A Deep Learning-Based Weather Forecast System for Data Volume and Recency Analysis
Jarrett Booz, Wei Yu, Guobin Xu, David W. Griffith, Nada T. Golmie
Accurate weather forecast is important to our daily life. Through physical atmospheric models, the weather can be accurately forecasted in a short period time. To provide weather forecast, machines learning techniques can be used for understanding and analyzing weather patterns. In this paper, we propose a deep learning-based weather forecast system and conduct data volume and recency analysis by utilizing a real world weather data set. By using Python Keras library and Pandas library, we implement the proposed system. The Keras Sequential model is the deep learning model in our system to learn and predict the weather data. Based on the system, we find out not only the relationship between the prediction accuracy and data volume, but also the relationship between the prediction accuracy and data recency. Through extensive evaluations, our results show that more data is beneficial to increasing the accuracy of a trained model. In addition, our finding shows that the recency of the data does not have a consistently significant impact on the accuracy of the trained model. These results are validated by using data from five different geographical regions of the United States.
International Conference on Computing, Networking and Communications (ICNC 2019)
, Yu, W.
, Xu, G.
, Griffith, D.
and Golmie, N.
A Deep Learning-Based Weather Forecast System for Data Volume and Recency Analysis, International Conference on Computing, Networking and Communications (ICNC 2019), Honolulu, HI, [online], https://doi.org/10.1109/ICCNC.2019.8685584
(Accessed September 23, 2021)