RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes
Aqueous Organic Redox Flow Batteries (AORFBs) are considered as one of the most appealing technologies for large-scale energy storage due to their electroactive organic materials, which are abundant, easy to produce, and recyclable. A prevailing challenge for the redox chemistries applied in AORFBs...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Artificial Intelligence Chemistry |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2949747724000228 |
| _version_ | 1797214818882551808 |
|---|---|
| author | Murat Cihan Sorkun Elham Nour Ghassemi Cihan Yatbaz J.M. Vianney A. Koelman Süleyman Er |
| author_facet | Murat Cihan Sorkun Elham Nour Ghassemi Cihan Yatbaz J.M. Vianney A. Koelman Süleyman Er |
| author_sort | Murat Cihan Sorkun |
| collection | DOAJ |
| description | Aqueous Organic Redox Flow Batteries (AORFBs) are considered as one of the most appealing technologies for large-scale energy storage due to their electroactive organic materials, which are abundant, easy to produce, and recyclable. A prevailing challenge for the redox chemistries applied in AORFBs is to achieve high power and energy density. The chemical design and molecular engineering of the electroactive compounds is an effective approach for the optimization of their physicochemical properties. Among them, the reaction energy of redox couples is often used as a proxy for the measured potentials. In this study, we present RedPred, a machine learning (ML) model that predicts the one-step two-electron two-proton redox reaction energy of redox-active molecule pairs. RedPred comprises an ensemble of Artificial Neural Networks, Random Forests, and Graph Convolutional Networks, trained using the RedDB database, which contains over 15,000 reactant-product pairs for AORFBs. We evaluated RedPred’s performance using six different molecular encoders and five prominent ML algorithms applied in chemical science. The predictive capability of RedPred was tested on both its training chemical space and the chemical space outside its training domain using two separate test datasets. We released a user-friendly web tool with open-source code to promote software sustainability and broad use. |
| first_indexed | 2024-04-24T11:20:13Z |
| format | Article |
| id | doaj.art-5c08e029f9a1431988f65f1cabdb36d7 |
| institution | Directory Open Access Journal |
| issn | 2949-7477 |
| language | English |
| last_indexed | 2024-04-24T11:20:13Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Artificial Intelligence Chemistry |
| spelling | doaj.art-5c08e029f9a1431988f65f1cabdb36d72024-04-11T04:42:16ZengElsevierArtificial Intelligence Chemistry2949-74772024-06-0121100064RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytesMurat Cihan Sorkun0Elham Nour Ghassemi1Cihan Yatbaz2J.M. Vianney A. Koelman3Süleyman Er4DIFFER – Dutch Institute for Fundamental Energy Research, De Zaale 20, Eindhoven 5612 AJ, The Netherlands; Center for Computational Energy Research, Department of Applied Physics, Eindhoven University of Technology, Eindhoven 5600 MB, The NetherlandsDIFFER – Dutch Institute for Fundamental Energy Research, De Zaale 20, Eindhoven 5612 AJ, The NetherlandsDIFFER – Dutch Institute for Fundamental Energy Research, De Zaale 20, Eindhoven 5612 AJ, The NetherlandsDIFFER – Dutch Institute for Fundamental Energy Research, De Zaale 20, Eindhoven 5612 AJ, The Netherlands; Center for Computational Energy Research, Department of Applied Physics, Eindhoven University of Technology, Eindhoven 5600 MB, The NetherlandsDIFFER – Dutch Institute for Fundamental Energy Research, De Zaale 20, Eindhoven 5612 AJ, The Netherlands; Corresponding author.Aqueous Organic Redox Flow Batteries (AORFBs) are considered as one of the most appealing technologies for large-scale energy storage due to their electroactive organic materials, which are abundant, easy to produce, and recyclable. A prevailing challenge for the redox chemistries applied in AORFBs is to achieve high power and energy density. The chemical design and molecular engineering of the electroactive compounds is an effective approach for the optimization of their physicochemical properties. Among them, the reaction energy of redox couples is often used as a proxy for the measured potentials. In this study, we present RedPred, a machine learning (ML) model that predicts the one-step two-electron two-proton redox reaction energy of redox-active molecule pairs. RedPred comprises an ensemble of Artificial Neural Networks, Random Forests, and Graph Convolutional Networks, trained using the RedDB database, which contains over 15,000 reactant-product pairs for AORFBs. We evaluated RedPred’s performance using six different molecular encoders and five prominent ML algorithms applied in chemical science. The predictive capability of RedPred was tested on both its training chemical space and the chemical space outside its training domain using two separate test datasets. We released a user-friendly web tool with open-source code to promote software sustainability and broad use.http://www.sciencedirect.com/science/article/pii/S2949747724000228Machine learningArtificial IntelligenceCheminformaticsRedox Flow BatteryAI for Chemistry |
| spellingShingle | Murat Cihan Sorkun Elham Nour Ghassemi Cihan Yatbaz J.M. Vianney A. Koelman Süleyman Er RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes Artificial Intelligence Chemistry Machine learning Artificial Intelligence Cheminformatics Redox Flow Battery AI for Chemistry |
| title | RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| title_full | RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| title_fullStr | RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| title_full_unstemmed | RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| title_short | RedPred, a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| title_sort | redpred a machine learning model for the prediction of redox reaction energies of the aqueous organic electrolytes |
| topic | Machine learning Artificial Intelligence Cheminformatics Redox Flow Battery AI for Chemistry |
| url | http://www.sciencedirect.com/science/article/pii/S2949747724000228 |
| work_keys_str_mv | AT muratcihansorkun redpredamachinelearningmodelforthepredictionofredoxreactionenergiesoftheaqueousorganicelectrolytes AT elhamnourghassemi redpredamachinelearningmodelforthepredictionofredoxreactionenergiesoftheaqueousorganicelectrolytes AT cihanyatbaz redpredamachinelearningmodelforthepredictionofredoxreactionenergiesoftheaqueousorganicelectrolytes AT jmvianneyakoelman redpredamachinelearningmodelforthepredictionofredoxreactionenergiesoftheaqueousorganicelectrolytes AT suleymaner redpredamachinelearningmodelforthepredictionofredoxreactionenergiesoftheaqueousorganicelectrolytes |