Asia-Pacific Journal of Atmospheric Sciences

Korean Meteorological Society (한국기상학회)
권호 표지

Evaluation of Artificial Neural Network Correction Skill on Dynamically Downscaled Summer Rainfall over South Korea

역학적으로 규모축소된 남한의 여름철 강수에 대한 인공신경망 보정 능력 평가

Cha, Yu-Mi;Ahn, Joong-Bae
차유미;안중배

  • Published : 2005.12.30
⟨ Previous Next ⟩

Abstract

In this study, 10-day mean July precipitation anomalies for the period 1990-2001 downscaled dynamically from AGCM have been corrected using Multiple Linear Regression (MLR) and nonlinear Artificial Neural Network (ANN) methods, and the results are analyzed for the determination of the optimal Model Output Statistics (MOS) method applicable to the regional precipitation forecasting over South Korea. The dynamically downscaled precipitation anomalies are cross-validated respectively, by MLR and ANN methods. Overall, the corrected results are better than the uncorrected one compared with the observation, and the ANN-corrected results are found to be more realistic than those of the MLR-corrected. In particular, the cross-validated time series analysis shows that the ANN method has better capability in reproducing heavy rainfall. Heidke Skill Score based on a trisectional forecast for the cross-validated precipitation shows that ANN-corrected scores are closer to 1 over the whole domain, which implies that the ANN method has high skill in correcting precipitation forecast. Brier Skill Score based on the occurrence and non-occurrence of precipitation event also indicates that ANN method has an outstanding predictability of precipitation. The fact that the ANN-corrected results are more similar to the observation than those of the MLR-corrected implies that the non-linear function applied to ANN algorism might be more efficient and suitable in capturing non-linear characters of precipitation than a linear function. Thus it is concluded that precipitation predictability can be improved dramatically using nonlinear MOS such as ANN.

