Machine learning detects weather fronts from satellite images over Europe
SATFRONT: Detecting Atmospheric Fronts with Satellite Data using Machine Learning
Machine Learning
Summary
Weather fronts are boundaries between air masses that often cause big weather changes, but spotting and labeling them usually needs experts and takes time. The authors created a machine learning tool called SATFRONT that can recognize cold, warm, and occluded fronts using just satellite pictures, or with some extra weather data for better accuracy. They tested SATFRONT against expert analyses and found it works about as well as different experts do and better than older satellite-based methods. This means weather services could get quick, automatic updates about important weather fronts without waiting for manual work.
What this means in practice
- •For meteorological services: Provide frequent, automatic identification of weather fronts using satellite images to support faster weather warnings.
- •For emergency management teams: Gain timely updates on evolving weather fronts for better preparation and response during severe weather events.
Authors
Ioannis Dravilas, Miruna Stoicescu, Roope Tervo, Carlos Horn, Oriol Hinojo Comellas, Sina Montazeri, Andrea Meraner, Ana Lucic
Abstract
Atmospheric fronts are associated with much of the high-impact weather in the mid-latitudes, yet their identification and classification remain largely manual and subjective. Existing deep learning approaches rely primarily on gridded reanalysis or forecast data, limiting their applicability to satellite observations available for time-critical applications. We introduce SATFRONT, a machine learning framework for detecting cold, warm, and occluded fronts over Europe from geostationary satellite observations, with reanalysis data as an optional additional input. The model is trained on frontal analyses from five European national meteorological services and evaluated against UK Met Office analyses for 2024. Using satellite observations alone, SATFRONT achieves a Critical Success Index (CSI) of 0.428 at a 150 km tolerance, within the range of agreement between analyses from different meteorological services (0.277-0.501) and higher than that of an operational rule-based front detector that uses satellite data (0.133). Adding ERA5 reanalysis increases the CSI to 0.591. ERA5 substantially improves the placement of individual fronts, although its effect on their annual spatial distribution varies by front type. These results demonstrate that cold, warm, and occluded fronts can be detected directly from geostationary satellite observations, providing a basis for automated frontal analyses at the high temporal frequency required for time-critical applications.