• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.3
• /
• pp.273-283
• /
• 2020

Because of climate change, the occurrence of localized and heavy rainfall is increasing. It is important to predict floods in urban areas that have suffered inundation in the past. For flood prediction, not only numerical analysis models but also machine learning-based models can be applied. The LSTM (Long Short-Term Memory) neural network used in this study is appropriate for sequence data, but it demands a lot of data. However, rainfall that causes flooding does not appear every year in a single urban basin, meaning it is difficult to collect enough data for deep learning. Therefore, in addition to the rainfall observed in the study area, the observed rainfall in another urban basin was applied in the predictive model. The LSTM neural network was used for predicting the total overflow, and the result of the SWMM (Storm Water Management Model) was applied as target data. The prediction of the inundation map was performed by using logistic regression; the independent variable was the total overflow and the dependent variable was the presence or absence of flooding in each grid. The dependent variable of logistic regression was collected through the simulation results of a two-dimensional flood model. The input data of the two-dimensional flood model were the overflow at each manhole calculated by the SWMM. According to the LSTM neural network parameters, the prediction results of total overflow were compared. Four predictive models were used in this study depending on the parameter of the LSTM. The average RMSE (Root Mean Square Error) for verification and testing was 1.4279 ㎥/s, 1.0079 ㎥/s for the four LSTM models. The minimum RMSE of the verification and testing was calculated as 1.1655 ㎥/s and 0.8797 ㎥/s. It was confirmed that the total overflow can be predicted similarly to the SWMM simulation results. The prediction of inundation extent was performed by linking the logistic regression with the results of the LSTM neural network, and the maximum area fitness was 97.33 % when more than 0.5 m depth was considered. The methodology presented in this study would be helpful in improving urban flood response based on deep learning methodology.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.2
• /
• pp.95-102
• /
• 2005

Currently, the government has been established GIS DB related to river as a part of the river map digitization projects such as RIMGIS and flood map. This study was aimed to demonstrate the generation of thematic maps related to river space and their management system, the one of the major river thematic maps proposed from the precedent study "Establishment of River Thematic Map Project" in an effort to maximize the utilization of river related database, the major product of the project for digitization of river maps. This study includes amending database model for building river thematic maps. Also, metadata were amended and built for efficient management and distribution of the river related data based on the national standard metadata proposed from "Establishing Standard Metadata" sponsored by National Geography Institute in 2003 for more effective management of river thematic maps. In addition, this study analyzed the method for utilizing existing data from RIMGIS and WAMIS as well as digital topographic maps to produce 25 river thematic maps in accordance of defined building procedure. Management system of the river thematic maps for Kyungan watershed has been generated for effective managing river thematic maps based on the design and pilot generation of river thematic maps, and metadata management function has been added into the management system.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4B
• /
• pp.389-398
• /
• 2006

The present study compositely applied the self-organizing map (SOM), which is a kind of artificial neural networks (ANNs), and the back propagation algorithm (BPA) for the rainfall-runoff prediction model taking account of the irregular variation of the spatiotemporal distribution of rainfall. To solve the problems from the previous studies on ANNs, such as the overestimation of low flow during the dry season, the underestimation of runoff during the flood season and the persistence phenomenon, in which the predicted values continuously represent the preceding runoffs, we introduced SOM theory for the preprocessing in the prediction model. The theory is known that it has the pattern classification ability. The method proposed in the present research initially includes the classification of the rainfall-runoff relationship using SOM and the construction of the respective models according to the classification by SOM. The individually constructed models used the data corresponding to the respectively classified patterns for the runoff prediction. Consequently, the method proposed in the present study resulted in the better prediction ability of runoff than that of the past research using the usual application of ANNs and, in addition, there were no such problems of the under/over-estimation of runoff and the persistence.

• Journal of Korea Water Resources Association
• /
• v.42 no.8
• /
• pp.591-605
• /
• 2009

In this study the risk integrated erosion and seepage failure factor and combined risk of the levee embankment were assessed. For the research of the reliability, the risk assessment of erosion, seepage and both of them combined for the levee embankment were conducted using discharge curve and stage hydrograph generated by stochastic rainfall variation method during typhoon and monsoon season. The risk of erosion was evaluated using tractive force and the seepage analysis was performed by selecting representative cross sections for SEEP/W model analysis. And the probability of seepage failure was assessed with MFOSM analysis using critical hydraulic gradient method. Unlike deterministic analysis method, quantitative risk could be obtained and the characteristics of realistic rainfall variation patterns as well as a variety of factors contributing to levee failure could be reflected in this research. The results of this study show significantly enhanced applicability for the combined risk. As this model can be employed to determine dangerous spots for levee failure and to establish flood insurance linked with flood risk map, it will dramatically contribute to the establishment of both efficient and systematic measures for integrated flood management on a watershed.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.1057-1066
• /
• 2019

The storage function method is used as a flood prediction model for four flood control offices in Korea as a method to analyze the actual rainfall-runoff relationship with non-linearity. It is essential to accurately estimate the parameters of the storage function method for accurate runoff analysis. However, the parameters of the storage function method currently in use are estimated by the empirical formula developed by the limited hydrological analysis in 2012; therefore, they are somewhat inaccurate. The kinematic wave method is a method based on physical variables of watershed and channel and is widely used for rainfall-runoff analysis. By adopting the two-term storage function method by the conversion of the kinematic wave method, parameters can be estimated based on physical variables, which can increase the accuracy of runoff calculation. In this research, the reproducibility of the kinematic wave method by the two-term storage function method was investigated. It is very easy to estimate the parameters because equivalent roughness, which is an important physical variable in watershed runoff, can be easily obtained by using land use and land cover, and the physical variable of channel runoff can be easily obtained from the basic river planning report or topographic map. In addition, this research examined the applicability of the two-term storage function method to runoff simulation of Naechon Stream, a tributary of the Hongcheon River in the Han River basin. As a result, it is considered that more accurate runoff calculation results could be obtained than the existing one-term storage function method. It is expected that the utilization of the storage function method can be increased because the parameters can be easily estimated using physical variables even in unmeasured watersheds and channels.

