eLibrary
  • Home
  • Sources
  • Search
  • About

Data-Driven Development of Deep Eutectic Solvents: A Review of Machine Learning in Property Prediction and Rational Design

Zhen Yang, Xingchi Deng, Jin Shu, Yichi Zhang, Shengtao He
International Core Journal of Engineering, (2026), Vol.12, No.6, pp.119-132
Published: June 18, 2026
DOI: 10.6919/ICJE.202606_12(6).0011
PDF: Download Full Text PDF
Abstract

Deep Eutectic Solvents (DESs) represent a novel class of emerging green solvents formed through hydrogen-bonding interactions between hydrogen bond donors (HBDs) and hydrogen bond acceptors (HBAs). Boasting core advantages such as facile synthesis, low cost, environmental benignity, and exceptional structural and functional designability, DESs have demonstrated substantial application value and industrial potential across various sectors, including natural product extraction, biomass valorization, hydrometallurgy, acidic gas capture, and electrochemical energy storage. However, several fundamental scientific and technical bottlenecks-including the combinatorial explosion of the chemical design space arising from vast HBD/HBA combinations, the elusive structure-property relationships between microscopic intermolecular interactions and macroscopic physicochemical properties, and the challenges in synergistically optimizing multiple performance indicators in complex application scenarios-have rendered traditional "trial-and-error" R&D models inadequate for the targeted rational design of DESs, thereby significantly impeding their large-scale industrialization. As a data-driven intelligent research paradigm, machine learning (ML) provides a transformative technical route to address these challenges by leveraging its robust capabilities in high-dimensional feature mining, complex non-linear relationship fitting, and global optimization. This review systematically delineates the latest domestic and international advancements in ML-enabled DES research. First, it elucidates the core principles and mainstream methodologies for molecular descriptor selection and high-quality dataset construction in DES property prediction. Second, it summarizes model architectures, algorithmic optimizations, and predictive performance of ML regarding the thermophysical properties as well as chemical and biological activities of DESs. Subsequently, it highlights technical implementations and application outcomes of ML in the intelligent prediction of DES formation, application-oriented reverse design, and multi-objective optimization of extraction and separation processes. Finally, the review provides an in-depth analysis of the core challenges currently facing the field-such as the lack of standardized datasets, insufficient model interpretability, and weak mechanistic insights-while offering perspectives on future research directions. This review aims to provide a systematic theoretical framework and research roadmap for the intelligent rational design, precise property modulation, and industrial application of DESs, facilitating the paradigm shift in green solvent development from traditional empirical trial-and-error toward a data-driven intelligent paradigm.

Keywords: Deep Eutectic Solvents (DES); Machine Learning; Property Prediction; Inverse Design; Multi-objective Optimization; Data-driven.
APA Citation: Zhen Yang, Xingchi Deng, Jin Shu, Yichi Zhang, Shengtao He (2026). Data-Driven Development of Deep Eutectic Solvents: A Review of Machine Learning in Property Prediction and Rational Design. International Core Journal of Engineering, 12(6), 119-132. https://doi.org/10.6919/ICJE.202606_12(6).0011

References

  1. Yin, Y., Li, S. H., Han, J., et al. (2025). Research progress on deep eutectic solvents. Shandong Chemical Industry, 54, 95–97.
  2. Hou, Y. C., Yao, C. F., & Wu, W. Z. (2018). Deep eutectic solvents: green solvents for separation applications. Acta Physico-Chimica Sinica, 34, 873–885.
