A machine learning model with crude estimation of property strategy for performance prediction of perovskite solar cells based on process optimization DOI Creative Commons
Dan Li, Ernie Che Mid, Shafriza Nisha Basah

et al.

APL Materials, Journal Year: 2024, Volume and Issue: 12(12)

Published: Dec. 1, 2024

Perovskite solar cells (PSCs) have attracted significant attention due to their high power conversion efficiency (PCE) and affordability. However, optimizing the preparation parameters for PSCs is crucial. This study establishes a machine learning model incorporating crude estimation of property (CEP) strategy enhance prediction accuracy precisely control process parameters. The model’s evaluation metrics improved by utilizing excess non-stoichiometric components (Ensc) perovskite additive compounds (Pac) as CEP. Notably, coefficient determination (R2) on test set increased 16.14%, while root mean square error decreased 20.44%, respectively. Nine algorithms, including decision tree (DT), random forest (RF), CatBoost, LassoLarsCV, histogram gradient boosting, extreme boosting (XGBoost), K nearest neighbor, ridge regression (Ridge), linear (Linear R), were employed optimize PSC assess its impact device performance. best-performing models, DT RF, combined create stacking demonstrating most stable overall performance training sets. identified key affecting PCE based model. Among these, adding Ensc was critical factor, followed thickness, thermal annealing time (Ta-ti), deposition solvent (Pds), mixing ratio, Pac. Experimental verification showed that with 10% PbI2 exhibited higher compared those 5% excess, confirming can effectively PCE. These findings offer valuable reference improving performance, thereby saving labor costs.

Language: Английский

Benzothiophene semiconductor polymer design by machine learning with low exciton binding energy: A vast chemical space generation for new structures DOI

Shaimaa Hassan Mallah,

Cihat Güleryüz, Sajjad Hussain Sumrra

et al.

Materials Science in Semiconductor Processing, Journal Year: 2025, Volume and Issue: 190, P. 109331 - 109331

Published: Jan. 28, 2025

Language: Английский

Citations

3
Practical Machine Learning Model Selection and Interpretation for Organophosphorus Flame Retardancy in Epoxy Resin DOI
Jiajun Li, Bin Zou, Amirbek Bekeshev

et al.

Polymer Degradation and Stability, Journal Year: 2025, Volume and Issue: 234, P. 111209 - 111209

Published: Jan. 19, 2025

Language: Английский

Citations

1
Design of experiments with the support of machine learning for process parameter optimization of all‐small‐molecule organic solar cells DOI Creative Commons
Kuo Wang, Jiaojiao Liang, Zhennan Li

et al.

FlexMat., Journal Year: 2024, Volume and Issue: 1(3), P. 234 - 247

Published: Sept. 24, 2024

Abstract Traditionally, squaraine dyes have been studied and employed in biomedical research due to their excellent optical properties, the molecules are being adopted different fields such as organic solar cells. In this study, we investigate correlations between cell performance processing parameters of all‐small‐molecule bulk heterojunction cells comprising (SQ) electron donor (D) non‐fullerene small (e.g., ITIC) acceptor (A) with help machine learning (ML) design experiment (DoE) methods. Among five predictive ML models tested selected parameters, eXtreme gradient boosting model shows satisfactory results quite high coefficient determination 0.999 0.997 training testing sets, respectively. By measuring contribution each input variable efficiency, four process that is, total concentration, ratio D/A, rotational speed spin coating, annealing temperature, found be key features strongly correlated efficiency. From contour plots DoE, highest efficiency approximately 5% can predicted under conditions 15 mg mL −1 solution a 1:2 mix D A, speeds ranging from 800 900 rpm, temperatures within 100–110°C. Using suggested parameter conditions, fabricated cells, achieving 4%. Besides global optimization also employ solvent vapor combination thermal facilitate further mobilization more optimized microstructure films, resulting enhancement than 20%.

Language: Английский

Citations

7
The Pseudo-Bilayer Bulk Heterojunction Active Layer of Polymer Solar Cells in Green Solvent with 18.48% Efficiency DOI Open Access

Jingyue Cao,

Zheng Xu

Polymers, Journal Year: 2025, Volume and Issue: 17(3), P. 284 - 284

Published: Jan. 22, 2025

Planar heterojunction (PHJ) is employed to obtain proper vertical phase separation for highly efficient polymer solar cells (PSCs). However, it heavily relies on the choice of orthogonal solvent in production process. Here, we fabricated a pseudo-bilayer bulk (PBHJ) PSC with cross-distribution direction by preparing two layers PM6 and BTP-eC9 blends an o-XY solution different dilution ratios study morphological evolution PBHJ film. We found that film exhibits more uniform suitable continuous interpenetrating network morphology formation p-i-n structure. This provides effective channel exciton dissociation charge transport, which confirmed both generation simulations dynamics measurements. The devices can effectively inhibit trap recombination accelerate transfer. Based good active layer balanced mobility, all-green solvent-processed PSCs champion power conversion efficiencies (PCEs) 18.48% 16.83% are obtained PM6:BTP-eC9 PTQ10:BTP-eC9 systems, respectively. work reveals potential mechanism induced structure alternative approach developing processing PSCs.

