Extensible Structure-Informed Prediction of Formation Energy with improved accuracy and usability employing neural networks

Adam M. Krajewski, Jonathan W. Siegel, Jinchao Xu, Zi Kui Liu

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

In the present paper, we introduce a new neural network-based tool for the prediction of formation energies of atomic structures based on elemental and structural features of Voronoi-tessellated materials. We provide a concise overview of the connection between the machine learning and the true material–property relationship, how to improve the generalization accuracy by reducing overfitting, how new data can be incorporated into the model to tune it to a specific material system, and preliminary results on using models to preform local structure relaxations. The present work resulted in three final models optimized for (1) highest test accuracy on the Open Quantum Materials Database (OQMD), (2) performance in the discovery of new materials, and (3) performance at a low computational cost. On a test set of 21,800 compounds randomly selected from OQMD, they achieve a mean absolute error (MAE) of 28, 40, and 42 meV/atom, respectively. The second model provides better predictions in a test case of interest not present in the OQMD, while the third reduces the computational cost by a factor of 8. We collect our results in a new open-source tool called SIPFENN (Structure-Informed Prediction of Formation Energy using Neural Networks). SIPFENN not only improves the accuracy beyond existing models but also ships in a ready-to-use form with pre-trained neural networks and a GUI interface. By virtue of this, it can be included in DFT calculations routines at nearly no cost.
Original languageEnglish (US)
JournalComputational Materials Science
Volume208
DOIs
StatePublished - Jun 1 2022
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2023-02-15

ASJC Scopus subject areas

  • General Physics and Astronomy
  • Mechanics of Materials
  • General Materials Science
  • Computational Mathematics
  • General Chemistry
  • General Computer Science

Fingerprint

Dive into the research topics of 'Extensible Structure-Informed Prediction of Formation Energy with improved accuracy and usability employing neural networks'. Together they form a unique fingerprint.

Cite this