Compute the training-set and test-set errors of an MLFF model for given reference data. Error estimation of an MLFF model gives insights into the accuracy of the trained model and how …

为了让每个力场模型都可以通过同一种方式调用，所以写模式时需要注意一些规则。 以下是我使用的方式，我将做以介绍！ 因为水平有限，可能存在一些未注意到的事项，希望大家可以不吝 …

该研究以「Efficient interatomic descriptors for accurate machine learning force fields of extended molecules」为题，于 2023 年 6 月 15 日发布在《Nature Communications》。 可靠的原子力 …

2024年8月9日 · 该研究以「A Euclidean transformer for fast and stable machine learned force fields」为题，于 2024 年 8 月 6 日发布在《Nature Communications》。 分子动力学（MD） …

机器学习力场借助已有的第一性原理计算结果，拟合单个原子的能量，可在不进行第一性原理计算的情况下获得体系能量。 对于平衡态附近的体系，机器学习力场有望大幅加速分子动力学计 …

In this review, we introduce the fundamental principles of ML and FFs in the context of machine learning force fields (MLFF). We also discuss the advantages and applications of MLFF …

Machine-learned force fields used in combination with ab-initio molecular dynamics (MD) allow capturing the underlying physics from first principles and still reach long simulation times …

Generating a machine learning force field for liquid Si. For this tutorial, we expect that the user is already familiar with running conventional ab initio molecular dynamic calculations. In this …

Multi-Lane Free Flow (MLFF) is an innovative toll road solution that utilizes Global Navigation Satellite System (GNSS) technology. This allows toll transactions to be faster and more …

2023年8月11日 · With MLFF is it possible to perform MD simulations that capture mechanisms and processes for time scales of up to 100ps and even ns for compounds with up to 8 (eight!) …