# Spatio-Temporal Wildfire Prediction using Multi-Modal Data

arXiv: https://arxiv.org/abs/2207.13250 · HTML: https://mlsanity.com/paper/2207.13250/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2022.

## Built on by (most cited first, 6 of 6)

- [Conformal prediction for multi-dimensional time series by ellipsoidal sets](https://mlsanity.com/paper/2403.03850/) (2024)
- [Calibrated Physics-Informed Uncertainty Quantification](https://mlsanity.com/paper/2502.04406/) (2025)
- [Neural Spatiotemporal Point Processes: Trends and Challenges](https://mlsanity.com/paper/2502.09341/) (2025)
- [Valid Error Bars for Neural Weather Models using Conformal Prediction](https://mlsanity.com/paper/2406.14483/) (2024)
- [Score-Based Change-Point Detection and Region Localization for Spatio-Temporal Point Processes](https://mlsanity.com/paper/2602.04798/) (2026)
- [Machine Learning Guided Optimal Transmission Switching to Mitigate Wildfire Ignition Risk](https://mlsanity.com/paper/2510.25147/) (2025)

## Abstract (arXiv)

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.