (Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification)
National University of Singapore Reports Findings in Machine Learning (Scalable crystal structure relaxation using an iteration-free deep generative model with uncertainty quantification)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating in Singapore, Sin gapore, by NewsRx journalists, research stated, “In computational molecular and materials science, determining equilibrium structures is the crucial first step for accurate subsequent property calculations. However, the recent discovery of millions of new crystals and super large twisted structures has challenged tradi tional computational methods, both ab initio and machine-learningbased, due to their computationally intensive iterative processes.” The news reporters obtained a quote from the research from the National Universi ty of Singapore, “To address these scalability issues, here we introduce DeepRel ax, a deep generative model capable of performing geometric crystal structure re laxation rapidly and without iterations. DeepRelax learns the equilibrium struct ural distribution, enabling it to predict relaxed structures directly from their unrelaxed ones. The ability to perform structural relaxation at the millisecond level per structure, combined with the scalability of parallel processing, make s DeepRelax particularly useful for large-scale virtual screening. We demonstrat e DeepRelax’s reliability and robustness by applying it to five diverse database s, including oxides, Materials Project, two-dimensional materials, van der Waals crystals, and crystals with point defects. DeepRelax consistently shows high ac curacy and efficiency, validated by density functional theory calculations. Fina lly, we enhance its trustworthiness by integrating uncertainty quantification.”
NETL
NSTL
