A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble

Abstract

Dissolved oxygen (DO) is an important indicator of aquaculture, and its accurate forecasting can effectively improve the quality of aquatic products. In this paper, a new DO hybrid forecasting model is proposed that includes three stages: multi-factor analysis, adaptive decomposition, and an optimization-based ensemble. First, considering the complex factors affecting DO, the grey relational (GR) degree method is used to screen out the environmental factors most closely related to DO. The consideration of multiple factors makes model fusion more effective. Second, the series of DO, water temperature, salinity, and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform (EWT) method. Then, five benchmark models are utilized to forecast the sub-series of EWT decomposition. The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm (PSOGSA). Finally, a multi-factor ensemble model for DO is obtained by weighted allocation. The performance of the proposed model is verified by time-series data collected by the pacific islands ocean observing system (PacIOOS) from the WQB04 station at Hilo. The evaluation indicators involved in the experiment include the nash-sutcliffe efficiency (NSE), kling-gupta efficiency (KGE), mean absolute percent error (MAPE), standard deviation of error (SDE), and coefficient of determination (R2). Example analysis demonstrates that: ① the proposed model can obtain excellent DO forecasting results; ② the proposed model is superior to other comparison models; and ③ the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.

Keywords

Dissolved oxygen concentrations forecasting / Time-series multi-step forecasting / Multi-factor analysis / Empirical wavelet transform decomposition / Multi-model optimization ensemble

References

[[1]] Yang Z. Watershed ecology and its applications. Engineering 2018;4(5):582–3.

[[2]] Hoogakker BAA, Lu Z, Umling N, Jones L, Zhou X, Rickaby RE, et al. Glacial expansion of oxygen-depleted seawater in the eastern tropical Pacific. Nature 2018;562(7727):410–3.

[[3]] McClanahan TR, Ateweberhan M, Muhando CA, Maina J, Mohammed MS. Effects of climate and seawater temperature variation on coral bleaching and mortality. Ecol Monogr 2007;77(4):503–25.

[[4]] Gimpel A, Stelzenmüller V, Grote B, Buck BH, Floeter J, Núñez-Riboni I, et al. A GIS modelling framework to evaluate marine spatial planning scenarios: colocation of offshore wind farms and aquaculture in the German EEZ. Mar Policy 2015;55:102–15.

[[5]] Keller AA, Ciannelli L, Wakefield WW, Simon V, Barth JA, Pierce SD. Occurrence of demersal fishes in relation to near-bottom oxygen levels within the California Current large marine ecosystem. Fish Oceanogr 2015;24(2):162–76.

[[6]] Addanki SC, Venkataraman H. Greening the economy: a review of urban sustainability measures for developing new cities. Sustainable Cities Soc 2017;32:1–8.

[[7]] Schmidtko S, Stramma L, Visbeck M. Decline in global oceanic oxygen content during the past five decades. Nature 2017;542(7641):335–9.

[[8]] Culberson SD, Piedrahita RH. Aquaculture pond ecosystem model: temperature and dissolved oxygen prediction—mechanism and application. Ecol Modell 1996;89(1–3):231–58.

[[9]] Liu S, Xu L, Li D, Li Q, Jiang Yu, Tai H, et al. Prediction of dissolved oxygen content in river crab culture based on least squares support vector regression optimized by improved particle swarm optimization. Comput Electron Agric 2013;95:82–91.

[[10]] Faruk DÖ. A hybrid neural network and ARIMA model for water quality time series prediction. Eng Appl Artif Intell 2010;23(4):586–94.

[[11]] Li C, Li Z, Wu J, Zhu L, Yue J. A hybrid model for dissolved oxygen prediction in aquaculture based on multi-scale features. Inf Process Agric 2018;5(1):11–20.

[[12]] Huan J, Cao W, Qin Y. Prediction of dissolved oxygen in aquaculture based on EEMD and LSSVM optimized by the Bayesian evidence framework. Comput Electron Agric 2018;150:257–65.

