Energy use and CO2 emissions of the Moroccan transport sector

Hasnaa Oubnaki, Charifa Haouraji, Badia Mounir, Ilham Mounir, Abdelmajid Farchi


In this paper, optimized models based on two different machine learning (ML) methods were developed to forecast the transport energy consumption (TEC) and carbon dioxide (CO2) emissions in Morocco by 2030. More precisely, artificial neural networks (ANN) and support vector regression (SVR) were used for modelling non-linear TEC and CO2 emissions data. This study uses data from 1990 to 2020 and employs various independent parameters, including population, gross domestic product, urbanization rate, evolution of the number of vehicles, and the number of electric vehicle introductions. Four statistical metrics are derived to assess the effectiveness of the ML algorithms used. The forecasts for 2030 were based on six scenarios, including three scenarios for the growth of gross domestic product (GDP) and two scenarios for the evolution of electric cars’ introduction into Moroccan vehicle fleet. The ANN model outputs showed that a decrease in TEC and CO2 emissions is expected until 2030. However, the SVR model predicts outputs values close to those in 2020. The study's results also indicate that: i) TEC and transport CO2 emissions are positively impacted by economic growth in Morocco and ii) electric vehicles will be essential components enabling substantial reductions in overall CO2 emissions in future transport systems.


CO₂ emissions; Forecasting; Machine learning; Morocco; Transport energy use

Full Text:



Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578

This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).