Author(s)

I. K. Hadihardaja, D. Indrawati, Y. Suryadi & N. S. Griggs

Abstract

Floods, one of classical disaster occurrences, are difficult to identify accurately; most of the incidents have no recorded predictions and floods are generally frequent events with poor data acquisition. Development of a flood database system has become important for improving the management of information with regard to a flood early warning system for vulnerable communities along the flood area. In the case of the Upper Citarum river basin, flooding has occurred since the 1960s and was still happening up until 2010, even though a lot of study has been done and infrastructure has been built. Numerical modelling (using hydrology and hydraulics model) are usually employed to simulate the flood area (Ag), flood depth (hg), and travel time (tpr). However, numerical modelling for flood prediction is too time-consuming to be useful as an early warning system for the mitigation of flood-related damage and loss. Therefore, this model was used to develop a flood database system, based on hypothetical data, in order to develop a recognition pattern for a neural network learning process that will improve the speed and accuracy of flood prediction. To improve the accuracy of numerical modelling and observation, an adjustment was established for an advanced training process which used a generalized regression neural network. In other words, the training and testing data sets were obtained by correcting near-field hydrograph numerical models from hypothetical rainfall.

Keywords

hard and soft computing, flood database, generalised regression neural network