Keywords

References

  1. 김호준, 백희정, 권원태, 최병철, 2001: 구간 연산 신경망을 이용한 강수량 장기예측 기법. 한국기상학회지, 37, 443- 452
  2. 박성진, 1997: 신경망을 이용한 태풍 진로 예측. 포항공과대 학교 정보통신대학원 석사학위논문, 49pp
  3. 박순웅, 안현주, 전영식, 1989: 한반도 중부지방 장마전선 상에 발생한 호우와 관련된 종관기상장의 변화. 한국기상학회지, 25, 168-191
  4. 안중배․차유미, 2005: 역학적으로 규모축소된 남한의 겨 울철 기온에 대한 인공신경망과 다중선형회귀모형을 이 용한 보정 비교 연구. 한국기상학회지, 41, 401-413
  5. 이다운, 이호만, 서장원, 유승협, 윤용훈, 2005: 신경망을 이 용한 폭풍해일 예측 연구. 한국기상학회지, 41, 661-670
  6. 이동규 외, 2002: 한반도 집중강수 예측 향상. '슈퍼컴을 활용한 예보능력 향상연구' 3차년도 최종보고서. 81pp
  7. 하경자, 박성규, 김기영, 2003: 한반도 주변의 하계 강수량의 경년 변동과 이에 연관된 동아시아 순환의 특성. 한국기상학회지, 39, 575-586
  8. 허창회․강인식, 1988: 한국 지역 강수의 변동성에 관한 연구. 한국기상학회지, 24, 38-48
  9. Coulibaly, P, Y. B. Dibike, and F. Anctil, 2005: Downscaling Precipitation and Temperature with Temporal Neural Networks. J. Hydrometeorology. 6, 483-496 https://doi.org/10.1175/JHM409.1
  10. Dean, A. R., and B. H. Fiedler, 2002: Forecasting Warm-Season Burnoff of Low Clouds at the San Francisco International Airport Using Linear Regression and a Neural Network. J. App. Meteor., 41, 629-629 https://doi.org/10.1175/1520-0450(2002)041<0629:FWSBOL>2.0.CO;2
  11. Heidke, P, 1926: Berechnung des Erfolges und der Güte der Windstarkevorhersagen im Sturmwarnungsdienst. Geogr. Ann., 8, 310-349
  12. Hong, S.-Y., and H.-L. Pan, 1996: Nonlocal boundary layer vertical diffusion in a medium-range forecast model. Mon. Wea. Rev., 124, 2322-2339 https://doi.org/10.1175/1520-0493(1996)124<2322:NBLVDI>2.0.CO;2
  13. IPCC, 2001 : Clmate Change 2001: The Scientific Bias. J. T. Houghton, Y. Ding, D. J. Griggs, M. Noguer, P. J. van der Linden, X. Dai, K. Maskell, C. A. Johnson, Cambrigde Univ. Press, 881pp
  14. Kain, J. S., and J. M. Fritsch, 1993: Convective parameterization for mesoscale models: The Kain-Fritsch scheme. The representation of cumulus convection in numerical models, K. A. Emanuel and D. J. Raymond, Eds., Amer. Meteor. Soc., 246pp
  15. Kretzschmar, R., P. Eckert, D. Cattani, and F. Eggimann, 2004: Neural Network Classifiers for Local Wind Prediction. J. App. Meteor., 43, 727-738 https://doi.org/10.1175/2057.1
  16. Kuligowski, Robert J., and Ana P. Barros, 1998: Localized Precipitation Forecasts from a Numerical Weather Prediction Model Using Artificial Neural Networks. Weather and Forecasting, 13, 1194-1203 https://doi.org/10.1175/1520-0434(1998)013<1194:LPFFAN>2.0.CO;2
  17. Marzban, Caren, 2003: Neural Networks for Postprocessing Model Output: ARPS. Mon. Wea. Rev., 131, 1103-1111 https://doi.org/10.1175/1520-0493(2003)131<1103:NNFPMO>2.0.CO;2
  18. Mihalakakou, G., H. A. Flocas, M. Santamouris, and C. G. Helmis, 2002: Application of Neural Networks to the Simulation of the Heat Island over Athens, Greece, Using Synoptic Types as a Predictor, J. App. Meteor., 41, 519-527 https://doi.org/10.1175/1520-0450(2002)041<0519:AONNTT>2.0.CO;2
  19. Sahai, A. K., M. K. Soman, and V. Satyan, 2000: All India summer monsoon rainfall prediction using an artificial neural network. Climate Dyn., 6, 291-302
  20. Schoof, J. T., and S. C. Pryor, 2001: Downscaling Temperature and Precipitation: A Comparison of Regression-based Methods and Artifical Neural Networks. Int. J. Climatol., 21, 773-790 https://doi.org/10.1002/joc.655
  21. Silverman, D., and J. A. Dracup, 2000: Artificial Neural Networks and Long-Range Precipitation Prediction in California. J. App. Meteor., 39, 57-66 https://doi.org/10.1175/1520-0450(2000)039<0057:ANNALR>2.0.CO;2
  22. Snell, S. E., S. Gopal, and R. K. Kaufmann, 2000: Spatial Interpolation of Surface Air Temperatures Using Artificial Neural Networks: Evaluating Their Use for Downscaling GCMs. J. Climate, 13, 886-895 https://doi.org/10.1175/1520-0442(2000)013<0886:SIOSAT>2.0.CO;2
  23. Taylor, Karl E., 2001: Summarizing Multiple Aspects of Model Performance in a Single Diagram. J. Geophys. Res., 106, 7183-7192 https://doi.org/10.1029/2000JD900719
  24. Yuval, 2001: Enhancement and Error Estimation of Neural Network Prediction of Niño-3.4 SST Anomalies. J.Climate, 14, 2150-2163 https://doi.org/10.1175/1520-0442(2001)014<2150:EAEEON>2.0.CO;2
  25. Yuval and William W. Hsieh, 2003: An adaptive nonlinear MOS scheme for precipitation forecasts using neural networks. Weather and Forecasting, 18, 303-310 https://doi.org/10.1175/1520-0434(2003)018<0303:AANMSF>2.0.CO;2
  26. Wilks, D. S., 1995: Statistical Methods in the Atmospheric Sciences. International geophysics series, 59, 467pp.