Louise Schmidt's Thesis Presentation

Title: Recurrent Neural Networks and Explainability Techniques to Identify Extreme Wildfire Events

Abstract: The aim of this research was to obtain wildfire spreads simulations through a Recurrent Neural Network model that uses historical wildfire simulations and their associated topographic characteristics as input. To achieve this, 9,700 fire spread simulations were generated using the Cell2Fire simulator for the Catalonia region in Spain. The model outputs visualizations of wildfire events. To enhance interpretability, explainability techniques were incorporated to highlight differences in fire behavior. As an hypothesis, it was proposed that considering the sequential order of fire expansion within a specific time frame helps to generate accurate predictions of Extreme Wildfire Events and to obtain explanations of the landscape conditions that favor them. A deep learning model that employs RNN’s offers various benefits. One advantage is that RNNs preserve the sequential nature of the input, highlighting the importance of temporal dependencies when analyzing the spread of a wildfire. Also, the amount of data required to utilize such models is relatively low, as is the computer’s processing capacity.

Details

• Room: Grace Hopper, West Building
• Date: Monday the 30th at 04:00 PM