Forecasting Carbon Dioxide Emissions in the United States using Machine Learning

Namboori, Shreeya (2020) Forecasting Carbon Dioxide Emissions in the United States using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Climate change has been realized as a major concern worldwide and people along with the government are coming together to combat this worldwide issue to ensure that our future generation doesn't have to suffer. United States(U.S.) has been one of the top emitters of GHG (Green House Gas) emissions for a long time, although the emissions have been decreasing. Carbon dioxide(CO2 ) is a major GHG gas that makes up 80% of the GHG emissions. Therefore the reduction of CO2 emissions will help in reducing GHG emissions produced by the U.S. per year. The data for monthly C02 emission is taken from the U.S. Energy Information Administration (EIA). The analysis of the pre-processed data reveals three highly CO2 emitting sectors that are Coal Electric Power Sector, Natural Gas Electric Power Sector, and Total Energy Electric Power Sector. The emissions from these three sectors are used by ARIMA, SVM, SVM-PSO, and Prophet models for forecasting CO2 emissions. The performance of the models are compared with each other using RMSE, MAE and MAPE metric and the results show that the Prophet model outperforms all the other models in forecasting CO2 emissions from different sectors. Therefore the Prophet model is used for forecasting future emissions for the next 36 months for all three sectors.
Keywords : SVM, SVM-PSO, ARIMA, PROPHET, GHG , Carbon dioxide

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	11 Jun 2020 09:46
Last Modified:	11 Jun 2020 09:46
URI:	https://norma.ncirl.ie/id/eprint/4268

Actions (login required)

View Item