• Journal of Environmental Impact Assessment
• /
• v.30 no.2
• /
• pp.75-88
• /
• 2021

Six locations in the automated monitoring network at the Geum River Basin were selected forthis study. The water quality characteristics at two of the locations in the water quality monitoring network that were identical, or nearby, were examined, and their correlations were evaluated through statistical analysis. The results of the water quality analysis were converted to the water quality index and expressed in grades for comparison. For the data necessary for the study, public data from four years, from 2016-2019 were used and the evaluation parameters were water temperature, pH, EC, DO, TOC, TN, and TP. Results of the analysis showed that the water quality concentrations measured in the automated monitoring network and the water quality monitoring network differed in some measured values, but they tended to register variation in a specified ratio in most of the locations in the network. The analysis of the correlations of the parameters between the two monitoring networks found that water temperature, EC, and DO showed high correlations between the two monitoring networks. The TOC, TN, and TP showed high correlations, with a 0.7 or higher (correlation coefficient r), with the exception of some of the monitoring networks, although their correlations were lower than those of the basic parameters. The water quality index analysis showed that the water quality index values of the automated monitoring network and the water quality monitoring network were similar. The water quality index decreased and the pollution degree increased in the downstream direction, in both networks.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1078-1083
• /
• 2004

We proposed a method to compensate incomplete observations and made a study of environmental problem, water quality of Tama-River in Tokyo.The method is based on interpolations of the multi-layer neural networks. We call the approach as CQSAR method .which can compensate the defect data.The water quality data include defects which will give wrong effect to other normal data. The CQSAR method suppresses the wrong effect .Thus, we believe that the proposed CQSAR method has practical usability for environment examinations.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.1073-1080
• /
• 1996

The impact of the input and output probability distributions on the performance of neural networks to forecast two year peak stream flow (cubic meters per second) is examined for two major river basins of the US. The neural network input consisted of drainage area(square kilometers ) and elevation (meters). When data are normally distributed , the neural networks predict much better than when the data are non-normal and have larger tails in their distributions.

• Journal of KIISE
• /
• v.44 no.6
• /
• pp.607-612
• /
• 2017

This paper presents an attempt to apply Deep Learning technology to solve the problem of forecasting floods in urban areas. We employ Recurrent Neural Networks (RNNs), which are suitable for analyzing time series data, to learn observed data of river water and to predict the water level. To test the model, we use water observation data of a station in the Trinity river, Texas, the U.S., with data from 2013 to 2015 for training and data in 2016 for testing. Input of the neural networks is a 16-record-length sequence of 15-minute-interval time-series data, and output is the predicted value of the water level at the next 30 minutes and 60 minutes. In the experiment, we compare three Deep Learning models including standard RNN, RNN trained with Back Propagation Through Time (RNN-BPTT), and Long Short-Term Memory (LSTM). The prediction quality of LSTM can obtain Nash Efficiency exceeding 0.98, while the standard RNN and RNN-BPTT also provide very high accuracy.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.5 no.4 s.19
• /
• pp.17-27
• /
• 2005

In this paper the watershed is divided by stream order law of Horton to estimate the runoff with stream order. We use the contour data to extract spatially distributed topographical information like stream channels and networks of sub-basins. A contour model is developed, validated, and adopted to estimate the effective stream order number for the runoff. The results show that the peak discharge which is divided into first river order was close to observed one. The contour model will provide effective informations to plan river works classified by sub-basins for river restoration.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.37-37
• /
• 2023

There is currently a high-accuracy modern forecasting method that uses machine learning algorithms or artificial neural network models to forecast river water levels or flowrate. As a result, this study aims to develop a mathematical model based on artificial neural networks to effectively forecast river water levels upstream of Tranh Culvert in North Vietnam's Bac Hung Hai irrigation system. The mathematical model was thoroughly studied and evaluated by using hydrological data from six gauge stations over a period of twenty-two years between 2000 and 2022. Furthermore, the results of the developed model were also compared to those of the long-short-term memory neural networks model. This study performs four predictions, with a forecast time ranging from 6 to 24 hours and a time step of 6 hours. To validate and test the model's performance, the Nash-Sutcliffe efficiency coefficient (NSE), mean absolute error, and root mean squared error were calculated. During the testing phase, the NSE of the model varies from 0.981 to 0.879, corresponding to forecast cases from one to four time steps ahead. The forecast results from the model are very reasonable, indicating that the model performed excellently. Therefore, the proposed model can be used to forecast water levels in North Vietnam's irrigation system or rivers impacted by tides.

