• 한국환경과학회지
• /
• 제19권6호
• /
• pp.771-778
• /
• 2010

The prediction of discharge is very important in water resources management and plan. In this study, we have analyzed discharge data of site at up and down stream in watershed. In order to forecast discharge the regression equations were developed by measuring flow data. Also, to forecast the change of water quality followed by change of inflow the correlation relationship between inflow of the Youngchun site and the Chunhju dam was shown as very high. The forecast of inflow at the Chungju dam would be possible through flow analysis of the Youngchun site. And, it is possible to forecast water quality by flow analysis because the correlation relationship of SS and turbidity followed by change of flow for each station of investigation was very high.

• 상하수도학회지
• /
• 제21권5호
• /
• pp.601-607
• /
• 2007

In order to maintain constant residual chlorine in sedimentation basin, It is necessary to develop real time prediction model of residual chlorine considering water treatment plant data such as water qualities, weather, and plant operation conditions. Based on the operation data acquired from K water treatment plant, prediction models of residual chlorine in sediment basin were accomplished. The input parameters applied in the models were water temperature, turbidity, pH, conductivity, flow rate, alkalinity and pre-chlorination dosage. The multiple regression models were established with linear and non-linear model with 5,448 data set. The corelation coefficient (R) for the linear and non-linear model were 0.39 and 0.374, respectively. It shows low correlation coefficient, that is, these multiple regression models can not represent the residual chlorine with the input parameters which varies independently with time changes related to weather condition. Artificial neural network models are applied with three different conditions. Input parameters are consisted of water quality data observed in water treatment process based on the structure of auto-regressive model type, considering a time lag. The artificial neural network models have better ability to predict residual chlorine at sediment basin than conventional linear and nonlinear multi-regression models. The determination coefficients of each model in verification process were shown as 0.742, 0.754, and 0.869, respectively. Consequently, comparing the results of each model, neural network can simulate the residual chlorine in sedimentation basin better than mathematical regression models in terms of prediction performance. This results are expected to contribute into automation control of water treatment processes.

• 환경영향평가
• /
• 제19권5호
• /
• pp.465-473
• /
• 2010

This study was carried out to investigate the effect of EFDC hydrodynamic result on the WASP7.3 water quality modeling result in accordance with the change of number of grid for the dam reservoir to be constructed. The simulated flow and BOD, T-N and T-P loads by the HSPF watershed model was used for boundary conditions and the hydrodynamic modeling results was linked with WASP model to predict future water quality after dam construction. The scenarios for EFDC modeling were composed of Scenario 1(141 grid cells) and Scenario 2(568 grid cells). The results of Scenario 2 showed that BOD, T-N, T-P and Chl-a concentrations were decreased 0.073mg/L(8.5%), 0.032mg/L(2.6%), 0.003mg/L(6.8%), 0.644mg/L(4.2%) compared with those of Scenario 1, respectively. As number of grid cell increased, water quality concentrations were decreased and also it caused the longer running time. Therefore, this study suggests that the consideration of the geometry of water body is more important than the number of grid cells for the prediction of water quality of a dam reservoir in EIA.

• 한국습지학회지
• /
• 제23권2호
• /
• pp.144-153
• /
• 2021

최근 반복되고 있는 녹조는 수질관리에 가장 큰 과제로서 대두되고 있다. 현재 환경부에서는 7일 단위의 선행수질예측을 통한 수질예보를 수행하고 있으나, 선제적인 조치를 위해서 좀 더 장기간의 수질예측이 필요한 시점이다. 이에 본 연구에서는 수질예보의 보완자료로서 대청호의 Chl-a 농도를 3개월 선행예측하기 위한 방법론을 제안하고 그 적용성을 검토하고자 한다. 이를 위하여 대청호의 수질자동측정망 자료와 ECMWF의 수문기상예측자료를 수집하였으며 각 시계열 자료의 특성을 분석하였다. 대청호의 Chl-a 농도와의 상관 및 웨이블릿 분석을 바탕으로 수문기상입력인자를 결정하고 지연시간을 가지는 NARX모형을 이용하여 대청호의 Chl-a에 대한 3개월 선행예측 모형을 구축하였으며, 결과에 대한 비교분석을 통하여 모형의 적용성을 제시하였다.

