• Journal of Korea Water Resources Association
• /
• v.56 no.11
• /
• pp.801-813
• /
• 2023

Recently, as studies about Artificial Neural Network (ANN) are actively progressing, studies for predicting water quality of rivers using ANN are being conducted. However, it is difficult to analyze the operation process inside ANN, because ANN is form of Black-box. Although eXplainable Artificial Intelligence (XAI) is used to analyze the computational process of ANN, research using XAI technology in the field of water resources is insufficient. This study analyzed Multi Layer Perceptron (MLP) to predict Water Temperature (WT), Dissolved Oxygen (DO), hydrogen ion concentration (pH) and Chlorophyll-a (Chl-a) at the Dasan water quality observatory in the Nakdong river using Layer-wise Relevance Propagation (LRP) among XAI technologies. The MLP that learned water quality was analyzed using LRP to select the optimal input data to predict water quality, and the prediction results of the MLP learned using the optimal input data were analyzed. As a result of selecting the optimal input data using LRP, the prediction accuracy of MLP, which learned the input data except daily precipitation in the surrounding area, was the highest. Looking at the analysis of MLP's DO prediction results, it was analyzed that the pH and DO a had large influence at the highest point, and the effect of WT was large at the lowest point.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.5
• /
• pp.572-581
• /
• 2005

This research is conducted to develop predictable method of real scale nanofiltration treatability with small scale nanofiltration experiments. As a result of comparing calculated values with measured values, they are in a good agreement for the concentrations in filtered water and concentrated water. The results of that are not affected by change of system recovery from 20% to 95%. The proposed method is produced using constant recovery of elements, that is, no considering the pressure change. we can predict filtrated flux and contaminant concentrations with the method. The method has the following steps. (1) Calculate recovery of each element with water quality level after fixing recovery elements, (2) Predict system recovery with recovery of elements in 1, 2, 3, and 4 banks, (3) Run small scale nanofiltration experiments in predicted water quality and (4) Simulate large scale nanofiltration system for forecasting actual water quality. As the cost for nanofiltration pretest will reduced if we use the proposed method, it will be a promising method for introducing nanofiltration to supply safe drinking water.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.47 no.4
• /
• pp.65-74
• /
• 2005

AnnAGNPS model was applied to a catchment mainly occupied with bushland for modeling non-point source pollution. Since the single event model cannot handle events longer than 24 hours duration, the event-based calibration was carried out using the continuous mode. As event flows affect sediment and nutrient generation and transport, the calibration of the model was performed in three steps: Hydrologic, Sediment and Nutrient calibrations. The results from hydrologic calibration for the catchment indicate a good prediction of the model with average ARE(Absolute Relative Error) of $24.6\%$ fur the runoff volume and $12\%$ for the peak flow. For the sediment calibration, the average ARE was $198.8\%$ indicating acceptable model performance for the sediment prediction. The predicted TN(Total Nitrogen) and TP(Total Phosphorus) were also found to be acceptable as the average ARE for TN and TP were $175.5\%\;and\;126.5\%$, respectively. The AnnAGNPS model was therefore approved to be appropriate to model non-point source pollution in bushland catchments. In general, the model was likely to result in underestimation for the larger events and overestimation fur the smaller events for the water quality predictions. It was also observed that the large errors in the hydrologic prediction also produced high errors in sediment and nutrient prediction. This was probably due to error propagation in which the error in the hydrologic prediction influenced the generation of error in the water quality prediction. Accurate hydrologic calibration should be hence obtained for a reliable water quality prediction.

• Water for future
• /
• v.28 no.2
• /
• pp.103-114
• /
• 1995

A stochastic model "STO-RIV" for the prediction of water quality variation in a river system has been developed. Extended Streeter-Phelps equation and Monte Carlo simulation are used in the model. The model is applied to the reach of Waegwan to Mulkeum in the Nakdong River to compute the probability distribution of BOD and DO concentration at Mulkeum site. As the strategies to attain the goal of the water quality, some alternatives considering the treatment effect of the Keumho river are discussed using the stochastic model. Application of stochastic analysis to water quality management is strongly recommended in this country.s country.

