Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning
Abstract In this study, we developed a machine learning (ML) model to predict the rapid intensification (RI) of North Atlantic tropical cyclones (TCs) using 6‐hourly Statistical Hurricane Intensity Prediction Scheme (SHIPS) predictors and additional data on very deep convective clouds with an infrar...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-03-01
|
| Series: | Journal of Geophysical Research: Machine Learning and Computation |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2025JH000595 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850278221776420864 |
|---|---|
| author | Qiaoyan Wu Tong Luo Jiacheng Hong |
| author_facet | Qiaoyan Wu Tong Luo Jiacheng Hong |
| author_sort | Qiaoyan Wu |
| collection | DOAJ |
| description | Abstract In this study, we developed a machine learning (ML) model to predict the rapid intensification (RI) of North Atlantic tropical cyclones (TCs) using 6‐hourly Statistical Hurricane Intensity Prediction Scheme (SHIPS) predictors and additional data on very deep convective clouds with an infrared brightness temperature below 208 K. The presence of these clouds is considered a precursor to TC RI. The ML model, which incorporates SHIPS data with hourly cloud coverage, outperformed the ML model with 6‐hourly coverage of very deep convective clouds for TCs in the Atlantic basin from 2018 to 2023, as indicated by improvements in the Brier Skill Score by 5.9%, 9.9%, 1.0%, and 11.3%, for RI thresholds of ≥25, 30, 35, and 40 knots in 24 hr, respectively. These results highlight the potential of hourly cloud data, with pronounced diurnal variations, to enhance TC RI forecasting accuracy. |
| format | Article |
| id | doaj-art-c55dc04ffc444bf2b1403ac3c82612fa |
| institution | OA Journals |
| issn | 2993-5210 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Geophysical Research: Machine Learning and Computation |
| spelling | doaj-art-c55dc04ffc444bf2b1403ac3c82612fa2025-08-20T01:49:35ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102025-03-0121n/an/a10.1029/2025JH000595Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine LearningQiaoyan Wu0Tong Luo1Jiacheng Hong2School of Marine Sciences Nanjing University of Information Science and Technology Nanjing ChinaSchool of Oceanography Shanghai Jiao Tong University Shanghai ChinaSchool of Oceanography Shanghai Jiao Tong University Shanghai ChinaAbstract In this study, we developed a machine learning (ML) model to predict the rapid intensification (RI) of North Atlantic tropical cyclones (TCs) using 6‐hourly Statistical Hurricane Intensity Prediction Scheme (SHIPS) predictors and additional data on very deep convective clouds with an infrared brightness temperature below 208 K. The presence of these clouds is considered a precursor to TC RI. The ML model, which incorporates SHIPS data with hourly cloud coverage, outperformed the ML model with 6‐hourly coverage of very deep convective clouds for TCs in the Atlantic basin from 2018 to 2023, as indicated by improvements in the Brier Skill Score by 5.9%, 9.9%, 1.0%, and 11.3%, for RI thresholds of ≥25, 30, 35, and 40 knots in 24 hr, respectively. These results highlight the potential of hourly cloud data, with pronounced diurnal variations, to enhance TC RI forecasting accuracy.https://doi.org/10.1029/2025JH000595tropical cyclonerapid intensificationdiurnal cyclemachine learning |
| spellingShingle | Qiaoyan Wu Tong Luo Jiacheng Hong Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning Journal of Geophysical Research: Machine Learning and Computation tropical cyclone rapid intensification diurnal cycle machine learning |
| title | Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning |
| title_full | Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning |
| title_fullStr | Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning |
| title_full_unstemmed | Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning |
| title_short | Incorporating Hourly Convective Cloud Data Into Tropical Cyclone Rapid Intensification Forecasting With Machine Learning |
| title_sort | incorporating hourly convective cloud data into tropical cyclone rapid intensification forecasting with machine learning |
| topic | tropical cyclone rapid intensification diurnal cycle machine learning |
| url | https://doi.org/10.1029/2025JH000595 |
| work_keys_str_mv | AT qiaoyanwu incorporatinghourlyconvectiveclouddataintotropicalcyclonerapidintensificationforecastingwithmachinelearning AT tongluo incorporatinghourlyconvectiveclouddataintotropicalcyclonerapidintensificationforecastingwithmachinelearning AT jiachenghong incorporatinghourlyconvectiveclouddataintotropicalcyclonerapidintensificationforecastingwithmachinelearning |