• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.531-538
• /
• 2024

While the importance of the water quality environment is being emphasized, the water quality index for improving the water quality of urban rivers in Gwangju Metropolitan City is an important factor affecting the aquatic ecosystem and requires accurate prediction. In this paper, the XGBoost and LightGBM machine learning algorithms were used to compare the performance of the water quality inspection items of the downstream Pyeongchon Bridge and upstream BanghakBr_Gwangjucheon1 water systems, which are important points of Gwangju Stream, as a result of statistical verification, three water quality indicators, Nitrogen(TN), Nitrate(NO3), and Ammonia amount(NH3) were predicted, and the performance of the predictive model was evaluated by using RMSE, a regression model evaluation index. As a result of comparing the performance after cross-validation by implementing individual models for each water system, the XGBoost model showed excellent predictive ability.

• Journal of Plant Biology
• /
• v.29 no.2
• /
• pp.117-127
• /
• 1986

Phytoplankton community was investigated at the Paldang Dam Reservoir in the Mid-Han River by it's depth, in spring and summer known as the period of phytoplankton's blooming. It was only in summer that phytoplankton bloomed at the investigated area. 128 kinds of phytoplankton were identified and of them, diatoms were abundunt in spring but cyanophyta and chlorophyta were in summer. Because some species with high pollution index were observed in summer, it could be proved that the investigated area was polluted especially in summer. In spring shown the circulation period by vertical distribution pattern of chlorophyll-a and isothermal distribution pattern of water temperature, maximum value of phytoplankton standing crops appeared at the upper layer, except for surface layer. In summer shown the circulation period after the stagnation period by vertical distribution pattern of chlorophyll-a and immediate destruction after stratification of water temperature, maximum value of phytoplankton standing crops appeared at the lower layer. the layer at which the maximum value of chlorophyll-a appeared also accorded with that of phytoplankton standing crops. So, it could be approved that there existed a close relationship among phytoplankton standing crops, chlorophyll-a, and water temperature.

• Journal of Environmental Science International
• /
• v.27 no.8
• /
• pp.689-699
• /
• 2018

The changes on community structures of benthic macroinvertebrates, relevance to the environment and interrelationship between benthos were studied over two years in stream with large environmental disturbance, which caused by localized heavy rain during Typhoon Chaba in October 2016. As a result, the number of species and individuals were increased after localized heavy rain, especially numbers of individuals of Ephemeroptera and Plecoptera were greatly increased. On the contrary, those of Semisulcospira libertina and Semisulcospira forticosta of Mesogastropoda were greatly decreased. Dominant species was Baetis fuscatus of Ephemeroptera, numbers of species and individuals of Ephemeroptera, Plecoptera and Trichoptera(EPT group) were dramatically increased from 26 species, 110 individuals to 32 species, 365 individuals respectively. This suggests that the change of river bed and flow velocity due to heavy rain provided a suitable environment for the EPT group that preferred the rift of a stream. In the functional feeding group, only gathering collectors and filtering collectors were identified in autumn of 2017 because some functional groups preferentially adapted to the changed environment. The interspecific competition and environmental condition were the worst in autumn after heavy rain due to the increase individuals of some species. The ecological score of benthic macroinvertebrate community(ESB) was higher after the heavy rain than before. Results of the Group Pollution Index(GPI), Korean Saprobic Index(KSI) and Benthic Macroinvertebrate Index(BMI) were similar to those before and after heavy rainfall. Therefore, ESB was the most discriminating method for estimating the biological water quality in this study. Some species that are sensitive to water quality changes still appear or increase individuals in the area under investigation after the heavy rain. On the other hand, the individuals of some pollutant species decreased. This is thought to be because the habitat fluctuation caused by heavy rainfall has improved the water environment.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.10
• /
• pp.1351-1357
• /
• 2010

Water monitoring equipments using daphnia can be used to monitor the pollution levels of a country's main rivers. Such equipments should be capable of providing a prompt warning about increase in the contamination levels, which is evaluated on the basis of impulse number or toxicity index. As unmanned remote control equipments, they must provide reliable pollution monitoring results for each season and for the annual physical changes in each river. Two different equipments based on the impulse number and toxicity index showed different results for the operating rates and for the number of emergency checks required even though both were operated at the same conditions. The results are affected by many parameters such as the presence of any air bubbles and the microscopic pressure. The purpose of this study is to develop a method that can reduce the effect of bubbles or microscopic pressure on the monitoring data. We expect to achieve reliable monitoring data for water pollutants irrespective of the location of the equipment setup.

• Journal of Environmental Science International
• /
• v.28 no.12
• /
• pp.1085-1099
• /
• 2019

We investigated the spatial and temporal variation in characteristics and pollution assessment of sediments in the watersheds of Andong-Dam and Imha-Dam, in Korea. Surface sediments were collected from six sites once a year for three years (2015-2017), and analyzed for organic matter (water content, IL, COD, TOC, TN, and TP), grain size, and concentration of trace metals (Al, Li, Zn, Cr, Pb, Cu, Ni, and As). Organic matter generally tended to increase, and was higher in the Andong watershed compare to Imha watershed. Surface sediments were mainly composed of silt. Coarse sediments were mainly distributed at the site adjacent to Andong-Dam, and showed fining after coarsening. Fine sediment were mainly distributed at the site adjacent to Imha-Dam, and were gradually coarsening. Concentration of trace metals generally tended to increase, and was higher for sites in watershed of Andong watershed (PLI > 1) than for sites in Imha watershed (PLI < 1). Trace metals in the study area were considered to be affected by fine sediment (silt), and contamination of trace metals was somewhat affected by Pb, and greatly affected by Zn and As.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.1
• /
• pp.24-35
• /
• 2023

