Artificial intelligence and geo-statistical models for stream-flow forecasting in ungauged stations: state of the art

Developing an accurate model for discharge estimation techniques of the ungauged river basin is a crucial challenge in water resource management especially in under-development regions. This article is a thorough review of the historical improvement stages of this topic to understand previous challenges that faced researchers, the shortfalls of methods and techniques, how researchers prevailed and what deficiencies still require solutions. This revision focuses on data-driven approaches and GIS-based methods that have improved the accuracy of estimation of hydrological variables, considering their advantages and disadvantages. Past studies used artificial intelligence and geo-statistical methods to forecast the runoff at ungauged river basins, and mapping the spatial distribution has been considered in this study. A recommendation for future research on the potential of a hybrid model utilizing both approaches is proposed and described.

[1]  A Critto,et al.  Risk based characterisation of contaminated industrial site using multivariate and geostatistical tools. , 2001, Environmental pollution.

[2]  T. Sathish,et al.  River Flow Forecasting using Recurrent Neural Networks , 2004 .

[3]  Kunlun Xin,et al.  Using Radial Basis Function Neural Networks to Calibrate Water Quality Model , 2008 .

[4]  J. Salas,et al.  Conceptual Basis of Seasonal Streamflow Time Series Models , 1992 .

[5]  Dong-Sheng Jeng,et al.  Application of Neural Network in Civil Engineering Problems , 2003 .

[6]  G. Blöschl,et al.  Spatiotemporal topological kriging of runoff time series , 2007 .

[7]  Zaher Mundher Yaseen,et al.  RBFNN versus FFNN for daily river flow forecasting at Johor River, Malaysia , 2015, Neural Computing and Applications.

[8]  Ranhang Zhao,et al.  A hybrid fuzzy and neural network model for hydrological forecasting in ungauged basins , 2008 .

[9]  G. Vandewiele,et al.  Monthly water balance of ungauged catchments obtained by geographical regionalization , 1995 .

[10]  Ronald R. P. van Nooijen,et al.  A problem in hydrological model calibration in the case of averaged flux input and flux output , 2012, Environ. Model. Softw..

[11]  Majid Montaseri,et al.  Flood Estimation at Ungauged Sites Using a New Hybrid Model , 2008 .

[12]  Gwo-Fong Lin,et al.  A non-linear rainfall-runoff model using radial basis function network , 2004 .

[13]  Li-Chiu Chang,et al.  Intelligent control for modelling of real‐time reservoir operation , 2001 .

[14]  R. Vogel,et al.  Regional calibration of a watershed model , 2000 .

[15]  A. Schumann,et al.  SOIL AND DIAPREPES ABBREVIATUS ROOT WEEVIL SPATIAL VARIABILITY IN A POORLY DRAINED CITRUS GROVE , 2004 .

[16]  P. C. Mahalanobis,et al.  Experiments in statistical sampling in the Indian Statistical Institute , 1961 .

[17]  P. Goovaerts,et al.  Geostatistical modeling of the spatial variability of arsenic in groundwater of southeast Michigan , 2005 .

[18]  Murugesu Sivapalan,et al.  A conceptual model of sediment transport: Application to the Avon River Basin in Western Australia , 1999 .

[19]  L. Gottschalk,et al.  Mapping average annual runoff: a hierarchical approach applying a stochastic interpolation scheme , 2000 .

[20]  A. Montanari,et al.  Prediction of low-flow indices in ungauged basins through physiographical space-based interpolation. , 2009 .

[21]  Connie Ko,et al.  GIS modeling for predicting river runoff volume in ungauged drainages in the Greater Toronto Area, Canada , 2006, Comput. Geosci..

[22]  T.-C. Jim Yeh,et al.  Quantitative Information Fusion for Hydrological Sciences , 2008, Studies in Computational Intelligence.

[23]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[24]  E. Prepas,et al.  Towards a generic neural network model for the prediction of daily streamflow in ungauged boreal plain watersheds , 2008 .

[25]  C. Obled,et al.  Objective analyses and mapping techniques for rainfall fields: An objective comparison , 1982 .

[26]  Mohammad Ali Ghorbani,et al.  Comparison of three artificial intelligence techniques for discharge routing , 2011 .

[27]  Donna M. Rizzo,et al.  Advances in ungauged streamflow prediction using artificial neural networks , 2010 .

[28]  M. R. Yazdani,et al.  Monthly Runoff Estimation Using Artificial Neural Networks , 2009 .

[29]  Donald H. Burn,et al.  Spatial patterns of homogeneous pooling groups for flood frequency analysis , 2003 .

