Comparison of an artificial neural network and a conceptual rainfall–runoff model in the simulation of ephemeral streamflow

ABSTRACT The rainfall–runoff process is governed by parameters that can seldom be measured directly for use with distributed models, but are rather inferred by expert judgment and calibrated against historical records. Here, a comparison is made between a conceptual model (CM) and an artificial neural network (ANN) for their ability to efficiently model complex hydrological processes. The Sacramento soil moisture accounting model (SAC-SMA) is calibrated using a scheme based on genetic algorithms and an input delay neural network (IDNN) is trained for variable delays and hidden layer neurons which are thoroughly discussed. The models are tested for 15 ephemeral catchments in Crete, Greece, using monthly rainfall, streamflow and potential evapotranspiration input. SAC-SMA performs well for most basins and acceptably for the entire sample with R2 of 0.59–0.92, while scoring better for high than low flows. For the entire dataset, the IDNN improves simulation fit to R2 of 0.70–0.96 and performs better for high flows while being outmatched in low flows. Results show that the ANN models can be superior to the conventional CMs, as parameter sensitivity is unclear, but CMs may be more robust in extrapolating beyond historical record limits and scenario building. EDITOR M.C. Acreman; ASSOCIATE EDITOR not assigned

[1]  Paulin Coulibaly,et al.  Improving groundwater level forecasting with a feedforward neural network and linearly regressed projected precipitation , 2008 .

[2]  J. McNair,et al.  COMPARISON OF PROCESS‐BASED AND ARTIFICIAL NEURAL NETWORK APPROACHES FOR STREAMFLOW MODELING IN AN AGRICULTURAL WATERSHED 1 , 2006 .

[3]  Ian Flood,et al.  Neural Networks in Civil Engineering. I: Principles and Understanding , 1994 .

[4]  Keith W. Hipel.  Stochastic and statistical methods in hydrology and environmental engineering , 1994 .

[5]  R. W. Hann,et al.  Optimal Operation of Large Agricultural Watersheds with Water Quality Restraints , 1978 .

[6]  Tsung-Yi Pan,et al.  State space neural networks for short term rainfall-runoff forecasting , 2004 .

[7]  Richard H. McCuen,et al.  Hydrologic modeling: Statistical methods and applications , 1986 .

[8]  S. Sorooshian,et al.  A Shuffled Complex Evolution Metropolis algorithm for optimization and uncertainty assessment of hydrologic model parameters , 2002 .

[9]  Jagadeesh Anmala,et al.  Rainfall-Runoff Modeling Using Artificial Neural Networks , 2010 .

[10]  B. Bobée,et al.  Improving extreme hydrologic events forecasting using a new criterion for artificial neural network selection , 2001 .

[11]  Kuolin Hsu,et al.  Artificial Neural Network Modeling of the Rainfall‐Runoff Process , 1995 .

[12]  Naota Hanasaki,et al.  A global water scarcity assessment under Shared Socio-economic Pathways – Part 1: Water use , 2012 .

[13]  N. J. DE VOS,et al.  Multi-objective performance comparison of an artificial neural network and a conceptual rainfall—runoff model , 2007 .

[14]  Bernard Bobée,et al.  Prévision hydrologique par réseaux de neurones artificiels : état de l'art , 1999 .

[15]  J. David Fuller,et al.  Back propagation in time‐series forecasting , 1995 .

[16]  Pascal Côté,et al.  Comparison of Stochastic Optimization Algorithms in Hydrological Model Calibration , 2014 .

[17]  Jeroen M. Schoorl,et al.  Evaluating the hydrological component of the new catchment-scale sediment delivery model LAPSUS-D , 2014 .

[18]  Keith Beven,et al.  The future of distributed models: model calibration and uncertainty prediction. , 1992 .

[19]  Juraj Lieskovský,et al.  MODELLING THE EFFECT OF VEGETATION COVER AND DIFFERENT TILLAGE PRACTICES ON SOIL EROSION IN VINEYARDS: A CASE STUDY IN VRÁBLE (SLOVAKIA) USING WATEM/SEDEM , 2014 .

