• 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.

• Geomechanics and Engineering
• /
• v.37 no.1
• /
• pp.65-72
• /
• 2024

Water ingress poses a common and intricate geological hazard with profound implications for tunnel construction's speed and safety. The project's success hinges significantly on the precision of estimating water inflow during excavation, a critical factor in early-stage decision-making during conception and design. This article introduces an optimized model employing the gene expression programming (GEP) approach to forecast tunnel water inflow. The GEP model was refined by developing an equation that best aligns with predictive outcomes. The equation's outputs were compared with measured data and assessed against practical scenarios to validate its potential applicability in calculating tunnel water input. The optimized GEP model excelled in forecasting tunnel water inflow, outperforming alternative machine learning algorithms like SVR, GPR, DT, and KNN. This positions the GEP model as a leading choice for accurate and superior predictions. A state-of-the-art machine learning-based graphical user interface (GUI) was innovatively crafted for predicting and visualizing tunnel water inflow. This cutting-edge tool leverages ML algorithms, marking a substantial advancement in tunneling prediction technologies, providing accuracy and accessibility in water inflow projections.

• Journal of Korea Water Resources Association
• /
• v.31 no.1
• /
• pp.45-57
• /
• 1998

The purpose of this paper is to develop a neural network model in order to forecast flood inflow into the reservoir that has the nature of uncertainty and nonlinearity. The model has the features of multi-layered structure and parallel multi-connections. To develop the model. backpropagation learning algorithm was used with the Momentum and Levenberg-Marquardt techniques. The former technique uses gradient descent method and the later uses gradient descent and Gauss-Newton method respectively to solve the problems of local minima and for the speed of convergency. Used data for learning are continuous fixed real values of input as well as output to emulate the real physical aspects. after learning process. a reservoir inflows forecasting model at flood period was constructed. The data for learning were used to calibrate the developed model and the results were very satisfactory. applicability of the model to the Chungju Mlultipurpose Reservoir proved the availability of the developed model.

• Journal of Wetlands Research
• /
• v.21 no.3
• /
• pp.236-243
• /
• 2019

Hydrologic time series has been analyzed and forecasted by using classical linear models. However, there is growing evidence of nonlinear structure in natural phenomena and hydrologic time series associated with their patterns and fluctuations. Therefore, the classical linear techniques for time series analysis and forecasting may not be appropriate for nonlinear processes. Daily streamflow series at St. Johns river near Cocoa, Florida, USA showed an interesting result of a low dimensional, nonlinear dynamical system but daily inflow at Soyang reservoir, South Korea showed stochastic property. Based on the chaotic dynamical characteristic, DVS (deterministic versus stochastic) algorithm is used for short-term forecasting, as well as for exploring the properties of the system. In addition to the use of DVS algorithm, a neural network scheme for the forecasting of the daily streamflow series can be used and the two techniques are compared in this study. As a result, the daily streamflow which has chaotic property showed much more accurate result in short term forecasting than stochastic data.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.2
• /
• pp.63-74
• /
• 2019

The objective of this study was to evaluate the influence of rainfall observation network on daily dam inflow using artificial neural networks(ANNs). Chungju Dam and Soyangriver Dam were selected for the study watershed. Rainfall and dam inflow data were collected as input data for construction of ANNs models. Five ANNs models, represented by Model 1 (In watershed, point rainfall), Model 2 (All in the Thiessen network, point rainfall), Model 3 (Out of watershed in the Thiessen network, point rainfall), Model 1-T (In watershed, area mean rainfall), Model 2-T (All in the Thiessen network, area mean rainfall), were adopted to evaluate the influence of rainfall observation network. As a result of the study, the models that used all station in the Thiessen network performed better than the models that used station only in the watershed or out of the watershed. The models that used point rainfall data performed better than the models that used area mean rainfall. Model 2 achieved the highest level of performance. The model performance for the ANNs model 2 in Chungju dam resulted in the $R^2$ value of 0.94, NSE of 0.94 $NSE_{ln}$ of 0.88 and PBIAS of -0.04 respectively. The model-2 predictions of Soyangriver Dam with the $R^2$ and NSE values greater than 0.94 were reasonably well agreed with the observations. The results of this study are expected to be used as a reference for rainfall data utilization in forecasting dam inflow using artificial neural networks.

