• Journal of Korean Society on Water Environment
• /
• v.27 no.6
• /
• pp.914-925
• /
• 2011

The variation of streamflow is regarded as one of the most influential factors on the fluctuation of water quality in the stream. The characteristics of the variation should be taken into account in the plans for the management of Total Maximum Daily Loads (TMDLs). This study analysed and characterized spatial distribution and temporal variation of streamflow at each unit watershed in Guem-river basin. For the analysis of the distribution of streamflow, the type and the extent of the distribution were investigated for the unit watershed. For the analysis of the variation, short and long term changes of streamflow were examined. The result showed that most of the distributions were not log-normalized and the extent of variation tends to be greater at the unit watershed placed on the tributaries in the basin. A kind of margin could be granted to the unit watershed involving high variations so as to establish the water quality goal and load allotment more reasonably and effectively in view of whole waterbody.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.4
• /
• pp.17-27
• /
• 2021

Streamflow prediction is a very vital disaster mitigation approach for effective flood management and water resources planning. Lately, torrential rainfall caused by climate change has been reported to have increased globally, thereby causing enormous infrastructural loss, properties and lives. This study evaluates the contribution of rainfall to streamflow prediction in normal and peak rainfall scenarios, typical of the recent flood at Piney Resort in Vernon, Hickman County, Tennessee, United States. Daily streamflow, water level, and rainfall data for 20 years (2000-2019) from two USGS gage stations (03602500 upstream and 03599500 downstream) of the Piney River watershed were obtained, preprocesssed and fitted with Long short term memory (LSTM) model. Tensorflow and Keras machine learning frameworks were used with Python to predict streamflow values with a sequence size of 14 days, to determine whether the model could have predicted the flooding event in August 21, 2021. Model skill analysis showed that LSTM model with full data (water level, streamflow and rainfall) performed better than the Naive Model except some rainfall models, indicating that only rainfall is insufficient for streamflow prediction. The final LSTM model recorded optimal NSE and RMSE values of 0.68 and 13.84 m³/s and predicted peak flow with the lowest prediction error of 11.6%, indicating that the final model could have predicted the flood on August 24, 2021 given a peak rainfall scenario. Adequate knowledge of rainfall patterns will guide hydrologists and disaster prevention managers in designing efficient early warning systems and policies aimed at mitigating flood risks.

• Journal of Korea Water Resources Association
• /
• v.34 no.3
• /
• pp.275-285
• /
• 2001

Since the majority of streamflow during dry periods is provided by groundwater storage, the streamflow depends on a basin moisture state recharged from rainfall during wet periods. This hydrologic characteristics dives good condition to predict long-term streamflow if the basin state like groundwater recharge is known in advance. The objective of this study is to examine groundwater recharge effect to monthly streamflow, and to attempt monthly streamflow prediction using estimated groundwater recharge. The ground water recharge is used as an independent variable with streamflow and precipitation to construct multiple regression models for the prediction. Correlation analysis was performed to assess the effect of groundwater carry-over to streamflow and to establish the associations among independent variables. The predicted streamflow shows that the multiple regression model involved groundwater recharge gives improved results comparing to the model only using streamflow and precipitation as independent variables. In addition, this paper shows that the prediction model with the effect of groundwater carry-over taken into account can be developed using only precipitation.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.227-240
• /
• 2006

In the several decades, various storage facilities have been developed and operated to supply water resource, flood control or environmental preservation etc. Then, how those man-maid storage facilities affect on the downstream water and environment and how the hydrologists can evaluate those features for water resources problem-solving are high-concentrated problems in this field. Most large watersheds in Korea contain various types of artificial facilities such dams, reservoirs, in-land ponds, wetlands etc. But the study to develop the technology for achieving the effect of the variances and properties of the long term streamflow caused by the artificial storage facilities have been on the simple watershed models and experimental modeling in the real fields. In this paper, we introduce the procedure and methods to consider the above problems based on continuous and semi-distributed featured SWAT model. At the first, we describe the elements and mechanisms of storage facilities in SWAT model to see how we can apply that in proper and appropriate manner for real field problems. Then, we applied the process to a sample watershed, Taewha River basin which covers the most of Ulsan region. Specially, we concentrate on our effort to the effect of upper reservoirs on down stream long term flows based on various scenario basis. The result was described and analysed in spacial and temporal variations on that basin using the precise manner.

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.275-288
• /
• 2006

This study develops ESP (Ensemble Streamflow Prediction) system by using medium-term numerical weather prediction model which is GDAPS(T213) of KMA. The developed system forecasts medium- and long-range exceedance Probability for streamflow and RPSS evaluation scheme is used to analyze the accuracy of probability forecasts. It can be seen that the daily probability forecast results contain high uncertainties. A sensitivity analysis with respect to forecast time resolution shows that uncertainties decrease and accuracy generally improves as the forecast time step increase. Weekly ESP results by using the GDAPS output with a lead time of up to 28 days are more accurately predicted than traditional ESP results because conditional probabilities are stably distributed and uncertainties can be reduced. Therefore, it can be concluded that the developed system will be useful tool for medium- and long-term reservoir inflow forecasts in order to manage water resources.

