Quantitative flood forecasting using multisensor data and neural networks

Abstract Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict streamflow and flash floods. Previously, neural networks were used to develop a Quantitative Precipitation Forecasting model that highly improved forecasting skill at specific locations in Pennsylvania, using both Numerical Weather Prediction output and rainfall and radiosonde data. The objective of this study was to modify the existing artificial neural network model to include the evolving structure and frequency of intense weather systems in the mid-Atlantic region of the United States for improved flood forecasting. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems, and convective cloud clusters as input. The convective classification and automated tracking system was used to identify and quantify storm properties such as life time, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships among weather systems, rainfall production and streamflow response in the study area. Here, we present results from the application of the quantitative flood forecasting model in four watersheds on the leeward side of the Appalachian mountains in the mid-Atlantic region. The areal extent of the watersheds ranges from 750 to 8700 km 2 . The reduction in the mean-squared error of the peak streamflow with respect to persistence was up to 60% for the 24 h lead-time forecasts. For the 18 h lead-time forecasts, the number of successful forecasts for streamflow peaks in the upper 5% percentile was consistently above 60%, and close to 80–90%.

[1]  Thomas Kailath,et al.  Hoo Optimality Criteria for LMS and Backpropagation , 1993, NIPS 1993.

[2]  Lucien Duckstein,et al.  Fuzzy rule-based classification of atmospheric circulation patterns , 1995 .

[3]  A. Barros,et al.  Localized Precipitation Forecasts from a Numerical Weather Prediction Model Using Artificial Neural Networks , 1998 .

[4]  S. Sorooshian,et al.  Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks , 1997 .

[5]  A. Soldati,et al.  River flood forecasting with a neural network model , 1999 .

[6]  Akira Kawamura,et al.  Real-time rainfall prediction at small space-time scales using a two-dimensional stochastic advection-diffusion model , 1993 .

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

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

[9]  A. Barros,et al.  Orographic Effects during a Severe Wintertime Rainstorm in the Appalachian Mountains , 1998 .

[10]  H. Maier,et al.  The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters , 1996 .

[11]  Richard L. Bankert,et al.  Cloud Classification of AVHRR Imagery in Maritime Regions Using a Probabilistic Neural Network , 1994 .

[12]  Thomas Kailath,et al.  Optimal Training Algorithms and their Relation to Backpropagation , 1994, NIPS.

[13]  D. J. Gorney,et al.  A sunspot maximum prediction using a neural network , 1990 .

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

[15]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

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

[17]  Desmond Fletcher,et al.  Forecasting with neural networks: An application using bankruptcy data , 1993, Inf. Manag..

[18]  J. Evans,et al.  A Procedure for Automated Satellite-Based Identification and Climatology Development of Various Classes of Organized Convection , 1996 .

[19]  Caren Marzban,et al.  A Neural Network for Tornado Prediction Based on Doppler Radar-Derived Attributes , 1996 .

[20]  A. W. Minns,et al.  The classification of hydrologically homogeneous regions , 1999 .

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