  3. Abbott, A. P., Capper, G., Davies, D. L., et al. (2002). Novel solvent properties of choline chloride/urea mixtures. Chemical Communications, 1, 70–71. https://doi.org/10.1039/b108270g
  4. Wu, C., Chen, Q. C., Ni, Q., et al. (2025). Genetic algorithm-back propagation artificial neural network model-and response surface methodology-based optimization of crude Lophatherum gracile Brongn. polysaccharides extraction and their anti-NAFLD effects via regulating liver-adipose tissue crosstalk. International Journal of Biological Macromolecules, 320, 145806. https://doi.org/10.1016/j.ijbiomac.2025.145806
  5. Wang, S., Wei, J., Ge, H., et al. (2025). Molecular simulation and machine learning assisted in exploring betaine-based deep eutectic solvent extraction of active compounds from peony petals. Separation and Purification Technology, 361, 131550. https://doi.org/10.1016/j.seppur.2025.131550
  6. Cai, J., Xue, J., Li, Y., et al. (2024). Research progress on high-value-added application of lignocellulosic biomass based on deep eutectic solvent pretreatment. Biomass Conversion and Biorefinery, 14, 30913–30928. https://doi.org/10.1007/s13399-023-01542-9
  7. Xiao, T., Hou, M., Guo, X., et al. (2024). Recent progress in deep eutectic solvent (DES) fractionation of lignocellulosic components: a review. Renewable and Sustainable Energy Reviews, 192, 114243. https://doi.org/10.1016/j.rser.2024.114243
  8. Lin, B., Liu, X. L., & Bi, C. Y. (2025). Research progress on pretreatment of lignocellulose with deep eutectic solvents. Jiangxi Chemical Industry, 41, 11–14.
  9. Yu, Q. Y., Long, Y., Liu, Y. Z., et al. (2025). Application progress of deep eutectic solvents in hydrometallurgical leaching. Green Mining and Metallurgy, 41, 23–29.
  10. Zhang, Y. (2015). Study on leaching of zinc oxide ore by deep eutectic solvent-type ionic liquids [Master’s thesis]. Kunming University of Science and Technology.
  11. Rodriguez Rodriguez, N., Machiels, L., & Binnemans, K. (2019). p-Toluenesulfonic acid-based deep-eutectic solvents for solubilizing metal oxides. ACS Sustainable Chemistry & Engineering, 7, 3940–3948. https://doi.org/10.1021/acssuschemeng.8b06146
  12. Zhou, K., Dai, X., Li, P., et al. (2024). Recent advances in deep eutectic solvents for next-generation lithium batteries: safer and greener. Progress in Materials Science, 146, 101338. https://doi.org/10.1016/j.pmatsci.2024.101338
  13. Wang, S. S., Li, W. S., Guo, B., et al. (2026). Efficient catalytic synthesis of ethylene glycol monoacetate with deep eutectic solvents under mild conditions. Acta Petrolei Sinica (Petroleum Processing Section), 1–15.
  14. Chen, S. M., Liu, J. C., Zhong, Z. X., et al. (2025). Development and application of deep eutectic solvents in carbon dioxide capture. Chemical Industry and Engineering Progress, 44, 5377–5390.
  15. Liu, J. X., & Hua, E. (2025). Analysis of CO2 absorption by glycerol-alkylethylenediamine deep eutectic solvents based on DFT theory and MD simulation. Low-Carbon Chemistry and Chemical Engineering, 50, 121–132.
  16. Sun, J., Sato, Y., Sakai, Y., et al. (2023). A review of ionic liquids and deep eutectic solvents design for CO2 capture with machine learning. Journal of Cleaner Production, 414, 137695. https://doi.org/10.1016/j.jclepro.2023.137695
  17. Tian, Y., Zhang, H., Qiao, Y., et al. (2025). Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning. Chinese Journal of Chemical Engineering.
