Monthly streamflow prediction using a hybrid stochastic-deterministic approach for parsimonious non-linear time series modeling

Accurate streamflow prediction is essential in reservoir management, flood control, and operation of irrigation networks. In this study, the deterministic and stochastic components of modeling are considered simultaneously. Two nonlinear time series models are developed based on autoregressive conditional heteroscedasticity and self-exciting threshold autoregressive methods integrated with the gene expression programming. The data of four stations from four different rivers from 1971 to 2010 are investigated. For examining the reliability and accuracy of the proposed hybrid models, three evaluation criteria, namely the R2, RMSE, and MAE, and several visual plots were used. Performance comparison of the hybrid models revealed that the accuracy of the SETAR-type models in terms of R2 performed better than the ARCH-type models for Daryan (0.99), Germezigol (0.99), Ligvan (0.97), and Saeedabad (0.98) at the validation stage. Overall, prediction results showed that a combination of the SETAR with the GEP model performs better than ARCH-based GEP models for the prediction of the monthly streamflow. Abbreviations: ADF = Augmented Dickey-Fuller; AIC = Akaike Information Criterion; ANFIS = Adaptive Neuro-Fuzzy Inference System; ANNs = Artificial Neural Networks; AR = Autoregressive Models; ARIMA = Autoregressive Integrated Moving Average; ARCH = Autoregressive Conditional Heteroscedasticity; ATAR = Aggregation Operator Based TAR; BL = Bilinear Models; BNN = Bayesian Neural Network; CEEMD = Complete Ensemble Empirical Mode Decomposition; DDM =Data-Driven Model; GA = Genetic Algorithm; GARCH = Generalized Autoregressive Conditional Heteroscedasticity; GEP = Gene Expression Programming; KNN = K-Nearest Neighbors; KPSS = Kwiatkowski–Phillips–Schmidt–Shin; LMR = Linear and Multilinear Regressions; LR = Likelihood Ratio; LSTAR = Logistic STAR; MAE = Mean Absolute Error; PACF = Partial Autocorrelation Function; PARCH = Partial Autoregressive Conditional Heteroscedasticity; R 2 = Coefficient of Determination; RMSE = Root Mean Square Error; RNNs = Recurrent Neural Networks; SETARMA = Self-Exciting Threshold Autoregressive Moving Average; SETAR = Self-Exciting Threshold Autoregressive; STAR = Smooth Transition AR; SVR = Support Vector Regression; TAR = Threshold Autoregressive; TARMA = Threshold Autoregressive Moving Average; ULB = Urmia Lake Basin; VMD = Variational Mode Decomposition; WT = Wavelet Transforms

[1]  R. Deo,et al.  Input selection and performance optimization of ANN-based streamflow forecasts in the drought-prone Murray Darling Basin region using IIS and MODWT algorithm , 2017 .

[2]  Qian Zhu,et al.  Integration of a Parsimonious Hydrological Model with Recurrent Neural Networks for Improved Streamflow Forecasting , 2018, Water.

[3]  Chong-Yu Xu,et al.  Improving monthly streamflow prediction in alpine regions: integrating HBV model with Bayesian neural network , 2018, Stochastic Environmental Research and Risk Assessment.

[4]  J. A. Stewart,et al.  Nonlinear Time Series Analysis , 2015 .

[5]  Aytac Guven,et al.  A stepwise model to predict monthly streamflow , 2016 .

[6]  James J. Heckman,et al.  Handbook of Econometrics , 1985 .

[7]  Ronny Berndtsson,et al.  Phase-space reconstruction and self-exciting threshold modeling approach to forecast lake water levels , 2014, Stochastic Environmental Research and Risk Assessment.

[8]  Farshad Fathian,et al.  Modeling streamflow time series using nonlinear SETAR-GARCH models , 2019, Journal of Hydrology.

