TY - JOUR
T1 - Forecasting daily temperatures with different time interval data using deep neural networks
AU - Lee, Sungjae
AU - Lee, Yung Seop
AU - Son, Youngdoo
N1 - Publisher Copyright:
© 2020 by the authors.
PY - 2020/3/1
Y1 - 2020/3/1
N2 - Temperature forecasting has been a consistent research topic owing to its significant effect on daily lives and various industries. However, it is an ever-challenging task because temperature is affected by various climate factors. Research on temperature forecasting has taken one of two directions: time-series analysis and machine learning algorithms. Recently, a large amount of high-frequent climate data have been well-stored and become available. In this study, we apply three types of neural networks, multilayer perceptron, recurrent, and convolutional, to daily average, minimum, and maximum temperature forecasting with higher-frequency input features than researchers used in previous studies. Applying these neural networks to the observed data from three locations with different climate characteristics, we show that prediction performance with highly frequent hourly input data is better than forecasting performance with less-frequent daily inputs. We observe that a convolutional neural network, which has been mostly employed for processing satellite images rather than numeric weather data for temperature forecasting, outperforms the other models. In addition, we combine state of the art weather forecasting techniques with the convolutional neural network and evaluate their effects on the temperature forecasting performances.
AB - Temperature forecasting has been a consistent research topic owing to its significant effect on daily lives and various industries. However, it is an ever-challenging task because temperature is affected by various climate factors. Research on temperature forecasting has taken one of two directions: time-series analysis and machine learning algorithms. Recently, a large amount of high-frequent climate data have been well-stored and become available. In this study, we apply three types of neural networks, multilayer perceptron, recurrent, and convolutional, to daily average, minimum, and maximum temperature forecasting with higher-frequency input features than researchers used in previous studies. Applying these neural networks to the observed data from three locations with different climate characteristics, we show that prediction performance with highly frequent hourly input data is better than forecasting performance with less-frequent daily inputs. We observe that a convolutional neural network, which has been mostly employed for processing satellite images rather than numeric weather data for temperature forecasting, outperforms the other models. In addition, we combine state of the art weather forecasting techniques with the convolutional neural network and evaluate their effects on the temperature forecasting performances.
KW - Convolution neural network
KW - Deep learning
KW - Long short term memory
KW - Temperature forecasting
UR - http://www.scopus.com/inward/record.url?scp=85082484260&partnerID=8YFLogxK
U2 - 10.3390/app10051609
DO - 10.3390/app10051609
M3 - Article
AN - SCOPUS:85082484260
SN - 2076-3417
VL - 10
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
IS - 5
M1 - 1609
ER -