Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data

Recent advances in machine learning (ML) have enabled predictive programs for photovoltaic characterization, optimization, and materials discovery. Despite these advances, the standard photovoltaic materials development workflow still involves manually performing multiple characterization techniques...

Full description

Saved in:
Bibliographic Details
Main Authors: Hoon Jeong Lee, Arlene Chiu, Yida Lin, Sreyas Chintapalli, Serene Kamal, Eric Ji, Susanna M. Thon
Format: Article
Language:English
Published: Wiley 2025-04-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400310
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203024760242176
author Hoon Jeong Lee
Arlene Chiu
Yida Lin
Sreyas Chintapalli
Serene Kamal
Eric Ji
Susanna M. Thon
author_facet Hoon Jeong Lee
Arlene Chiu
Yida Lin
Sreyas Chintapalli
Serene Kamal
Eric Ji
Susanna M. Thon
author_sort Hoon Jeong Lee
collection DOAJ
description Recent advances in machine learning (ML) have enabled predictive programs for photovoltaic characterization, optimization, and materials discovery. Despite these advances, the standard photovoltaic materials development workflow still involves manually performing multiple characterization techniques on every new device, requiring significant time and expenditures. One barrier to ML implementation is that most models reported to date are trained on computer simulated data, due to the difficulty in experimentally collecting the massive data sets needed for model training, limiting the ability to assess the limitations and validity of these methods, as well as to access new potential physical mechanisms absent in simulations. Herein, several neural networks trained on experimental data from PbS colloidal quantum dot thin‐film solar cells are introduced. These models predict multiple, complex materials properties, including carrier mobility, relative photoluminescence intensity, and electronic trap‐state density, from a single, simple measurement: illuminated current–voltage curves. The measurement system considers the spatial distribution of the materials parameters to gather and predict large amounts of data by treating an inhomogeneous device as a series of thousands of micro‐devices, a novel feature compared to existing solutions. This model can be extended to other materials and devices, accelerating development times for new optoelectronic technologies.
format Article
id doaj-art-fbaa0c543cea4e94b07aee7c9feefb24
institution OA Journals
issn 2640-4567
language English
publishDate 2025-04-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-fbaa0c543cea4e94b07aee7c9feefb242025-08-20T02:11:37ZengWileyAdvanced Intelligent Systems2640-45672025-04-0174n/an/a10.1002/aisy.202400310Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental DataHoon Jeong Lee0Arlene Chiu1Yida Lin2Sreyas Chintapalli3Serene Kamal4Eric Ji5Susanna M. Thon6Department of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USADepartment of Electrical and Computer Engineering Johns Hopkins University 3400 N. Charles Street Baltimore MD 21218 USARecent advances in machine learning (ML) have enabled predictive programs for photovoltaic characterization, optimization, and materials discovery. Despite these advances, the standard photovoltaic materials development workflow still involves manually performing multiple characterization techniques on every new device, requiring significant time and expenditures. One barrier to ML implementation is that most models reported to date are trained on computer simulated data, due to the difficulty in experimentally collecting the massive data sets needed for model training, limiting the ability to assess the limitations and validity of these methods, as well as to access new potential physical mechanisms absent in simulations. Herein, several neural networks trained on experimental data from PbS colloidal quantum dot thin‐film solar cells are introduced. These models predict multiple, complex materials properties, including carrier mobility, relative photoluminescence intensity, and electronic trap‐state density, from a single, simple measurement: illuminated current–voltage curves. The measurement system considers the spatial distribution of the materials parameters to gather and predict large amounts of data by treating an inhomogeneous device as a series of thousands of micro‐devices, a novel feature compared to existing solutions. This model can be extended to other materials and devices, accelerating development times for new optoelectronic technologies.https://doi.org/10.1002/aisy.202400310machine learningsmaterials parameter predictionsoptoelectronicsPbS colloidal quantum dotsphotovoltaics
spellingShingle Hoon Jeong Lee
Arlene Chiu
Yida Lin
Sreyas Chintapalli
Serene Kamal
Eric Ji
Susanna M. Thon
Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
Advanced Intelligent Systems
machine learnings
materials parameter predictions
optoelectronics
PbS colloidal quantum dots
photovoltaics
title Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
title_full Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
title_fullStr Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
title_full_unstemmed Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
title_short Predicting PbS Colloidal Quantum Dot Solar Cell Parameters Using Neural Networks Trained on Experimental Data
title_sort predicting pbs colloidal quantum dot solar cell parameters using neural networks trained on experimental data
topic machine learnings
materials parameter predictions
optoelectronics
PbS colloidal quantum dots
photovoltaics
url https://doi.org/10.1002/aisy.202400310
work_keys_str_mv AT hoonjeonglee predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT arlenechiu predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT yidalin predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT sreyaschintapalli predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT serenekamal predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT ericji predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata
AT susannamthon predictingpbscolloidalquantumdotsolarcellparametersusingneuralnetworkstrainedonexperimentaldata