Language: Английский

Citations

0
Machine Learning-assisted Prediction of Organic Solar Cell Efficiency from TCA triplelayer reflectance Spectra DOI
Fuhao Gao, Jinxin Zhou, Junwei Zhao

et al.

Optics Communications, Journal Year: 2025, Volume and Issue: unknown, P. 131654 - 131654

Published: Feb. 1, 2025

Language: Английский

Citations

0
Quantitative Analysis of Perovskite Morphologies Employing Deep Learning Framework Enables Accurate Solar Cell Performance Prediction DOI Open Access
Haixin Zhou, Kuo Wang,

Cong Nie

et al.

Small, Journal Year: 2025, Volume and Issue: unknown

Published: March 20, 2025

Abstract In perovskite solar cells, grain boundaries are considered one of the major structural defect sites, and consequently affect cell performance. Therefore, a precise edge detection grains may enable to predict resulting Herein, deep learning model, Self‐UNet, is developed extract quantify morphological information such as boundary length (GBL), number (NG), average surface area (AGSA) from scanning elecron microscope (SEM) images. The Self‐UNet excels conventional Canny UNet models in extraction; Dice coefficient F1‐score exhibit high 91.22% 93.58%, respectively. accuracy allows for not only identifying tiny stuck between relatively large grains, but also distinguishing actual grooves on low quality SEM images, avoiding under‐ or over‐estimation information. Moreover, gradient boosted decision tree (GBDT) regression integrated exhibits predicting efficiency with relative errors less than 10% compared experimentally measured efficiencies, which corroborated by results literature experiments. Additionally, GBL can be verified multiple ways new feature.

Language: Английский

Citations

0
Modeling and Design of Non-Fullerene Organic Solar Cells Using Pyramidal Lens Arrays. DOI
Asma Iqbal wani,

Farkhanda Ana,

Hakim Najeeb-ud-din

et al.

Micro and Nanostructures, Journal Year: 2025, Volume and Issue: unknown, P. 208175 - 208175

Published: April 1, 2025

Language: Английский

Citations

0
Applications of machine learning in surfaces and interfaces DOI Open Access
Shaofeng Xu, Jing‐Yuan Wu, Ying Guo

et al.

Chemical Physics Reviews, Journal Year: 2025, Volume and Issue: 6(1)

Published: March 1, 2025

Surfaces and interfaces play key roles in chemical material science. Understanding physical processes at complex surfaces is a challenging task. Machine learning provides powerful tool to help analyze accelerate simulations. This comprehensive review affords an overview of the applications machine study systems materials. We categorize into following broad categories: solid–solid interface, solid–liquid liquid–liquid surface solid, liquid, three-phase interfaces. High-throughput screening, combined first-principles calculations, force field accelerated molecular dynamics simulations are used rational design such as all-solid-state batteries, solar cells, heterogeneous catalysis. detailed information on for

Language: Английский

Citations

0
Investigation of Short‐Circuit Current Density in Non‐Fullerene‐Based Ternary Organic Solar Cells by Incorporating Machine Learning Algorithms with Effective Descriptors DOI
Min‐Hsuan Lee, Ying‐Chun Chen, Yi‐Ming Chang

et al.

Solar RRL, Journal Year: 2025, Volume and Issue: unknown

Published: May 8, 2025

Non‐fullerene acceptor (NFA)‐based ternary organic solar cells (OSCs) are emerging as promising devices for converting sunlight into electricity, contributing to environmental solutions. However, selecting the third component remains a significant challenge, it plays critical role in achieving high short‐circuit current density ( J sc ) NFA‐based OSCs (comprising donors, acceptors, and component). Traditional trial‐and‐error experimental methods face substantial limitations, including energy consumption, cost, time demands, which may not be sufficient investigating quantitative relationships between material properties OSCs. In this study, we examine effects of highest occupied molecular orbital–lowest unoccupied orbital (HOMO–LUMO) gap (ΔHOMO ΔLUMO) different materials, considering these effective descriptors, on primary photovoltaic parameter The eXtreme Gradient Boosting (XGBoost) algorithm yields reasonable predictions, with an R 2 value 0.76. Additionally, three fabricated characterized experimentally validate predictions made by proposed model. Using inputs, model demonstrates good predictive accuracy values. interpretable descriptors offer practical machine‐learning approach accelerating development targeted values can also extended other electronic applications.

Language: Английский

Citations

0
Optimization of defect regulation parameters in CsPbI3 perovskite solar cells via machine learning-assisted response surface methodology DOI
Cong Shen, Ziqi Zhou, Tengling Ye

et al.

Renewable Energy, Journal Year: 2025, Volume and Issue: unknown, P. 123426 - 123426

Published: May 1, 2025

Language: Английский

Citations

0