• Journal of Korean Society of Water and Wastewater
• /
• v.24 no.5
• /
• pp.549-560
• /
• 2010

Recently, heavy rainfalls due to the climate change in Korea have caused inundation problems in urban sewer networks. In july 2006, a flooding accident at Misari motorboat racing stadium near the Han river occurred due to the effect of record-breaking outflow discharge from Paldang-dam. The purpose of this study was to simulate and analyze the flooding accident at Misari stadium by MOUSE model. The results of simulation analysis indicated that the total flood volume was $1,313,450m^3$. The effect of back water was 85.9% of the total volume which was caused by the manhole accident, and the effect of accumulated runoff was 14.1% of total volume which was caused by non-return valve shutdown. The simulation results of this MOUSE modeling that was linked to the boundary condition of the dynamic flows in the river by DWOPER model showed the potential of successful inundation analysis for sewer networks.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.161-161
• /
• 2016

본 연구는 Matlab GUI 언어를 기반으로 제작된 수질관리모형(WAQUMURIN; Water QUality Management program for Urban RIver Networks)의 개발 및 적용, 검증을 통한 수질분석을 목적으로 둔다. 서울한강수계를 대상지역으로 한강 상류의 팔당댐부터 한강 하류에 위치한 가양대교까지의 오염원 이동에 따른 BOD, T-P 농도를 분석하였다. 한강의 본류를 따라 분류되는 지천들과 한강서울수계 관할 하 4곳의 물재생센터(탄천, 중랑, 서남, 난지)의 배출부하량, 유량, 반응속도상수는 본 모형의 main factor로 설정되었으며 격자화된 데이터의 입출력이 가능토록 하였다. 6곳의 수질측정망(암사, 구의, 잠실, 똑도, 보광, 노량진, 영등포, 가양) 지점을 기준으로 실측치와 모형의 모의결과를 비교함으로써 정확도를 검토하였다. 이는 기존의 사용법이 어려운 수질모형의 한계를 깬 간단한 입출력 방식으로 비전문가들 또한 사용이 가능하며 예측 모형의 단순화라는 점의 연구 목적에 있다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.363-363
• /
• 2023

Artificial Neural Networks (ANN) is a powerful tool for addressing various practical problems and it has been extensively applied in areas of water resources. In this study, Artificial Neural Networks (ANNs) were developed for flood forecasting at specific locations on the Han River. The Partial Mutual Information (PMI) technique was used to select input variables for ANNs that are neither over-specified nor under-specified while adequately describing the underlying input-output relationships. Historical observations including discharges at the Paldang Dam, flows from tributaries, water levels at the Paldang Bridge, Banpo Bridge, Hangang Bridge, and Junryu gauge station, and time derivatives of the observed water levels were considered as input candidates. Lagged variables from current time t to the previous five hours were assumed to be sufficient in this study. A three-layer neural network with one hidden layer was used and the neural network was optimized by selecting the optimal number of hidden neurons given the selected inputs. Given an ANN architecture, the weights and biases of the network were determined in the model training. The use of PMI-based input variable selection and optimized ANNs for different sites were proven to successfully predict water levels during flood periods.

• Structural Engineering and Mechanics
• /
• v.23 no.1
• /
• pp.75-95
• /
• 2006

Two-step identification approaches for effective bridge health monitoring are proposed to alleviate the issues associated with many unknown parameters faced in real structures and to improve the accuracy in the estimate results. It is suitable for on-line monitoring scheme, since the damage assessment is not always needed to be carried out whereas the alarming for damages is to be continuously monitored. In the first step for screening potentially damaged members, a damage indicator method based on modal strain energy, probabilistic neural networks and the conventional neural networks using grouping technique are utilized and then the conventional neural networks technique is utilized for damage assessment on the screened members in the second step. The effectiveness of the proposed methods is investigated through a field test on the northern-most span of the old Hannam Grand Bridge over the Han River in Seoul, Korea.