신경망 모델을 이용한 적도 태평양 표층 수온 예측 = Forecasting the Sea Surface Temperature in the Tropical Pacific by Neural Network Model

국문 초록 (Abstract)

대표적인 엘니뇨 지수인 태평양 Niño 해역의 표층 수온을 예측하기 위해 비선형 통계모델 중의 하나인 신경망 기법을 적용하였다. 신경망 모델 학습 과정의 입력 자료로 1951년부터 1993년까지의 태평양 해역(120o E-290o E, 20o S-20o N) NCEP/NCAR의 재분석 표층 수온 편차의 경험적 직교함수 7개 주모드를 사용하였고, 그 중 1994년부터 2003년까지의 10년 결과를 분석하였다. 모든 해역에서의 9개월까지의 신경망 모델의 예측력은 비교적 우수하였으며,특히 1997년과 1998년의 강한 엘니뇨의 발달 및 소멸도 잘 예측함을 확인할수 있었다. 해역별로는 Niño3 지역의 예측성능이 가장 높았으며, 9개월 이후부터는 그 예측력이 급격히 감소하였다. 한편 지역적인 영향이 커 예측력이 낮은 동태평양 연안의 Niño1+2 지역은 9개월 이후에도 예측력의 감소가 관찰되지 않았다.

다국어 초록 (Multilingual Abstract)

Temperature Anomalies (SSTA) in the Nio regions, which represent El Nio indices. The data used as inputs in thetraining step of neural network model were the first seven empirical orthogonal functions in the tropical Pacific (120o E-290o E, 20o S-20o N) obtained from the NCEP/NCAR reanalysis data. The period of 1951 to 1993 was adopted for thetraining of neural network model, and the period 1994 to 2003 for the forecasting validation. Forecasting results suggestedthat neural network models were resonable for SSTA forecasting until 9-month lead time. They also predicted greatly thedevelopment and decay of strong El Nio occurred in 1997-1998 years. Especially, Nio3 region appeared to be the bestforecast region, while the forecast skills rapidly decreased since 9-month lead time. However, in the Nio1+2 regionwhere they are relatively low by the influence of local effects, they did not decrease even after 9-month lead time

참고문헌 (Reference)

1 "인공신경망 모델을 이용한 폭풍해일 예측 연구" 348-349, 2004

2 "연안 실시간 정보를 이용한 태풍해일 예측" 7-17, 2004

3 "구간 연산 신경망을 이용한 강수량 장기예측 기법" 37 (37): 443-452, 2001

4 "o signals contained in precipitation at the East China Sea" 23 (23): 31-38, 2002

5 "its climatology and temporal changes associated with the climate regime shift in the 1970s" 47 : 223-256, 2000

6 "a fundamental property of the atmosphere" 98-110, 1984

7 "Relations between two sets of variates" 321-366, 1936

8 "Prediction of El Niñ o events in the Pacific by means of neural networks" 51-63, 1994

9 "Origins and levels of monthly and seasonal forecast skill for United States surface air temperatures determined by canonical correlation analysis" 19871825-1850

10 "Interannual variability and lagged correlation during strong El Niñ o events in the Pacific Ocean" 27 (27): 51-58, 2004

11 "Forecsting the equatorial Pacific sea surface temperature by neural network model" 13, : 135-147, 1997

12 "Forecasting the regional sea surface temperature of the tropical Pacific by neural network models with wind stress and sea level pressure as predictors" 103, : 7511-7522, 1998

13 "Empirical orthogonal analysis of Pacific sea surface temperature Journal of Physical Oceanography" 671-678, 1976

14 "Department of the Meteorology Massachusetts Institute of Technology" 49-, 1956

15 "Bulletin of the American Meteorological Society" and (and): 49-60, 1992

16 "Bulletin of the American Meteorological Society" 2097-2114, 1994

17 "A study of Arctic sea ice and sea-level pressure using POP and neural network methods" 507-529, 1994