Application of deep learning in predicting suspended sediment concentration: A case study in Jiaozhou Bay, China
文献类型：期刊论文
| 作者 | Xie, Jianbin1,6; Feng, Xingru1,4,5,6; Gao, Tianhai1,6; Wang, Zhifeng3; Wan, Kai2 ; Yin, Baoshu1,4,5,6
|
| 刊名 | MARINE POLLUTION BULLETIN
 |
| 出版日期 | 2024-04-01 |
| 卷号 | 201页码:10 |
| 关键词 | Suspended sediment concentration Geostationary Ocean Color Imager Deep learning Winds Tidal current |
| ISSN号 | 0025-326X |
| DOI | 10.1016/j.marpolbul.2024.116255 |
| 通讯作者 | Feng, Xingru(fengxingru07@qdio.ac.cn) |
| 英文摘要 | Previous research methodologies for quantifying Suspended Sediment Concentration (SSC) have encompassed insitu observations, numerical simulations, and analyses of remote sensing datasets, each with inherent constraints. In this study, we have harnessed Convolutional Neural Networks (CNNs) to create a deep learning model, which has been applied to the remote sensing data procured from the Geostationary Ocean Color Imager (GOCI) spanning April 2011 to March 2021. Our research indicates that on a small time scale, wind and hydrodynamic forces both have a significant impact on the prediction results of CNNs model. Considering both wind and hydrodynamic forces can effectively improve the model's prediction efficiency for SSC. Moreover, we have employed CNNs to interpolate absent values within the remote sensing datasets, yielding enhancements superior to those attained via linear or multivariate regression techniques. Finally, the correlation coefficient between CNN-derived SSC estimates for Jiaozhou Bay (JZB) and its corresponding remote sensing data is 0.72. Correlation coefficient and root mean square error differ in different regions. In the shallow water of JZB, due to water level changes, there is limited data, and the correlation coefficient in this area is about 0.5-0.6. In the central region of JZB with sufficient data, the correlation coefficient is generally higher than 0.75. Therefore, we believe that this CNNs model can be used to predict the hourly variation of SSC. When juxtaposed with alternative methodologies, the CNN approach is found to economize computational resources and enhance processing efficiency. |
| WOS关键词 | TEMPORAL VARIABILITY |
| 资助项目 | National Natural Science Foundation of China[42276028] ; National Key Research and Development Program of China[2023YFC3008200] ; Marine S & T Fund of Shandong Province for Pilot National Laboratory for Marine Science and Technology (Qingdao)[2021QNLM040001-5] |
| WOS研究方向 | Environmental Sciences & Ecology ; Marine & Freshwater Biology |
| 语种 | 英语 |
| WOS记录号 | WOS:001299000500001 |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 源URL | [http://ir.qdio.ac.cn/handle/337002/198262]  |
| 专题 | 海洋研究所_海洋环流与波动重点实验室 |
| 通讯作者 | Feng, Xingru |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100029, Peoples R China 2.MNR, North China Sea Survey Ctr, Qingdao 266071, Peoples R China 3.Ocean Univ China, Qingdao 266071, Peoples R China 4.Chinese Acad Sci, Inst Oceanol, CAS Engn Lab Marine Ranching, Qingdao 266071, Peoples R China 5.Pilot Natl Lab Marine Sci & Technol, Qingdao 266071, Peoples R China 6.Chinese Acad Sci, Inst Oceanol, Key Lab Ocean Observat & Forecasting, Key Lab Ocean Circulat & Waves, Qingdao 266071, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xie, Jianbin,Feng, Xingru,Gao, Tianhai,et al. Application of deep learning in predicting suspended sediment concentration: A case study in Jiaozhou Bay, China[J]. MARINE POLLUTION BULLETIN,2024,201:10. |
| APA | Xie, Jianbin,Feng, Xingru,Gao, Tianhai,Wang, Zhifeng,Wan, Kai,&Yin, Baoshu.(2024).Application of deep learning in predicting suspended sediment concentration: A case study in Jiaozhou Bay, China.MARINE POLLUTION BULLETIN,201,10. |
| MLA | Xie, Jianbin,et al."Application of deep learning in predicting suspended sediment concentration: A case study in Jiaozhou Bay, China".MARINE POLLUTION BULLETIN 201(2024):10. |
入库方式： OAI收割
来源：海洋研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。