Abstract
Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Allawi MF, Jaafar O, Hamzah FM et al (2018) Reservoir inflow forecasting with a modified coactive neuro-fuzzy inference system : a case study for a semi-arid region. Theor Appl Climatol 134:545–563
ARSO (2019a) Klimatološka povprečja 1981–2010. http://www.meteo.si/met/sl/climate/tables/n-ormals_81_10/. Accessed 24 May 2019
ARSO (2019b) Arhiv hidroloških podatkov. Arhiv površinskih voda. http://vode.arso.gov.si/hi-darhiv/pov_arhiv_tab.php. Accessed 24 May 2019
Badrzadeh H, Sarukkalige R, Jayawardena AW (2016) Improving Ann-based short-term and long-term seasonal river flow forecasting with signal processing techniques. River Res Appl 32:245–256
Bai Y, Chen Z, Xie J et al (2016a) Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models. J Hydrol 532:193–206
Bai Y, Xie J, Wang X et al (2016b) Model fusion approach for monthly reservoir inflow forecasting. J Hydroinf 18:634–650
Bat M, Dolinar M, Frantar P, et al (2008) Water balance of Slovenia 1971–2000. Ljubljana, p 119
Bengio Y, Lamblin P, Popovici D, et al (2006) Greedy layer-wise training of deep networks. In: NIPS’06 proceedings of the 19th international conference on neural information processing systems. Canada, pp 153-160
Costabile P, Macchione F (2015) Enhancing river model set-up for 2-D dynamic flood modelling. Environ Model Softw 67:89–107
CTG (2019) China Three Gorges corporation. https://www.ctg.com.cn/english/. Accessed 15 Mar 2019
Devia GK, Ganasri BP, Dwarakish GS (2015) A review on hydrological models. Aquatic Procedia 4:1001–1007
Gers FA, Schmidhuber J, Cummins F (1999) Learning to forget: continual predivtion with LSTM. In: Proc. ICANN’99 Int. Conf. On Arti cial neural networks, Edinburgh, Scotland. London, UK, pp 850-855
Gupta HV, Kling H, Yilmaz KK et al (2009) Decomposition of the mean squared error and NSE performance criteria : implications for improving hydrological modelling. J Hydrol 377:80–91
Hinton GE, Osindero S (2006) A fast learning algorithm for deep belief nets. Neural Comput 18:1527–1554
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(80):504–507
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
Humphrey GB, Gibbs MS, Dandy GC et al (2016) A hybrid approach to monthly streamflow forecasting : integrating hydrological model outputs into a Bayesian artificial neural network. J Hydrol 540:623–640
Islam MMM, Hofstra N, Sokolova E (2018) Modelling the present and future water level and discharge of the tidal Betna River. Geosciences 8:271
Jothiprakash V, Kote AS (2011) Effect of pruning and smoothing while using M5 model tree technique for reservoir inflow prediction. J Hydrol Eng 16:563–574
Juston J, Seibert J, Johansson P (2009) Temporal sampling strategies and uncertainty in calibrating a conceptual hydrological model for a small boreal catchment. Hydrol Process 23(21):3093–3109
Li C, Bai Y, Zeng B (2016) Deep feature learning architectures for daily reservoir inflow forecasting. Water Resour Manag 30(14):5145–5161
Long JY, Sun Z, Pardalos PM et al (2019) A hybrid multi-objective genetic local search algorithm for the prize-collecting vehicle routing problem. Inf Sci 478:40–61
Mosavi A, Ozturk P, Chau K (2018) Flood prediction using machine learning models: literature review. Water 10:1536
Myronidis D, Ioannou K, Fotakis D et al (2018) Streamflow and hydrological drought trend analysis and forecasting in Cyprus. Water Resour Manag 32(5):1759–1776
Perrin C, Oudin L, Andreassian V et al (2007) Impact of limited streamflow data on the efficiency and the parameters of rainfall-runoff models. Hydrol Sci J 52:131–151
Pool S, Vis M, Seibert J et al (2018) Evaluating model performance : towards a non- parametric variant of the Kling-Gupta efficiency Kling-Gupta efficiency. Hydrol Sci J 63:1941–1953
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(8):2907–2923
