Abstract

We model wind velocity fields for applications in wildfire modeling. We improve the accuracy of the mass-conserving WindNinja solver without compromising efficient temporal complexity. We consider two approaches: the parameterization method and the neural network method. In the parameterization method, we analyze eddies in the wake of obstacles by parameterizing cavity zones as inspired by the research by Kaplan & Dinar in 1996. Kaplan & Dinar parameterize cavity zones around rectangular buildings, and we approximate a continuous landscape with rectangular buildings in order to extend this parameterization to complex terrains. In the neural network method, we train a U-net CNN on a dataset consisting of outputs of the mass-conserving solver, outputs of the CFD solver, and elevation grids. We achieve high accuracy in approximating the output of the CFD solver with the neural network approach while retaining efficient temporal complexity.

Degree

MS

College and Department

Mathematics

Rights

https://lib.byu.edu/about/copyright/

Date Submitted

2025-04-22

Document Type

Thesis

Handle

http://hdl.lib.byu.edu/1877/etd13624

Keywords

windflow, parameterization, cavity zone, neural network, U-net, wildfire, machine learning, WindNinja

Language

english

Share

COinS