Skip to main content
SpringerLink
Log in

Scale Effects of the Monthly Streamflow Prediction Using a State-of-the-art Deep Learning Model

  • Published:
Water Resources Management Aims and scope Submit manuscript

Abstract

The accurate prediction of monthly streamflow is important in sustainable water resources planning and management. There is a growing interest in the development of deep learning models for monthly streamflow prediction with the advances in computer sciences. This study aims at investigating the spatial and temporal scale effects on predictive performance when using the deep learning model for monthly streamflow prediction. To achieve this goal, a hybrid deep learning prediction model combining Convolutional Neural Network and Gated Recurrent Unit (i.e., CNN-GRU) was first proposed and applied to many watersheds with varying hydroclimatic characteristics around globe. The Nash–Sutcliffe efficiency coefficient (NSE) and mean relative error (MRE) are used as criteria to evaluate the predictive performance. The results show that the deep learning model is more suitable for monthly streamflow predictions on watersheds with large drainage areas. The drainage area of 3,000 km2 can be considered as a threshold for the predictive performance. The median NSE increases from 0.31 to 0.40, while the median MRE decreases from 53.2% to 46.2% for watersheds with areas larger than 3,000 km2 compared with those with areas smaller than 3,000 km2. In addition, the predictive performance tends to get better with the extension of a training period for the model. When the length of the training period increases stepwise from 10 to 50 years, there is a large increase in NSE (from 0.28 to 0.40) and a moderate decrease in MRE (from 50.3% to 46.2%) for watersheds with areas larger than 3,000 km2. Similar changes can also be found for watersheds smaller than 3,000 km2. The 25- to 35-year training period is the minimum length to obtain a stable predictive performance for most watersheds.

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

Similar content being viewed by others

Abbreviations

ANN:

Artificial neural network

KNN:

K-nearest neighbors

ANFIS:

Adaptive neuro-fuzzy inference system

GP:

Genetic programming

ELM:

Extreme learning machine

SVM or SVR:

Support vector machine or regression

RNN:

Recurrent neural network

LSTM:

Long short-term memory

GRU:

Gated Recurrent Unit

CNN:

Convolutional Neural Network

VMD:

Variational mode decomposition

NSE:

Nash-Sutcliffe efficiency coefficient

MRE:

Mean relative error

R2 :

Coefficient of determination

Qmean:

Monthly mean streamflow

Cv:

Coefficient of variation for monthly streamflow

ACF(1):

One-month-lag autocorrelation function of streamflow

References

  • Ai P, Song YH, Xiong CS, Chen BB, Yue ZX (2022) A novel medium- and long-term runoff combined forecasting model based on different lag periods. J Hydroinform 24(2):367–387

  • Alizadeh B, Bafti AG, Kamangir H, Zhang Y, Wright DB, Franz KJ (2021) A novel attention-based LSTM cell post-processor coupled with bayesian optimization for streamflow prediction. J Hydrol 601:126526

    Article  Google Scholar 

  • Arsenault R, Bazile R, Dallaire CO, Brissette F (2016) CANOPEX: A Canadian hydrometeorological watershed database. Hydrol Process 30:2734–2736

    Article  Google Scholar 

  • Bloschl G, Sivapalan M (1995) Scale issues in hydrological modeling - A review. Hydrol Process 9:251–290

    Article  Google Scholar 

  • Chen L, Chen SB, Li S, Shen ZY (2019) Temporal and spatial scaling effects of parameter sensitivity in relation to non-point source pollution simulation. J Hydrol 571:36–49

    Article  Google Scholar 

  • Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. Comput Sci 1724–1734

    Google Scholar 

  • Chu HB, Wei JH, Qiu J (2018) Monthly streamflow forecasting using EEMD-Lasso-DBN method based on multi-scale predictors selection. Water 10(10):1486

    Article  Google Scholar 

  • Cirstea RG, Micu DV, Muresan GM, Guo CJ, Yang B (2018) Correlated time series forecasting using multi-task deep neural networks. Cikm'18: Proceedings of the 27th Acm International Conference on Information and Knowledge Management 1527–1530

