Year-end Sale % OFF 
Abstract
The trend detection of the sudden change of typhoon intensity has always been a difficult issue in typhoon forecast. Artificial intelligence (AI) can implicitly extract the complex features in the images through learning a large number of samples, and it has been widely applied in the meteorological field nowadays. In this study, based on the deep residual network (ResNet) model and the long short-term memory (LSTM) model, an automatic and objective method of identifying the trend of typhoon rapid intensification (RI) is presented through marking and learning the key information on the satellite images of the typhoons on the Northwest Pacific and South China Sea from 2005 to 2018. This method introduces the typhoon lifecycle indication and can effectively forecast and identify the trend of typhoon RI. By applying the detecting method in analyzing the operational typhoon satellite cloud images in 2019, we find that the method can well capture the sudden change tendency of typhoon intensity, and the threat score of independent sample estimation in 2019 reached 0.24. In addition, four typhoon cases with RI processes from 2019 to 2021 are tested, and the results show that the AI-based identification method of typhoon RI is superior to the traditional subjective intensity prediction method, and it has important application values.
Highlights
Feng et al [2] created statistics of tropical cyclones with abrupt intensity changes in China’s coastal waters from 1970 to 1991, and they found that when tropical cyclones moved to China’s coastal waters, the intensity suddenly increased by 20.4%
Based on the deep residual network (ResNet) model in the field of artificial intelligence and the deep learning model long short-term memory (LSTM) based on spatio-temporal correlation, the key features in the satellite cloud images are labeled, learned, and predicted to realize the detection and prediction of typhoon rapid intensification (RI)
The results indicated that the Artificial intelligence (AI)-based typhoon RI trend detection method performed better than the traditional subjective methods, and it shows potential values in operational weather forecast
Summary
A typhoon is one of the most disastrous weather affecting China. In recent years, extreme storms and secondary geological disasters caused by landfall typhoons have brought huge losses to the national economy and people’s lives. Chen et al [10] and Zheng et al [11] pointed out that a weak vertical shear between high and low levels and suitable sea surface temperature are important reasons for the RI of the No 1409 super typhoon Rammasun in offshore areas. [12] carefully analyzed the ocean and atmospheric conditions when No 1522 Typhoon Mujigae moved into the South China Sea and found that the RI of Mujigae in the offshore areas is closely related to the interaction between the underlying surface and the ambient atmosphere. Many previous studies on the prediction of typhoon RI used the prediction variables as features, such as statistics of typhoon intensity forecast SHIPS series, or by analyzing the climatic characteristics and temporal and spatial characteristics of tropical cyclones (such as season, month, latitude and longitude, air pressure change, monthly mean water temperature field, etc.), meteorologists used statistics to find some laws as the important basis for judging whether tropical cyclones will rapidly enhance. With the continuous development of meteorological satellites in China, it is a good idea to introduce and develop AI techniques in detecting the trend of typhoon RI
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
