• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.95-95
• /
• 2023

Common hydrological problems of developing countries include poor data management, insufficient measuring devices and ungauged watersheds, leading to small or unreliable data availability. This has greatly affected the adoption of artificial intelligence techniques for flood risk mitigation and damage control in several developing countries. While climate datasets have recorded resounding applications, but they exhibit more uncertainties than ground-based measurements. To encourage AI adoption in developing countries with small ground-based dataset, we propose data augmentation for regression tasks and compare performance evaluation of different AI models with and without data augmentation. More focus is placed on simple models that offer lesser computational cost and higher accuracy than deeper models that train longer and consume computer resources, which may be insufficient in developing countries. To implement this approach, we modelled and predicted streamflow data of the Asa River Watershed located in Ilorin, Kwara State Nigeria. Results revealed that adequate hyperparameter tuning and proper model selection improve streamflow prediction on small water dataset. This approach can be implemented in data-scarce regions to ensure timely flood intervention and early warning systems are adopted in developing countries.

• Journal of Korean Society of Water and Wastewater
• /
• v.34 no.6
• /
• pp.503-512
• /
• 2020

Identifying the water circulation status is one of the indispensable processes for watershed management in an urban area. Recently, various water circulation models have been developed to simulate the water circulation, but it takes a lot of time and cost to make a water circulation model that could adapt the characteristics of the watershed. This paper aims to develop a water circulation state estimation model that could easily calculate the status of water circulation in an urban watershed by using multiple linear regression analysis. The study watershed is a watershed in Seoul that applied the impermeable area ratio in 1962 and 2000. And, It was divided into 73 watersheds in order to consider changes in water circulation status according to the urban characteristic factors. The input data of the SHER(Similar Hydrologic Element Response) model, a water circulation model, were used as data for the urban characteristic factors of each watershed. A total of seven factors were considered as urban characteristic factors. Those factors included annual precipitation, watershed area, average land-surface slope, impervious surface ratio, coefficient of saturated permeability, hydraulic gradient of groundwater surface, and length of contact line with downstream block. With significance probabilities (or p-values) of 0.05 and below, all five models showed significant results in estimating the water circulation status such as the surface runoff rate and the evapotranspiration rate. The model that was applied all seven urban characteristics factors, can calculate the most similar results such as the existing water circulation model. The water circulation estimation model developed in this study is not only useful to simply estimate the water circulation status of ungauged watersheds but can also provide data for parameter calibration and validation.

• Journal of Korean Society on Water Environment
• /
• v.28 no.4
• /
• pp.582-594
• /
• 2012

A simple ecohydorlogic model that simulates hydrologic components and vegetation dynamics simultaneously based on equations of soil water dynamics and vegetation's growth and mortality is discussed. In order to simulate ungauged watersheds, the proposed model is calibrated with indirected estimated observation data set; 1) empirically estimated annual vaporization, 2) monthly surface runoff estimated by NRCS-CN method, and 3) vegetation fraction estimated by SPOT/VEGETATION NDVI. In order to check whether the model is performed well with indirectly estimated data or not, four upper dam watersheds (Andong, Habcheon, Namgang, Milyang) in Nakdong River watershed are selected, and the model is verified.

• Proceedings of the Korea Water Resources Association Conference
• /
• 1989.07a
• /
• pp.17-30
• /
• 1989

In this study, more exact runoff phenomina of the watersheds were comprehened and the relationships between geographical factors of the selected watershed and the unit hydrograph characteristic variables representing runoff processes, were also established. Moreover, the estimation of the adequate design flood was presented, which is needed for the design of the hydrologic structures in the ungauged watersheds. And owing to these results, it is considered to be possible to execute the effective flood control projects of the river and the efficient water resources management.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.2244-2248
• /
• 2008

This study was focused on estimated Stream Maintenance Flow and performed for simulate securing Stream Maintenance Flow in New town development area. Tributary streams were made of 6 small streams, joined Gong-ji Stream and Eu-am lake finally. For estimate Stream Maintenance Flow used Kajiyama and SWAT models for calculate available flow in study area. As a result the annual average stream flow dry years were $2,300{\sim}136,000\;m^/day3$, the annual average stream flow wet years were $4,800{\sim}136,031\;m^3/day$. The coefficient of determination($R^2$) and Nash-sutcliffe coefficient(EI) for comparison between Kajiyama and SWAT models were 0.88, 0.78 respectively.