  18. Uzochukwu, M. I., Oyegoke, T., Momoh, R. O., et al. (2023). Computational insights into deep eutectic solvent design: modeling interactions and thermodynamic feasibility using choline chloride & glycerol. Chemical Engineering Journal Advances, 16, 100564. https://doi.org/10.1016/j.cejadv.2023.100564
  19. Abdollahzadeh, M., Khosravi, M., Hajipour Khire Masjidi, B., et al. (2022). Estimating the density of deep eutectic solvents applying supervised machine learning techniques. Scientific Reports, 12, 4954. https://doi.org/10.1038/s41598-022-08946-7
  20. Yang, F., Zheng, Q., Tan, H., et al. (2024). Insight into the role of hydrogen bond donor in deep eutectic solvents. Journal of Molecular Liquids, 399, 124332. https://doi.org/10.1016/j.molliq.2024.124332
  21. Wang, Y., Liu, H., Ji, X., et al. (2023). Production of nanocellulose using acidic deep eutectic solvents based on choline chloride and carboxylic acids: a review. International Journal of Biological Macromolecules, 245, 125227. https://doi.org/10.1016/j.ijbiomac.2023.125227
  22. Lee, K. M., Yoo, J., Kim, S. W., et al. (2019). Autonomic machine learning platform. International Journal of Information Management, 49, 491–501. https://doi.org/10.1016/j.ijinfomgt.2019.07.011
  23. Choi, H. J., Naznin, M., Alam, M. B., et al. (2022). Optimization of the extraction conditions of Nypa fruticans Wurmb. using response surface methodology and artificial neural network. Food Chemistry, 381, 132086. https://doi.org/10.1016/j.foodchem.2022.132086
  24. Wan, H. Y., Zhang, Y. Y., Yu, L., et al. (2020). Optimization of ultrasonic extraction process of two active components in safflower based on random forest model. Journal of Chinese Medicinal Materials, 43, 673–677.
  25. (2025). Application of machine learning in deep eutectic solvents: advances in property prediction and molecular design. Journal of Molecular Liquids, 437, 128317. https://doi.org/10.1016/j.molliq.2025.128317
  26. Abbas, U. L., Zhang, Y., Tapia, J., et al. (2024). Machine learning-assisted design of deep eutectic solvents based on unravelled hydrogen bonding patterns. Engineering, 39, 74–83. https://doi.org/10.1016/j.eng.2023.12.008
  27. Abbott, A. P., Boothby, D., Capper, G., et al. (2004). Deep eutectic solvents formed between choline chloride and carboxylic acids: versatile alternatives to ionic liquids. Journal of the American Chemical Society, 126, 9142–9147. https://doi.org/10.1021/ja0482667
  28. Liu, Y., et al. (2025). Screening deep eutectic solvent systems with UNIFAC: application to aromatics extraction from pyrolysis gasoline. Chemical Engineering Science, 123130. https://doi.org/10.1016/j.ces.2025.123130
  29. Wojciechowski, J. P., et al. (2021). Using COSMO-RS to predict solvatochromic parameters for deep eutectic solvents. ACS Sustainable Chemistry & Engineering, 9, 12113–12127. https://doi.org/10.1021/acssuschemeng.1c03252
  30. Le, T., Winter, R., Noé, F., et al. (2020). Neuraldecipher - reverse-engineering ECFP fingerprints to their molecular structures. ChemRxiv. https://doi.org/10.26434/chemrxiv.12965555.v1
  31. Klamt, A., et al. (1975). UNIFAC group contribution method for activity coefficients. AIChE Journal, 21, 108–115. https://doi.org/10.1002/aic.690210115
  32. Roosta, A., Haghbakhsh, R., Duarte, A. R. C., et al. (2023). Machine learning coupled with group contribution for predicting the density of deep eutectic solvents. Fluid Phase Equilibria, 565, 113672. https://doi.org/10.1016/j.fluid.2023.113672
  33. Li, Y., Wang, X., Zhou, L., et al. (2024). Interpretable artificial intelligence model for estimating heat capacity of deep eutectic solvents. Chemical Engineering Transactions, 96, 71–78.
  34. Zhang, H., Liu, J., Chen, W., et al. (2024). Machine learning approach for mapping heat capacity of deep eutectic solvents for sustainable energy applications. Journal of Molecular Liquids, 399, 126736. https://doi.org/10.1016/j.molliq.2024.126736
  35. Wang, J., Li, M., Zhang, Y., et al. (2024). Learning to listen: predicting speed of sound in deep eutectic solvents through molecular features. AIChE Journal, 70, e18013. https://doi.org/10.1002/aic.18013
  36. Luan, V. T. A. (2024). Integrating computational tools to address the thermophysical behavior of deep eutectic solvents in gas separation applications [Joint master’s thesis]. Universitat Rovira i Virgili & Universidade Federal do Rio de Janeiro.
