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

Key points

• 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is available with about a 1.5-day latency, so each forecast cycle relies on the most recently available, but already outdated, fire observations.1
• We develop a data-driven model that predicts global FRP one to seven days ahead from the most recent available observations.1
• 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.1
• 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.1

Sources (1)

• [1]A Graph Neural Network for Global Daily Fire Radiative Power Prediction at Medium-Range Lead Times
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 12:14 AM

  Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction.

  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is available with about a 1.5-day latency, so each forecast cycle relies on the most recently available, but already outdated, fire observations.

Extractive summary: sentences quoted from the sources.