  • Fang K, Kifer D, Lawson K, Shen CP (2020) Evaluating the potential and challenges of an uncertainty quantification method for long short-term memory models for soil moisture predictions. Water Resour Res 56(12):e2020WR028095

    Article  Google Scholar 

  • Feng DP, Fang K, Shen CP (2020a) Enhancing streamflow forecast and extracting insights using long-short term memory networks with data integration at continental scales. Water Resour Res 56(9):e2019WR026793

    Article  Google Scholar 

  • Feng ZK, Niu WJ, Tang ZY, Jiang ZQ, Xu Y, Liu Y, Zhang HR (2020b) Monthly runoff time series prediction by variational mode decomposition and support vector machine based on quantum-behaved particle swarm optimization. J Hydrol 583:124627

    Article  Google Scholar 

  • Fu R, Zhang Z, Li L, Ieee (2016) Using LSTM and GRU neural network methods for traffic flow prediction. 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (Yac) 324–328

  • Gao S, Huang YF, Zhang S, Han JC, Wang GQ, Zhang MX, Lin QS (2020) Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. J Hydrol 589:125188

    Article  Google Scholar 

  • Gauch M, Mai J, Lin J (2021) The proper care and feeding of CAMELS: How limited training data affects streamflow prediction. Environ Model Softw 135:104926

    Article  Google Scholar 

  • Gers FA, Schmidhuber J, Cummins F (2000) Learning to forget: Continual prediction with LSTM. Neural Comput 12:2451–2471

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Ha S, Choi S, Ieee (2016) Convolutional neural networks for human activity recognition using multiple accelerometer and gyroscope sensors. Int Joint Conf Neural Netw (IJCNN) 381–388

  • Ha S, Liu DR, Mu L (2021) Prediction of Yangtze River streamflow based on deep learning neural network with El Nino-Southern Oscillation. Sci Rep 11(1):11738

    Article  Google Scholar 

  • He RR, Chen YF, Huang Q, Pan ZW, Liu Y (2020a) Predictability of monthly streamflow time series and its relationship with basin characteristics: an empirical study based on the MOPEX basins. Water Resour Manag 34:4991–5007

    Article  Google Scholar 

  • He X, Luo J, Zuo G, Xie J (2019) Daily runoff forecasting using a hybrid model based on variational mode decomposition and deep neural networks. Water Resour Manag 33:1571–1590

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Herbert ZC, Asghar Z, Oroza CA (2021) Long-term reservoir inflow forecasts: Enhanced water supply and inflow volume accuracy using deep learning. J Hydrol 601:126676

    Article  Google Scholar 

  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780

    Article  Google Scholar 

  • Hu CH, Wu Q, Li H, Jian SQ, Li N, Lou ZZ (2018) Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water 10(11):1543

    Article  Google Scholar 

  • Kashani MH, Inyurt S, Golabi MR, AmirRahmani M, Band SS (2022) Estimation of solar radiation by joint application of phase space reconstruction and a hybrid neural network model. Theoret Appl Climatol 147:1725–1742

    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 Manag 29:5109–5127

    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 

  • Kumar DN, Raju KS, Sathish T (2004) River flow forecasting using recurrent neural networks. Water Resour Manag 18:143–161

    Article  Google Scholar 

  • LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    Article  Google Scholar 

  • LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551

    Article  Google Scholar 

  • Liu JJ, Yuan X, Zeng JH, Jiao Y, Li Y, Zhong LH, Yao L (2022) Ensemble streamflow forecasting over a cascade reservoir catchment with integrated hydrometeorological modeling and machine learning. Hydrol Earth Syst Sci 26:265–278

    Article  Google Scholar 

  • Ma K, Feng DP, Lawson K, Tsai WP, Liang CA, Huang XR, Sharma ASO, Shen CP (2021) Transferring hydrologic data across continents - leveraging data-rich regions to improve hydrologic prediction in data-sparse regions. Water Resour Res 57(5):e2020WR028600

