Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Spatio‐temporal patterns of the impact of COVID‐19 on public transit: An exploratory analysis from Lyon, France
Published in Regional Science Policy & Practice, 2023
This paper focuses on the impact of COVID-19, as a large scale and long-term disruption, on public transport demand.
Recommended citation: Cottreau, B., Adraoui, A., Manout, O., & Bouzouina, L. (2023). " Spatio-temporal patterns of the impact of COVID-19 on public transit: an exploratory analysis from Lyon, France." Regional Science Policy & Practice. DOI: https://doi.org/10.1111/rsp3.12718
Download Paper | Download Bibtex
Spatio-temporal impacts of unplanned service disruptions on public transit demand
Published in Transportation Research and Interdisciplinary Perspectives, 2025
This paper shows the impact of metro disruptions on public transport demand. It uses a Gaussian Mixture Model (GMM) to cluster the disruptions relative to the intensity of their impact, and shows what attributes are the most representative of each class using a MultiNomial Logit (MNL)
Recommended citation: Cottreau, B., Manout, O., & Bouzouina, L. (2025). "Spatio-temporal impacts of unplanned service disruptions on public transit demand." Transportation Research Interdisciplinary Perspective. DOI: https://doi.org/10.1016/j.trip.2025.101354
Download Paper | Download Bibtex
Resilience of public transport in the face of disruptions: Insights from explainable machine learning
Published in Transportation Research Part A: Policy and Practice, 2025
How to detect disruptions with fine-grained demand data? This work provides a fully interpretable modelling framework using tree-based learning.
Recommended citation: Cottreau, B., Celbiş, M.G., Manout, O., & Bouzouina, L. (2025). "Detection of subway service disruptions and contribution of alternative stops to public transit resilience." Transportation Research Part A: Policy & Practice. https://doi.org/10.1016/j.tra.2025.104550
Download Paper | Download Bibtex
talks
To what extent does public transit demand persist in the face of COVID-19? A case study from Lyon, France.
Published:
The presentation analyses the impacts of the COVID-19 pandemic on the public transport system of Lyon (France) based on smart card data. It evaluates concepts related to resilience and breaks down the impacts at different geographical scales. [Slides]
Transport Modelling
Published:
Introduction to transport modelling using bike-sharing data. (Load: 14h)
Statistics and Data Project
Published:
Review of the basic concepts of inferential statistics and application using R and RStudio. (Load: 16h)
Sustainable Mobility
Published:
Introduction to mobility and transport studies through the lens of economic, sociological and environmental analyses. (Load: 42h)
Improving public transit demand forecasting models in case of disruptions: an integrated approach using explainable AI
Published:
This talk presents an integrated approach using a module for disruption detection (Random Forest) and a demand forecasting module (LSTM) to better assess mobility behaviours in the event of disruptions. [Video]
From econometrics to machine learning: Insights from transportation studies
Published:
Econometrics is the field of economics which intends to unveil the decision-making process of individuals and firms: econometricians use statistical tools aiming to understand people’s choices and predict their behaviours. Using case studies coming from the transportation field, I will present the main limitations of the traditional econometric approach and identify where machine learning can bridge the gap. [Slides]
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.