Regression Analysis using Machine Learning Algorithms to Predict CO2 Emissions

• Published in: 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom) pp. 444 - 448
• Main Authors: Joshy, Lida Anna, Sambandam, Rakoth Kandan, Vetriveeran, Divya, Jenefa, J.
• Format: Conference Proceeding
• Language: English
• Published: Bharati Vidyapeeth, New Delhi 28.02.2024
• Subjects: Analytical models; CO; Data models; Data preprocessing; Emission Control; k-NN; Machine Learning; Machine learning algorithms; Prediction algorithms; Predictive models; Random Forest; Training
• DOI: 10.23919/INDIACom61295.2024.10499094

Precise measurement of fuel consumption and emissions plays an important role in evaluating the environmental effects of materials and stringent emission control methods, especially within the transportation sector. This sector represents a substantial contributor to both global greenhouse gas emissions and the release of hazardous pollutants, making accurate assessment imperative for addressing climate change. The primary objective is to construct accurate predictive models that estimate CO 2 emissions based on vehicle attributes, fostering a deeper understanding of the environmental impact of vehicular activities. Leveraging the "CO 2 Emissions_Canada.csv" dataset, the paper embarks on an extensive journey of data preprocessing, exploratory data analysis, and model training. These algorithms are meticulously fine-tuned and evaluated through metrics such as R-squared and mean absolute percentage error, rendering insights into their predictive accuracies. In essence, this paper pioneers a pathway towards environmentally responsible mobility solutions, capitalizing on the fusion of data science and environmental conservation.