J. Korean Soc. Hazard Mitig Search

CLOSE


J. Korean Soc. Hazard Mitig. > Volume 19(7); 2019 > Article
기상방재
Journal of the Korean Society of Hazard Mitigation 2019;19(7):55-62.
DOI: https://doi.org/10.9798/KOSHAM.2019.19.7.55    Published online December 31, 2019.
Is Deep Better in Extreme Temperature Forecasting?
Trang Thi Kieu Tran1, Taesam Lee2
Member, Graduate Student, Department of Civil Engineering, ERI, Gyeongsang National University
Member, Professor, Dept. of Civil Engineering, Gyeongsang National University
Corresponding author:  Taesam Lee, Tel: +82‐55‐772‐1797, Fax: +82‐55‐772‐1799, 
Email: tae3lee@gnu.ac.kr
Received: 3 September 2019   • Revised: 4 September 2019   • Accepted: 29 October 2019
Abstract
In recent years, the application of deep learning based on artificial neural networks (ANNs) to forecast highly non-linear and complex weather phenomena, such as rainfall, wind speed, and temperature, has become an attractive pursuit in the field of environmental sciences. However, the critical research addressing the question of whether or not a deep learning network can perform better has not been completed. The current study conducted a systematic comparison of a one-hidden-layer (shallow) network and a multiple-hidden-layer (deep) network in maximum temperature forecasting Datasets of daily maximum temperature at five stations in South Korea, spanning the years 1976 to 2015, were used for training and testing the different-architecture models, respectively. With each model, one-day-ahead forecasting was made for the winter, spring, summer, and autumn seasons. Moreover, the performance and effectiveness of the models were then assessed by the root mean square error (RMSE). In addition, a genetic algorithm was applied to select the optimal network architecture. Finally, the empirical results indicated that the ANN model with one hidden layer, compared with the case of multiple-hidden-layer networks, produced the most accurate forecasts.
Key Words: Artificial Neural Network, Maximum Temperature Forecasting, One‐day‐ahead Forecasting, Genetic Algorithm, Deep Network
요지
최근 들어서 인공신경망을 이용한 딥러닝이 강우, 풍속, 온도 등의 높은 비선형성과 복잡성을 가진 여러 기상현상을 예측하는데 널리 이용되어지고 있다. 하지만 실제적인 딥러닝이 그만큼의 성능을 발휘하는지에 대한 중요한 연구들은 실제로 많이 이루어지지 못하고 있다. 따라서 본 연구에서는 하나의 은닉층을 바탕으로 한 얕은 층의 모형과 여러 은닉층을 가진 깊은 은닉층의 모형에 대해서 비교 평가하였다. 자료는 한국의 5개 기상관측지점을 대상으로 1975-2015년의 일최고기온을 바탕으로 수행되어졌다. 각각의 모형은 겨울, 봄, 여름, 가을 자료의 1일단위 예측하는데 적용되었다. 이와 더불어, 모델의 성능과 효율성이 RMSE를 통해 평가되었고, 유전알고리즘이 최상의 네트워크구조를 찾는데 사용되었다. 전체적으로, 한 개의 은닉층을 가진 모형이 다수의 은닉층을 가진 모델보다 더 좋은 성능을 가지는 특징을 보여 주었다.
핵심용어: 인공신경망, 일최고기온 예측, 1일단위 예측, 유전 알고리즘, 딥 네트워크


ABOUT
ARTICLE CATEGORY

Browse all articles >

BROWSE ARTICLES
AUTHOR INFORMATION
Editorial Office
307 Main Bldg., The Korea Science Technology Center, 22 Teheran-ro 7-gil(635-4 Yeoksam-dong), Gangnam-gu, Seoul 06130, Korea
Tel: +82-2-567-6311    Fax: +82-2-567-6313    E-mail: master@kosham.or.kr                

Copyright © 2020 by The Korean Society of Hazard Mitigation. All rights reserved.

Developed in M2community

Close layer
prev next