[9]  Ronny Berndtsson,et al.  Phase-space reconstruction and self-exciting threshold models in lake level forecasting: a case study of the three largest lakes of Sweden , 2014 .

[10]  Ahmad Sharafati,et al.  Complementary data-intelligence model for river flow simulation , 2018, Journal of Hydrology.

[11]  Zaher Mundher Yaseen,et al.  An enhanced extreme learning machine model for river flow forecasting: State-of-the-art, practical applications in water resource engineering area and future research direction , 2019, Journal of Hydrology.

[12]  Mohammad Rezaie-Balf,et al.  An evolutionary approach to formulate the compressive strength of roller compacted concrete pavement , 2020 .

[13]  Ahmed El-Shafie,et al.  Improving artificial intelligence models accuracy for monthly streamflow forecasting using grey Wolf optimization (GWO) algorithm , 2020 .

[14]  M. R. Kousari,et al.  Non-parametric trend analysis of the aridity index for three large arid and semi-arid basins in Iran , 2013, Theoretical and Applied Climatology.

[15]  Jesus Gonzalo,et al.  Subsampling inference in threshold autoregressive models , 2005 .

[16]  H. Pourghasemi,et al.  Groundwater potential mapping at Kurdistan region of Iran using analytic hierarchy process and GIS , 2015, Arabian Journal of Geosciences.

[17]  Hui-Chen Su,et al.  A nonlinear time series analysis using two‐stage genetic algorithms for streamflow forecasting , 2008 .

[18]  Tim Bollerslev,et al.  Chapter 49 Arch models , 1994 .

[19]  Ali Ahani,et al.  Performance Assessment of the Linear, Nonlinear and Nonparametric Data Driven Models in River Flow Forecasting , 2017, Water Resources Management.

[20]  Amin Talei,et al.  The Impact of Training Data Sequence on the Performance of Neuro-Fuzzy Rainfall-Runoff Models with Online Learning , 2018, Water.

[21]  Radko Mesiar,et al.  Comparison of forecasting performance of nonlinear models of hydrological time series , 2006 .

[22]  Zaher Mundher Yaseen,et al.  Novel approach for streamflow forecasting using a hybrid ANFIS-FFA model , 2017 .

[23]  Jinshan Liu,et al.  Bayesian analysis of multiple thresholds autoregressive model , 2017, Comput. Stat..

[24]  Dillip K. Ghose,et al.  Estimating Runoff Using Feed-Forward Neural Networks in Scarce Rainfall Region , 2018, Smart Intelligent Computing and Applications.

[25]  Celso Augusto Guimarães Santos,et al.  Analysis of the use of discrete wavelet transforms coupled with ANN for short-term streamflow forecasting , 2019, Appl. Soft Comput..

[26]  J. P. King,et al.  Developing an intelligent expert system for streamflow prediction, integrated in a dynamic decision support system for managing multiple reservoirs: A case study , 2017, Expert Syst. Appl..

[27]  James D. Hamilton,et al.  Autoregressive conditional heteroskedasticity and changes in regime , 1994 .

[28]  R. Engle.  Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation , 1982 .

[29]  L. C. Brown,et al.  The influence of climatic inputs on stream-flow pattern forecasting: case study of Upper Senegal River , 2018, Environmental Earth Sciences.

[30]  Ahmad Sharafati,et al.  Development of multivariate adaptive regression spline integrated with differential evolution model for streamflow simulation , 2019, Journal of Hydrology.

[31]  Zhongmin Liang,et al.  Long-term streamflow forecasting using SWAT through the integration of the random forests precipitation generator: case study of Danjiangkou Reservoir , 2018 .

[32]  Zaher Mundher Yaseen,et al.  Non-tuned machine learning approach for hydrological time series forecasting , 2016, Neural Computing and Applications.

[33]  Ozgur Kisi,et al.  Forecasting Sea Water Levels at Mukho Station, South Korea Using Soft Computing Techniques , 2014 .

