IIASA RepositoryImproving neural network for flood forecasting using radar data on the Upper Ping RiverT.ChaipimonplinauthorL.SeeauthorP.KnealeauthorArtificial Neural Networks (ANNs) and other data-driven methods are appearing with increasing frequency in the literature for the prediction of water discharge or stage. Unfortunately, many of these data-driven models are used as the forecasting tools only short lead times where unsurprisingly they perform very well. There have not been much documented attempts at predicting floods at longer and more useful lead times for flood warning. In this paper ANNs flood forecasting model are developed for the Upper Ping River, Chiang Mai, Thailand. Raw radar reflectively data are used as the primary inputs and water stage are used as the additional inputs, also four input determination techniques (Correlation, Stepwise regression, combination between Correlation and Stepwise Regression and Genetic algorithms) are applied to select the most appropriated inputs. Normally, the ANNs model can predict up to 6 hours when only water stage used as the input data and the lead time can be increased up to 24 hours by using only radar data. In addition, combination of the input between water stage and radar data, gave the overall result better then using only water stage or radar data, also selecting different appropriated inputs could improve model's performance.2011-12Book Section

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant IIASA Repository the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that IIASA Repository does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at IIASA Repository) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.