Hybrid dual decomposition-machine learning model for forecasting dissolved oxygen in aquaculture
Abstract
In aquaculture, dissolved oxygen levels are a primary determinant of water quality; leveraging accurate forecasts for this parameter directly contributes to improved yields and higher-quality harvests. Given that current dissolved oxygen prediction models utilize just one decomposition process, they are unable to sufficiently mitigate residual noise interference or properly handle non-stationary features. To enhance prediction accuracy, our model begins by processing the original dissolved oxygen sequence via an improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), yielding multiple intrinsic mode functions (IMFs). These IMFs are then clustered according to their fuzzy entropy using the K-means algorithm. The component with the maximum fuzzy entropy value is selected for further refinement through a Sequential Variational Mode Decomposition (SVMD). This dual decomposition approach effectively preserves valid information while enhancing detailed feature extraction. For the forecasting stage, an Extreme Learning Machine (ELM) whose parameters are optimized by the rime optimization algorithm is developed to generate forecasts for each sub-component. Ultimately, the predictions of all components are aggregated through a Back-Propagation (BP) neural network to produce the final dissolved oxygen time series. The proposed model is applied to verify dissolved oxygen in the standard pond of Huludao sea cucumber aquaculture base, Liaoning province, China. Evaluation results show that the proposed model exceeds the performance of existing comparative models. With the RMSE of 0.2443, MAE of 0.1782, MAPE of 0.0352, and R2 of 0.9835, the model exhibits exceptional predictive accuracy and operational stability, validating that it is well-suited to meet the practical demands of contemporary aquaculture.
Keywords: dissolved oxygen, secondary decomposition, fuzzy entropy, rime, extreme learning machine
DOI: 10.25165/j.ijabe.20261901.10299 Citation: Chen C, Liu C Y, Peng S M, Wang Y L, Wang K Q, Yin Z N. Hybrid dual decomposition-machine learning model for forecasting dissolved oxygen in aquaculture. Int J Agric & Biol Eng, 2026; 19(1): 33–46.References
[1] Yu Z H, Zhou Y, Yang H S, Hu C Q. Bottom culture of the sea cucumber Apostichopus japonicus Selenka （Echinodermata: Holothuroidea） in a fish farm, southern China. Aquaculture Research, 2014; 45（9）: 1434–1441.
[2] Hu J Y, Wang J J, Zhang X S, Fu Z T. Research status and development trends of information technologies in aquacultures. Transactions of the CSAM, 2015; 46（7）: 251–263.
[3] Mendivil-García K, Amabilis-Sosa L E, Salinas-Juárez M G, Pat-Espadas A, Rodríguez-Mata A E, Figueroa-Pérez M G, et al. Climate change impact assessment on a tropical river resilience using the Streeter-Phelps dissolved oxygen model. Frontiers in Environmental Science, 2022; 10: 3389.
[4] Li X Y, Wang H, Wang Y Q, Zhang L J, Wu Y. Machine learning-based dissolved oxygen prediction modeling and evaluation in the Yangtze River estuary. Environmental Science, 2024; 45（12）: 7123–7133.
[5] Liu S Y, Xu L Q, Li D L, Zeng L H. Dissolved oxygen prediction model of eriocheir sinensis culture based on least squares support vector regression optimized by ant colony algorithm. Transactions of the CSAE, 2012; 28（23）: 167–175.
[6] Liu S, Xu L Q, Jiang Y, Li D L, Chen Y Y, Li Z B. A hybrid WA–CPSO-LSSVR model for dissolved oxygen content prediction in crab culture. Engineering Applications of Artificial Intelligence, 2014; 29（3）: 114–124.
[7] Huan J, Liu X Q. Dissolved oxygen prediction in water based on K-means clustering and ELM neural network for aquaculture. Transactions of the CSAE, 2016; 32（17）: 174–181.
[8] Shi P, Kuang L, Yuan L M, Wang Q, Li G H, Yuan Y M, et al. Dissolved oxygen prediction using regularized extreme learning machine with clustering mechanism in a black bass aquaculture pond. Aquacultural Engineering, 2024; 105: 102408.
[9] Li W H, Dong Z T, Chen T, Wang F H, Huang F L. Enhanced prediction of dissolved oxygen concentration using a hybrid deep learning approach with sinusoidal geometric mode decomposition. Water, Air, & Soil Pollution, 2024; 235: 447. DOI: 10.1007/S11270-024-07242-X
[10] He M, Cui M, Zheng Q Y, Xu L Q, Liu S Y. PSG-Crossformer: a hybrid model for long-term dissolved oxygen prediction in aquaculture. Aquaculture International, 2025; 33: 301.
[11] Jiao J G, Ma Q Q, Liu F L, Zhao L Q, Huang S J. A hybrid prediction model of dissolved oxygen concentration based on secondary decomposition and bidirectional gate recurrent unit. Environmental Geochemistry and Health, 2024; 46: 127.