• Journal of Korea Water Resources Association
• /
• v.42 no.10
• /
• pp.809-824
• /
• 2009

Hydrological system forecasting, which is the short term runoff historical data during the limited period in dam site, is a conditional precedent of hydrological persistence by stochastic analysis. We have forecasted the monthly hydrological system from Andong dam basin data that is the rainfall, evaporation, and runoff, using the seasonal ARIMA (autoregressive integrated moving average) model. Also we have conducted long term runoff simulations through the forecasted results of TANK model and ARIMA+TANK model. The results of analysis have been concurred to the observation data, and it has been considered for application to possibility on the stochastic model for dam inflow forecasting. Thus, the method presented in this study suggests a help to water resource mid- and long-term strategy establishment to application for runoff simulations through the forecasting variables of hydrological time series on the relatively short holding runoff data in an object basins.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.1
• /
• pp.61-74
• /
• 2019

In this study, the SPI (Standardized Precipitation Index) of meteorological drought and SDI (Streamflow Drought Index) of hydrological drought for 1, 3, 6, 9, and 12 months duration were estimated to analyse the characteristics of drought using rainfall and dam inflow data for Chungju dam ($6,661.8km^2$) with 31 years (1986-2016) and Boryeong dam ($163.6km^2$) watershed with 19 years (1998-2016) respectively. Using the estimated SPI and SDI, the drought forecasting was conducted using seasonal autoregressive integrated moving average (SARIMA) model for the 5 durations. For 2016 drought, the SARIMA had a good results for 3 and 6 months. For the 3 months SARIMA forecasting of SPI and SDI, the correlation coefficient of SPI3, SPI6, SPI12, SDI1, and SDI6 at Chungju Dam showed 0.960, 0.990, 0.999, 0.868, and 0.846, respectively. Also, for same duration forecasting of SPI and SDI at Boryeong Dam, the correlation coefficient of SPI3, SPI6, SDI3, SDI6, and SDI12 showed 0.999, 0.994, 0.999, 0.880, and 0.992, respectively. The SARIMA model showed the possibility to provide the future short-term SPI meteorological drought and the resulting SDI hydrological drought.

• Journal of Korea Water Resources Association
• /
• v.49 no.4
• /
• pp.327-333
• /
• 2016

Due to climate changes accelerated by global warming, South Korea has experienced regional climate variations as well as increasing severities and frequencies of extreme weather. The precipitation in South Korea during the summer season in 2013 was concentrated mainly in the central region; the maximum number of rainy days were recorded in the central region while the southern region had the minimum number of rainy days. As a result, much attention has been paid to the importance of flood control due to damage caused by spatiotemporal intensive rainfalls. In this study, forecast rainfall data was used for rapid responses to prevent disasters during flood seasons. For this purpose, the applicability of numerical weather forecast data was analyzed using the ground observation rainfall and inflow rate. Correlation coefficient, maximum rainfall intensity percent error and total rainfall percent error were used for the quantitative comparison of ground observation rainfall data. In addition, correlation coefficient, Nash-Sutcliffe efficiency coefficient, and standardized RMSE were used for the quantitative comparison of inflow rate. As a result of the simulation, the correlation coefficient up to six hours was 0.7 or higher, indicating a high correlation. Furthermore, the Nash-Sutcliffe efficiency coefficient was positive until six hours, confirming the applicability of forecast rainfall.

• Journal of Korea Water Resources Association
• /
• v.38 no.12 s.161
• /
• pp.1061-1072
• /
• 2005

A hydrological grey model is developed to forecast short-term river runoff from the Naju watershed located at upstream of the Youngsan estuary dam in Korea. The runoff of the Naju watershed is measured in real time at the Naju streamflow gauge station, which is a key station for forecasting the upstream inflow and operating the gates of the estuary dam in flood period. The model's governing equation is formulated on the basis of the grey system theory. The model parameters are reparameterized in combination with the grey system parameters and estimated with the annealing-simplex method In conjunction with an objective function, HMLE. To forecast accurately runoff, the fifth order differential equation was adopted as the governing equation of the model in consideration of the statistic values between the observed and forecast runoff. In calibration, RMSE values between the observed and simulated runoff of two and six Hours ahead using the model range from 3.1 to 290.5 $m^{3}/s,\;R^2$ values range from 0.909 to 0.999. In verification, RMSE values range from 26.4 to 147.4 $m^{3}/s,\;R^2$ values range from 0.940 to 0.998, compared to the observed data. In forecasting runoff in real time, the relative error values with lead-time and river stage range from -23.4 to $14.3\%$ and increase as the lead time increases. The results in this study demonstrate that the proposed model can reasonably and efficiently forecast runoff for one to six Hours ahead.

• The Journal of Engineering Geology
• /
• v.23 no.3
• /
• pp.227-234
• /
• 2013

The vertical shaft of a selective intake structure, which is constructed in a large reservoir, is required to be impermeable and to employ a grouting technology to prevent water inflow from the reservoir or surrounding ground. In this study, groundwater inflow is estimated using a numerical model for two cases (i.e., grouting or non-grouting cases at the exterior of a vertical shaft) and compared with data measured during an excavation at the construction site of a selective intake structure in the Soyang reservoir, Korea. Groundwater inflow is estimated to range from 444 to 754 $m^3/d$ in the case of non-grouting and from 58 to 95 $m^3/d$ in the case of grouting. The groundwater inflow measured in a vertical shaft, which ranges from 30 to 100 $m^3/d$, is similar to the simulated amount. It is recommended that before the excavation of a shaft, water inflow is estimated using a numerical model and a grouting test to ensure excavation stability and improve excavation efficiency.