Study of Global Temperature Levels Based on the ARIMA Model
DOI:
https://doi.org/10.54097/hset.v67i.11801Keywords:
Data Collection and Preprocessing, Independent-sample T-test, Seasonal Time Series.Abstract
The continuous growth of global carbon dioxide content has exacerbated global warming [1]. Based on this issue, this article mainly studies global temperature levels based on the ARIMA model. This article first uses data collection and preprocessing to determine whether the global temperature increase in March 2022 has led to a greater increase than the past 10 years. Then, ARIMA and seasonal ARIMA are established to describe the past and predict the future, predict the specific time when the average temperature reaches 20℃, and test the accuracy of the model. Finally, it is concluded that seasonal time series prediction is more accurate. For this study, this article first collects and completes the required temperature data for visual analysis. And independent sample t-tests were conducted on the two rising scenarios, and the results did not lead to a greater increase. Then the chapter describes the past data through the Run chart, and uses ARIMA and seasonal ARIMA to predict the future global temperature level [2]. Afterwards, this article adopts pre analysis on the data used and uses a predictive model to calculate the specific time to reach 20℃. The study found that the average temperature could not reach 20.00℃ in 2050 or 2100, but reached 20℃ in 3062. Finally, based on the data description and the characteristics of the data itself, this article demonstrates that seasonal ARIMA is more accurate.
Downloads
References
The US National Oceanic and Atmospheric Administration. The National Oceanic and Atmospheric Administration Earth Systems Research Laboratory. (October, 2022). Trend of carbon dioxide in the atmosphere.
Wang Yuanhao. Analysis of global air temperature prediction based on the ARIMA model and the LSTM neural network [J]. Science and Technology Innovation, 2021 (35): 166-170.
Xu Sichuan, Ma Xiyu, Zhou Tianhao, etc. Carbon emission CO_2 greenhouse effect mechanism [J]. Journal of Yunnan University (Natural Science Edition), 2023, 45 (02): 513-522.
The US National Oceanic and Atmospheric Administration. Research news and specialty articles in NOAA. (June 3, 2022). Carbon dioxide is now more than 50% higher than pre-industrial levels.
Snow White. Temperature prediction and heat heat wave warning analysis based on time series model and XGBoost combination [D]. Nanjing University of Information Science and Technology, 2021.
Dong Yanyan. Research on the construction of ARIMA-BiLSTM model in vegetable price prediction under different combination modes [D]. Dongbei University of Finance and Economics, 2022.
Yang Weikang, Qiao Jianfang, Gao Xingyi, Zhong Wenqin. Use of the rank-sum test in the analysis of bird habitat selection [J]. Drought Zone Study, 2001 (03): 42-44.
Wang Yan. Applied a time-series analysis [M]. Beijing: China Renmin University Press, 2005.
Hao Junzhang, Cui Yujie, Han Jiangxue. Passenger volume prediction based on ARIMA model in China [J]. The Practice and Understanding of Mathematics, 2015 (18): 10.
Wang Fang, Yu Lean, Zha Rui. Integrated prediction modeling of scale decomposition of electronic waste recovery driven by seasonal data characteristics [J]. Chinese Management Science, 2022, 30(03): 199-210.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