[30]  Marco Franchini,et al.  Physical interpretation and sensitivity analysis of the TOPMODEL , 1996 .

[31]  Ahmed El-Shafie,et al.  Forecasting the Level of Reservoirs Using Multiple Input Fuzzification in ANFIS , 2013, Water Resources Management.

[32]  W. DeBuys.  Seeing Things Whole: The Essential John Wesley Powell , 2001 .

[33]  S. Dingman,et al.  Application of kriging to estimating mean annual precipitation in a region of orographic influence , 1988 .

[34]  Wen‐Cheng Huang,et al.  Streamflow estimation using kriging , 1998 .

[35]  Nicolas G. Wright,et al.  EFFECTS OF RIVER BASIN CLASSIFICATION ON ARTIFICIAL NEURAL NETWORKS BASED UNGAUGED CATCHMENT FLOOD PREDICTION , 2001 .

[36]  Mehdi Vafakhah,et al.  A Wavelet-ANFIS Hybrid Model for Groundwater Level Forecasting for Different Prediction Periods , 2013, Water Resources Management.

[37]  Yangbo Chen.  GIS and Remote Sensing in Hydrology, Water Resources and Environment , 2004 .

[38]  M. J. Hall,et al.  Regional flood frequency analysis for the Gan-Ming River basin in China , 2004 .

[39]  Donald H. Burn,et al.  Estimation of hydrological parameters at ungauged catchments , 1993 .

[40]  Pierre Goovaerts,et al.  Using elevation to aid the geostatistical mapping of rainfall erosivity , 1999 .

[41]  J. S. R. Murthy,et al.  A practical approach to rainfall-runoff modelling in arid zone drainage basins , 1998 .

[42]  D. McCormick,et al.  Turning on and off recurrent balanced cortical activity , 2003, Nature.

[43]  M. Cobaner.  Evapotranspiration estimation by two different neuro-fuzzy inference systems , 2011 .

[44]  Attilio Castellarin,et al.  Geostatistical prediction of flow–duration curves in an index-flow framework , 2014 .

[45]  Soichi Nishiyama,et al.  Neural Networks for Real Time Catchment Flow Modeling and Prediction , 2007 .

[46]  Chung-Chieh Meng,et al.  Deterministic Insight into ANN Model Performance for Storm Runoff Simulation , 2008 .

[47]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[48]  Jingjing Xu,et al.  Heavy metal contamination in arable land of Chongming based on GIS and Geostatistics , 2010, 2010 18th International Conference on Geoinformatics.

[49]  Lawrence Dingman,et al.  Elevation: a major influence on the hydrology of New Hampshire and Vermont, USA / L'altitude exerce une influence importante sur l'hydrologie du New Hampshire et du Vermont, Etats-Unis , 1981 .

[50]  W. Pitts,et al.  A Statistical Consequence of the Logical Calculus of Nervous Nets , 1943 .

[51]  S. H. Ahmadi,et al.  Application and evaluation of kriging and cokriging methods on groundwater depth mapping , 2008, Environmental monitoring and assessment.

[52]  D. Viviroli,et al.  Continuous simulation for flood estimation in ungauged mesoscale catchments of Switzerland - Part II: Parameter regionalisation and flood estimation results , 2009 .

[53]  J. Alcázar,et al.  A neural net model for environmental flow estimation at the Ebro River Basin, Spain , 2008 .

[54]  S. H. Ahmadi,et al.  Geostatistical Analysis of Spatial and Temporal Variations of Groundwater Level , 2007, Environmental monitoring and assessment.

[55]  A. Altunkaynak.  Forecasting Surface Water Level Fluctuations of Lake Van by Artificial Neural Networks , 2007 .

[56]  J. Delgado,et al.  Geostatistical modelling of heavy metal contamination in the topsoil of Guadiamar river margins (S Spain) using a stochastic simulation technique , 2006 .

[57]  Attilio Castellarin,et al.  Regional flow-duration curves: reliability for ungauged basins , 2004 .

[58]  Günter Blöschl,et al.  Spatial prediction on river networks: comparison of top‐kriging with regional regression , 2014 .

[59]  Han Yan,et al.  Adaptive neuro fuzzy inference system for classification of water quality status. , 2010, Journal of environmental sciences.

[60]  L. Braun,et al.  Application of a conceptual runoff model in different physiographic regions of Switzerland , 1992 .

[61]  Neslihan Seçkin,et al.  Modeling flood discharge at ungauged sites across Turkey using neuro-fuzzy and neural networks , 2011 .

[62]  Denis A. Hughes,et al.  Monthly rainfall-runoff models applied to arid and semiarid catchments for water resource estimation purposes , 1995 .

