CoChat

Machine Learning Approach to Delineate the Impact of Material Properties on Solar Cell Device Physics

Open access

The DOI matches its Crossref record; 81 of the 82 references it cites were found in a registry or an index.

Abstract

In this research, solar cell capacitance simulator-one-dimensional (SCAPS-1D) software was used to build and probe nontoxic Cs-based perovskite solar devices and investigate modulations of key material parameters on ultimate power conversion efficiency (PCE). The input material parameters of the absorber Cs-perovskite layer were incrementally changed, and with the various resulting combinations, 63,500 unique devices were formed and probed to produce device PCE. Versatile and well-established machine learning algorithms were thereafter utilized to train, test, and evaluate the output dataset with a focused goal to delineate and rank the input material parameters for their impact on ultimate device performance and PCE. The most impactful parameters were then tuned to showcase unique ranges that would ultimately lead to higher device PCE values. As a validation step, the predicted results were confirmed against SCAPS simulated results as well, highlighting high accuracy and low error metrics. Further optimization of intrinsic material parameters was conducted through modulation of absorber layer thickness, back contact metal, and bulk defect concentration, resulting in an improvement in the PCE of the device from 13.29 to 16.68%. Overall, the results from this investigation provide much-needed insight and guidance for researchers at large, and experimentalists in particular, toward fabricating commercially viable nontoxic inorganic perovskite alternatives for the burgeoning solar industry.

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 · 10.1021/acsomega.2c01076

Cites

81 of 81 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 Schematic of environment pollution by Pb-based perovskites.
Figure 1 Schematic of environment pollution by Pb-based perovskites.CC BY-NC-ND · PubMed Central
Figure 2 Crystal structure of CsSnI3.
Figure 2 Crystal structure of CsSnI3.CC BY-NC-ND · PubMed Central
Figure 3 Schematic of the solar device structure utilized in SCAPS simulation.
Figure 3 Schematic of the solar device structure utilized in SCAPS simulation.CC BY-NC-ND · PubMed Central
Figure 4 Optical absorption coefficient of Cs-based perovskite materials.
Figure 4 Optical absorption coefficient of Cs-based perovskite materials.CC BY-NC-ND · PubMed Central
Figure 5 Parity plot for train and test data side by side.
Figure 5 Parity plot for train and test data side by side.CC BY-NC-ND · PubMed Central
Figure 6 Relative strengths of importance indices of features.
Figure 6 Relative strengths of importance indices of features.CC BY-NC-ND · PubMed Central
Figure 7 Noncorrelated features’ contribution on device PCE as measured by SHAP with random forest regression (in decreasing order).
Figure 7 Noncorrelated features’ contribution on device PCE as measured by SHAP with random forest regression (in decreasing order).CC BY-NC-ND · PubMed Central
Figure 8 Branch of the decision tree with only pure leaf nodes, demonstrating a route to achieve higher PCE.
Figure 8 Branch of the decision tree with only pure leaf nodes, demonstrating a route to achieve higher PCE.CC BY-NC-ND · PubMed Central
Figure 9 PCE as a function of changing bandgap and hole mobility, and at a constant EA 4.25 eV.
Figure 9 PCE as a function of changing bandgap and hole mobility, and at a constant EA 4.25 eV.CC BY-NC-ND · PubMed Central
Figure 10 Contour plots showing the relation of bandgap and hole mobility with device PCE at different EA values (A) 4.15, (B) 4.20, (C) 4.25, and (D) 4.30 eV.
Figure 10 Contour plots showing the relation of bandgap and hole mobility with device PCE at different EA values (A) 4.15, (B) 4.20, (C) 4.25, and (D) 4.30 eV.CC BY-NC-ND · PubMed Central
Figure 11 J–V characteristic parameters as a function of absorber (perovskite) thickness: (a) Voc, (b) Jsc, (c) FF, and (d) PCE.
Figure 11 J–V characteristic parameters as a function of absorber (perovskite) thickness: (a) Voc, (b) Jsc, (c) FF, and (d) PCE.CC BY-NC-ND · PubMed Central
Figure 12 Characteristic device parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the bulk absorber layer.
Figure 12 Characteristic device parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the bulk absorber layer.CC BY-NC-ND · PubMed Central
Figure 13 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the HTL/absorber interface.
Figure 13 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the HTL/absorber interface.CC BY-NC-ND · PubMed Central
Figure 14 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the ETL/absorber interface.
Figure 14 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE at different defect concentrations and energy levels for the ETL/absorber interface.CC BY-NC-ND · PubMed Central
Figure 15 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE utilizing different back contact metal work functions.
Figure 15 Characteristic parameters: (a) Voc, (b) Jsc, (c) FF, and (d) PCE utilizing different back contact metal work functions.CC BY-NC-ND · PubMed Central
Figure 16 External quantum efficiency (EQE) at different photon energy levels for the champion device before and after optimization.
Figure 16 External quantum efficiency (EQE) at different photon energy levels for the champion device before and after optimization.CC BY-NC-ND · PubMed Central
Figure 17 J–V curve of the optimized and unoptimized devices.
Figure 17 J–V curve of the optimized and unoptimized devices.CC BY-NC-ND · PubMed Central

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

Show all 81 references

Research works printed but not linked: 2

  1. James G., 2013, Springer Texts in Statistics, 103
  2. Kramer O., 2016, Studies in Big Data, 45

Cited by

Metadata

Authors
Islam, M. S., Islam, M. T., Sarker, S., Jame, H. A., Nishat, S. S., Jani, M. R., Rauf, A., Ahsan, S., Shorowordi, K. M., Efstathiadis, H., Carbonara, J., & Ahmed, S.
Affiliations
  • Bangladesh University of Engineering and Technology (BD)
  • University at Buffalo, State University of New York (US)
  • Rensselaer Polytechnic Institute (US)
  • SUNY Polytechnic Institute (US)
  • Buffalo State University (US)
Corresponding author
Ahmed, Saquib
Venue
ACS Omega
Published
2022-06-22
Volume
7
Issue
26
Pages
22263-22278
ISSN
2470-1343 (ISSN-L)
OpenAlex
W4283265756
Cited by
76
References
82
Citations by year
2026: 28 · 2025: 24 · 2024: 14 · 2023: 10
FWCI
3.29
Type
journal article
Language
en
Open access
Locations
  • ACS Omega (publishedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Funders
University at Buffalo (53)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Perovskite Materials and Applications
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Materials Science › Materials Chemistry › Ferroelectric and Piezoelectric Materials
Keywords
power conversion efficiency, absorber thickness, SCAPS-1D simulation

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.