Qiao W, Lu H, Zhou G et al (2020) A hybrid algorithm for carbon dioxide emissions forecasting based on improved lion swarm optimizer. J Clean Prod 244:118612
Sazli MH (2006) A brief review of feed-forward neural networks. Commun Fac Sci Univ Ankara Ser 50:11–17
Sodnik J, Mikoš M (2006) Estimation of magnitudes of debris flows in selected torrential watersheds in Slovenia. Acta geogrpahica Slov 46:93–123
Srivastava S, Lessmann S (2018) A comparative study of LSTM neural networks in forecasting day-ahead global horizontal irradiance with satellite data. Sol Energy 162:232–247
Su B, Lu S (2017) Accurate recognition of words in scenes without character segmentation using. Pattern Recogn 63:397–405
Su J, Li C, Zeng Q et al (2019) A green closed-loop supply chain coordination mechanism based on third-party recycling. Sustainability 11:5335
Sun L, Nistor I, Seidou O (2015) Streamflow data assimilation in SWAT model using extended Kalman filter. J Hydrol 531:671–684
The MathWorks (2018) MATLAB release 2018a. Natick, Massachusetts, USA
Vincent P, Larochelle H, Bengio Y, et al (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25 th international conference on machine learning. Helsinki, Finland, pp 1096–1103
Wang H, Li G, Wang G et al (2017) Deep learning based ensemble approach for probabilistic wind power forecasting. Appl Energy 188:56–70
Wang W, Chau K, Xu D et al (2015) Improving forecasting accuracy of annual runoff time series using ARIMA based on EEMD decomposition. Water Resour Manag 29(8):2655–2675
Wei N, Li C, Peng X et al (2019) Daily natural gas consumption forecasting via the application of a novel hybrid model. Appl Energy 250:358–368
Xie J, Wang X, Liu Y et al (2018) Autoencoder-based deep belief regression network for air particulate matter concentration forecasting. J Intell Fuzzy Syst 34:3475–3486
Xu X, Zhang X, Fang H et al (2017) A real-time probabilistic channel flood-forecasting model based on the Bayesian particle filter approach. Environ Model Softw 88:151–167
Yang T, Asanjan AA, Welles E et al (2017a) Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information. Water Resour Res 53:2786–2812
Yang Y, Zhang M, Zhu L, Liu W, Han J, Yang Y (2017b) Infuence of large reservoir operation on water-levels and flows in reaches below dam: case study of the three gorges reservoir. Sci Rep 7:15640
Yuan X, Chen C, Lei X et al (2018) Monthly runoff forecasting based on LSTM–ALO model. Stoch Environ Res Risk Assess 32:2199–2212
Zhang X, Moynihan GP, Ernest ANS et al (2018) Evaluation of the benefits of using a backward chaining decision support expert system for local flood forecasting and warning. Expert Syst 35:e12261
Zhao J, Xu J, Xie X, Lu H (2016) Drought monitoring based on TIGGE and distributed hydrological model in Huaihe River basin, China. Sci Total Environ 553:358–365
Zhao X, Chen X, Xu Y et al (2017) An EMD-based chaotic least squares support vector machine hybrid model for annual runoff forecasting. Water 9:153
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China (71801044), the international cooperation of the Ministry of Science and Technology of China (12-24: bilateral project between China and Slovenia entitled: “Evaluation of intelligent learning techniques for prediction of hydrological data: useful case studies in China and Slovenia”), and the Natural Science Foundation of Chongqing (cstc2018jcyjAX0436). This work was also partially supported by the Slovenian Research Agency (ARRS) through grants J2-7322 and P2-0180.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
No conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
ESM 1
(PDF 720 kb)
Rights and permissions
About this article
Cite this article
Bai, Y., Bezak, N., Sapač, K. et al. Short-Term Streamflow Forecasting Using the Feature-Enhanced Regression Model. Water Resour Manage 33, 4783–4797 (2019). https://doi.org/10.1007/s11269-019-02399-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11269-019-02399-1