• Journal of Korean Society of Water and Wastewater
• /
• v.21 no.3
• /
• pp.305-314
• /
• 2007

Forecasting of water quality variation is not an easy process due to the complicated nature of various water quality factors and their interrelationships. The objective of this study is to test the applicability of neural network models to the forecasting of the water quality at Dalchun station in Han River. Input data is consist of monthly data of concentration of DO, BOD, COD, SS and river flow. And this study selected optimal neural network model through changing the number of hidden layer based on input layer(n) from n to 6n. After neural network theory is applied, the models go through training, calibration and verification. The result shows that the proposed model forecast water quality of high efficiency and developed web-based water quality forecasting system after extend model

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.32 no.3
• /
• pp.116-129
• /
• 1990

A rational management of water resources in estuary reservoirs necessiates the prediction of water quality. In this study, a multiple box model for the water quality prediction was developed as a tool for the purpose of examining an adequate way to improve and maintain the water quality. Some submodels that are suitable for simulating the mixing behavior of pollutant materials in a lake were considered in this model. The model was appiled for predicting water qualities of Haenam Esturay Reservoir. The result from this study can be summarized as follows : 1.A water quality simulation model that can predict the 10-day mean value of water qualities was developed by adding some submodels that simulate the concentrations of chlorophyll-a, BOD, T-P and T-N to the existing Multiple Box Model representing the mixing and circulating of materials by the hydarulic action. 2.As input data for the model developed, the climatic data including precipitation, solar radiation, temperature, cloudness, wind speed and relative humidity, and the water buget records including the pumping discharge and the releasing discharge by drainage gate were ollected. The hydrologic data for the inflow discharge from the watershed was obtained by simulation with the aid of USDAUL-74/SNUA watershed model. Also the water quality data were measured at streams and the reservoir. 3.As a result of calibration and verification test by using four comonents of water quality such as Chlorophyll-a, BOD, T-P and T-N, it was found that the correlation coefficeints between the observed and the simulated water qualities showed greater than 0.6, therefore the capability of the model to simulate the water quality was proved. 4.The result based on the model application showed that the water quality of the Haenam Estuary Reservoir varies seasonally with the harmonic trend, however the water quality is good in winter and get worse in summer. Also it may be concluded that the current grarde of water quality in the Heanam Esutary Reservoir is ranked as grade 4 suitable only for the agricultutal use.

• 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 Korean Society on Water Environment
• /
• v.20 no.4
• /
• pp.321-326
• /
• 2004

The objective of this study is to test the applicability of neural network models to forecast water quality at Naesa and Pyongchang river. Water quality data devided into rainy day and non-rainy day to find characteristics of them. The mean and maximum data of rainy day show higher than those of non-rainy day. And discharge correlate with TOC at Pyongchang river. Neural network model is trained to the correlation of discharge with water quality. As a result, it is convinced that the proposed neural network model can apply to the analysis of real time water quality monitoring.

• Ecology and Resilient Infrastructure
• /
• v.9 no.1
• /
• pp.24-35
• /
• 2022

For water quality management, it is necessary to continuously improve the forecasting by analyzing the past water quality, and a Data-driven model is emerging as an alternative. Because the Data-driven model is built based on a wide range of data, it is essential to apply the correlation analysis method for the combination of input variables to obtain more reliable results. In this study, the Gamma Test was applied as a preceding step to build a faster and more accurate data-driven water quality prediction model. First, a physical-based model (HSPF, EFDC) was operated to produce daily water quality reflecting the complexity of the watershed according to various hydrological conditions for Paldang Dam. The Gamma Test was performed on the water quality at the water quality prediction site (Paldangdam2) and major rivers flowing into the Paldang Dam, and the method of selecting the optimal input data combination was presented through the analysis results (Gamma, Gradient, Standar Error, V-Ratio). As a result of the study, the selection criteria for a more efficient combination of input data that can save time by omitting trial and error when building a data-driven model are presented.

• Journal of Environmental Science International
• /
• v.9 no.6
• /
• pp.455-462
• /
• 2000

This study aims at the development of the model for a forecasting of water quality in river basins using artificial neural network technique. Water quality by Artificial Neural Network Model forecasted and compared with observed values at the Sangju q and Dalsung stations in Nakdong river basin. For it, a multi-layer neural network was constructed to forecast river water quality. The neural network learns continuous-valued input and output data. Input data was selected as BOD, CO discharge and precipitation. As a result, it showed that method III of three methods was suitable more han other methods by statistical test(ME, MSE, Bias and VER). Therefore, it showed that Artificial Neural Network Model was suitable for forecasting river water quality.

