Comparison of a Hybrid Neural Network and Semi-distributed Simulator for Stream Flow Prediction
Hydrological models are widely used for the simulation of stream flow in order to aid water resources planning and management in catchment or river basin. Numerous hydrological models have been developed based on different theories. Performance of such mo
- PDF / 387,355 Bytes
- 13 Pages / 439.37 x 666.142 pts Page_size
- 24 Downloads / 196 Views
Abstract Hydrological models are widely used for the simulation of stream flow in order to aid water resources planning and management in catchment or river basin. Numerous hydrological models have been developed based on different theories. Performance of such models depends on hydro-climatic setting of a catchment. In the present study, performance of a widely used physically based distributed model known as Soil and Water Assessment (SWAT) and a data-driven model, namely hybrid artificial neural network (HANN), has been evaluated to simulate stream flow in an arid catchment located in the south of Iran. Data related to topography, hydrometeorology, land cover, and soil were collected and processed for this purpose. The models were calibrated and validated with same time period to evaluate the advantage and disadvantages of different models. The results showed SWAT outperformed HANN in terms of relative errors such as Nash-Sutcliffe efficiency and percent of bias during model validation. Other error indicates, namely root mean square error (RMSE), mean square error, and mean relative error (MRE), were found close to zero for SWAT during both model calibration and validation. The study suggests that both models have their own promising flow prediction due to their own features and capabilities for daily flow. Keywords SWAT
Hybrid neural network Hydrologic modeling Streamflow
1 Introduction Estimation of mean and seasonal or daily fluctuation of stream flow is essential for water managers, planning authorities, and disaster mitigation authorities. Long-term simulation of stream flow in catchment or river basin is also required for water M. Jajarmizadeh (&) L.M. Sidek H. Basri College of Engineering, Universiti Tenaga Nasional Malaysia, Putrajaya, Malaysia e-mail: [email protected] S. Harun S. Shahid Faculty of Civil Engineering, Universiti Teknologi Malaysia, Skudai, Malaysia © Springer Science+Business Media Singapore 2016 W. Tahir et al. (eds.), ISFRAM 2015, DOI 10.1007/978-981-10-0500-8_10
115
116
M. Jajarmizadeh et al.
resource management, sustainable development, evaluation of hydrologic cycle, and related details such as the storage capacity, power generation, release pattern for irrigation, and municipal demands [1]. These pieces of information are particularly important for arid region, where less reliability of stream flow due to little and erratic rainfall is a major concern. Water scarcity is a common problem in such region. At the same time, erratic rainfall often causes prolonged drought or severe flood in such region. It is anticipated that global-induced climate change will make the water resource management in arid or semiarid region more challenging in near future. Iran is facing increasing challenge due to aridity in recent years. Declination of groundwater and reduction of freshwater resources is a growing concern in the country. The literature review shows that Iran is a water-deficit country since 1999. The World Water Council [2] ranked Iran as one of the highest water st
Data Loading...
