• Journal of Korea Water Resources Association
• /
• v.54 no.3
• /
• pp.157-166
• /
• 2021

Forecasting dam inflow based on high reliability is required for efficient dam operation. In this study, deep learning technique, which is one of the data-driven methods and has been used in many fields of research, was manipulated to predict the dam inflow. The Long Short-Term Memory deep learning with Sequence-to-Sequence model (LSTM-s2s), which provides high performance in predicting time-series data, was applied for forecasting inflow of Soyang River dam. Various statistical metrics or evaluation indicators, including correlation coefficient (CC), Nash-Sutcliffe efficiency coefficient (NSE), percent bias (PBIAS), and error in peak value (PE), were used to evaluate the predictive performance of the model. The result of this study presented that the LSTM-s2s model showed high accuracy in the prediction of dam inflow and also provided good performance for runoff event based runoff prediction. It was found that the deep learning based approach could be used for efficient dam operation for water resource management during wet and dry seasons.

• Journal of Korea Water Resources Association
• /
• v.55 no.7
• /
• pp.495-504
• /
• 2022

With the recent development of artificial intelligence, a Long Short-Term Memory (LSTM) model that is efficient with time-series analysis is being used to increase the accuracy of predicting the inflow of dams. In this study, we predict the inflow of the Soyang River dam, using the LSTM model with the Sequence-to-Sequence (LSTM-s2s) and attention mechanism (LSTM-s2s with attention) that can further improve the LSTM performance. Hourly inflow, temperature, and precipitation data from 2013 to 2020 were used to train the model, and validate and test for evaluating the performance of the models. As a result, the LSTM-s2s with attention showed better performance than the LSTM-s2s in general as well as in predicting a peak value. Both models captured the inflow pattern during the peaks but detailed hourly variability is limitedly simulated. We conclude that the proposed LSTM-s2s with attention can improve inflow forecasting despite its limits in hourly prediction.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.14 no.3
• /
• pp.179-188
• /
• 1981

The authors made an investigation concerning the geographical distribution and some major differentiations in morphological characteristics associated with the each habitat, of the pond smelt, Hypomesus olidus, which was introduced into Korea more than 50 years ago. Major characteristics utilized for the comparison study were upper jaw (maxillary), number of fin rays, scale structure, vertebral count, number of pyloric caeca, number of gill rakers, and the relative measurements of these and other internal characters. 1. The main areas of natural distribution are Paro Lake, Soyang Lake, Han River, Euirim Lake, and Ogjeong Lake (or Unam Lake) and the tributaries of these waters. 2. Morphological variations varied when the mean values of measurements from each area were compared with the standard measurement value by mosaic comparison, and in some instances a significant variation was found. 3. The most significant variations were found in the number of fin rays of pectoral and anal fins; the lengths from the tip of snout to the origin of pectoral fin, from snout to ventral fin, and from snout to anal fin, relative to standard body length; eye depth relative to head length; upper jaw: the number of pyloric caeca and the scale structure. Variations, on the other hand, by each habitat were not clear in the numbers of ventral and dorsal fin rays, gill rakers, vertebrae and lateral line scale : and the depth of caudal peduncle and distance from the tip of snout to the origin of dorsal fin relative to standard body length. 4. The scales of pond smelt showed some differences in the shape of scales, the shape and position of the focus and the number of ridges according to the scale positions on the body. No radii were present. The relations between longitudinal and transverse diameters of the scale suggest that the pond smelts of Soyang Lake and Un-am Lake are closely related, and those of Han River and Euirim Lake are also closely related. 5. The geographical variations in morphology of the pond smelt seem to have resulted from the variations in turbidity, water temperature, salinity (rather conductivity) and currents. 6. From the results obtained, it may be concluded that such factors as supramaxillary, relation between scale length and its breadth, number of caudal vertebrae and eye depth relative to head length may be used as the key characters for the classification of geographical varieties of Pond smelt.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.

