Closed-Loop, Efficient, Adaptive, and Robust AI for Agentic Chemical Manufacturing
Developing efficient chemical manufacturing processes requires identifying catalyst materials and operating conditions that deliver desired products reliably.
CLEAR-AI (Closed-Loop, Efficient, Adaptive, and Robust AI for Agentic Chemical Manufacturing), led by the University at Buffalo, will build a closed-loop agentic AI platform connecting modeling, synthesis, characterization, and performance testing for electrosynthesis of carbon-based fuels and chemicals. The project will integrate physics-based modeling, automated experimentation, advanced materials characterization, electrochemical testing, and data-driven analysis so that results continuously guide informative calculations and experiments. By coordinating computation and experiment within one adaptive workflow, CLEAR-AI will support faster, more reliable, resource-efficient decisions during catalyst design and optimization. Together, these capabilities will provide a scalable foundation for electrosynthetic applications, advancing energy-efficient production of fuels and critical chemical building blocks while strengthening U.S. leadership in AI-enabled manufacturing.
