Data for: Machine-learning-accelerated simulations enable heuristic-free surface reconstruction

This is the dataset for the publication "Machine-learning-accelerated simulations to enable automatic surface reconstruction", by X. Du, J.K. Damewood, J.R. Lunger, R. Millan, B. Yildiz, L. Li, and R. Gómez-Bombarelli. The repository contains the density-functional theory (DFT) data used to train the neural network force fields (NFF), selected results from our GaN(0001), Si(111), and SrTiO3(001) Virtual Surface Site Relaxation-Monte Carlo (VSSR-MC) runs, and Jupyter notebooks used for analysis and plots. To run the .ipynb's, you will need to install surface-sampling (tested up to commit 02820d339eed6291b6af6ccb809f154ad6244110 on master) and NeuralForceField (tested up to commit 72d1f32f43f202c1a466116beeed15845a6456e7 on master) from the Rafael Gómez-Bombarelli Group @ MIT.

Related Organizations

Massachusetts Institute of Technology
United States

Keywords

semi-grand canonical ensemble, active learning, neural network force field, Markov-chain Monte Carlo, density-functional theory

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	1
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average