• Journal of Korea Water Resources Association
• /
• v.41 no.10
• /
• pp.1035-1044
• /
• 2008

It is critical to study on data charateristics analysis and prediction for the flood disaster prevention and water quality monitoring because discharge and TOC data in a river channel are strongly nonlinear. Therefore, in the present study, prediction models for discharge, TOC, and TOC load data were developed using approximation component in the last level and detail components segregated by wavelet transform. The results show that the developed model overcame the persistence phenomenon which could be seen from previous models and improved the prediciton accuracy comparing with the previous models. It might be expected that the results from the present study can mitigate flood disaster damage and construct active alternatives to various water quality problems in the future.

• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1285-1294
• /
• 2021

In recent years, as rainfall is concentrated and rainfall intensity increases worldwide due to climate change, the scale of flood damage is increasing. Rainfall of a previously unobserved magnitude falls, and the rainy season lasts for a long time on record. In particular, these damages are concentrated in ASEAN countries, and at least 20 million people among ASEAN countries are affected by frequent flooding due to recent sea level rise, typhoons and torrential rain. Korea supports the domestic flood warning system to ASEAN countries through various ODA projects, but the communication network is unstable, so there is a limit to the central control method alone. Therefore, in this study, an artificial intelligence-based flood prediction model was developed to develop an observation station that can observe water level and rainfall, and even predict and warn floods at once at one observation station. Training, validation and testing were carried out for 0.5, 1, 2, 3, and 6 hours of lead time using the rainfall and water level observation data in 10-minute units from 2009 to 2020 at Junjukbi-bridge station of Seolma stream. LSTM was applied to artificial intelligence algorithm. As a result of the study, it showed excellent results in model fit and error for all lead time. In the case of a short arrival time due to a small watershed and a large watershed slope such as Seolma stream, a lead time of 1 hour will show very good prediction results. In addition, it is expected that a longer lead time is possible depending on the size and slope of the watershed.

• Journal of Satellite, Information and Communications
• /
• v.12 no.3
• /
• pp.22-34
• /
• 2017

The K-DRUM(K-water hydrologic & hydraulic Distributed RUnoff Model), a distributed rainfall-runoff model of K-water, calculates predicted runoff and water surface level of a dam using precipitation data. In order to obtain long-term hydrometeorological information, K-DRUM requires long-term weather forecast. In this study, we built a system providing long-term hydrometeorological information using predicted rainfall ensemble of GloSea5(Global Seasonal Forecast System version 5), which is the seasonal meteorological forecasting system of KMA introduced in 2014. This system produces K-DRUM input data by automatic pre-processing and bias-correcting GloSea5 data, then derives long-term inflow predictions via K-DRUM. Web-based UI was developed for users to monitor the hydrometeorological information such as rainfall, runoff, and water surface level of dams. Through this UI, users can also test various dam management scenarios by adjusting discharge amount for decision-making.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4B
• /
• pp.347-359
• /
• 2010

A simple web-based flood forecasting system using data from stage and rainfall monitoring stations was developed to solve the difficulty that real-time forecasting model could not get the reliabilities because of assumption of future rainfall duration and intensity. The regression model in this research could forecast future water level of maximum 2 hours after using data from stage and rainfall monitoring stations in Daejeon area. Real time stage and rainfall data were transformed from web-sites of Geum River Flood Control Office & Han River Flood Control Office based MS-Excel 2007. It showed stable forecasts by its maximum standard deviation of 5 cm, means of 1~4 cm and most of improved coefficient of determinations were over 0.95. It showed also more researches about the stationarity of watershed and time-series approach are necessary.

• Journal of Korea Water Resources Association
• /
• v.53 no.4
• /
• pp.273-283
• /
• 2020

Quantitative forecasting of groundwater levels for the assessment of groundwater variation and vulnerability is very important. To achieve this purpose, various time series analysis and machine learning techniques have been used. In this study, we developed a prediction model based on LSTM (Long short term memory), one of the artificial neural network (ANN) algorithms, for predicting the daily groundwater level of 11 groundwater wells in Hankyung-myeon, Jeju Island. In general, the groundwater level in Jeju Island is highly autocorrelated with tides and reflected the effects of precipitation. In order to construct an input and output variables based on the characteristics of addressing data, the precipitation data of the corresponding period was added to the groundwater level data. The LSTM neural network was trained using the initial 365-day data showing the four seasons and the remaining data were used for verification to evaluate the fitness of the predictive model. The model was developed using Keras, a Python-based deep learning framework, and the NVIDIA CUDA architecture was implemented to enhance the learning speed. As a result of learning and verifying the groundwater level variation using the LSTM neural network, the coefficient of determination (R²) was 0.98 on average, indicating that the predictive model developed was very accurate.

• Korean System Dynamics Review
• /
• v.9 no.2
• /
• pp.105-128
• /
• 2008

City of Gyeongju's referendum finally offered the long-waited low-level radioactive waste disposal site in November 2005. Gyeongju's positive decision was due to the various economic rewards and incentives the national government promised to the city. 300 billion won for an accepting bonus, the location of the headquarter building of the Korean Hydro and Nuclear Power Co., and the accelerator research center and 3.25 trillion won for supporting regional development program implementation. All of the above will affect the city's infrastructure and the citizens' economic and social lives. Population, land use, economic structure, SOC and quality of life will be affected. Some will be very positive, and some will be negative. This research project will see the future of the city and forecast the demographic, economic, physical and environmental changes of the city via computer simulation's system dynamics technique. This kind of simulation will help City of Gyeongju's what to prepare for the future. The population forecasting of the year 2046 will be 662,424 with the waste disposal site, and 327,274 without the waste disposal site in Gyeongju. The waste disposal site and regional supporting program will increase 184,246 Jobs more with 1,605 agriculture and fishery, 5,369 manufacturing shops and 27,577 shops. The population increase will bring 96,726 more houses constructed in the city. Land use will also be affected. More land will be developed. And road, water plant and waste water plant will be expanded as much. The city's financial structure will be expanded, due to the increased revenues from the waste disposal site, and property tax revenues from the middle-class employees of the company, and the high-powered scientists and technologists from the accelerator research center. All in all, the future of the city will be brighter after operating the nuclear waste disposal site inside the city.

