Citation
Abstract
Precipitation is a key driving factor of hydrologic modeling for impact studies. However, there are challenges due to limited long-term data availability and complex parameterizations of existing stochastic weather generators (SWGs) due to spatiotemporal uncertainty. We introduced state-of-the-art Generative Adversarial Network (GAN) as a data-driven multi-site SWG and synthesized extensive hourly precipitation over 30 years at 14 stations. These samples were then fed into an hourly-calibrated SWAT model for streamflow generation. Results showed that the well-trained GAN improved rainfall data by accurately representing spatiotemporal distribution of raw data rather than simply replicating its statistical characteristics. GAN also helped display authentic spatial correlation patterns of extreme rainfall events well. We concluded that GAN offers a superior spatiotemporal distribution of raw data compared to conventional methods, thus enhancing the reliability of flood frequency evaluations.
Download File
Full text not available from this repository.
|
Additional Metadata
Item Type: | Article |
---|---|
Divisions: | Faculty of Engineering |
DOI Number: | https://doi.org/10.1016/j.envsoft.2023.105896 |
Publisher: | Elsevier Ltd |
Keywords: | Complex data distribution; Deep learning; Flood frequency; Generative adversarial network; SWAT; Rain; Spatial distribution; Stochastic systems; Data driven; Hydrologic models; Soil and water assessment tool; Weather; Weather forecasting |
Depositing User: | Mr. Mohamad Syahrul Nizam Md Ishak |
Date Deposited: | 29 Mar 2024 03:28 |
Last Modified: | 29 Mar 2024 03:28 |
Altmetrics: | http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1016/j.envsoft.2023.105896 |
URI: | http://psasir.upm.edu.my/id/eprint/105818 |
Statistic Details: | View Download Statistic |
Actions (login required)
View Item |