Interpretable machine learning for developing high-performance organic solar cells

Abadi, Elyas Abbasi Jannat; Sahu, Harikrishna; Javadpour, Seyed Morteza; Goharimanesh, Masoud

doi:10.1016/j.mtener.2022.100969

Cited by 11 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Brabec et al 64 proposed a modification to the Scharber model by taking the absorption of non-fullerene acceptors (NFAs) into account. In 2018, Ma et al 50 created a FA based dataset of 280 OSCs with small molecule donors, and the same dataset was used by Goharimanesh et al 65 in 2022 for interpretable ML models. Saeki et al 66 in 2018 created a FA based dataset of 1200 OSCs with polymer donors for PCE prediction, and the same approach was used by Wei et al 67 for 500 NFA based OSCs.…”

Section: Machine Learning Workflowmentioning

confidence: 99%

“…Quantitative structure–property relationship (QSPR) models are being used to understand the hidden relationship between materials and their photovoltaic properties. 52 A relationship between the structure of materials and their target property could be obtained by generating feature importance 53 and visualization of decision tree. 71 Various ML methodologies have been used specifically on OSCs for QSPR.…”

Section: Machine Learning Workflowmentioning

confidence: 99%

“…Goharimanesh et al 65 in 2022 used 240 small molecule OSC data from the dataset of Ma et al . 50 The performance of six ML models (LR, k-NN, ANN, RF, GB, and XGB) was compared for the prediction of PCE.…”

Section: Review Of ML In Osc Researchmentioning

confidence: 99%

“…Here comes the use of dimensionality reduction techniques such as principal component analysis (PCA), which is commonly used in the community. ML has granted the OSC research community entirely new abilities from predicting photovoltaic properties, 50 quantitative structure–property relationship (QSPR), 51,52 design of experiments (DOE), 47,53 novel polymer/NFA discovery, 54,55 and robotization of labs. 48,56 Most of the studies in the field are regression problems, and only a few are done for classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Opportunities and challenges for machine learning to select combination of donor and acceptor materials for efficient organic solar cells

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Machine Learning Workflowmentioning

confidence: 99%

Section: Machine Learning Workflowmentioning

confidence: 99%

Section: Review Of ML In Osc Researchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Opportunities and challenges for machine learning to select combination of donor and acceptor materials for efficient organic solar cells

et al. 2022

View full text Add to dashboard Cite

show abstract

“…[14][15][16] This early understanding of the optoelectronic device through the ML approach helps the material science community to clearly understand, discover, and optimize the fabrication process to develop highly efficient TFSCs. [17][18][19][20][21][22] It also provides key steps in the device fabrication process and optimal layer fabrication conditions omitting excessive experimental stages (Figure 1). [22][23][24][25] Accordingly, high throughput ML techniques are extensively employed for different photovoltaic (PV) materials.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Assisted Analysis, Prediction, and Fabrication of High‐Efficiency CZTSSe Thin Film Solar Cells

Karade

Sutar

Shin

et al. 2023

Adv Funct Materials

View full text Add to dashboard Cite

The Earth‐abundant element‐based Cu2ZnSn(S,Se)4 (CZTSSe) absorber is considered as a promising material for thin‐film solar cells (TFSCs). The current record power conversion efficiency (PCE) of CZTSSe TFSCs is ≈13%, and it's still lower than CdTe and CIGS‐based TFSCs. A further breakthrough in its PCE mainly relies on deep insights into the various device fabrication conditions; accordingly, the experimental–oriented machine learning (ML) approach can be an effective way to discover key governing factors in improving PCE. The present work aims to identify the key governing factors throughout the device fabrication processes and apply them to break the saturated PCE for CZTSSe TFSCs. For realization, over 25,000 data points were broadly collected by fabricating more than 1300 CZTSSe TFSC devices and analyzed them using various ML techniques. Through extensive ML analysis, the i‐ZnO thickness is found to be the first, while Zn/Sn compositional ratio and sulfo‐selenization temperature are other key governing factors under thin or thick i‐ZnO thickness to achieve over 11% PCE. Based on these key governing factors, the applied random forest ML prediction model for PCE showed Adj. R2 = >0.96. Finally, the best‐predicted ML conditions considered for experimental validation showed well‐matched experimental outcomes with different ML models.

show abstract

Design of experiments with the support of machine learning for process parameter optimization of all‐small‐molecule organic solar cells

Wang,

Liang,

et al. 2024

FlexMat

View full text Add to dashboard Cite

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

show abstract

Interpretable machine learning for developing high-performance organic solar cells

Cited by 11 publications

References 37 publications

Opportunities and challenges for machine learning to select combination of donor and acceptor materials for efficient organic solar cells

Opportunities and challenges for machine learning to select combination of donor and acceptor materials for efficient organic solar cells

Machine Learning Assisted Analysis, Prediction, and Fabrication of High‐Efficiency CZTSSe Thin Film Solar Cells

Design of experiments with the support of machine learning for process parameter optimization of all‐small‐molecule organic solar cells

Contact Info

Product

Resources

About