Enhancing aquaculture water quality forecasting using novel adaptive multi-channel spatial-temporal graph convolutional network
Abstract
quality prediction is of critical importance. However, traditional water quality prediction models face limitations in handling
complex spatiotemporal patterns. To address this challenge, a prediction model was proposed for water quality, namely an
adaptive multi-channel temporal graph convolutional network (AMTGCN). The AMTGCN integrates adaptive graph
construction, multi-channel spatiotemporal graph convolutional network, and fusion layers, and can comprehensively capture
the spatial relationships and spatiotemporal patterns in aquaculture water quality data. Onsite aquaculture water quality data and
the metrics MAE, RMSE, MAPE, and R2 were collected to validate the AMTGCN. The results show that the AMTGCN
presents an average improvement of 34.01%, 34.59%, 36.05%, and 17.71% compared to LSTM, respectively; an average
improvement of 64.84%, 56.78%, 64.82%, and 153.16% compared to the STGCN, respectively; an average improvement of
55.25%, 48.67%, 57.01%, and 209.00% compared to GCN-LSTM, respectively; and an average improvement of 7.05%,
5.66%, 7.42%, and 2.47% compared to TCN, respectively. This indicates that the AMTGCN, integrating the innovative
structure of adaptive graph construction and multi-channel spatiotemporal graph convolutional network, could provide an
efficient solution for water quality prediction in aquaculture.
Keywords: water quality prediction, aquaculture, spatial-temporal graph convolutional network, multi-channel, adaptive graph
construction
DOI: 10.25165/j.ijabe.20251801.9074
Citation: Xiang T Q, Guo X Y, Chi J J, Gao J, Zhang L W. Enhancing aquaculture water quality forecasting using novel
adaptive multi-channel spatial-temporal graph convolutional network. Int J Agric & Biol Eng, 2025; 18(1): 279–291.
Keywords
Full Text:
PDFReferences
Price C, Black K D, Hargrave B T, Morris Jr J A. Marine cage culture and the environment: Effects on water quality and primary production. Aquaculture Environment Interactions, 2015; 6: 151–174.
Garlock T, Asche F, Anderson J, Ceballos-Concha A, Love D C, Osmundsen T C, et al. Aquaculture: The missing contributor in the food security agenda. Global Food Security, 2022; 32: 100620.
Nowakowski A J, Canty S W J, Bennett N J, Cox C E, Valdivia A, Deichmann J L, et al. Co-benefits of marine protected areas for nature and people. Nature Sustainability, 2023; 6: 1210–1218.
Wang F L, Gao Y T, Gao Y H, Li M Y, Zhang B Z, Guan C T, et al. Preliminary study on land-sea alternate aquaculture of spotted knifejaw Oplegnathus punctatus. Fishery Modernization, 2022; 49（4）: 8–14. （in Chinese）
Lu H Y, Cheng C Y, Cheng S C, Cheng Y H, Lo W C, Jiang W L, et al. A low-cost AI buoy system for monitoring water quality at offshore aquaculture cages. Sensors, 2022; 22（11）: 4078.
Huan J, Li H, Li M B, Chen B. Prediction of dissolved oxygen in aquaculture based on gradient boosting decision tree and long short-term memory network: A study of Chang Zhou fishery demonstration base, China. Computers and Electronics in Agriculture, 2020; 175: 105530.
Hu Z H, Zhang Y R, Zhao Y C, Xie M S, Zhong J Z, Tu Z G, et al. A water quality prediction method based on the deep LSTM network considering correlation in smart mariculture. Sensors, 2019; 19（6）: 1420.
Meyer A M, Klein C, Fünfrocken E, Kautenburger R, Beck H P. Real-time monitoring of water quality to identify pollution pathways in small and middle scale rivers. Science of The Total Environment, 2019; 651（Part2）: 2323–2333.
Li D S, Zhao W J, Hu J Z, Zhao S W, Liu S E. A long-term water quality prediction model for marine ranch based on time-graph convolutional neural network. Ecological Indicators, 2023; 154: 110782.
Lin W, Luo H M, Wu J Y, Hung T-C, Cao B B, Liu X L, et al. A review of the emerging risks of acute ammonia nitrogen toxicity to aquatic decapod crustaceans. Water, 2023; 15（1）: 27.
Erickson R J. An evaluation of mathematical models for the effects of pH and temperature on ammonia toxicity to aquatic organisms. Water Research, 1985; 19（8）: 1047–1058.
Eze E, Halse S, Ajmal T. Developing a novel water quality prediction model for a South African aquaculture farm. Water, 2021; 13（13）: 1782.
