Skip to main content
SpringerLink
Log in

A Novel Hybrid Decompose-Ensemble Strategy with a VMD-BPNN Approach for Daily Streamflow Estimating

  • Published:
Water Resources Management Aims and scope Submit manuscript

Abstract

Streamflow estimation is highly significant for water resource management. In this work, we improve the accuracy and stability of streamflow estimation through a novel hybrid decompose-ensemble model that employs variational mode decomposition (VMD) and back-propagation neural networks (BPNN). First, the latest decomposition algorithm, namely, VMD, was used to extract multiscale features that were subsequently learned and ensembled by the BPNN model to obtain the final estimate streamflow results. The historical daily streamflow series of Laoyukou and Wushan hydrological stations in China were analysed by VMD-BPNN, by a single GBRT and BPNN model, ensemble empirical mode decomposition (EEMD) models. The results confirmed that the VMD outperformed a single-estimation model without any decomposition and EEMD-based models; moreover, ensemble estimations using the BPNN model development technique were consistently better than a general summation method. The VMD-BPNN model’s estimation performance was superior to that of five other models at the Wushan station (GBRT, BPNN, EEMD-BPNN-SUM, VMD-BPNN-SUM, and EEMD-BPNN) using evaluation criteria of the root-mean-square error (RMSE = 2.62 m3/s), the Nash–Sutcliffe efficiency coefficient (NSE = 0. 9792) and the mean absolute error (MAE = 1.38 m3/s). The proposed model also had a better performance in estimating higher-magnitude flows with a low criterion for MAE. Therefore, the hybrid VMD-BPNN model could be applied as a promising approach for short-term streamflow estimating.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Data Availability

The data used to support the findings of this study are available from the corresponding author upon request.

References

  • Barge J, Sharif H (2016) An ensemble empirical mode decomposition, self-organizing map, and linear genetic programming approach for forecasting river streamflow. Water 8(6):247

    Article  Google Scholar 

  • Boyd S, Parikh N, Chu E, Peleato B, Eckstein J (2010) Distributed optimization and statistical learning via the alternating direction method of multipliers. Found Trends Mach Learn 3(1):1–122

    Article  Google Scholar 

  • Chiamsathit C, Adeloye AJ, Bankaruswamy S (2016) Inflow forecasting using artificial neural networks for reservoir operation. P Int Assoc Hydrol Sci 373:209–214

    Google Scholar 

  • Cigizoglu HK, Kisi O (2005) Flow prediction by three back propagation techniques using k-fold partitioning of neural network training data. Nord Hydrol 36:49–64

    Article  Google Scholar 

  • Dai HC, Macbeth C (1997) Effects of learning parameters on learning procedure and performance of a BPNN. Neural Netw 10(8):1505–1521

    Article  Google Scholar 

  • Dehghani M, Saghafian B, Nasiri Saleh F, Farokhnia A, Noori R (2014) Uncertainty analysis of streamflow drought forecast using artificial neural networks and Monte-Carlo simulation. Int J Climatol 34:1169–1180

    Article  Google Scholar 

  • Dopke J, Fritsche U, Pierdzioch C (2017) Predicting recessions with boosted regression trees. Int J Forecasting 33:745–759

    Article  Google Scholar 

  • Dragomiretskiy K, Zosso D (2014) Variational mode decomposition. IEEE T Signal Proces 62(3):531–544

    Article  Google Scholar 

  • Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann Stat 29(5):1189–1232

    Article  Google Scholar 

  • Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data an 38(4):367–378

    Article  Google Scholar 

  • Gamboa J, Silva A, Araujo I et al (2020) Validation of the rapid detection approach for enhancing the electronic nose systems performance, using different deep learning models and support vector machines. Sensor Actuat B-Chem 327:1–7

    Google Scholar 

  • Guo J, Zhou JZ, Qin H, Zou Q (2011) Monthly streamflow forecasting based on improved support vector machine model. Expert Syst Appl 38:13073–13081

    Article  Google Scholar 

  • Guo ZH, Zhao WG, Lu HY, Wang JZ (2012) Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model. Renew Energy 37:241–249

    Article  Google Scholar 

  • He XX, Luo JG, Zuo GG, Xie JC (2019) Daily runoff forecasting using a hybrid model based on variational mode decomposition and deep neural networks. Water Resour Manage 33(4):1571–1590

    Article  Google Scholar 

  • He XX, Luo JG, Li P, Zuo GG, Xie JC (2020) A hybrid model based on variational mode decomposition and gradient boosting regression tree for monthly runoff forecasting. Water Resour Manage 34(2):865–884

    Article  Google Scholar 

  • Hong SG, Oh SK, Kim MS, Lee JJ (2001) Nonlinear time series modelling and prediction using Gaussian RBF network with evolutionary structure optimization. Electron Lett 37:639–640

