Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network
Imidazolium-based ionic liquids (ILs) have been regarded as green solvents owing to their unique properties. Among these, the melting point is key to their excellent performance in applications such as catalysis, biomass processing, and energy storage, where stability and operational temperature ran...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Chemistry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2624-8549/6/6/94 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105365503016960 |
|---|---|
| author | Xinyu Liu Jie Yin Xinmiao Zhang Wenxiang Qiu Wei Jiang Ming Zhang Linhua Zhu Hongping Li Huaming Li |
| author_facet | Xinyu Liu Jie Yin Xinmiao Zhang Wenxiang Qiu Wei Jiang Ming Zhang Linhua Zhu Hongping Li Huaming Li |
| author_sort | Xinyu Liu |
| collection | DOAJ |
| description | Imidazolium-based ionic liquids (ILs) have been regarded as green solvents owing to their unique properties. Among these, the melting point is key to their excellent performance in applications such as catalysis, biomass processing, and energy storage, where stability and operational temperature range are critical. The utilization of neural networks for forecasting the melting point is highly significant. Nevertheless, the excessive selection of descriptors obtained by density functional theory (DFT) calculations always leads to huge computational costs. Herein, this study strategically selected only 12 kinds of quantum chemical descriptors by employing a much more efficient semi-empirical method (PM7) to reduce computational costs. Four principles of data pre-processing were proposed, and the innovative use of a simulated annealing algorithm to search for the lowest energy molecular conformation improved accuracy. Based on these descriptors, a multi-layer perceptron neural network model was constructed to efficiently predict the melting points of 280 imidazolium-based ILs. The R<sup>2</sup> value of the current model reached 0.75, and the mean absolute error reached 25.03 K, indicating that this study achieved high accuracy with very little computational cost. This study reveals a strong correlation between descriptors and melting points. Additionally, the model accurately predicts unknown melting points of imidazolium-based ILs, achieving good results efficiently. |
| format | Article |
| id | doaj-art-982452d1fb2546429b69d3dce8c74429 |
| institution | Kabale University |
| issn | 2624-8549 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Chemistry |
| spelling | doaj-art-982452d1fb2546429b69d3dce8c744292024-12-27T14:17:00ZengMDPI AGChemistry2624-85492024-11-01661552157110.3390/chemistry6060094Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural NetworkXinyu Liu0Jie Yin1Xinmiao Zhang2Wenxiang Qiu3Wei Jiang4Ming Zhang5Linhua Zhu6Hongping Li7Huaming Li8Institute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaSchool of the Environment and Safety Engineering, Jiangsu University, Zhenjiang 212013, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaEngineering Research Center of Tropical Marine Functional Polymer Materials of Hainan Province, Key Laboratory of Water Pollution Treatment and Resource Reuse of Hainan Province, Key Laboratory of Functional Organic Polymers of Haikou, College of Chemistry and Chemical Engineering, Hainan Normal University, Haikou 571158, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaInstitute for Energy Research, Jiangsu University, Zhenjiang 212013, ChinaImidazolium-based ionic liquids (ILs) have been regarded as green solvents owing to their unique properties. Among these, the melting point is key to their excellent performance in applications such as catalysis, biomass processing, and energy storage, where stability and operational temperature range are critical. The utilization of neural networks for forecasting the melting point is highly significant. Nevertheless, the excessive selection of descriptors obtained by density functional theory (DFT) calculations always leads to huge computational costs. Herein, this study strategically selected only 12 kinds of quantum chemical descriptors by employing a much more efficient semi-empirical method (PM7) to reduce computational costs. Four principles of data pre-processing were proposed, and the innovative use of a simulated annealing algorithm to search for the lowest energy molecular conformation improved accuracy. Based on these descriptors, a multi-layer perceptron neural network model was constructed to efficiently predict the melting points of 280 imidazolium-based ILs. The R<sup>2</sup> value of the current model reached 0.75, and the mean absolute error reached 25.03 K, indicating that this study achieved high accuracy with very little computational cost. This study reveals a strong correlation between descriptors and melting points. Additionally, the model accurately predicts unknown melting points of imidazolium-based ILs, achieving good results efficiently.https://www.mdpi.com/2624-8549/6/6/94imidazolium-based ionic liquidmelting pointsemi-empirical methodannealingartificial neural network |
| spellingShingle | Xinyu Liu Jie Yin Xinmiao Zhang Wenxiang Qiu Wei Jiang Ming Zhang Linhua Zhu Hongping Li Huaming Li Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network Chemistry imidazolium-based ionic liquid melting point semi-empirical method annealing artificial neural network |
| title | Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network |
| title_full | Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network |
| title_fullStr | Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network |
| title_full_unstemmed | Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network |
| title_short | Rapid and Accurate Prediction of the Melting Point for Imidazolium-Based Ionic Liquids by Artificial Neural Network |
| title_sort | rapid and accurate prediction of the melting point for imidazolium based ionic liquids by artificial neural network |
| topic | imidazolium-based ionic liquid melting point semi-empirical method annealing artificial neural network |
| url | https://www.mdpi.com/2624-8549/6/6/94 |
| work_keys_str_mv | AT xinyuliu rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT jieyin rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT xinmiaozhang rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT wenxiangqiu rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT weijiang rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT mingzhang rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT linhuazhu rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT hongpingli rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork AT huamingli rapidandaccuratepredictionofthemeltingpointforimidazoliumbasedionicliquidsbyartificialneuralnetwork |