Skip to main content
SpringerLink
Log in

Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting

  • Published:
Water Resources Management Aims and scope Submit manuscript

Abstract

Streamflow forecasting plays a key role in improvement of water resource allocation, management and planning, flood warning and forecasting, and mitigation of flood damages. There are a considerable number of forecasting models and techniques that have been employed in streamflow forecasting and gained importance in hydrological studies in recent decades. In this study, the main objective was to compare the accuracy of four data-driven techniques of Linear Regression (LR), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) network in daily streamflow forecasting. For this purpose, three scenarios were defined based on historical precipitation and streamflow series for 26 years of the Kentucky River basin located in eastern Kentucky, US. Statistical criteria including the coefficient of correlation (\(R\)), Nash-Sutcliff coefficient of efficiency (\(E\)), Nash-Sutcliff for High flow (\({E}_{H}\)), Nash-Sutcliff for Low flow (\({E}_{L}\)), normalized root mean square error (\(NRMSE\)), relative error in estimating maximum flow (\(REmax\)), threshold statistics (\(TS\)), and average absolute relative error (\(AARE\)) were employed to compare the performances of these methods. The results show that the LSTM network outperforms the other models in forecasting daily streamflow with the lowest values of \(NRMSE\) and the highest values of\({E}_{H}\),\({E}_{L}\), and \(R\) under all scenarios. These findings indicated that the LSTM is a robust data-driven technique to characterize the time series behaviors in hydrological modeling applications.

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

Similar content being viewed by others

Availability of Data and Materials

All the data and materials as well as software application or custom code support our published claims and comply with field standards.

References

  • Adnan R M, Yuan X, Kisi O, Yuan Y (2017) Streamflow forecasting using artificial neural network and support vector machine models. Am Sci Res J Eng Technol Sci (ASRJETS) 29:286–294

  • AlDahoul N, Essam Y, Kumar P, Ahmed AN, Sherif M, Sefelnasr A, Elshafie A (2021) Suspended sediment load prediction using long short-term memory neural network. Sci Rep 11:1–22

    Article  Google Scholar 

  • Aoulmi Y, Marouf N, Amireche M, Kisi O, Shubair R, Keshtegar B (2021) Highly Accurate Prediction Model for Daily Runoff in Semi-Arid Basin Exploiting Metaheuristic Learning Algorithms. IEEE Access

  • Apaydin H, Feizi H, Sattari MT, Colak MS, Shamshirband S, Chau KW (2020) Comparative analysis of recurrent neural network architectures for reservoir inflow forecasting. Water 12:1500

    Article  Google Scholar 

  • Attar NF, Pham QB, Nowbandegani SF, Rezaie-Balf M, Fai CM, Ahmed AN, Pipelzadeh S, Dung TD, Nhi PTT, Khoi DN (2020) Enhancing the prediction accuracy of data-driven models for monthly streamflow in Urmia Lake basin based upon the autoregressive conditionally heteroskedastic time-series model. Appl Sci 10:571

    Article  Google Scholar 

  • Azad A, Farzin S, Kashi H, Sanikhani H, Karami H, Kisi O (2018) Prediction of river flow using hybrid neuro-fuzzy models. Arab J Geosci 11:1–14

    Article  Google Scholar 

  • Balogun AL, Adebisi N (2021) Sea level prediction using ARIMA, SVR and LSTM neural network: assessing the impact of ensemble Ocean-Atmospheric processes on models’ accuracy. Geomatics Nat Hazards Risk 12:653–674

    Article  Google Scholar 

  • Bing-jun L, Chun-hua H (2007) The combined forecasting method of GM (1, 1) with linear regression and its application. In Proceedings of the 2007 IEEE International Conference on Grey Systems and Intelligent Services 394–398

  • Boulmaiz T, Guermoui M, Boutaghane H (2020) Impact of training data size on the LSTM performances for rainfall–runoff modeling

  • Bui DT, Hoang ND, Martínez-Álvarez F, Ngo PTT, Hoa PV, Pham TD, Samui P, Costache R (2020) A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area. Sci Total Environ 701:134413

  • Chen X, Huang J, Han Z, Gao H, Liu M, Li Z, Liu X, Li Q, Qi H, Huang Y (2020) The importance of short lag-time in the runoff forecasting model based on long short-term memory. J Hydrol 589:125359

  • Cheng M, Fang F, Kinouchi T, Navon I, Pain C (2020) Long lead-time daily and monthly streamflow forecasting using machine learning methods. J Hydrol 590:125376

  • Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Article  Google Scholar 

  • Damavandi HG, Shah R, Stampoulis D, Wei Y, Boscovic D, Sabo J (2019) Accurate Prediction of Streamflow Using Long Short-Term Memory Network: A Case Study in the Brazos River Basin in Texas. Int J Environ 10:294–300

  • Daniell T (1991) Neural networks. Applications in hydrology and water resources engineering. In Proceedings of the National Conference Publication- Institute of Engineers. Australia

  • Dong L, Fang D, Wang X, Wei W, Damaševičius R, Scherer R, Woźniak M (2020) Prediction of Streamflow Based on Dynamic Sliding Window LSTM. Water 12:3032

    Article  Google Scholar 

  • England Jr JF, Cohn TA, Faber BA, Stedinger JR, Thomas Jr WO, Veilleux AG, Kiang JE, Mason Jr RR (2019) Guidelines for determining flood flow frequency-Bulletin 17C. In: US Geological Survey

  • Eswaran C, Logeswaran R (2012) An enhanced hybrid method for time series prediction using linear and neural network models. Appl Intell 37:511–519

    Article  Google Scholar 

  • Gao H, Birkel C, Hrachowitz M, Tetzlaff D, Soulsby C, Savenije HH (2019) A simple topography-driven and calibration-free runoff generation module. Hydrol Earth Syst Sci 23:787–809

    Article  Google Scholar 

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

  • Gebregiorgis AS, Hossain F (2012) Understanding the dependence of satellite rainfall uncertainty on topography and climate for hydrologic model simulation. IEEE Trans Geosci Remote Sens 51:704–718

    Article  Google Scholar 

  • Genç O, Dağ A (2016) A machine learning-based approach to predict the velocity profiles in small streams. Water Resour Manag 30:43–61

    Article  Google Scholar 

  • Hadi SJ, Tombul M (2018) Forecasting daily streamflow for basins with different physical characteristics through data-driven methods. Water Resour Manag 32:3405–3422

    Article  Google Scholar 

  • Halff A H, Halff H M, Azmoodeh M (1993) Predicting runoff from rainfall using neural networks. In Proceedings of the Engineering hydrology 760–765

  • Han H, Choi C, Jung J, Kim HS (2021) Deep Learning with Long Short Term Memory Based Sequence-to-Sequence Model for Rainfall-Runoff Simulation. Water 13:437

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Hrnjica B, Danandeh Mehr A (2020) Energy demand forecasting using deep learning. Smart Cities Performability, Cognition, & Security (pp. 71–104): Springer

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

    Article  Google Scholar 

  • Hu Y, Yan L, Hang T, Feng J (2020) Stream-Flow Forecasting of Small Rivers Based on LSTM. arXiv

  • Jayawardena A (2013) Environmental and hydrological systems modelling. CRC Press

    Book  Google Scholar 

  • Jimeno-Sáez P, Senent-Aparicio J, Pérez-Sánchez J, Pulido-Velazquez D (2018) A comparison of SWAT and ANN models for daily runoff simulation in different climatic zones of peninsular Spain. Water 10:192

    Article  Google Scholar 

  • Karmiani D, Kazi R, Nambisan A, Shah A, Kamble V (2019) Comparison of predictive algorithms: backpropagation, SVM, LSTM and Kalman Filter for stock market. In Proceedings of the 2019 Amity International Conference on Artificial Intelligence (AICAI), 228–234

  • Kişi Ö (2008) Stream flow forecasting using neuro-wavelet technique. Hydrol Process 22:4142–4152

    Article  Google Scholar 

  • Kisi, Ö, Moghaddam Nia A, Ghafari Gosheh M, Jamalizadeh Tajabadi M R, Ahmadi A (2012) Intermittent Streamflow Forecasting by Using Several Data Driven Techniques. Water Resour Manage 26, 457–474

    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 

  • Lafdani EK, Moghaddam Nia A, Ahmadi A, Jajarmizadeh M, Gosheh MG (2013a) Stream Flow Simulation using SVM, ANFIS and NAM Models (A Case Study).Caspian Journal of Applied Sciences Reaserch 2(4): 86-93 (In Persian)

  • Lafdani EK, Moghaddam Nia A, Pahlavanravi A, Ahmadi A, Jajarmizadeh M (2013b) Research article daily rainfall-runoff prediction and simulation using ANN, ANFIS and conceptual hydrological MIKE11/NAM models. Int J Eng Technol 1:32–50

    Google Scholar 

  • Le XH, Ho HV, Lee G, Jung S (2019) Application of long short-term memory (LSTM) neural network for flood forecasting. Water 11:1387

