Forecasting annual CO₂ emissions in Vietnam using ARIMA; Holt-Winters exponential smoothing models

This study uses time series modeling approaches, notably Autoregressive Integrated Moving Average (ARIMA) and Holt-Winters models, to forecast Vietnam’s annual CO 2 emissions. Historical emissions data were examined to find patterns and forecast future emissions over the following five years. The Holt-Winters seasonal model ( α, β, γ = 0.995, 0.142, 0.001) offered marginally better accuracy with a Mean Absolute Percentage Error (MAPE) of 18.65%. In contrast, the ARIMA ( p, d, q = 3, 3, 2) model successfully reproduced the historical trends with MAPE of almost 26%. According to both estimates, CO 2 emissions would climb significantly, highlighting the urgent need for sustainable behaviors and efficient climate legislation to lessen the increasing environmental impact. Future research will use sophisticated modeling approaches and explanatory variables to improve forecast reliability.