Online flood forecasting in fast responding catchments on the basis of a synthesis of artificial neural networks and process models

A detailed and comprehensive description of the state of the art in the field of flood forecasting opens this work. Advantages and shortcomings of currently available methods are identified and discussed. Amongst others, one important aspect considers the most exigent weak point of today’s forecasting systems: The representation of all the fundamentally different event specific patterns of flood formation with one single set of model parameters. The study exemplarily proposes an alternative for overcoming this restriction by taking into account the different process characteristics of flood events via a dynamic parameterisation strategy. Other fundamental shortcomings in current approaches especially restrict the potential for real time flash flood forecasting, namely the considerable computational requirements together with the rather cumbersome operation of reliable physically based hydrologic models. The new PAI-OFF methodology (Process Modelling and Artificial Intelligence for Online Flood Forecasting) considers these problems and offers a way out of the general dilemma. It combines the reliability and predictive power of physically based, hydrologic models with the operational advantages of artificial intelligence. These operational advantages feature extremely low computation times, absolute robustness and straightforward operation. Such qualities easily allow for predicting flash floods in small catchments taking into account precipitation forecasts, whilst extremely basic computational requirements open the way for online Monte Carlo analysis of the forecast uncertainty. The study encompasses a detailed analysis of hydrological modeling and a problem specific artificial intelligence approach in the form of artificial neural networks, which build the PAI-OFF methodology. Herein, the synthesis of process modelling and artificial neural networks is achieved by a special training procedure. It optimizes the network according to the patterns of possible catchment reaction to rainstorms. This information is provided by means of a physically based catchment model, thus freeing the artificial neural network from its constriction to the range of observed data – the classical reason for unsatisfactory predictive power of netbased approaches. Instead, the PAI-OFF-net learns to portray the dominant process controls of flood formation in the considered catchment, allowing for a reliable predictive performance. The work ends with an exemplary forecasting of the 2002 flood in a 1700 km2 East German watershed.

[1]  M. Kelsch.  Hydrometeorological Characteristics of Flash Floods , 2001 .

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

[3]  Mario L. V. Martina,et al.  A Bayesian decision approach to rainfall thresholds based flood warning , 2005 .

[4]  K Beven,et al.  On the concept of model structural error. , 2005, Water science and technology : a journal of the International Association on Water Pollution Research.

[5]  Ezio Todini,et al.  TOPKAPI: a model for the representation of the rainfall‐runoff process at different scales , 2002 .

[6]  A. Bonafe,et al.  Neural Networks For Daily Mean FlowForecasting , 1970 .

[7]  K. Cauwenberghs,et al.  An innovative flood forecasting system for the Demer basin: A case study , 2005 .

[8]  H. K. Cigizoglu,et al.  Incorporation of ARMA models into flow forecasting by artificial neural networks , 2003 .

[9]  Joseph R. Bocchieri,et al.  National Weather Service Warning Performance Based on the WSR-88D. , 1994 .

[10]  Raúl Rojas,et al.  Neural Networks - A Systematic Introduction , 1996 .

[11]  M. Kang,et al.  APPLICATION OF GREY MODEL AND ARTIFICIAL NEURAL NETWORKS TO FLOOD FORECASTING 1 , 2006 .

[12]  Carrie Knerr,et al.  Time series prediction using neural networks , 2004 .

[13]  R. Iman,et al.  A distribution-free approach to inducing rank correlation among input variables , 1982 .

[14]  Neil McIntyre,et al.  Towards reduced uncertainty in conceptual rainfall‐runoff modelling: dynamic identifiability analysis , 2003 .

[15]  Michael Rode,et al.  Investigation of parameter uncertainty and identifiability of the hydrological model WaSiM-ETH , 2006 .

[16]  R. D. Black,et al.  Partial Area Contributions to Storm Runoff in a Small New England Watershed , 1970 .

[17]  Sevket Durucan,et al.  River flow prediction using artificial neural networks: generalisation beyond the calibration range. , 2000 .

[18]  W. Green,et al.  Studies on soil physics, I Flow of water and air through soils , 1911 .

[19]  S. Barbero,et al.  Operational hydro-meteorological warning and real-time flood forecasting: the Piemonte Region case study , 2005 .

