Tools
Tools
Chaipimonplin, T., See, L. 
ORCID: https://orcid.org/0000-0002-2665-7065, & Kneale, P.
(2011).
Improving neural network for flood forecasting using radar data on the Upper Ping River.
In:
MODSIM 2011 - 19th International Congress on Modelling and Simulation - Sustaining Our Future: Understanding and Living with Uncertainty.
pp. 1070-1076 Perth, WA; Australia.
ISBN 978-098721431-7
Preview |
Text
Improving neural network for flood forecasting using radar data on the Upper Ping River.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
Artificial 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.
| Item Type: | Book Section |
|---|---|
| Uncontrolled Keywords: | Chiang Mai; Flood forecasting; Neural network; Radar data |
| Research Programs: | Ecosystems Services and Management (ESM) |
| Depositing User: | Luke Kirwan |
| Date Deposited: | 25 Jul 2016 14:21 |
| Last Modified: | 27 Aug 2021 17:27 |
| URI: | https://pure.iiasa.ac.at/13410 |
Actions (login required)
 |
View Item |