A conceptual and neural network model for real-time flood forecasting of the Tiber River in Rome

Abstract Rome is at risk from flooding when extreme events with a return period of about 200 years occur. For this reason, an accurate real-time flood forecasting system may be a useful non-structural countermeasure. Two different approaches are considered to develop a real-time forecasting system capable of predicting hourly water levels at Ripetta stream gauging station in Rome. The first is an adaptive, conceptual model (TFF model), which consists of a rainfall-runoff model that simulates the contribution of 41 ungauged sub-basins (covering approximately 30% of the catchment area) of the Tiber River and a hydraulic model to route the flood through the hydrographic network. The rainfall-runoff model is calibrated online during each flood event at every time step via an adaptive procedure while the flood routing model parameters were calibrated offline and held constant during the forecast. The second approach used is a data-driven one through the application of an artificial neural network (TNN model). Feedforward networks trained with backpropagation and Bayesian regularization were developed using a continuous historical dataset. Both models were used to forecast the most recent significant floods that occurred in Rome (November 2005 and December 2008) with lead times of 12 and 18 h. The results show good performance using both models when compared with observations for a series of absolute and relative performance measures as well as a visual inspection of the hydrographs. At present both models are suitable for real-time forecasting and the power of an integrated approach is still to be investigated.

[1]  Robert J. Abrahart,et al.  HydroTest: A web-based toolbox of evaluation metrics for the standardised assessment of hydrological forecasts , 2007, Environ. Model. Softw..

[2]  J. Cunge,et al.  Practical aspects of computational river hydraulics , 1980 .

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

[4]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[5]  Vijay P. Singh,et al.  A real-time stage Muskingum forecasting model for a site without rating curve , 2006 .

[6]  Ezio Todini,et al.  An operational decision support system for flood risk mapping, forecasting and management , 1999 .

[7]  F. Savi,et al.  Monte Carlo analysis of probability of inundation of Rome , 2007, Environ. Model. Softw..

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

[9]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[10]  Florisa Melone,et al.  Flood forecasting and infiltration modelling , 2004 .

[11]  F. Savi,et al.  Real-time flood forecasting of the Tiber river in Rome , 2006 .

[12]  N. Lauzon,et al.  Generalisation for neural networks through data sampling and training procedures, with applications to streamflow predictions , 2004 .

[13]  Q. J. Wang.  The Genetic Algorithm and Its Application to Calibrating Conceptual Rainfall-Runoff Models , 1991 .

[14]  P. Kitanidis,et al.  Real‐time forecasting with a conceptual hydrologic model: 2. Applications and results , 1980 .

[15]  Holger R. Maier,et al.  The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study , 1998 .

[16]  Corrado Corradini,et al.  Flood forecasting and infiltration modeling/Prévision de crue et modélisation de l’infiltration , 2004 .

[17]  Holger R. Maier,et al.  Understanding the behaviour and optimising the performance of back-propagation neural networks: an empirical study , 1998 .