Comparative assessment of time series and artificial intelligence models to estimate monthly streamflow: A local and external data analysis approach

Abstract River flow rates are important for water resources projects. Given this, the current study explored the use of autoregressive (AR) and moving average (MA) techniques as individual time series models and compared them to the same models hybridized with an autoregressive conditional heteroscedasticity (ARCH) model to estimate monthly streamflow. In addition, two artificial intelligence (AI) approaches, namely, multivariate adaptive regression splines (MARS) and gene expression programming (GEP), were explored. The performance of each of these models in estimating monthly streamflow was compared based on local and external data analyses. Using the local data analysis approach, streamflow data at each target station was estimated using observed streamflow at the same station. The external data analysis approach used neighboring station streamflow data to estimate streamflow data for the target station. The Beinerahe Roodbar and Pole Astaneh stations on the Sefidrood River, Iran, as well as the Port Elgin and Walkerton stations on the Saugeen River, Canada, were used as study areas. Upstream and downstream monthly streamflow time series data were used. The performance of all models was compared using three error metrics, including the root mean square error, mean absolute error, and correlation coefficient. The results showed that the hybrid time series models (i.e., AR-ARCH and MA-ARCH) outperformed the conventional AR and MA models. A comparison of all applied models revealed that the hybrid AR-ARCH and MA-ARCH time series models performed better than the AI techniques, when using a local data analysis approach. The external data analysis approach was more accurate for monthly streamflow estimation than the local data analysis approach. To conclude, based on the outcomes of the AI models under the external data analysis approach, nearby data can be used to estimate streamflow of a target station when the target station streamflow data are not available.

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

[2]  Jan Adamowski,et al.  Hybrid artificial intelligence-time series models for monthly streamflow modeling , 2019, Appl. Soft Comput..

[3]  Puteh Saad,et al.  River flow time series using least squares support vector machines , 2011 .

[4]  Taha B. M. J. Ouarda,et al.  Modelling heteroscedasticty of streamflow times series , 2013 .

[5]  X. Y. Chen,et al.  A comparative study of population-based optimization algorithms for downstream river flow forecasting by a hybrid neural network model , 2015, Eng. Appl. Artif. Intell..

[6]  Saeid Mehdizadeh,et al.  New Approaches for Estimation of Monthly Rainfall Based on GEP-ARCH and ANN-ARCH Hybrid Models , 2017, Water Resources Management.

[7]  Cândida Ferreira,et al.  Gene Expression Programming: A New Adaptive Algorithm for Solving Problems , 2001, Complex Syst..

[8]  Saeid Mehdizadeh,et al.  Application of gene expression programming to predict daily dew point temperature , 2017 .

[9]  Vijay P. Singh,et al.  Stage and Discharge Forecasting by SVM and ANN Techniques , 2012, Water Resources Management.

[10]  P Stephon.  FORECASTING RECESSIONS: CAN WE DO BETER ON MARSTM? , 2001 .

[11]  R. Maheswaran,et al.  Wavelet–Volterra coupled model for monthly stream flow forecasting , 2012 .

[12]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

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

[14]  Özlem Terzi,et al.  Forecasting of monthly river flow with autoregressive modeling and data-driven techniques , 2013, Neural Computing and Applications.

[15]  Rameswar Panda,et al.  Application of neural network and adaptive neuro-fuzzy inference systems for river flow prediction , 2009 .

[16]  A. D. Mehr.  An improved gene expression programming model for streamflow forecasting in intermittent streams , 2018 .

[17]  Peter Romilly,et al.  Time series modelling of global mean temperature for managerial decision-making. , 2005, Journal of environmental management.

[18]  Özgür Kişi,et al.  Daily River Flow Forecasting Using Artificial Neural Networks and Auto-Regressive Models , 2005 .

[19]  Taymoor A. Awchi,et al.  River Discharges Forecasting In Northern Iraq Using Different ANN Techniques , 2014, Water Resources Management.

[20]  S. K. Mittal,et al.  Stochastic modelling of rainfall and runoff phenomenon: a time series approach review , 2014 .

[21]  Saeid Mehdizadeh,et al.  Assessing the potential of data-driven models for estimation of long-term monthly temperatures , 2018, Comput. Electron. Agric..

[22]  Saeid Mehdizadeh,et al.  A Comparative Study of Autoregressive, Autoregressive Moving Average, Gene Expression Programming and Bayesian Networks for Estimating Monthly Streamflow , 2018, Water Resources Management.

[23]  T. Ouarda,et al.  Generalized autoregressive conditional heteroscedasticity modelling of hydrologic time series , 2012 .

[24]  Alex J. Cannon,et al.  Daily streamflow forecasting by machine learning methods with weather and climate inputs , 2012 .

[25]  Zaher Mundher Yaseen,et al.  Artificial intelligence based models for stream-flow forecasting: 2000-2015 , 2015 .

[26]  H. Thomas.  Mathematical synthesis of streamflow sequences for the analysis of river basin by simulation , 1962 .

[27]  Jun Guo,et al.  Monthly streamflow forecasting based on improved support vector machine model , 2011, Expert Syst. Appl..

[28]  Muttucumaru Sivakumar,et al.  Evolutionary Modeling for Streamflow Forecasting with Minimal Datasets: A Case Study in the West Malian River, China , 2010 .

[29]  T. Ouarda,et al.  Multiple streamflow time series modeling using VAR–MGARCH approach , 2019, Stochastic Environmental Research and Risk Assessment.

[30]  George E. P. Box,et al.  Time Series Analysis: Forecasting and Control , 1977 .

[31]  Sinan Jasim Hadi,et al.  Forecasting Daily Streamflow for Basins with Different Physical Characteristics through Data-Driven Methods , 2018, Water Resources Management.

[32]  Peter S. Sephton,et al.  Forecasting recessions: can we do better on MARS? , 2001 .

[33]  Saeid Mehdizadeh,et al.  A comparison of monthly precipitation point estimates at 6 locations in Iran using integration of soft computing methods and GARCH time series model , 2017 .

[34]  Ozgur Kisi,et al.  A wavelet-support vector machine conjunction model for monthly streamflow forecasting , 2011 .

[35]  Mir Jafar Sadegh Safari,et al.  Hybrid models to improve the monthly river flow prediction: Integrating artificial intelligence and non-linear time series models , 2019, Journal of Hydrology.

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

[37]  Basant Yadav,et al.  Discharge forecasting using an Online Sequential Extreme Learning Machine (OS-ELM) model: A case study in Neckar River, Germany , 2016 .

[38]  Chuntian Cheng,et al.  A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series , 2009 .

[39]  Shiv O. Prasher,et al.  Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data , 2012 .

[40]  K. Hipel,et al.  Time series modelling of water resources and environmental systems , 1994 .

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

[42]  Saeid Mehdizadeh,et al.  Estimation of daily reference evapotranspiration (ETo) using artificial intelligence methods: Offering a new approach for lagged ETo data-based modeling , 2018 .