A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Transportation Engineering

Thesis (M.Eng.) - Asian Institute of Technology, 2023

The Autoregressive Integrated Moving Average (ARIMA) model is a forecasting technique for time-series data and finds extensive application in various fields.However, its potential for forecasting and estimating greenhouse gas (GHG) emissions within academic institutions warrants further exploration. This study aims to address this gap with two primary objectives: firstly, to analyze the GHG emissions for transportation, including both land and air travel, for the baseline year 2022, and secondly, to compare the emissions from land transportation for AIT's offline and online classes during the COVID-19 pandemic.Initially, the study assessed GHG emissions from land and air travel for the baseline year 2022, employing the IPCC bottom-up approach and quantitative calculations.Following this, the ARIMA model was trained using historical data up to the end of 2019, a period characterized by regular offline classes and the absence of COVID-19 pandemic influences. This trained model was used to forecast emissions for 2020 and 2021 under the assumption of continued offline classes.The comparison of forecasted emissions assuming offline classes (100 tons of CO2eq) with actual emissions during the implementation of online classes (40 tons of CO2eq) due to the COVID-19 pandemic revealed a significant decrease in emissions over two years 2020 and 2021.In examining the influence of the transition to online classrooms and other pandemic related adjustments, this study demonstrates the ARIMA model's applicability in projecting GHG emissions in academic institutions. It provides insights into the pandemic's impact on emission trends. The findings of this research can contribute significantly to the academic community's understanding of GHG emissions and offer invaluable implications for the development of sustainable policies and practices in the context of unforeseen disruptions such as a pandemic.