• The Journal of Engineering Geology
• /
• v.24 no.4
• /
• pp.501-510
• /
• 2014

Volcanic eruptions alone may lead to serious natural disasters, but the associated release of water from a caldera lake may be equally damaging. There is both historical and geological evidence of the past eruptions of Mt. Baekdusan, and the volcano, which has not erupted for over 100 years, has recently shown signs of reawakening. Action is required if we are to limit the social, political, cultural, and economic damage of any future eruption. This study aims to identify the area that would be inundated following a volcanic flood from the Cheon-Ji caldera lake that lies within Mt. Baekdusan. A scenario-based numerical analysis was performed to generate a flood hydrograph, and the parameters required were selected following a consideration of historical records from other volcanoes. The amount of water at the outer rim as a function of time was used as an upper boundary condition for the downstream routing process for a period of 10 days. Data from the USGS were used to generate a DEM with a resolution of 100 m, and remotely sensed satellite data from the moderate-resolution imaging spectroradiometer (MODIS) were used to show land cover and use. The simulation was generated using the software FLO-2D and was superposed on the remotely sensed map. The results show that the inundation area would cover about 80% of the urban area near Erdaobaihezhen assuming a 10 m/hr collapse rate, and 98% of the area would be flooded assuming a 100 m/hr collapse rate.

• Journal of Korean Society for Geospatial Information Science
• /
• v.16 no.1
• /
• pp.23-32
• /
• 2008

According to recent frequent local flash flood due to climate change, the very short-term rainfall forecast using remotely sensed rainfall like radar is necessary to establish. This research is to evaluate the feasibility of GIS-based distributed model coupled with radar rainfall, which can express temporal and spatial distribution, for multipurpose dam operation during flood season. $Vflo^{TM}$ model was used as physically based distributed hydrologic model. The study area was Yongdam dam basin ($930\;km^2$) and the 3 storm events of local convective rainfall in August 2005, and the typhoon.Ewiniar.and.Bilis.collected from Jindo radar was adopted for runoff simulation. Distributed rainfall consistent with hydrologic model grid resolution was generated by using K-RainVieux, pre-processor program for radar rainfall. The local bias correction for original radar rainfall shows reasonable results of which the percent error from the gauge observation is less than 2% and the bias value is $0.886{\sim}0.908$. The parameters for the $Vflo^{TM}$ were estimated from basic GIS data such as DEM, land cover and soil map. As a result of the 3 events of multiple peak hydrographs, the bias of total accumulated runoff and peak flow is less than 20%, which can provide a reasonable base for building operational real-time short-term rainfall-runoff forecast system.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.2
• /
• pp.99-105
• /
• 2007

This research is about applying aerial photos to three-dimensional simulation of road design. Instead of existing road design approach using digital map, which inexactly represent some part of topography and landmarks, digital aerial photos are applied to three-dimensional road design to address such inexactness of the map. First of all, ortho-photos are made using aerial photos, and a digital elevation model is created by extracting DEM. Then, by applying the coordinates practically using in planar design to three-dimensional approach, this model will be much helpful in the analyses of road route and viewscape. In addition, through the use of Virtual GIS, many evaluation factors such as urban design, flora, soil, water channel or road shape, flood plan are used for examination, and the effectiveness of applying three-dimensional simulation based on such route design standard is to be reviewed. In this paper, a basic research about three-dimensional design of structures is performed, and through the three-dimensional design, some effective determination to decision-making was carried out. Hereafter, it appears some research regarding environment-friendly construction and design should be followed.

• Water for future
• /
• v.28 no.5
• /
• pp.117-127
• /
• 1995

The application and analysis for the scale considering GIUH model proposed by the authors in this issue have been performed for the leemokjung sub-basin in the Pyungchang basin one of IHP representative basin in Korea. Scales of topographic maps for model application and fractal analysis are 1:25,000, 1:50,000 and 1:100,000. The ratio between successive scales is therefore constant. Link lengths were measured using a curvimeter with the resolution of 1 mm. Richardson's method was employed to have fractal dimension of streams. Apparent alternations of parameters were found in accordance with variations of map scale. And this tendency could mislead physical meanings of parameters because model parameters had to preserve their own value in spite of map scale change. It was found that uses of fractal transform and Melton's law could help to control the scale problem effectively. This methodlogy also could emphasize the relationship between network and basin to the model. To verify the applicability of GIUH proposed in this research, the model was compared with the exponential GIUH model. It is proven that proposed 2-parameter gamma GIUH model can better simulate the corresponding runoff from any given flood events than exponential GIUH model. The result showed that 2-parameter gamma GIUH model and fractal theory could be used for deriving scale considered IUH of the basin.

• Journal of Cadastre & Land InformatiX
• /
• v.47 no.2
• /
• pp.135-144
• /
• 2017

The riverbed areas have exposed to various natural disasters and the private use by neighboring residents have caused many problems. The research objectives are to survey the actual situation of riverbed areas in order to prevent landscape damage and private use. Drone and photogrammetry, orthophoto, DSM(Digital Surface Model), digital topographic map and cadastral information have been integrated by GIS technology. The flood and disaster vulnerable area has been surveyed and the land use and private use has been analyzed using cadastral information. The research results show that the analyzed data can be used for providing foundation data for management of river and also can be used for surveying actual situation of private use on the riverbed areas.