[20]  Chuntian Cheng,et al.  Comparison of three global optimization algorithms for calibration of the Xinanjiang model parameters , 2013 .

[21]  N. Raghuwanshi,et al.  Rainfall-Runoff Modeling: Comparison of Two Approaches with Different Data Requirements , 2010 .

[22]  John R. Williams,et al.  LARGE AREA HYDROLOGIC MODELING AND ASSESSMENT PART I: MODEL DEVELOPMENT 1 , 1998 .

[23]  Ronny Berndtsson,et al.  Monthly runoff simulation: Comparing and combining conceptual and neural network models , 2006 .

[24]  Felipe J. Colón-González,et al.  Multimodel assessment of water scarcity under climate change , 2013, Proceedings of the National Academy of Sciences.

[25]  Allen T. Hjelmfelt,et al.  Artificial Neural Networks as Unit Hydrograph Applications , 1993 .

[26]  P. Döll,et al.  How is the impact of climate change on river flow regimes related to the impact on mean annual runoff? A global-scale analysis , 2012 .

[27]  José Neves,et al.  Preventing Premature Convergence to Local Optima in Genetic Algorithms via Random Offspring Generation , 1999, IEA/AIE.

[28]  J. Poesen,et al.  ASSESSING THE PERFORMANCE OF A SPATIALLY DISTRIBUTED SOIL EROSION AND SEDIMENT DELIVERY MODEL (WATEM/SEDEM) IN NORTHERN ETHIOPIA , 2013 .

[29]  Nicolas Gagarin,et al.  An Artificial Neural Network for Computing Sediment Transport , 1993 .

[30]  Ozgur Kisi,et al.  Streamflow Forecasting Using Different Artificial Neural Network Algorithms , 2007 .

[31]  Dimitri P. Solomatine,et al.  River flow forecasting using artificial neural networks , 2001 .

[32]  Quan J. Wang,et al.  Using genetic algorithms to optimise model parameters , 1997 .

[33]  Ian Flood,et al.  Neural networks in civil engineering. II: Systems and application , 1994 .

[34]  H. Watanabe,et al.  Prediction of Daily Water Demands by Neural Networks , 1994 .

[35]  Pute Wu,et al.  EFFECTS OF LAND USE ON SOIL MOISTURE VARIATIONS IN A SEMI‐ARID CATCHMENT: IMPLICATIONS FOR LAND AND AGRICULTURAL WATER MANAGEMENT , 2014 .

[36]  Tawatchai Tingsanchali,et al.  Application of tank, NAM, ARMA and neural network models to flood forecasting , 2000 .

[37]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[38]  Soroosh Sorooshian,et al.  Status of Automatic Calibration for Hydrologic Models: Comparison with Multilevel Expert Calibration , 1999 .

[39]  P. C. Nayak,et al.  Rainfall-runoff modeling using conceptual, data driven, and wavelet based computing approach , 2013 .

[40]  J. Nyssen,et al.  TWENTIETH CENTURY LAND RESILIENCE IN MONTENEGRO AND CONSEQUENT HYDROLOGICAL RESPONSE , 2014 .

[41]  Witold F. Krajewski,et al.  Rainfall forecasting in space and time using a neural network , 1992 .

[42]  V. Singh,et al.  Soil Conservation Service Curve Number (SCS-CN) Methodology , 2003 .

[43]  M. Märker,et al.  Modelling Post‐Tree‐Harvesting Soil Erosion and Sediment Deposition Potential in the Turano River Basin (Italian Central Apennine) , 2015 .

[44]  Eric Gaume,et al.  Over-parameterisation, a major obstacle to the use of artificial neural networks in hydrology? , 2003 .

[45]  S. Sorooshian,et al.  Shuffled complex evolution approach for effective and efficient global minimization , 1993 .

