Northern Hemisphere Midlatitude Cyclone Intensity Biases in Machine Learning Weather Prediction Models

Helen Dacre, Andrew James Charlton-Perez, Simon Driscoll, S. L. Gray, Ben J. Harvey, N. J. Harvey, Kevin I. Hodges, Kieran M R Hunt, Ambrogio Volonté

Bulletin of the American Meteorological Society · 23 December 2025 · University of Cambridge (Aardvark), University of Reading

Paper

In one sentence. Seven MLWP models match IFS midlatitude cyclone track skill to 10 days but underestimate cyclone central pressure by over 5 hPa and peak winds at all leads.

Abstract

Abstract Forecasting the location and intensity of strong winds associated with midlatitude cyclones is important as they can have significant safety, economic, and environmental impacts. In this study, we use a feature-based evaluation method to assess the performance of both numerical weather prediction and machine learning weather prediction (MLWP) models in forecasting midlatitude cyclone winds. By tracking over 1000 cyclones across the Northern Hemisphere from 1 October 2023 to 31 March 2024 in seven MLWP models, we systematically compare model performance. Our results show that MLWP models predict midlatitude cyclone tracks with accuracy comparable to the ECMWF Integrated Forecasting System (IFS) forecast out to 10 days. However, MLWP models exhibit a persistent intensity bias, underestimating cyclone minimum sea level pressure by more than 5 hPa at 10-day forecast lead times, whereas the ECMWF IFS forecast has no bias. Additionally, all MLWP models produce weaker than observed peak 10-m winds, even at short lead times. In contrast, the ECMWF IFS forecast exhibits no bias in 10-m wind speed. These differences highlight the limitations of current MLWP models in capturing important high-impact weather features like peak wind speeds. SIGNIFICANCE STATEMENT Machine learning weather prediction models predict midlatitude cyclone tracks comparably to numerical weather prediction models but underestimate cyclone intensity, particularly minimum surface pressure and peak wind speeds, highlighting areas where machine learning models need improvement.

Labels

Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.