Particle-Guided Diffusion for Gas-Phase Reaction Kinetics
🤖 AI Summary
This work addresses the limited applicability of diffusion models in gaseous reactive transport systems by proposing a physics-guided diffusion generative model. Leveraging numerical solutions of the advection–reaction–diffusion (ARD) equations as training data, the method learns the coupled dynamics of chemical kinetics and transport processes across varying parameter regimes. By incorporating particle-based guidance during sampling, the model generates concentration fields that are physically consistent. To the best of our knowledge, this is the first integration of diffusion models with physics-guided sampling for gaseous reaction systems, demonstrating accurate prediction of outlet concentrations under unseen parameter conditions and validating its efficiency and generalization capability for complex reactive transport inference.
Application Category
📝 Abstract
Physics-guided sampling with diffusion model priors has shown promise for solving partial differential equation (PDE) governed problems, but applications to chemically meaningful reaction-transport systems remain limited. We apply diffusion-based guided sampling to gas-phase chemical reactions by training on solutions of the advection-reaction-diffusion (ARD) equation across varying parameters. The method generates physically consistent concentration fields and accurately predicts outlet concentrations, including at unseen parameter values, demonstrating the potential of diffusion models for inference in reactive transport.
Problem
Research questions and friction points this paper is trying to address.
diffusion model
gas-phase reaction
reaction-transport
advection-reaction-diffusion
concentration prediction
Innovation
Methods, ideas, or system contributions that make the work stand out.
diffusion model
guided sampling
reaction-transport
advection-reaction-diffusion
physics-informed
🔎 Similar Papers
No similar papers found.
