Chemicals that are free of impurities are critical to everyday products such as electronics, medicine, and food. However, separating a chemical mixture into its pure constituents is energy intensive and expensive. This project will develop new membrane materials that can separate chemical mixtures at lower cost and use less energy. The research team will combine advanced data science with lab experiments to speed up materials discovery. The project will focus on separating a liquid mixture of small molecules called paraffins and olefins. This specific separation is especially important to the chemical industry because these molecules are used to make fuels and plastics. The results of this project will be new membrane materials, and better computer programs for finding these materials. Additional benefits to society will come from training science and engineering students in data science, undergraduate research and training, and public outreach at science festivals. This project combines researchers with expertise in polymer synthesis, materials science, chemical engineering, and data science. The goal is to discover new organic-inorganic (hybrid) membrane materials that can separate organic liquid mixtures. The research team will combine high-throughput physical experimentation with machine learning (ML) models to create new data-driven frameworks for membrane material discovery and optimization. This project will focus on using combinatorial chemistry to create structura