Deep neural networks for accurate predictions of crystal stability

By Weike Ye, Chi Chen, Zhenbin Wang, Iek Heng Chu, Shyue Ping Ong. 2017

251 citations recorded by the source corpus.

Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors—the Pauling electronegativity and ionic radii—can predict the DFT formation energies of C3A2D3O12 garnets and ABO3 perovskites with low mean absolute errors (MAEs) of 7–10 meV atom−1 and 20–34 meV atom−1, respectively, well within the limits of DFT accuracy. Further extension to mixed garnets and perovskites with little loss in accuracy can be achieved using a binary encoding scheme, addressing a critical gap in the extension of machine-learning models from fixed stoichiometry crystals to infinite universe of mixed-species crystals. Finally, we demonstrate the potential of these models to rapidly transverse vast chemical spaces to accurately identify stable compositions, accelerating the discovery of novel materials with potentially superior properties. Crystal stability prediction is of paramount importance for novel material discovery, with theoretical approaches alternative to expensive standard schemes highly desired. Here the authors develop a deep learning approach which, just using two descriptors, provides crystalline formation energies with very high accuracy.

Subfields: Inorganic Chemistry, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Inorganic Chemistry

1. Zhen Zhou
2. Ryan Jacobs
3. Dane Morgan

In Materials Chemistry

1. Ryan Jacobs
2. Rohit Batra
3. Dane Morgan
4. Xu Zhang
5. Rampi Ramprasad
6. Zhen Zhou
7. An Chen
8. J. A. Flores-Livas

Citations in the corpus

• Opportunities and Challenges for Machine Learning in Materials Science (2020, background): “…science Gubernatis and Lookman 2018 193 Machine learning in materials design and discovery: Examples from the present and suggestions for the future Ye et al. 2018 194 Harnessing the Materials Project for machine-learning and accelerated discovery Seko et al. 2018 195 Progress in…”
• Emerging materials intelligence ecosystems propelled by machine learning (2020, background): “…constituting elemental species as inputs to simple architectures (one or two hidden layers) of NNs, it was possible to learn the DFT formation energies of C 3 A 2 D 3 O 12 garnets and ABO 3 per-ovskites with a mean absolute error (MAE) of 7–10 meV per atom and 20–34 meV per atom, respectively 95 .”
• A perspective on conventional high-temperature superconductors at high pressure: Methods and materials (2019, background): “In principle, the construction of a generalized convex hull is a type of problem perfectly accessible for machine learning [372] and neural networks [373].”
• Machine learning: Accelerating materials development for energy storage and conversion (2020, methodology): “Besides, deep neural networks based on only two descriptors, ionic radii and Pauling electronegativity can be used to predict formation energies of ABO3 perovskites and garnets with low MAEs.(180) Recently, ML technology has also been used to identify and classify perovskites for solar cells, furthe”