    Article  Google Scholar 

  • Madaeni F, Chokmani K, Lhissou R, Gauthier Y, Tolszczuk-Leclerc S (2022) Convolutional neural network and long short-term memory models for ice-jam predictions. Cryosphere 16:1447–1468

    Article  Google Scholar 

  • Mehr AD, Ghadimi S, Marttila H, Haghighi AT (2022) A new evolutionary time series model for streamflow forecasting in boreal lake-river systems. Theoret Appl Climatol 148:255–268

    Article  Google Scholar 

  • Merz R, Parajka J, Bloeschl G (2009) Scale effects in conceptual hydrological modeling. Water Resour Res 45:W09405

    Google Scholar 

  • Milly PCD, Dunne KA, Vecchia AV (2005) Global pattern of trends in streamflow and water availability in a changing climate. Nature 438:347–350

    Article  Google Scholar 

  • Modaresi F, Araghinejad S, Ebrahimi K (2018) A Comparative assessment of artificial neural network, generalized regression neural network, least-square support vector regression, and k-nearest neighbor regression for monthly streamflow forecasting in linear and nonlinear conditions. Water Resour Manag 32:243–258

    Article  Google Scholar 

  • Mohammadi B, Linh NTT, Pham QB, Ahmed AN, Vojtekova J, Guan YQ, Abba SI, El-Shafie A (2020) Adaptive neuro-fuzzy inference system coupled with shuffled frog leaping algorithm for predicting river streamflow time series. Hydrol Sci J 65:1738–1751

    Article  Google Scholar 

  • Morovati K, Nakhaei P, Tian FQ, Tudaji M, Hou SY (2021) A Machine learning framework to predict reverse flow and water level: A case study of Tonle Sap Lake. J Hydrol 603:127168

    Article  Google Scholar 

  • Ni LL, Wang D, Wu JF, Wang YK, Tao YW, Zhang JY, Liu JF (2020) Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model. J Hydrol 586:124901

    Article  Google Scholar 

  • Niu WJ, Feng ZK, Chen YB, Zhang HR, Cheng CT (2020) Annual streamflow time series prediction using extreme learning machine based on gravitational search algorithm and variational mode decomposition. J Hydrol Eng 25(5):04020008

    Article  Google Scholar 

  • Niu WJ, Feng ZK, Zeng M, Feng BF, Min YW, Cheng CT, Zhou JZ (2019) Forecasting reservoir monthly runoff via ensemble empirical mode decomposition and extreme learning machine optimized by an improved gravitational search algorithm. Appl Soft Comput 82:105589

    Article  Google Scholar 

  • Nourani V, Baghanam AH, Adamowski J, Kisi O (2014) Applications of hybrid wavelet-Artificial Intelligence models in hydrology: A review. J Hydrol 514:358–377

    Article  Google Scholar 

  • Oquab M, Bottou L, Laptev I, Sivic J, Ieee (2014) Learning and transferring mid-level image representations using convolutional neural networks. 27th IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 1717–1724

  • Parisouj P, Mohebzadeh H, Lee T (2020) Employing machine learning algorithms for streamflow prediction: a case study of four river basins with different climatic zones in the United States. Water Resour Manag 34:4113–4131

    Article  Google Scholar 

  • Poul AK, Shourian M, Ebrahimi H (2019) A comparative study of MLR, KNN, ANN and ANFIS models with wavelet transform in monthly stream flow prediction. Water Resour Manag 33:2907–2923

    Article  Google Scholar 

  • Qu JH, Ren K, Shi XY (2021) Binary grey wolf optimization-regularized extreme learning machine wrapper coupled with the boruta algorithm for monthly streamflow forecasting. Water Resour Manag 35:1029–1045

    Article  Google Scholar 

  • Schmidhuber J (2015) Deep learning in neural networks: An overview. Neural Netw 61:85–117

    Article  Google Scholar 

  • Shortridge JE, Guikema SD, Zaitchik BF (2016) Machine learning methods for empirical streamflow simulation: a comparison of model accuracy, interpretability, and uncertainty in seasonal watersheds. Hydrol Earth Syst Sci 20:2611–2628

