DOI QR코드

DOI QR Code

Prediction of Storm Surge Height Using Synthesized Typhoons and Artificial Intelligence

합성태풍과 인공지능을 활용한 폭풍해일고 예측

  • 엄호식 ((주)지오시스템리서치 해양예보사업부) ;
  • 박종집 ((주)지오시스템리서치 해양예보사업부) ;
  • 정광영 (국립해양조사원 해양과학조사연구실) ;
  • 박영민 ((주)지오시스템리서치 해양예보사업부)
  • Received : 2020.11.27
  • Accepted : 2020.12.28
  • Published : 2020.12.31

Abstract

The rapid and accurate prediction of storm-surge height during typhoon attacks is essential in responding to coastal disasters. Most methods used for predicting typhoon data are based on numerical modeling, but numerical modeling takes significant computing resources and time. Recently, various studies on the expeditious production of predictive data based on artificial intelligence have been conducted, and in this study, artificial intelligence-based storm-surge height prediction was performed. Several learning data were needed for artificial intelligence training. Because the number of previous typhoons was limited, many synthesized typhoons were created using the tropical cyclone risk model, and the storm-surge height was also generated using the storm surge model. The comparison of the storm-surge height predicted using artificial intelligence with the actual typhoon, showed that the root-mean-square error was 0.09 ~ 0.30 m, the correlation coefficient was 0.65 ~ 0.94, and the absolute relative error of the maximum height was 1.0 ~ 52.5%. Although errors appeared to be somewhat large at certain typhoons and points, future studies are expected to improve accuracy through learning-data optimization.

태풍 내습 시 신속하고 정확한 해일고 예측은, 연안재해 대응에 필수적인 요소이다. 이러한 해일고의 예측을 위해서 기존에는 태풍예측정보를 수치모델에 적용하여 예측자료를 생산하는 것이 대부분 이였다. 이러한 방법은 대용량의 컴퓨팅 자원과 시간이 소요된다는 단점이 있다. 최근에는 인공지능 기반으로 신속하게 예측자료를 생산하는 연구가 다양한 분야에서 진행되고 있으며, 본 연구에서는 인공지능 기반 해일고 예측을 수행하였다. 인공지능 적용을 위해서는 많은 수의 학습자료가 필요하게 되며, 기왕 발생태풍은 개수가 한정되어 있어 본 연구에서는 TCRM(Tropical Cyclone Risk Model)을 통하여 합성태풍을 생성하고, 이를 폭풍해일 모델에 적용하여 해일고 자료를 생성한 후, 학습자료로 활용하였다. 인공지능으로 예측한 해일고와 실제 발생 태풍에 대한 비교 결과, RMSE(Root Mean Square Error)는 0.09 ~ 0.30 m, CC(Correlation Coefficient)는 0.65 ~ 0.94, 최대 해일고의 ARE(Absolute Relative Error)는 1.0 ~ 52.5 %로 분석되었다. 특정 태풍/지점에서는 다소 오차가 크게 나타나고 있으나, 향후 학습자료의 최적화 등을 통하여 정확도를 개선할 수 있을 것으로 기대된다.

