High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model
The high porosity and tunable chemical functionality of metal-organic frameworks (MOFs) make it a promising catalyst design platform. High-throughput screening of catalytic performance is feasible since the large MOF structure database is available. In this study, we report a machine learning model...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2025-01-01
|
| Series: | Green Energy & Environment |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468025724000323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560099713187840 |
|---|---|
| author | Xuefeng Bai Yi Li Yabo Xie Qiancheng Chen Xin Zhang Jian-Rong Li |
| author_facet | Xuefeng Bai Yi Li Yabo Xie Qiancheng Chen Xin Zhang Jian-Rong Li |
| author_sort | Xuefeng Bai |
| collection | DOAJ |
| description | The high porosity and tunable chemical functionality of metal-organic frameworks (MOFs) make it a promising catalyst design platform. High-throughput screening of catalytic performance is feasible since the large MOF structure database is available. In this study, we report a machine learning model for high-throughput screening of MOF catalysts for the CO2 cycloaddition reaction. The descriptors for model training were judiciously chosen according to the reaction mechanism, which leads to high accuracy up to 97% for the 75% quantile of the training set as the classification criterion. The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding. 12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100 °C and 1 bar within one day using the model, and 239 potentially efficient catalysts were discovered. Among them, MOF-76(Y) achieved the top performance experimentally among reported MOFs, in good agreement with the prediction. |
| format | Article |
| id | doaj-art-38fabfddce154176aa7403f8893bb44a |
| institution | Kabale University |
| issn | 2468-0257 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Green Energy & Environment |
| spelling | doaj-art-38fabfddce154176aa7403f8893bb44a2025-01-05T04:28:24ZengKeAi Communications Co., Ltd.Green Energy & Environment2468-02572025-01-01101132138High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning modelXuefeng Bai0Yi Li1Yabo Xie2Qiancheng Chen3Xin Zhang4Jian-Rong Li5Beijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaBeijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaBeijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaBeijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaCorresponding authors.; Beijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaCorresponding authors.; Beijing Key Laboratory for Green Catalysis and Separation and Department of Chemical Engineering, College of Materials Science & Engineering, Beijing University of Technology, Beijing, 100124, ChinaThe high porosity and tunable chemical functionality of metal-organic frameworks (MOFs) make it a promising catalyst design platform. High-throughput screening of catalytic performance is feasible since the large MOF structure database is available. In this study, we report a machine learning model for high-throughput screening of MOF catalysts for the CO2 cycloaddition reaction. The descriptors for model training were judiciously chosen according to the reaction mechanism, which leads to high accuracy up to 97% for the 75% quantile of the training set as the classification criterion. The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding. 12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100 °C and 1 bar within one day using the model, and 239 potentially efficient catalysts were discovered. Among them, MOF-76(Y) achieved the top performance experimentally among reported MOFs, in good agreement with the prediction.http://www.sciencedirect.com/science/article/pii/S2468025724000323Metal-organic frameworksHigh-throughput screeningMachine learningExplainable modelCO2 cycloaddition |
| spellingShingle | Xuefeng Bai Yi Li Yabo Xie Qiancheng Chen Xin Zhang Jian-Rong Li High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model Green Energy & Environment Metal-organic frameworks High-throughput screening Machine learning Explainable model CO2 cycloaddition |
| title | High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model |
| title_full | High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model |
| title_fullStr | High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model |
| title_full_unstemmed | High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model |
| title_short | High-throughput screening of CO2 cycloaddition MOF catalyst with an explainable machine learning model |
| title_sort | high throughput screening of co2 cycloaddition mof catalyst with an explainable machine learning model |
| topic | Metal-organic frameworks High-throughput screening Machine learning Explainable model CO2 cycloaddition |
| url | http://www.sciencedirect.com/science/article/pii/S2468025724000323 |
| work_keys_str_mv | AT xuefengbai highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel AT yili highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel AT yaboxie highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel AT qianchengchen highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel AT xinzhang highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel AT jianrongli highthroughputscreeningofco2cycloadditionmofcatalystwithanexplainablemachinelearningmodel |