Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System
Marine heatwaves (MHWs) are extreme events characterized by abnormally high sea surface temperatures, and they have significant impacts on marine ecosystems and human society. The rapid and accurate forecasting of MHWs is crucial for preventing and responding to the impacts they can lead to. However...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/16/4068 |
| _version_ | 1797583331332718592 |
|---|---|
| author | Wenjin Sun Shuyi Zhou Jingsong Yang Xiaoqian Gao Jinlin Ji Changming Dong |
| author_facet | Wenjin Sun Shuyi Zhou Jingsong Yang Xiaoqian Gao Jinlin Ji Changming Dong |
| author_sort | Wenjin Sun |
| collection | DOAJ |
| description | Marine heatwaves (MHWs) are extreme events characterized by abnormally high sea surface temperatures, and they have significant impacts on marine ecosystems and human society. The rapid and accurate forecasting of MHWs is crucial for preventing and responding to the impacts they can lead to. However, the research on relevant forecasting methods is limited, and a dedicated forecasting system specifically tailored for the South China Sea (SCS) region has yet to be reported. This study proposes a novel forecasting system utilizing U-Net and ConvLSTM models to predict MHWs in the SCS. Specifically, the U-Net model is used to forecast the intensity of MHWs, while the ConvLSTM model is employed to predict the probability of their occurrence. The indication of an MHW relies on both the intensity forecasted by the U-Net model exceeding threshold T and the occurrence probability predicted by the ConvLSTM model surpassing threshold P. Incorporating sensitivity analysis, optimal thresholds for T are determined as 0.9 °C, 0.8 °C, 1.0 °C, and 1.0 °C for 1-, 3-, 5-, and 7-day forecast lead times, respectively. Similarly, optimal thresholds for P are identified as 0.29, 0.30, 0.20, and 0.28. Employing these thresholds yields the highest forecast accuracy rates of 0.92, 0.89, 0.88, and 0.87 for the corresponding forecast lead times. This innovative approach gives better predictions of MHWs in the SCS, providing invaluable reference information for marine management authorities to make well-informed decisions and issue timely MHW warnings. |
| first_indexed | 2024-03-10T23:36:25Z |
| format | Article |
| id | doaj.art-38692aebf9d4432db97234ce088c2775 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:36:25Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-38692aebf9d4432db97234ce088c27752023-11-19T02:54:06ZengMDPI AGRemote Sensing2072-42922023-08-011516406810.3390/rs15164068Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM SystemWenjin Sun0Shuyi Zhou1Jingsong Yang2Xiaoqian Gao3Jinlin Ji4Changming Dong5School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaDepartment of Earth System Science, Ministry of Education Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University, Beijing 100084, ChinaSchool of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollege of Ocean Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaSchool of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaSchool of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaMarine heatwaves (MHWs) are extreme events characterized by abnormally high sea surface temperatures, and they have significant impacts on marine ecosystems and human society. The rapid and accurate forecasting of MHWs is crucial for preventing and responding to the impacts they can lead to. However, the research on relevant forecasting methods is limited, and a dedicated forecasting system specifically tailored for the South China Sea (SCS) region has yet to be reported. This study proposes a novel forecasting system utilizing U-Net and ConvLSTM models to predict MHWs in the SCS. Specifically, the U-Net model is used to forecast the intensity of MHWs, while the ConvLSTM model is employed to predict the probability of their occurrence. The indication of an MHW relies on both the intensity forecasted by the U-Net model exceeding threshold T and the occurrence probability predicted by the ConvLSTM model surpassing threshold P. Incorporating sensitivity analysis, optimal thresholds for T are determined as 0.9 °C, 0.8 °C, 1.0 °C, and 1.0 °C for 1-, 3-, 5-, and 7-day forecast lead times, respectively. Similarly, optimal thresholds for P are identified as 0.29, 0.30, 0.20, and 0.28. Employing these thresholds yields the highest forecast accuracy rates of 0.92, 0.89, 0.88, and 0.87 for the corresponding forecast lead times. This innovative approach gives better predictions of MHWs in the SCS, providing invaluable reference information for marine management authorities to make well-informed decisions and issue timely MHW warnings.https://www.mdpi.com/2072-4292/15/16/4068South China Sea marine heatwavemarine heatwave forecastmarine heatwaveU-Net networkConvLSTM network |
| spellingShingle | Wenjin Sun Shuyi Zhou Jingsong Yang Xiaoqian Gao Jinlin Ji Changming Dong Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System Remote Sensing South China Sea marine heatwave marine heatwave forecast marine heatwave U-Net network ConvLSTM network |
| title | Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System |
| title_full | Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System |
| title_fullStr | Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System |
| title_full_unstemmed | Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System |
| title_short | Artificial Intelligence Forecasting of Marine Heatwaves in the South China Sea Using a Combined U-Net and ConvLSTM System |
| title_sort | artificial intelligence forecasting of marine heatwaves in the south china sea using a combined u net and convlstm system |
| topic | South China Sea marine heatwave marine heatwave forecast marine heatwave U-Net network ConvLSTM network |
| url | https://www.mdpi.com/2072-4292/15/16/4068 |
| work_keys_str_mv | AT wenjinsun artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem AT shuyizhou artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem AT jingsongyang artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem AT xiaoqiangao artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem AT jinlinji artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem AT changmingdong artificialintelligenceforecastingofmarineheatwavesinthesouthchinaseausingacombinedunetandconvlstmsystem |