Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data

Yixuan Hou; Zixian Zhang; Yichen Wei; Ruoxuan Cao; Yihang Xu; Yong Yue; Ruyu Yan; Xiaohui Zhu

doi:10.1007/978-3-031-88850-2_5

Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data

Yixuan Hou, Zixian Zhang, Yichen Wei, Ruoxuan Cao, Yihang Xu, Yong Yue, Ruyu Yan, Xiaohui Zhu^*

^*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

Abstract

Blue-green algae (BGA) blooms are a common and harmful occurrence in many water bodies. In this study, a spatial–temporal deep learning prediction model based on Graph Convolutional Network and Gated Recurrent Unit (GCN-GRU) is utilized to predict BGA concentration based on water quality data gathered by an unmanned surface vehicle (USV). To solve the uneven distribution of the water quality sampling positions of USV, the Kriging algorithm is applied to structure the water quality data into a graphical distribution, which can be further input into our proposed GCN-GRU deep learning network to predict short-term BGA concentration. We compare the prediction accuracy of our algorithm with the other four prediction benchmarks (HA, SVR, GRU, LTSM) in four metrics (RMSE, MAE, MAPE, R-Squared). Experimental results indicate that our GCN-GRU model has the best performance in predicting the spatial–temporal distribution of BGA in each metric.

Original language	English
Title of host publication	Proceedings of the 7th International Symposium on Water Resource and Environmental Management
Editors	Haoqing Xu
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	55-69
Number of pages	15
ISBN (Print)	9783031888496
DOIs	https://doi.org/10.1007/978-3-031-88850-2_5
Publication status	Published - 2025
Event	7th International Symposium on Water Resource and Environmental Management, WREM 2024 - Hangzhou, China Duration: 5 Dec 2024 → 6 Dec 2024

Publication series

Name	Environmental Science and Engineering
ISSN (Print)	1863-5520
ISSN (Electronic)	1863-5539

Conference

Conference	7th International Symposium on Water Resource and Environmental Management, WREM 2024
Country/Territory	China
City	Hangzhou
Period	5/12/24 → 6/12/24

Keywords

Deep learning
Harmful algal blooms
Spatial–temporal forecasting
USV sampling

Access to Document

10.1007/978-3-031-88850-2_5

Cite this

Hou, Y., Zhang, Z., Wei, Y., Cao, R., Xu, Y., Yue, Y., Yan, R., & Zhu, X. (2025). Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data. In H. Xu (Ed.), Proceedings of the 7th International Symposium on Water Resource and Environmental Management (pp. 55-69). (Environmental Science and Engineering). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-88850-2_5

Hou, Yixuan ; Zhang, Zixian ; Wei, Yichen et al. / Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data. Proceedings of the 7th International Symposium on Water Resource and Environmental Management. editor / Haoqing Xu. Springer Science and Business Media Deutschland GmbH, 2025. pp. 55-69 (Environmental Science and Engineering).

@inproceedings{2ee895cf6ba64e04870c174dad64587f,

title = "Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data",

abstract = "Blue-green algae (BGA) blooms are a common and harmful occurrence in many water bodies. In this study, a spatial–temporal deep learning prediction model based on Graph Convolutional Network and Gated Recurrent Unit (GCN-GRU) is utilized to predict BGA concentration based on water quality data gathered by an unmanned surface vehicle (USV). To solve the uneven distribution of the water quality sampling positions of USV, the Kriging algorithm is applied to structure the water quality data into a graphical distribution, which can be further input into our proposed GCN-GRU deep learning network to predict short-term BGA concentration. We compare the prediction accuracy of our algorithm with the other four prediction benchmarks (HA, SVR, GRU, LTSM) in four metrics (RMSE, MAE, MAPE, R-Squared). Experimental results indicate that our GCN-GRU model has the best performance in predicting the spatial–temporal distribution of BGA in each metric.",

keywords = "Deep learning, Harmful algal blooms, Spatial–temporal forecasting, USV sampling",

author = "Yixuan Hou and Zixian Zhang and Yichen Wei and Ruoxuan Cao and Yihang Xu and Yong Yue and Ruyu Yan and Xiaohui Zhu",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 7th International Symposium on Water Resource and Environmental Management, WREM 2024 ; Conference date: 05-12-2024 Through 06-12-2024",

year = "2025",

doi = "10.1007/978-3-031-88850-2\_5",

language = "English",

isbn = "9783031888496",

series = "Environmental Science and Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "55--69",

editor = "Haoqing Xu",

booktitle = "Proceedings of the 7th International Symposium on Water Resource and Environmental Management",

