Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data

TL;DR

This paper introduces a comprehensive, multi-variable dataset for wildfire spread prediction using remote sensing data, and demonstrates its utility with neural network models for one-day ahead wildfire propagation forecasting.

Contribution

The paper provides a large-scale, multi-variable wildfire dataset and benchmarks neural network models for predicting wildfire spread from remote sensing data.

Findings

Neural networks outperform logistic regression and random forest in wildfire prediction.

The dataset enables effective one-day ahead wildfire spread modeling.

The dataset serves as a benchmark for future wildfire propagation research.

Abstract

Predicting wildfire spread is critical for land management and disaster preparedness. To this end, we present `Next Day Wildfire Spread,' a curated, large-scale, multivariate data set of historical wildfires aggregating nearly a decade of remote-sensing data across the United States. In contrast to existing fire data sets based on Earth observation satellites, our data set combines 2D fire data with multiple explanatory variables (e.g., topography, vegetation, weather, drought index, population density) aligned over 2D regions, providing a feature-rich data set for machine learning. To demonstrate the usefulness of this data set, we implement a neural network that takes advantage of the spatial information of this data to predict wildfire spread. We compare the performance of the neural network with other machine learning models: logistic regression and random forest. This data set can be used as a benchmark for developing wildfire propagation models based on remote sensing data for a lead time of one day.