Ca-STANet: Spatio-Temporal Attention Network for chlorophyll-a prediction with gap-filled remote sensing data
Ca-STANet: Spatio-Temporal Attention Network for chlorophyll-a prediction with gap-filled remote sensing data
Long-term chlorophyll-a (Chl-a) prediction has the potential to provide an early warning of red tide and support fishery management and marine ecosystem health. The existing learning-based Chl-a prediction methods mostly predict a single point or multiple points with monitoring data. However, the monitoring data are subject to sparse sampling and difficult to be measured in a large-scale and synchronous way. Moreover, the advanced learning-based models for point Chl-a prediction, such as long short-term memory (LSTM) and convolutional neural network (CNN)-LSTM, are unable to fully mine the spatiotemporal correlation of Chl-a variations. Therefore, by using the satellite remote sensing data with extensive coverage, we design a framework, namely, Ca-STANet, to simultaneously predict the Chl-a of all the locations in a large-scale area from the perspective of spatiotemporal field. Specifically, in our method, the original data are first divided into multiple subregions to capture the spatial heterogeneity of large-scale area. Then, two modules are, respectively, operated to mine the spatial correlation and long-term dependency features. Finally, the outputs from the two modules are integrated by a fusion module to fully mine the spatiotemporal correlations, which are exploited to attain the final Chl-a prediction. In this article, the proposed Ca-STANet is comprehensively evaluated and compared with the legacy methods based on the OC-CCI Chl-a 5.0 data of the Bohai Sea. The results demonstrate that the proposed Ca-STANet is highly effective for Chl-a prediction and achieves higher prediction accuracy than the baseline methods. Moreover, as the OC-CCI Chl-a 5.0 data have many missing areas, we introduce DINEOF method to fill the data gaps before using them for prediction.
Chlorophyll-a (Chl-a), convolutional neural network, deep learning (DL), remote sensing data, spatiotemporal attention, spatiotemporal prediction
1-14
Ye, Min
0b62f82f-fbce-4d20-a140-286b33f7abdb
Li, Bohan
79b7a5a4-0966-4611-805b-621d4ff9abb5
Nie, Jie
2af15a92-68b2-463f-a969-f29b514d7b86
Qian, Yuntao
10669c6f-8759-4aa9-8817-3a087c9e56d7
Yang, Lie-Liang
ae425648-d9a3-4b7d-8abd-b3cfea375bc7
2023
Ye, Min
0b62f82f-fbce-4d20-a140-286b33f7abdb
Li, Bohan
79b7a5a4-0966-4611-805b-621d4ff9abb5
Nie, Jie
2af15a92-68b2-463f-a969-f29b514d7b86
Qian, Yuntao
10669c6f-8759-4aa9-8817-3a087c9e56d7
Yang, Lie-Liang
ae425648-d9a3-4b7d-8abd-b3cfea375bc7
Ye, Min, Li, Bohan, Nie, Jie, Qian, Yuntao and Yang, Lie-Liang
(2023)
Ca-STANet: Spatio-Temporal Attention Network for chlorophyll-a prediction with gap-filled remote sensing data.
IEEE Transactions on Geoscience and Remote Sensing, 61, , [4203314].
(doi:10.1109/TGRS.2023.3262749).
Abstract
Long-term chlorophyll-a (Chl-a) prediction has the potential to provide an early warning of red tide and support fishery management and marine ecosystem health. The existing learning-based Chl-a prediction methods mostly predict a single point or multiple points with monitoring data. However, the monitoring data are subject to sparse sampling and difficult to be measured in a large-scale and synchronous way. Moreover, the advanced learning-based models for point Chl-a prediction, such as long short-term memory (LSTM) and convolutional neural network (CNN)-LSTM, are unable to fully mine the spatiotemporal correlation of Chl-a variations. Therefore, by using the satellite remote sensing data with extensive coverage, we design a framework, namely, Ca-STANet, to simultaneously predict the Chl-a of all the locations in a large-scale area from the perspective of spatiotemporal field. Specifically, in our method, the original data are first divided into multiple subregions to capture the spatial heterogeneity of large-scale area. Then, two modules are, respectively, operated to mine the spatial correlation and long-term dependency features. Finally, the outputs from the two modules are integrated by a fusion module to fully mine the spatiotemporal correlations, which are exploited to attain the final Chl-a prediction. In this article, the proposed Ca-STANet is comprehensively evaluated and compared with the legacy methods based on the OC-CCI Chl-a 5.0 data of the Bohai Sea. The results demonstrate that the proposed Ca-STANet is highly effective for Chl-a prediction and achieves higher prediction accuracy than the baseline methods. Moreover, as the OC-CCI Chl-a 5.0 data have many missing areas, we introduce DINEOF method to fill the data gaps before using them for prediction.
Text
final_manuscript_latex
- Accepted Manuscript
Text
final_manuscript_latex
- Accepted Manuscript
More information
Accepted/In Press date: 22 March 2023
e-pub ahead of print date: 28 March 2023
Published date: 2023
Additional Information:
Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 62072418 and Grant 62172376 and in part by the Fundamental Research Funds for the Central Universities under Grant 202042008. The work of Min Ye was supported by the Chinese Scholarship Council (CSC) through the School of Electronics and Computer Science, University of Southampton, U.K. The work of Lie-Liang Yang was supported by the Engineering and Physical Sciences Research Council under Project EP/X01228X/1.
Publisher Copyright:
© 1980-2012 IEEE.
Keywords:
Chlorophyll-a (Chl-a), convolutional neural network, deep learning (DL), remote sensing data, spatiotemporal attention, spatiotemporal prediction
Identifiers
Local EPrints ID: 476874
URI: http://eprints.soton.ac.uk/id/eprint/476874
ISSN: 0196-2892
PURE UUID: daf5ed3b-3ed6-4d6d-a9ae-81802265a5e6
Catalogue record
Date deposited: 18 May 2023 16:48
Last modified: 17 Mar 2024 02:47
Export record
Altmetrics
Contributors
Author:
Min Ye
Author:
Bohan Li
Author:
Jie Nie
Author:
Yuntao Qian
Author:
Lie-Liang Yang
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics