The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

Benthic macroinvertebrates are important ecological and environmental indicators as primary or secondary consumers, and therefore are widely used in the evaluation of aquatic environments. However, there are no comprehensive river ecosystem monitoring surveys that link the major physicochemical water quality items with benthic macroinvertebrates in urban streams. Therefore, this study investigated the distribution characteristics of benthic macroinvertebrates and physicochemical water quality items (17 items) in Yangjaecheon and Yeouicheon from 2019 to 2020. At the same time, by applying Spearman’s rank correlation analysis and nonmetric multidimensional scaling (nMDS) analysis in the water quality data and biotic index, we tried to provide basic data for diagnosing the current status of river ecosystems in major urban rivers in Seoul. Based on the study results, a total of 39 species and 3,787 individuals were identified in Yangjaecheon, the water quality (based on BOD, TOC, and TP) of Yangjaecheon was higher than Grade Ib (good), and the BMI using benthic macroinvertebrates appeared as Grade C (normal) at all the sites. In Yeouicheon, a total of 51 species and 4,199 individuals were identified, the water quality (based on BOD, TOC, TP) was higher than Grade Ib (good) similar to Yangjaecheon, and the BMI of both Upstream and Saewon bridge was Grade B (good), while Yeoui bridge was Grade C (normal). Overall, analysis results for the distribution of benthic macroinvertebrates by a nonmetric multidimensional scaling method showed no significant difference between the two streams (p=0.1491). Also, significant environmental variables related to benthic macroinvertebrates distribution were determined as water temperature and DO. On the other hand, the results of the correlation analysis between biotic index and major water quality items confirmed that R1 and BMI could be used for on-site urban river water quality evaluation.

Understanding the characteristics of reservoir water quality is fundamental in reservoir ecosystem management. The water quality of reservoirs is affected by various factors including hydro-morphology of reservoirs, land use/cover, and human activities in their catchments. In this study, we classified 83 major reservoirs in South Korea based on nine physicochemical factors (pH, dissolved oxygen, chemical oxygen demand, total suspended solid, total nitrogen, total phosphorus, total organic carbon, electric conductivity, and chlorophyll-a) measured for five years (2015~2019). Study reservoirs were classified into five main clusters through hierarchical cluster analysis. Each cluster reflected differences in the water quality of reservoirs as well as hydromorphological variables such as elevation, catchment area, full water level, and full storage. In particular, water quality condition was low at a low elevation with large reservoirs representing cluster I. In the comparison of eutrophication status in major reservoirs in South Korea using the Korean trophic state index, in some reservoirs including cluster IV composed of lagoons, the eutrophication was improved compared to 2004~2008. However, eutrophication status has been more impaired in most agricultural reservoirs in clusters I, III, and V than past. Therefore, more attention is needed to improve the water quality of these reservoirs.

저서동물은 저서환경특성을 나타내는 중요한 지시자로 알려져 있다. 본 연구에서는 무안만 조 하대의 환경 및 저서동물의 분포특성을 조사하였으며, 수질평가지수(WQI)와 저서생물지수 (AMBI)를 이용하여 저서생태계 건강성을 평가하였다. 현장채집은 2019년 하계 무안만 조하대 의 10개 정점에서 이루어졌다. 무안만 조하대는 상부지역이 하부지역에 비해 세립한 입도특성 을 나타내고 있었으며, 높은 유기물 함량을 보였다. 일부 정점에서 오염지표종인 Musculista senhousia, Theora fragilis and Lumbrineris longifolia과 같은 종들도 우점을 나타내고 있었다. 군집분석결과 무안만 조하대는 상부, 중부, 하부 그룹으로 구분되었으며, 유기물 함량과 저서 건강성 평가지수(WQI 및 AMBI)와의 상관결과와 일치하였다. 본 연구결과, 무안만 조하대의 저서생태계는 양호한 것으로 평가되었다. 하지만 저서동물이 균등하게 분포하지 않고, 기회 종이 출현하고 있어 조하대의 유기물 부하량이 증가하고 있는 것으로 보인다.

빈번한 가뭄의 피해는 수자원의 양극화를 초래하고 있다. 국내에서는 2011년부터 2017년 사이에 국지적이고 주 기적인 이상 가뭄이 지속되어 10년 가뭄 빈도로 설계된 소규모 저수지의 저수율이 감소하였다. 이러한 저수율의 감소 는 수질을 떨어트릴 수 있고 이미 확보된 용수의 사용마저 제한할 수 있다. 따라서 가뭄에 대비하고 극복하기 위해서 는 수질관리와 가뭄 빈도의 재산정이 필요하다. 이 연구는 저수지에서 수질 변화의 원인인 잠재적 오염물질을 추정하고, 가뭄 기간 동안 저수지의 저수율 감소와 그에 따른 수질 변화를 검토한 것이다.

This study assessed the levels of water qualities and microbials contamination of inland olive flounder farms in Jeju in the summers from 2015 to 2017. Three farms (A-C) located in a concentrated area using mixing coastal seawater and underground seawater and one farm (D) located in an independent area using only coastal seawater were selected. Total ammonia nitrogen (TAN) reached a maximum of 0.898 ± 1.024 mg/L as N in the coastal seawater of A-C, which was close to the limit of the water quality management goal of the fish farm. TAN in the influent from A-C was up to three times higher than that of D, so that the discharged water did not spread to a wide range area along the coast and continued to affect the influent. TAN of the effluent in A-C increased by 2.7-4.6 times compared to the influent, resulting in serious self-pollution in the flounder farm. Heterotrophic marine bacteria in the influent of A-C was about 600 times higher than D, and the discharge of A-C was increased by about 30 times compared to the influent.

Pilot-scale coagulation and sedimentation processes were operated to investigate the T-P (Total phosphorus) removal efficiency. A multiple regression model was also derived to predict the water quality improvement effect with river water characteristics. The inflow rates for the pilot-scale facility were 157–576 m3/day, and the coagulant doses were in the range of 13.7–58.5 mg/L (average 38.9 mg/L) for PAC (Poly alum chloride) and 16.5–62.1 mg/L (average 36.0 mg/L) for alum. The results found that the influent BOD (Biochemical oxygen demand) and T-P concentrations were 4.9 mg/L and 0.115 mg/L, and the removal efficiencies were 52.7% and 59.4%, respectively. T-P removal efficiencies on wet weather days were higher by 10% than dry weather days because influent solids influenced T-P's coagulation process. The pH of river water was 6.9–7.8, and the average pH was 7.3. Although the pH variation was not significant, the trend showed that the treatment efficiency of T-P and PO4-P removal increased. Thus, the pH range considered in this study seems to be appropriate for the coagulation process, which is essential for phosphorous removal. The T-P removal efficiencies were 19.6–93.3% (average 59.2%) for PAC and 16.4–98.5%(average 55.9%) for alum; thus, both coagulants showed similar results. Furthermore, the average coagulant doses were similar at 42.4 mg/L for PAC and 41.3 mg/L for alum. When the T-P concentration of the effluent was compared by the [Al]/[P] ratio, the phosphorus concentration of the treated water decreased with an increasing [Al]/[P] ratio, and the lowest T-P concentration range appeared at the [Al]/[P] ratio of 10–30. A seasonal multiple regression analysis equations were derived from the relationships between 10 independent and dependent variables (T-P concentration of effluent). This study could help lake water quality maintenance, reduce eutrophication, and improve direction settings for urban planning, especially plans related to developing waterfront cities.