Tropical cyclone track prediction model for multidimensional features and time differences series observation
Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824012559 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524909099974656 |
|---|---|
| author | Peihao Yang Guodong Ye |
| author_facet | Peihao Yang Guodong Ye |
| author_sort | Peihao Yang |
| collection | DOAJ |
| description | Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize losses. However, traditional movement track forecasting methods suffer the disadvantages of low efficiency and low accuracy. To address the these problems, a novel Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) model based on Multidimensional Features and Time Difference Series (MT-CNN-TCN) is presented in this paper. First, different types of meteorological data are processed and then the feature differences between adjoining moments are extracted. Second, a two-branch structure based on Two Dimensional Convolutional Neural Network (2DCNN), 3DCNN and TCN is taken to effectively integrate different types of meteorological features to strengthen its forecasting effect. Finally, experiments are conducted using Northwest Pacific TC data from years 2000–2019. Test results show that the proposed model MT-CNN-TCN can perform well at all three forecast periods (12 h, 24 h, and 48 h), with a significant improvement in accuracy by 7 %, 13 %, and 16 % respectively, compared with current forecasting methods such as Long Short Term Memory (LSTM). |
| format | Article |
| id | doaj-art-8ed2abd776cc43b0a9fc7d06d0cbf2b2 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-8ed2abd776cc43b0a9fc7d06d0cbf2b22025-01-18T05:03:42ZengElsevierAlexandria Engineering Journal1110-01682025-01-01111432445Tropical cyclone track prediction model for multidimensional features and time differences series observationPeihao Yang0Guodong Ye1College of Ocean and Meteorology, Guangdong Ocean University, Zhangjiang 524088, ChinaCollege of Ocean and Meteorology, Guangdong Ocean University, Zhangjiang 524088, China; Faculty of Mathematics and Computer Science, Guangdong Ocean University, Zhanjiang 524088, China; Corresponding author at: College of Ocean and Meteorology, Guangdong Ocean University, Zhangjiang 524088, China.Tropical Cyclones (TCs) are highly destructive weather phenomena that can cause significant social and economic damage. With the development of meteorological monitoring technology and the updating of database, accurately forecasting the track of TC movement is one of the effective ways to minimize losses. However, traditional movement track forecasting methods suffer the disadvantages of low efficiency and low accuracy. To address the these problems, a novel Convolutional Neural Network-Temporal Convolutional Network (CNN-TCN) model based on Multidimensional Features and Time Difference Series (MT-CNN-TCN) is presented in this paper. First, different types of meteorological data are processed and then the feature differences between adjoining moments are extracted. Second, a two-branch structure based on Two Dimensional Convolutional Neural Network (2DCNN), 3DCNN and TCN is taken to effectively integrate different types of meteorological features to strengthen its forecasting effect. Finally, experiments are conducted using Northwest Pacific TC data from years 2000–2019. Test results show that the proposed model MT-CNN-TCN can perform well at all three forecast periods (12 h, 24 h, and 48 h), with a significant improvement in accuracy by 7 %, 13 %, and 16 % respectively, compared with current forecasting methods such as Long Short Term Memory (LSTM).http://www.sciencedirect.com/science/article/pii/S1110016824012559Tropical cycloneTrack predictionDeep learningTemporal convolutional networkMultidimensional features |
| spellingShingle | Peihao Yang Guodong Ye Tropical cyclone track prediction model for multidimensional features and time differences series observation Alexandria Engineering Journal Tropical cyclone Track prediction Deep learning Temporal convolutional network Multidimensional features |
| title | Tropical cyclone track prediction model for multidimensional features and time differences series observation |
| title_full | Tropical cyclone track prediction model for multidimensional features and time differences series observation |
| title_fullStr | Tropical cyclone track prediction model for multidimensional features and time differences series observation |
| title_full_unstemmed | Tropical cyclone track prediction model for multidimensional features and time differences series observation |
| title_short | Tropical cyclone track prediction model for multidimensional features and time differences series observation |
| title_sort | tropical cyclone track prediction model for multidimensional features and time differences series observation |
| topic | Tropical cyclone Track prediction Deep learning Temporal convolutional network Multidimensional features |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824012559 |
| work_keys_str_mv | AT peihaoyang tropicalcyclonetrackpredictionmodelformultidimensionalfeaturesandtimedifferencesseriesobservation AT guodongye tropicalcyclonetrackpredictionmodelformultidimensionalfeaturesandtimedifferencesseriesobservation |