| Title |
Deep Learning Based Prediction Model for Easterly Wind |
| Authors |
김경태(Kyoungtae Kim) ; 서기성(Kisung Seo) |
| DOI |
https://doi.org/10.5370/KIEE.2019.68.12.1607 |
| Keywords |
Easterly wind; Deep neural network; Convolution neural network; Long short-term memory; Deep learning |
| Abstract |
Understanding the characteristics of the easterly-related weather phenomena in the eastern coast in Korean Peninsula is very important to analyze abnormal atmospheric phenomena such as heavy rain, heavy snow, and hot-dry wind. As data science techniques have steadily improved, data driven prediction models are becoming more powerful in the quantitative forecasting weather. In this paper, we apply the deep learning based methods to predict the presence or absence of the easterly wind around the Korean peninsula. The DNN, CNN, and LSTM based deep learning approaches for prediction of easterly wind are experimented and compared for the Korean Peninsula and East Sea. Vertical pressure levels of ERA5 data in year 2013 and 2014 are used. |