Using a Convolution Neural Network to Improve Ensemble Tropical Cyclone Track Forecasts across the Atlantic Basin
Name
wefo-WAF-D-24-0157.1.pdf
Size
13.4 MB
Format
Adobe PDF
Checksum (MD5)
a7de6a74d3683d7dbcdfb1809abc2a19
Author(s)
Agrawal, Nikita
Colle, Brian
Date Issued
September 15, 2025
Journal
Weather and Forecasting
Publisher
American Meteorological Society
Citation
Agrawal, N., and B. A. Colle, 2025: Using a Convolution Neural Network to Improve Ensemble Tropical Cyclone Track Forecasts across the Atlantic Basin. Wea. Forecasting, 40, 2137–2146.
Version
Final published version
Abstract
This study compares the 5-day tropical cyclone (TC) track forecasts from the Global Ensemble Forecast System (GEFS) with a machine learning approach applied to this ensemble. A convolutional neural network (CNN) model was developed using northern Atlantic TC training data from 2008 to 2022, while an independent set of storms was used to evaluate the CNN model. The CNN for tropical cyclone track forecasting was trained using fivefold cross validation on a shuffled dataset split into 90% training/validation and 10% evaluation. PyTorch was used to develop a CNN model with a custom loss function, and performance was assessed using the haversine function and error metrics, comparing the CNN’s TC track forecasts to GEFS mean track forecasts. The CNN has a 58%–86% better track prediction against GEFS mean for forecast hours 0–96, which decreases to 35%–53% for hours 108–120. Track differences between those cases that the CNN improved the forecast versus did not improve are also explored, which shows that most of the CNN improvement is from a decrease in the along-track error (ATE). This is consistent with past studies of this ensemble, which showed that the largest bias exists in the along-track direction.
Subjects
North Atlantic Ocean
Tropical cyclones
Neural networks
Ensembles
Numerical weather prediction/forecasting
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1175/WAF-D-24-0157.1