Zheng Z Q, Ding H, Weng Z, Wang L X. Research on a multiparameter water quality prediction method based on a hybrid model. Ecological Informatics, 2023; 76: 102125.
Wang J, Zhang L Y, Zhang W, Wang X D. Reliable model of reservoir water quality prediction based on improved ARIMA method. Environmental Engineering Science, 2019; 36（9）: 1041–1048.
Phan T T H, Nguyen X H. Combining statistical machine learning models with ARIMA for water level forecasting: The case of the red river. Advances in Water Resources, 2020; 142: 103656.
Dong Q X, Liu J C, Qu M. Simple model for predicting hourly air temperatures inside Chinese solar greenhouses. Int J Agric & Biol Eng, 2023; 16（5）: 56–60.
Ma L L, Zhou L F, Wang T L. Water quality prediction based on BP neural network at Dahuofang Reservoir, China. Nature Environment and Pollution Technology, 2015; 14（3）: 727–732.
Otsuka T, Kitazawa Y, Ito T. Seawater temperature prediction method for sustainable marine aquaculture. Preprints. Available: https://doi.org/10.20944/preprints201709.0114.v1. Accessed on [2023-11-10].
Usanapong R, Boonnam N. Data standardization analysis for water quality parameters of nursery aquaculture. In: 2022 19th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology （ECTI-CON）, Prachuap Khiri Khan: IEEE, 2022; pp.1–4. doi: 10.1109/ECTI-CON54298.2022.9795389.
Li C, Li Z, Wu J, Zhu L, Yue J. A hybrid model for dissolved oxygen prediction in aquaculture based on multi-scale features. Information Processing in Agriculture, 2018; 5（1）: 11–20.
Nagaraju T V, Sunil B M, Chaudhary B, Prasad C D, Gobinath R. Prediction of ammonia contaminants in the aquaculture ponds using soft computing coupled with wavelet analysis. Environmental Pollution, 2023; 331: 121924.
Ahmed U, Mumtaz R, Anwar H, Shah A A, Irfan, R, García-Nieto J. Efficient water quality prediction using supervised machine learning. Water, 2019; 11（11）: 2210.
Zhu N Y, Liu X, Liu Z Q, Hu K, Wang Y K, Tan J L, et al. Deep learning for smart agriculture: Concepts, tools, applications, and opportunities. Int J Agric & Biol Eng, 2018; 11（4）: 32–44.
Duan E Z, Wang L J, Wang H Y, Hao H Y, Li R L. Remaining feed weight estimation model for health monitoring of meat rabbits based on deep convolutional neural network. Int J Agric & Biol Eng, 2022; 15（1）: 233–240.
Li W S, Wei Y G, An D, Jiao Y S, Wei Q. LSTM-TCN: Dissolved oxygen prediction in aquaculture, based on combined model of long short-term memory network and temporal convolutional network. Environmental Science and Pollution Research, 2022; 29: 39545–39556.
Zhou X H, Wang J P, Liu Y R, Duan Q L. Deep learning with PID residual elimination network for time-series prediction of water quality in aquaculture industry. Computers and Electronics in Agriculture, 2023; 212: 108125.
Li Y L, Zhang L, Li L. Study on water quality prediction of south source of Qiantang River based on GCN-LSTM. Yellow River, 2023; 45（12）: 83–87, 95. （in Chinese）
Skarding J, Gabrys B, Musial K. Foundations and modelling of dynamic networks using dynamic graph neural networks: A survey. IEEE Access, 2021; 9: 79143–79168.
Yu B, Yin H T, Zhu Z X. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018; pp.3634–3640. doi: 10.24963/ijcai.2018/505.
Feng A, Tassiulas L. Adaptive graph spatial-temporal transformer network for traffic forecasting. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, ACM: Atlanta: ACM, 2022; pp.3933–3937.
Li P F, Zhang T, Jin Y T. A spatio-temporal graph convolutional network for air quality prediction. Sustainability, 2023; 15（9）: 7624.
Xing M D, Ding W L, Zhang T P, Li H. STCGCN: A spatio-temporal complete graph convolutional network for remaining useful life prediction of power transformer. International Journal of Web Information Systems, 2023; 19（2）: 102–117.
Dwivedi V P, Luu A T, Laurent T, Bengio Y, Bresson X. Graph neural networks with learnable structural and positional representations. arXiv. Available: https://arxiv.org/abs/2110.07875v2. Accessed on [2023-11-10].
Huang Q, Olenin S, Sun S, De Troch M. Impact of farming non-indigenous scallop Argopecten irradians on benthic ecosystem functioning: A case-study in Laizhou Bay, China. Aquaculture Environment Interactions, 2018; 10: 227–241.
