• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.6
• /
• pp.981-987
• /
• 2017

Jeju Island is a volcanic island which has a large permeability. Groundwater is a major water resources and its proper management is essential. Especially, there is a multilevel restriction due to the groundwater level decline during a drought period to protect sea water intrusion. Preliminary countermeasure using long-term groundwater level prediction is necessary to use agricultural groundwater properly. For this purpose, the monthly groundwater level prediction technique by Artificial Neural Network model was developed and applied to the representative monitoring wells. The monthly prediction model showed excellent results for training and test periods. The continuous groundwater level prediction model also developed, which used the monthly forecasted values adaptively as input data. The characteristics of groundwater declines were analyzed under extreme cases without precipitation for several months.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.4
• /
• pp.1-11
• /
• 2014

Rural groundwater monitoring network has been managed by Korea Rural Community Corporation (KRC) since 1998. The network consists of two kinds of subnetworks; rural groundwater management network (RGMN) and seawater intrusion monitoring network (SIMN). RGMN has been operated to promote a sound and sustainable development of rural groundwater within the concerned area for groundwater quality and quantity. SIMN has been operated to protect the crops against hazards by the saline water in coastal areas in which the shortage of irrigation water become a main problem for agriculture. Currently, a total of 283 monitoring wells has been installed; 147 wells in 79 municipalities for RGMN and 136 wells in 52 ones for SIMN, respectively. Two subnetworks commonly monitor three hydrophysical properties (groundwater level, temperature, and electric conductivity) every hour. Monitored data are automatically transferred to the management center located in KRC. Data are opened to the public throughout website named to be the Rural Groundwater Net (www.groundwater.or.kr). Annual reports involving well logging and hydrochemical data of RGMN and SIMN have been published and distributed to the rural water management office of each municipalities. In addition, anyone who concerns about RGMN an SIMN can freely download these reports throughout the Rural Groundwater Net as well.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.186-186
• /
• 2022

강수 및 침투 등으로 발생하는 지하수위의 변동을 예측하는 것은 지하수 자원의 활용 및 관리에 필수적이다. 지하수위의 변동은 지하수 자원의 활용 및 관리뿐만이 아닌 홍수 발생과 지반의 응력상태 등에 직접적인 영향을 미치기 때문에 정확한 예측이 필요하다. 본 연구는 인공신경망 중 다층퍼셉트론(Multi Layer Perceptron, MLP)을 이용한 지하수위 예측성능 향상을 위해 MLP의 구조 중 Optimizer를 개량하였다. MLP는 입력자료와 출력자료간 최적의 상관관계(가중치 및 편향)를 찾는 Optimizer와 출력되는 값을 결정하는 활성화 함수의 연산을 반복하여 학습한다. 특히 Optimizer는 신경망의 출력값과 관측값의 오차가 최소가 되는 상관관계를 찾는 연산자로써 MLP의 학습 및 예측성능에 직접적인 영향을 미친다. 기존의 Optimizer는 경사하강법(Gradient Descent, GD)을 기반으로 하는 Optimizer를 사용했다. 하지만 기존의 Optimizer는 미분을 이용하여 상관관계를 찾기 때문에 지역탐색 위주로 진행되며 기존에 생성된 상관관계를 저장하는 구조가 없어 지역 최적해로 수렴할 가능성이 있다는 단점이 있다. 본 연구에서는 기존 Optimizer의 단점을 개선하기 위해 지역탐색과 전역탐색을 동시에 고려할 수 있으며 기존의 해를 저장하는 구조가 있는 메타휴리스틱 최적화 알고리즘을 이용하였다. 메타휴리스틱 최적화 알고리즘 중 구조가 간단한 화음탐색법(Harmony Search, HS)과 GD의 결합모형(HS-GD)을 MLP의 Optimizer로 사용하여 기존 Optimizer의 단점을 개선하였다. HS-GD를 이용한 MLP의 성능검토를 위해 이천시 지하수위 예측을 실시하였으며 예측 결과를 기존의 Optimizer를 이용한 MLP 및 HS를 이용한 MLP의 예측결과와 비교하였다.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2003.04a
• /
• pp.259-262
• /
• 2003

In the Republic of Korea, Ministry of Construction & Transportation and Korea Water Resources Corporation manage the national groundwater monitoring network at the 169 stations and will organize the supplementary groundwater monitoring network at the 10,000 stations by 2011 year. The method that organizes the monitoring network was developed using the Analytic Hierarchy Process with pairwise comparison. Several estimation factors for the estimating every district were selected to reflect each district conditions. Their weighting value was decided by pairwise comparison and questions to the experts about groundwater The optimal number of groundwater monitoring well was calculated through the developed method. To verify this method, groundwater was monitored in Jeonju city by way showing the example. The study area In Jeonju city needs 7 stations for the supplementary groundwater monitoring network. The results monitored in 7 stations inferred the groundwater level around the study area by Kriging. The mean of residual between inferred groundwater level value from Kriging and actual groundwater level is rather low. Furthermore, the mean and standard deviation of residual between inferred groundwater level change and actual groundwater change is much lower. The Fact that 7 monitoring stations are sufficient for observing the groundwater condition in the study area makes it possible for suggested monitoring number to be proper.