[63]  S. Solomon,et al.  The Use of a Square Grid System for Computer Estimation of Precipitation, Temperature, and Runoff , 1968 .

[64]  V. Singh,et al.  Mathematical models of large watershed hydrology , 2002 .

[65]  R. Abrahart,et al.  Flood estimation at ungauged sites using artificial neural networks , 2006 .

[66]  The baseflow correlation method with multiple gauged sites , 2007 .

[67]  Robert LIN,et al.  NOTE ON FUZZY SETS , 2014 .

[68]  M. H. Quenouille.  Approximate Tests of Correlation in Time‐Series , 1949 .

[69]  Ali Berktay,et al.  Groundwater quality mapping in urban groundwater using GIS , 2010, Environmental monitoring and assessment.

[70]  Chris Barrow,et al.  River Basin Development Planning and Management: A Critical Review , 1998 .

[71]  Enoch M. Dlamini,et al.  Effects of model complexity and structure, data quality, and objective functions on hydrologic modeling , 1997 .

[72]  Khaled Ahmad Aali,et al.  Application of kriging and cokriging in spatial estimation of groundwater quality parameters , 2011 .

[73]  Zaher Mundher Yaseen,et al.  ANN Based Sediment Prediction Model Utilizing Different Input Scenarios , 2015, Water Resources Management.

[74]  R. Wetzel.  Limnology: Lake and River Ecosystems , 1975 .

[75]  Attilio Castellarin,et al.  Regional prediction of flow-duration curves using a three-dimensional kriging , 2014 .

[76]  Ralph A. Wurbs.  Modeling river/reservoir system management, water allocation, and supply reliability , 2005 .

[77]  Timothy C. Coburn,et al.  Geostatistics for Natural Resources Evaluation , 2000, Technometrics.

[78]  Pierre Goovaerts,et al.  Geostatistical modelling of uncertainty in soil science , 2001 .

[79]  Surendra Shrestha,et al.  Design Flood Estimation for Ungauged Catchments: Application of Artificial Neural Networks for Eastern Australia , 2010 .

[80]  Zhandong Sun,et al.  Modelling the stream flow change in a poorly gauged mountainous watershed, southern Tianshan Mountain, using multi-source remote sensing data , 2009, Remote Sensing.

[81]  C. Shu,et al.  Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system , 2008 .

[82]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[83]  Christian W. Dawson,et al.  Neural Network Solutions to Flood Estimation at Ungauged Sites , 2009 .

[84]  Mukand S. Babel,et al.  Application of ANN-Based Streamflow Forecasting Model for Agricultural Water Management in the Awash River Basin, Ethiopia , 2011 .

[85]  C. Lembi.  Limnology, Lake and River Ecosystems , 2001 .

[86]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex Adaptive Systems.

[87]  Patrick Willems,et al.  Spatial and temporal rainfall variability in mountainous areas: A case study from the south Ecuadorian Andes , 2006 .

[88]  T. Ouarda,et al.  Physiographical space‐based kriging for regional flood frequency estimation at ungauged sites , 2004 .

[89]  N. Seçkin,et al.  Comparison of Artificial Neural Network Methods with L-moments for Estimating Flood Flow at Ungauged Sites: the Case of East Mediterranean River Basin, Turkey , 2013, Water Resources Management.

[90]  A. Brath,et al.  Assessing the reliability of regional depth‐duration‐frequency equations for gaged and ungaged sites , 2002 .

[91]  Ahmed El-Shafie,et al.  Enhancing Inflow Forecasting Model at Aswan High Dam Utilizing Radial Basis Neural Network and Upstream Monitoring Stations Measurements , 2009 .

[92]  A. Dégre,et al.  Geostatistical interpolation of daily rainfall at catchment scale: the use of several variogram models in the Ourthe and Ambleve catchments, Belgium , 2011 .

[93]  Etienne Leblois,et al.  Correlation and covariance of runoff revisited , 2011 .

[94]  H. Wendland,et al.  Multivariate interpolation for fluid-structure-interaction problems using radial basis functions , 2001 .

[95]  Jeffrey Marc Yarus,et al.  Practical Geostatistics - An Armchair Overview for Petroleum Reservoir Engineers , 2006 .

[96]  Rory Nathan,et al.  Identification of homogeneous regions for the purposes of regionalisation , 1990 .

[97]  Fi-John Chang,et al.  Adaptive neuro-fuzzy inference system for prediction of water level in reservoir , 2006 .

[98]  P. E. O'connell,et al.  IAHS Decade on Predictions in Ungauged Basins (PUB), 2003–2012: Shaping an exciting future for the hydrological sciences , 2003 .

