Advanced Global Wildfire Activity Modeling with Hierarchical Graph ODE

TL;DR

This paper introduces HiGO, a hierarchical graph neural ODE framework that models multi-scale, continuous-time wildfire dynamics, significantly improving long-range wildfire forecasting accuracy and consistency over existing methods.

Contribution

The paper presents a novel hierarchical graph ODE model for multi-scale wildfire prediction, integrating adaptive message passing and continuous-time dynamics learning.

Findings

HiGO outperforms state-of-the-art baselines on long-range wildfire forecasting.

The model demonstrates strong observational consistency in predictions.

Extensive experiments validate the effectiveness of the hierarchical graph ODE approach.

Abstract

Wildfires, as an integral component of the Earth system, are governed by a complex interplay of atmospheric, oceanic, and terrestrial processes spanning a vast range of spatiotemporal scales. Modeling their global activity on large timescales is therefore a critical yet challenging task. While deep learning has recently achieved significant breakthroughs in global weather forecasting, its potential for global wildfire behavior prediction remains underexplored. In this work, we reframe this problem and introduce the Hierarchical Graph ODE (HiGO), a novel framework designed to learn the multi-scale, continuous-time dynamics of wildfires. Specifically, we represent the Earth system as a multi-level graph hierarchy and propose an adaptive filtering message passing mechanism for both intra- and inter-level information flow, enabling more effective feature extraction and fusion. Furthermore, we incorporate GNN-parameterized Neural ODE modules at multiple levels to explicitly learn the continuous dynamics inherent to each scale. Through extensive experiments on the SeasFire Cube dataset, we demonstrate that HiGO significantly outperforms state-of-the-art baselines on long-range wildfire forecasting. Moreover, its continuous-time predictions exhibit strong observational consistency, highlighting its potential for real-world applications.