AI-Powered Catalyst Design for Efficient Hydrogen Generation, Carbon Capture, and Energy Storage

Researchers from the University of Houston are using AI and microwave plasma to improve catalysts for renewable energy processes. They aim to accelerate catalyst discovery and enhance efficiency in areas like hydrogen generation and carbon capture.

Adopting renewable energy has become a major priority as the world confronts climate challenges and environmental degradation. However, the transition has been slowed by the unpredictability of wind, solar, and other renewable sources, which complicates maintaining a steady energy supply.

An interdisciplinary team of scientists is combining expertise in chemistry, materials science, and engineering with artificial intelligence and microwave plasma technology to address this issue. Their goal is to develop a viable solution that enhances energy efficiency and stability.

The project, funded by the National Science Foundation, uses machine learning to discover new catalysts and create characterization techniques to study chemical reactions under extreme conditions, such as plasma—one of the four states of matter, consisting of ionized particles. The aim is to improve catalyst efficiency for energy storage, carbon capture, and hydrogen production.

The University of Houston team includes Jiefu Chen, Associate Professor of Electrical and Computer Engineering; Lars Grabow, Professor of Chemical and Biomolecular Engineering; Xiaonan Shan, Associate Professor of Electrical and Computer Engineering; and Xuquing Wu, Associate Professor of Information Science Technology. They are collaborating with Su Yan, Associate Professor of Electrical Engineering and Computer Science at Howard University.

By enhancing the efficiency of catalytic reactions in key areas such as hydrogen generation, carbon capture, and energy storage, this research directly contributes to these global challenges. This interdisciplinary effort ensures comprehensive and innovative solutions to complex problems.

Jiefu Chen, Study Principal Investigator and Associate Professor, Electrical and Computer Engineering, University of Houston

Project Details

Finding materials for new catalytic processes is a labor-intensive and complex task requiring material science, robotics, artificial intelligence, synthesis, testing, and modeling expertise. To address this, the researchers are developing an AI model for unsupervised learning while assembling a robotic synthesis and testing facility.

Shan and Wu emphasize that integrating theory and experiments through advanced, unsupervised machine-learning approaches will streamline catalyst design. Automating the experimental testing and verification process with robotic equipment will significantly enhance efficiency.

The project focuses on four main research areas:

1. Machine learning-driven catalyst discovery for plasma-assisted chemical reactions: The team will use a graph neural network model trained with the Open Catalyst Project dataset to identify materials for plasma-assisted catalytic processes.
2. Multiscale and multiphysics microwave-plasma simulation: New techniques for modeling the complex interactions of electromagnetics, plasma physics, and thermodynamics will be developed to better understand microwave-plasma-assisted heating, including the study of micro-plasma heating with different catalysts.
3. Design, synthesize, and characterization of the catalyst support material and architecture: The team will collaborate to enhance methane conversion, optimize catalyst supports for microwave-assisted processes like steam reforming and pyrolysis, and improve micro-plasma efficiency. The goal is to increase energy conversion efficiency and facilitate micro-plasma creation.
4. Bench-scale demonstration of efficient reactions using the micro-plasma catalyst system: The researchers will set up a bench-scale reactor to further demonstrate the effectiveness of the refined catalyst support system.

Another essential aspect of the project is the development of a comprehensive research and education program. This program will cover advanced characterization, applied electromagnetics, computational catalysis, machine learning, and material synthesis, providing instruction and training for the next generation of STEM professionals.

This project will help create a knowledgeable and skilled workforce capable of addressing critical challenges in the clean energy transition. Moreover, this interdisciplinary project is going to be transformative in that it advances insights and knowledge that will lead to tangible economic impact in the not-too-far future.

Lars Grabow, Professor, Chemical and Biomolecular Engineering, University of Houston

He declared that the group is willing to collaborate with businesses on relevant initiatives and to continue developing both during and after the project.