Machine-learning correction to density-functional crystal structure optimization
arXiv:2111.02206 · doi:10.1557/s43577-022-00310-9
Abstract
Density functional theory is routinely applied to predict crystal structures. The most common exchange-correlation functionals used to this end are the Perdew-Burke-Ernzerhof (PBE) approximation and its variant PBEsol. We investigate the performance of these functionals for the prediction of lattice parameters and show how to enhance their accuracy using machine learning. Our dataset is constituted by experimental crystal structures of the Inorganic Crystal Structure Database matched with PBE-optmized structures stored in the materials project database. We complement these data with PBEsol calculations. We demonstrate that the accuracy and precision of PBE/PBEsol volume predictions can be noticeably improved a posteriori by employing simple, explainable machine learning models. These models can improve PBE unit cell volumes to match the accuracy of PBEsol calculations, and reduce the error of the latter with respect to experiment by 35%. Further, the error of PBE lattice constants is reduced by a factor of 3--5. A further benefit of our approach is the implicit correction of finite temperature effects without performing phonon calculations.
arXiv comment62 pages, 5 figures, 3 tables
References in corpus (16)
- Scikit-learn: Machine Learning in Python
- Restoring the density-gradient expansion for exchange in solids and surfaces
- Generalized gradient approximation for solids and their surfaces
- Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
- SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
- How to Explain Individual Classification Decisions
- Error estimates for solid-state density-functional theory predictions: an overview by means of the ground-state elemental crystals
- Machine learning modeling of superconducting critical temperature
- Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
- Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
- Deep Neural Networks for Accurate Predictions of Garnet Stability
- Prototype selection for interpretable classification
- Efficient nonparametric -body force fields from machine learning
- Anharmonic Phonon Quasiparticle Theory of Zero-point and Thermal Shifts in Insulators: Heat Capacity, Bulk Modulus, and Thermal Expansion
- Theory for structure and bulk-modulus determination
- Thermal Expansion in Insulating Solids From First Principles