• Korean Journal of Hydrosciences
• /
• v.7
• /
• pp.51-60
• /
• 1996

• Journal of The Korean Society of Agricultural Engineers
• /
• v.47 no.5
• /
• pp.75-86
• /
• 2005

Recently since urbanization has brought about a dried stream and a worse water quality, Anyang city discharged the third treated sewage into the upper stream of Anyancheon and Hakuicheon. As the result, Hakuicheon had the water level and velocity enough for a living thing in the water to live in but water quality was worse than it had been. Therefore in case of meeting the water level and velocity of the second grade water-quality which living things in the water can live in, the discharge and water quality to secure in-stream flow must be at least 0.350 $m^3/s$ and $BOD_5\;3.2 mg/{\iota}$ respectively. In Anyancheon the water level was increased a little higher than it had been but the velocity was almost unchanged in comparison with it before. On the other hand the water quality was a little better than it had been. Therefore in case of meeting the water level and velocity of the third grade water-quality that people can do water-friendly activity, the discharge and water quality to secure in-stream flow must be at least 0.688 $m^3/s$ and $BOD_5\;4.8 mg/{\iota}$ respectively. The water-quality prediction on the suggested eight scenarios was simulated in all satisfying the third grade water-quality.

• Journal of Environmental Science International
• /
• v.20 no.3
• /
• pp.373-384
• /
• 2011

This study aims at the examination of the relative characteristics of discharge and water quality in river basins using statistical methods. For it, water quality and discharge data was collected in observed stations of Nakdong river and carried out correlation analysis, regression analysis, factor analysis and cluster analysis. And it was investigated the applicability of water quality prediction using Nearest-neighbor method. As a result, it grasped a trenditional characteristics and mutual relations between discharge an water quality data. Therefore, this results were suggested the comprehensive data and methods for a management of water quality, effective operation and policy development in Nakdong river basin.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.42 no.5
• /
• pp.94-102
• /
• 2000

Investigated was the effectiveness of a constructed wetland system on water quality in Hwa-Ong estruarin reservoir, located in Hwasung-Gun, Kyunggi-Do. Procedures for estimation of pollutant loading from watershed and required area for natural systems, and simulation of corresponding reservoir water quality were reviewed. Generally, simulated reservoir water quality was within the reasonable range, and about 15% of total polder farmland was required to meet the agricultural water quality standards. The model was applied based on the current loading condition without additional treatment systems. Wetland system is an ecologically sound treatment system. Therefore, natural systems can be an alternative measure for water quality improvement in polder projects. The area for natural systems was estimated using literature value which might be acceptable at the planning stage. However, pilot system and its experimental data are requisite for large scale field application. WASP5 was proved to be a useful and versatile model, and its application to estuarine reservoir water quality simulation was thought to be appropriate.

• Proceedings of the Korean Society of Agricultural Engineers Conference
• /
• 2000.10a
• /
• pp.578-583
• /
• 2000

In order to operate water quality model for a lake or a channel, user should examine the all kinds of parameters and should know how them react to the model for calculating the pollution which are happened from the watershed or are reacted in the water. The aim of this study is analyzing the characteristics of parameters which are used by a water quality model (CE-QUAL-W2), so that we are trying to find out how them to react to the model for calculating the many kinds of pollution.

• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.461-470
• /
• 2024

This study aimed to predict total phosphorus (T-P) to address early eutrophication caused by nutrient influx from various human activities. Traditional T-P monitoring systems are labor-intensive and time-consuming, leading to a global trend of using direct reading sensors. Therefore, this study utilized water quality parameters obtained from direct reading sensors in a two-stage T-P prediction process. The importance of turbidity (Tur) in T-P prediction was examined, and an analysis was conducted to determine if T-P prediction is possible using only direct reading sensor parameters by adding automatic water quality analyzer parameters. The study found that T-P concentrations were higher in the mid-lower reaches of the Nakdong River basin compared to the upper reaches. Pearson correlation analysis identified water quality parameters highly correlated with T-P at each site, which were then used in multiple linear regression analysis to predict T-P. The analysis was conducted with and without the inclusion of Tur, and the performance of models incorporating automatic water quality analyzer parameters was compared with those using only direct reading sensor parameters. The results confirmed the significance of Tur in T-P prediction, suggesting that it can be used as a foundational element in the development of measures to prevent eutrophication.