Flash-flood forecasting by means of neural networks and nearest neighbour approach ? a comparative study

A. Piotrowski (1) , J. J. Napiórkowski (1) , P.M. Rowi?ski (1)

1 Institute of Geophysics

In this paper, Multi-Layer Perceptron and Radial-Basis Function Neural Networks, along with the Nearest Neighbour approach and linear regression are utilized for flash-flood forecasting in the mountainous Nysa Klodzka river catchment. It turned out that the Radial-Basis Function Neural Network is the best model for 3- and 6-h lead time prediction and the only reliable one for 9-h lead time forecasting for the largest flood used as a test case.

Domaines: Cosmologie et astrophysique extra-galactique [astro-ph.CO]; Astrophysique [astro-ph]; Sciences de la Terre

A. Piotrowski, J. J. Napiórkowski, P.M. Rowi?ski. Flash-flood forecasting by means of neural networks and nearest neighbour approach ? a comparative study. Nonlinear Processes in Geophysics, 2006, 13 (4), pp.443-448. ⟨hal-00302773⟩