적설량 예측을 위한 신경망 및 다중회귀 모형의 적용성 평가 = Evaluation for Snowfall Depth Forecasting using Neural Network and Multiple Regression Models

다국어 초록 (Multilingual Abstract)

Since snowfall is related to various meteorological variables such as temperature and precipitation, it is generated in nonlinear manner. Therefore this study constructs snowfall forecasting model using neural networks and multiple regression which can consider nonlinear process of snowfall. The study constructs the forecasting models for each station using temperature, precipitation, and snowfall depth observed from starting time of observation to 1999. And snowfalls are calculated for all stations by using temperature and precipitation in the period of 2000 to 2011. From the statistical analysis of the calculated snowfall, the proper model is selected. The selected models show the correlation coefficients R2 of 0.700 to 0.949 and the adjusted determination coefficients of 41.7% to 89.8%. The applicability of neural network models is superior to other model at almost every station. But in some cases multiple regression models show better results than neural network models due to the lack of observational data during learning period and the extreme peak values which are not learned during forecasting period. According to the study, the results of the models confirm the predicting snowfall depth by using temperature and precipitation is possible and show neural network model is better than the existing statistical models.

국문 초록 (Abstract)

적설량은 기상변수들의 복잡한 비선형 조합으로 발생하기 때문에 적설량에 영향을 미치는 온도, 강수량, 적설량의 비선형 과정들을 고려할 수 있는 신경망 모형과 통계적 기법인 다중회귀 모형을 이용하여 적설량 예측 모형을 구성하였다. 관측시점부터1999년까지의 관측된 기온, 강수량, 적설량을 이용하여 지점별로 예측모형을 구성하였고, 2000년부터 2011년까지의 지점별 기온, 강수량을 통해 적설량 산정과 관측 자료와의 통계분석을 실시하였으며, 이 중 상관계수와 수정결정계수가 높은 모형을 채택하였다. 채택된 모형의 상관계수는 0.700~0.949로 매우 높은 관계를 나타냈으며, 수정결정계수는 41.7%~89.8%로 적설량의 총 변동을 설명하였다. 대부분의 지점에서 신경망 모형의 적용성이 우수한 것으로 나타났으나, 학습기간에서 관측자료의 부족, 예측기간 중 학습되지 않은 극값의 발생 등에 의해 울진, 대전, 부산, 목포의 경우 신경망 보다 다중회귀 모형의 적용성이 더 높게산정되었다. 본 연구를 통하여 기온 및 강수량을 이용한 적설량 예측이 가능함을 확인하였으며, 기상자료의 비선형과정을 고려할 수 있는 신경망 모형을 적용하는 것이 기존의 통계적 모형을 이용한 예측보다 적용성이 높은 것으로 분석되었다.

참고문헌 (Reference)

1 Yonhap news agency, "Title : ‘Snowfall guidance’ development, December 7"

2 Kim, G.S., "Sensitivity of numerical prediction of snowfall to model physics and initial conditions" Yonsei University 2003

3 Jeong Y. K., "Seasonal Prediction by Interannual Variability of Snowfall in Honam Region and Atmospheric Circulation Characteristics" 152-153, 2005

4 Lee, H.S., "SPSS 12.0 manual" Bobmunsa 2005

5 Roebber, P. J., "Real-Time Forecasting of Snowfall Using a Neural Network" 22 : 676-684, 2007

6 Kwon, Y.S, "Radar Rainfall adjustment by Artificial Neural Network and Runoff Analysis" Inha University 2009

7 Oh, I.S., "Pattern recognition" Kyobo Bookstore 2008

8 Byun, K.Y, "Numerical Prediction of the Snowfall Depth" 156-157, 2004

9 Lee T.Y, "Numerical Prediction of Snowfall Depth" 348-349, 2005

10 Oh, C.S, "Neuro Computer" Naeha Publisher 1996

11 Oh, J.W, "Missing Hydrological Data Estimation using Neural Network and Auto Data Reconciliation" Chungnam National University 2008

12 Kim, H.S, "Linking Environmental Assessment and Sustainable Development Indicators" Korea Environment Institute 2007

13 "Korea Meteorological Administration(KMA)"

14 Oh, C.S, "Introduction to Neuro Computer" Naeha Publisher 2000

15 Roebber, P. J., "Improving Snowfall Forecasting by Diagnosing Snow Density" 18 : 264-287, 2003

16 Ware, E. C., "Improving Snowfall Forecasting by Accounting for the Climatological Variability of Snow Density" 21 : 94-103, 2006

17 Song, J.O, "Examination of Prediction Model for Snowfall in Honam Region" 246-249, 2002

18 Kim, Y.S., "Estimation of Frequency Based Snowfall Depth Considering Climate Change" 70-, 2010

19 Kim, Y.S, "Estimation of Frequency Based Snowfall Depth Considering Climate Change" 196-, 2012

20 Chung, S.B., "Development of Prediction Method for Snowfall by cP Expansion in Honam Province" 286-287, 2003