• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1133-1140
• /
• 2008

The goal of this paper is to analysis of the trend for stream quality in Gumi industrial complex with Winters' exponential smoothing method. It used the five different monthly time series data such as BOD, COD, TN, TP and EC from January 1998 to December 2006. The data of BOD, COD, TN, TP and EC are analyzed by time series method and forecasted the trends until December 2007. The stream qualities change for the better about BOD, COD, TN and TP, but the stream qualities resulted by EC is still serious.

• 정보과학회 논문지
• /
• 제44권6호
• /
• pp.607-612
• /
• 2017

도시에서 홍수 피해를 방지하기 위한 침수를 예측하기 위해 본 논문에서는 딥러닝(Deep Learning) 기법을 적용한다. 딥러닝 기법 중 시계열 데이터 분석에 적합한 Recurrent Neural Networks (RNNs)을 활용하여 강의 수위 관측 데이터를 학습하고 침수 가능성을 예측하였다. 예측 정확도 검증을 위해 사용한 데이터는 미국의 트리니티강의 데이터로, 학습을 위해 2013 년부터 2015 년까지 데이터를 사용하였고 평가 데이터로는 2016 년 데이터를 사용하였다. 입력은 16개의 레코드로 구성된 15분단위의 시계열 데이터를 사용하였고, 출력으로는 30분과 60분 후의 강의 수위 예측 정보이다. 실험에 사용한 딥러닝 모델들은 표준 RNN, RNN-BPTT(Back Propagation Through Time), LSTM(Long Short-Term Memory)을 사용했는데, 그 중 LSTM의 NE(Nash Efficiency)가 0.98을 넘는 정확도로 기존 연구에 비해 매우 높은 성능 향상을 보였고, 표준 RNN과 RNN-BPTT에 비해서도 좋은 성능을 보였다.

• 상하수도학회지
• /
• 제19권5호
• /
• 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.

• 한국수자원학회논문집
• /
• 제30권4호
• /
• pp.411-420
• /
• 1997

낙동강 유역에서 수질예보시스템의 개발을 위해서 신뢰도해석 기법에 기초한 QUAL2E-AFOSM모형을 개발하였다. 왜관∼물금 구간에 대해 수리학적 부등류 해석을 실시하였고, 최적의 반응계수 추정을 위해 BFGS 기법을 사용하여 최적화 해석을 실시하였으며, 이를 기초로 하여 모형의 보정과 검증을 실시하였다. 추계학적 해석을 위하여 AFSOM 기법을 적용한 신뢰도 해석을 수행하였다. 상류단과 주요 지류에서의 수질, 유량과 반응계수에 대한 변동성을 고려하였다. 수질 측정자료를 기초로 하여 낙동강의 수개 지점에 대한 기준 수질을 초과할 확률을 AFOSM 기법을 이용하여 산정하였다. 본 QUAL2E-AFOSM 모형에 의한 해석결과는 Monte-Carlo 기법의 결과와 일치하는 것으로 나타났다.

• 한국해양공학회지
• /
• 제22권2호
• /
• pp.34-41
• /
• 2008

As a basic study for developing a forecasting/estimating system that predicts water quality changes when Deep Sea Water (DSW) drains to the ocean after using it, this study was carried out as follows: 1) numerical simulation of the present state at DSW developing region in the East sea using SWEM, 2) numerical prediction of water quality changes by effluent DSW, 3) analysis of influence degree 'With defined DEI (DSW effect index) at F station. On the whole, when DSW drained to the ocean, Chl-a, COD and water-temperature were decreased and DIN, DIP and DO were increased by effluent DSW, and Salinity was steady. According to analysis of influence degree, the influence degree of DIN was the highest and it was high in order of Chl-a, COD, Water-temperature, DO, DIP and Salinity. The influence degree classified by DSW effluent position was predicted that suiface outflow was lower than bottom outflow. Ad When DSW discharge increased 10 times, the influence degree increased about $5{\sim}14$ times.

• 한국해양환경ㆍ에너지학회지
• /
• 제1권2호
• /
• pp.96-108
• /
• 1998

대표적인 부영양화 해역인 일본의 뢰호내해를 대상으로 하여 해수ㆍ저질문의 욕존 산소와 영양염의 수수과정을 표현할 수ㆍ저질예측모델을 개발하여, 해역의 유입부하량과 수질의 응답특성, 부하량삭감의 영향해석 및 유입부하량과 수산자원의 관계 해석을 통하여 부영양화 해역의 수질관리방안에 대하여 연구하였다. 부하에 대응한 수질의 장기예측결과, 부하량과 수질의 응답특성이 해역에 따라 다르게 나타난다. 적상부하량의 간역추산방법으로서 인접해역의 부하영향 및 기여율을 포함한 부하삭감후의 수질예측에 대한 개산식을 제안하였다. 부하량 삭감효과의 수직계산결과 인(P) 뿐만 아니라 질소(N)의 부하삭감의 영향이 크게 기여함을 보였다. 유입부하량과 수산자원의 관계를 수질을 매개로 검토한 바, 뢰호내해와 같은 부영양화 해역에서는 유입부하량의 증가는 1차생산량의 증가에 반영되지만 2차생산 이후의 전송효율에도 한도가 있는 것으로 나타났다.

