Computationally complemented insights into new generation solvents for radiation-induced graft polymerization

The adoption of next-generation solvents has lagged behind that of conventional solvents, primarily due to the operational and economic advantages associated with the latter. These advantages stem from the well-established body of knowledge regarding their chemical applications. This disparity creates a reinforcing cycle, where the widespread use of conventional solvents limits the integration of next-generation alternatives. To address this issue, this study focuses on optimizing solvents in radiation-induced graft polymerization (RIGP) processes to advance sustainable materials chemistry. By leveraging machine learning approaches, the study provides practical guidelines for facilitating the transition from conventional to next-generation solvents, effectively transferring chemical insights from established systems to emerging alternatives. • Machine learning optimizes solvents in radiation-induced graft polymerization. • Practical guidelines enable a shift from conventional to next-generation solvents. • Sustainable chemistry is feasible through transferable chemical insights.