• Environmental Engineering Research
• /
• v.15 no.3
• /
• pp.135-140
• /
• 2010

With the various urban characteristics of each city, the existing water demand prediction, which uses average liter per capita day, cannot be used to achieve an accurate prediction as it fails to consider several variables. Thus, this study considered social and industrial factors of 164 local cities, in addition to population and other directly influential factors, and used main substance and cluster analyses to develop a more efficient water demand prediction model that considers unique localities of each city. After clustering, a multiple regression model was developed that proved that the $R^2$ value of the inclusive multiple regression model was 0.59; whereas, those of Clusters A and B were 0.62 and 0.74, respectively. Thus, the multiple regression model was considered more reasonable and valid than the inclusive multiple regression model. In summary, the water demand prediction model using principal component and cluster analyses as the standards to classify localities has a better modification coefficient than that of the inclusive multiple regression model, which does not consider localities.

• Journal of Environmental Science International
• /
• v.11 no.12
• /
• pp.1275-1279
• /
• 2002

This study was performed to improve water demand estimation and analize correlation between generation of domestic sewage and domestic water use. To improve the prediction of water demand estimation, new water demand equation was developed. The results is as follows. $InQ_t = {\beta}_0+{\beta}_1InP_t+{\beta}_2InY_t+{\beta}_3InH_t+{varepsilon}_t$By using the statistical analysis of the "generation of domestic sewage" and "domestic water use", the regression equation between them is formed. The result is as follows. Generation of domestic sewage : 0.8487 $\times$ Domestic water use + 684.57 ($R^2$= 0.972)>$R^2$= 0.972)

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.4
• /
• pp.377-389
• /
• 2014

In recent years, Smart Water Grid (SWG) concept has globally emerged over the last decade and also gained significant recognition in South Korea. Especially, there has been growing interest in water demand forecast and this has led to various studies regarding energy saving and improvement of water supply reliability. In this regard, this study aims to develop a nonlinear ensemble model for hourly water demand forecasting which allow us to estimate uncertainties across different model classes. The concepts was demonstrated through application to observed from water plant (A) in the South Korea. Various statistics (e.g. the efficiency coefficient, the correlation coefficient, the root mean square error, and a maximum error rate) were evaluated to investigate model efficiency. The ensemble based model with an cross-validate prediction procedure showed better predictability for water demand forecasting at different temporal resolutions. In particular, the performance of the ensemble model on hourly water demand data showed promising results against other individual prediction schemes.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.9-17
• /
• 2016

This study identifies major features in water supply and introduces important factors in water services based on the information from data mining analysis of water quantity and water pressure measured from sensors. It also suggests more accurate methods using multiple regression analysis and neural network in predicting short term prediction of water demand in water service. A small block of a county is selected for the data collection and tests. There isa water demand on business such as public offices and hospitalstoo in this area. Real stream data from sensors in this area is collected. Among 2,728 data sets collected, 2,632 sets are used for modelling and 96 sets are used for testing. The shows that neural network is better than multiple regression analysis in their prediction performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.156-156
• /
• 2022

Explicitly spatially distributed and reliable data on industrial water demand is very much important for both policy makers and researchers in order to carry a region-specific analysis of water resources management. However, such type of data remains scarce particularly in underdeveloped and developing countries. Current research is limited in using different spatially available socio-economic, climate data and geographical data from different sources in accordance to predict industrial water demand at finer resolution. This study proposes a random forest regression (RFR) model to predict the industrial water demand at 0.50× 0.50 spatial resolution by combining various features extracted from multiple data sources. The dataset used here include National Polar-orbiting Partnership (NPP)/Visible Infrared Imaging Radiometer Suite (VIIRS) night-time light (NTL), Global Power Plant database, AQUASTAT country-wise industrial water use data, Elevation data, Gross Domestic Product (GDP), Road density, Crop land, Population, Precipitation, Temperature, and Aridity. Compared with traditional regression algorithms, RF shows the advantages of high prediction accuracy, not requiring assumptions of a prior probability distribution, and the capacity to analyses variable importance. The final RF model was fitted using the parameter settings of ntree = 300 and mtry = 2. As a result, determinate coefficients value of 0.547 is achieved. The variable importance of the independent variables e.g. night light data, elevation data, GDP and population data used in the training purpose of RF model plays the major role in predicting the industrial water demand.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.646-648
• /
• 1999

