Abstract
Monthly river flow forecasting has a vital role in many water resource management activities, especially in extreme events such as flood and drought. Therefore, experts need a reliable and precise model for forecasting. The ensemble machine learning (EML) models can provide more accurate results by combining coupled models. To this end, the chief aim of this study is to present multiple individual and integrated approaches to achieve more precise predictions. This study investigates the adaptive neuro-fuzzy inference system (ANFIS), multi-layer perceptron neural network (MLPNN), and group method of data handling (GMDH) models along with EML models including stacking and averaging techniques for forecasting regulated and natural river flow. Multiple linear regression (MLR) and support vector regression (SVR) strategies are applied as meta-learner EMLs as well as simple and weighted averaging. Monthly river flow datasets were collected from the Nashua River and the St. John River in the USA evaluating all models. The models’ performances are compared using five standard evaluation indices such as the root mean square error, Nash–Sutcliffe efficiency, mean absolute error, mean index of agreement, and coefficient of determination (R2). In both modeling scenarios, the predicative stacking-SVR model followed by the simple averaging, weighted averaging, GMDH, and stacking-MLR acted appropriately with R2 of 0.996 in the Nashua River (regulated) and 0.909 in the St. John River (natural flow). The prediction results of the MLPNN and ANFIS models were almost similar. Overall, the EMLs produce more precise and reliable predictions, demonstrating the superiority of EML methodologies over individual models.
Similar content being viewed by others
Abbreviations
- ANFIS:
-
Adaptive neuro-fuzzy inference system
- ANN:
-
Artificial neural networks
- EFA:
-
Exploratory factor analysis
- EGB:
-
Extreme gradient boosting
- EML:
-
Ensemble machine learning
- ENR:
-
Elastic net regression
- GMDH:
-
Group method of data handling
- IA:
-
Index of agreement
- MAE:
-
Mean absolute error
- ML:
-
Machine learning
- MLPNN:
-
Multi-layer perceptron neural network
- MLR:
-
Multiple linear regression
- NSE:
-
Nash–Sutcliffe efficiency
- Q :
-
Discharge
- R 2 :
-
Coefficient of determination
- RF:
-
Random forest
- SA:
-
Simple averaging
- SEM:
-
Stacking ensemble model
- t :
-
Time
- WA:
-
Weighted averaging
References
Aburomman AA, Reaz MBI (2016) A novel SVM-kNN-PSO ensemble method for intrusion detection system. Appl Soft Comput 38:360–372
Akkoyun S (2020) Estimation of fusion reaction cross-sections by artificial neural networks. Nucl Instrum Methods Phys Res, Sect B 462:51–54
Akyildiz O, Hudaverdi T (2020) ANFIS modelling for blast fragmentation and blastinduced vibrations considering stiffness ratio. Arab J Geosci 13:1162
Dai Zh, Amatya D, Sun G, Trettin C, Li Ch, Li H (2011) Climate variability and its impact on forest hydrology on South Carolina coastal plain, USA. Atmosphere 2(3):330–357
Delafrouz H, Ghaheri A, Ghorbani MA (2017) A novel hybrid neural network based on phase space reconstruction technique for daily river flow prediction. Soft Comput 22:2205–2215
Fatahi Nafchi R, Yaghoobi P, ReaisiVanani H et al (2021a) Eco-hydrologic stability zonation of dams and power plants using the combined models of SMCE and CEQUALW2. Appl Water Sci 11(7):109
Fattahi Nafchi R, Raeisi Vanani H, Noori Pashaee K et al (2021b) Investigation on the effect of inclined crest step pool on scouring protection in erodible river beds. Nat Hazards (2021b)
Graczyk M, Lasota T, Trawínski B, Trawínski K (2010) Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal, in: Asian Conference on Intelligent Information and Database Systems. Springer 5991: 340–350
HasanpourKashani M, Daneshfaraz R, Ghorbani MA, Najafi MR, Kisi O (2015) Comparison of different methods for developing a stage discharge curve of the Kizilirmak River. J Flood Risk Manag 8:71–86
Heddam S, Ptak M, Zhu S (2020) Modelling of daily lake surface water temperature from air temperature: extremely randomized trees (ERT) versus Air2Water, MARS, M5Tree, RF and MLPNN. J Hydrol 588:125130
Hong M, Wang D, Wang Y, Zeng X, Ge S, Yan H, Singh VP (2016) Mid- and long-term runoff predictions by an improved phase-space reconstruction model. Environ Res 148:560–573
Ivakhnenko A (1960) New methods of control-system investigation. Control 3 (30): 96–99
Jain A, Kumar AM (2007) Hybrid neural network models for hydrologic time series forecasting. J Appl Soft Comput 7(3):585–592
Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23(3):665–685
Kalantar B, Pradhan B, Naghibi SA, Motevalli A, Mansor S (2018) Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN). Geomat Nat Haz Risk 9(1):49–69
Kim D, Yu H, Lee H, Beighley E, Durand M, Alsdorf DE, Hwang E (2019) Ensemble learning regression for estimating river discharges using satellite altimetry data: Central Congo River as a Test-bed. Remote Sens Environ 221:741–755
Kim SE, Seo IW (2015) Artificial neural network ensemble modeling with exploratory factor analysis for streamflow forecasting. J Hydroinf 17(4):614–639
Kisi O, Cigizoglu HK (2007) Comparison of different ANN techniques in river flow prediction. Civ Eng Environ Syst 24(3):211–231
Kisi O, Shiri J, Tombul M (2013) Modeling rainfall-runoff process using soft computing techniques. Comput Geosci 51:108–117