}

Hou, Y, Zhang, Z, Wei, Y, Cao, R, Xu, Y, Yue, Y, Yan, R & Zhu, X 2025, Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data. in H Xu (ed.), Proceedings of the 7th International Symposium on Water Resource and Environmental Management. Environmental Science and Engineering, Springer Science and Business Media Deutschland GmbH, pp. 55-69, 7th International Symposium on Water Resource and Environmental Management, WREM 2024, Hangzhou, China, 5/12/24. https://doi.org/10.1007/978-3-031-88850-2_5

Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data. / Hou, Yixuan; Zhang, Zixian; Wei, Yichen et al.
Proceedings of the 7th International Symposium on Water Resource and Environmental Management. ed. / Haoqing Xu. Springer Science and Business Media Deutschland GmbH, 2025. p. 55-69 (Environmental Science and Engineering).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data

AU - Hou, Yixuan

AU - Zhang, Zixian

AU - Wei, Yichen

AU - Cao, Ruoxuan

AU - Xu, Yihang

AU - Yue, Yong

AU - Yan, Ruyu

AU - Zhu, Xiaohui

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - Blue-green algae (BGA) blooms are a common and harmful occurrence in many water bodies. In this study, a spatial–temporal deep learning prediction model based on Graph Convolutional Network and Gated Recurrent Unit (GCN-GRU) is utilized to predict BGA concentration based on water quality data gathered by an unmanned surface vehicle (USV). To solve the uneven distribution of the water quality sampling positions of USV, the Kriging algorithm is applied to structure the water quality data into a graphical distribution, which can be further input into our proposed GCN-GRU deep learning network to predict short-term BGA concentration. We compare the prediction accuracy of our algorithm with the other four prediction benchmarks (HA, SVR, GRU, LTSM) in four metrics (RMSE, MAE, MAPE, R-Squared). Experimental results indicate that our GCN-GRU model has the best performance in predicting the spatial–temporal distribution of BGA in each metric.

AB - Blue-green algae (BGA) blooms are a common and harmful occurrence in many water bodies. In this study, a spatial–temporal deep learning prediction model based on Graph Convolutional Network and Gated Recurrent Unit (GCN-GRU) is utilized to predict BGA concentration based on water quality data gathered by an unmanned surface vehicle (USV). To solve the uneven distribution of the water quality sampling positions of USV, the Kriging algorithm is applied to structure the water quality data into a graphical distribution, which can be further input into our proposed GCN-GRU deep learning network to predict short-term BGA concentration. We compare the prediction accuracy of our algorithm with the other four prediction benchmarks (HA, SVR, GRU, LTSM) in four metrics (RMSE, MAE, MAPE, R-Squared). Experimental results indicate that our GCN-GRU model has the best performance in predicting the spatial–temporal distribution of BGA in each metric.

KW - Deep learning

KW - Harmful algal blooms

KW - Spatial–temporal forecasting

KW - USV sampling

UR - https://www.scopus.com/pages/publications/105009228955

U2 - 10.1007/978-3-031-88850-2_5

DO - 10.1007/978-3-031-88850-2_5

M3 - Conference Proceeding

AN - SCOPUS:105009228955

SN - 9783031888496

T3 - Environmental Science and Engineering

SP - 55

EP - 69

BT - Proceedings of the 7th International Symposium on Water Resource and Environmental Management

A2 - Xu, Haoqing

PB - Springer Science and Business Media Deutschland GmbH

T2 - 7th International Symposium on Water Resource and Environmental Management, WREM 2024

Y2 - 5 December 2024 through 6 December 2024

ER -

Hou Y, Zhang Z, Wei Y, Cao R, Xu Y, Yue Y et al. Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data. In Xu H, editor, Proceedings of the 7th International Symposium on Water Resource and Environmental Management. Springer Science and Business Media Deutschland GmbH. 2025. p. 55-69. (Environmental Science and Engineering). doi: 10.1007/978-3-031-88850-2_5

Algal Bloom Prediction Based on Graph Convolutional Network and Gated Recurrent Unit Deep Neural Network and Massive Spatial–temporal Water Quality Data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this