ERI: integrated molecular simulation and artificial intelligence framework for the design of task-specific ionic liquids

The National Science Foundation Division of Chemical, Bioengineering, Environmental, and Transport Systems awarded The University of Texas at Tyler $199,995 on July 1, 2026, under the Engineering program (CFDA 47.041) to develop an integrated molecular simulation and artificial intelligence framework for the design of task-specific ionic liquids.

The award funds research combining molecular simulations, machine learning, and generative artificial intelligence to accelerate discovery and design of ionic liquids—tunable salts with applications in energy storage, carbon capture, water treatment, chemical separations, and advanced manufacturing. Deliverables include accurate force fields, an ionic-liquid-specific molecular transformer for property prediction, a generative AI framework to expand the chemical space of ionic liquids, a comprehensive ionic liquid database, and design tools for task-specific applications such as refrigerant separation and critical material recovery. The research supports sustainable chemical processes, pollution reduction, environmentally friendly technologies, and student educational opportunities.

Performance runs from July 1, 2026, through June 30, 2028, with work performed in Tyler, Texas. No sub-awards are planned for this award.

Abstract

This project focuses on designing ionic liquids (ILS), which are chemical compounds with customizable properties. They can be used in a variety of applications including energy storage, carbon capture, water treatment, and advanced manufacturing. Designing new ILS is challenging because there are many possible compositions. This project uses advanced computer simulations, machine learning, and artificial intelligence to predict IL properties and design new ones efficiently. IT creates a comprehensive IL database and tools for designing task-specific ILS, such as those for refrigerant separation and resource recovery. The research outcomes support sustainable chemical processes, reduce pollution, advance environmentally friendly technologies, and foster educational opportunities for students. This project leverages molecular simulations, machine learning (ML), and generative artificial intelligence (AI) to accelerate the design and discovery of ionic liquids - versatile, tunable salts with applications in energy storage, carbon capture, water treatment, and chemical separations. By developing accurate force fields, an IL-specific molecular transformer for property prediction, and a generative AI framework to expand the IL chemical space, the research enables scalable IL discovery and task-specific design for applications like refrigerant separation and critical material recovery. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are not planned for this award.