    Article  Google Scholar 

  • Hsu KL, Gupta HV, Gao X, Sorooshian S, Imam B (2002) Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis. Water Resour Res 38(12):38–1–38–17

  • Hu H, Zhang JF, Li T (2020) A comparative study of vmd-based hybrid forecasting model for nonstationary daily streamflow time series. Complexity 2020(2):1–21

    Google Scholar 

  • Huang NE, Shen Z, Long SR, Wu MC, Shih EH, Zheng Q, Tung CC, Liu HH (1998) The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis. Proc R Soc London Ser A 454(1971):903–995

    Article  Google Scholar 

  • Huang NE, Wu Z (2008) A review on Hilbert-Huang transform: Method and its applications to geophysical studies. Rev Geophys 46(2)

  • Huang SZ, Chang J, Huang Q, Chen Y (2014) Monthly streamflow prediction using modified EMD-based support vector machine. J Hydrol 511:764–775

    Article  Google Scholar 

  • Johnson NE, Ianiuk O, Cazap D, Liu L, Starobin D, Dobler G, Ghandeharia M (2017) Patterns of waste generation: A gradient boosting model for short-term waste prediction in New York city. Waste Manage 62:3–11

    Article  Google Scholar 

  • Kasiviswanathan KS, He J, Sudheer KP, Tay JH (2016) Potential application of wavelet neural network ensemble to forecast streamflow for flood management. J Hydrol 536:161–173

    Article  Google Scholar 

  • Kirsta YB, Lovtskaya OV (2021) Good-quality long-term forecast of spring-summer flood runoff for mountain rivers. Water Resour Manage 35(3):811–825

    Article  Google Scholar 

  • Kisi O (2015) Streamflow forecasting and estimation using least square support vector regression and adaptive neuro-fuzzy embedded fuzzy c-means clustering. Water Resour Manage 29(14):5109–5127

    Article  Google Scholar 

  • Kratzert F, Klotz D, Brenner C, Schulz K, Herrnegger M (2018) Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks. Hydrol Earth Syst Sci 22:6005–6022

    Article  Google Scholar 

  • Längkvist M, Karlsson L, Loutfi A (2014) A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognit Lett 42(6):11–24

    Article  Google Scholar 

  • Li C, Liang M (2011) Extraction of oil debris signature using integral enhanced empirical mode decomposition and correlated reconstruction. Meas Sci Technol 22(8):85701–85710

    Article  Google Scholar 

  • Li X, Zhao L, Wei L, Yang M, Wu F, Zhuang Y, Ling HB, Wang JD (2016) Deepsaliency: Multi-task deep neural network model for salient object detection. IEEE T Image Process 25(8):3919–3930

    Article  Google Scholar 

  • Lin JY, Cheng CT, Chau KW (2006) Using support vector machines for long-term discharge prediction. Hydrolog Sci J 51(4):599–612

    Article  Google Scholar 

  • Liu C, Zhu L, Ni C (2018) Chatter detection in milling process based on VMD and energy entropy. Mech Syst Signal Pr 105:169–182

    Article  Google Scholar 

  • Liu Y, Brown J, Demargne J, Seo DJ (2011) A wavelet-based approach to assessing timing errors in hydrologic predictions. J Hydrol 397:210–224

    Article  Google Scholar 

  • Liu Y, Wu J, Liu Y, Hu BX, Hao Y, Huo X, et al. (2015) Analyzing effects of climate change on streamflow in a glacier mountain catchment using an arma model. Quatern Int 358(Feb 9):137–145

  • Lohani AK, Goel NK, Bhatia KKS (2014) Improving real time flood forecasting using fuzzy inference system. J Hydrol 509:25–41

    Article  Google Scholar 

  • Luchetta A, Manetti S (2003) A real time hydrological forecasting system using a fuzzy clustering approach. Comput Geosci 29:1111–1117

    Article  Google Scholar 

  • Luo X, Xu Y, Xu J (2011) Regularized back-propagation neural network for rainfall-runoff modeling. International Conference on Network Computing & Information Security. IEEE Comput Soc.

  • Ma N, Chen YP (1998) An ANN and wavelet transformation based method for short term load forecast. International Conference on Energy Management and Power Delivery. In: International Conferences 2:405–410

  • Maity R, Kashid SS (2011) Importance analysis of local and global climate inputs for basin-scale streamflow prediction. Water Resour Res 47:1–17

    Article  Google Scholar 

  • Mohanty S, Gupta KK, Raju KS (2018) Hurst based vibro-acoustic feature extraction of bearing using EMD and VMD. Measurement 117:200–220

    Article  Google Scholar 

  • Mutlu E, Chaubey I, Hexmoor H, Bajwa SG (2008) Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed. Hydrol Process 22:5097–5106

    Article  Google Scholar 

  • Nayak PC, Sudheer KP, Ramasastri KS (2005) Fuzzy computing based rainfallrunoff model for real time flood forecasting. Hydrol Process 19(4):955–968

    Article  Google Scholar 

  • Ning M, Yunping C (1998) An ANN and wavelet transformation based method for short term load forecast. International Conference on Energy Management & Power Delivery IEEE 405–410.

