SeasFire as a Multivariate Earth System Datacube for Wildfire Dynamics

TL;DR

The paper introduces SeasFire, a comprehensive multivariate Earth system datacube designed to improve wildfire modeling and prediction by integrating climate, oceanic, vegetation, and human data over two decades.

Contribution

It presents a new, detailed spatiotemporal dataset for wildfire research, enabling advanced modeling of wildfire drivers and patterns using Earth observation data.

Findings

SeasFire covers 59 variables from 2001 to 2021 at 8-day intervals.

The dataset facilitates analysis of wildfire seasonality and variability.

Deep learning models using SeasFire can predict wildfire patterns across multiple timescales.

Abstract

The global occurrence, scale, and frequency of wildfires pose significant threats to ecosystem services and human livelihoods. To effectively quantify and attribute the antecedent conditions for wildfires, a thorough understanding of Earth system dynamics is imperative. In response, we introduce the SeasFire datacube, a meticulously curated spatiotemporal dataset tailored for global sub-seasonal to seasonal wildfire modeling via Earth observation. The SeasFire datacube comprises of 59 variables encompassing climate, vegetation, oceanic indices, and human factors, has an 8-day temporal resolution and a spatial resolution of 0.25$^{\circ}$, and spans from 2001 to 2021. We showcase the versatility of SeasFire for exploring the variability and seasonality of wildfire drivers, modeling causal links between ocean-climate teleconnections and wildfires, and predicting sub-seasonal wildfire patterns across multiple timescales with a Deep Learning model. We publicly release the SeasFire datacube and appeal to Earth system scientists and Machine Learning practitioners to use it for an improved understanding and anticipation of wildfires.