In this study, the machine learning which has been widely used in prediction algorithms recently was used. the research point was the CD(chudong) point which was a representative point of Daecheong Lake. Chlorophyll-a(Chl-a) concentration was used as a target variable for algae prediction. to predict the Chl-a concentration, a data set of water quality and quantity factors was consisted. we performed algorithms about random forest and gradient boosting with Python. to perform the algorithms, at first the correlation analysis between Chl-a and water quality and quantity data was studied. we extracted ten factors of high importance for water quality and quantity data. as a result of the algorithm performance index, the gradient boosting showed that RMSE was 2.72 mg/m³ and MSE was 7.40 mg/m³ and R² was 0.66. as a result of the residual analysis, the analysis result of gradient boosting was excellent. as a result of the algorithm execution, the gradient boosting algorithm was excellent. the gradient boosting algorithm was also excellent with 2.44 mg/m³ of RMSE in the machine learning hyperparameter adjustment result.

This study focused on evaluating the efficiency of the removal of non-point source pollution by Daecheong Lake Juwon Stream constructed wetlands. The constructed wetland system is a surface flow type designed in the year 2007 for purifying eutrophic water of Daecheong Lake Juwon Stream. The value of conductivity, suspended solids(SS), chemical oxygen demand using a potassium permanganate(CODMn), five-day biochemical oxygen demand(BOD5), total nitrogen(T-N), total phosphorous(T-P), and pH in inflow averaged 220.2, 2.46, 3.33, 1.34, 2.00, 0.04 mg/L and 7.24, respectively and in outflow averaged 227.9, 1.12, 3.34, 0.87, 1.16, 0.02 mg/L and 7.45, respectively. The average removal efficiency of constructed wetlands was 30 % for SS, 22 % for BOD5, 45 % for T-N and 31 % for T-P. The removal rates of SS, BOD5 and T-N in the spring, summer and autumn were higher than those in winter. The removal rate of T-P was not significant different in all seasons. The amounts of pollutants removal in the constructed wetlands were higher in the order of 3rd ‹ 2nd ‹ 1st wetland for SS and T-P, 2nd ‹ 3rd ‹ 1st wetland for BOD5 and T-N. Therefore, our findings suggest that the constructed wetlands could well treat the eutrophic Daecheong Lake Juwon Stream waters.

대청호 남조세균 수화 기작에 대한 이해를 돕고자, 1997년부터 2002년까지 (2000년 제외)의 조사 자료를 바탕으로 남조세균 군집 특성을 해석하고 수화 발달 단계를 3단계로 구분하여 환경요인과의 관련성을 파악하였다. 남조세균 수화의 시작은 6월 하순부터 시작하며, 강과 호소의 중간 성향을 가진 정점 1부터 발생하였다. 대청호의 수화 발생 기간은 댐축 앞 지점인 정점 4를 기준으로 하는 경우, 약 60~70일이었으나, 1999년의 경우는 7월

강우시 저수지로 유입하는 탁수의 시공간분포를 실시간으로 예측하기 위해서는 하천 유입수 수온의 정확한 예측이 필요하다. 본 연구에서는 강우시 하천 수온의 변동특성을 조사하기 위해 2004년 홍수기 동안 대청호 상류 하천에서 한 시간 단위의 연속측정을 실시하였다. 강우사상 동안 하천수온은 강우 전 보다 최대 정도 하강하는 것으로 나타났으며, 이것은 저수지로 유입하는 하천수의 밀도를 tcg/ () 상승시켜 중층 밀도류를 형성하는 원인으로 작용했다. 실측자

This study was performed to analyze the variation characteristics of water qulity, correlation analysis of water quality data at each site and among the items of water quality data. Water quality for analysis was monthly values of water temperature, pH, dissolved oxygen, biochemical oxygen demand, chemical oxygen demand, suspended solid, T-N and T-P checked in Daecheong Lake from January to December, 1995. It was analyzed variation of monthly water qulity was well from February to April, water temperature and COD seemed to have high correlationships at all sites. Regression equation is COD = 0.07 Water temperature + 1.23 (R^2 = 0.7616) . Results of the correlation analysis of water quality data showed that DO had higt correlationships between site 1 and site 2, BOD did site 1 and 3, COD did site 1 and 2, SS did site 5 and 6, T-N did 2 and 3, T-P did site 4 and 6. Regression equations for estimate of water quality data are as follows. DO_1 = 4.46 + 0.59 DO_2 (R^2 = 0.8868), BOD_1 = 0.52 + 0.63 BOD_3 (R^2 = 0.6390) COD_2 = 0.44 + 0.71 COD_1 (R^2 = 0.9183), SS_6 = 0.89 + 0.70 SS_5 (R^2 = 0.9155) TN_3 = 0.151 + 0.886 TN_2 (R^2 = 0.9415), TP_4 = 0.004 + 0.758 TP_6 (R^2 = 0.9669)