CO2 Emissions and Road Traffic in Paris: Study, Modelling and Visualisation for a Better Environmental Understanding

Abstract

The environmental impact of human activities is a major problem in today's society, attracting increasing attention in the world of research. Among these activities, road traffic stands out for its significant contribution to greenhouse gas emissions, particularly carbon dioxide (CO2). These emissions play a crucial role in global warming, which is why it is so important to understand and quantify them. We have conducted an in-depth study to estimate CO2 emissions from road traffic in the Paris metropolitan area and developed an intuitive visualization tool for these data. Our ultimate goal is to develop an eco-friendly navigation application guiding users along the most ecological routes. For this, we are planning to implement a hybrid deep learning (CNN-LSTM) model [16], whose architecture was outlined in our previous work. This model aims to use both historical and real-time traffic data for predictions. Yet, understanding the factors affecting CO2 emissions on Paris streets, and how traffic reshapes these emissions, is an essential preliminary step. This article focuses on our algorithm for estimating CO2 emissions in relation to road traffic in Paris. This in-house developed algorithm is used to generate data that we then analyse and visualise to derive meaningful information. We describe in detail the process of creating this algorithm: from the definition of the input parameters, through the various stages of calculation, to the management of the challenges associated with its construction.

However, the purpose of our prediction model is to provide more accurate interpretations of the data generated using our algorithm. Additionally, data visualization tools are crucial to make this information understandable and actionable. In order to better understand this data, we are using several types of visual representation. We will also show how these generated estimates are integrated into our visualisation application, providing users with an intuitive visual representation of the distribution of CO2 emissions along the different roads in the city. Finally, we will discuss how our visualisation tool can be improved to enhance the user experience, improve understanding of the data and raise awareness of the environmental footprint of urban traffic.