摘要
一位新闻记者兼机器人与机器学习的工作人员新闻编辑每日新闻-机器学习的新研究是一篇报道的主题。根据NewsRx Jo Urnalists在瑞士洛桑的新闻报道，研究人员指出：“本文提出了对[Xi，C；et al . 6878]方法的扩展，从混合溶剂化模型的第一原理(FP)分子动力学(MD)Si计算溶剂化自由能i。该方法首先在溶剂化的准化学理论中重新表述。”新闻记者从瑞士洛桑联邦理工学院(EPFL)获得了一段研究的引文，“那么，为了允许比最初的第一原理分子动力学方法更长的模拟时间，因此我以原始计算成本的一小部分改进了统计平均值的收敛性，”在FP能量和力上训练机器学习的(ML)能量函数，并用于MD模拟。调整ML工作流和MD模拟t imes(200 ps)，以在0.04ev的化学精度内收敛预测的溶剂化能。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Machine Learning is the subject o f a report. According to news reporting from Lausanne, Switzerland, by NewsRx jo urnalists, research stated, “The present work proposes an extension to the appro ach of [Xi, C; et al. 6878] to calculate i on solvation free energies from first-principles (FP) molecular dynamics (MD) si mulations of a hybrid solvation model. The approach is first re-expressed within the quasi-chemical theory of solvation.” The news correspondents obtained a quote from the research from the Swiss Federa l Institute of Technology Lausanne (EPFL), “Then, to allow for longer simulation times than the original first-principles molecular dynamics approach and thus i mprove the convergence of statistical averages at a fraction of the original com putational cost, a machine-learned (ML) energy function is trained on FP energie s and forces and used in the MD simulations. The ML workflow and MD simulation t imes ( 200 ps) are adjusted to converge the predicted solvation energies within a chemical accuracy of 0.04 eV.”
NETL
NSTL