Machine learning for Bushfires

September 7, 2020 — January 6, 2025

dynamical systems
machine learning
neural nets
physics
sciml
SDEs
signal processing
spatial
statistics
statmech
stochastic processes
straya
time series
Figure 1

On the use of machine learning to analyse, predict, control, or detect bushfires (wildfires, if you are from the US). A practically important and theoretically-interesting problem. I am curious about whether we can solve it using spatiotemporal deep learning, even foundation models.

1 Incoming

Figure 2

2 References

Dabrowski, Pagendam, Hilton, et al. 2023. Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires.” Spatial Statistics.
Hilton, Sullivan, Swedosh, et al. 2018. Incorporating Convective Feedback in Wildfire Simulations Using Pyrogenic Potential.” Environmental Modelling & Software.
Mandel, Beezley, Coen, et al. 2009. Data Assimilation for Wildland Fires.” IEEE Control Systems Magazine.
Rochoux, Emery, Ricci, et al. 2015. Towards Predictive Data-Driven Simulations of Wildfire Spread – Part II: Ensemble Kalman Filter for the State Estimation of a Front-Tracking Simulator of Wildfire Spread.” Natural Hazards and Earth System Sciences.
Rochoux, Ricci, Lucor, et al. 2014. Towards Predictive Data-Driven Simulations of Wildfire Spread – Part I: Reduced-Cost Ensemble Kalman Filter Based on a Polynomial Chaos Surrogate Model for Parameter Estimation.” Natural Hazards and Earth System Sciences.
Rothermel. 1972. A Mathematical Model for Predicting Fire Spread in Wildland Fuels.