Machine Learning Interatomic Potential Development with MAML

In this talk at NanoHUB's Hands-on Data Science and Machine Learning Training Series, Yunxing Zuo from the Materials Virtual Lab discusses how to conveniently develop machine learning interatomic potentials (MLIAPs) using the Materials Machine Learning (maml) library. ML-IAPs describe the potential energy surface using local environment descriptors and has been demonstrated to be able to achieve near-DFT accuracy with linear scaling wrt number of atoms.

maml: https://github.com/materialsvirtualla...

Zuo, Y.; Chen, C.; Li, X.; Deng, Z.; Chen, Y.; Behler, J.; Csányi, G.; Shapeev, A. V.; Thompson, A. P.; Wood, M. A.; Ong, S. P. Performance and Cost Assessment of Machine Learning Interatomic Potentials. J. Phys. Chem. A 2020, 124 (4), 731–745. https://doi.org/10.1021/acs.jpca.9b08723.