A universal graph deep learning interatomic potential for the periodic table
Chi Chen,Shyue Ping Ong +1 more
TL;DR: In this article , a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet) was reported, which was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces.
read more
Abstract: Interatomic potentials (IAPs), which describe the potential energy surface of atoms, are a fundamental input for atomistic simulations. However, existing IAPs are either fitted to narrow chemistries or too inaccurate for general applications. Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces. About 1.8 million materials were identified from a screening of 31 million hypothetical crystal structures to be potentially stable against existing Materials Project crystals based on M3GNet energies. Of the top 2000 materials with the lowest energies above hull, 1578 were verified to be stable using DFT calculations. These results demonstrate a machine learning-accelerated pathway to the discovery of synthesizable materials with exceptional properties.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Scaling deep learning for materials discovery
Amil Merchant,Simon Batzner,Samuel S. Schoenholz,Muratahan Aykol,Gowoon Cheon,Ekin D. Cubuk +5 more
TL;DR: It is shown that graph networks trained at scale can reach unprecedented levels of generalization, improving the efficiency of materials discovery by an order of magnitude and leading to the discovery of 2.2 million crystal structures, of which 381,000 are newly discovered stable materials.
442
CHGNet as a pretrained universal neural network potential for charge-informed atomistic modelling
Bowen Deng,Peichen Zhong,KyuJung Jun,Janosh Riebesell,Kevin Han,Christopher J. Bartel,Gerbrand Ceder +6 more
TL;DR: A universal graph neural network-based interatomic potential integrating atomic magnetic moments as charge constraints is introduced, which allows for capturing subtle chemical properties in several lithium-based solid-state materials.
226
DeePMD-kit v2: A software package for Deep Potential models
Jinzhe Zeng,Duoduo Zhang,Denghui Lu,Pinghui Mo,Yixiao Chen,Mari'an Ryn'ik,Liang Huang,Zi Tong Li,Shaochen Shi,Yingze Wang,Hao-Tong Ye,Ping Tuo,Ye Ding,Yifan Li,D. Tisi,Qiyu Zeng,Yu Xia,Koki Muraoka,Junhan Chang,Feng Yuan,Sigbjørn Løland Bore,Chun-Lin Cai,Yinnian Lin,Bo Wang,Jia-yu Xu,Jiahong Zhu,Chenxing Luo,Yuzhi Zhang,Rhys E. A. Goodall,Wenshuo Liang,Sikai Yao,Jingchao Zhang,Renata M. Wentzcovitch,Jiequn Han,Jieming Liu,Wei Jia,Darrin M. York,E Weinan,Roberto Car,Linfeng Zhang,Han Wang +40 more
- 19 Apr 2023
TL;DR: The DeePMD-kit as mentioned in this paper is a powerful open-source software package that facilitates molecular dynamics simulations using machine learning potentials (MLP) known as Deep Potential (DP) models.
Metal–Organic Framework Supercapacitors: Challenges and Opportunities
Jamie W. Gittins,Chloe J. Balhatchet,Aron Walsh,Alexander C. Forse +3 more
TL;DR: MOF supercapacitors have high capacitance and energy storage capabilities, but face challenges such as low potential windows, limited cycle lifetimes, and poor rate performances. There is a need for more studies on charge storage and degradation mechanisms to improve supercapacitor performance.
78
A critical examination of robustness and generalizability of machine learning prediction of materials properties
TL;DR: In this article , the authors show that ML models trained on Materials Project 2018 can have severely degraded performance on new compounds in Materials Project 2021 due to the distribution shift, and they use the uniform manifold approximation and projection (UMAP) to investigate the relation between the training and test data within the feature space.
References
Generalized Gradient Approximation Made Simple
TL;DR: A simple derivation of a simple GGA is presented, in which all parameters (other than those in LSD) are fundamental constants, and only general features of the detailed construction underlying the Perdew-Wang 1991 (PW91) GGA are invoked.
•Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
- 01 Jan 2015
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
138.5K
•Journal Article
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +15 more
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set
Georg Kresse,Jürgen Furthmüller +1 more
TL;DR: A detailed description and comparison of algorithms for performing ab-initio quantum-mechanical calculations using pseudopotentials and a plane-wave basis set is presented in this article. But this is not a comparison of our algorithm with the one presented in this paper.
65.9K
Ab initio molecular dynamics for liquid metals.
Georg Kresse,Jürgen Hafner +1 more
TL;DR: In this paper, the authors present an ab initio quantum-mechanical molecular-dynamics calculations based on the calculation of the electronic ground state and of the Hellmann-Feynman forces in the local density approximation.
41.5K