Forecasting and analysing global average temperature trends based on LSTM and ARIMA models

Can Tan, Junyi Zhong, Dajun Yang and Weiming Huang

PLOS ONE, 2025, vol. 20, issue 9, 1-27

Abstract: Previous studies have demonstrated a significant correlation between global average temperature change trends and greenhouse gases, and employed various prediction models. However, the potential of the combination of the LSTM and ARIMA models for temperature forecasting has not been fully explored, especially in terms of enhancing prediction accuracy. Based on the hypothesis that COVID-19 has affected the global average temperature, this study utilizes global average temperature data from 1880 to 2022. We combine the LSTM model, which excels at capturing long-term dependencies, with the ARIMA model, known for its effectiveness in handling linear time series data, to predict the global mean temperature. This combination compensated for the limitations of individual models, providing a more accurate and comprehensive temperature forecast. Our findings reveal that the early trend of global temperature rise is significant, yet the implementation delay leads to severe issues. Moreover, COVID-19 has indirectly reduced greenhouse gas emissions, slowing global warming. Additionally, we find that the correlation between longitude and mean temperature is weak, while the correlation between latitude and temperature is strongly negative. This study offers valuable insights and provides a reliable prediction method for ecological environment governance and the formulation of economic construction policies.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0330645 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 30645&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0330645

DOI: 10.1371/journal.pone.0330645

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().