• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• 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.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• 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.

• 지질공학
• /
• 제22권2호
• /
• pp.207-221
• /
• 2012

낙동강 하류지역 주변 충적층 지역내 설치 운영중인 27개의 지하수 관측정의 시계열 자료를 활용하여 지표수와 지하수의 연계 특성 평가를 위한 통계적 분석을 수행하였다. 지하수위의 변화는 하천수위의 변화와 교차상관계수가 0.601로서 연관성이 높은 것으로 분석되었으며, 이는 강우와의 교차상관계수 0.125보다 매우 높다. 지하수위 시계열 자료에 대한 주성분 분석 결과, 연구지역내 지하수위는 2개의 그룹으로 분류된다. 이중에서 그룹 A에 속하는 하천에 인접한 관측정에서의 수위 변화는 하천수와 유사한 변동을 보이며 호우시의 지하수위 상승량도 상대적으로 크게 나타났다. 홍수 발생에 대한 지하수 기여에 대한 추가적 이해를 위해서는 지하수위 변동 특성을 기반으로 지구화학 분석 및 온도 계측 등이 추가적으로 수행될 필요가 있다.

• 한국물환경학회지
• /
• 제20권6호
• /
• pp.615-624
• /
• 2004

The distribution pattern of water quality parameters and phytoplankton biomass in upper inflow rivers of lake Paldang had surveyed. In North-Han river system, nutrient concentrations and algal biomass was below the standard of mesoand oligotrophy from lake Soyang to lake Paldang, maintaining good water quality, except the N5 site located near the Chuncheon-Si, showing high nutrients concentrations and algal biomass. The algal biomass of the South-Han river system showed oligotrophic level in the upstream near the lake Chungju, and increased along the flow direction showing eutrophic level in the downstream within the lake Paldang area. On the other hand, the highest concentrations of nutrients were detected in the middle stream near the Yeoju-Si and Yangpyung-Gun rather than in the downstream suggesting algal biomass in lake Paldang would not come from the upper river area but come from the growth within the lake area using nutrients from the upper inflow river.

• 한국물환경학회지
• /
• 제23권6호
• /
• pp.822-828
• /
• 2007

Perchlorate is an unregulated contaminant but recently many cases of perchlorate contamination have been reported in the US. In Japan, also, a couple of contamination incidents caused by perchlorate occurred. Against this backdrop, investigation on perchlorate was urgent for Korea. Accordingly, perchlorate investigation in tap water and river water was conducted one time a week for seven consecutive weeks at major water sources of Korea including Han River, Guem River, Yeong-san River, and Nak-dong River. Perchlorate was not found at Han River, Guem River, and Yeong-san River. However, all the 4 tap water samples in Nak-dong River recorded high level of perchlorate. Among others, NT1 located at Daegu posted the highest value of $22.3{\mu}g/L$. This level is lower than $24.5{\mu}g/L$, the threshold recommended by US EPA. Still, perchlorate contamination in drinking water can deal a heavy blow to nerve development of infants and children by causing iodine deficiency. At the 1st and 2nd investigations, perchlorate concentration reached $18.7{\sim}95.6{\mu}g/L$ and $4.0{\sim}25.6{\mu}g/L$ respectively, both of which are relatively higher. The high perchlorate concentration in Nak-dong River was possible because of the waste water discharged from LCD manufacturing factory which was located at NS3 in Gumi, Korea. Perchlorate concentration of waste water from the factory was $730{\sim}1,858{\mu}g/L$.

