In the face of pressing environmental concerns and the urgent need to address climate challenges, the shift towards renewable energy has taken center stage. Nevertheless, the unpredictable nature of wind, solar, and other renewable sources presents a significant obstacle to maintaining a reliable energy supply, thereby impeding the transition.
A collaborative team of interdisciplinary scientists is actively working towards a viable solution by leveraging the potential of artificial intelligence and microwave plasma. Their approach integrates expertise from the fields of chemistry, materials science, and engineering, offering a promising path forward.
The project “Multidisciplinary High-Performance Computing and Artificial Intelligence Enabled Catalyst Design for Micro-Plasma Technologies in Clean Energy Transition” has been awarded a $1 million grant from the National Science Foundation. This initiative will utilize machine learning for catalyst discovery and develop advanced characterization methods for studying chemical reactions in extreme conditions such as plasma.
The primary goal is to enhance catalyst efficiency in hydrogen generation, carbon capture, and energy storage.
The University of Houston team comprises esteemed faculty members including Jiefu Chen, associate professor of electrical and computer engineering, Lars Grabow, professor of chemical and biomolecular engineering, Xiaonan Shan, associate professor of electrical and computing engineering, and Xuquing Wu, associate professor of information science technology. They are working in partnership with Su Yan, an 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,” said Jiefu Chen, the principal investigator of the project. “This interdisciplinary effort ensures comprehensive and innovative solutions to complex problems.”
Finding new materials for catalytic processes is a complex and time-consuming task that requires expertise in robotics, AI, material science, synthesis, testing, and modeling. The researchers are working on establishing a robotic synthesis and testing facility while simultaneously developing an AI model for unsupervised learning.
By automating experimental testing and verification with robotic facilities, the catalyst design process will become significantly more efficient, integrating theory and experiments through advanced, unsupervised machine learning techniques, as highlighted by Shan and Wu.
The project has four major research thrusts:
- Machine learning driven catalyst discovery for plasma assisted chemical reactions: The team will use a graph neural network model trained on the Open Catalyst Project dataset to discover promising materials for plasma-assisted catalytic reactions.
- Multiscale and multiphysics microwave-plasma simulation: New methods will be developed to model and simulate complex interactions involving electromagnetics, plasma physics, and thermodynamics at various scales, including studies of micro-plasma heating with different catalysts to better understand the microwave-plasma assisted heating phenomena.
- Design, synthesize and characterization of the catalyst support material and architecture: The researchers will optimize catalyst supports for efficient microwave-assisted reactions, such as pyrolysis and steam reforming, and to improve methane conversion by controlling micro-plasma efficiency. The goal is to facilitate micro-plasma generation and improve energy conversion efficiency.
- Bench scale demonstration of efficient reactions using the micro-plasma catalyst system: The researchers will establish a bench scale reactor to further demonstrate the efficiency of the designed and optimized catalyst support system.
Establishing a multidisciplinary research and education program encompassing machine learning, computational catalysis, applied electromagnetics, and material synthesis and advanced characterization is crucial. This program will play a pivotal role in educating and training the next generation STEM workforce.
“This project will help create a knowledgeable and skilled workforce capable of addressing critical challenges in the clean energy transition,” Grabow said. “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.”
He expressed the team’s readiness to collaborate with the industry on related projects and to pursue further development during and after the project.
