• 한국전자통신학회논문지
• /
• 제19권3호
• /
• pp.531-538
• /
• 2024

수질 환경의 중요성이 강조되고 있는 가운데 광주광역시 도시 하천의 수질개선을 위한 수질 지표는 수생 생태계에 영향을 미치는 중요한 요소로 정확한 예측이 필요하다. 본 연구에서는 XGBoost와 LightGBM 머신러닝 알고리즘을 활용하여 광주천의 중요한 지점인 하류 평촌교(PyeongchonBr)와 상류 방학교(BangHakBr_Gwangjucheon1) 수계의 수질 검사 항목 중 통계적 검증 결과 유의미한 항목인 질소(TN), 질산염(NO3), 암모니아 양(NH3) 세 가지 수질 지표를 예측하는 연구를 수행하였고, 회귀 모델 평가 지표인 RMSE를 이용하여 예측 모델의 성능을 평가하였다. 수계별 개별적인 모델을 구현하여 교차 검증 후 성능을 비교한 결과, XGBoost 모델이 뛰어난 예측 능력을 보였다

• 해양환경안전학회지
• /
• 제15권2호
• /
• pp.91-98
• /
• 2009

아산만 해역으로 방류수가 배출될 경우, 생태-유체역학모델을 이용하여 아산만 해역의 장기 수질변화를 예측하였다. 생태-유체역학 모델은 해수유동 시뮬레이션을 위한 다층모델과 수질시뮬레이션을 위한 생태계모델로 구성되어 있다. 생태-유체역학모델을 이용하여 아산만해역의 장기 수질을 예측한 결과, 5개 정점에서 화학적산소요구량, 용존무기질소 및 용존무기인의 농도분포는 현재 계산결과에서 6개월 동안 증가하였다. 수치실험 수행시간 1년에서 2년 사이에서는 화학적 산소요구랑, 용존무기질소, 용존무기인의 농도분포는 6개월 동안 증가한 농도분포가 차츰 감소하는 경향을 보였으며, 3년에서 10년 사이에서는 일정한 농도분포를 보였다. 화학적 산소요구량, 용존무기질소 및 용존무기인의 농도는 $11{\sim}67%$, $10{\sim}67%$ 및 0.57%의 범위로 증가하였다. 10년 동안의 수치 실험 결과 화학적산소요구량과 용존무기질소의 변화 폭이 크게 나타났으며 이는 하수처리장의 방류수 중 이 두 오염부하량이 많은 양을 차지하고 있기 때문이다. 아산만 연안해역에서 화학적산소요구량, 총질소, 총인의 농도는 해역수질환경기준 II등급으로 조사되었으나, 하수처리장의 방류수가 배출될 경우 사업지구 인근의 아산만 방조제 부근에서는 해역수질환경기준 III등급으로 나타났다.

• 품질경영학회지
• /
• 제19권1호
• /
• pp.72-82
• /
• 1991

This study deals with the problem of water resources development by using bayesian theory. The purpose of this study is to develop the optimal decision model by applying bayesian theory which determine the optimal alternative in water resources development system. A relevant mathematical model to find an optimal solution formulated and then used in developing an efficient water resources that determine optimal alternative. A numerical example is solved to illustrate the algorithm developed.

• 한국환경과학회지
• /
• 제16권5호
• /
• pp.623-632
• /
• 2007

The objective of this study is analysis of Andong-Dam lake water quality with water quality model. Model parameters of the WASP applied to Lake Andong-Dam were estimated. The methodology is based on grouping water quality constituents and relevant parameters and successively estimating parameters by a trial-and-error procedure. Water qualify system for modeling consisted of BOD, DO, T-N, T-P. The results of water quality modelling using WASP. T-N was maximum affected by K71C(Organic nitrogen mineralization rate) parameter. T-P was maximum affected by K83C(Dissolved organic phosphorus mineralization) parameter, and It did not show a difference almost from the parameter of others and it omitted. BOD was maximum affected by Temperature parameter, it was visible of the reaction due to the KDC(Deoxygenation rate) in afterwords, and it did not show a difference from the parameter of others and it omitted. DO was maximum affect by Temperature parameter, and It did not show a difference almost from the parameter of others and it omitted. The parameter which it presumes from the this study uses a water quality modeling and Actual value and the result with which it compares, error rate the parameter presumption which is appropriate with 1% interior and exterior is investigated, It will reach and it uses and it will be able to apply to the suitable parameter in water quality modelling of the objective area which can be feeded by it becomes.

