Browse > Article
http://dx.doi.org/10.12652/Ksce.2020.40.3.0273

Prediction of Urban Flood Extent by LSTM Model and Logistic Regression  

Kim, Hyun Il (Kyungpook National University)
Han, Kun Yeun (Kyungpook National University)
Lee, Jae Yeong (Korea Institute of Civil Engineering and Builidng Technology)
Publication Information
KSCE Journal of Civil and Environmental Engineering Research / v.40, no.3, 2020 , pp. 273-283 More about this Journal
Abstract
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.
Keywords
Flood prediction; Urban runoff analysis; LSTM model; Logistic regression;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 Cultural Heritage Administration (2020). Flood history, Available at: http://royaltombs.cha.go.kr (Accessed: January 2, 2020).
2 Gardner, K. K. and Vogel, R. M. (2005). "Predicting ground water nitrate concentration from land use." Ground Water, Vol. 43, No. 3, pp. 343-352.   DOI
3 Hu, C., Wu, Q., Li, H., Jian, S., Li, N. and Lou, Z. (2018). "Deep learning with a long short-term memory networks approach for rainfall-runoff simulation." Water, Vol. 10, No. 11, 1543.   DOI
4 Korea Meteorological Administration (KMA) (2020). Meteorological database, Observation Data, Available at: https://data.kma.go.kr (Accessed: December 1, 2019).
5 Le, X. H., Ho, H. V., Lee, G. H. and Jung, S. H. (2019). "Application of long short-term memory (LSTM) neural network for flood forecasting." Water, Vol. 11, No. 7, 1387, DOI: 10.3390/w11071387.   DOI
6 Moore, M. R. (2011). Development of a high-resolution 1D/2D coupled flood simulation of Charles City, Iowa, Master's Thesis, University of Iowa, United States of America (USA).
7 Mosavi, A., Ozturk, P. and Chaw K. K. (2018). "Flood prediction using machine learning models: Literature review." Water, Vol. 10, No. 11, 1536, DOI: 10.3390/w10111536.   DOI
8 Nandi, A., Mandal, A., Wilson, M. and Smith, D. (2016). "Flood hazard mapping in Jamaica using principal component analysis and logistic regression." Environment Earth Science, Vol. 75, No. 465, DOI: 10.1007/s12665-016-5323-0.
9 Ozdemir, A. (2011). "Using a binary logistic regression method and GIS for evaluating and mapping the groundwater spring potential in the Sultan Mountains (Aksehir, Turkey)." Journal of Hydrology, Vol. 405, No. 1-2, pp. 123-136.   DOI
10 Park, J. H., Kim, S. H. and Bae, D. H. (2019). "Evaluating appropriateness of the design methodology for urban sewer system." Journal of Korea Water Resource Association, KWRA, Vol. 52, No. 6, pp. 411-420.   DOI
11 Pradhan, B. (2009). "Flood susceptible mapping and risk area delineation using logistic regression, GIS and remote sensing." Journal of Spatial Hydrology, Vol. 9, No. 2, pp. 1-18.
12 Rai, P. K., Chahar, B. R. and Dhanya, C. T. (2017). "GIS-based SWMM model for simulating the catchment response to flood evetns." Hydrology Research, Vol. 48, No. 2, pp. 384-394.   DOI
13 Risi, R. D., Jalayer, F. and Paola, F. D. (2015). "Meso-scale hazard zoning of potentially flood prone areas." Journal of Hydrology, Vol. 527, pp. 316-325.   DOI
14 Seoul Metropolitan City (2015). Comprehensive plan for storm and flood damage reduction, Korea, Vol. 1, Chapter 3, pp. 374-375.
15 Seoul Metropolitan Government (2020). Flood criterion data, Available at: http://safecity.seoul.go.kr (Accessed: January 5, 2020)
16 Shen, C. (2018). "A transdisciplinary review of deep learning research and its relevance for water resources scientists." Water Resources Research, Vol. 54, No. 11, pp. 8558-8593, DOI: 10.1029/2018WR022643.   DOI
17 Son, A. L., Kim, B. H. and Han, K. Y. (2015). "A study on prediction of inundation area considering road network in urban area." Journal of the Korean Society of Civil Engineers, KSCE, Vol. 35, No. 2, pp. 307-318.   DOI