[[13]] Khan U, Valeo C, Comparing A. Bayesian and fuzzy number approach to uncertainty quantification in short-term dissolved oxygen prediction. J Environ Inform 2017;30(1):1–16.

[[14]] Khan UT, Valeo C, He J. Non-linear fuzzy-set based uncertainty propagation for improved DO prediction using multiple-linear regression. Stochastic Environ Res Risk Assess 2013;27(3):599–616.

[[15]] Kisi O, Parmar KS. Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. J Hydrol 2016;534:104–12.

[[16]] Ay M, Kisi O. Modelling of chemical oxygen demand by using ANNs, ANFIS and k-means clustering techniques. J Hydrol 2014;511:279–89.

[[17]] Ay M, Kisi O. Modeling of dissolved oxygen concentration using different neural network techniques in Foundation Creek, El Paso County, Colorado. J Environ Eng 2012;138(6):654–62.

[[18]] Zhu S, Heddam S. Prediction of dissolved oxygen in urban rivers at the Three Gorges Reservoir, China: extreme learning machines (ELM) versus artificial neural network (ANN). Water Quality Res J 2020;55(1):106–18.

[[19]] Heddam S, Kisi O. Modelling daily dissolved oxygen concentration using least square support vector machine, multivariate adaptive regression splines and M5 model tree. J Hydrol 2018;559:499–509.

[[20]] Ay M, Kisi Ö. Estimation of dissolved oxygen by using neural networks and neuro fuzzy computing techniques. KSCE J Civ Eng 2017;21(5):1631–9.

[[21]] Khan UT, Valeo C. Dissolved oxygen prediction using a possibility theory based fuzzy neural network. Hydrol Earth Syst Sci 2016;20(6):2267–93.

[[22]] Shi P, Li G, Yuan Y, Huang G, Kuang L. Prediction of dissolved oxygen content in aquaculture using Clustering-based Softplus Extreme Learning Machine. Comput Electron Agric 2019;157:329–38.

[[23]] Ren Q, Zhang L, Wei Y, Li D. A method for predicting dissolved oxygen in aquaculture water in an aquaponics system. Comput Electron Agric 2018;151:384–91.

[[24]] Wu J, Li Z, Zhu L, Li G, Niu B, Peng F. Optimized BP neural network for dissolved oxygen prediction. IFAC-PapersOnLine 2018;51(17):596–601.

[[25]] Liu S, Xu L, Jiang Yu, Li D, Chen Y, Li Z. A hybrid WA–CPSO-LSSVR model for dissolved oxygen content prediction in crab culture. Eng Appl Artif Intell 2014;29:114–24.

[[26]] Raheli B, Aalami MT, El-Shafie A, Ghorbani MA, Deo RC. Uncertainty assessment of the multilayer perceptron (MLP) neural network model with implementation of the novel hybrid MLP-FFA method for prediction of biochemical oxygen demand and dissolved oxygen: a case study of Langat River. Environ Earth Sci 2017;76(14):503.

[[27]] Yang H, Csukás B, Varga M, Kucska B, Szabó T, Li D. A quick condition adaptive soft sensor model with dual scale structure for dissolved oxygen simulation of recirculation aquaculture system. Comput Electron Agric 2019;162:807–24.

[[28]] Ma J, Ding Y, Cheng JCP, Jiang F, Xu Z. Soft detection of 5-day BOD with sparse matrix in city harbor water using deep learning techniques. Water Res 2020;170:115350.

[[29]] Ren Q, Wang X, Li W, Wei Y, An D. Research of dissolved oxygen prediction in recirculating aquaculture systems based on deep belief network. Aquacult Eng 2020;90:102085.

[[30]] Kisi O, Akbari N, Sanatipour M, Hashemi A, Teimourzadeh K, Shiri J. Modeling of dissolved oxygen in river water using artificial intelligence techniques. J Environ Inform 2013;22(2):92–101.