[99]  Joos Vandewalle,et al.  Modelling and forecasting of hydrological variables using artificial neural networks: the Kafue River sub-basin , 2003 .

[100]  Tommy S. W. Wong,et al.  Evaluation of rainfall and discharge inputs used by Adaptive Network-based Fuzzy Inference Systems (ANFIS) in rainfall–runoff modeling , 2010 .

[101]  G. Blöschl,et al.  Flood frequency regionalisation—spatial proximity vs. catchment attributes , 2005 .

[102]  Nariman Valizadeh.  Daily water level forecasting using adaptive neuro-fuzzy interface system with different scenarios: Klang Gate, Malaysia , 2011 .

[103]  John R. Koza,et al.  Genetic programming 2 - automatic discovery of reusable programs , 1994, Complex adaptive systems.

[104]  G. Blöschl,et al.  Top-kriging - geostatistics on stream networks , 2005 .

[105]  Gail Gong.  Cross-Validation, the Jackknife, and the Bootstrap: Excess Error Estimation in Forward Logistic Regression , 1986 .

[106]  Ahmed El-Shafie,et al.  Adaptive neuro-fuzzy inference system based model for rainfall forecasting in Klang River, Malaysia , 2011 .

[107]  Mohammad Taghi Dastorani,et al.  Using neural networks to predict runoff from ungauged catchments. , 2010 .

[108]  Rasoul Irani,et al.  Evolving neural network using real coded genetic algorithm for permeability estimation of the reservoir , 2011, Expert Syst. Appl..

[109]  S. B. Awulachew,et al.  Estimation of flow in ungauged catchments by coupling a hydrological model and neural networks: case study , 2011 .

[110]  Mehdi Vafakhah,et al.  Application of Several Data-Driven Techniques for Predicting Groundwater Level , 2012, Water Resources Management.

[111]  Ozgur Kisi,et al.  Daily pan evaporation modelling using a neuro-fuzzy computing technique , 2006 .

[112]  Eric Sauquet,et al.  Mapping mean annual river discharges: Geostatistical developments for incorporating river network dependencies , 2006 .

[113]  Amir AghaKouchak,et al.  Application of a Conceptual Hydrologic Model in Teaching Hydrologic Processes , 2010 .

[114]  V. Singh,et al.  LASCAM: large scale catchment model. , 1995 .

[115]  Shang-Lien Lo,et al.  Predicting real-time coagulant dosage in water treatment by artificial neural networks and adaptive network-based fuzzy inference system , 2008, Eng. Appl. Artif. Intell..

[116]  Neal M. Ashkanasy,et al.  Regional Parameters for the Sacramento Model: A Case Study , 1983 .

[117]  Yasuto Tachikawa,et al.  Weather Radar Information and Distributed Hydrological Modelling , 2003 .

[118]  Reza Kerachian,et al.  Developing operating rules for reservoirs considering the water quality issues: Application of ANFIS-based surrogate models , 2010, Expert Syst. Appl..

[119]  Frederick N.-F. Chou,et al.  Spatial Information-Based Back-Propagation Neural Network Modeling for Outflow Estimation of Ungauged Catchment , 2010 .

[120]  V. Singh,et al.  Mathematical Modeling of Watershed Hydrology , 2002 .

[121]  Debashis Chakraborty,et al.  Assessment of groundwater pollution in West Delhi, India using geostatistical approach , 2010, Environmental monitoring and assessment.

[122]  Jing Wang,et al.  Swarm Intelligence in Cellular Robotic Systems , 1993 .

[123]  P. Goovaerts.  Geostatistical approaches for incorporating elevation into the spatial interpolation of rainfall , 2000 .

[124]  D. Neary,et al.  Riparian Areas of the Southwestern United States: Hydrology, Ecology, and Management , 2007 .

[125]  B. Efron,et al.  The Jackknife: The Bootstrap and Other Resampling Plans. , 1983 .

[126]  Yu-Pin Lin,et al.  Delineating the hazard zone of multiple soil pollutants by multivariate indicator kriging and conditioned Latin hypercube sampling , 2010 .

[127]  M. H. Quenouille.  Approximate tests of correlation in time-series 3 , 1949, Mathematical Proceedings of the Cambridge Philosophical Society.

[128]  Alberto Campisano,et al.  Regional Models for the Estimation of Streamflow Series in Ungauged Basins , 2007 .

[129]  K. Bronson,et al.  Cotton lint yield variability in a heterogeneous soil at a landscape scale , 2001 .

[130]  Steven C. Wheelwright,et al.  Forecasting methods and applications. , 1979 .