• Journal of Korea Water Resources Association
• /
• v.51 no.2
• /
• pp.165-174
• /
• 2018

The model using time series data can be considered as a flood forecasting model of a small river due to its efficiency for model development and the advantage of rapid simulation for securing predicted time when reliable data are obtained. Transfer Function Noise (TFN) model has been applied hourly flood forecast in Italy, and UK since 1970s, while it has mainly been used for long-term simulations in daily or monthly basis in Korea. Recently, accumulating hydrological data with good quality have made it possible to simulate hourly flood prediction. The purpose of this study is to assess the TFN model applicability that can reflect exogenous variables by combining dynamic system and error term to reduce prediction error for tributary rivers. TFN model with hourly data had better results than result from Storage Function Model (SFM), according to the flood events. And it is expected to expand to similar sized streams in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.12 no.4
• /
• pp.1-17
• /
• 2009

In recent years, most of flood damage is associated with the levee failure. The objective of this study is to predict flow depths, flood area, flooding time and flood damage through flood inundation analysis considering the overflow of levee and the characteristics of levee failure. The hydrological parameters were extracted from GIS data such as DEM, land cover and soil map to estimate levee failure discharge. In addition, the characteristics of flood wave propagation could be accurately predicted as flood inundation analysis was accomplished considering the affection of structure within protected lowland and hourly prediction of flooded areas and estimation of flood strength will be utilized as basic data for the flood defence and establishment of measure to reduce flood damage.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.147-147
• /
• 2018

In this article, we use an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The proposed model based on a deep neural network model, LSTM (Long Short-Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. For LSTM modeling, the input data is hourly water level data for 15 years from 2002 to 2016 at 4 stations includes 3 upstream stations (Sutong, Hotan, and Songcheon) and the forecasting-target station (Okcheon). The data are subdivided into three purposes: a training data set, a testing data set and a validation data set. The model was formulated to predict Okcheon Station water level for many cases from 3 hours to 12 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation, the prediction is very stable and reliable up to 9 hours of lead time with the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm. The result indicated that the method is able to produce the river water level time series and be applicable to the practical flood forecasting instead of hydrologic modeling approaches.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.134-134
• /
• 2022

Streamflow forecasting plays a crucial role in water resource control, especially in highly urbanized areas that are very vulnerable to flooding during heavy rainfall event. In addition to providing the accurate prediction, the evaluation of effects and importance of the input predictors can contribute to water manager. Recently, machine learning techniques have applied their advantages for modeling complex and nonlinear hydrological processes. However, the techniques have not considered properly the importance and uncertainty of the predictor variables. To address these concerns, we applied the GA-BART, that integrates a genetic algorithm (GA) with the Bayesian additive regression tree (BART) model for hourly streamflow forecasting and analyzing input predictors. The Jungrang urban basin was selected as a case study and a database was established based on 39 heavy rainfall events during 2003 and 2020 from the rain gauges and monitoring stations. For the goal of this study, we used a combination of inputs that included the areal rainfall of the subbasins at current time step and previous time steps and water level and streamflow of the stations at time step for multistep-ahead streamflow predictions. An analysis of multiple datasets including different input predictors was performed to define the optimal set for streamflow forecasting. In addition, the GA-BART model could reasonably determine the relative importance of the input variables. The assessment might help water resource managers improve the accuracy of forecasts and early flood warnings in the basin.

• Journal of Korea Water Resources Association
• /
• v.44 no.1
• /
• pp.51-64
• /
• 2011

The objective of this study is to develop a continuous rainfall-runoff model for flood prediction on a large-scale basin. For this study, the hourly surface runoff estimation method based on the variable retention parameter and runoff curve number is developed. This model is composed that the soil moisture to continuous rainfall can be simulated with applying the hydrologic components to the continuous equation for soil moisture. The runoff can be simulated by linking the hydrologic components with the storage function model continuously. The runoff simulation to large basins can be performed by using channel storage function model. Nakdong river basin is selected as the study area. The model accuracy is evaluated at the 8 measurement sites during flood season in 2006 (calibration period) and 2007~2008 (verification period). The calibrated model simulations are well fitted to the observations. Nash and Sutcliffe model efficiencies in the calibration and verification periods exist in the range of 0.81 to 0.95 and 0.70 to 0.94, respectively. The behavior of soil moisture depending on the rainfall and the annual loadings of simulated hydrologic components are rational. From this results, continuous rainfall-runoff model developed in this study can be used to predict the discharge on large basins.

