Abstract

본 연구에서는 LOC/MTG 온도지표를 이용하여 한강유역의 강우변동특성을 분석하였다. 장기간의 온도인자에 내포되어 있는 비정상 진동의 복합적인 특성을 파악하기 위해 EEMD(Ensemble Empirical Mode Decomposition) 기법을 적용하여 유한개의 진동패턴인 IMFs(Intrinsic mode functions)를 추출하였으며, MLP-ANN(Multi-layer Perceptron Artificial Neural Network) 기법을 적용하여 두 온도지표의 단기예측을 실시하였다. 또한 트리모델을 통하여 두 온도지표에 따른 여름철 강우 및 비태풍 강우에 대한 그룹화를 실시하여 한강유역의 장래 강우 발생에 대한 예측의 적용가능성을 검토하였다. In the current study, we analyzed the characteristics of summer precipitation variability in the Han River basin using the Land-Ocean Contrast (LOC) and Meridional Temperature Gradient (MTG) temperature indices. To analyze the complex characteristics of abnormal variations internalized in the long-term temperature indices, the Ensemble Empirical Mode Decomposition (EEMD) method was applied to extract Intrinsic Mode Functions (IMFs), a finite number of variation patterns. The extended IMFs were applied to the Multi-layer Perceptron Artificial Neural Network (MLP-ANN) model to forecast the short-term period of two temperature indices. In addition, we performed grouping on summer precipitation with using decision making model, Tree model. We also, studied nontyphoons precipitation in consideration of the complex effects of the two temperature indices and examined the applicability of forecast regarding the monsoon related precipitation during the summer season over the Han River basin.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call