• 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 Korea Water Resources Association
• /
• v.44 no.6
• /
• pp.477-486
• /
• 2011

The objective of this study is to investigate the water pollution problems brought about by the construction of eco-friendly waterfront space through the physical model experiment including water quality consideration. Due to the lack of water supply into the artificial ponds and canals, the water quality problems such as eutrophication, odor and so on can be occurred. There have been many numerical models on such phenomena but limited studies using physical test due to the difficulty in the verification of physical interpretation of the study area. In this study, a prototype model that is not affected by the dimensionless parameters was carried out, where unpolluted water is mixed into the contaminated water to reduce the concentration of nutrients. In addition, this study also attempt to find the optimal configuration of the flow induction machines using the scale model which will evaluate and verify the effectiveness of the enforcement methods to maintain the water quality objectives.

• Journal of the korean society of oceanography
• /
• v.39 no.2
• /
• pp.148-154
• /
• 2004

This study describes the realtime monitoring system for water quality conditions in coastal waters. Some issues on the data qualify control and quality analysis are examined along with examples of erroneous data. Three different cases of database produced by the realtime monitoring system are presented and analyzed, namely 1) hypoxic condition, 2) over-saturated D.O. and 3) short-term variability of temperature and D.O. In utilizing the realtime database, D.O. prediction and warning models are developed based on autoregressive stochastic process. The model is very simple, yet, users in various levels from powerful and useful with its ability to send warning messages to users in varous levels from governmental administrative staff to local fisherman, and give them some allowances to cope with the situation.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.1
• /
• pp.102-114
• /
• 2003

The objectives of the paper are to evaluate cell based pollutant loadings for different storm events, to monitor the hydrology and water quality of the Baran HP#6 watershed, and to validate AGNPS with the field data. Simplification was made to AGNPS in estimating storm erosivity factors from a triangular rainfall distribution. GIS-AGNPS interface model consists of three subsystems; the input data processor based on a geographic information system. the models. and the post processor Land use patten at the tested watershed was classified from the Landsat TM data using the artificial neural network model that adopts an error back propagation algorithm. AGNPS model parameters were obtained from the GIS databases, and additional parameters calibrated with field data. It was then tested with ungauged conditions. The simulated runoff was reasonably in good agreement as compared with the observed data. And simulated water quality parameters appear to be reasonably comparable to the field data.

• Korean Journal of Food Science and Technology
• /
• v.38 no.3
• /
• pp.337-341
• /
• 2006

The quality characteristics of a surimi-based product with sea tangle single cell detritus (SCD) were studied in order to utilize SCD from sea tangle as a food additive. Mixture design and regression models were applied to optimize the processing conditions and to investigate the interaction between surimi and the other ingredients. Surimi and SCD decreased hardness and cohesiveness of surimi gels, and then increased them. Water increased hardness and then decreased it, whereas cohesiveness was reversed. Surimi and water increased gumminess and brittleness of surimi gels, but SCD decreased them. SCD increased water retention ability (WRA) and whiteness of surimi gels, whereas water decreased it. Hardness and cohesiveness fitted nonlinear models by ANOVA, but gumminess, brittleness, WRA and whiteness fitted linear models. The response constraint coefficient showed that surimi influenced hardness and whitenessmore than water and SCD, whereas water influenced WRA more than surimi and SCD. Moreover, SCD influenced cohesiveness, gumminess and brittleness more than surimi and water. Hardness and cohesiveness fitted nonlinear models with interaction terms for surimi-SCD and surimi-water, respectively. Optimum mixed ratio values of surimi, water, and SCD were 36.80, 57.07 and 4.14%, respectively, by mixture model.

• Journal of Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.769-777
• /
• 2021

This study investigated the change of the achievement rate of the target water quality conditioned on the occurrence of severe drought, to assess the effects of meteorological drought on the water quality management in the Nakdong River basin. Using three drought indices with difference time scales such as 30-, 60-, 90-day, i.e., SPI30, SPI60, SPI90, and three water quality indicators such as biochemical oxygen demand (BOD), total organic carbon (TOC), and total phosphorus (T-P), we first analyzed the relationship between severe drought occurrence water quality change in mid-sized watersheds, and identified the watersheds in which water quality was highly affected by severe drought. The Bayesian network models were constructed for the watersheds to probabilistically assess the relationship between severe drought and water quality management. Among 22 mid-sized watersheds in the Nakdong River basin, four watersheds, such as #2005, #2018, #2021, and #2022, had high environmental vulnerability to severe drought. In addition, severe drought affected spring and fall water quality in the watershed #2021, summer water quality in the #2005, and winter water quality in the #2022. The causal relationship between drought and water quality management is usufaul in proactive drought management.