Lee DG, Ahn KH (2021) A stacking ensemble model for hydrological post-processing to improve streamflow forecasts at medium-range timescales over South Korea. J Hydrol 600:126681
Li Y, Liang Z, Hu Y, Li B, Xu B, Wang D (2020) A multi-model integration method for monthly streamflow prediction: modified stacking ensemble strategy. J Hydroinf 22(2):310–326
Mahdavi-Meymand A, Sulisz W, Zounemat-Kermani M (2022) A comprehensive study on the application of firefly algorithm in prediction of energy dissipation on block ramps. Eksploatacja I Niezawodnosc – Maintenance and Reliability 24(2):200–208
Naftaly U, Intratorz N, Horn D (1997) Optimal ensemble averaging of neural networks. Comput Neural Syst 8:283–296
Nourani V, Elkiran G, Abba SI (2018) Wastewater treatment plant performance analysis using artificial intelligence – an ensemble approach. Water Sci Technol 78(10):2064–2076
Onyelowe KC, Shakeri J, Amini-Khoshalann H, Salahudeen AB, Arinze EE, Ugwu HU (2021) Application of ANFIS hybrids to predict coefficients of curvature and uniformity of treated unsaturated lateritic soil forsustainable earthworks. Cleaner Materials 1:100005
Ostad-Ali-Askari K, Shayan M (2021) Subsurface drain spacing in the unsteady conditions by HYDRUS-3D and artificial neural networks. Arab J Geosci 14:1936
Ostad-Ali-Askari K, Shayannejad M (2021) Computation of subsurface drain spacing in the unsteady conditions using artificial neural networks (ANN). Appl Water Sci 11:21
Ostad-Ali-Askari K, Shayannejad M, Eslamian S (2017a) Chapter No. 18: deficit irrigation: optimization models. Management of Drought and Water Scarcity. Handbook of Drought and Water Scarcity Vol. 3: 373–389. Taylor & Francis Publisher. Imprint: CRC Press. eBook ISBN: 9781315226774. 1st Edition
Ostad-Ali-Askari K, Shayannejad M, Ghorbanizadeh-Kharazi H (2017b) Artificial neural network for modeling nitrate pollution of groundwater in marginal area of Zayandeh-Rood River, Isfahan Iran. KSCE J Civ Eng Korean Soc Civ Eng 21(1):134–140
Panahi M, Sadhasivam N, Pourghasemid HR, Rezaiee F, Lee S (2020) Spatial prediction of groundwater potential mapping based on convolutional neural network (CNN) and support vector regression (SVR). J Hydrol 588:125033
Peng T, Zhou J, Zhang C, Fu W (2017) Streamflow forecasting using empirical wavelet transform and artificialneural networks. Water 9:406
Pumo D, Conti FL, Viola F, Noto LV (2017) An automatic tool for reconstructing monthly time-series of hydro-climatic variables at ungauged basins. Environ Model Softw 95:381–400
Pumo D, Viola F, Noto LV (2016) Generation of natural runoff monthly series at ungauged sites using a regional regressive model. Water 8:209
Seewald A K (2002) How to make stacking better and faster while also taking care of an unknown weakness. Conference: Machine Learning, Proceedings of the Nineteenth International Conference (ICML 2002), University of New South Wales, Sydney, Australia. 554–561
Sharghi E, Nourani V, Behfar N (2018) Earth fill dam seepage analysis using ensemble artificial intelligence-based modeling. J Hydro Informatics 20(5):1071–1084
Shi F, Liua Y, Liua Zh, Lib E (2018) Prediction of pipe performance with stacking ensemble learning based approaches. J Intell Fuzzy Syst 34(6):3845–3855
Srinivasulu S, Jain A (2009) River flow prediction using an integrated approach. J Hydrol Eng 14(1):75–83
Terzi O (2011) Monthly river flow forecasting by data mining process. knowledge-oriented applications in data mining, ISBN: 978-953-307-154-1, chapter 8. https://doi.org/10.5772/13566
Tyralis H, Papacharalampous G, Langousis A (2019) Super learning for daily streamflow forecasting: large-scale demonstration and comparison with multiple machine learning algorithms. Neural Comput Appl 33:3053–3068
Vapnik V, Golowich SE, Smola AJ (1997) Support vector method for function approximation, regression estimation and signal processing. Adv Neural Inf Process Syst 9:281–287
Wolpert DH, Macready WG (1992) An efficient method to estimate bagging’s generalization error. Mach Learn 35(1):41–55
Wu T, Zhang W, Jiao X, Guo W, Hamoud YA (2021) Evaluation of stacking and blending ensemble learning methods for estimating daily reference evapotranspiration. Comput Electron Agric 184:106039
Xu L, Wang X, Bai L, Xiao J, Liu Q, Chen E, Jiang X, Luo B (2020) Probabilistic SVM classifier ensemble selection based on GMDH-type neural network. Pattern Recogn 106:107373
Zhou J, Peng T, Zhang C, Sun N (2018) Data pre-analysis and ensemble of various artificial neural networks for monthly streamflow forecasting. Water 10(5):628
Zounemat-Kermani M, Batelaan O, Fadaee M, Hinkelmann R (2021a) Ensemble machine learning paradigms in hydrology: a review. J Hydrol 598:126266
Zounemat-Kermani M, Mahdavi-Meymand A, Hinkelmann R (2021b) A comprehensive survey on conventional and modern neural networks: application to river flow forecasting. Earth Sci Inform 14: 893–911.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no competing interests.
Additional information
Responsible Editor: Broder J. Merkel
Rights and permissions
About this article
Cite this article
Sayari, S., Meymand, A.M., Aldallal, A. et al. Meta-learner methods in forecasting regulated and natural river flow. Arab J Geosci 15, 1051 (2022). https://doi.org/10.1007/s12517-022-10274-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-022-10274-4