Skip to main content

ORIGINAL RESEARCH article

Front. Environ. Sci.
Sec. Big Data, AI, and the Environment
Volume 12 - 2024 | doi: 10.3389/fenvs.2024.1362748
This article is part of the Research Topic AI and Data Analytics for Climate Data Management View all 8 articles

Predicting CO 2 Emissions in Morocco: Exploring the Use of Ridge Regression with Data Preprocessing and Feature Impact Analysis

Provisionally accepted
Yassine Dani Yassine Dani *Naoual Belouaggadia Naoual Belouaggadia Mustapha Jammoukh Mustapha Jammoukh
  • Université Hassan II Mohammedia, Mohammedia, Morocco

The final, formatted version of the article will be published soon.

    This study investigates the use of Ridge Regression (RR) for predicting CO2 emissions in Morocco, providing a comparative analysis with Lasso Regression, Elastic Net Regression, and Linear Regression models. The research leverages a comprehensive dataset encompassing various energy consumption and economic-demographic variables to develop an accurate predictive model and identify key contributing factors. The motivation for this study stems from the global urgency to mitigate climate change impacts and the specific need to understand emissions drivers in Morocco, a country undergoing rapid economic and industrial development. Accurately predicting CO2 emissions is crucial for informing policy decisions aimed at sustainable growth and environmental preservation. The RR model is trained on data spanning from 1965 to 2009 and validated on data from 2010 to 2021. Performance is assessed using Mean Squared Error (MSE), with the RR model achieving an MSE of 0.193, indicating superior accuracy compared to Elastic Net (4.852), Linear Regression (1.427), and Lasso Regression (4.577). Noteworthy coefficients are observed, with energy consumption variables showing significant impacts: the highest coefficient is 1.64E+00 (129%), and another key coefficient is 1.2E-01 (9.46%). The results underscore the pivotal role of energy consumption in driving CO2 emissions in Morocco. Furthermore, the RR model's performance and simplicity highlight its effectiveness, offering valuable insights for policymakers to devise targeted mitigation strategies. This study reinforces the potential of Ridge Regression as a powerful tool for environmental impact analysis and strategic planning in Morocco.

    Keywords: Ridge regression, CO2 emissions, energy consumption, economic-demographic variables, Morocco

    Received: 28 Dec 2023; Accepted: 26 Jun 2024.

    Copyright: © 2024 Dani, Belouaggadia and Jammoukh. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Yassine Dani, Université Hassan II Mohammedia, Mohammedia, Morocco

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.