• Journal of Korean Society on Water Environment
• /
• v.25 no.6
• /
• pp.902-909
• /
• 2009

With various reservoirs, dams and reduction of water velocity in downstream, rivers in Korea often have characteristics of accumulation of pollutants. Therefore, the main focus of water quality modeling in Korea needs to be shifted from DO to algae and organic matter. Moreover the structures of water quality models should be modified to have capability of simulating BOD which is a key factor of total water pollution load management in Korea as laboratory experiment BOD (Bottle $BOD_5$). In the SWAT model which is one of the widely used water quality models in Korea, the channel water quality module is using main algorithm of the QUAL2E model which has limitations in simulating algae, organic matter and Bottle BOD5 etc. To overcome this hindrance, in this study, the improved channel water quality module of the SWAT model (Q-SWAT) was proposed by linking the algorithms of the QUAL-NIER model which was developed based on the QUAL2E model to the SWAT model. The algorithms estimating the increase of internal organic matter by fractionization algal metabolism process and calculating Bottle $BOD_5$ were added and the results of proposed model were compared to those of the original SWAT model. The results of comparison test are showing that more accurate BOD values can be obtained with the Q-SWAT model and it is anticipated that the Q-SWAT model can be used as an effective tool of decision support through the water quality simulation and long term pollution source analysis.

• Journal of Korea Water Resources Association
• /
• v.44 no.6
• /
• pp.439-447
• /
• 2011

This study aims to test the feasibility of combined use of EFDC (Environmental Fluid Dynamics Code) hydrodynamic model and WASP7.3 (Water Quality Analysis Program) model to improve accuracy of water quality predictions of the Yongdam Lake, Korea. The orthogonal curvilinear grid system was used for EFDC model to represent riverine shape of the study area. Relationship between volume, surface and elevation results were checked to verify if the grid system represents morphology of the lake properly. Monthly average boundary water quality conditions were estimated using the monthly monitored water quality data from Korean Ministry of Environment DB system. Monthly tributary flow rates were back-routed using dam discharge data and allocated in proportion to each basin area as direct measurements were not available. The optimum number of grid system was determined to be 372 horizontal cells and 10 vertical layers of the site for 1 year simulation of hydrodynamics and water quality out of iterative trials. Monthly observed BOD, TN, TP and Chl-a concentrations inside the lake were used for calibration of WASP7.3 model. This study shows that EFDC and WASP can be used in series successfully to improve accuracy in water quality modeling. However, it was observed that the amount of data to develop inflow water quality and flow rate boundary conditions and water quality data inside lake for calibration were not enough for accurate modeling. It is suggested that object-oriented data collection systems would be necessary to ensure accuracy of EFDC-WASP model application and thus for efficient lake water quality management strategy development.

• Water for future
• /
• v.29 no.2
• /
• pp.179-190
• /
• 1996

The characteristics of water quality in the downstream of the Han River were analyzed by statistical techniques. Basic characteristics, areal and temporal variations, and correlations of water quality data were investigated. Monthly water quality data have been investigated systematically by exploring data analysis, including time series plot, summary statistics, distribution test, time dependence test, seasonality test and flow relatedness test. Results show that water quality data in this river have seasonality. And applicability of stochastic models such as Thomas-Fiering model and ARMA(1,1) model was identified. From the examination of water quality data related to discharge, it was found that DO and SS are sensitive to water temperature rather than discharge, while BOD and COD are sensitive to discharge at dry seasons. Seasonal periodicities were identified in all water quality variables from the cross correlation analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.282-285
• /
• 1996

In the water purification plant, the raw water is promptly purified by injecting chemicals. The amount of chemicals is directly related to water quality such as turbidity, temperature, pH and alkalinity. At present, however, the process of chemical reaction to the turbidity has not been clarified as yet. Since the process of coagulant dosage has no feedback signal, the amount of chemical can not be calculated from water quality data which were sensed from the plant. Accordingly, it has to be judged and determined by Jar-Test data which were made by skilled operators. In this paper, it is concerned to model and control the coagulant dosing process using jar-test results in order to predict optimum dosage of coagulant, PAC(Polymerized Aluminium Chloride). The considering relations to the reaction of coagulation and flocculation, the five independent variables(turbidity, temperature, pH, Alkalinity of the raw water, PAC feed rate) are selected out and they are put into calculation to develope a neural network model and a fuzzy model for coagulant dosing process in water purification system. These model are utilized to predict optimum coagulant dosage which can minimize the water turbidity in flocculator. The efficacy of the proposed control schemes was examined by the field test.