• 한국수자원학회논문집
• /
• 제54권spc1호
• /
• pp.1023-1035
• /
• 2021

본 연구는 머신러닝 기반의 분석으로 해수담수화(Desalination) 시설의 전력비 예측모델의 가능성을 검토하였다. 해수담수화 주요 공정인 역삼투(Seawater Reverse Osmosis) 시설의 전력비 예측 모델을 개발하고, 전력비 산정에 영향을 미치는 인자를 분석하였으며, 해수 수질 중에서 선정된 수온 및 염분도 측정자료를 활용하여 검토하였다. 국립해양조사원(Korea Hydrographic and Oceanographic Agency, KHOA)의 2003년부터 2014년까지의 자료를 이용하였으며, 모형의 구조는 시행오차법(Trial & Error)으로 하이퍼파라미터를 최적화하여 머신러닝 기반의 예측 모델을 구축하고, 장래 해수 수질을 예측하였다. 해수 수온은 기존 패턴과 유사할 것으로 예측되었고, 염분도는 과거 측정자료 범위 이내로 최대값이 점차 감소되는 경향을 보여 해수담수화의 전력비가 약 0.80% 감소하는 것으로 검토되었다. 본 연구는 머신러닝 기반의 예측 모델을 구축하여 장래 수질 변화 예측하였으며, 해수 수질 변동의 영향 및 대안을 제시했다는데 의의가 있다.

• 대한환경공학회지
• /
• 제22권3호
• /
• pp.535-546
• /
• 2000

주암호는 광주 전남지역의 주민생활이나 공 농업활동에 기반이 되는 중요한 수자원의 역할을 하고 있으나, 주암호에 유입되는 오염물질로 말미암아 호수의 수질은 점점 악화되고 있는 실정이다. 주암호의 수질개선대책을 수립하기 위한 예비단계로서 호수의 수질모델링을 실시하여 수질이 장래에 어떻게 변화될 것인지를 확인할 필요성이 있다. 수질모델링 작업에 이용할 수 있는 컴퓨터 프로그램은 여러 종류가 있으나, 각 프로그램에서 요구하는 오염물질 유입량, 수리 수문 등의 압력자료(Input data)는 불확실성을 포함하고 있으며, 이러한 불확실성은 예측결과(장래수질)의 불확실성을 초래하게 된다. 수질모델링에서 불확실성이 발생하는 주요원인은 활용할 수 있는 정보의 부족, 미래상황 및 예측모델의 불확실, 그리고 전문가 지식의 한계 때문이다. 따라서 본 연구의 목적은 퍼지이론을 응용하여 수질예측 모델에서 요구하는 입력자료들의 불확실성 정도를 해석하고, 이를 수질예측 모델에 그대로 결합시킬 수 있는 방법을 개발하는 것이다. 이러한 방법의 적용은 불확실성을 고려하지 않는 방법들에 비해 합리적이고 현실성 있는 주암호의 장래수질을 예측하는데 도움이 될 것이다.