[20]  Soroosh Sorooshian,et al.  A chaotic approach to rainfall disaggregation , 2001 .

[21]  P. Julien,et al.  Time to equilibrium for spatially variable watersheds , 1995 .

[22]  David R. Dawdy,et al.  Physical interpretations of regional variations in the scaling exponents of flood quantiles , 1995 .

[23]  Christel Prudhomme,et al.  Uncertainty and climate change impact on the flood regime of small UK catchments , 2003 .

[24]  Charles A. Doswell,et al.  Precipitation Forecasting Using a Neural Network , 1999 .

[25]  Michael Bruen,et al.  Functional networks in real-time flood forecasting—a novel application , 2005 .

[26]  Slobodan P. Simonovic,et al.  Short term streamflow forecasting using artificial neural networks , 1998 .

[27]  V. Ponce.  Engineering Hydrology: Principles and Practices , 1989 .

[28]  Anthony J. Jakeman,et al.  RELATIONSHIPS BETWEEN CATCHMENT ATTRIBUTES AND HYDROLOGICAL RESPONSE CHARACTERISTICS IN SMALL AUSTRALIAN MOUNTAIN ASH CATCHMENTS , 1996 .

[29]  K. Beven,et al.  Bayesian Estimation of Uncertainty in Runoff Prediction and the Value of Data: An Application of the GLUE Approach , 1996 .

[30]  Arlen Feldman,et al.  Closure of "Evolution of Clark’s Unit Graph Method to Spatially Distributed Runoff" , 1999 .

[31]  C. Doswell,et al.  Flash Flood Forecasting: An Ingredients-Based Methodology , 1996 .

[32]  Eric A. Anderson,et al.  National Weather Service river forecast system: snow accumulation and ablation model , 1973 .

[33]  Oscar J. Mesa,et al.  Multiscaling theory of flood peaks: Regional quantile analysis , 1994 .

[34]  Y. Gyasi‐Agyei.  Stochastic disaggregation of daily rainfall into one-hour time scale , 2005 .

[35]  Milton S. Boyd,et al.  Forecasting futures trading volume using neural networks , 1995 .

[36]  Jan Feyen,et al.  Use of sensitivity and uncertainty measures in distributed hydrological modeling with an application to the MIKE SHE model , 2002 .

[37]  S. Dyck,et al.  Grundlagen der Hydrologie , 1983 .

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

[39]  John Doherty,et al.  Efficient accommodation of local minima in watershed model calibration , 2006 .

[40]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[41]  R. Spear.  Eutrophication in peel inlet—II. Identification of critical uncertainties via generalized sensitivity analysis , 1980 .

[42]  H. Halff,et al.  Predicting Runoff from Rainfall Using Neural Networks , 1993 .

[43]  J. O’Connor,et al.  Spatial distribution of the largest rainfall‐runoff floods from basins between 2.6 and 26,000 km2 in the United States and Puerto Rico , 2004 .

[44]  Christian W. Dawson,et al.  An artificial neural network approach to rainfall-runoff modelling , 1998 .

[45]  Robert M. Pap,et al.  Handbook of neural computing applications , 1990 .

[46]  Ana P. Barros,et al.  Quantitative flood forecasting using multisensor data and neural networks , 2001 .

[47]  N. J. De Vos.  Rainfall-Runoff modelling using artificial neural networks , 2003 .

[48]  Keith Beven,et al.  Changing ideas in hydrology — The case of physically-based models , 1989 .

[49]  Konstantine P. Georgakakos,et al.  On the design of national, real-time-warning systems with capability for site-specific, flash-flood forecasts , 1986 .

[50]  A. W. Minns,et al.  The extrapolation of artificial neural networks for the modelling of rainfall-runoff relationships , 2005 .

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

[52]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[53]  David R. Maidment,et al.  Developing a spatially distributed unit hydrograph by using GIS , 1993 .

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

[55]  Christian W. Dawson,et al.  Hydrological modelling using artificial neural networks , 2001 .

[56]  Robert J. Kuligowski,et al.  Experiments in Short-Term Precipitation Forecasting Using Artificial Neural Networks , 1998 .

[57]  Henrik Madsen,et al.  An evaluation of the impact of model structure on hydrological modelling uncertainty for streamflow simulation , 2004 .