• 한국물환경학회지
• /
• 제27권6호
• /
• pp.830-840
• /
• 2011

Climate change has been settled as pending issues to consider water resources and environment all over the world, however, scientific and quantitative assessment methods of climate change have never been standardized. When South Korea headed toward water deficiency nation, the study is not only required analysis of atmospheric or hydrologic factors, but also demanded analysis of correlation with water quality environment factors to gain management policies about climate change. Therefore, this study explored appropriate monthly rainfall elasticity in chosen 41 unit watersheds in Nak-dong river which is the biggest river in Korea and applied monitored discharge data in 2004 to 2009 with monthly rainfall using Thiessen method. Each unit watershed drew elasticity between water temperature and water quality factors such as BOD, COD, SS, T-N, and T-P. Moreover, this study performed non-linear correlation analysis with monitored discharge data. Based on results of analysis, this is first steps of climate change analysis using long-term monitoring to develop basic data by Nak-dong river Environmental Research Center (Ministry of Environment) and to draw quantitative results for reliable forecasting. Secondary, the results considered characteristic of air temperature and rainfall in each unit watershed so that the study has significance its various statistical applications. Finally, this study stands for developing comparable data through "The 4 major river restoration" project by Korea government before and after which cause water quality and water environment changes.

• 한국물환경학회지
• /
• 제30권6호
• /
• pp.673-682
• /
• 2014

A watershed model was constructed using Hydrological Simulation Program Fortran to predict the water temperature at major tributaries of Nakdong River basin, Korea. Water temperature is one of the most fundamental indices used to determine the nature of an aquatic environment. Most processes of an aquatic environment such as saturation level of dissolved oxygen, the decay rate of organic matter, the growth rate of phytoplankton and zooplankton are affected by temperature. The heat flux to major reservoirs and tributaries was analyzed to simulate water temperature accurately using HSPF model. The annual mean heat flux of solar radiation was estimated to $150{\sim}165W/m^2$, longwave radiation to $-48{\sim}-113W/m^2$, evaporative heat loss to $-39{\sim}-115W/m^2$, sensible heat flux to $-13{\sim}-22W/m^2$, precipitation heat flux to $2{\sim}4W/m^2$, bed heat flux to $-24{\sim}22W/m^2$ respectively. The model was calibrated at major reservoir and tributaries for a three-year period (2008 to 2010). The deviation values (Dv) of water temperature ranged from -6.0 to 3.7%, Nash-Sutcliffe efficiency(NSE) of 0.88 to 0.95, root mean square error(RMSE) of $1.7{\sim}2.8^{\circ}C$. The operational water temperature forecasting results presented in this study were in good agreement with measured data and had a similar accuracy with model calibration results.

• 한국물환경학회지
• /
• 제30권1호
• /
• pp.44-59
• /
• 2014

Despite the implementation of TMDL, the water quality in lower watershed of Nam river dam has worsened continuously since 2005. Multifarious pollution sources such as cities and industrial districts are scattered around it. Nam river downstream bed slope is very gentle towards the downstream water flow of slows it down even more, depending on the water quality deterioration is accelerated eutrophication occurs. In this study, the mainstream in lower watershed of Nam river dam region to target aquatic organic matter by phytoplankton growth contribution was evaluated by statistical analysis. and statistical evaluation of water quality and the accuracy of forecasting, model calibration and verification procedures by completing QUALKO2 it's eutrophic phenomena that occur frequently in the dam outflow through scenarios predict an increase in water quality management plans to present the best should.

• 한국환경과학회지
• /
• 제27권6호
• /
• pp.371-381
• /
• 2018

Multifunctional weirs constructed through the Four Major Rivers Restoration Project are operated as management water levels. The purpose of this study was to evaluate the effect of water level in the main stem on the tributary water level according to multifunctional weir operation, because the operation of multifunctional weirs for water level management influences the drainage of tributaries. In this study, water level pressure gauges were installed and spatial and temporal water quality was observed. The LOcally Weighted Scatterplot Smoothing (LOWESS) technique was applied to the Nakdong River and the Baekcheon Junction, both upstream of the Gangjeong-Goryeong weir, in order to analyze water quality trends. When considering the overall analysis and observations, it was found that the water quality forecasting point located at the Baekcheon estuary point should be transferred to the Dosung Bridge, which is located upstream of the Sunwon Bridge.