• Journal of Korea Water Resources Association
• /
• v.50 no.3
• /
• pp.139-153
• /
• 2017

The variation in runoff due to global climate change and urbanization should be identified quantitatively because these two factors have been significantly accelerated during the last three decades in South Korea. However, only a few research to analyze the impacts due to two factors over different time scales can be found. Therefore, in this study, the hydrological model based approach and the hydrological sensitivity approach were used to separate relative impacts by two factors on monthly, seasonal, and annual time scales at the Soyang River upper basin and the Seom River basin in South Korea. The 3 techniques such as the double mass curve method, the Pettitt's test, and the BCP analysis were performed to detect change point occurred by abrupt change in the collected observed runoff. After detection of change ponts, SWAT models calibrated on the natural periods were used to calculate the changes due to human activities. Also, 6 Budyko based methods were auxiliary to verify the results from hydrological based approach.

• Journal of Wetlands Research
• /
• v.25 no.2
• /
• pp.121-131
• /
• 2023

This study examines the possible problem in the rainfall-runoff analysis process using the VIC (Variable Infiltration Capacity) model caused by using the effective soil depth instead of the soil depth. The parameters of the model are determined as follows. First, parameters that can be determined using available numerical information are fixed. For parameters related to direct runoff and base runoff, the recommended values of the VIC model are applied. In the case of soil depth, four cases are considered: (1) the effective soil depth is applied as the soil depth, (2) 1.5 times of the effective soil depth is applied as the soil depth by reflecting the vertical structure of the soil layer, (3) 1.25 times of the effective soil depth, and (4) 2.0 times of the effective soil depth as alternative soil depths. This study simulates the rainfall-runoff for the period from 1983 to 2020 targeting the Chungju Dam and Soyang River Dam basins of the Han River system. As a result of the study, it is confirmed that when the effective soil depth is applied instead of the soil depth, direct runoff and baseflow have opposite effects, and direct runoff increases by more than 3% while base runoff decreases by the same scale. In addition, the most influential factor in the estimation of the effective soil depth in the Chungju Dam and Soyanggang Dam basins is found to be the proportion of rock outcrop area. The difference between the direct runoff ratio and the base runoff ratio in the two basins is conformed significantly different due to the influence of the rock outcrop area.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.2
• /
• pp.53-69
• /
• 2020

The increase of the impermeable area due to industrialization and urban development distorts the hydrological circulation system and cause serious stream drying phenomena. In order to manage this, it is necessary to develop a technology for impact assessment of stream drying phenomena, which enables quantitative evaluation and prediction. In this study, the cause of streamflow reduction was assessed for dam and weir watersheds in the five major river basins of South Korea by using distributed hydrological model DrySAT-WFT (Drying Stream Assessment Tool and Water Flow Tracking) and GIS time series data. For the modeling, the 5 influencing factors of stream drying phenomena (soil erosion, forest growth, road-river disconnection, groundwater use, urban development) were selected and prepared as GIS-based time series spatial data from 1976 to 2015. The DrySAT-WFT was calibrated and validated from 2005 to 2015 at 8 multipurpose dam watershed (Chungju, Soyang, Andong, Imha, Hapcheon, Seomjin river, Juam, and Yongdam) and 4 gauging stations (Osucheon, Mihocheon, Maruek, and Chogang) respectively. The calibration results showed that the coefficient of determination (R²) was 0.76 in average (0.66 to 0.84) and the Nash-Sutcliffe model efficiency was 0.62 in average (0.52 to 0.72). Based on the 2010s (2006~2015) weather condition for the whole period, the streamflow impact was estimated by applying GIS data for each decade (1980s: 1976~1985, 1990s: 1986~1995, 2000s: 1996~2005, 2010s: 2006~2015). The results showed that the 2010s averaged-wet streamflow (Q95) showed decrease of 4.1~6.3%, the 2010s averaged-normal streamflow (Q185) showed decreased of 6.7~9.1% and the 2010s averaged-drought streamflow (Q355) showed decrease of 8.4~10.4% compared to 1980s streamflows respectively on the whole. During 1975~2015, the increase of groundwater use covered 40.5% contribution and the next was forest growth with 29.0% contribution among the 5 influencing factors.