• Journal of Soil and Groundwater Environment
• /
• v.14 no.5
• /
• pp.29-40
• /
• 2009

In general, understanding groundwater flow in fractured bedrock is critical during tunnel and underground cavern construction. In that case, borehole data may be useful to examine groundwater flow properties of the fractured bedrock from pre-excavation until completion stages, yet sufficient borehole data is not often available to acquire. This study evaluated groundwater discharge rate into Jikri tunnel in Gyeonggi province using hydraulic parameters, groundwater level data in the later stage of tunneling, national groundwater monitoring network data, and electrical resistivity survey data. Groundwater flow rate into the tunnel by means of analytical method was estimated $7.12-74.4\;m^3/day/m$ while the groundwater flow rate was determined as $64.8\;m^3/day/m$ by means of numerical modeling. The estimated values provided by the numerical modeling may be more logical than those of the analytical method because the numerical modeling could take into account spatial variation of hydraulic parameters that was not possible by using the analytical method. Transient modeling for a period of one year from the tunnel completion resulted in the recovery of pre-excavation groundwater level.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.63-63
• /
• 2020

최근 머신러닝 기술의 발전에 따라 비선형 시계열자료에 대한 예측이 가능해졌으며, 기존의 과정기반모형을 대체하여 지하수, 하천수 예측 등 다양한 수문분야에 활용되고 있다. 본 연구에서는 기존의 연구들과 달리 과정기반모형을 이용한 하천수 모의결과를 개선하기 위해 과정기반모형과 결합하는 방식으로 머신러닝 기술을 활용하였다. 머신러닝 기술을 통해 관측값과 모의값 간의 차이를 예측하고 과정기반모형의 모의결과에 반영함으로써 관측값을 정확히 재현할 수 있도록 하는 시스템을 구축하고 평가하였다. 과정기반모형으로는 Weather Research and Forecasting model-Hydrological modeling system (WRF-Hydro)을 소양강 유역을 대상으로 구축하였다. 머신러닝 모형으로는 순환 신경망 중 하나인 Long Short-Term Memory (LSTM) 신경망을 이용하여 장기시계열예측이 가능하게 하였다(WRF-Hydro-LSTM). 머신러닝 모형은 2013년부터 2017년까지의 기상자료 및 유입량 잔차를 이용하여 학습시키고, 2018년 기상자료를 이용하여 예상되는 유입량 잔차를 모의하였다. 모의된 잔차를 WRF-Hydro 모의결과에 반영시켜 최종 유입량 모의값을 보정하였다. 또한, 연구에서 제안된 새로운 방법론의 성능을 비교평가하기 위해 머신러닝 단독 모형으로 유입량을 학습 후 모의하였다(LSTM-only). 상관계수와 Nash-Sutcliffe 효율계수(NSE)를 사용해 평가한 결과, LSTM을 이용한 두 방법(WRF-Hydro-LSTM과 LSTM-only) 모두 기존의 과정기반모형(WRF-Hydro-only)에 비해 높은 정확도의 하천수 모의가 가능했으며, PBIAS 지수를 사용하여 평가한 결과, LSTM을 단독으로 사용하였을 때보다 WRF-Hydro와 결합했을 때 더 관측값과 가까운 모의가 가능함을 확인할 수 있었다.

• Journal of Korea Water Resources Association
• /
• v.40 no.6 s.179
• /
• pp.469-483
• /
• 2007

Nitrate and chloride are the most common contaminants in groundwater and their concentrations increase easily due to fertilizer consumption and urbanization. The number of time series data for groundwater quality at a single site was not sufficient to analyze trends on Jeju Island. Therefore rectangle grids were drawn for the whole island and single grid was determined to be $500m{\times}500m$ after considering similar stream density, homogeneous hydraulic coefficients, geologic features of volcanic rock and low topographic slopes. All data within each lattice were collected and arranged in time series order and analyzed using Sen's method. 10.6 % of the total lattices for chloride and 22.4% for nitrate showed upward trends from the early 1990's to the early 2000's. Especially, upward trends for nitrate concentration are distinct in the low mid-mountainous areas of western and southern watersheds. Many septic tanks and much domestic waste from the urbanization of the low mid-mountainous area have produced this upward trend. Additionally, the agricultural region has dramatically increased since the 1990's and this has led to an increase of fertilizer consumption and, as a result, nitrate concentration. Therefore, the target of any management plan for groundwater quality on Jeiu Island needs to be focused on careful land use decisions in the mid-mountainous areas which are near Halla Mountain.