    Article  Google Scholar 

  • Shu XS, Ding W, Peng Y, Wang ZR, Wu J, Li M (2021) Monthly streamflow forecasting using convolutional neural network. Water Resour Manag 35(15):5089–5104

    Article  Google Scholar 

  • Slater LJ, Villarini G, Bradley AA, Vecchi GA (2019) A dynamical statistical framework for seasonal streamflow forecasting in an agricultural watershed. Clim Dyn 53:7429–7445

    Article  Google Scholar 

  • Sudheer C, Maheswaran R, Panigrahi B, Mathur S (2014) A hybrid SVM-PSO model for forecasting monthly streamflow. Neural Comput Appl 24:1381–1389

    Article  Google Scholar 

  • Sun XP, Wang J, She MFH, Kong LX (2014) Sparse representation with multi-manifold analysis for texture classification from few training images. Image vis Comput 32:835–846

    Article  Google Scholar 

  • Sun ZL, Long D, Yang WT, Li XY, Pan Y (2020) Reconstruction of GRACE Data on Changes in Total Water Storage Over the Global Land Surface and 60 Basins. Water Resour Res 56(4):e2019WR026250

    Article  Google Scholar 

  • Tao YM, Gao XG, Hsu KL, Sorooshian S, Ihler A (2016) A deep neural network modeling framework to reduce bias in satellite precipitation products. J Hydrometeorol 17:931–945

    Article  Google Scholar 

  • Tennant C, Larsen L, Bellugi D, Moges E, Zhang L, Ma HX (2020) The utility of information flow in formulating discharge forecast models: a case study from an arid snow-dominated catchment. Water Resour Res 56(8):e2019WR024908

    Article  Google Scholar 

  • Tibshirani R (1996) Regression shrinkage and selection via the Lasso. J R Stat Soc Ser B-Methodol 58(1):267–288

    Google Scholar 

  • Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476:433–441

    Article  Google Scholar 

  • Wang GX, Liu GS, Liu LA (2012) Spatial scale effect on seasonal streamflows in permafrost catchments on the Qinghai-Tibet Plateau. Hydrol Process 26:973–984

    Article  Google Scholar 

  • Wang J, Peng B, Zhang XJ (2018) Using a stacked residual LSTM model for sentiment intensity prediction. Neurocomputing 322:93–101

    Article  Google Scholar 

  • Wang QJ, Robertson DE, Chiew FHS (2009a) A Bayesian joint probability modeling approach for seasonal forecasting of streamflows at multiple sites. Water Resour Res 45:W05407

    Google Scholar 

  • Wang WC, Chau KW, Cheng CT, Qiu L (2009b) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J Hydrol 374:294–306

    Article  Google Scholar 

  • Wilson AC, Roelofs R, Stern M, Srebro N, Recht B (2017) The marginal value of adaptive gradient methods in machine learning. Adv Neural Inf Process Syst 30:4148–4158

    Google Scholar 

  • Wu CL, Chau KW (2010) Data-driven models for monthly streamflow time series prediction. Eng Appl Artif Intell 23:1350–1367

    Article  Google Scholar 

  • Wu CL, Chau KW, Li YS (2009) Predicting monthly streamflow using data-driven models coupled with data-preprocessing techniques. Water Resour Res 45:W08432

    Article  Google Scholar 

  • Xiang ZR, Yan J, Demir I (2020) A Rainfall-Runoff Model With LSTM-Based Sequence-to-Sequence Learning. Water Resour Res 56(1):e2019WR025326

  • Xie T, Zhang G, Hou JW, Xie JC, Lv M, Liu FC (2019) Hybrid forecasting model for non-stationary daily runoff series: A case study in the Han River Basin, China. J Hydrol 577:123915

    Article  Google Scholar 

  • Yang TT, Asanjan AA, Welles E, Gao XG, Sorooshian S, Liu XM (2017) Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information. Water Resour Res 53:2786–2812

    Article  Google Scholar 

  • Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks ? Adv Neural Inf Process Syst 27(Nips 2014):27