• Journal of Korea Water Resources Association
• /
• v.31 no.1
• /
• pp.105-113
• /
• 1998

Reservoir operation during flood period can be divided into two parts: One is for an operating policy during flood period to consider water conservation and flood control, and the other is for flood time on a random water level at flood forecasting, This study is concerned with reservoir operation and discusses general reservoir operation at flood time. Flood control has problems such as the uncertainty of hydrologic models. technical limitations and some constraints. Therefore, we may prepare the quantitative flood control methods based on the assured flood control storage for reservoir operation. Transformed Reservoir Flood(TRF) Reservoir Operation Method(ROM) is a procedure which determines the adequate releases with considering dam safety for flood inflows over non-damaging discharge. Based on the TRF ROM which was explained in our published paper. the study discusses the TRF ROM with additional investigations and the general reservoir operation rules at flood time.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.3
• /
• pp.123-133
• /
• 2014

It is important to predict the groundwater level fluctuation for effective management of groundwater monitoring system and groundwater resources. In the present study, three different time series models for the prediction of groundwater level in response to rainfall were built, those are transfer function noise model (TFNM), artificial neural network (ANN), and adaptive neuro fuzzy interference system (ANFIS). The models were applied to time series data of Boen, Cheolsan, and Hongcheon stations in National Groundwater Monitoring Network. The result shows that the model performance of ANN and ANFIS was higher than that of TFNM for the present case study. As lead time increased, prediction accuracy decreased with underestimation of peak values. The performance of the three models at Boen station was worst especially for TFNM, where the correlation between rainfall and groundwater data was lowest and the groundwater extraction is expected on account of agricultural activities. The sensitivity analysis for the input structure showed that ANFIS was most sensitive to input data combinations. It is expected that the time series model approach and results of the present study are meaningful and useful for the effective management of monitoring stations and groundwater resources.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.563-563
• /
• 2016

국내 강우발생은 기상학적인 영향으로 인하여 장마기간(6~8월)에 집중되어있으며, 최근에는 기후변화의 영향으로 짧은 시간에 많은 양의 강우가 발생하는 집중호우의 발생빈도가 증가하고 있다. 또한, 시간과 지역에 관계없이 국지성호우의 발생빈도 역시 높아지고 있다. 집중호우와 국지성호우는 짧은 시간에 하천수위를 상승시키므로 홍수로 인한 물적 피해가 크게 발생된다. 국토교통부에서는 그동안 홍수예보에 필수적인 우량, 하천수위 등 기초자료를 확보하기 위해 관측소(500여개) 및 홍수량 측정지점(80여개)을 확대하였으며, 관측된 자료는 모두 전산망에 기록, 보관하고 있다. 또한 한강, 금강, 낙동강, 영산강의 경우 홍수통제소에서 홍수량 예측 계산 등을 통해 홍수 예경보를 실시하고 있다. 하지만 4대강을 제외한 중소하천의 홍수예경보에 대한 정보를 찾아볼 수 없으며, 현재 연구가 진행중이다. 강우-유출모형을 활용하여 중소하천의 강우와 유출의 관계를 해석하는 과정은 다양한 인자를 고려해야하지만 중소하천의 경우 하천단면 등 하천자료가 충분히 구축되어 있지 못하므로 유출량 계산에 많은 어려움을 겪고 있다. 이에 본 연구에서는 중소하천의 홍수위 예측을 위해 한강의 과거 수위와 현재 수위만을 활용하여 인공신경망(Artificial Neural Network, ANN)의 학습을 진행하였다. 첫 번째로 ANN을 활용하여 한강유역 중 홍수예보지점(잠수교)의 수위변화에 직접적으로 연관이 있는 5개 수위관측소를 선정하였으며, 과거 장마기간(6~8월)관측 자료를 활용하였다. 두 번째로 홍수예보지점(잠수교)과 5개 수위관측소의 과거 관측수위(2009~2014년)를 인공신경망의 학습자료로 활용하여 모델을 훈련시켰으며, 마지막으로 2015년의 관측수위를 이용하여 ANN의 학습정확도에 대한 검증을 하였다. 본 과정은 수위예측을 위한 ANN의 훈련단계로 Training/Test를 반복하였으며, 학습결과와 2015년 관측수위 비교시 $R^2=0.987$과 상관계수 r=0.994로 유사한 패턴을 보였으나 최대치와 최소치에 대한 오차가 있음을 확인하였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.432-436
• /
• 2009

Recently, damage of flood is increased because of a short of time of concentration by development and a rise in runoff discharge by frequently heavy rain. The increase of runoff discharge is resulted in not only rise of water level but also damage of lives and property around river. Therefore, it is should be the first to estimate the exact runoff discharge. And based on the estimated flood discharge, flood damage is prevented by estimating inundated area of flood. In this study, flood stage is forecasted using HEC-HMS and HEC-RAS for Namdae-stream. The peak discharges were determinated by probability rainfall with the return period. The peak discharges obtained from HEC-HMS were inputted boundary conditions for the channel routing. Flood stages were evaluated using HEC-RAS.