A Graph Neural Network for Global Daily Fire Radiative Power Prediction at Medium-Range Lead Times

2026-10-07

AI Summary

This study addresses the limitations of satellite fire observation latency and the assumption of constant fire activity in forecasting by proposing a global Fire Radiative Power (FRP) prediction model based on Spatio-Temporal Graph Neural Networks (ST-GNN). By integrating reanalysis meteorological, land cover, vegetation, and GBBEPx satellite data, the method transcends traditional fixed-input constraints to construct a dynamic evolution model capable of high-resolution 1- to 7-day forecasts. Experimental results demonstrate that the model preserves seasonal periodicity while significantly outperforming persistence baselines, reducing mean squared error at 0.1° resolution by 32% and 43% for 1-day and 7-day forecasts, respectively. Furthermore, it reliably detects large fires, providing critical support for air quality and aerosol forecasting.

Abstract

Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction. Two operational constraints motivate this work. First, the GBBEPx satellite fire radiative power (FRP) product used to initialize NOAA's GEFS-Aerosols is available with about a 1.5-day latency, so each forecast cycle relies on the most recently available, but already outdated, fire observations. Second, these fire inputs are then held fixed throughout the subsequent 5-day operational forecast, or 7 days in the GSL experimental system, effectively assuming no evolution in fire activity. We develop a data-driven model that predicts global FRP one to seven days ahead from the most recent available observations. The model adapts a spatiotemporal graph neural network using reanalysis meteorology, land-cover and vegetation information, recent fire history, and GBBEPx FRP as the training target. It is trained on 2020-2022 data and evaluated for 2023-2024. The model reproduces the global seasonal cycle and substantially outperforms persistence. At 0.1$^\circ$ resolution, mean squared error is reduced by 32% at one-day lead and 43% at seven days in 2023, and by 24% and 40% in 2024. At 1$^\circ$ resolution, the critical success index ranges from 0.32 to 0.60. Detection skill declines only modestly with lead time, whereas intensity skill degrades more rapidly. Large fires are detected reliably, but their radiative power is systematically underestimated. These results demonstrate useful predictability of fire activity several days ahead and identify intensity calibration and small-fire placement as the main remaining challenges before predicted FRP can support operational aerosol forecasts.

Problem

• Fire Radiative Power
• Medium-Range Prediction
• Biomass Burning
• Air Quality Forecasting
• Data Latency

Innovation

• Graph Neural Network
• Fire Radiative Power
• Spatiotemporal Prediction
• Medium-Range Forecasting
• Data-driven Model