Global temperature prediction based on SARIMA+LSTM model

Wuzhe Huang; Fa Si; Feifei Han; Jiahao Liu; Jingshi Zheng; Yuwen Wei

doi:10.1117/12.2686399

28 July 2023 Global temperature prediction based on SARIMA+LSTM model

Wuzhe Huang, Fa Si, Feifei Han, Jiahao Liu, Jingshi Zheng, Yuwen Wei

Proceedings Volume 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023); 127563R (2023) https://doi.org/10.1117/12.2686399
Event: 2023 3rd International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC 2023), 2023, Tangshan, China

Abstract

After the Industrial Revolution, global temperatures generally began to rise. With global warming as the background, this paper builds a forecast model of future temperature, studies to determine whether the temperature rise in March 2022 leads to a larger rise, and builds more than two models to predict the temperature and evaluate the model. SARIMA(1,1,1)(1,1) model and LSTM model were established for temperature prediction. The study found that the temperature will not reach 20°C in either 2050 or 2100, and the global average temperature is expected to reach 20°C around 2180. Through model evaluation, the r square of SARIMA model is 0.87, and the accuracy of LSTM model is 0.783. Therefore, we think the SARIMA model is superior.

Citation Download Citation

Wuzhe Huang, Fa Si, Feifei Han, Jiahao Liu, Jingshi Zheng, and Yuwen Wei "Global temperature prediction based on SARIMA+LSTM model", Proc. SPIE 12756, 3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023), 127563R (28 July 2023); https://doi.org/10.1117/12.2686399

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available