• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.6
• /
• pp.507-516
• /
• 2021

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.

• Journal of Korean Society on Water Environment
• /
• v.35 no.1
• /
• pp.1-8
• /
• 2019

The purpose of this study is to evaluate the nutritional status of Lake Jinyang using Landsat 8 satellite image band correlated with chlorophyll-a, which is also related to algae proliferation. We selected 20 Landsat 8 images dating from 2013 to 2017, taken close to water quality measurement date when the cloud cover was less than 20 %. Based on the results of the previous studies, analyzing the correlation between chlorophyll-a, and Landsat 8 satellite image band, we selected near infrared wavelength, band 5 which is closely related to the population of algae. The nutritional status was classified using the Aizaki trophic state index (TSIm). The results of the regression equation between band 5 and the observed chlorophyll-a data was used to calculate chlorophyll-a for the image data from 2013 to 2017. The concentration of chlorophyll-a ranged from 3 to $16.1mg/m^3$. To illustrate the spatial distribution of chlorophyll-a within the lake, the chlorophyll-a concentration was divided into five grades. The images on October 14, 2014 and April 10, 2016 showed relatively high value of chlorophyll-a, while January 18, 2015 and December 6, 2016 chlorophyll-a value were below 5. The images on October 14, 2014 and April 10, 2016 were rated as eutrophic status in most areas. The results of simulating water quality for the day when the water quality was not measured resulted to an approximate value for the Panmun station while the Naedong station needed some corrections.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• Journal of Korean Society of Environmental Engineers
• /
• v.22 no.11
• /
• pp.2025-2036
• /
• 2000

A physicochemical process called ultra rapid coagulation(URC) was applied as a pilot scale to recover eutrophicated lake water at Inkyung Lake located on-campus in Inha university. The URC was uniquely designed to completely remove the presence of phosphorus up to 95%, which in turn leading to lessen the level of eutrophication of lake. For a pilot test of period, the lake was restored showing Carlson's Trophic State Index(TSI) of mesotrophic state which accounts for the reduction of total phosphorus and chlorophyll-a down to approximately 55 from 70 and 73, respectively. A residual presence of aluminum and additional coagulants in the effluent was tested for their potential effects on Photobacterium phosphoreum. The effect concentration ($EC_{50}$-15 min) observed in the effluent revealed that the bioactivity of Photobacterium phosphoreum was not influenced by the residual presence of coagulants. After the pilot test of period, the lake was consequently restored as a mesotrophic state in obtaining the second grade of lake water quality. The URC may be further applied for restoration of greater scale of lake in eutrophication.

• Journal of Korean Society on Water Environment
• /
• v.23 no.1
• /
• pp.144-154
• /
• 2007

The acute and chronic toxicity of ambient and effluent water discharged to Lake Shihwa were investigated by using Vibrio fischeri, Daphnia magna and Oryzias latipes. Physicochemical characteristics including biochemical oxygen demand (BOD) and nine heavy metals in a total of 15 water samples were evaluated and were satisfied with relevant Korean Water Quality Standards (KWQS) except for Hg in one sample. Acute toxicity was observed in five samples collected from three sampling locations. When impacts on reproduction and growth after chronic exposure were evaluated with D. magna, all the samples showed significant chronic effects. Reproduction appeared relatively more sensitive endpoint. In 21 days chronic tests on O. latipes, survival, mean egg number per female per day, hatching success rate and time to hatch were affected by increasing sample concentration. The organ-level changes such as gonadosomatic index (GSI), and hepatosomatic index (HSI), and molecular biomarker of vitellogenin (Vtg) induction that evaluated with O. latipes increased as exposure concentrations increased. It is noteworthy that the samples that did not exceed the KWQS resulted in acute and chronic toxicities. The results suggested that numeric criteria based on physicochemical parameters may not be protective of aquatic ecosystem. Acute and chronic toxicity tests with organisms representing different trophic groups should be supplemented in order to provide adequate level of environmental protection.

• Ocean and Polar Research
• /
• v.31 no.1
• /
• pp.71-76
• /
• 2009

Drastic changes in the water quality and phytoplankton community of the new Saemankeum Lakeduring the first decade following the construction of the Saemankeum Sea Wall has been considered to be unavoidable. Input of eutrophicated water through the Mankyeong River and Dongjin River might produce more direct effects on the water quality and phytoplankton community, which lead us to launch a long-term semi-weekly investigation at the "Mankyeong Bridge" monitoring point to resolve its short-term effect as well as long-term stabilization of the ecosystem in the new Saemankeum Lake. During 15 months starting from June 2006, the water temperature varied in accordance with the typical seasonal variations in temperate on the coasts, and no significant daily variations evoked by tidal cycle could be detected. However, there was an inverse relationship between seasonal precipitation and salinity even though the range in annual variation was drastically reduced right after the construction of the Saemankeum Sea Wall. Species richness in the phytoplankton community was also reduced due to the narrowed annual range of salinity, which would eliminate the mid-high salinity species from the Mankyeong Bridge monitoring point. Similarly, species diversity was decreased with increased dominance of the phytoplankton community after the construction. Between the two summer seasons during the present study, species diversity was higher in 2007 than in 2006, which might indicate the early stage of a gradual stabilization in the ecosystem including the phytoplankton community at the monitoring station. The phytoplankton community thus needs to be monitored on a long-term basis to identify indirect signals that can be used to assess the stability of the ecosystem in the young Saemankeum Lake.