• 한국수자원학회논문집
• /
• 제52권12호
• /
• pp.975-984
• /
• 2019

하천수의 체계적이고 통합적인 관리를 위한 필수 전제로, 하천으로 공급되고, 하천에서 방류되는 유량 등의 기초자료 확보가 필요하다. 현행되는 하천수 사용 허가제도에 의하면 2017년 허가시설 중 59.1%는 유량 계측기기가 없는 것으로 확인되었고, 특히 농업용수의 경우, 보고량의 상당부분이 사용자의 자발적인 보고로 이루어져 신뢰성 있는 자료의 확보가 어려운 실정이다. 본 연구에서는 양수장의 전력사용량을 통해 유량을 산정하는 간접 유량 계측방법을 적용하여 경제적이고 신뢰성 있는 유량자료의 확보에 대한 연구를 수행하였다. 특히, 전력량법에 의해 산정된 유량이 하천의 수위에 따라 실측 유량과 차이가 나는 점에 집중하여, 하천수위를 반영한 전력량법의 개선 및 유량자료의 정확도 향상에 대한 적용성 연구를 수행하였다. 하천수위를 고려한 전력량법으로 산정된 유량을 회귀분석, 백분율 차이, 평균 제곱근 오차 등의 상관성 분석 방법 등을 이용하여 분석한 결과, 기존의 전력량법과 비교하여 보다 더 실측 유량에 근사한 결과를 산정하는 것으로 확인하였다. 이를 통해, 양수장에서는 기존의 전력량법으로도 신뢰성 있는 유량 자료를 확보할 수 있지만, 하천의 수위 변동폭이 큰 지점에서 개선된 전력량법을 사용한다면, 보다 정확한 하천수 취수량 자료를 확보할 수 있을 것으로 기대한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2005년도 학술발표회 논문집
• /
• pp.1138-1142
• /
• 2005

The tidal river is a river affected by tide, which causes the water level to rise and fall two times everyday periodically. The local velocity across the river could be very fast because of the cross-sectional characteristics of the river even though it's not a rainy season. Therefore extreme local scour could take place around hydraulic structures such as piers and caissons due to backward flow velocity. For the construction of pier foundation of Ilsan-bridge In the Han River, the field observations were performed to get the velocity and water level. The numerical analysis was performed by HEC-RAS(UNET). The relationship between measured maximum velocity and calculated mean velocity is achieved, which is used to estimate the velocity and water level as the construction is proceeding. Countermeasures for scour were designed with the results of the hydraulic analysis to avoid potential damage during construction work. According to the results of monitoring, the velocity increase after temporary road embankment was negligible, from which it is considered that the degradation of main channel compensated for the constriction of cross-section by embankment.

• 산업기술연구
• /
• 제26권B호
• /
• pp.249-255
• /
• 2006

In this paper, we study the river level/velocimetry measuring system using the ultrasonic sensor to acquire the more precise data from the river circumstance in rainy season. We design the two ultrasonic sensor system to calculate the water level and surface current speed of the river using the dedicated hardware and software. We investigate the validity and effectiveness of the proposed system which applied to the real river environment monitoring system that will be extended to the GIS.

• Ecology and Resilient Infrastructure
• /
• 제5권2호
• /
• pp.88-93
• /
• 2018

In-situ water quality sampling is used for accurate water quality assessment. However, in-situ water quality sampling offers limited samples and requires much time and intensive labors. Remote sensing approach has recently applied for water quality assessment. It has shown the advantage of offering a synoptic view but also more efficient and economical. In this study, we utilized Landsat Imagery to estimate the water quality of the Tamsui River basin, considered as one of the most important rivers located in the north of Taiwan. In order to monitor water quality of Tamsui River basin, a linear regression relation between the value of spectral radiance and four water quality parameters are investigated with 38 water sampling stations. Through the regression model, we could estimate river pollution index (RPI) from the predicted value of four water quality parameters. By using RPI, we can examine the pollution level of Tamsui River. The accuracy of RPI conversion of this study ranged from 32.2% to 68.2%.

• 한국환경과학회지
• /
• 제12권3호
• /
• pp.287-297
• /
• 2003

To investigate water quality and pollution states of rivers in Gwangju city, total of 30 water samples were taken from the main stream of Yeongsan river, Hwangryong river and Gwangju stream in dry and flood seasons. Physico-chemical characteristics of above streams according to pH-Eh and Piper's diagrams we, typically, assigned to natural river water. In the streams, BOD, COD, T-N and T-P indicating water quality mostly increase toward downstream. Notably, water qualities in area near connection between the Gwangju stream and the main stream of Yeongsan river are polluted over V level in rivers and lakes water quality standard. The pollutions are influenced by lift and agricultural foul waters from Gwangju City and farming areas around upstream branches of the Yeongsan river, reasonably. Besides, heavy metals are below the standard in those streams. So, it is considered that the streams are polluted by not industrial but life/agricultural foul waters.