Journal of the Korean earth science society (한국지구과학회지)

The Korean Earth Science Society (한국지구과학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Tropical Cyclone Intensity and Track Over the Western North Pacific using the Artificial Neural Network Method

인공신경망 기법을 이용한 태풍 강도 및 진로 예측

  • Choi, Ki-Seon (Department of Environmental Atmospheric Sciences, Pukyong National University) ;
  • Kang, Ki-Ryong (National Typhoon Center, Korea Meteorological Administration) ;
  • Kim, Do-Woo (Department of Environmental Atmospheric Sciences, Pukyong National University) ;
  • Kim, Tae-Ryong (National Typhoon Center, Korea Meteorological Administration)
  • 최기선 (부경대학교 환경대기과학과) ;
  • 강기룡 (기상청 국가태풍센터) ;
  • 김도우 (부경대학교 환경대기과학과) ;
  • 김태룡 (기상청 국가태풍센터)
  • Published : 2009.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

A statistical prediction model for the typhoon intensity and track in the Northwestern Pacific area was developed based on the artificial neural network scheme. Specifically, this model is focused on the 5-day prediction after tropical cyclone genesis, and used the CLIPPER parameters (genesis location, intensity, and date), dynamic parameters (vertical wind shear between 200 and 850hPa, upper-level divergence, and lower-level relative vorticity), and thermal parameters (upper-level equivalent potential temperature, ENSO, 200-hPa air temperature, mid-level relative humidity). Based on the characteristics of predictors, a total of seven artificial neural network models were developed. The best one was the case that combined the CLIPPER parameters and thermal parameters. This case showed higher predictability during the summer season than the winter season, and the forecast error also depended on the location: The intensity error rate increases when the genesis location moves to Southeastern area and the track error increases when it moves to Northwestern area. Comparing the predictability with the multiple linear regression model, the artificial neural network model showed better performance.

북서태평양에서 발생한 태풍에 대해 발생 후 5일 동안 12시간 간격으로 태풍의 강도 및 진로를 예측할 수 있는 인공신경망 모델을 개발하였다. 사용되어진 예측인지는 CLIPER(발생 위치 강도 일자), 운동학적 파라미터(연직바람시어, 상층발산, 하층상대와도), 열적 파라미터(상층 상당온위, ENSO, 상층온도, 중층 상대습도)로 구성되어졌다. 예측인자의 특성에 따라 일곱개의 인공신경망 모델들이 개발되었으며, CLIPER와 열적 파라미터가 조합된(CLIPER-THERM) 모델이 가장 좋은 예측성능을 보였다. 이 CLIPER-THERM 모델은 강도 및 진로 모두에서 동절기보다 하절기에 더 나은 예측성능을 나타내었다. 또한 태풍의 발생이 아열대 서태평양의 남동쪽에 위치할수록 강도예측에서는 큰 오차를 보였고, 진로예측에서는 아열대 서태평양의 북서쪽에서 발생할수록 큰 오차를 보였다. 이후 인공신경망 모델의 예측성능을 검증하기 위해 같은 예측인자들을 이용하여 다중선형회귀모델을 개발하였으며, 결과로서 비선형 통계기법인 인공신경망 모델이 다중선형회귀모형보다는 더 나은 예측성능을 보였다.