  37. Halder, A. K., Haghbakhsh, R., Ferreira, E. S. C., et al. (2025). Machine learning-driven prediction of deep eutectic solvents heat capacity for sustainable process design. Journal of Chemical Theory and Computation, 21, 1359–1369. https://doi.org/10.1021/acs.jctc.5c00098
  38. Wu, T., & Lin, X. Q. (2025). Accurate viscosity prediction of deep eutectic solvents achieved by multiscale feature mining. AIChE Journal, 71, e18007. https://doi.org/10.1002/aic.18007
  39. Mood, M., et al. (2024). Accurate machine learning for the prediction of the viscosities of deep eutectic solvents. Journal of Chemical Theory and Computation, 20, 5344–5357. https://doi.org/10.1021/acs.jctc.4c00528
  40. Zhang, Y., et al. (2022). Machine learning coupled with group contribution for predicting the density of deep eutectic solvents. ChemistryOpen, 11, e202200097. https://doi.org/10.1002/open.202200097
  41. Cysewski, P., Jeliński, T., Przybyłek, M., et al. (2025). Navigating the deep eutectic solvent landscape: experimental and machine learning solubility explorations of syringic, p-coumaric, and caffeic acids. International Journal of Molecular Sciences, 26, 10099. https://doi.org/10.3390/ijms262010099
  42. (2025). Data-driven classification of solubility space in deep eutectic solvents: deciphering driving forces using PCA and k-means clustering. Journal of Molecular Liquids, 437, 128317. https://doi.org/10.1016/j.molliq.2025.128317
  43. (2024). Predicting the solubility of carbon dioxide in water and brine using advanced machine learning models. International Journal of Greenhouse Gas Control, 138, 104726. https://doi.org/10.1016/j.ijggc.2024.104726
  44. (2024). Predicting laccase activity in deep eutectic solvents by combining COSMO-RS and machine learning techniques. Journal of Chemical Technology & Biotechnology, 99, 4235–4245. https://doi.org/10.1002/jctb.7521
  45. (2025). Machine learning for deep eutectic solvents: advances in property prediction and molecular design. Journal of Molecular Liquids, 437, 128317. https://doi.org/10.1016/j.molliq.2025.128317
  46. (2024). Comparison of machine learning models and performance. Chemical Engineering Journal, 475, 144939. https://doi.org/10.1016/j.cej.2024.144939
  47. Chen, T., & Guestrin, C. (2016, August 13–17). XGBoost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). https://doi.org/10.1145/2939672.2939785
  48. Microsoft. (2024). Comparison of LightGBM and XGBoost [Technical documentation]. LightGBM Technical Documentation.
  49. Abbas, U. L., Zhang, Y., Tapia, J., et al. (2024). Machine-learning-assisted design of deep eutectic solvents based on uncovered hydrogen bond patterns. Engineering. https://doi.org/10.1016/j.eng.2023.12.008
  50. Sun, J., Sato, Y., & Kansha, S. Y. (2023). A review of ionic liquids and deep eutectic solvents design for CO2 capture with machine learning. Journal of Cleaner Production, 414, 137695. https://doi.org/10.1016/j.jclepro.2023.137695
  51. Tian, Y., Zhang, H., Qiao, Y., et al. (2025). Intelligent prediction of ionic liquids and deep eutectic solvents by machine learning. Chinese Journal of Chemical Engineering.
  52. Wang, S., Wei, J., Ge, H., et al. (2025). Molecular simulation and machine learning assisted in exploring betaine-based deep eutectic solvent extraction of active compounds from peony petals. Separation and Purification Technology, 361, 131550. https://doi.org/10.1016/j.seppur.2025.131550
  53. Zhang, W., Cao, Z., Chen, Q., et al. (2025). Machine learning-assisted separation of lignin from hydrothermal treatment of biomass by deep eutectic solvents. Bioresource Technology, 133537. https://doi.org/10.1016/j.biortech.2025.133537
  54. Liu, C., Lei, J., Liu, X., et al. (2025). Novel ternary deep eutectic solvent coupled with in-situ-ultrasound synergistic extraction of flavonoids from Epimedium wushanense: machine learning, mechanistic investigation, and antioxidant activity. Ultrasonics Sonochemistry, 121, 107547. https://doi.org/10.1016/j.ultsonch.2025.107547
© 2026 eLibrary · Stand on the shoulders of giants