Machine Learning for Predicting and Optimizing Physicochemical Properties of Deep Eutectic Solvents: Review and Perspectives
Francisco Javier López-Flores, César Ramírez‐Márquez, J. Betzabe González‐Campos, José María Ponce‐Ortega
Abstract
This review explores the application of machine learning in predicting and optimizing the key physicochemical properties of deep eutectic solvents, including CO 2 solubility, density, electrical conductivity, heat capacity, melting temperature, surface tension, and viscosity. By leveraging machine learning, researchers aim to enhance the understanding and customization of deep eutectic solvents, a critical step in expanding their use across various industrial and research domains. The integration of machine learning represents a significant advancement in tailoring deep eutectic solvents for specific applications, marking progress toward the development of greener and more efficient processes. As machine learning continues to unlock the full potential of deep eutectic solvents, it is expected to play an increasingly pivotal role in revolutionizing sustainable chemistry and driving innovations in environmental technology.