• Journal of Korea Water Resources Association
• /
• v.53 no.3
• /
• pp.215-223
• /
• 2020

The objective of this study is to develop a prediction model of specific degradation using data mining classification especially for the rivers in South Korea river. A number of critical predictors such as erosion and sediment transport were extracted for the prediction model considering watershed morphometric characteristics, rainfall, land cover, land use, and bed material. The suggested model includes the elevations at the mid relative area of the hypsometric curve of watershed morphomeric characteristics, the urbanization ratio, and the wetland and water ratio of land cover factors as the condition factors. The proposed model describes well the measured specific degradation of the rivers in South Korea. In addition, the development model was compared with the existing models, since the existing models based on different conditions and purposes show low predictability, they have a limit about the application of Korean River. Therefore, this study is focusing on improving the applicability of the existing model

• Journal of the Korea Convergence Society
• /
• v.6 no.2
• /
• pp.37-42
• /
• 2015

Nowadays, as the environmental pollution becomes severe on the earth, the water resource which can be used practically is dried up because of the natural disaster. And so, this is the time to be necessary to have the method for saving the water resource. This study investigates the distributions of velocity and temperature by the flow analysis inside the faucet models for bathroom. Model 3 has the most uniform distribution of temperature after mixing among all models. As model 3 has the smallest velocity distribution and the biggest space to mix by comparing the other models, it is seen to have the most influence on the discharged velocity of water and save the water. As the space of various configuration inside faucet model for bathroom is made by using the result of this study, it is thought to utilize at the development of this model in which more mixing becomes and the water can be saved. And it is possible to be grafted onto the convergence technique at design and show the esthetic sense.

• Structural Engineering and Mechanics
• /
• v.67 no.2
• /
• pp.105-113
• /
• 2018

To improve the prediction accuracy of the strong-unloading rock slope performance and obtain the range of variation in the slope displacement, a new displacement time-series prediction model is proposed, called the fuzzy information granulation (FIG)-genetic algorithm (GA)-back propagation neural network (BPNN) model. Initially, a displacement time series is selected as the training samples of the prediction model on the basis of an analysis of the causes of the change in the slope behavior. Then, FIG is executed to partition the series and obtain the characteristic parameters of every partition. Furthermore, the later characteristic parameters are predicted by inputting the earlier characteristic parameters into the GA-BPNN model, where a GA is used to optimize the initial weights and thresholds of the BPNN; in the process, the numbers of input layer nodes, hidden layer nodes, and output layer nodes are determined by a trial method. Finally, the prediction model is evaluated by comparing the measured and predicted values. The model is applied to predict the displacement time series of a strong-unloading rock slope in a hydropower station. The engineering case shows that the FIG-GA-BPNN model can obtain more accurate predicted results and has high engineering application value.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.617-628
• /
• 2021

Drought is a major natural disaster that causes serious social and economic losses. Local drought forecasts can provide important information for drought preparedness. In this study, we propose a new machine learning model that predicts drought by using historical drought indices and meteorological data from 10 sites from 1981 to 2020 in the southeastern part of the Korean Peninsula, Busan-Ulsan-Gyeongnam. Using Bayesian optimization techniques, a hyper-parameter-tuned Random Forest, XGBoost, and Light GBM model were constructed to predict the evaporative demand drought index on a 6-month time scale after 1-month. The model performance was compared by constructing a single site model and a regional model, respectively. In addition, the possibility of improving the model performance was examined by constructing a fine-tuned model using data from a individual site based on the regional model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• Journal of Korean Society on Water Environment
• /
• v.38 no.6
• /
• pp.306-315
• /
• 2022

In this study, long-term measurement data were applied to the LOADEST model and used as an analysis tool to identify and interpret trends in pollution load. The LOADEST model is a regression equation-based pollution load estimation program developed by the United States Geological Survey (USGS) to estimate the change in the pollution load of rivers according to flow rate and time and provides 11 regression equations for pollution load evaluation. As a result of simulating the Gwangjuchen2, Pungyeongjeongchen, and Pyeongdongchen in the Yeongbon B unit basin in the middle and upper reaches of the Yeongsan River with the LOADEST model using water quality and flow measurement data, lower values were observed for the Gwangjuchen2 and Pyeongdongchen, whereas the Pungyeongjeongchen had higher values. This was judged to be due to the characteristics of the LOADEST model related to data continuity. According to the parameters estimated by the LOADEST model, pollutant trends were affected by increases in the flow. In addition, variability increased with time, and BOD and T-P were affected by the season. Thus, the LOADEST model can contribute to water quality management as an analytical tool for long-term data monitoring.

• Journal of Korean Society of Water and Wastewater
• /
• v.26 no.6
• /
• pp.861-869
• /
• 2012

The chlorine's residual concentration prevents the regrowth of microorganism in water transport along the pipeline system. Precise prediction of chlorine concentration is important in determining disinfectant injection for the water distribution system. In this study, a pilot scale water distribution system was designed and fabricated to measure the temporal variation of chlorine concentration for three flow conditions (V = 0.88, 1.33, 1.95 m/s). Various kinetic models were applied to identify the relationship between hydraulic condition and chlorine decay. Genetic Algorithm (GA) was integrated into five kinetic models and time series of chlorine were used to calibrate parameters. Model fitness was compared by Root Mean Square Error (RMSE) between measurement and prediction. Limited first order model and Parallel first order showed good fitness for prediction of chlorine concentration.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2006.05a
• /
• pp.51-56
• /
• 2006

Biases embedded in numerical weather precipitation forecasts by the RDAPS model was determined, quantified and corrected. The ultimate objective is to eventually enhance the reliability of reservoir operation by Korean Water Resources Corporation (KOWACO), which is based on precipitation-driven forecasts of stream flow. Statistical post-processing, so called MOS (Model Output Statistics) was applied to RDAPS to improve their performance. The Artificial Neural Nwetwork (ANN) model was applied for 4 cases of 'Probability of Precipitation (PoP) for wet and dry season' and 'Quantitative Precipitation Forecasts (QPF) for wet and dry season'. The reduction on the large systematic bias was especially remarkable. The performance of both networks may be improved by retraining, probably every month. In addition, it is expected that performance of the networks will improve once atmospheric profile data are incorporated in the analysis. The key to the optimal performance of ANN is to have a large data set relevant to the predictand variable. The more complex the process to be modeled by the ANN, the larger the data set needs to be.

• Journal of Korean Society of Rural Planning
• /
• v.11 no.4 s.29
• /
• pp.59-65
• /
• 2005

Proper management of small rural watershed is important since it does affect water quality improvement of larger scale watershed. Therefore, effective small watershed management guideline including participatory program of local people is required to achieve water environment improvement. Feasibility of water quality goal, short and long-term watershed management plan and funding sources were investigated by field monitoring of Hampyungchun watershed which has characteristics of rural stream, and literature review. The relevant parties and their roles fer watershed management were identified and suggested. A hybrid model, that is mixture of government driven model and NGO model, is recommended for watershed management organization in this study.

• Spatial Information Research
• /
• v.4 no.2
• /
• pp.147-157
• /
• 1996

A rural water quality management information system(RWQMIS) by integrating Geo¬graphic Information System(GIS) with the existing models (pollutants transport and river water quality) is described. A simple pollutant load model to calculate delivered pollutants to stream, Tank model to generate daily runoff and QUAL2E model to predict river water quality, were incorporated into GIS. The system was applied to $80km^2$ watershed in Icheon Gun and Yongin Gun, Kyonggi Do. The spatial distributions of produced pollutant load, discharged pollutant load, delivered ratio to the stream, and the river water quality status for given sites were successfully generated.