Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Applicability study on urban flooding risk criteria estimation algorithm using cross-validation and SVM

교차검증과 SVM을 이용한 도시침수 위험기준 추정 알고리즘 적용성 검토

  • Lee, Hanseung (Disaster Prevention Research Division, National Disaster Management Research Institute) ;
  • Cho, Jaewoong (Disaster Prevention Research Division, National Disaster Management Research Institute) ;
  • Kang, Hoseon (Disaster Prevention Research Division, National Disaster Management Research Institute) ;
  • Hwang, Jeonggeun (Disaster Prevention Research Division, National Disaster Management Research Institute)
  • 이한승 (국립재난안전연구원 방재연구실) ;
  • 조재웅 (국립재난안전연구원 방재연구실) ;
  • 강호선 (국립재난안전연구원 방재연구실) ;
  • 황정근 (국립재난안전연구원 방재연구실)
  • Received : 2019.07.30
  • Accepted : 2019.11.19
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study reviews a urban flooding risk criteria estimation model to predict risk criteria in areas where flood risk criteria are not precalculated by using watershed characteristic data and limit rainfall based on damage history. The risk criteria estimation model was designed using Support Vector Machine, one of the machine learning algorithms. The learning data consisted of regional limit rainfall and watershed characteristic. The learning data were applied to the SVM algorithm after normalization. We calculated the mean absolute error and standard deviation using Leave-One-Out and K-fold cross-validation algorithms and evaluated the performance of the model. In Leave-One-Out, models with small standard deviation were selected as the optimal model, and models with less folds were selected in the K-fold. The average accuracy of the selected models by rainfall duration is over 80%, suggesting that SVM can be used to estimate flooding risk criteria.

본 연구는 도시침수 위험기준이 산정되지 않은 지역의 예·경보 기준을 예측하기 위해 유역특성 자료와 피해이력 기반으로 산정된 한계강우량을 활용하여 도시침수 위험기준을 추정하는 모델을 검토하였다. 위험기준 추정모델은 머신러닝 알고리즘의 하나인 Support Vector Machine을 이용하여 설계하였으며, 학습자료는 지역별 한계강우량과 유역특성으로 구성하였다. 학습자료는 정규화 한 후 SVM 알고리즘에 적용하였으며, SVM에 적용시 Leave-One-Out과 K-fold 교차검증 알고리즘을 이용하여 절대평균오차와 표준편차를 계산한 후 모델의 성능을 평가하였다. Leave-One-Out의 경우 표준편차가 작은 모델이 최적모델로 선정되었으며, K-fold의 경우 fold의 개수가 적은 모델이 선정되었다. 선정된 모델의 지속시간별 평균 정확도는 80% 이상으로 나타나 침수 위험기준 추정을 위해 SVM을 활용가능 할 것으로 판단된다.

Keywords

References

  1. Behzad, M., Asghari, K., Eazi, M., and Palhang, M. (2009). "Generalization performance of support vector machines and neural networks in runoff modeling, expert systems with applications." An International Journal, Vol. 36, No. 4, pp. 7624-7629.
  2. Chang, J.G. (2006). "Real-time vehicle recognition mechanism using support vector machines." Journal of Korea Academia Industrial Cooperation Society, Vol. 7, No. 6, pp. 1160-1166.
  3. Cho, J.W., Choi, C.W., Kang, H.S., Lee, H.S., Bae, C.Y., Hwang, J.G., and Bae, S.J. (2018b). Deep learning based urban flood alert critrria estimation model design. NDMI-PR-2018-09-01-01. National Disaster Management Research Institute, Ulsan.
  4. Cho, J., Bae, C., and Kang, H. (2018a). "Development and application of urban flood alert criteria considering damage records and runoff characteristics." Journal of Korea Water Resource Association, KWRA, Vol. 51, No. 1, pp. 1-10. https://doi.org/10.3741/JKWRA.2018.51.1.1
  5. Hipni, A., El-shafie, A., Najah, A., Karim, O.A., Hussain, A., and Mukhlisin, M. (2013). "Daily forecasting of dam water levels: comparing a support vector machine (SVM) model with adaptive neuro fuzzy inference system (ANFIS)." Water Resources Management, Vol. 27, No. 10, pp. 3803-3823. https://doi.org/10.1007/s11269-013-0382-4
  6. Kim, S., Shiri, J., and Kisi, O. (2012). "Pan evaporation modeling using neural computing approach for different climatic zones." Water resources management, Vol. 26, No. 11, pp. 3231-3249. https://doi.org/10.1007/s11269-012-0069-2
  7. Korea Meteorological Administration (KMA) (2016). Planning study on introduction plan of influence forecast.
  8. Lin, G.F., Chen, G.R., Huang, P.Y., and Chou, Y.C. (2009). "Support vector machine-based models for hourly reservoir inflow forecasting during typhoon-warning periods." Journal of hydrology, Vol. 372, No. 1-4, pp. 17-29. https://doi.org/10.1016/j.jhydrol.2009.03.032
  9. Ministry of the Interior and Safety (MOIS) (2018). 2017 Statistical yearbook of natural disaster.
  10. Misra, D., Oommen, T., Agarwal, A., Mishra, S.K., and Thompson, A.M. (2009). "Application and analysis of support vector machine based simulation for runoff and sediment yield." Biosystems Engineering, Biosystems Engineering, Vol. 103, No. 4, pp. 527-535. https://doi.org/10.1016/j.biosystemseng.2009.04.017
  11. Vapnik, V. (1995). The nature of statistical learning theory. Springer, Verlag New York.
  12. World Meteorological Organization (WMO) (2015). Guidelines on multi-hazard impact-based forecast and warning services. No. 1150, Swiss Geneva.