• Journal of Korea Water Resources Association
• /
• v.43 no.6
• /
• pp.533-541
• /
• 2010

It is basic for a flood prediction to calculate direct runoff from rainfall in a basin by the rainfall-runoff model. The direct runoff is calculated from rainfall excess or effective rainfall based on a rainfall-runoff model. The total rainfall minus rainfall loss equals rainfall excess with time. This loss can be treated equal to an infiltration loss under the assumption that the infiltration is a major one among the losses in the rainfall-runoff model. Practically obtaining the infiltration loss $\Phi$ index method, W index method or modified ones of these have been used. In this study it is assumed the loss of rainfall in a basin be a well-known Horton infiltration mechanism. And in case that the parameter set is given in the Horton infiltration model a procedure and assumption for calculating hourly infiltration loss and rainfall excess are offered and the results of its application are compared with those of $\Phi$ index method. By this study it is well shown the value of Horton infiltration function is exponentially decay with time as the Horton infiltration mechanism.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1131-1141
• /
• 2021

In this study, the artificial neural network model is applied for real-time dam inflow prediction and then evaluated for the prediction lead times (1, 3, 6 hr) in dam basins in Korea. For the training and testing the model, hourly precipitation and inflow are used as input data according to average annual inflow. The results show that the model performance for up to 6 hour is acceptable because the NSE is 0.57 to 0.79 or higher. Totally, the predictive performance of the model in dry seasons is weaker than the performance in wet seasons, and this difference in performance increases in the larger basin. For the 6 hour prediction lead time, the model performance changes as the sequence length increases. These changes are significant for the dry season with increasing sequence length compared to the wet season. Also, with increasing the sequence length, the prediction performance of the model improved during the dry season. Comparison of observed and predicted hydrographs for flood events showed that although the shape of the prediction hydrograph is similar to the observed hydrograph, the peak flow tends to be underestimated and the peak time is delayed depending on the prediction lead time.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.2
• /
• pp.69-79
• /
• 2017

In this study, we developed real-time urban stream discharge forecasting model using short-term rainfall forecasts data simulated by a regional climate model (RCM). The National Centers for Environmental Prediction (NCEP) Climate Forecasting System (CFS) data was used as a boundary condition for the RCM, namely the Global/Regional Integrated Model System(GRIMs)-Regional Model Program (RMP). In addition, we make ensemble (ESB) forecast with different lead time from 1-day to 3-day and its accuracy was validated through temporal correlation coefficient (TCC). The simulated rainfall is compared to observed data, which are automatic weather stations (AWS) data and Tropical Rainfall Measuring Mission (TRMM) Multisatellite Precipitation Analysis (TMPA 3B43; 3 hourly rainfall with $0.25^{\circ}{\times}0.25^{\circ}$ resolution) data over midland of Korea in July 26-29, 2011. Moreover, we evaluated urban rainfall-runoff relationship using Storm Water Management Model (SWMM). Several statistical measures (e.g., percent error of peak, precent error of volume, and time of peak) are used to validate the rainfall-runoff model's performance. The correlation coefficient (CC) and the Nash-Sutcliffe efficiency (NSE) are evaluated. The result shows that the high correlation was lead time (LT) 33-hour, LT 27-hour, and ESB forecasts, and the NSE shows positive values in LT 33-hour, and ESB forecasts. Through this study, it can be expected to utilizing the real-time urban flood alert using short-term weather forecast.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.140-140
• /
• 2021

Urban flood management is a crucial and challenging task, particularly in developed cities. Therefore, accurate prediction of urban flooding under heavy precipitation is critically important to address such a challenge. In recent years, machine learning techniques have received considerable attention for their strong learning ability and suitability for modeling complex and nonlinear hydrological processes. Moreover, a survey of the published literature finds that hybrid computational intelligent methods using nature-inspired algorithms have been increasingly employed to predict or simulate the streamflow with high reliability. The present study is aimed to propose a novel approach, an ensemble tree, Bayesian Additive Regression Trees (BART) model incorporating a nature-inspired algorithm to predict hourly multi-step ahead streamflow. For this reason, a hybrid intelligent model was developed, namely GA-BART, containing BART model integrating with Genetic algorithm (GA). The Jungrang urban basin located in Seoul, South Korea, was selected as a case study for the purpose. A database was established based on 39 heavy rainfall events during 2003 and 2020 that collected from the rain gauges and monitoring stations system in the basin. For the goal of this study, the different step ahead models will be developed based in the methods, including 1-hour, 2-hour, 3-hour, 4-hour, 5-hour, and 6-hour step ahead streamflow predictions. In addition, the comparison of the hybrid BART model with a baseline model such as super vector regression models is examined in this study. It is expected that the hybrid BART model has a robust performance and can be an optional choice in streamflow forecasting for urban basins.