Wildfire risk forecast: An optimizable fire danger index

TL;DR

This paper introduces a differentiable fire risk index model that can be optimized regionally using observed fire data, enhancing prediction accuracy while maintaining interpretability.

Contribution

It presents a novel, gradient-based optimization method for fire risk indices, enabling regional parameter tuning with real fire data using machine learning frameworks.

Findings

Optimized fire risk index parameters improve prediction accuracy.

Model maintains interpretability for fire specialists.

Effective in diverse regions like the USA and Europe.

Abstract

Wildfire events have caused severe losses in many places around the world and are expected to increase with climate change. Throughout the years many technologies have been developed to identify fire events early on and to simulate fire behavior once they have started. Another particularly helpful technology is fire risk indices, which use weather forcing to make advanced predictions of the risk of fire. Predictions of fire risk indices can be used, for instance, to allocate resources in places with high risk. These indices have been developed over the years as empirical models with parameters that were estimated in lab experiments and field tests. These parameters, however, may not fit well all places where these models are used. In this paper we propose a novel implementation of one index (NFDRS IC) as a differentiable function in which one can optimize its internal parameters via gradient descent. We leverage existing machine learning frameworks (PyTorch) to construct our model. This approach has two benefits: (1) the NFDRS IC parameters can be improved for each region using actual observed fire events, and (2) the internal variables remain intact for interpretations by specialists instead of meaningless hidden layers as in traditional neural networks. In this paper we evaluate our strategy with actual fire events for locations in the USA and Europe.