[12] Su H, Zhao D, Asghar H A, Liu L, Zhang X Q, Majdi M, et al. RIME: A physics-based optimization. Neurocomputing, 2023; 532: 183–214.
[13] Colominas M A, Schlotthauer G, Torres M E. Improved complete ensemble EMD: A suitable tool for biomedical signal processing. Biomedical Signal Processing and Control, 2014; 14: 19–29.
[14] Kong Y L, Meng Y, Li W, Yue A Z, Yuan Y. Satellite image time series decomposition based on EEMD. Remote Sensing, 2015; 7（11）: 15583–15604.
[15] Wu Z H, Huang N E. Ensemble empirical mode decomposition: A noise-assisted data analysis method. Advances in Adaptive Data Analysis, 2009; 1（1）: 1–41.
[16] Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Trans. Signal Processing, 2013; 62（3）: 531–544.
[17] Huang G B, Chen L, Siew C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Transactions on Neural Networks, 2006; 17（4）: 879–892.
[18] Ravikumar R R S, Apparao G. Extreme learning machine with Sigmoid activation function on large data. International Journal of Recent Technology and Engineering, 2019; 8（2）: 3523–3526.
[19] Zhou Y T, Zhao X Y, He F, Shi C J. Atmospheric temperature and humidity prediction based on Gaussian process mixture model. Transactions of the CSAE, 2018; 34（5）: 219–226.
[20] Hassani H, Yeganegi M R, Mehreyan S Z, Sayyareh A. On the sample autocorrelation function’s absolute summability. Fluctuation and Noise Letters, 2022; 21（1）. DOI: 10.1142/S0219477522500043
[21] Hassani H, Marvian L, Yarmohammadi M, Yeganegi M R. Unraveling time series dynamics: evaluating partial autocorrelation function distribution and its implications. Mathematical and Computational Applications, 2024; 29（4）: 58–58.
[22] Belaire-Franch J. Estimating the maximum Lyapunov exponent with denoised data to test for chaos in the German stock market. Computational Economics, 2025; 66: 3517–3543.
[23] Wei L, Cao H, Wang L D. Optimal choices of reconstruction parameters united improved C-C algorithm and improved G-P algorithm. Journal of Physics: Conference Series, 2023; 2508（1）. DOI: 10.1088/1742-6596/2508/1/012057
[24] Adnan R M, Parmar K S, Heddam S, Shahid S, Kisi O. Suspended sediment modeling using a heuristic regression method hybridized with kmeans clustering. Sustainability, 2021; 13（9）: 4648–4648.
[25] Ali K B, Morteza F A, Mohamed S, Haj A M E, Natarajan P. Modeling carbon dioxide emission of countries in southeast of Asia by applying artificial neural network. International Journal of Low-Carbon Technologies, 2022; 17: 321–326.
[26] Tümer A E, Edebali S. Modeling of trivalent chromium sorption onto commercial resins by artificial neural network. Applied Artificial Intelligence, 2019; 33（4）: 349–360.
[27] Yaldi G, Nur I M, Apwiddhal. Calibrating trip distribution neural network models with different scenarios of transfer functions used in hidden and output layers. International Journal on Advanced Science, Engineering and Information Technology, 2020; 10（6）: 2410–2418.
[28] Hu C Y, Zhong Y, Lu Y Q, Luo X T, Wang S R. A prediction model for time series of dissolved gas content in transformer oil based on LSTM. Journal of Physics: Conference Series, 2020; 1659（1）: 012030.
[29] Jiang W T, Ling L W, Zhang D B, Lin R B, Zeng L L. A time series forecasting model selection framework using CNN and data augmentation for small sample data. Neural Processing Letters, 2023; 55（5）: 5783–5810.
[30] Ma J K, Xu W P. GA-BP-based nonlinear time series forecasting: method and applications. Academic Journal of Computing & Information Science, 2024; 7（8）: 15–20.
[31] Gao D, Li K, Cai Y C, Wen T. Landslide displacement prediction based on time series and PSO-BP model in three georges reservoir, China. Journal of Earth Science, 2024; 35（3）: 1079–1082.
[32] Yan J L, Hu G, Shu B. MGCHMO: A dynamic differential human memory optimization with Cauchy and Gauss mutation for solving engineering problems. Advances in Engineering Software, 2024; 198: 103793.
[33] Yang X Y, Zhou G F, Ren Z J, Qiao Y X, Yi J C. High-precision air conditioning load forecasting model based on improved sparrow search algorithm. Journal of Building Engineering, 2024; 92: 109809.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Agricultural and Biological Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
IJABE is an international peer reviewed, open access journal, adopting Creative Commons Copyright Notices as follows.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