Rapid industrialization and urbanization have led to severe marine pollution. A Water Quality Index (WQI) has been developed to allow the effective management of marine pollution. However, the WQI suffers from problems with loss of information due to the complex calculations involved, changes in standards, calculation errors by practitioners, and statistical errors. Consequently, research on the use of artificial intelligence techniques to predict the marine and coastal WQI is being conducted both locally and internationally. In this study, six techniques (RF, XGBoost, KNN, Ext, SVM, and LR) were studied using marine environmental measurement data (2000-2020) to determine the most appropriate artificial intelligence technique to estimate the WOI of five ecoregions in the Korean seas. Our results show that the random forest method offers the best performance as compared to the other methods studied. The residual analysis of the WQI predicted score and actual score using the random forest method shows that the temporal and spatial prediction performance was exceptional for all ecoregions. In conclusion, the RF model of WQI prediction developed in this study is considered to be applicable to Korean seas with high accuracy.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.4
• /
• pp.182-192
• /
• 2008

In oder to develop a decision supporting system for oil spill response, the prototype of pollution response support system which has integrated oil spill prediction system and pollution risk prediction system has developed for Incheon-Daesan area. Spill prediction system calculates oil spill aspects based on real-time wind data and real-time water flow and the residual volume of spilt oil and spread pattern are calculated considering the characteristic of spilt oil. In this study, real-time data is created from results of real-time meteorological forecasting model(National Institute of Environmental Research) using ftp, real-time tidal currents datasets are built using CHARRY(Current by Harmonic Response to the Reference Yardstick) model and real-time wind-driven currents are calculated applying the correlation function between wind and wind-driven currents. In order to model the feature which is spilt oil spreading according to real-time water flow is weathered, the decrease ratio by oil kinds was used. These real-time data and real-time prediction information have been integrated with ESI(Environmental Sensitivity Index) and response resources and then these are provided using GIS as a whole system to make the response strategy.

• Korean Journal of Ecology and Environment
• /
• v.53 no.1
• /
• pp.91-101
• /
• 2020

Stormwater runoff is known as a major non-point water pollution source that transports heavy metals, which have accumulated in road surface, to stream and coastal area. Dissolved and particulate metals in stormwater runoffs have been investigated to understand the outflow characteristics of heavy metals during rainfall events and to identify their pollution sources. The concentration of dissolved Co and Ni decreased after the outflow with high concentrations at the beginning of the rainfall, and other metals showed different characteristics depending on the rainfall and rate of discharge. Particulate metals showed a similar trend with the temporal variation of suspended solids concentration in stormwater runoffs. The results of geo-accumulation index (I_geo) indicated that the stormwater runoffs from industrial region were very highly polluted with Cu, Zn and Cd. As a result of comparing the metal concentrations of <125 ㎛ for road dust near the study area, Cu, Zn and Cd were originated from inside of metal manufacturing facilities rather than traffic activities at road surface and these metals accumulated on the surface area of facilities were transported to the water environments during stormwater event. The average discharged amounts of heavy metals for one rainfall event were Cr 128 g, Co 12.35 g, Ni 98.5 g, Cu 607.5 g, Zn 8,429.5 g, As 6.95 g, Cd 3.7 g, Pb 251.75 g, indicating that metal runoff loads in the stormwater runoffs are closely related to surrounding industry types.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.3 no.2
• /
• pp.51-61
• /
• 1997

The in situ observations and the seawater analyses were conducted in July and Auguse, 1996 for the purpose of evaluating the characteristics of seawater quality centered about eutrophication in Mokpo harbour. By applying the OECD standards of trophic classification to the parameters such as secchi depth, total inorganic nitrogen, phosphate phosphorus and chlorophyll-a, the trophic level of seawater in Mokpo harbour was evaluated to be in eutrophic state in summer. The estimation of pollution index by eutrophication showed the seawater quality of Mokpo harbour to deteriorate and fall under the regular grades. The results of eutrophic index estimation showed the high otentiality of red tide occurrence in Mokpo harbour.

• Journal of Korean Society on Water Environment
• /
• v.30 no.6
• /
• pp.612-621
• /
• 2014

Physicochemical factors and the phytoplankton communities in the downstream area of Namhan-River were investigated from June 2012 to November 2013. We also assessed water quality using biological water quality indices. Total nitrogen was 2.4 mg/L, total phosphorus was 0.04 mg/L, and biological oxygen demand was 1.1 mg/L. This resulted in a level 2 (Ib, good) water quality rating. A total of 259 phytoplankton taxa were classified, consisting of 26 families, two subfamilies, 64 genera, 222 species, 32 varieties, and five formas. Bacillariophyceae dominated during a1l seasons and at all sites. The dominant species were Aulacoseira granulata, Cyclotella meneghiniana, C. stelligera, Melosira varians, Cocconeis placentula var. lineata, Nitzschia palea, N. amphibia, Cymbella minuta, and Achnanthes convergens. The diatom assemblage index for organic pollution values was level A-D, and TDI was level B-D. P-IBI at most sites was at the M (moderate) level, but TSI was at the E (eutrophic) level. Most indices dropped from upstream to downstream.