Keywords

References

  1. 김진원, 이재규, 2007, 태풍 루사와 관련된 WRF의 수치모의 결과 분석. 대기지, 17, 393-405
  2. 김주혜, 추교명, 김백조, 원성희, 권혁조, 2007, 이동격자태풍모델을 이용한 2006년 태풍의 진로 및 강도 예측성능평가. 대기지, 17, 207-216
  3. 권인혁, 정형빈, 2003, DFS 전구순압 모델을 이용한 태풍진로 예측. 대기지, 13, 98-99
  4. 권혁조, 이상호, 1993, 태풍진로 예보에 있어서 지역적으로 강화된 CLIPER 모델의 개발에 관한 연구. 한국기상학회지, 29, 195-204
  5. 윤순창, 박경선, 1990, 한국에 접근하는 태풍의 특성과 통계 지속 모델의 신뢰도에 관한 연구. 한국기상학회지, 6, 104-110
  6. 장동언, 이동규, 1989, 중간규모 모델을 이용한 태풍 Vera의 수치 실험. 한국기상학회지, 25, 148-167
  7. 정병석, 박광호, 유승아, 정준석, 2002, 2002년 제15호 태풍 '루사'에 의하여 야기된 영동지방 호우 분석. 대기지, 12, 414-417
  8. Baik, J.J. and Hwang, H.S., 1998, Tropical cyclone intensity prediction using regression method and neural network. Journal of Meteorological Society of Japan, 76, 711-717
  9. Baik, J.J. and Paek, J.S., 2000a, A neural network model for predicting typhoon intensity. Journal of Meteorological Society of Japan, 78, 857-867
  10. Baik, J.J. and Paek, J.S., 2000b, Performance test of backpropagation neural network in typhoon track and intensity prediction. Korean Journal of Atmospheric Science, 3, 33-38
  11. Chan, J.CL, Shi, J.E., and Lam, C.M., 1998, Seasonal Forecasting of Tropical Cyclone Activity over the Western North Pacific and the South China Sea. Weather and Forecasting, 13, 997-1004 https://doi.org/10.1175/1520-0434(1998)013<0997:SFOTCA>2.0.CO;2
  12. DeMaria, M. and Kaplan, J., 1999, An updated Statistical Hurricane Intensity Prediction Scheme (SHIPS) for the Atlantic and eastern North Pacific basins. Weather and Forecasting, 14, 326-337 https://doi.org/10.1175/1520-0434(1999)014<0326:AUSHIP>2.0.CO;2
  13. Gray, W.M., 1975, Tropical cyclone genesis. Department of Atmospheric Science Paper 234, Colorado State University, CO, USA, 121 p
  14. Hanley, D.E., 2002, The Evolution of a hurricane-trough Interaction from a Satellite Perspective. Weather and Forecasting, 17, 916-926 https://doi.org/10.1175/1520-0434(2002)017<0916:TEOAHT>2.0.CO;2
  15. Hsieh, W.W. and Tang, B., 1998, Applying neural network models to prediction and data analysis in meteorology and oceanography. Bulletin of American Meteorological Society, 79, 1855-1870 https://doi.org/10.1175/1520-0477(1998)079<1855:ANNMTP>2.0.CO;2
  16. Kalnay, E., Kanamitsu, M., Kistler, R., Collins, W., Deaven, D., Gandin, L., Iredell, M., Saba, S., White, G., Woollen, J., Zhu, Y., Leetmaa, A., Reynolds, R., Chelliah, M., Ebisuzaki, W., Higgins, W., Janowiak, J., Mo, K.C., Ropelewski, C., Wang, J., Jenne, R., and Joseph, D., 1996, The NCEP/NCAR 40-Year reanalysis project. Bulletin of American Meteorological Society, 77, 437-471 https://doi.org/10.1175/1520-0477(1996)077<0437:TNYRP>2.0.CO;2
  17. Kistler, R., Kalnay, E., Collins, W., Saha, S., White, G., Woollen, J., Chelliah, M., Ebisuzaki, W., Kanamitsu, M., Kousky, V., Dool, H., Jenne, R., and Fiorino, M., 2001, The NCEP/NCAR 50-year reanalysis. Bulletin of American Meteorological Society, 82, 247-267 https://doi.org/10.1175/1520-0477(2001)082<0247:TNNYRM>2.3.CO;2
  18. Kwon, H.J., Won, S.H., Ahn, M.H., Sub, A.S., and Chung, H.S., 2002, GFDL-type typhoon initialization in MM5. Monthly Weather Review, 130, 2966-2974 https://doi.org/10.1175/1520-0493(2002)130<2966:GTTIIM>2.0.CO;2
  19. Neumann, C. and Randrianarison, E., 1976, Statistical prediction of tropical cyclone motion over the southeast Indian Ocean. Monthly Weather Review, 104, 76-85 https://doi.org/10.1175/1520-0493(1976)104<0076:SPOTCM>2.0.CO;2
  20. Park, S.K. and Lee, E.H., 2007, Synoptic features of orographically enhanced heavy rainfall on the east coast of Korea associated with typhoon Rusa (2002). Geophysical Research Letters, 34, L02803, doi: 10.1029/2006GL028592
  21. Petty, K.R., 1999, Statistically forecasting tropical cyclone intensity change in the eastern North Pacific. 23rd conference of Hurricane and tropical meteorology, Dallas, TX, American Meterological Society, 600-602
  22. Rumelhart, D.E., Hinton, G.E., and Williams, R.J., 1986, Learning representations by back-propagating errors. Nature, 323, 533-536 https://doi.org/10.1038/323533a0
  23. Wang, B. and Chan, J.C.L., 2002, How strong ENSO events affect tropical storm activity over the western North Pacific. Journal of Climate, 15, 1643-1658 https://doi.org/10.1175/1520-0442(2002)015<1643:HSEEAT>2.0.CO;2

Cited by

  1. A Study on the Observation of the Typhoons that Affected Southeastern Region of the Korean Peninsula vol.20, pp.9, 2011, https://doi.org/10.5322/JES.2011.20.9.1191
  2. Assessment of Precipitation Characteristics and Synoptic Pattern Associated with Typhoon Affecting the South Korea vol.48, pp.6, 2015, https://doi.org/10.3741/JKWRA.2015.48.6.463
  3. Development of a Heavy Rain Damage Prediction Function by Risk Classification vol.18, pp.7, 2018, https://doi.org/10.9798/KOSHAM.2018.18.7.503