  • Young PC, Beven KJ (1994) Data-based mechanistic modeling and the rainfall-flow nonlinearity. Environmetrics 5:335–363

    Article  Google Scholar 

  • Yu JX, Zhang X, Xu LL, Dong J, Zhangzhong LL (2021) A hybrid CNN-GRU model for predicting soil moisture in maize root zone. Agric Water Manag 245:106649

    Article  Google Scholar 

  • Yuan XH, Chen C, Lei XH, Yuan YB, Adnan RM (2018) Monthly runoff forecasting based on LSTM-ALO model. Stoch Env Res Risk Assess 32:2199–2212

    Article  Google Scholar 

  • Zhang XL, Peng Y, Zhang C, Wang BD (2015) Are hybrid models integrated with data preprocessing techniques suitable for monthly streamflow forecasting? Some experiment evidences. J Hydrol 530:137–152

    Article  Google Scholar 

  • Zhang YH, Ye AZ, Nguyen P, Analui B, Sorooshian S, Hsu KL (2021) Error characteristics and scale dependence of current satellite precipitation estimates products in hydrological modeling. Remote Sensing 13(16):3061

    Article  Google Scholar 

  • Zhao XH, Lv HF, Lv SJ, Sang YT, Wei YZ, Zhu XP (2021a) Enhancing robustness of monthly streamflow forecasting model using gated recurrent unit based on improved grey wolf optimizer. J Hydrol 601:126607

    Article  Google Scholar 

  • Zhao XH, Lv HF, Wei YZ, Lv SJ, Zhu XP (2021b) Streamflow forecasting via two types of predictive structure-based gated recurrent unit models. Water 13(1):91

    Article  Google Scholar 

  • Zheng JD, Cheng JS, Yang Y (2014) Partly ensemble empirical mode decomposition: An improved noise-assisted method for eliminating mode mixing. Signal Process 96:362–374

    Article  Google Scholar 

  • Zhu S, Zhou J, Ye L, Meng C (2016) Streamflow estimation by support vector machine coupled with different methods of time series decomposition in the upper reaches of Yangtze River, China. Environ Earth Sci 75(6):531

    Article  Google Scholar 

  • Zuo GG, Luo JG, Wang N, Lian YN, He XX (2020) Two-stage variational mode decomposition and support vector regression for streamflow forecasting. Hydrol Earth Syst Sci 24:5491–5518

    Article  Google Scholar 

Download references

Acknowledgements

This work was partially supported by the Natural Science Foundation of China (Grant No. 52079093), the Hubei Provincial Natural Science Foundation of China (Grant No. 2020CFA100), and the Overseas Expertise Introduction Project for Discipline Innovation (111 Project) funded by the Ministry of Education and State Administration of Foreign Experts Affairs, P. R. China (Grant No. B18037). Many thanks to Phil Busteed who helped to proofread the manuscript. The authors would also like to thank the anonymous reviewers and the editor for their comments, which have substantially improved the quality of this paper.

Author information

Authors and Affiliations

  1. State Key Laboratory of Water Resources and Hydropower Engineering Science, Wuhan University, Wuhan, 430072, China

    Wenxin Xu & Jie Chen

  2. Hubei Provincial Key Lab of Water System Science for Sponge City Construction, Wuhan University, Wuhan, China

    Wenxin Xu & Jie Chen

  3. USDA-ARS Grazinglands Research Lab, El Reno, OK, USA

    Xunchang J. Zhang

Authors
  1. Wenxin Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jie Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xunchang J. Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jie Chen.

Ethics declarations

Ethical Approval

Not applicable.

Consent to Participate

Not applicable.

Consent for Publication

All authors have duly consented to publish this manuscript.

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 6339 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, W., Chen, J. & Zhang, X.J. Scale Effects of the Monthly Streamflow Prediction Using a State-of-the-art Deep Learning Model. Water Resour Manage 36, 3609–3625 (2022). https://doi.org/10.1007/s11269-022-03216-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11269-022-03216-y

Keywords

Search

Navigation