(44a) Machine Learning Boosted Catalyst and Operation Design for Clean Energy

Developing advanced theory, modeling, and data science approaches for understanding field-enhanced catalysis has extensive applications in clean energy technologies, particularly for plasma catalysis, electrostatic catalysis, interfacial electrocatalysis, programmed catalysis, and fuel cells. Theoretically determining and quantifying the physics and chemical understanding of electrified interfacial structure and field-dipole interactions on controlling the activity and selectivity of chemical processes and then integrating these physics/chemical rules to establish deep collaborations between interpretable, physics-informed machine learning and electrified interfacial chemical processes is crucial for rationally designing these electrified modular systems for energy storage and sustainable chemical production.1,2 This presentation will focus on several examples, including organic-inorganic interface and its impact on electrocatalysis of carbon dioxide3, field-dipole interaction effects on sustainable ammonia synthesis,1 non-thermal plasma catalysis for ammonia decomposition and synthesis and so on.

Reference

1. M. Wan, H. Yue, J. Notarangelo, H. Liu, F. Che*, “Deep-Learning Assisted Electric Field-Accelerated Ammonia Synthesis”, JACS Au, Accepted, 2022, ACS Editor’s Choice.

2. Mou, T.; Pillai, H. S.; Wang, S.; Wan, M.; Han, X.; Schweitzer, N. M.; Che, F.; Xin, H., Bridging the complexity gap in computational heterogeneous catalysis with machine learning. Nat. Catal. 2023, 6 (2), 122-136.

3. Wan, M.; Gu, Z.; Che, F., Hybrid Organic-Inorganic Heterogeneous Interfaces for Electrocatalysis: A Theoretical Study of CO2 Reduction to C2. ChemCatChem 2021, (14), e202101224