  • Niu M, Wang Y, Sun S, Li Y (2016) A novel hybrid decomposition-and-ensemble model based on ceemd and gwo for short-term pm2.5 concentration forecasting. Atmos Environ 134:168–180

    Article  Google Scholar 

  • Niu M, Hu Y, Sun S, Liu Y (2018) A novel hybrid decomposition-ensemble model based on VMD and HGWO for container throughput forecasting. Appl Math Model 57:163–178

    Article  Google Scholar 

  • Okkan U, Serbes ZA (2013) The combined use of wavelet transform and black box models in reservoir inflow modeling. J Hydrol Hydromech 61(2):112–119

    Article  Google Scholar 

  • Raman H, Sunilkumar N (1995) Multivariate modelling of water resources time series using artificial neural networks. Hydrol Sci J 40(2):145–163

    Article  Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Nature 323(2):318–362

    Google Scholar 

  • Sachindra DA et al (2019) Pros and cons of using wavelets in conjunction with genetic programming and generalised linear models in statistical downscaling of precipitation. Theor Appl Climatol 138(1/2):617–638

    Article  Google Scholar 

  • Shiri J, Kisi O (2010) Short-term and long-term streamflow forecasting using a wavelet and neuro-fuzzy conjunction model. J Hydrol 394(3–4):486–493

    Article  Google Scholar 

  • Sivakumar B, Berndtsson R (2010) Advances in Data-based Approaches for Hydrologic Modeling and Forecasting. World Scientific, Singapore

    Book  Google Scholar 

  • Taieb SB, Hyndman RJ (2014) A gradient boosting approach to the kaggle load forecasting competition. Int J Forecasting 30(2):382–394

    Article  Google Scholar 

  • Tian X, Negenborn RR, Van Overloop PJ, José MM, Sadowska A, Nick VDG (2017) Efficient multi-scenario model predictive control for water resources management with ensemble streamflow forecasts. Adv Water Resour 109:58–68

    Article  Google Scholar 

  • Wang XG, Tang Z, Tamura H, Ishii M (2004) A modified error function for the backpropagation algorithm. Neurocomputing 57:477–484

    Article  Google Scholar 

  • Wu ZH, Huang NE (2009) Ensenbol enpirical mode decomposition: A noise-assisted data analysis method. Adv Adap Data Anal 1:1–41

    Article  Google Scholar 

  • Yadav B et al (2016) Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: A case study in Neckar River, Germany. Measurement 92:433–445

    Article  Google Scholar 

  • Yang CC, Chen CS (2009) Application of integrated backpropagation network and self organizing map for flood forecasting. Hydrol Processes 23:1313–1323

    Article  Google Scholar 

  • Yaseen ZM, Kisi O, Demir V (2016) Enhancing long-term streamflow forecasting and predicting using periodicity data component: application of artificial intelligence. Water Resour Manage 30(12):4125–4151

    Article  Google Scholar 

  • Yonaba H, Anctil F, Fortin V (2010) Comparing sigmoid transfer functions for neural network multistep ahead streamflow forecasting. J Hydrol Eng 15(4):275–283

    Article  Google Scholar 

  • Zhang H, Chen Y, Ren G, Yang G (2008) The characteristics of precipitation variation of Weihe River Basin in Shaanxi Province during recent 50 years. Agri Res Arid Areas 26(4):236–242

    Google Scholar 

Download references

Funding

This research was supported financially by the National Natural Science Foundation of China (Grant No. 51609197), the State Key Laboratory Base of Eco-hydraulic Engineering in Arid Area, China (Grant No. 2017ZZKT-5), CAS “Light of West China” Program (Grant No. XAB2016AW06) and the Xian Science and Technology Program (Grant No. SF1335).

Author information

Authors and Affiliations

  1. State Key Laboratory Base of Eco-Hydraulic Engineering in Arid Areas, School of Water Resources and Hydropower, Xi’an University of Technology, Xi’an, 710048, China

    Hui Hu, Jianfeng Zhang & Tao Li

Authors
  1. Hui Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianfeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

H. Hu and T. Li designed all experiments. H. Hu collected and preprocessed the data, and conduced all experiments, and analyzed the results. H. Hu wrote the first draft of the manuscript. T. Li and J. Zhang edited the manuscript.

Corresponding author

Correspondence to Tao Li.

Ethics declarations

Conflict of Interest

The authors declare no conflicts of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hu, H., Zhang, J. & Li, T. A Novel Hybrid Decompose-Ensemble Strategy with a VMD-BPNN Approach for Daily Streamflow Estimating. Water Resour Manage 35, 5119–5138 (2021). https://doi.org/10.1007/s11269-021-02990-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11269-021-02990-5

Keywords

Search

Navigation