Deep Learning Models for Predicting Wildfires from Historical Remote-Sensing Data

Abstract

Identifying regions that have high likelihood for wildfires is a key component of land and forestry management and disaster preparedness. We create a data set by aggregating nearly a decade of remote-sensing data and historical fire records to predict wildfires. This prediction problem is framed as three machine learning tasks. Results are compared and analyzed for four different deep learning models to estimate wildfire likelihood. The results demonstrate that deep learning models can successfully identify areas of high fire likelihood using aggregated data about vegetation, weather, and topography with an AUC of 83%.

arXiv commentPresented at 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Artificial Intelligence for Humani- tarian Assistance and Disaster Response Workshop, Vancouver, Canada

References in corpus (4)

• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Machine Learning for Precipitation Nowcasting from Radar Images
• FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
• Machine Learning for Generalizable Prediction of Flood Susceptibility

Cited by in corpus (4)

• Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data
• SegNet: A Segmented Deep Learning based Convolutional Neural Network Approach for Drones Wildfire Detection
• Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale
• Deep Learning Methods for Daily Wildfire Danger Forecasting