Keywords

References

  1. Anton, B., B. Blanton, and S. Reinaldo(2016), Multi-Output Articial Neural Network for Storm Surge Prediction in North Carolina, Neural Networks, arXiv:1609.07378.
  2. French, J., M. Robert, F. Taku, and A. Kamal(2017), Combining machine learning with computational hydrodynamics for prediction of tidal surge inundation at estuarine ports, IUTAM symposium on storm surge modelling and forecasting, Vol. 25, pp. 28-35.
  3. Holland, G. J.(1980), An analytic model of the wind and pressure profiles in hurricanes, Monthly Weather Review, Vol. 108, pp. 1212-1218. https://doi.org/10.1175/1520-0493(1980)108<1212:AAMOTW>2.0.CO;2
  4. Jung, S. H., H. S. Cho, J. G Kim, and G. H. Lee(2018), Prediction of water level in a tidal river using a deep-learning based LSTM model, Journal of Korea Water Resources Association, Vol. 51, No. 12, pp. 1207-1216.
  5. Kim, H. J. and S. W. Suh(2019), Estimation of Frequency of Storm Surge Heights on the West and South Coasts of Korea Using Synthesized Typhoons. Journal of Korean Society of Coastal and Ocean Engineers Vol. 31, No. 5, pp. 241-252. https://doi.org/10.9765/KSCOE.2019.31.5.241
  6. Lee, G. H., S. H. Jung, and D. E. Lee(2018), Comparison of physicsbased and data-driven models for streamflow simulation of the Mekong river. Journal of Korea Water Resources Association, Vol. 51, No. 6, pp. 503-514. https://doi.org/10.3741/JKWRA.2018.51.6.503
  7. Lee, H. Y., D. S. Kim, J. R. Park, and S. J. Hong(2017), Operation of Real-time Storm Surge Response System for Decision-making Support. Journal of Korean Society of Hazard Mitigation, Vol. 17, No. 3, pp. 367-380. https://doi.org/10.9798/KOSHAM.2017.17.3.367
  8. Luettich, R. A. and J. J. Westerink(2004), Formulation and numerical implementation of the 2D/3D ADCIRC finite element model version 44.XX.
  9. Luettich, R. A., S. Hu, and J. J. Westerink(1994), The development of the direct stress solution technique for three-dimensional hydrodynamic models using finite elements, International, Journal for Numerical Methods in Fluids, Vol. 19, pp. 295-319. https://doi.org/10.1002/fld.1650190403
  10. Luettich, R. A., S. Hu, J. J. Westerink, and N. W. Scheffner (1992), Modeling 3-D Circulation Using Computations for the Western North Atlantic and Gulf of Mexico, Estuarine and Coastal Modeling II, M. Spaulding [ed.], ASCE, pp. 632-643.
  11. Matsumoto, K., T. Takanezawa, and M. Ooe(2000), Ocean Tide Models Developed by Assimilating TOPEX/POSEIDON Altimeter Data into Hydrodynamical Model: A Global Model and a Regional Model Around Japan, Journal of Oceanography, Vol. 56, pp. 567-581. https://doi.org/10.1023/A:1011157212596
  12. Park, C. H. and I. M. Chung(2020), Evaluating the groundwater prediction using LSTM model. Journal of Korea Water Resources Association, Vol. 53, No. 4, pp. 273-283. https://doi.org/10.3741/JKWRA.2020.53.4.273
  13. Park, J. K., B. S. Kim, W. S. Jung, E. B. Kim, and D. G. Lee(2006), Change in Statistical Characteristics of Typhoon Afferting the Korean Peninsula, Jounal of Korean Meteorological Society: Atmosphere, Vol 16, No. 1, pp. 1-17.
  14. Vickery, P. J. and D. Wadhera(2009), Statistical models of Holland pressure profile parameter and radius to maximum winds of hurricanes from flight-level pressure and H*Wind data. Journal of Applied Meteorology and Climatology, Vol. 47, No. 10, pp. 2497-2517. https://doi.org/10.1175/2008JAMC1837.1
  15. Willoughby, H. E., R. Darling, W. R, and M. E. Rahn(2006), Parametric representation of the primary hurricane vortex. Part II: A new family of sectionally continuous profiles, Monthly Weather Review, Vol. 134, pp. 1102-1120. https://doi.org/10.1175/MWR3106.1
  16. Xie, L., S. Bao, L. J. Pietrafesa, K. Foley, and M. Fuentes(2006), A real-time hurricane surface wind forecasting model: formulation and verification. Monthly Weather Review, Vol. 134, No.5, pp. 1355-1370. https://doi.org/10.1175/MWR3126.1