    Article  Google Scholar 

  • Li J (2021) Exploration of Deep Learning Models on Streamflow Simulations. In: University of Californa, Irvine

  • Liu D, Jiang W, Mu L, Wang S (2020a) Streamflow Prediction Using Deep Learning Neural Network: Case Study of Yangtze River. IEEE Access 8:90069–90086

    Article  Google Scholar 

  • Liu M, Huang Y, Li Z, Tong B, Liu Z, Sun M, Jiang F, Zhang H (2020b) The Applicability of LSTM-KNN Model for Real-Time Flood Forecasting in Different Climate Zones in China. Water 12:440

    Article  Google Scholar 

  • Mehr AD, Nourani V (2018) Season algorithm-multigene genetic programming: A new approach for rainfall-runoff modelling. Water Resour Manag 32:2665–2679

    Article  Google Scholar 

  • Meng E, Huang S, Huang Q, Fang W, Wu L, Wang L (2019) A robust method for non-stationary streamflow prediction based on improved EMD-SVM model. J Hydrol 568:462–478

    Article  Google Scholar 

  • Moghaddas-Tafreshi S, Farhadi M (2008) A linear regression-based study for temperature sensitivity analysis of Iran electrical load. In Proceedings of the 2008 IEEE International Conference on Industrial Technology 1–7

  • Mosavi A, Ozturk P, Chau K-w (2018) Flood prediction using machine learning models: Literature review. Water 10:1536

    Article  Google Scholar 

  • Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—A discussion of principles. J Hydrol 10:282–290

    Article  Google Scholar 

  • Ni L, Wang D, Singh VP, Wu J, Wang Y, Tao Y, Zhang J (2020) Streamflow and rainfall forecasting by two long short-term memory-based models. J Hydrol 583:124296

  • 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 

  • Pham QB, Abba SI, Usman AG, Linh NTT, Gupta V, Malik A, Costache R, Vo ND, Tri DQ (2019) Potential of hybrid data-intelligence algorithms for multi-station modelling of rainfall. Water Resour Manag 33:5067–5087

    Article  Google Scholar 

  • Praveen B, Talukdar S, Mahato S, Mondal J, Sharma P, Islam ARMT, Rahman A (2020) Analyzing trend and forecasting of rainfall changes in India using non-parametrical and machine learning approaches. Sci Rep 10:1–21

    Article  Google Scholar 

  • Rahimzad M, Homayouni S, Alizadeh Naeini A, Nadi S (2021) An Efficient Multi-Sensor Remote Sensing Image Clustering in Urban Areas via Boosted Convolutional Autoencoder (BCAE). Remote Sens 13:2501

    Article  Google Scholar 

  • Ren K, Fang W, Qu J, Zhang X, Shi X (2020) Comparison of eight filter-based feature selection methods for monthly streamflow forecasting–three case studies on CAMELS data sets. J Hydrol 586:124897

  • Rezaie-Balf M, Zahmatkesh Z, Kim S (2017) Soft computing techniques for rainfall-runoff simulation: local non–parametric paradigm vs. model classification methods. Water Resour Manag 31:3843–3865

    Article  Google Scholar 

  • Riad S, Mania J, Bouchaou L, Najjar Y (2004) Rainfall-runoff model usingan artificial neural network approach. Math Comput Model 40:839–846

    Article  Google Scholar 

  • Roy B, Singh MP, Singh A (2021) A novel approach for rainfall-runoff modelling using a biogeography-based optimization technique. Int J River Basin Manag 19:67–80

    Article  Google Scholar 

  • Sahraei A, Chamorro A, Kraft P, Breuer L (2021) Application of machine learning models to predict maximum event water fractions in streamflow. Front Water 3:52

    Article  Google Scholar 

  • Shafaei M, Kisi O (2017) Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models. Neural Comput Appl 28:15–28

    Article  Google Scholar 

  • Singh SK (2016) Long-term streamflow forecasting based on ensemble streamflow prediction technique: a case study in New Zealand. Water Resour Manag 30:2295–2309

    Article  Google Scholar 

  • Srushti G, Bhandary VS, Mendonca AE (2020) Comparison of Support Vector Machine and Long Short-Term Memory for Stock Market Analysis. Int Res J Eng Technol

  • Stähler SC, Sens-Schönfelder C, Niederleithinger E (2011) Monitoring stress changes in a concrete bridge with coda wave interferometry. J Acoust Soc 129:1945–1952

