River flood forecasting with a neural network model

Abstract

Abstract. A neural network model was developed to analyze and forecast the behavior of the river Tagliamento, in Italy, during heavy rain periods. The model makes use of distributed rainfall information coming from several rain gauges in the mountain district and predicts the water level of the river at the section closing the mountain district. The water level at the closing section in the hours preceding the event was used to characterize the behavior of the river system subject to the rainfall perturbation. Model predictions are very accurate (i.e., mean square error is less than 4%) when the model is used with a 1-hour time horizon. Increasing the time horizon, thus making the model suitable for flood forecasting, decreases the accuracy of the model. A limiting time horizon is found corresponding to the minimum time lag between the water level at the closing section and the rainfall, which is characteristic of each flooding event and depends on the rainfall and on the state of saturation of the basin. Performance of the model remains satisfactory up to 5 hours. A model of this type using just rainfall and water level information does not appear to be capable of predicting beyond this time limit.

Artificial neural networks and high and low flows in various climate regimes

“…Campolo et al, 1999;Imrie et al, 2000), since it is more effective and efficient than the widely used back-propagation algorithms. Furthermore, the model has been shown to capture the global or near-global solutions of a problem with fewer function evaluations.…”

“…Although ANNs have already been shown to produce river flow predictions well compared to conventional models (Crespo & Mora, 1993;Karunanithi et al, 1994;Hsu et al, 1995;Abrahart & Kneale, 1997;Dawson & Wilby, 1998;Abrahart & See, 2000;Tingsanchali & Gautam, 2000), their ability to capture high and low flows is restricted to the research environment (Minns & Hall, 1996), and they often overestimate or underestimate high and low flows (Dawson & Wilby, 1998;Campolo et al, 1999;Karunanithi et al, 1994).…”

“…For example, Dawson & Wilby (1998), and Campolo et al (1999) suggested that the underestimation of peak flows could be attributed to a lack of information provided to the network, such as the antecedent rainfall. Karunanithi et al (1994) suggested that the problem could be alleviated by including more high-flow patterns in the training data sets, while Hsu et al (1995) proposed log-transformations of flow values to reduce the gap between the high-and low-flow conditions.…”

Water demand forecasting using extreme learning machines

“…Following this, the optimal network geometry for the ANN model was identified by trial and error, and the number of hidden neurons that produced the lowest generalization error, ranging between 1 and 15, was considered to be the optimal structure [JIA, CUL-VER 2006]. ANN models were initially developed using the significant inputs that were log-transformed and linearly scaled to a range of 0 to 1 [CAMPOLO et al 1999]. A second-order training method, the Levenberg-Marquardt optimization method was used to minimize the mean square error (MSE) between the forecasted and observed UWD values.…”

Comparison of fuzzy inference systems for streamflow prediction

“…Their applications range from the forecasting of hourly and daily river stages or discharges (Thirumalaiah & Deo, 1998;Campolo et al, 1999Campolo et al, , 2003Imrie et al, 2000), groundwater modelling (Yang et al, 1997;Lallahem & Mania, 2003), and reservoir operation (Jain et al, 1999;Hasebe & Nagayama, 2002) to rainfall-runoff modelling (Shamseldin, 1997;Tokar & Markus, 2000).…”