Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation
Tropical cyclone (TC) is a highly catastrophic weather event, and accurate estimation of intensity is of great significance. The current proposed TC intensity estimation model focuses on training using satellite images from single or two channels, and the model cannot fully capture features related...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845190/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207054394982400 |
|---|---|
| author | Chang-Jiang Zhang Mei-Shu Chen Lei-Ming Ma Xiao-Qin Lu |
| author_facet | Chang-Jiang Zhang Mei-Shu Chen Lei-Ming Ma Xiao-Qin Lu |
| author_sort | Chang-Jiang Zhang |
| collection | DOAJ |
| description | Tropical cyclone (TC) is a highly catastrophic weather event, and accurate estimation of intensity is of great significance. The current proposed TC intensity estimation model focuses on training using satellite images from single or two channels, and the model cannot fully capture features related to TC intensity, resulting in low accuracy. To this end, we propose a double-layer encoder–decoder model for estimating the intensity of TC, which is trained using images from three channels: infrared, water vapor, and passive microwave. The model mainly consists of three modules: wavelet transform enhancement module, multichannel satellite image fusion module, and TC intensity estimation module, which are used to extract high-frequency information from the source image, generate a three-channel fused image, and perform TC intensity estimation. To validate the performance of our model, we conducted extensive experiments on the TCIR dataset. The experimental results show that the proposed model has MAE and RMSE of 3.76 m/s and 4.62 m/s for TC intensity estimation, which are 15.70% and 20.07% lower than advanced Dvorak technology, respectively. Therefore, the model proposed in this article has great potential in accurately estimating TC intensity. |
| format | Article |
| id | doaj-art-d128a8ad060d4a6eae0945c31a2f4619 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-d128a8ad060d4a6eae0945c31a2f46192025-02-07T00:00:16ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184711473510.1109/JSTARS.2025.353144810845190Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity EstimationChang-Jiang Zhang0https://orcid.org/0000-0002-2170-3878Mei-Shu Chen1Lei-Ming Ma2https://orcid.org/0000-0003-0103-5830Xiao-Qin Lu3https://orcid.org/0000-0003-4374-8927School of Electronic and Information Engineering (School of Big Data Science), Taizhou University, Taizhou, ChinaCollege of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua, ChinaShanghai Typhoon Institute of the China Meteorological Administration, Shanghai, ChinaShanghai Typhoon Institute of the China Meteorological Administration, Shanghai, ChinaTropical cyclone (TC) is a highly catastrophic weather event, and accurate estimation of intensity is of great significance. The current proposed TC intensity estimation model focuses on training using satellite images from single or two channels, and the model cannot fully capture features related to TC intensity, resulting in low accuracy. To this end, we propose a double-layer encoder–decoder model for estimating the intensity of TC, which is trained using images from three channels: infrared, water vapor, and passive microwave. The model mainly consists of three modules: wavelet transform enhancement module, multichannel satellite image fusion module, and TC intensity estimation module, which are used to extract high-frequency information from the source image, generate a three-channel fused image, and perform TC intensity estimation. To validate the performance of our model, we conducted extensive experiments on the TCIR dataset. The experimental results show that the proposed model has MAE and RMSE of 3.76 m/s and 4.62 m/s for TC intensity estimation, which are 15.70% and 20.07% lower than advanced Dvorak technology, respectively. Therefore, the model proposed in this article has great potential in accurately estimating TC intensity.https://ieeexplore.ieee.org/document/10845190/Deep learningimage fusionintensity estimationtropical cyclones (TC)wavelet transform |
| spellingShingle | Chang-Jiang Zhang Mei-Shu Chen Lei-Ming Ma Xiao-Qin Lu Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep learning image fusion intensity estimation tropical cyclones (TC) wavelet transform |
| title | Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation |
| title_full | Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation |
| title_fullStr | Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation |
| title_full_unstemmed | Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation |
| title_short | Deep Learning and Wavelet Transform Combined With Multichannel Satellite Images for Tropical Cyclone Intensity Estimation |
| title_sort | deep learning and wavelet transform combined with multichannel satellite images for tropical cyclone intensity estimation |
| topic | Deep learning image fusion intensity estimation tropical cyclones (TC) wavelet transform |
| url | https://ieeexplore.ieee.org/document/10845190/ |
| work_keys_str_mv | AT changjiangzhang deeplearningandwavelettransformcombinedwithmultichannelsatelliteimagesfortropicalcycloneintensityestimation AT meishuchen deeplearningandwavelettransformcombinedwithmultichannelsatelliteimagesfortropicalcycloneintensityestimation AT leimingma deeplearningandwavelettransformcombinedwithmultichannelsatelliteimagesfortropicalcycloneintensityestimation AT xiaoqinlu deeplearningandwavelettransformcombinedwithmultichannelsatelliteimagesfortropicalcycloneintensityestimation |