Kalman Filter model of demand for residental water and consumption pattern were tested for their ability to explain the hourly residental demand for water in metropolitan distribution system. The hourly residental demand for water is calculated from the daily residental demand and consumption pattern. The consumption pattern which has 24 time rates is characterized by data granulization in accordance with season kind, weather and holiday. The proposed approach is applied to water distribution system of metropolitan areas in Korea and its effectiveness is checked.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.9
• /
• pp.108-116
• /
• 2009

In this paper, we develop an ELM(Extreme Learning Machine) based short-tenn water demand prediction algorithm which solves overfitting problem of MLP(Multi Layer Perceptron) and has quick training time. To show effectiveness of proposed method, we analyzed time series data collected in A water treatment plant at Chung-Nam province during $2007{\sim}2008$ years and used the selected data for the verification of developed algorithm. According to the experimental results, MLP model showed 5.82[%], but the proposed ELM based model showed 5.61[%] with respect to MAPE, respectively. Also, MLP model needed 7.57s training time, but ELM based model was 0.09s. Therefore, the proposed ELM based short-term water demand prediction model can be used to operate the water treatment plant effectively.

• Journal of Korean Society of Water and Wastewater
• /
• v.11 no.1
• /
• pp.109-118
• /
• 1997

In this study, we examined the structural analysis of water demand fluctuation for water distribution control of water supply network. In order to analyze for the length of stationary time series, we calculate autocorrelation coefficient of each case equally divided data size. As a result, it was found that, with the data size of around three months, any case could be used as stationary time series. we analyze cross-correlation coefficient between the daily water consumption's data and primary influence factors. As a result, we have decided to use weather conditions and maximum temperature as natural primary factors and holidays as a social factor. Applying the multiple ARIMA model, we obtains an effective model to describe the daily water demand prediction. From the forecasting result, even though we forecast water distribution quantity of the following year, estimated values well express the flctuations of measurements. Thus, the suitability of the model for practical use can be confirmed. When this model is used for practical water distribution control, water distribution quantity for the following day should be found by inputting maximum temperature and weather conditions obtained from weather forecast, and water purification plants and service reservoirs should be operated based on this information while operation of pumps and valves should be set up. Consequently, we will be able to devise a rational water management system.

• Korean Journal of Agricultural Science
• /
• v.46 no.1
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• Membrane and Water Treatment
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2019

The Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report (AR5) predicted that recent extreme hydrological events would affect water quality and aggravate various forms of water pollution. To analyze changes in water quality due to future climate change, input data (precipitation, average temperature, relative humidity, average wind speed and sunlight) were established using the Representative Concentration Pathways (RCP) 8.5 climate change scenario suggested by the AR5 and calculated the future runoff for each target period (Reference:1989-2015; I: 2016-2040; II: 2041-2070; and III: 2071-2099) using the semi-distributed land use-based runoff processes (SLURP) model. Meteorological factors that affect water quality (precipitation, temperature and runoff) were inputted into the multiple linear regression analysis (MLRA) and artificial neural network (ANN) models to analyze water quality data, dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand (COD), suspended solids (SS), total nitrogen (T-N) and total phosphorus (T-P). Future water quality prediction of the Anseongcheon River basin shows that DO at Gongdo station in the river will drop by 35% in autumn by the end of the $21^{st}$ century and that BOD, COD and SS will increase by 36%, 20% and 42%, respectively. Analysis revealed that the oxygen demand at Dongyeongyo station will decrease by 17% in summer and BOD, COD and SS will increase by 30%, 12% and 17%, respectively. This study suggests that there is a need to continuously monitor the water quality of the Anseongcheon River basin for long-term management. A more reliable prediction of future water quality will be achieved if various social scenarios and climate data are taken into consideration.