• 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%.

• 물과 미래
• /
• 제15권3호
• /
• pp.23-36
• /
• 1982

The stochastic variations and structures of time series data on water quality were examined by employing the techniques of autocorrelation function, variance spectrum, Fourier series, autoregressive model and ARIMA model. These time series included hourly and daily observation on DO, turbidity, conductivity pH and water temperature. The measurement was made by automatic recording instrument at Noryangjin and Dook-do located in the downstream part of Han River during 1975 and 1976. Hourly water quality time series varied with the dominant 24-hour periodicity, and the 12-hour periodicity was also observed. An important factor affecting 24-hour periodic variation of DO is believed to be photosynthesis by algae. These phenomena might be attributable to periodic discharges of municipal sewage. Noryangjin site showed the more distinct 12-hour periodicity than Dook-do site did, and tidal effect might be responsible for the difference. The water quality, as measured by DO and turbidity, was better in the afternoon compared with the quality in the morning. This change can be explained by the periodic variation of DO, temperature and the amount of municipal wewage discharge. It was also observed that the water temperature at Noryangjin was higher than the temperature at Dook-do. This difference might have been caused by the pollutants that were added to the section between two sites. The correlation coefficients between some of the variables were fairly high. For example, the coefficient was -0.88 between DO and water temperature, 0.75 between turbidity and river flow, and 0.957 between water temperature and air temperature. The lag time of heat transfer from the air to the water was estimated as 24 days. The first order auto-regressive model was appropriate for explaning standardized hourly DO time series. The ARIMA model of (1, 0, 0) type provided relatively satisfactory results for daily DO time series after the removal of significant harmonic value.

• 상하수도학회지
• /
• 제21권1호
• /
• pp.101-112
• /
• 2007

This study has used RMA2 model and RMA4 model, which are depth-averaged two-dimensional flow and water-quality prediction models, to analyze the variation of the water-quality by the gates operation in the Seonakdong River. Sensitivity analysis is performed to get the Manning coefficient and the coefficient of eddy viscosity for RMA2 model, and to get the diffusion coefficient for RMA4 model. Since the numerical simulation using RMA2 and RMA4 models did not consider tributary pollutant load except for that of Joman River, it could make a little difference from the natural phenomenon. Nevertheless, the numerical simulation shows that the discharge of $30m^3/s$, which is the continuous inflow from the Daedong-gate, can make it possible to achieve the target water-quality (BOD 4.3mg/L) of Nakbon-N watershed about 10 days later if the Daejeo-gate could remain opened in connection with the Noksan-gate operation.

• 물과 미래
• /
• 제14권4호
• /
• pp.19-26
• /
• 1981

자연하천에서의 수질은 유량의 변화에 많은 영향을 받을 것으로 기대되는 바, 유량과 각 수질인자의 통계적 특성 및 유량변화와 수질인자간의 상관관계를 조사하기 위하여 자기 및 상호상관함수 power spectrum, coherence 함수 및 Markov 모형을 적용하였다. 일부 자료만이 입수 가능한 한강 하류부 인도교 지점에서의 유량, 용존산소, 전기전도도는 명백한 1년 주기와 6, 4, 3개월의 약한 주기를 가지며, 유량과 용존산소, 유량과 전도도 사이의 상관은 약하게 나타났고 상호상관함수에서 첨두가 지체 1일에서 발생하여 미약하지만 유량의 변화에 의한 영향이 1일 정도 차이로 수질인자에게 미치는 것으로 해석된다. 계열 발생 및 예측수단인 선형회귀모형의 검토에서 유량은 1차 및 2차 Markov 모형과, 용존산소와 전도도는 1차 Markov 모형과 흡사하게 나타났다.

