Next Article in Journal
Model Updating of an Offshore Wind Turbine Support Structure Based on Modal Identification and Bayesian Inference
Previous Article in Journal
Acoustic Emission and Electromagnetic Radiation Caused by Compression and Bending Destruction of Ice
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JMSE
Volume 13
Issue 12
10.3390/jmse13122353
jmse-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Multistep-Ahead Forecasting of Chlorophyll Concentration Based on Dynamic Collaborative Attention Network

by
Lei Wang
1,
Guodong Han
1,
Ping Wu
1,
Jie Mei
1,
Zhenyu Lin
1,
Shengming Cheng
2,
Xianhua Wei
3,
Xu Yang
4,
Chuxu Xiong
5,
Shaoyang Dai
6 and
Ying Zhao
1,*
1
East China Sea Forecasting and Disaster Reduction Center, Ministry of Natural Resources, Shanghai 200136, China
2
China Three Gorges Investment Management Co., Ltd., Shanghai 201025, China
3
CRCC Harbour & Channel Engineering Bureau Group Co., Ltd., Zhuhai 519000, China
4
Huaneng (Shanghai) Clean Energy Development Co., Ltd., Shanghai 201900, China
5
Shanghai Electric Power Co., Ltd., Shanghai 200126, China
6
Shanghai Electric Wind Power Group Co., Ltd., Shanghai 200233, China
*
Author to whom correspondence should be addressed.
J. Mar. Sci. Eng. 2025, 13(12), 2353; https://doi.org/10.3390/jmse13122353
Submission received: 21 November 2025 / Revised: 8 December 2025 / Accepted: 8 December 2025 / Published: 10 December 2025
(This article belongs to the Section Marine Environmental Science)
Versions Notes

Abstract

Multistep-ahead forecasting of chlorophyll concentration is of great significance in red tide early warning systems. Existing methods often neglect the potential adverse interactions between non-predictive variables and chlorophyll while failing to fully utilize the effective information in historical decoder units. To address these issues, this paper proposes a Dynamic Collaborative Attention Network (DCAN) model for chlorophyll concentration forecasting, which consists of two components: a Two-Stage Variable Embedding Network (TSVEN) and a Dynamic Attention Network (DyAN). The TSVEN can identify the non-predictive variables that have the most significant impact on chlorophyll changes and generate corresponding spatial vectors from them, thereby alleviating the information conflict between chlorophyll and non-predictive variables. The DyAN integrates a context attention module and a filtering gate mechanism. The former effectively extends the forecasting time range by dynamically retrieving historical decoder states, while the latter selectively integrates historical decoder information, thereby improving the reliability of model decisions and prediction accuracy. Experimental results based on real datasets show that the proposed model outperforms the current state-of-the-art methods in chlorophyll concentration forecasting tasks and exhibits good interpretability.
Keywords: chlorophyll; multistep-ahead forecasting; red tide; interpretability chlorophyll; multistep-ahead forecasting; red tide; interpretability

Share and Cite

MDPI and ACS Style

Wang, L.; Han, G.; Wu, P.; Mei, J.; Lin, Z.; Cheng, S.; Wei, X.; Yang, X.; Xiong, C.; Dai, S.; et al. Multistep-Ahead Forecasting of Chlorophyll Concentration Based on Dynamic Collaborative Attention Network. J. Mar. Sci. Eng. 2025, 13, 2353. https://doi.org/10.3390/jmse13122353

AMA Style

Wang L, Han G, Wu P, Mei J, Lin Z, Cheng S, Wei X, Yang X, Xiong C, Dai S, et al. Multistep-Ahead Forecasting of Chlorophyll Concentration Based on Dynamic Collaborative Attention Network. Journal of Marine Science and Engineering. 2025; 13(12):2353. https://doi.org/10.3390/jmse13122353

Chicago/Turabian Style

Wang, Lei, Guodong Han, Ping Wu, Jie Mei, Zhenyu Lin, Shengming Cheng, Xianhua Wei, Xu Yang, Chuxu Xiong, Shaoyang Dai, and et al. 2025. "Multistep-Ahead Forecasting of Chlorophyll Concentration Based on Dynamic Collaborative Attention Network" Journal of Marine Science and Engineering 13, no. 12: 2353. https://doi.org/10.3390/jmse13122353

APA Style

Wang, L., Han, G., Wu, P., Mei, J., Lin, Z., Cheng, S., Wei, X., Yang, X., Xiong, C., Dai, S., & Zhao, Y. (2025). Multistep-Ahead Forecasting of Chlorophyll Concentration Based on Dynamic Collaborative Attention Network. Journal of Marine Science and Engineering, 13(12), 2353. https://doi.org/10.3390/jmse13122353

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop