• 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.

• Korean Journal of Agricultural Science
• /
• v.47 no.3
• /
• pp.471-483
• /
• 2020

Flood prediction is an important issue to prevent damages by flood inundation caused by increasing high-intensity rainfall with climate change. In recent years, machine learning algorithms have been receiving attention in many scientific fields including hydrology, water resources, natural hazards, etc. The performance of a machine learning algorithm was investigated to predict the water elevation of a river in this study. The aim of this study was to develop a new method for securing a large enough lead time for flood defenses by predicting river water elevation using the a long- short-term memory (LSTM) technique. The water elevation data at the Oisong gauging station were selected to evaluate its applicability. The test data were the water elevation data measured by K-water from 15 February 2013 to 26 August 2018, approximately 5 years 6 months, at 1 hour intervals. To investigate the predictability of the data in terms of the data characteristics and the lead time of the prediction data, the data were divided into the same interval data (group-A) and time average data (group-B) set. Next, the predictability was evaluated by constructing a total of 36 cases. Based on the results, group-A had a more stable water elevation prediction skill compared to group-B with a lead time from 1 to 6 h. Thus, the LSTM technique using only measured water elevation data can be used for securing the appropriate lead time for flood defense in a river.

• Spatial Information Research
• /
• v.21 no.5
• /
• pp.63-72
• /
• 2013

This paper analyzed the flood propagation characteristics of each flood elevation due to failure of embankment in Muju Namdae Stream using recursive call algorithm. A flood propagation order by the flood elevation was estimated by setting destruction point at Beonggu and Chasan small dam through recursive call algorithm and then, the number of grids of each flood propagation order and accumulated inundation area were calculated. Based on the flood propagation order and the grid size of DEM, flood propagation time could be predicted each flood elevation. As a result, the study could identify the process of flood propagation through distribution characteristic of the flood propagation order obtained from recursive call algorithm, and could provide basic data for protection from flood disaster by selecting the flood vulnerable area through the gradient pattern of the graph for accumulated inundation area each flood propagation order. In addition, the prediction of the flood propagation time for each flood water level using this algorithm helped provide valuable information to calculate the evacuation path and time during the flood season by predicting the flood propagation time of each flood water level.

• Ocean Systems Engineering
• /
• v.5 no.4
• /
• pp.245-259
• /
• 2015

The numerical simulation of wave slamming on a 3D platform deck was investigated using a coupled Level-Set and Volume-of-Fluid (CLSVOF) method for overset grid system incorporated into the Finite-Analytic Navier-Stokes (FANS) method. The predicted slamming impact forces were compared with the corresponding experimental data. The comparisons showed that the CLSVOF method is capable of accurately predicting the slamming impact and capturing the violent free surface flow including wave slamming, wave inundation and wave recession. Moreover, the capability of the present CLSVOF method for overset grid system is a prominent feature to handle the prediction of wave slamming on offshore structure.

• Journal of Environmental Science International
• /
• v.31 no.12
• /
• pp.1027-1038
• /
• 2022

The intertidal zone has both land and marine characteristics and shows complex weather environments. These characteristics are suited for studying climate change, energy balance and ecosystems, and may play an important role in coastal and marine weather prediction and analysis. This study was conducted at Odo Island, approximately 300m from the mainland in Yeosu. We built a weather observation system capable of real-time monitoring on the mud flat in the intertidal zone and measured actual weather and marine data. Weather observation was conducted from April to June 2022. The results showed changes in air temperature and water temperature with changes in the tide level during spring. Correlation analysis revealed characteristic changes in air temperature and water temperature during the day and night, and with inundation and exposure.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.477-477
• /
• 2021

지구온난화로 인한 집중호우 및 태풍의 발생 횟수와 강도가 증가함에 따라 홍수피해가 증가하고 있으며, 특히 도로침수는 피해 측면에서 '복구-보상' 중심의 사후처리 체계에서 벗어나 '예방-대응-관리'를 통한 사전 재난대응 체계로 정책 전환이 요구되고 있다. 이에, 도로침수관련 재난정책의 기반기술이 될 수 있는 '도로침수 실시간 예측·감시 및 운영 기술'을 경상남도 진주시를 대상으로 침수피해 관련 지역현안을 해결하고자 하며, 강우예측자료를 활용한 침수해석, CCTV영상을 이용한 AI기반 실시간 침수감시, 공간 빅데이터 기반 침수정보제공, e-SOP 등 다양한 기술이 융합된 실증 연구로 이루어진다. 본 연구결과물이 실용화되어 도로침수통합관리시스템으로 운영된다면 지역 수재해 대응력 향상에 기여할 것으로 판단된다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.3
• /
• pp.76-92
• /
• 2018

This study aimed to establish database of rainfall inundation area by rainfall scenarios and conduct a real time prediction for urban flood mitigation. the data leaded model was developed for the mapping of inundated area with rainfall forecast data provided by korea meteorological agency. for the construction of data leaded model, 1d-2d modeling was applied to Gangnam area, where suffered from severe flooding event including september, 2010. 1d-2d analysis result agree with observed in term of flood depth. flood area and flood occurring report which maintained by NDMS(national disaster management system). The fitness ratio of the NDMS reporting point and 2D flood analysis results was revealed to be 69.5%. Flood forecast chart was created using pre-flooding database. It was analyzed to have 70.3% of fitness in case of flood forecast chart of 70mm, and 72.0% in case of 80mm flood forecast chart. Using the constructed pre-flood area database, it is possible to present flood forecast chart information with rainfall forecast, and it can be used to secure the leading time during flood predictions and warning.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.4
• /
• pp.545-550
• /
• 2019

The frequency of natural disasters and the scale of damage are increasing due to the abnormal weather phenomenon occurring all over the world. As a result, as the hydrological aspect of the urban watershed changes, the increase in impervious area leads to serious domestic flood damage due to increased rainfall. In order to minimize the damage of life and property, domestic flooding prediction system is needed. In this study, we developed a flood nomogram capable of predicting flooding only by rainfall intensity and duration. This study suggests a method to set the internal water immersion alarm criterion by analyzing the characteristics of the flooding damage in the flooded area in the metropolitan area where flooding is highly possible and the risk of flooding is high. In addition, based on the manhole and the pipe, the water level was set as follows under the four conditions. 1) When manhole overflows, 2) when manhole is full, 3) when 70% of the pipe is reached, and 4) when 60% of the pipe is reached. Therefore, it can be used as a criterion and a predictive measure to cope with the pre-preparation before the flooding starts, through the rainfall that causes the flooding and the flooding damage.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.671-683
• /
• 2018

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.267-267
• /
• 2016

Extreme events, such as Winnie(1987), Rusa(2002), Maemi(2003) at sea-side urban area, resulted not only economic losses but also life losses. The Korean sea-side characterisitcs are so complicated thar the prediction of sea level rise makes difficult. Geomophologically, Korean pennisula sits on the rim of the Pacific mantle so the sea level is sensitive to the surges due to earth quake, typoon and abnormal climate changes. These environmetns require closer investigation for the preparing the inundatioin due to the sea level rise with customized prediction for local basin. The goal of this research is provide the information of inundation risk so the sea side urban basin could be more safe from the natural water disastesr.