The performance of machine learning interatomic potentials relies on the quality of the training dataset. In this work, we present an approach for generating diverse and representative training data points which initiates with \it{ab initio} calculations for bulk structures. The data generation and potential construction further proceed side-by-side in a cyclic process of training the neural network and crystal structure prediction based on the developed interatomic potentials. All steps of the data generation and potential development are performed with minimal human intervention. We show the reliability of our approach by assessing the performance of neural network potentials developed for two inorganic systems.
Developing data-driven machine-learning interatomic potentials for materials containing many elements becomes increasingly challenging due to the vast configuration space that must be sampled by the training data. We study the learning rates and achievable accuracy of machine-learning interatomic potentials for many-element alloys with different combinations of descriptors for the local atomic environments. We show that for a five-element alloy system, potentials using simple low-dimensional descriptors can reach meV/atom-accuracy with modestly sized training datasets, significantly outperform…
The highly anisotropic thermal conductivity in layered materials is crucial for a broad range of applications such as thermal management of electronic devices, thermal insulation, and thermoelectrics. Understanding of anisotropic thermal transport in layered materials largely depends on atomistic simulations based on density functional theory (DFT) or empirical potentials, which however suffer either low computational efficiency or accuracy. Recently, machine learning interatomic potentials (MLIPs) are emerging as a powerful tool to bridge the gap. Despite the recent progress in developing MLI…
Developing reliable interatomic potential models with quantified predictive accuracy is crucial for atomistic simulations. Commonly used potentials, such as those constructed through the embedded atom method (EAM), are derived from semi-empirical considerations and contain unknown parameters that must be fitted based on training data. In the present work, we investigate Bayesian calibration as a means of fitting EAM potentials for binary alloys. The Bayesian setting naturally assimilates probabilistic assertions about uncertain quantities. In this way, uncertainties about model parameters and …
Large-scale atomistic computer simulations of materials heavily rely on interatomic potentials predicting the potential energy and Newtonian forces on atoms. Traditional interatomic potentials are based on physical intuition but contain few adjustable parameters and are usually not accurate. The emerging machine-learning (ML) potentials achieve highly accurate interpolation between the energies in a large DFT database but, being purely mathematical constructions, suffer from poor transferability to unknown structures. We propose a new approach that can drastically improve the transferability o…
Automated Machine Learning Pipeline: Large Language Models-Assisted Automated Dataset Generation for Training Machine-Learned Interatomic Potentials
NYU, Department of Chemistry（纽约大学化学系）；Initiative for Computational Catalysis, Flatiron Institute（计算催化计划，Flatiron研究所）；NYU, Department of Physics（纽约大学物理系）；Courant Institute of Mathematical Sciences, NYU（数学科学学院，纽约大学）；NYU-ECNU Center for Computational Chemistry（纽约大学-复旦大学计算化学中心）；Simons Center for Computational Physical Chemistry, NYU（Simons计算物理化学中心，纽约大学）
Evaluating approaches for on-the-fly machine learning interatomic potential for activated mechanisms sampling with the activation-relaxation technique nouveau
Probing Elastic Isotropy in Entropy Stabilized Transition Metal Oxides: Experimental Estimation of Single Crystal Elastic Constants from Polycrystalline Materials
Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
Imperial College London（帝国理工学院）；University College London（伦敦大学学院）；University of California Berkeley（加州大学伯克利分校）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
The FAST Framework: Developing a Data-Efficient Machine Learning Potential to Decode Superionic Transition-Induced Thermophysical and Kinetic Anomalies in UO2 under Extreme Conditions
State Key Laboratory for Strength and Vibration of Mechanical Structures, Shaanxi Engineering Laboratory for Vibration Control of Aerospace Structures, School of Aerospace, Xi'an Jiaotong University（西安交通大学航天学院）；Aircraft Strength Research Institute of China（中国飞机强度研究所）
Amorphous materials are coming within reach of realistic computer simulations, but new approaches are needed to fully understand their intricate atomic structures. Here, we show how machine-learning (ML)-based techniques can give new, quantitative chemical insight into the atomic-scale structure of amorphous silicon (a-Si). Based on a similarity function ("kernel"), we define a structural metric that unifies the description of nearest- and next-nearest-neighbor environments in the amorphous state. We apply this to an ensemble of a-Si networks, generated in melt-quench simulations with an ML-ba…
The recently proposed crystal graph convolutional neural network (CGCNN) offers a highly versatile and accurate machine learning (ML) framework by learning material properties directly from graph-like representations of crystal structures ("crystal graphs"). Here, we develop an improved variant of the CGCNN model (iCGCNN) that outperforms the original by incorporating information of the Voronoi tessellated crystal structure, explicit 3-body correlations of neighboring constituent atoms, and an optimized chemical representation of interatomic bonds in the crystal graphs. We demonstrate the accu…
Interatomic potential models based on machine learning (ML) are rapidly developing as tools for materials simulations. However, because of their flexibility, they require large fitting databases that are normally created with substantial manual selection and tuning of reference configurations. Here, we show that ML potentials can be built in a largely automated fashion, exploring and fitting potential-energy surfaces from the beginning (de novo) within one and the same protocol. The key enabling step is the use of a configuration-averaged kernel metric that allows one to select the few most re…
NepTrain and NepTrainKit: Automated Active Learning and Visualization Toolkit for Neuroevolution Potentials
College of physics and electronic information engineering, Guilin University of Technology, Guilin, 541008, P. R. China（桂林理工大学物理与电子信息工程学院）；School of Interdisciplinary Science, Beijing Institute of Technology, Beijing 100081, P. R. China（北京理工大学 interdisciplinary science 学院）；School of Mechanical and Electrical Engineering, Xinyu University, Xinyu, 338004, P. R. China（新余大学机械与电子工程学院）；School of Science, Harbin Institute of Technology (Shenzhen), Shenzhen 518055, China（哈尔滨工业大学（深圳）科学学院）；College of Physical Science and Technology, Bohai University, Jinzhou 121013, P. R. China（渤海大学物理科学与技术学院）