    Article  Google Scholar 

  • Tan Q, Wang X, Cai S, Lei X (2015) Daily runoff time-series prediction based on the adaptive neural fuzzy inference system. In Proceedings of the 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD) 506–512

  • Taylor R (1990) Interpretation of the correlation coefficient: a basic review. J Diagn Med Sonogr 6:35–39

    Article  Google Scholar 

  • Te Chow V (2010) Applied hydrology. Tata McGraw-Hill Education

  • Wang S, Cao J, Yu P (2020) Deep learning for spatio-temporal data mining: A survey. IEEE Trans Knowl Data Eng

  • Wang W, Van Gelder P, Vrijling J (2005) Trend and stationarity analysis for streamflow processes of rivers in western Europe in the 20th century. In Proceedings of the IWA International Conference on water economics, statistics, and finance, Rethymno, Greece 8–10

  • Widiasari IR, Nugoho LE, Efendi R (2018) Context-based hydrology time series data for a flood prediction model using LSTM. In Proceedings of the 2018 5th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE) 385–390

  • Xiang Z, Yan J, Demir I (2020) A rainfall‐runoff model with LSTM‐based sequence‐to‐sequence learning. Water Resour Res 56:e2019WR025326

  • Xu W, Jiang Y, Zhang X, Li Y, Zhang R, Fu G (2020) Using long short-term memory networks for river flow prediction. Nord Hydrol 51:1358–1376

    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 Manag 30:4125–4151

    Article  Google Scholar 

  • Yaseen ZM, Mohtar WHMW, Ameen AMS, Ebtehaj I, Razali SFM, Bonakdari H, Salih SQ, Al-Ansari N, Shahid S (2019) Implementation of univariate paradigm for streamflow simulation using hybrid data-driven model: Case study in tropical region. IEEE Access 7:74471–74481

    Article  Google Scholar 

  • Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918–929

    Article  Google Scholar 

  • Zuo G, Luo J, Wang N, Lian Y, He X (2020) Decomposition ensemble model based on variational mode decomposition and long short-term memory for streamflow forecasting. J Hydrol 124776

Download references

Funding

'Not applicable'. No funds, grants, or other support was received.

Author information

Authors and Affiliations

  1. Department of Geomatics Engineering, Faculty of Civil Engineering and Transportation, University of Isfahan, Isfahan, Iran

    Maryam Rahimzad

  2. Department of Reclamation of Arid and Mountainous Regions, Faculty of Natural Resources, University of Tehran, Karaj, Iran

    Alireza Moghaddam Nia

  3. DEEC, INESC Coimbra, University of Coimbra, Coimbra, Portugal

    Hosam Zolfonoon

  4. Department of Water Engineering, Aburaihan Campus, University of Tehran, Pakdasht, Iran

    Jaber Soltani

  5. Department of Civil Engineering, Antalya Bilim University, Antalya, Turkey

    Ali Danandeh Mehr

  6. Department of Civil and Environmental Engineering, Sejong University, Seoul, South Korea

    Hyun-Han Kwon

Authors
  1. Maryam Rahimzad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alireza Moghaddam Nia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hosam Zolfonoon
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jaber Soltani
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ali Danandeh Mehr
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Hyun-Han Kwon
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: [Alireza Moghaddam Nia]; Methodology: [Maryam Rahimzad], [Hosam Zolfonoon]; Formal analysis and investigation: [Maryam Rahimzad], [Hosam Zolfonoon]; Writing—original draft preparation: [Maryam Rahimzad], [Hosam Zolfonoon]; Writing—review and editing: [Maryam Rahimzad], [Alireza Moghaddam Nia], [Hosam Zolfonoon], [Jaber Soltani], [Ali Danandeh Mehr], [Hyun-Han Kwon]; All authors read and approved the final manuscript.

Corresponding author

Correspondence to Alireza Moghaddam Nia.

Ethics declarations

Ethical Approval

All authors have read this manuscript and would like to have it considered exclusively for publication in this journal. None of the material related to this manuscript has been published or is under consideration for publication elsewhere, including the internet.

Consent to Participate

All authors have read this manuscript and contributed to the study.

Consent to Publish

All authors would like to have it considered exclusively for publication in this journal.

Competing Interests

'Not applicable'.

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

Rahimzad, M., Moghaddam Nia, A., Zolfonoon, H. et al. Performance Comparison of an LSTM-based Deep Learning Model versus Conventional Machine Learning Algorithms for Streamflow Forecasting. Water Resour Manage 35, 4167–4187 (2021). https://doi.org/10.1007/s11269-021-02937-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11269-021-02937-w

Keywords

Search

Navigation