• Korean Journal of Environmental Agriculture
• /
• v.22 no.2
• /
• pp.100-110
• /
• 2003

This study was conducted to evaluate influence of chemical properties in the riparian on the species diversity and to get plant information for enhancement of natural purification in Mankyeong River. The concentration of total nitrogen was high in Jeonju and Sam stream, while that of total nitrogen showed the highest peak in Winter. Concentrations of $NH_4-N$ was $0.01{\sim}0.06\;mg/L$ in Gosan and Soyang stream. The water quality of upstream along with Mankyeong River was suitable for the irrigation source. The riparian vegetation was investigated by Zurich-Montpellier school's method from June, 2001 to September, 2002. The number of riparian plants were 59 families, 129 genera, 165 species, 20 varieties in Gosancheon, on the while 53 families, 111 genera, 141 species, 19 varieties in Soyangcheon. The number of riparian plants in Bari basin was higher than that of other sites namely, 73 families, 134 genera, 218 species, 33 varieties. Riparian vegetation was consisted of 12 plant communities. The contents of organic matter, total nitrogen and electrical conductivity had negative relationship with species diversity (Species richness index, Heterogeneity index, Species evenness index Species number). On the while, species diversity had positive relationship with soil pH. Species diversify of the plant communities were affected by topography and disturbance.

• Korean Journal of Ecology and Environment
• /
• v.51 no.2
• /
• pp.160-167
• /
• 2018

The role played by reservoirs in the biogeochemical cycles of elements is a subject of ongoing debate. Recent research has revealed that reservoirs emit significant levels of greenhouse gases. To assess the importance of reservoirs in monsoon climate areas as a source of methane gas into the atmosphere, we investigated variations in organic carbon (OC) input into the reservoir, oxic state changes, and finally the amount of methane emitted (focusing on the ebullition pathway) in Lake Soyang, which is the largest reservoir in South Korea. Total organic carbon (TOC) concentrations were higher during summer after two years of heavy rainfall. The sedimentation rates of particulate organic carbon (POC) and particulate organic nitrogen (PON) were higher in the epilimnion and hypolimnion than the metalimnioin, indicating that autochthonous and allochthonous carbon made separate contributions to the TOC. During stratification, oxygen depletion occurred in the hypolimnion due to the decomposition of organic matter. Under these conditions, $H_2S$ and $CH_4$ can be released from sediment. The methane emissions from the reservoir were much higher than from other natural lakes. However, the temporal and spatial variations of methane ebullition were huge, and were clearly dependent on many factors. Therefore, more research via a well-organized field campaign is needed to investigate methane emissions.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.261-274
• /
• 2006

This study performs a daily long-term runoff analysis for 30 years to forecast medium- and long-term probabilistic reservoir inflows on the Soyang River basin. Snowmelt is computed by Anderson's temperature index snowmelt model and potenetial evaporation is estimated by Penman-combination method to produce input data for a rainfall-runoff model. A semi-distributed TOPMODEL which is composed of hydrologic rainfall-runoff process on the headwater-catchment scale based on the original TOPMODEL and a hydraulic flow routing model to route the catchment outflows using by kinematic wave scheme is used in this study It can be observed that the time variations of the computed snowmelt and potential evaporation are well agreed with indirect observed data such as maximum snow depth and small pan evaporation. Model parameters are calibrated with low-flow(1979), medium-flow(1999), and high-flow(1990) rainfall-runoff events. In the model evaluation, relative volumetric error and correlation coefficient between observed and computed flows are computed to 5.64% and 0.91, respectively. Also, the relative volumetric errors decrease to 17% and 4% during March and April with or without the snowmelt model. It is concluded that the semi-distributed TOPMODEL has well performance and the snowmelt effects for the long-term runoff computation are important on the study area.