CoChat

Computational Screening of New Perovskite Materials Using Transfer Learning and Deep Learning

Open access

The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.

Abstract

As one of the most studied materials, perovskites exhibit a wealth of superior properties that lead to diverse applications. Computational prediction of novel stable perovskite structures has big potential in the discovery of new materials for solar panels, superconductors, thermal electric, and catalytic materials, etc. By addressing one of the key obstacles of machine learning based materials discovery, the lack of sufficient training data, this paper proposes a transfer learning based approach that exploits the high accuracy of the machine learning model trained with physics-informed structural and elemental descriptors. This gradient boosting regressor model (the transfer learning model) allows us to predict the formation energy with sufficient precision of a large number of materials of which only the structural information is available. The enlarged training set is then used to train a convolutional neural network model (the screening model) with the generic Magpie elemental features with high prediction power. Extensive experiments demonstrate the superior performance of our transfer learning model and screening model compared to the baseline models. We then applied the screening model to filter out promising new perovskite materials out of 21,316 hypothetical perovskite structures with a large portion of them confirmed by existing literature.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/app9245510

Cites

44 of 44 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 ( a ) is a list of elements considered by the A and B sites. The color coding of the element is a function of the amount of stabilized perovskite and the corresponding element of the A and B positions; ( b ) is a perovskite structure with 12-fold coordinated A cation (green A atom) and the octahedral coordinated B cation (blue B atom). The X atoms in the three-dimensional (3D) Wyckoff positions are in red. Figure 1. ( a ) is a list of elements considered by the A and B sites. The color coding of the element is a function of the amount of stabilized perovskite and the corresponding element of the A and B positions; ( b ) is a perovskite structure with 12-fold coordinated A cation (green A atom) and the octahedral coordinated B cation (blue B atom). The X atoms in the three-dimensional (3D) Wycko positions are in red.
Figure 1 ( a ) is a list of elements considered by the A and B sites. The color coding of the element is a function of the amount of stabilized perovskite and the corresponding element of the A and B positions; ( b ) is a perovskite structure with 12-fold coordinated A cation (green A atom) and the octahedral coordinated B cation (blue B atom). The X atoms in the three-dimensional (3D) Wyckoff positions are in red. Figure 1. ( a ) is a list of elements considered by the A and B sites. The color coding of the element is a function of the amount of stabilized perovskite and the corresponding element of the A and B positions; ( b ) is a perovskite structure with 12-fold coordinated A cation (green A atom) and the octahedral coordinated B cation (blue B atom). The X atoms in the three-dimensional (3D) Wycko positions are in red.CC-BY · From the PDF
Figure 2 Framework for the computational screening of perovskite materials. Abbreviations: RFR, random forest regression; SVR, support vector regression; GBR, gradient boosting regressor; Crystallographic Information File (CIF). Figure 2. Framework for the computational screening of perovskite materials. Abbreviations: RFR, random forest regression; SVR, support vector regression; GBR, gradient boosting regressor; Crystallographic Information File (CIF).
Figure 2 Framework for the computational screening of perovskite materials. Abbreviations: RFR, random forest regression; SVR, support vector regression; GBR, gradient boosting regressor; Crystallographic Information File (CIF). Figure 2. Framework for the computational screening of perovskite materials. Abbreviations: RFR, random forest regression; SVR, support vector regression; GBR, gradient boosting regressor; Crystallographic Information File (CIF).CC-BY · From the PDF
Figure 3 Pool processing matrix.
Figure 3 Pool processing matrix.CC-BY · From the PDF
Image 4
CC-BY · From the PDF
Figure 5 Feature importance from random forest (RF) for the formation energy of perovskite. Figure 5. Feature importance from random forest (RF) for the formation energy of perovskite.
Figure 5 Feature importance from random forest (RF) for the formation energy of perovskite. Figure 5. Feature importance from random forest (RF) for the formation energy of perovskite.CC-BY · From the PDF
Figure 6 Prediction performances of different models using hybrid features: ( a ) GBR; ( b ) least absolute shrinkage and selection operator (Lasso); ( c ) RFR; and ( d ) SVR. Figure 6. Prediction performances of di erent models using hybrid features: ( a ) GBR; ( b ) least absolute shrinkage and selection operator (Lasso); ( c ) RFR; and ( d ) SVR.
Figure 6 Prediction performances of different models using hybrid features: ( a ) GBR; ( b ) least absolute shrinkage and selection operator (Lasso); ( c ) RFR; and ( d ) SVR. Figure 6. Prediction performances of di erent models using hybrid features: ( a ) GBR; ( b ) least absolute shrinkage and selection operator (Lasso); ( c ) RFR; and ( d ) SVR.CC-BY · From the PDF
Image 7
CC-BY · From the PDF
Figure 8 Cont .
Figure 8 Cont .CC-BY · From the PDF
Figure 8 Formation energy distribution of hypothetical perovskite materials predicted by M2 model.
Figure 8 Formation energy distribution of hypothetical perovskite materials predicted by M2 model.CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 2

  1. Michie, 1994, Machine learning, Neural Stat. Classif., 13, 19
  2. Bishop, C.M. (2006). Pattern Recognition and Machine Learning, Springer.

Cited by

See all 75

Metadata

Authors
Li, X., Dan, Y., Dong, R., Cao, Z., Niu, C., Song, Y., Li, S., & Hu, J.
Affiliations
  • Guizhou University (CN)
  • Key laboratory of advanced manufacturing technology, Ministry of education, Guiyang 550025, China
  • University of South Carolina (US)
Corresponding author
  • Li, Shaobo
  • Hu, Jianjun
Venue
Applied Sciences
Publisher
MDPI AG
Published
2019-12-14
Volume
9
Issue
24
Pages
5510
ISSN
2076-3417 (ISSN-L)
OpenAlex
W2994650566
Cited by
74
References
45
Citations by year
2026: 7 · 2025: 19 · 2024: 8 · 2023: 15 · 2022: 13 · 2021: 6 · 2020: 6
FWCI
2.26
Type
journal article
Language
en
Open access
Locations
  • Applied Sciences (publishedVersion, cc-by)
  • Scholar Commons (University of South Carolina) (submittedVersion, cc-by)
Funders
  • National Science Foundation (OIA-1655740, 1940099, and 1905775)
  • National Natural Science Foundation of China (51741101)
  • National Important Project of China (2018AAA0101803)
  • Guizhou Province Science and Technology Project ([2015]4011)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
Keywords
perovskite, materials discovery, computational screening, transfer learning, formation energy prediction, gradient boosting regression, convolutional neural networks, structural descriptors, limited training data

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.