[58]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[59]  S. Sorooshian,et al.  Comparison of simple versus complex distributed runoff models on a midsized semiarid watershed , 1994 .

[60]  Khashayar Khorasani,et al.  Constructive feedforward neural networks using Hermite polynomial activation functions , 2005, IEEE Transactions on Neural Networks.

[61]  Tomas Vitvar,et al.  A comparative study in modelling runoff and its components in two mountainous catchments , 2003 .

[62]  Jörg Schulla,et al.  Hydrologische Modellierung von Flussgebieten zur Abschätzung der Folgen von Klimaänderungen , 1997 .

[63]  Mu-Lan Zhu,et al.  Application of Neural Networks to Runoff Prediction , 1994 .

[64]  Bhaskar D. Rao,et al.  A generalized learning paradigm exploiting the structure of feedforward neural networks , 1996, IEEE Trans. Neural Networks.

[65]  Roberto Battiti,et al.  Accelerated Backpropagation Learning: Two Optimization Methods , 1989, Complex Syst..

[66]  Katherine K. Hirschboeck.  Catastrophic flooding and atmospheric circulation anomalies , 2020, Catastrophic Flooding.

[67]  Joydeep Ghosh,et al.  Approximation of multivariate functions using ridge polynomial networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[68]  M. Castellano-Méndez,et al.  Modelling of the monthly and daily behaviour of the runoff of the Xallas river using Box-Jenkins and neural networks methods , 2004 .

[69]  S. Sorooshian,et al.  Effective and efficient global optimization for conceptual rainfall‐runoff models , 1992 .

[70]  E. Todini,et al.  Stochastic rainfall interpolation and downscaling , 2001 .

[71]  Roberto Revelli,et al.  A comparison of nonlinear flood forecasting methods , 2003 .

[72]  K. Lam,et al.  River flow time series prediction with a range-dependent neural network , 2001 .

[73]  Keith Beven,et al.  Equifinality, data assimilation, and uncertainty estimation in mechanistic modelling of complex environmental systems using the GLUE methodology , 2001 .

[74]  E. Todini,et al.  Towards a comprehensive physically-based rainfall-runoff model , 2002 .

[75]  L. Braun.  Simulation of snowmelt runoff in lowland and lower Alpine regions of Switzerland , 1984 .

[76]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[77]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[78]  Iu A. Shreider,et al.  Die Monte-Carlo-Methode und ihre Verwirklichung mit elektronischen Digitalrechnern , 1964 .

[79]  G. Hornberger,et al.  Approach to the preliminary analysis of environmental systems , 1981 .

[80]  B. S. Thandaveswara,et al.  A non-linear rainfall–runoff model using an artificial neural network , 1999 .

[81]  N. G. Mackay,et al.  Disaggregation of spatial rainfall fields for hydrological modelling , 2001 .

[82]  P. Cappus.  ÉTUDE DES LOIS DE L'ÉCOULEMENT - APPLICATION AU CALCUL ET À LA PRÉVISION DES DÉBITS , 1960 .

[83]  Christian Onof,et al.  Rainfall disaggregation using adjusting procedures on a Poisson cluster model , 2001 .

[84]  P. E. O'connell,et al.  An introduction to the European Hydrological System — Systeme Hydrologique Europeen, “SHE”, 1: History and philosophy of a physically-based, distributed modelling system , 1986 .

[85]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[86]  J. Monteith.  Evaporation and environment. , 1965, Symposia of the Society for Experimental Biology.

[87]  G. Pegram,et al.  Downscaling rainfields in space and time, using the String of Beads model in time series mode , 2001 .

[88]  E. Todini.  The ARNO rainfall-runoff model , 1996 .

[89]  R. Hock.  A distributed temperature-index ice- and snowmelt model including potential direct solar radiation , 1999, Journal of Glaciology.

[90]  R. Merz,et al.  A process typology of regional floods , 2003 .

[91]  U. C. Kothyari,et al.  Annual Runoff Estimation for Catchments in India , 1991 .

[92]  Jason Smith,et al.  Neural-Network Models of Rainfall-Runoff Process , 1995 .

[93]  A. Baltensweiler,et al.  Spatially distributed hydrotope-based modelling of evapotranspiration and runoff in mountainous basins , 1999 .