Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning
Forecasting rapid intensification (RI) of tropical cyclones (TC) is a mission known for large errors. One under-researched factor that affects TC intensification is salinity, which is important for density stratification in certain ocean regions and can affect the surface enthalpy flux under a stren...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Environmental Research Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/1748-9326/adac7f |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859092689518592 |
|---|---|
| author | Ryan Eusebi Hui Su Longtao Wu Pingping Rong Karthik Balaguru Ruby Leung Yong-Sang Choi Pak Wai Chan Jianping Gan Mark DeMaria Galina Chirokova |
| author_facet | Ryan Eusebi Hui Su Longtao Wu Pingping Rong Karthik Balaguru Ruby Leung Yong-Sang Choi Pak Wai Chan Jianping Gan Mark DeMaria Galina Chirokova |
| author_sort | Ryan Eusebi |
| collection | DOAJ |
| description | Forecasting rapid intensification (RI) of tropical cyclones (TC) is a mission known for large errors. One under-researched factor that affects TC intensification is salinity, which is important for density stratification in certain ocean regions and can affect the surface enthalpy flux under a strengthening hurricane. To investigate the impact and efficacy of using salinity information in state-of-the-art forecasting, we use a statistical model consisting of a variety of machine learning (ML) methods. For salinity data, we use satellite measurements of pre-storm sea surface salinity (SSS) as a proxy for the salinity stratification. We train and test the model on various ocean basins, including the Atlantic, eastern North Pacific and western North Pacific. A calibrator is trained on top of the ML models to correct and enhance probability forecasts. The calibrator significantly improves probability forecasts relative to recent works. The ML model performance is improved with the addition of SSS in the Eastern North Pacific, western North Pacific, and the Caribbean subregion of the North Atlantic, and the overall model performance is better than previous studies. SSS decreases model skill for a model trained on the full Atlantic basin. In the Indian Ocean, SSS is also notably correlated with RI occurrence, but the TC samples are not sufficient to train ML models. |
| format | Article |
| id | doaj-art-36fdf0f2d417405fa99fa449e80e253c |
| institution | Kabale University |
| issn | 1748-9326 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Letters |
| spelling | doaj-art-36fdf0f2d417405fa99fa449e80e253c2025-02-11T08:27:51ZengIOP PublishingEnvironmental Research Letters1748-93262025-01-0120303401010.1088/1748-9326/adac7fImproving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learningRyan Eusebi0https://orcid.org/0009-0008-0396-7731Hui Su1Longtao Wu2Pingping Rong3https://orcid.org/0000-0002-9923-0652Karthik Balaguru4https://orcid.org/0000-0003-0181-2687Ruby Leung5https://orcid.org/0000-0002-3221-9467Yong-Sang Choi6Pak Wai Chan7Jianping Gan8Mark DeMaria9https://orcid.org/0000-0003-4746-4462Galina Chirokova10California Institute of Technology , Pasadena, CA, United States of AmericaDepartment of Civil and Environmental Engineering, The Hong Kong University of Science and Technology , Clear Water Bay, Kowloon, Hong Kong Special Administrative Region of China, People’s Republic of China; Center for Ocean Research in Hong Kong and Macau (CORE), The Hong Kong University of Science and Technology , Clear Water Bay, Kowloon, Hong Kong Special Administrative Region of China, People’s Republic of ChinaJet Propulsion Laboratory, California Institute of Technology , Pasadena, CA 91109, United States of AmericaDepartment of Civil and Environmental Engineering, The Hong Kong University of Science and Technology , Clear Water Bay, Kowloon, Hong Kong Special Administrative Region of China, People’s Republic of ChinaPacific Northwest National Laboratory , Richland, WA, United States of AmericaPacific Northwest National Laboratory , Richland, WA, United States of AmericaEwha Womans University , Seoul, Republic of KoreaHong Kong Observatory , Hong Kong Special Administrative Region of China, People’s Republic of ChinaDepartment of Civil and Environmental Engineering, The Hong Kong University of Science and Technology , Clear Water Bay, Kowloon, Hong Kong Special Administrative Region of China, People’s Republic of ChinaCooperative Institute for Research in the Atmosphere, Colorado State University , Fort Collins, CO, United States of AmericaCooperative Institute for Research in the Atmosphere, Colorado State University , Fort Collins, CO, United States of AmericaForecasting rapid intensification (RI) of tropical cyclones (TC) is a mission known for large errors. One under-researched factor that affects TC intensification is salinity, which is important for density stratification in certain ocean regions and can affect the surface enthalpy flux under a strengthening hurricane. To investigate the impact and efficacy of using salinity information in state-of-the-art forecasting, we use a statistical model consisting of a variety of machine learning (ML) methods. For salinity data, we use satellite measurements of pre-storm sea surface salinity (SSS) as a proxy for the salinity stratification. We train and test the model on various ocean basins, including the Atlantic, eastern North Pacific and western North Pacific. A calibrator is trained on top of the ML models to correct and enhance probability forecasts. The calibrator significantly improves probability forecasts relative to recent works. The ML model performance is improved with the addition of SSS in the Eastern North Pacific, western North Pacific, and the Caribbean subregion of the North Atlantic, and the overall model performance is better than previous studies. SSS decreases model skill for a model trained on the full Atlantic basin. In the Indian Ocean, SSS is also notably correlated with RI occurrence, but the TC samples are not sufficient to train ML models.https://doi.org/10.1088/1748-9326/adac7ftropical cyclonesatellitehurricanerapid intensificationsalinitymachine learning |
| spellingShingle | Ryan Eusebi Hui Su Longtao Wu Pingping Rong Karthik Balaguru Ruby Leung Yong-Sang Choi Pak Wai Chan Jianping Gan Mark DeMaria Galina Chirokova Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning Environmental Research Letters tropical cyclone satellite hurricane rapid intensification salinity machine learning |
| title | Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| title_full | Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| title_fullStr | Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| title_full_unstemmed | Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| title_short | Improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| title_sort | improving tropical cyclone rapid intensification forecasts with satellite measurements of sea surface salinity and calibrated machine learning |
| topic | tropical cyclone satellite hurricane rapid intensification salinity machine learning |
| url | https://doi.org/10.1088/1748-9326/adac7f |
| work_keys_str_mv | AT ryaneusebi improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT huisu improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT longtaowu improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT pingpingrong improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT karthikbalaguru improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT rubyleung improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT yongsangchoi improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT pakwaichan improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT jianpinggan improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT markdemaria improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning AT galinachirokova improvingtropicalcyclonerapidintensificationforecastswithsatellitemeasurementsofseasurfacesalinityandcalibratedmachinelearning |