• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.2
• /
• pp.69-77
• /
• 2001

An artificial neural network model was developed to analyze and forecast daily steamflow flow a small watershed. Error Back propagation neural networks (EBPN) of daily rainfall and runoff data were found to have a high performance in simulating stremflow. The model adopts a gradient descent method where the momentum and adaptive learning rate concepts were employed to minimize local minima value problems and speed up the convergence of EBP method. The number of hidden nodes was optimized using Bayesian information criterion. The resulting optimal EBPN model for forecasting daily streamflow consists of three rainfall and four runoff data (Model34), and the best number of the hidden nodes were found to be 13. The proposed model simulates the daily streamflow satisfactorily by comparison compared to the observed data at the HS#3 watershed of the Baran watershed project, which is 391.8 ha and has relatively steep topography and complex land use.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.37 no.3_4
• /
• pp.48-60
• /
• 1995

A flood - flow forecasting system model of river basins has been developed in this study. The system model consists of the data management system(the observation and telemetering system, the rainfall forecasting and data-bank system), the flood runoff simulation system, the reservoir operation simulation system, the flood forecasting simulation system, the flood warning system and the user's menu system. The Multivariate Rainfall Forecasting model, Meteorological factor regression model and Zone expected rainfall model for rainfall forecasting and the Streamflow synthesis and reservoir regulation(SSARR) model for flood runoff simulation have been adopted for the development of a new system model for flood - flow forecasting. These models are calibrated to determine the optimal parameters on the basis of observed rainfall, 7 streamfiow and other hydrological data during the past flood periods.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.714-715
• /
• 2005

• Journal of Korea Water Resources Association
• /
• v.33 no.S1
• /
• pp.269-274
• /
• 2000

• Journal of Korea Water Resources Association
• /
• v.39 no.3 s.164
• /
• pp.253-259
• /
• 2006

In almost all previous hydrological studies, the standard approach adopted for nonlinear time series analysis is to perform system characterization first followed by forecasting. However, a practical inverse approach for forecasting nonlinear hydrological time series was proposed recently To investigate the applicability standard approach method and inverse approach, this study used a theoretical time series (Mackey-Glass time series) and daily streamflows of the Bear River in Idaho. To predict a theoretical time series and daily streamflow, this study used local approximation method. From chaos analysis, chaotic characteristics are found in daily streamflow of the Bear River in Idaho. Resulting from 1, 3 and 5-day prediction, inverse approach method is shown to be better than the standard approach for a theoretical chaotic time series and daily streamflow.

• Journal of Korea Water Resources Association
• /
• v.53 no.6
• /
• pp.395-408
• /
• 2020

This paper aims to develop and apply three different machine learning approaches (i.e., artificial neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), and wavelet-based neural networks (WNN)) combined with an evolutionary optimization algorithm and the k-fold cross validation for multi-step (days) streamflow forecasting at the catchment located in Algeria, North Africa. The ANN and ANFIS models yielded similar performances, based on four different statistical indices (i.e., root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), correlation coefficient (R), and peak flow criteria (PFC)) for training and testing phases. The values of RMSE and PFC for the WNN model (e.g., RMSE = 8.590 ㎥/sec, PFC = 0.252 for (t+1) day, testing phase) were lower than those of ANN (e.g., RMSE = 19.120 ㎥/sec, PFC = 0.446 for (t+1) day, testing phase) and ANFIS (e.g., RMSE = 18.520 ㎥/sec, PFC = 0.444 for (t+1) day, testing phase) models, while the values of NSE and R for WNN model were higher than those of ANNs and ANFIS models. Therefore, the new approach can be a robust tool for multi-step (days) streamflow forecasting in the Seybous River, Algeria.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2002.05a
• /
• pp.43-50
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict streamflow and flash floods. Previously, neural networks were used to develop a Quantitative Precipitation Forecasting (QPF) model that highly improved forecasting skill at specific locations in Pennsylvania, using both Numerical Weather Prediction (NWP) output and rainfall and radiosonde data. The objective of this study was to improve an existing artificial neural network model and incorporate the evolving structure and frequency of intense weather systems in the mid-Atlantic region of the United States for improved flood forecasting. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as life time, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships between weather system, rainfall production and streamflow response in the study area. The new Quantitative Flood Forecasting (QFF) model was applied to predict streamflow peaks with lead-times of 18 and 24 hours over a five year period in 4 watersheds on the leeward side of the Appalachian mountains in the mid-Atlantic region. Threat scores consistently above .6 and close to 0.8 ∼ 0.9 were obtained fur 18 hour lead-time forecasts, and skill scores of at least 4％ and up to 6％ were attained for the 24 hour lead-time forecasts. This work demonstrates that multisensor data cast into an expert information system such as neural networks, if built upon scientific understanding of regional hydrometeorology, can lead to significant gains in the forecast skill of extreme rainfall and associated floods. In particular, this study validates our hypothesis that accurate and extended flood forecast lead-times can be attained by taking into consideration the synoptic evolution of atmospheric conditions extracted from the analysis of large-area remotely sensed imagery While physically-based numerical weather prediction and river routing models cannot accurately depict complex natural non-linear processes, and thus have difficulty in simulating extreme events such as heavy rainfall and floods, data-driven approaches should be viewed as a strong alternative in operational hydrology. This is especially more pertinent at a time when the diversity of sensors in satellites and ground-based operational weather monitoring systems provide large volumes of data on a real-time basis.

