DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images
It is very crucial to identify the intensity of tropical cyclone (TC) accurately. In this article, a novel TC intensity estimation method is proposed to estimate the TC intensity from multispectral infrared images in the Northwest Pacific Basin. A deep multisource attention network (DMANet) is propo...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10121612/ |
| _version_ | 1797823422298849280 |
|---|---|
| author | Wenjun Jiang Gang Hu Tiantian Wu Lingbo Liu Bubryur Kim Yiqing Xiao Zhongdong Duan |
| author_facet | Wenjun Jiang Gang Hu Tiantian Wu Lingbo Liu Bubryur Kim Yiqing Xiao Zhongdong Duan |
| author_sort | Wenjun Jiang |
| collection | DOAJ |
| description | It is very crucial to identify the intensity of tropical cyclone (TC) accurately. In this article, a novel TC intensity estimation method is proposed to estimate the TC intensity from multispectral infrared images in the Northwest Pacific Basin. A deep multisource attention network (DMANet) is proposed to model the dynamics of multispectral infrared images along the spatial dimension. We first introduce a message-passing enhancement module based on the conditional random fields to process multispectral infrared images. Multispectral data transfer the complementary information to refine the features of TC. Second, we utilize a local global attention module to make the model focus on local key features (i.e., the typhoon eye) and obtain deeper global semantic information of TC. The ablation experiment is set up in the same dataset and computing environment to verify the effectiveness of each module. Finally, we use a Kalman filter to correct the error of TC intensity during its lifetime estimated by the DMANet model. After using Kalman filter, the evolution of TC intensity becomes smooth and corresponding root-mean-square error (RMSE) decreases from 9.79 to 7.82 knots. Compared with the best result of the existing TC intensity estimation method, the RMSE of our method is reduced by 9.07%. Therefore, the proposed TC intensity estimation method shows a great potential for accurately estimating the TC intensity. |
| first_indexed | 2024-03-13T10:23:47Z |
| format | Article |
| id | doaj.art-5ef2cc037db7472f83a61eebd1622374 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-13T10:23:47Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-5ef2cc037db7472f83a61eebd16223742023-05-19T23:00:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01164469448310.1109/JSTARS.2023.327323210121612DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared ImagesWenjun Jiang0https://orcid.org/0000-0002-8186-7698Gang Hu1https://orcid.org/0000-0001-6284-0812Tiantian Wu2Lingbo Liu3Bubryur Kim4Yiqing Xiao5Zhongdong Duan6School of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen, ChinaSchool of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen, ChinaSchool of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong KongDepartment of Robot and Smart System Engineering, Kyungpook National University, Daegu, South KoreaSchool of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen, ChinaSchool of Civil and Environmental Engineering, Harbin Institute of Technology, Shenzhen, ChinaIt is very crucial to identify the intensity of tropical cyclone (TC) accurately. In this article, a novel TC intensity estimation method is proposed to estimate the TC intensity from multispectral infrared images in the Northwest Pacific Basin. A deep multisource attention network (DMANet) is proposed to model the dynamics of multispectral infrared images along the spatial dimension. We first introduce a message-passing enhancement module based on the conditional random fields to process multispectral infrared images. Multispectral data transfer the complementary information to refine the features of TC. Second, we utilize a local global attention module to make the model focus on local key features (i.e., the typhoon eye) and obtain deeper global semantic information of TC. The ablation experiment is set up in the same dataset and computing environment to verify the effectiveness of each module. Finally, we use a Kalman filter to correct the error of TC intensity during its lifetime estimated by the DMANet model. After using Kalman filter, the evolution of TC intensity becomes smooth and corresponding root-mean-square error (RMSE) decreases from 9.79 to 7.82 knots. Compared with the best result of the existing TC intensity estimation method, the RMSE of our method is reduced by 9.07%. Therefore, the proposed TC intensity estimation method shows a great potential for accurately estimating the TC intensity.https://ieeexplore.ieee.org/document/10121612/Attention mechanismdeep learningintensity estimationKalman filtertropical cyclone (TC) |
| spellingShingle | Wenjun Jiang Gang Hu Tiantian Wu Lingbo Liu Bubryur Kim Yiqing Xiao Zhongdong Duan DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism deep learning intensity estimation Kalman filter tropical cyclone (TC) |
| title | DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images |
| title_full | DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images |
| title_fullStr | DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images |
| title_full_unstemmed | DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images |
| title_short | DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter From Multispectral Infrared Images |
| title_sort | dmanet kf tropical cyclone intensity estimation based on deep learning and kalman filter from multispectral infrared images |
| topic | Attention mechanism deep learning intensity estimation Kalman filter tropical cyclone (TC) |
| url | https://ieeexplore.ieee.org/document/10121612/ |
| work_keys_str_mv | AT wenjunjiang dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT ganghu dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT tiantianwu dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT lingboliu dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT bubryurkim dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT yiqingxiao dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages AT zhongdongduan dmanetkftropicalcycloneintensityestimationbasedondeeplearningandkalmanfilterfrommultispectralinfraredimages |