• Korean Journal of Ecology and Environment
• /
• v.44 no.2
• /
• pp.155-171
• /
• 2011

The research assessed water quality using physico-chemical factors, trophic status index and attached diatom index in 10 reservoirs located in Chungcheongnam-do from October 2007 to June 2008. The physico-chemical water quality assessments revealed that Dangjin-gun (St. 1~5), which displayed a high chemical oxygen demand (V and VI) and chlorophyll-${\alpha}$ (Eutrophic-Hypereutrophic), was more polluted than Yesan and Cheongyang-gun. The sample were also hypereutrophic [trophic status index (TSI) 74.6] and ${\beta}$-mesosaprobic [diatom assemblage index to the organic water pollution (DAIpo) 44.47]. Yesan and Cheongyang-gun. Which were mid-level in their pollution status, were eutrophic (TSI 56.9) and ${\alpha}$-oligosaprobic (DAIpo 60.11). TSI correlated strongly with the attached diatom index (of DAIpo 0.60~0.62, and trophic diatom index of 0.72~0.74). Hence, the attached diatom index can be used with the trophic status assessment of lakes using TSI, and lake trophic status index (LTSI).

• Journal of Wetlands Research
• /
• v.20 no.2
• /
• pp.173-180
• /
• 2018

The utilization of TOC(Total organic carbon), a new environmental standard, was evaluated for 30 lakes in the Nakdong River Basin, which is used for drinking and agricultural usage. The active use of water resources begins with securing satisfactory water quality. Since this allows people and nature to maintain stability of quality, water quality standards are being tightened to ensure good water quality. In order to improve the pollution level of organic matter in lakes in the living environment, it is important to use the appropriate organic substance index. The relationship between the newly introduced TOC and the existing COD(Chemical oxygen demand) in the targeted lake was positively correlated with the possibility of replacing the TOC with COD. However, the environmental grade standard using TOC is better than the environmental grade standard using COD, so it has the same effect as that of the grade of water quality using TOC as an organic substance factor. This indicates the limitation of TOC to directly replace existing COD when trying to determine or improve the quality level using organic indicators of lakes. Therefore, in order to secure the qualitative safety of the lake, it is required to strengthen environmental standards of TOC in terms of water quality grade. In addition, the correlation between TOC and COD shows a great difference depending on the utilization characteristics of the lake. This requires clear scientific identification, and it requires continuous monitoring of COD that has been used to accumulate indicators of lake organic matter.

• Korean Journal of Environmental Biology
• /
• v.34 no.4
• /
• pp.320-328
• /
• 2016

This study was conducted to provide important basic information about effective management of the marine environment at major inflow streams in Lake Andong and Lake Imha. The investigation was conducted 8 times from May, 2015 (AD1, AD2, IH1, IH2) to September, 2016 (AD3, AD4, IH3, IH4), and 8 surveyed sites were selected at Lake Andong (4 sites) and Lake Imha (4 sites). The inquiry identified 114 species, $59,913.7inds.\;m^{-2}$ in Lake Andong and 112 species, $39,038.4inds.\;m^{-2}$ in Lake Imha. The results indicate that the number of species and individuals in Lake Andong is more than that in Lake Imha, because Lake Andong has a variety of riparian vegetation and a richness of organic materials. Community analysis at Lake Imha revealed a dominant index of 0.57 (${\pm}0.18$), a diversity index of 2.87 (${\pm}0.31$), an evenness index of 0.73 (${\pm}0.04$), and a richness index of 4.17 (${\pm}0.71$). The results of functional feeding group analysis showed that a high proportion of species and individuals are gathering collectors. The results of functional habitat group analysis showed that a high proportion of species and individuals are clingers. The result of a physico-chemical water assay and dissolved oxygen and electric conductivity tests revealed that these measures increased when the water temperature decreased. The result of Pearson's correlation analysis by biological factors and physico-chemical factors showed that species and electric conductivity are highly correlated with one another. Major inflow streams of Lake Andong and Lake Imha were exposed to various point pollution sources and non-point pollution sources. This implies a necessity for continuous monitoring of the aquatic ecosystems in order to effect systematic water quality management of Lake Andong and Lake Imha.

• Korean Journal of Ecology and Environment
• /
• v.36 no.2 s.103
• /
• pp.161-171
• /
• 2003

The present study evaluated water quality variation, limiting nutrient, and sediment of a shallow eutrophic lake (Lake Ilgam) in the metropolitan area from 2000 to 2002. According to annual mean chl.a ($77.2{\pm}36.6\;{\mu}g/l) and TP ($66.6{\pm}20.5\;{\mu}g/l) concentration and trophic state index (>60), Lake llgam was in very eutrophic status. Both inorganic nitrogen ($NH_3-N$ and $NH_3-N$) and phosphorus (SRP) concentrations in the water column increased during winter and spring, but decreased during summer followed by the phytoplankton development. Evidence for phosphorus and nitrogen as being the potential limiting nutrients for phytoplankton growth was supported by the ratio of DIN/DIP (by mass) (${\sim}$835.8), TSI derivations analysis, and algal growth potential bioassay. Based on the results of TSI derivations, strong nutrient limitation by both N and P occurred from September to November when P content in sediment (114.6 mg P/kg) was relatively low compared with the summer. Sediment contained a large amount of nitrogen (TKN: 4,452${\pm}$283.0mg N/kg dry sediment). Phosphorus content in sediment (TP: 313${\pm}$155 mg P/kg) was relatively low with temporal change. P release rate (0.29${\pm}$0.02 mg $m^{-2}$ $day^{-1}$) was high under the aerobic condition at pH 9. These results indicate that the sediment could play an important role as a source of a limiting nutrient, and temporal change of P content in the sediment is closely related with water quality, especially algal biomass change in Lake llgam.