Neural Networks for Models of Forward and Inverse Problems in Fire Spread

This dataset contains fire spread simulations generated with a physics-driven and data-driven model. The data-driven model is trained with a TensorFlow applied to data generated with the physics-driven model described in the paper titled "A simple model for wildland fire vortex–sink interactions". The data are separated into

Data and Resources

CHANGES.md
Explore
- More information
- Go to resource

Additional Info

Field	Value
Last Updated	July 2, 2025, 21:57 (UTC)
Created	July 2, 2025, 21:57 (UTC)
Source	https://wfsi-data.org/view/doi%3A10.60594/W4B88N
award	The Role of Vorticity and Fuel Moisture on the Near-Field Plume Structure and Ember Dynamics
creators	Bryan Quaife, bquaife@fsu.edu, Florida State University, Department of Scientific Computing, https://orcid.org/0000-0002-9186-8926 \| Xin Tong, Florida State University
doi	doi:10.60594/W4B88N
funder	U. S. Department of Defense (DoD), Strategic Environmental Research and Development Program (SERDP), http://dx.doi.org/10.13039/100013316
maintainor	Bryan Quaife, bquaife@fsu.edu
method	Generate training and testing data for the first arrival time. In this dataset, we used the method described in: Quaife, B., & Speer, K. (2021). A simple model for wildland fire vortex–sink interactions. Atmosphere, 12(8), 1014, https://www.mdpi.com/2073-4433/12/8/1014.
project	Funding Award RC20-1298: The Role of Vorticity and Fuel Moisture on the Near-Field Plume Structure and Ember Dynamics
spatial	{"type": "Polygon", "coordinates": [[[-81.771737, 31.978517], [-81.848333, 31.978517], [-81.848333, 32.004167], [-81.771737, 32.004167], [-81.771737, 31.978517]]]}
temporal	{"endTime": "2024-08-31", "startTime": "2023-01-01"}