• Journal of Korean Society on Water Environment
• /
• v.31 no.2
• /
• pp.159-165
• /
• 2015

The organic matter sources of phytoplankton and related environmental factors influencing algal bloom in Paldang reservoir were studied using nitrogen and carbon isotope ratio(${\delta}^{15}N$, ${\delta}^{13}C$). Phytoplankton samples for stable isotope analysis were collected from four points in reservoir using a plankton net. Physicochemical water quality, algal taxa and hydrological data were collected from published monitoring material. Phytoplankton samples were analyzed by IRMS. CN ratio of each sample was very similar to that of phytoplankton from literature cited. ${\delta}^{15}N$ of each sample was decreased during July. Mixing and dilution of nitrogen sources due to increment of influx by concentrated rainfall were considered as the main reason for the decline of ${\delta}^{15}N$. Based on analyzed ${\delta}^{15}N$ value of each sample, nitrogen source of Bughan river sample was presumed to come from soil. The nitrogen sources of Namhan river and Kyeongan stream samples seemed to be sewage or animal waste. Low ${\delta}^{15}N$ value in August (2012) seemed to be influenced by isotope fractionation due to the blooming of nitrogen-fixation blue-green algae (Anabaena spp.). Variation in ${\delta}^{15}N$ values particularly by blue-green algal bloom was considered the important factor for estimating the organic matter sources of phytoplankton.

• Journal of Korean Society on Water Environment
• /
• v.39 no.1
• /
• pp.1-8
• /
• 2023

Monitoring and prediction of water quality are essential for effective river pollution prevention and water quality management. In this study, a multi-classification model was developed to predict chlorophyll-a (Chl-a) level in rivers. A model was developed using CatBoost, a novel ensemble machine learning algorithm. The model was developed using hourly field monitoring data collected from January 1 to December 31, 2015. For model development, chl-a was classified into class 1 (Chl-a≤10 ㎍/L), class 2 (10<Chl-a≤50 ㎍/L), and class 3 (Chl-a>50 ㎍/L), where the number of data used for the model training were 27,192, 11,031, and 511, respectively. The macro averages of precision, recall, and F1-score for the three classes were 0.58, 0.58, and 0.58, respectively, while the weighted averages were 0.89, 0.90, and 0.89, for precision, recall, and F1-score, respectively. The model showed relatively poor performance for class 3 where the number of observations was much smaller compared to the other two classes. The imbalance of data distribution among the three classes was resolved by using the synthetic minority over-sampling technique (SMOTE) algorithm, where the number of data used for model training was evenly distributed as 26,868 for each class. The model performance was improved with the macro averages of precision, rcall, and F1-score of the three classes as 0.58, 0.70, and 0.59, respectively, while the weighted averages were 0.88, 0.84, and 0.86 after SMOTE application.

• Journal of Korean Society on Water Environment
• /
• v.38 no.6
• /
• pp.292-305
• /
• 2022

The Yeongsan River, one of the four largest rivers in South Korea, has been facing difficulties with water quality management with respect to algal bloom. The algal bloom menace has become bigger, especially after the construction of two weirs in the mainstream of the Yeongsan River. Therefore, the prediction and factor analysis of Chlorophyll-a (Chl-a) concentration is needed for effective water quality management. In this study, Chl-a prediction model was developed, and the performance evaluated using machine and deep learning methods, such as Deep Neural Network (DNN), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). Moreover, the correlation analysis and the feature importance results were compared to identify the major factors affecting the concentration of Chl-a. All models showed high prediction performance with an R² value of 0.9 or higher. In particular, XGBoost showed the highest prediction accuracy of 0.95 in the test data.The results of feature importance suggested that Ammonia (NH₃-N) and Phosphate (PO₄-P) were common major factors for the three models to manage Chl-a concentration. From the results, it was confirmed that three machine learning methods, DNN, RF, and XGBoost are powerful methods for predicting water quality parameters. Also, the comparison between feature importance and correlation analysis would present a more accurate assessment of the important major factors.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.14 no.3
• /
• pp.155-162
• /
• 2009

To characterize the initiation, propagation and termination of Cochlodinium polykrikoides blooms in the southeast coastal waters of Korea, 2008, we analyzed the data set of phytoplankton composition, physical and chemical water properties, and meterological data. C. polykrikoides bloom in 2008 were long lasting and restricted to the coastal area with a low density. Our results indicate that C. polykrikoides blooms were affected by the atypical cold waters occurring in east-south coastal water in the early July. The cold water masses probably protected the free living cells of C. polykrikoides from entering into the coastal area from offshore waters as a pelagic seed population. The low density blooms of small scale established possibly by the germination of C. polykrikoides cyst in shallow coastal bottom could have not spread over because of the weak wind and low nutrient concentrations caused by severe drought in July and September.