[34]  André Gustavo da Silva Melo Honorato,et al.  Monthly streamflow forecasting using neuro-wavelet techniques and input analysis , 2018, Hydrological Sciences Journal.

[35]  Mohammed Akram Gill,et al.  Analysis of one-dimensional non-Darcy vertical infiltration , 1976 .

[36]  Zaher Mundher Yaseen,et al.  Incorporating synoptic-scale climate signals for streamflow modelling over the Mediterranean region using machine learning models , 2019, Hydrological Sciences Journal.

[37]  Hui Qin,et al.  Comparison of support vector regression and extreme gradient boosting for decomposition-based data-driven 10-day streamflow forecasting , 2020 .

[38]  You-meng Li,et al.  Comparison of hybrid models for daily streamflow prediction in a forested basin , 2018 .

[39]  Zaher Mundher Yaseen,et al.  Learning from Multiple Models Using Artificial Intelligence to Improve Model Prediction Accuracies: Application to River Flows , 2018, Water Resources Management.

[40]  Ronny Berndtsson,et al.  Impact of complexity on daily and multi-step forecasting of streamflow with chaotic, stochastic, and black-box models , 2017, Stochastic Environmental Research and Risk Assessment.

[41]  Ozgur Kisi,et al.  Wavelet-linear genetic programming: A new approach for modeling monthly streamflow , 2017 .

[42]  Ozgur Kisi,et al.  Daily Mean Streamflow Prediction in Perennial and Non-Perennial Rivers Using Four Data Driven Techniques , 2017, Water Resources Management.

[43]  Wanchang Zhang,et al.  Stream Flow Forecasting by Artificial Neural Network and TOPMODEL in Baohe River Basin , 2009, 2009 Third International Symposium on Intelligent Information Technology Application Workshops.

[44]  Hakan Tongal,et al.  NONLINEAR DYNAMICAL APPROACH AND SELF-EXCITING THRESHOLD MODEL IN FORECASTING DAILY STREAM-FLOW , 2013 .

[45]  Jalal Shiri,et al.  Forecasting daily stream flows using artificial intelligence approaches , 2012 .

[46]  Mohammad Ebrahim Banihabib,et al.  Auto-Regressive Neural-Network Models for Long Lead-Time Forecasting of Daily Flow , 2018, Water Resources Management.

[47]  Ozgur Kisi,et al.  Evaluating the generalizability of GEP models for estimating reference evapotranspiration in distant humid and arid locations , 2017, Theoretical and Applied Climatology.

[48]  Kishanjit Kumar Khatua,et al.  Prediction of discharge in converging and diverging compound channel by gene expression programming , 2019, ISH Journal of Hydraulic Engineering.

[49]  Quoc Bao Pham,et al.  Enhancing the Prediction Accuracy of Data-Driven Models for Monthly Streamflow in Urmia Lake Basin Based upon the Autoregressive Conditionally Heteroskedastic Time-Series Model , 2020, Applied Sciences.

[50]  Hung Man Tong,et al.  Threshold models in non-linear time series analysis. Lecture notes in statistics, No.21 , 1983 .

[51]  S. Nazif,et al.  Monthly prediction of streamflow using data-driven models , 2019, Journal of Earth System Science.

[52]  Aidin Rahmani-Rezaeieh,et al.  Ensemble gene expression programming: a new approach for evolution of parsimonious streamflow forecasting model , 2019, Theoretical and Applied Climatology.

[53]  Ján Szolgay,et al.  Hybrid Forecasting of Daily River Discharges Considering Autoregressive Heteroscedasticity , 2017 .

[54]  O. Kisi,et al.  A new intelligent method for monthly streamflow prediction: hybrid wavelet support vector regression based on grey wolf optimizer (WSVR–GWO) , 2019, Arabian Journal of Geosciences.

[55]  Cândida Ferreira.  Gene Expression Programming in Problem Solving , 2002 .