Predictive analytics of CO2 emission from agri-food activities using aachine learning
Authors
Ragashetti, Sandesh
Issue Date
2024-08-27
Degree
MSC in Information Systems with Computing
Publisher
Dublin Business School
Rights holder
Rights
Items in eSource are protected by copyright. Previously published items are made available in accordance with the copyright policy of the publisher/copyright holder.
Abstract
Global warming, Climate change, and Human health are getting impacted due to excessive agri-food emissions. Hence, the predictive analysis of CO2 emissions from agri-food activities is important for policymakers and researchers to develop strategies for sustainable agricultural practices. This study collected and explored secondary historical data on agri-food CO2 emissions in various countries around the world for a time span of 30 years (1990–2020) with machine learning techniques. Since previous research studies left a gap in predicting emissions from the agri-food sector and corresponding temperature rise, this project explores this area by implementing the four predictive models Linear Regression, Decision Trees, Random Forests, and Neural Networks. As a result, exploratory data analysis helps to understand the descriptive statistics, and data visualizations on agri-food activities, emissions, temperature rise, and their relationships. The four predictive models are trained and measured with metrics like MSE, RMSE, MAE, and R-squared. The Linear Regression model emerged as the best model with the highest predictive accuracy, with the lowest RMSE (1.55e-11), MAE (8.37e-12), and highest R2-score (1.00) for CO2 emissions. The study concludes that Linear Regression can serve as a robust tool in predicting CO2 emissions from agri-food activities and helps the policymakers, government bodies, and sustainable environment by providing useful insights and strategies to reduce the environmental impact of agriculture.