• 한국환경농학회지
• /
• 제10권1호
• /
• pp.67-75
• /
• 1991

본(本) 연구(硏究)는 만경강(萬頃江) 수계(水系)에 QUAL-IIE Model을 적용(適用)하여 장래수질예측(將來水質豫測)을 실시(實施)한 것으로 얻은 결론(結論)을 요약(要約)하면 다음과 같다. 1. M-3(백구정) 지점(地點)에서 실측(實測) BOD와 계산(計算) BOD의 오차범위(誤差範圍)는 10% 이내(以內)로서 적용(適用)모델은 만족스럽다. 동지점(同地點)에서 감응도분석결과(感應度分析結果) 만경강(萬頃江) 수계오염(水系汚染)에 영향(影響)을 미치는 가장 큰 인자(因子)는 전주천(全州川)의 유입부하량(流入負荷量)이다. 2. 예측결과(豫測結果) 하구(河口)로부터 약(約) 41km (지점)(M-1)에서 전주천(全州川)의 고농도(高濃度) 오염수(汚染水)가 유입(流入)되므로서 심(甚)한 오염상태(汚染狀態)를 나타내며, 또한 하구(河口)로부터 약(約) 28km 지점(地點)(M-3)에서는 수표면적(水表面積)이 넓어지면서 자정효과(自淨效果)가 크게 향상(向上)되어 수질개선(水質改善)이 이루어졌다. 3. 제수문(制水門) 이하(以下) 하류(下流)에서는 감조구간(感潮區間)으로 동(同) Model의 계산결과(計算結果)의 신뢰성(信賴性)이 떨어지므로 감조구간(感潮區間)에서 동(同) Model의 적용(適用)은 곤난(困難)하다. 4. BOD의 경우에는 전구간(全區間)이 심(甚)한 오염상태(汚染狀態)를 나타내며 M-3 지점(地點)에서 그 농도(濃度)가 1996년 26.6mg/1, 2001년(年) 30.7mg/1, 2006년(年) 33mg/1 그리고 2011년(年) 37.5mg/1로서 수질오염방지대책(水質汚染防止對策)이 수립(樹立)되지 않으면 용수관리(用水管理)에 있어서 많은 문제점(問題點)이 야기(惹起)될 것이다.

• 한국물환경학회지
• /
• 제27권5호
• /
• pp.670-679
• /
• 2011

Chlorophyll-a is a major water quality indicator for an algal bloom in streams and lakes. The purpose of the study is to estimate chlorophyll-a concentration in tributaries of the Seonakdonggang by an artificial neural network (ANN). As the tributaries are ungauged streams, a watershed runoff and quality model was used to simulate water quality parameters. The tributary watersheds include urban area and thus Storm Water Management Model (SWMM) was used to simulate TN, TP, BOD, COD, and SS. SWMM, however, can not simulate chlorophyll-a. The chlorophyll-a series data from the tributaries were estimated by the ANN and the simulation results of water quality parameters using SWMM. An assumption used is as follows: the relation between water quality parameters and chlorophyll-a in the tributaries of the Seonakdonggang would be similar to that in the mainstream of the Seonakdonggang. On the assumption, the measurement data of water quality and chlorophyll-a in the mainstream of the Seonakdonggang were used as the learning data of the ANN. Through the sensitivity analysis, the learning data combination of water quality parameters was determined. Finally, chlorophyll-a series were estimated for tributaries of the Seonakdonggang by the ANN and TN, TP, BOD, COD, and temperature data from those streams. The relative errors between the estimated and measured chlorophyll-a were approximately 40 ~ 50%. Though the errors are somewhat large, the estimation process for chlorophyll-a may be useful in ungauged streams.