• Environmental Engineering Research
• /
• v.18 no.1
• /
• pp.9-20
• /
• 2013

In this paper, the rainfall elasticity of streamflow was estimated to quantify the effects of climate change on 5 river basins. Rainfall elasticity denotes the sensitivity of annual streamflow for the variations of potential annual rainfall. This is a simple, useful method that evaluates how the balance of a water cycle on river basins changes due to long-term climate change and offers information to manage water resources and environment systems. The elasticity method was first used by Schaake in 1990 and is commonly used in the United States and Australia. A semi-distributed hydrological model (SLURP, semi-distributed land use-based runoff processes) was used to simulate the variations of area streamflow, and potential evapotranspiration. A nonparametric method was then used to estimate the rainfall elasticity on five river basins of Korea. In addition, the A2 (SRES IPCC AR4, Special Report on Emission Scenarios IPCC Fourth Assessment Report) climate change scenario and stochastic downscaling technique were used to create a high-resolution weather change scenario in river basins, and the effects of climate change on the rainfall elasticity of each basin were then analyzed.

• Journal of Korea Water Resources Association
• /
• v.41 no.6
• /
• pp.643-651
• /
• 2008

This study was conducted to promote reliability of the simulated result for the long-term streamflow in Daecheong watershed. This system was constructed by the SSARR model that considered the effect of small scale irrigation facilities. We investigated the present condition of small scale irrigation facilities and analyzed the relation between irrigation facilities and river discharge. According to the analysis result about the effect of irrigation facilities, the error occurrence frequency was increased at the sub-basin that has many reservoirs and during the second quarter except for the 2003 year. Therefore, we created the relative equation between small irrigation facilities and river water and estimated the simulated streamflow for the main stations. Consequently, error of the runoff simulated with considering small scale irrigation facilities was decreased than that without considering small scale irrigation facilities at all.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.131-131
• /
• 2021

Deep learning models, especially those based on long short-term memory (LSTM), have presented their superiority in addressing time series data issues recently. This study aims to comprehensively evaluate the performance of deep learning models that belong to the supervised learning category in streamflow prediction. Therefore, six deep learning models-standard LSTM, standard gated recurrent unit (GRU), stacked LSTM, bidirectional LSTM (BiLSTM), feed-forward neural network (FFNN), and convolutional neural network (CNN) models-were of interest in this study. The Red River system, one of the largest river basins in Vietnam, was adopted as a case study. In addition, deep learning models were designed to forecast flowrate for one- and two-day ahead at Son Tay hydrological station on the Red River using a series of observed flowrate data at seven hydrological stations on three major river branches of the Red River system-Thao River, Da River, and Lo River-as the input data for training, validation, and testing. The comparison results have indicated that the four LSTM-based models exhibit significantly better performance and maintain stability than the FFNN and CNN models. Moreover, LSTM-based models may reach impressive predictions even in the presence of upstream reservoirs and dams. In the case of the stacked LSTM and BiLSTM models, the complexity of these models is not accompanied by performance improvement because their respective performance is not higher than the two standard models (LSTM and GRU). As a result, we realized that in the context of hydrological forecasting problems, simple architectural models such as LSTM and GRU (with one hidden layer) are sufficient to produce highly reliable forecasts while minimizing computation time because of the sequential data nature.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.2
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.149-149
• /
• 2022

Accurate quantitative evaluation of baseflow contribution to streamflow is imperative to address seasonal drought vulnerability, flood occurrence and groundwater management concerns for efficient and sustainable water resources management in watersheds. Several baseflow separation algorithms using recursive filters, graphical method and tracer or chemical balance have been developed but resulting baseflow outputs always show wide variations, thereby making it hard to determine best separation technique. Therefore, the current global shift towards implementation of artificial intelligence (AI) in water resources is employed to compare the performance of deep learning models with conventional hydrograph separation techniques to quantify baseflow contribution to streamflow of Piney River watershed, Tennessee from 2001-2021. Streamflow values are obtained from the USGS station 03602500 and modeled to generate values of Baseflow Index (BI) using Web-based Hydrograph Analysis (WHAT) model. Annual and seasonal baseflow outputs from the traditional separation techniques are compared with results of Long Short Term Memory (LSTM) and simple Gated Recurrent Unit (GRU) models. The GRU model gave optimal BFI values during the four seasons with average NSE = 0.98, KGE = 0.97, r = 0.89 and future baseflow volumes are predicted. AI offers easier and more accurate approach to groundwater management and surface runoff modeling to create effective water policy frameworks for disaster management.