I am a postdoc researcher in the mechanical engineering department at the Massachusetts Institute of Technology. I develop interpretable machine learning for modeling dynamics in thermal fluids and biomedical applications.
In this talk, I will present an open-source Julia package called Arrhenius.jl. It bridges classical physics-based combustion models with Julia's scientific machine learning ecosystems, such as DifferentialEquations.jl, ForwardDiff.jl, and Flux.jl. I will present its applications in combustion model reduction, uncertainty quantification, and chemical kinetic model discovery.