Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies
This research provides a machine learning (ML) method to predict the optical density of photovoltaic (PV) polymers. The results show that extra gradient boosting regressor and random forest regressor are the best-performing models among all the tested ML models, whose good R-squared (R...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2025-07-01
|
| Series: | Open Physics |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/phys-2025-0172 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850096634277396480 |
|---|---|
| author | Aljaafreh Mamduh J. Hassan Abrar U. |
| author_facet | Aljaafreh Mamduh J. Hassan Abrar U. |
| author_sort | Aljaafreh Mamduh J. |
| collection | DOAJ |
| description | This research provides a machine learning (ML) method to predict the optical density of photovoltaic (PV) polymers. The results show that extra gradient boosting regressor and random forest regressor are the best-performing models among all the tested ML models, whose good R-squared (R
2) values reveal their prediction accuracy. Furthermore, their SHapley Additive exPlanations analysis demonstrates that the polar surface area is the most impactful feature to influence its model outputs for highlighting its essential role in their design process. The results also reveal that the evaluated models exhibit consistent performance across different K values, with their mean squared error values spanning from 0.001 to 0.009 and R
2 values of 0.96–0.98. In addition, their synthetic accessibility likelihood index scores show a value as high as 15 for the top polymers to imply favorable conditions for their practical synthesis. The current study not only expands the understanding of polymer design but also furthers the field of PVs by establishing a good framework to design efficient solar energy materials. |
| format | Article |
| id | doaj-art-3cc539994ba7452e9f6f0d2176dacecc |
| institution | DOAJ |
| issn | 2391-5471 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Open Physics |
| spelling | doaj-art-3cc539994ba7452e9f6f0d2176dacecc2025-08-20T02:41:11ZengDe GruyterOpen Physics2391-54712025-07-012311616519010.1515/phys-2025-0172Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studiesAljaafreh Mamduh J.0Hassan Abrar U.1Physics Department, College of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, 11623, Saudi ArabiaDepartment of Chemistry, University of Gujrat, Gujrat, 50700, Punjab, PakistanThis research provides a machine learning (ML) method to predict the optical density of photovoltaic (PV) polymers. The results show that extra gradient boosting regressor and random forest regressor are the best-performing models among all the tested ML models, whose good R-squared (R 2) values reveal their prediction accuracy. Furthermore, their SHapley Additive exPlanations analysis demonstrates that the polar surface area is the most impactful feature to influence its model outputs for highlighting its essential role in their design process. The results also reveal that the evaluated models exhibit consistent performance across different K values, with their mean squared error values spanning from 0.001 to 0.009 and R 2 values of 0.96–0.98. In addition, their synthetic accessibility likelihood index scores show a value as high as 15 for the top polymers to imply favorable conditions for their practical synthesis. The current study not only expands the understanding of polymer design but also furthers the field of PVs by establishing a good framework to design efficient solar energy materials.https://doi.org/10.1515/phys-2025-0172polymer designmachine learningdftshaptransformer assisted orientationsali |
| spellingShingle | Aljaafreh Mamduh J. Hassan Abrar U. Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies Open Physics polymer design machine learning dft shap transformer assisted orientation sali |
| title | Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies |
| title_full | Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies |
| title_fullStr | Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies |
| title_full_unstemmed | Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies |
| title_short | Design and prediction of high optical density photovoltaic polymers using machine learning-DFT studies |
| title_sort | design and prediction of high optical density photovoltaic polymers using machine learning dft studies |
| topic | polymer design machine learning dft shap transformer assisted orientation sali |
| url | https://doi.org/10.1515/phys-2025-0172 |
| work_keys_str_mv | AT aljaafrehmamduhj designandpredictionofhighopticaldensityphotovoltaicpolymersusingmachinelearningdftstudies AT hassanabraru designandpredictionofhighopticaldensityphotovoltaicpolymersusingmachinelearningdftstudies |