• 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.

• Journal of the Korean earth science society
• /
• v.28 no.4
• /
• pp.478-490
• /
• 2007

With groundwater data of seawater intrusion monitoring network in coastal areas of Korea's main land, we analyzed types of seawater intrusion through the coastal aquifer. The data including groundwater level, temperature and electrical conductivity obtained from 45 monitoring wells at 25 watershed regions were evaluated. Based on statistical analysis, correlation analysis and variation type analysis, groundwater levels were mainly affected by rainfall and artificial pumping. About 78% of the monitoring wells showed average temperature higher than $15^{\circ}C$ and about 58% of them showed minimum variations less than $0.2^{\circ}C$. Electrical conductivities showed a large magnitude of variation and irregular characteristics compared with groundwater levels and temperatures. Average electrical conductivities lower than $2,000\;{\mu}S/cm$ were observed at 28 monitoring wells while those of higher than $10,000\;{\mu}S/cm$ were done at 9 monitoring wells. From the cross-correlation analysis, groundwater levels were mostly affected by precipitation while temperature and electrical conductivity showed very low correlation. Meanwhile tidal variations strongly affected the groundwater levels comparing to precipitation. We classified the long-term monitoring data according to variation types such as constant process, linear trend, cyclic variation, impulse, step function and ramp. Impulse type was dominant for variations of groundwater level, which was largely affected by rainfall or artificial pumping, the constant process was dominant for temperature. Compared with groundwater level and temperature, electrical conductivities showed various types like linear trend, step function and ramp. According to the discrepancy of variation characteristics for monitoring data at each well in the same region, periodical analysis of monitoring data is essentially required.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.44-44
• /
• 2018

조류(녹조)발생과 대응 연차보고서(2016)에 따르면, 낙동강 유역의 녹조현상은 2013년부터 해마다 발생했으며 국가적으로 가장 극심한 가뭄을 겪은 2015년의 경우 최장 161일 동안 지속되었음을 보고하였다. 이러한 녹조대응을 위해 환경부 국토부 등 관계기관은 댐 보 연계운영협의회 등을 통해 2016년 8월부터 낙동강 일부 댐 및 보에 대해 부분 방류를 실시하였다. 댐-보 연계운영에 따른 수문 수질 거동 분석은 국가 유역관리 측면에서 우선적으로 대비해야 할 중요한 문제이나, 댐보 연계의 효율적인 운영을 위한 정확한 분석과 평가에 대한 연구가 체계적으로 이뤄지고 있지 않은 실정이다. 본 연구에서는 낙동강유역($2,369km^2$)을 대상으로 SWAT(Soil and Water Assessment Tool)을 이용하여 지표수와 지하수의 상호작용에 의한 물수지 분석을 수행하고, 수질(SS, T-N, T-P)을 모의하였다. SWAT 모형 구축을 위해 낙동강유역을 표준유역 단위로 구분하고, 기상자료, 다목적댐(안동댐, 임하댐, 합천댐, 남감댐, 밀양댐)과 다기능보(상주보, 구미보, 칠곡보, 강정보, 달성보, 합천보, 함안보) 운영자료, 국가지하수정보센터에서 관측 및 관리하고 있는 지하수위 관측자료, 국가수질측정망 하천수 수질 측정자료를 수집하였다. SWAT 모형의 신뢰성있는 수문 및 수질 보정을 위해 낙동강유역 내 위치하는 다목적댐 및 다기능보의 실측 방류량을 이용하여 댐 운영모의를 고려하였고, 지하수위, 토양수분 및 수질자료를 이용하여 모형의 시공간적 보정(2005~2009)과 검증(2010~2017)을 실시하였다. 댐-보 연계운영 평가를 위해 환경부에서 제시한 4개의 연계운영 시나리오 중 3개의 시나리오((1) 댐+보 동시방류+제약수위 유지, (2) 보 동시방류+제약수위 유지, (3) 보 순차방류+제약수위 유지)를 선택하여 모의하였으며, 시나리오에 따른 수문 수질 거동을 분석하였다.