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...

Full description

Saved in:
Bibliographic Details
Main Authors: Qiaoyan Wu, Tong Luo, Jiacheng Hong
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