[[31]] Li W, Wu H, Zhu N, Jiang Y, Tan J, Guo Y. Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU). Inf Process Agric 2020;8 (1):185–93.

[[32]] Ta X, Wei Y. Research on a dissolved oxygen prediction method for recirculating aquaculture systems based on a convolution neural network. Comput Electron Agric 2018;145:302–10.

[[33]] Mandal S, Debnath M, Ray S, Ghosh PB, Roy M, Ray S. Dynamic modelling of dissolved oxygen in the creeks of Sagar island, Hooghly–Matla estuarine system, West Bengal, India. Appl Math Model 2012;36(12):5952–63.

[[34]] Liu H, Yang R, Duan Z. Wind speed forecasting using a new multi-factor fusion and multi-resolution ensemble model with real-time decomposition and adaptive error correction. Energy Convers Manage 2020;217:112995.

[[35]] Liu H, Yang R, Wang T, Zhang L. A hybrid neural network model for short-term wind speed forecasting based on decomposition, multi-learner ensemble, and adaptive multiple error corrections. Renew Energy 2021;165:573–94.

[[36]] Zounemat-Kermani M, Seo Y, Kim S, Ghorbani MA, Samadianfard S, Naghshara S, et al. Can decomposition approaches always enhance soft computing models? Predicting the dissolved oxygen concentration in the St. Johns River, Florida. Appl Sci 2019;9(12):2534.

[[37]] Gilles J. Empirical wavelet transform. IEEE Trans Signal Process 2013;61 (16):3999–4010.

[[38]] Zhu JJ, Kang L, Anderson PR. Predicting influent biochemical oxygen demand: balancing energy demand and risk management. Water Res 2018;128:304–13.

[[39]] Kisi O, Alizamir M, Gorgij AD. Dissolved oxygen prediction using a new ensemble method. Environ Sci Pollut Res Int 2020;27(9):9589–603.

[[40]] Cao W, Huan J, Liu C, Qin Y, Wu F. A combined model of dissolved oxygen prediction in the pond based on multiple-factor analysis and multi-scale feature extraction. Aquacult Eng 2019;84:50–9.

[[41]] Chatfield C, Weigend AS. Time series prediction: forecasting the future and understanding the past: Neil A. Gershenfeld and Andreas S. Weigend, 1994, ‘The future of time series’, in: A.S. Weigend and N.A. Gershenfeld, eds., (Addison-Wesley, Reading, MA), 1-70. Int J Forecast 1994;10(1):161–3.

[[42]] Chatfield C. The future of the time-series forecasting. Int J Forecast 1988;4 (3):411–9.

[[43]] Hawkins S, He H, Williams G, Baxter R. Outlier detection using replicator neural networks. In: Proceedings of International Conference on Data Warehousing and Knowledge Discovery; Kinsdale, Ireland. Berlin: Springer; 2002. p. 170–80.

[[44]] Hu J, Wang J, Zhang X, Fu Z. Research status and development trends of information technologies in aquacultures. Nongye Jixie Xuebao 2015;46 (7):251–63.

[[45]] Ip WC, Hu BQ, Wong H, Xia J. Applications of grey relational method to river environment quality evaluation in China. J Hydrol 2009;379(3–4):284–90.

[[46]] Valentini G, Dietterich TG. Bias-variance analysis of support vector machines for the development of SVM-based ensemble methods. J Mach Learn Res 2004;5:725–75.

[[47]] Nash JE, Sutcliffe JV. River flow forecasting through conceptual models part I— a discussion of principles. J Hydrol 1970;10(3):282–90.

[[48]] Knoben WJM, Freer JE, Woods RA. Inherent benchmark or not? Comparing Nash–Sutcliffe and Kling–Gupta efficiency scores. Hydrol Earth Syst Sci 2019;23(10):4323–31.