Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
Name
wefo-WAF-D-21-0091.1.pdf
Description
Published version
Size
1.76 MB
Format
Adobe PDF
Checksum (MD5)
6f623c0a9ae49dec3fbb214aefd93bf1
Author(s)
Boussioux, Léonard
Zeng, Cynthia
Guénais, Théo
Bertsimas, Dimitris
Date Issued
June 1, 2022
Journal
Weather and Forecasting
Publisher
American Meteorological Society
Citation
Boussioux, L., C. Zeng, T. Guénais, and D. Bertsimas, 2022: Hurricane Forecasting: A Novel Multimodal Machine Learning Framework. Wea. Forecasting, 37, 817–831.
Version
Final published version
Abstract
This paper describes a novel machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple ML techniques and utilizing diverse data sources. Our multimodal framework, called Hurricast, efficiently combines spatial–temporal data with statistical data by extracting features with deep learning encoder–decoder architectures and predicting with gradient-boosted trees. We evaluate our models in the North Atlantic and eastern Pacific basins in 2016–19 for 24-h lead-time track and intensity forecasts and show they achieve comparable mean absolute error and skill to current operational forecast models while computing in seconds. Furthermore, the inclusion of Hurricast into an operational forecast consensus model could improve upon the National Hurricane Center’s official forecast, thus highlighting the complementary properties with existing approaches. In summary, our work demonstrates that utilizing machine learning techniques to combine different data sources can lead to new opportunities in tropical cyclone 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-21-0091.1
