Quality control of daily rainfall data with neural networks

A procedure for quality control of daily rainfall, designed to automatically detect erroneous data to be submitted for further manual controls, is herein described. Quality control of daily rainfall data is based on confidence intervals derived by means of neural networks on the basis of contemporaneous data observed at reference stations, since the presence of zero values in the series and the strong variability of precipitation at daily time scale do not allow reliable confidence intervals to be estimated from historical data from the same station. Application of the proposed procedure to automatic stations in Sicily (Italy), enables validation of more than 80% of the data. The accuracy of the procedures is verified by introducing known errors into the available datasets, supposed as correct, and by computing the probabilities of correctly classifying data as validated or not validated. (C) 2008 Elsevier B.V. All rights reserved.