Spatio-Temporal Wildfire Prediction using Multi-Modal Data

TL;DR

This paper presents a flexible spatio-temporal wildfire prediction framework utilizing multi-modal data, combining risk estimation with magnitude prediction, validated through extensive real-world experiments in California.

Contribution

It introduces a novel multi-modal data-driven framework for real-time wildfire risk and magnitude prediction, with theoretical guarantees and demonstrated scalability.

Findings

Effective wildfire risk prediction in real-time

Accurate wildfire magnitude estimation

Scalable and flexible to large regions

Abstract

Due to severe societal and environmental impacts, wildfire prediction using multi-modal sensing data has become a highly sought-after data-analytical tool by various stakeholders (such as state governments and power utility companies) to achieve a more informed understanding of wildfire activities and plan preventive measures. A desirable algorithm should precisely predict fire risk and magnitude for a location in real time. In this paper, we develop a flexible spatio-temporal wildfire prediction framework using multi-modal time series data. We first predict the wildfire risk (the chance of a wildfire event) in real-time, considering the historical events using discrete mutually exciting point process models. Then we further develop a wildfire magnitude prediction set method based on the flexible distribution-free time-series conformal prediction (CP) approach. Theoretically, we prove a risk model parameter recovery guarantee, as well as coverage and set size guarantees for the CP sets. Through extensive real-data experiments with wildfire data in California, we demonstrate the effectiveness of our methods, as well as their flexibility and scalability in large regions.