• 생태와환경
• /
• 제46권1호
• /
• pp.1-9
• /
• 2013

Algal blooms in potable water supplies are becoming an increasingly prevalent and serious water quality problem around the world. In addition to precipitating taste and odor problems, blooms damage the environment, and some classes like cyanobacteria (blue-green algae) release toxins that can threaten human health, even causing death. There is a recognized need in the water industry for models that can accurately forecast in real-time algal bloom events for planning and mitigation purposes. In this study, using data for an interconnected system of rivers and reservoirs operated by a New Jersey water utility, various ANN models, including both discrete prediction and classification models, were developed and tested for forecasting counts of three different algal classes for one-week and two-weeks ahead periods. Predictor model inputs included physical, meteorological, chemical, and biological variables, and two different temporal schemes for processing inputs relative to the prediction event were used. Despite relatively limited historical data, the discrete prediction ANN models generally performed well during validation, achieving relatively high correlation coefficients, and often predicting the formation and dissipation of high algae count periods. The ANN classification models also performed well, with average classification percentages averaging 94 percent accuracy. Despite relatively limited data events, this study demonstrates that with adequate data collection, both in terms of the number of historical events and availability of important predictor variables, ANNs can provide accurate real-time forecasts of algal population counts, as well as foster increased understanding of important cause and effect relationships, which can be used to both improve monitoring programs and forecasting efforts.

• 상하수도학회지
• /
• 제14권1호
• /
• pp.108-116
• /
• 2000

Chlorine is widely used as a disinfectant in drinking-water systems throughout the world. Chlorine residual was used as an indicator for prediction of water quality in water distribution systems. The variation of chlorine residual in drinking water distribution systems of Suwon city was simulated using EPANET. EPANET is a computerized simulation model which predicts the dynamic hydraulic and water quality behavior within a water distribution system operating over an extended time period. Sampling and analysis were performed to calibrated the computer model in 1999 (Aug. Summer). Water quality variables used in simulations are temperature, roughness coefficient, pipe diameter, pipe length, water demand, velocity and so on. Extended water residence time affected water quality due to the extended reaction time in some areas. All area showed the higher concentration of chlorine residual than 0.2mg/l(standard). So it can be concluded that any area in Suwon city is not in biological regrowth problem. Rechlorination turned out to be an useful method for uniform concentration of free chlorine residual in distribution system. The cost of disinfectant could be saved remarkably by cutting down the initial chlorine concentration to the level which guarantees minimum concentration (0.2mg/l) throughout the distribution system.

• 한국물환경학회지
• /
• 제39권1호
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• 한국습지학회지
• /
• 제17권4호
• /
• pp.348-358
• /
• 2015

기후변화로 인한 영향은 한반도뿐만 아니라 전 지구적으로 관찰되고 있다. 지난 100년간(1911 ~ 2010년) 전 지구적으로 $0.75^{\circ}C$가 상승한 반면, 한반도의 평균기온은 약 $1.5^{\circ}C$가 상승하였다. IPCC(Intergovermental Panel on Climate Change)에서 발간한 5차 기술보고서에 수온의 증가와 홍수 및 가뭄을 포함하는 극한 수문 사상의 변화는 수질에 영향을 미쳐 여러 가지 형태의 수질 오염을 보다 악화시킬 것으로 전망되고 있다(KMA and MOLIT, 2009). 본 연구에서는 기후변화에 따른 강원도 북한강에 위치한 홍천강 유역의 수질 변화를 분석하기 위하여 기후변화 시나리오 자료를 적용하여 미래유량을 각 목표 기간별로(Obs : 2001 ~ 2010년, Target I : 2011 ~ 2040년, Target II : 2041 ~ 2070년, Target III : 2071 ~ 2100년) 산정하였다. 또한, 수질 변화를 예측하기 위하여 미래유량을 토대로 유황분석을 시행한 후 다중회귀분석모형과 인공신경망모형을 통해 미래 수질변화를 분석하였다. 홍천강 유역의 수질예측 결과, 21세기 말 여름철에 생물학적 산소요구량, 화학적 산소요구량, 부유물질이 최대 16%, 13%, 15% 증가할 것으로 예측되어, 지속적이며 장기적인 수질 모니터링과 관리가 필요할 것으로 판단된다. 또한, 본 연구에서 사용한 기후자료뿐만 아니라 사회적 시나리오를 고려한다면 보다 신뢰성 있는 미래 수질 모의가 이루어질 것으로 판단된다.