[46]  Jose D. Salas,et al.  Predicting Streamflows Based on Neural Networks , 1995 .

[47]  E. Asphaug,et al.  Global Scale Impacts , 2015, 1504.02389.

[48]  Young-Oh Kim,et al.  Rainfall‐runoff models using artificial neural networks for ensemble streamflow prediction , 2005 .

[49]  N. Arnell,et al.  A global assessment of the impact of climate change on water scarcity , 2016, Climatic Change.

[50]  Lindell Ormsbee,et al.  Optimal functional forms for estimation of missing precipitation data. , 2009 .

[51]  S. Keesstra.  Impact of natural reforestation on floodplain sedimentation in the Dragonja basin, SW Slovenia , 2007 .

[52]  N. Arnell,et al.  The global-scale impacts of climate change on water resources and flooding under new climate and socio-economic scenarios , 2013, Climatic Change.

[53]  V. Singh,et al.  SCS-CN Method , 2003 .

[54]  Momcilo Markus,et al.  PRECIPITATION-RUNOFF MODELING USING ARTIFICIAL NEURAL NETWORKS AND CONCEPTUAL MODELS , 2000 .

[55]  Thomas A. McMahon,et al.  Physically based hydrologic modeling: 2. Is the concept realistic? , 1992 .

[56]  N. Crawford,et al.  DIGITAL SIMULATION IN HYDROLOGY' STANFORD WATERSHED MODEL 4 , 1966 .

[57]  L. S. Pereira,et al.  Crop evapotranspiration : guidelines for computing crop water requirements , 1998 .

[58]  Ronald L. Bingner,et al.  Estimation of Runoff, Peak Discharge and Sediment Load at the Event Scale in a Medium‐Size Mediterranean Watershed Using the Annagnps Model , 2015 .

[59]  F. Ziadat,et al.  EFFECT OF RAINFALL INTENSITY, SLOPE, LAND USE AND ANTECEDENT SOIL MOISTURE ON SOIL EROSION IN AN ARID ENVIRONMENT , 2013 .

[60]  Ioannis K. Tsanis,et al.  Seasonality of floods and their hydrometeorologic characteristics in the island of Crete. , 2010 .

[61]  Moonis Ali,et al.  Multiple Approaches to Intelligent Systems , 1999, Lecture Notes in Computer Science.

[62]  A. Shamseldin.  Application of a neural network technique to rainfall-runoff modelling , 1997 .

[63]  Alfred Stein,et al.  Assessment of a conceptual hydrological model and artificial neural networks for daily outflows forecasting , 2013, International Journal of Environmental Science and Technology.

[64]  S. Keesstra,et al.  Meso‐scale catchment sediment budgets: combining field surveys and modeling in the Dragonja catchment, southwest Slovenia , 2009 .

[65]  François Anctil,et al.  Impact of the length of observed records on the performance of ANN and of conceptual parsimonious rainfall-runoff forecasting models , 2004, Environ. Model. Softw..

[66]  D. Yates.  WatBal: an integrated water balance model for climate impact assessment of river basin runoff , 1996 .

[67]  A. Noble,et al.  ADAPTING TO CLIMATE CHANGE BY IMPROVING WATER PRODUCTIVITY OF SOILS IN DRY AREAS , 2013 .

[68]  Jorge J. Moré,et al.  The Levenberg-Marquardt algo-rithm: Implementation and theory , 1977 .

[69]  Edvaldo,et al.  Avaliação da erosão hídrica e transporte de sedimentos através do modelo hidrossedimentológico SWAT (Soil and Water Assessment Tool) , 2014 .

[70]  J. F. Martínez-Murillo,et al.  Seasonal changes in the soil hydrological and erosive response depending on aspect, vegetation type and soil water repellency in different Mediterranean microenvironments , 2013 .

[71]  Keith Beven,et al.  Dalton Medal Lecture: How far can we go in distributed hydrological modelling? , 2001 .