• Korean Journal of Environmental Biology
• /
• v.31 no.4
• /
• pp.429-439
• /
• 2013

This study was conducted to identify the relationship between environmental factors and algal bloom, and provide information for efficient management based on the results of monitoring the environmental parameters and algal diversity in the Jundai reservoir from March 2011 to October 2013. Little change in the weather conditions was observed during the study period except for a slight decrease in rainfall. Concentration of TN and TP in the reservoir exceeded water quality standards for agriculture and significant correlation between algal growth and environmental factors was observed. Phytoplankton in Jundai reservoir included 6 classes, 40 genus, 62 species, and the phytoplankton abundance was in the range of $1.3{\times}10^4{\sim}2.8{\times}10^6$ cells $mL^{-1}$. The annual average of phytoplankton abundance and Chl-a gradually decreased as TN and TP concentrations decreased. Overall Anabaena sp., Oscillatoria sp., and Microcystis sp. were the dominant species in Jundai reservoir. As the water temperature increased, the dominant species were Anabaena sp., Microcystis sp. and Oscillatoria sp., in that order. Anabaena sp. was dominant from spring to early summer with increase in water temperature and pollutant concentrations, and high correlation with environmental factors was observed. Microcystis sp. was dominant depending on changes in the nutrient levels. In the case of Oscillatoria sp., there was no significant correlation between phytoplankton biomess and Chl-a. However, efficient management of water environment and practical control of algal bloom in small scale reservoir polluted by livestock and farm irrigation should be achieved by identification of the relationship between algal growth and environmental factors.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.

• Journal of Korean Society of Water and Wastewater
• /
• v.16 no.6
• /
• pp.700-709
• /
• 2002

Present condition of the Youngsan River pollution is serious. Concentrations of organic materials and nutrients are high and algal bloom takes place frequently. The pollution is mainly caused by domestic wastewater input from urban areas like Kwangju and Naju City. In this study, 6 times of water quality surveys were done for mainstream and tributaries. Delivery ratios of each tributaries are calculated with the water quality and flow data. With Arc/View GIS, sub-basin are divided and pollution loads are estimated. These data are used for water quality modeling. River quality improvement effects are analysed with 5 scenarios including process upgrade of present WWTPs and construction of new WWTPs. These scenarios are applied for the Youngsan River based on the 7Q10 and Q275. And total wastewater treatment cost in the basin is analysed for each scenario.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.35 no.6
• /
• pp.568-577
• /
• 2002

The spreading Cocuoainim polykikoides bloom in the southern coastal waters of Korea was simulated using numerical model including the physical processes of water flow and the chemical processes of increasing cell of C. polykikoides by uptake of dissolved nutrients. The circulation of sea water was simulated by two dimensional tide model reflecting the main four tidal components of $M_2,\;S_2,\;K_1,\;O_1$, and permanent current was driven by inflow/outflow across open boundaries. According to the result of model which tidal and permanent current were reflected simultaneously, eastward flows entering the southern waters from the western waters of Korea are dominant but westward flows are weak relatively. These result suggest that it is difficult for initial C. polykikoides bloom generated in the coastal waters of Goheung to move to the western coast of Korea through Jeju Strait. For spreading model of C. poiyhikoides, the range of generating distribution and the generating time of C. polykikoides bloom in coastal area are similar to those of observation data in the field. Wind is the most important factor in moving and distribution of red tide. Permanent current flowing eastward is also considered to be important factor and tidal current was a little influenced.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.14 no.4
• /
• pp.229-239
• /
• 2009

To understand major factors that affected on distinct Cochlodinium bloom scale in Korean coasts in 2007 and 2008, oceanographic and meteorological characteristics during Cochlodinium bloom period were compared. The main reason for large scale blooms in 2007, covering both southern coast and eastern coast with about 10 million US dollars fish kills, was attributed to sufficient nutrient supply by heavy rainfall, upwelling in the coast arising from irregular wind shift, weak thermocline and low grazing pressure by zooplanktons during Cochlodimum bloom development period. On the contrary, small scale blooms in 2008 covering only inshore areas of southern coast without fish kills was attributed to the low nutrient level in coastal areas by long persistent drought and strong influence of oligotrophic offshore water onto inshore and high grazing pressure by extra ordinarily abundant zooplanktons during Cochlodinium development period. Conclusively, it was estimated that nutrient level, strength of offshore water and feeding pressure might play a significant role in the difference of bloom scale between the two years.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.5 no.1
• /
• pp.1-7
• /
• 2002

The effects of floating islands on the changes in phytoplankton community structure were investigated in a small artificial pond. The floating islands planted with various emergent macrophytes covered 35% of total water surface area of the pond. Total 17 genera and 25 species of phytoplankton were found in the pond, of which Dinophyceae was 1 genera and 1 species, Cyanophyceae 1 genera and 1 species, Bacillariophyceae 6 genera and 8 species, and Chlorophyceae 9 genera and 15 species. Dominant phytoplanktons under floating islands were changed from Aphanizomenon sp. as a Cyanophyceae to Golenkinia radiata, Kirchneriella contorta and Micractinium pusillum as a Chlorophyceae for 56 days after the construction of floating islands on July 24, 2001. The changes of dominant phytoplanktons of the control without floating islands were similar to those under floating islands in July and August, but Aphanizomenon sp. was rapidly increased in the control sites in September. About 99% of the cell number of Aphanizomenon sp. was disappeared for a month after construction of floating islands. Species diversity of phytoplankton under the floating islands of Iris pseudoacorus was higher than those of other macrophytes as well as the control without floating islands. The cell numbers of Cyanophyceae and Chlorophyceae were fewer under the floating islands of I. pseudoacorus than those of other macrophytes. Our results showed that the floating islands could be a useful eco-technique for the control of water bloom by Cyanophyceae and Chlorophyceae in a pond ecosystem.