首页|Kansas State University Reports Findings in Machine Learning (Predictions of Bor on Phase Stability Using an Efficient Bayesian Machine Learning Interatomic Pote ntial)
Kansas State University Reports Findings in Machine Learning (Predictions of Bor on Phase Stability Using an Efficient Bayesian Machine Learning Interatomic Pote ntial)
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 originating from Manhattan,Kansas,by NewsRx correspondents,research stated,"Thermodynamic phase stability of three elemental boron allotropes,i.e.,a-B,b-B,and g-B,was investigated using a Ba yesian interatomic potential trained via a sparse Gaussian process (SGP).SGP po tentials trained with data sets from on-the-fly active learning achieve quantum mechanical level accuracy when employed in molecular dynamics (MD) simulations t o predict wide-ranging thermodynamic,structural,and vibrational properties." Our news journalists obtained a quote from the research from Kansas State Univer sity,"The simulated phase diagram (500-1400 K and 0-16 GPa) agrees with experim ental measurements.The SGP-based MD simulations also successfully predicted tha t the B13 defect is critical in stabilizing b-B below 700 K.At higher temperatu res,the entropy becomes the dominant factor,making b-B the more stable phase o ver a-B." According to the news editors,the research concluded:"This letter demonstrates that SGP potentials based on a training set consisting of defect-free-only syst ems could make correct predictions of defect-related phenomena in solid-state cr ystals,paving the path to investigate crystal phase stability and transitions."
ManhattanKansasUnited StatesNorth and Central AmericaBoronCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