• Journal of Environmental Science International
• /
• v.24 no.8
• /
• pp.1023-1036
• /
• 2015

A reliable streamflow forecasting is essential for flood disaster prevention, reservoir operation, water supply and water resources management. This study proposes a hybrid model for river stage forecasting and investigates its accuracy. The proposed model is the wavelet packet-based artificial neural network(WPANN). Wavelet packet transform(WPT) module in WPANN model is employed to decompose an input time series into approximation and detail components. The decomposed time series are then used as inputs of artificial neural network(ANN) module in WPANN model. Based on model performance indexes, WPANN models are found to produce better efficiency than ANN model. WPANN-sym10 model yields the best performance among all other models. It is found that WPT improves the accuracy of ANN model. The results obtained from this study indicate that the conjunction of WPT and ANN can improve the efficiency of ANN model and can be a potential tool for forecasting river stage more accurately.

• Water Engineering Research
• /
• v.3 no.2
• /
• pp.113-122
• /
• 2002

Accurate quantitative forecasting of rainfall for basins with a short response time is essential to predict flash floods. In this study, a Quantitative Flood Forecasting (QFF) model was developed by incorporating the evolving structure and frequency of intense weather systems and by using neural network approach. Besides using radiosonde and rainfall data, the model also used the satellite-derived characteristics of storm systems such as tropical cyclones, mesoscale convective complex systems and convective cloud clusters as input. The convective classification and tracking system (CCATS) was used to identify and quantify storm properties such as lifetime, area, eccentricity, and track. As in standard expert prediction systems, the fundamental structure of the neural network model was learned from the hydroclimatology of the relationships between weather system, rainfall production and streamflow response in the study area. All these processes stretched leadtime up to 18 hours. The QFF model will be applied to the mid-Atlantic region of United States in a forthcoming paper.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.243-243
• /
• 2015

Low-flow simulation and forecasting is one of the emerging issues in hydrology due to the increasing demand of water in dry periods. Even though low-flow simulation and forecasting remains a difficult issue for hydrologists better simulation and earlier prediction of low flows are crucial for efficient water management. The UN has never stated that South Korea is in a water shortage. However, a recent study by MOLIT indicates that Korea will probably lack water by 4.3 billion m3 in 2020 due to several factors, including land cover and climate change impacts. The two main situations that generate low-flow events are an extended dry period (summer low-flow) and an extended period of low temperature (winter low-flow). This situation demands the hydrologists to concentrate more on low-flow hydrology. Korea's annual average precipitation is about 127.6 billion m3 where runoff into rivers and losses accounts 57% and 43% respectively and from 57% runoff discharge to the ocean is accounts 31% and total water use is about 26%. So, saving 6% of the runoff will solve the water shortage problem mentioned above. The main objective of this study is to present the hydrological modelling approach for low-flow simulation and forecasting using a model that have a capacity to represent the real hydrological behavior of the catchment and to address the water management of summer as well as winter low-flow. Two lumped hydrological models (GR4J and CAT) will be applied to calibrate and simulate the streamflow. The models will be applied to Seolmacheon catchment using daily streamflow data at Jeonjeokbigyo station, and the Nash-Sutcliffe efficiencies will be calculated to check the model performance. The expected result will be summarized in a different ways so as to provide decision makers with the probabilistic forecasts and the associated risks of low flows. Finally, the results will be presented and the capacity of the models to provide useful information for efficient water management practice will be discussed.