Han Q F, Zhang X R, Xu X Y, Wang X L, Yuan X Z, Ding Z J, et al. Antibiotics in marine aquaculture farms surrounding Laizhou Bay, Bohai Sea: Distribution characteristics considering various culture modes and organism species. Science of The Total Environment, 2021; 760: 143863.
Luo H P, Li G L, Peng W F, Song J, Bai Q W. Real-time remote monitoring system for aquaculture water quality. Int J Agric & Boil Eng, 2015; 8（6）: 136–143.
Rasheed Abdul Haq K P, Harigovindan V P. Water quality prediction for smart aquaculture using hybrid deep learning models. IEEE Access, 2022; 10: 60078–60098.
Wu Z H, Pan S R, Long G D, Jiang J, Chang X J, Zhang C Q. Connecting the dots: Multivariate time series forecasting with graph neural networks. In: Proceedings of the Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, ACM, 2020; pp.753–763. doi: 10.1145/3394486.3403118.
Chen Y Z, Xie Z X. Multi-channel fusion graph neural network for multivariate time series forecasting. Journal of Computational Science, 2022; 64: 101862.
Fang Y C, Ren K, Shan C H, Shen Y F, Li Y, Zhang W N, et al. Learning decomposed spatial relations for multi-variate time-series modeling. In: AAAI-23 Technical Tracks 6 - AAAI Technical Track on Machine Learning I, 2023; 37（6）: 7530–7538.
Klicpera J, Bojchevski A, Günnemann S. Predict then propagate: Graph neural networks meet personalized pagerank. In: International Conference on Learning Representations （ICLR）, New Orleans, 2019.
Bai S J, Zico Kolter J, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv. Available: http://arxiv.org/abs/1803.01271. Accessed on [2023-11-10].
Jiang B, Zhang Z, Lin D D, Tang J, Luo B. Semi-supervised learning with graph learning-convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach: IEEE, 2019; pp.11313–11320. doi: 10.1109/CVPR.2019.01157.
Li Q M, Han Z C, Wu X M. Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2018; 32: 11118105.
Chen F W, Pan S R, Jiang J, Huo H, Long G D. DAGCN: Dual attention graph convolutional networks. In 2019 International Joint Conference on Neural Networks （IJCNN）, Budapest, 2019; pp.1–8. doi: 10.1109/IJCNN.2019.8851698.
Abu-El-Haija S, Perozzi B, Kapoor A, Alipourfard N, Lerman K, Harutyunyan H, et al. MixHop: Higher-order graph convolutional architectures via sparsified neighborhood mixing. In: Proceedings of the Proceedings of the 36th International Conference on Machine Learning, 2019; pp.21–29.
Lim B, Zohren S. Time-series forecasting with deep learning: A survey. Philosophical Transactions of the Royal Society A-mathematical Physical and Engi, 2021; 379（2194）: 20200209.
Chen H L, Yang J B, Fu X H, Zheng Q X, Song X Y, Fu Z D, et al. Water quality prediction based on LSTM and attention mechanism: A case study of the Burnett River, Australia. Sustainability, 2022; 14（20）: 13231.
Zuo C H, Wang J L, Liu M P, Deng S H, Wang Q N. An ensemble framework for short-term load forecasting based on TimesNet and TCN. Energies, 2023; 16（14）: 5330.
Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. In: Proceedings of the 30th International Conference on Neural Information Processing Systems （NIPS’16）. Curran Associates Inc., Red Hook, 2016; pp.3844–3852.
Gehring J, Auli M, Grangier D, Yarats D, Dauphin Y N. Convolutional sequence to sequence learning. In: Proceedings of the Proceedings of the 34th International Conference on Machine Learning, PMLR, 2017; pp.1243–1252.
Chen H H, Zhu M Y, Hu X, Wang J R, Sun Y, Yang J D, et al. Multifeature short-term power load forecasting based on GCN-LSTM. International Transactions on Electrical Energy Systems, 2023; 2023（1）: 8846554.
Du S D, Li T R, Yang Y, Horng S J. Multivariate time series forecasting via attention-based encoder-decoder framework. Neurocomputing, 2020; 388: 269–279.
Liu G, Jiang Y, Zhong K, Yang Y, Wang Y. A time series model adapted to multiple environments for recirculating aquaculture systems. Aquaculture, 2023; 567: 739284.
Mohammadi H A, Ghofrani S, Nikseresht A. Using empirical wavelet transform and high-order fuzzy cognitive maps for time series forecasting. Applied Soft Computing, 2023; 135: 109990.
Copyright (c) 2025 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.