• Spatial Information Research
• /
• v.6 no.1
• /
• pp.91-102
• /
• 1998

The objectives of this research were to develop fish-habitat relationship models which can be used to estimate fish species riclmess of small and medium rivers in Korea, and test the accuracy of the models. The models are based on the Aquatic GAP Analysis model in the New York Cooperative Fish & Wildlife Research Unit (19%), and they employ three habitat factors; river size, physical habitat, and water quality of each river segment. Model 1 and model II are based on the water quality standard for life support of EP A and the water quality class of Korea, respectively. Test sites for this study include one urban stream and three less spoiled tributaries of the Han River. The results of this research can be summarized as follows. First, the number of habitat types identified by model I and model II are nine and 14, respectively. Second, the average accuracy of the three distribution maps of rare or endangered fish species are 80.6% (model 1) and 81.2% (model II). Third, the accuracy of fish species richness are 94% (model 1) and 95% (model II), and the water quality is the most important factor affecting fish species richness. Fourth, the accuracy of fish species list are 50.5% (model 1) and 68.7% (model II), but the accuracy of less spoiled stream segments and that of polluted stream segments are 67.1% and 86.5%, respectively. Finally, it can be concluded that the overall performance of model II is better than that of model I at our test sites.

• Journal of Korea Water Resources Association
• /
• v.38 no.9 s.158
• /
• pp.791-800
• /
• 2005

An ILLUDAS-NPS model was developed which is able to compute pollutant loadings and the concentrations of water quality constituents. This model is based on the existing ILLUDAS model, and added for use in the water quality analysis process during dry and rainy periods. For dry period, the specifications of coefficients for discharge and water quality were used. During rainfall, we used the daily pollutant accumulation method and the washoff equation for computing water quality each time. According to the results of verification, the ILLUDAS-NPS model provides generally similar outputs with the measured data on total loadings, peak concentration and time of peak concentration for three rainfall events in the Hong-je Basin. In comparison with the SWMM and STORM models, it was shown that there is little difference between ILLUDAS-NPS and SWMM.

• Journal of Environmental Science International
• /
• v.23 no.7
• /
• pp.1321-1332
• /
• 2014

The key objective of this study was to evaluate trophic state and empirical water quality models along with analysis of fish trophic guilds in relation to water chemistry (N, P). Trophic state index (TSI), based on total phosphorus (TP) and chlorophyll-a (CHL), ranged between oligotrophic and hypereutrophic state, by the criteria of Nurnberg(1996), and was lower than the trophic state of total nitrogen (TN). Trophic relations of Secchi depth (SD), TN, TP, and CHL were compared using an empirical models of premonsoon (Pr), monsoon (Mo), and postmonsoon (Po). The model analysis indicated that the variation in water transparency of Secchi depth (SD) was largely accounted (p < 0.001, range of $R^2$ : 0.76-0.80) by TP during the seasons of Mo and Po and that the variation of CHL was accounted (p < 0.001, $R^2=0.70$) up to 70% by TP during the Po season. The eutrophication tendency, based on the $TSI_{TP}$ vs. $TSI_{N:P}$ were predictable ($R^2$ ranged 0.85-0.90, p < 0.001), slope and y intercept indicated low seasonal variability. In the mean time, $TSI_{N:P}$ vs. $TSI_{CHL}$ had a monsoon seasonality in relation to values of $TSI_{N:P}$ during the monsoon season due to a dilution of reservoir waters by strong monsoon rainfall. Trophic compositions of reservoir fish reflected ambient contents of TN, TP, and CHL in the reservoir waters. Thus, the proportions of omnivore fish increased with greater trophic conditions of TP, TN and CHL and the proportions of insectivore fish decreased with greater trophic conditions.

• 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.