Time Series Analysis of Greenhouse Gas Emission Based on ARIMA and LSTM

Abstract

Greenhouse gas emissions have become a topic of great concern, and research on the prediction of greenhouse gas emissions is urgently needed. In this paper, based on the GHG emission data from 1990-2018, it applied ARIMA model and LSTM model to predict future GHG emissions, and evaluated their prediction performance using MAE. According to the analysis, the results show that the ARIMA model can more accurately capture the trend and seasonal characteristics in the greenhouse gas emission data, and generate prediction results that match the actual observations. Moreover, this study confirmed the effectiveness and feasibility of ARIMA and LSTM models in greenhouse gas emission prediction. At the same time, one must also be aware that greenhouse gas emission forecasts still face limitations such as data reliability, model assumptions, and policy uncertainties. Future research can further improve model performance and explore more comprehensive predictive models to improve accuracy. Overall, these results shed light on guiding further exploration of gas emission analysis.