Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea

In China’s coastal regions, severe seawater eutrophication has led to frequent occurrences of red tides, causing significant damage to marine fisheries and aquatic resources. Therefore, red tide detection and prediction are of great research importance. Although current deep learning-based red tide...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianhong Ding, Zhiqiang Xu, Yunjie Wang, Qinglian Hou, Xiangyong Liu, Fengshuang Ma
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3455
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849331017817522176
author Tianhong Ding
Zhiqiang Xu
Yunjie Wang
Qinglian Hou
Xiangyong Liu
Fengshuang Ma
author_facet Tianhong Ding
Zhiqiang Xu
Yunjie Wang
Qinglian Hou
Xiangyong Liu
Fengshuang Ma
author_sort Tianhong Ding
collection DOAJ
description In China’s coastal regions, severe seawater eutrophication has led to frequent occurrences of red tides, causing significant damage to marine fisheries and aquatic resources. Therefore, red tide detection and prediction are of great research importance. Although current deep learning-based red tide detection methods perform well in detecting single-day red tides, they struggle with continuous multi-day detection due to insufficient mining of temporal features and difficulties in accurately capturing dynamic variations, limiting further improvements in detection accuracy. To address these issues, this study proposes a time-series fusion network model (CSF-RTDNet) for red tide detection using time-continuous GOCI data from the East China Sea. By integrating multi-temporal GOCI data, the model comprehensively captures spatiotemporal characteristics of red tides, enhancing dynamic process modeling. The CSF-RTDNet method improves feature discrimination by introducing NDVI to enhance red tide characteristics and increase separability between red tides and seawater. Additionally, an ECA channel attention mechanism is employed to fully exploit spectral features across different bands for deeper feature extraction. A novel feature extraction module, ASPC-DSC, combines atrous spatial pyramid convolution with depthwise separable convolution to effectively fuse multi-scale contextual features while improving computational efficiency. Furthermore, ConvLSTM is introduced to integrate temporal and spatial features, effectively addressing the insufficient mining of sequential characteristics in multi-day red tide detection. Experimental results demonstrate that CSF-RTDNet achieves robust detection of red tides with complex boundaries and continuous temporal patterns, attaining an accuracy of 95.89%, precision of 93.03%, recall of 96.34%, and a Kappa coefficient of 0.95. This method significantly enhances red tide detection accuracy and provides valuable technical support for marine environmental monitoring.
format Article
id doaj-art-59442fe9799a4bd68ed8e6c8688cfeb5
institution Kabale University
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-59442fe9799a4bd68ed8e6c8688cfeb52025-08-20T03:46:45ZengMDPI AGSensors1424-82202025-05-012511345510.3390/s25113455Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China SeaTianhong Ding0Zhiqiang Xu1Yunjie Wang2Qinglian Hou3Xiangyong Liu4Fengshuang Ma5The Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaThe Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaThe Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaThe Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaThe Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaThe Fishery Machinery and Instrument Research Institute, Chinese Academy of Fishery Science, Shanghai 200092, ChinaIn China’s coastal regions, severe seawater eutrophication has led to frequent occurrences of red tides, causing significant damage to marine fisheries and aquatic resources. Therefore, red tide detection and prediction are of great research importance. Although current deep learning-based red tide detection methods perform well in detecting single-day red tides, they struggle with continuous multi-day detection due to insufficient mining of temporal features and difficulties in accurately capturing dynamic variations, limiting further improvements in detection accuracy. To address these issues, this study proposes a time-series fusion network model (CSF-RTDNet) for red tide detection using time-continuous GOCI data from the East China Sea. By integrating multi-temporal GOCI data, the model comprehensively captures spatiotemporal characteristics of red tides, enhancing dynamic process modeling. The CSF-RTDNet method improves feature discrimination by introducing NDVI to enhance red tide characteristics and increase separability between red tides and seawater. Additionally, an ECA channel attention mechanism is employed to fully exploit spectral features across different bands for deeper feature extraction. A novel feature extraction module, ASPC-DSC, combines atrous spatial pyramid convolution with depthwise separable convolution to effectively fuse multi-scale contextual features while improving computational efficiency. Furthermore, ConvLSTM is introduced to integrate temporal and spatial features, effectively addressing the insufficient mining of sequential characteristics in multi-day red tide detection. Experimental results demonstrate that CSF-RTDNet achieves robust detection of red tides with complex boundaries and continuous temporal patterns, attaining an accuracy of 95.89%, precision of 93.03%, recall of 96.34%, and a Kappa coefficient of 0.95. This method significantly enhances red tide detection accuracy and provides valuable technical support for marine environmental monitoring.https://www.mdpi.com/1424-8220/25/11/3455red tideNDVItime-series samplesASPC-DSCCSF-RTDNetConvLSTM
spellingShingle Tianhong Ding
Zhiqiang Xu
Yunjie Wang
Qinglian Hou
Xiangyong Liu
Fengshuang Ma
Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
Sensors
red tide
NDVI
time-series samples
ASPC-DSC
CSF-RTDNet
ConvLSTM
title Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
title_full Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
title_fullStr Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
title_full_unstemmed Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
title_short Red Tide Detection Method Based on a Time Series Fusion Network Model: A Case Study of GOCI Data in the East China Sea
title_sort red tide detection method based on a time series fusion network model a case study of goci data in the east china sea
topic red tide
NDVI
time-series samples
ASPC-DSC
CSF-RTDNet
ConvLSTM
url https://www.mdpi.com/1424-8220/25/11/3455
work_keys_str_mv AT tianhongding redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea
AT zhiqiangxu redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea
AT yunjiewang redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea
AT qinglianhou redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea
AT xiangyongliu redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea
AT fengshuangma redtidedetectionmethodbasedonatimeseriesfusionnetworkmodelacasestudyofgocidataintheeastchinasea