Experimental Measurements, Molecular Dynamics Simulations, and Machine Learning Predictions for the γ‐Butyrolactone–N,N‐Dimethylacetamide Binary System

Abstract

Binary solvent mixtures are widely used in chemical processes for their adjustable physicochemical properties and potential in sustainable chemistry. In this study, the γ‐butyrolactone (GBL) and N,N‐dimethylacetamide (DMA) binary system is examined through a combination of experimental measurements, molecular dynamics (MD) simulations, and machine learning (ML) techniques. Key thermophysical properties such as density, speed of sound, and refractive index were measured across a range of compositions and temperatures (298.15–318.15 K). These experimental observations were used to derive important thermodynamic parameters and assess deviations from ideal mixing behavior. MD simulations were employed to explore molecular‐level interactions, while ML models were developed to predict mixture densities. This multidisciplinary approach aims to deepen the understanding of complex solvent systems and demonstrate a framework that bridges experimental insight, computational modeling, and data‐driven prediction relevant for both academic research and industrial applications.