• Journal of Environmental Science International
• /
• v.23 no.4
• /
• pp.615-623
• /
• 2014

The groundwater level varies according to the characteristics and composite materials of aquifer. In this study, specific yield and reaction factor which are the major two hydrogeological parameters in the WTF(Water Table Fluctuation) method were estimated and analyzed spatial characteristics. 8 groundwater level stations which have enough measuring period and high correlation with rainfall in the Hancheon watershed were used. The results showed that specific yield was randomly distributed and reaction factor showed inverse trend with altitude. If the enough data were collected, reaction factor according to altitude in ungauged points could be estimated by using these parameter characteristics.

• Water for future
• /
• v.22 no.4
• /
• pp.423-433
• /
• 1989

In this study, more exact runoff phenomina of the watersheds were comprehended and the relationships between geographical factors of the selected watershed and the unit hydrograph characteristic variables representing runoff processes, were also established. Moreover, the estimation of the adequate design flood was presented, which is needed for the design of the hydrologic structures in the ungauged watersheds. And owing to these results, it is considered to be possible to execute the effective flood control projects of the river and the efficient water resources management.

• Journal of Korean Society on Water Environment
• /
• v.35 no.6
• /
• pp.481-496
• /
• 2019

The Ministry of Environment has measured streamflow at eight-day intervals for the estimation of standard flow of the Total Maximum Daily Loads (TMDL) system. This study identified the availability of the partially measured the eight-day interval data for estimating standard flow and found the optimal extension techniques of standard flow. The study area was selected for the Nakbon-A watershed in the Nakdong River, and four streamflow record extension techniques of standard flow were considered: extension, percentile, drainagearea, and regional regression methods. The flow duration curve (FDC) using the eight-day interval streamflow data indicated very high Nash and Sutcliffe Efficiency (NSE) values above 90 % from FDC-II to FDC-VII compared to FDC-VIII, the standard FDC. This result demonstrates that FDC using daily data of three-six cumulative years could represent standard FDC fairly well. For the streamflow record extension techniques of standard flow, the percentile method was selected as the optimal alternative, showing the minimal difference from FDC-VIII. These results validate the availability of the eight-day interval streamflow data in the standard flow estimation and the application of extension techniques. It seems that these results could reduce the uncertainty of partially measured streamflow data for water quantity and quality management.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.58 no.4
• /
• pp.67-74
• /
• 2016

Load Duration Curve (LDC) can be used as a method for load management of point and non-point pollution source because the LDC easily assesses the water quality corresponding to hydrological changes in a watershed. Recently, the application of LDC to total pollution load management is a growing interest in Korea. In this regard, A desktop-based LDC assessment system was developed in this study to provide convenience to users in water quality evaluation. The developed system can simply produce the LDC by using streamflow and water quality data involved in its database. Also, The system can quantitatively inform the success or failure of the achievement for a target water quality at monthly scale. Furthermore, seasonal water quality and point/non-point pollution load in a watershed can be estimated by this system. We expect that the developed system will contribute to establish local and national policies regarding water management and total pollution load management because of its advantages such as the pollution tracking investigation and the analysis of water quality and pollution loading amount in an ungauged watershed.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.19 no.2
• /
• pp.4377-4384
• /
• 1977

The curvilinear hydrograph can be replaced by an equivalent triangular hydrograph which is more easily constructed and, for routing through reservoirs or stream channels, gives results about as accurate as those obtained using the curvilinear hydrograph. A synthetic hydrograph is prepared using the data from a number of watersheds to develop a dimensionless unit hydrograph applicable to ungauged watersheds. The dimensionless unit hydrograph for the NakDong River Basin was prepared from the unit hydrographs of a variety of nine subwatersheds. The equation for the peak rate of flow (unit volume of runoff in 1.0mm) was derived as {{{{ { q}_{p } = { 0.21AR} over { {T }_{p } } }}}} The results summarized in this study are as follows: 1) It found that the watershed lag time (Lg, hrs) could be expressed by Lg=0.253(L.Lca)0.4171 The product L.Lca is a measure of the size and shape of the watershed. Correlation coefficient for Lg was 0.97 which defined with high significance. 2) The base length of the unitgraph, in hours, was adopted as Tb=17.51+2.073Lg with high significant correlation coefficient, 0.92. 3) Time in hour from start of rise to peak rate (TP) generally occured at the position of 0.289 Tb with some indication of higher values for larger watershed. 4) Triangular hydrograph is a dimensionless unitgraph prepared from the 40 unitgraphs. The equation is shown as {{{{ { q}_{p } = { K.A.R} over { { T}_{p } } }}}}. The constant K=0.21 is defined to NakDong River basin. 5) In the light of the results analyzed in this study, average errors in the peak discharge of the Trjangular unitgraph was estimated as 5.34 percent to the peak of observed average unitgraph. Each ordinate of the Triangular unitgraph was approached closely to the observed one.