Bahman Madadi

Bahman Madadi

(he/him)

Assistant Professor

Université Gustave Eiffel

ENTPE

Professional Summary

Assistant Professor at Université Gustave Eiffel & ENTPE within the EMob-Lab (Energy & Mobility Laboratory), where I am the Principal Investigator and Coordinator of the GREENSHIFT project—an ANR JCJC personal research grant awarded by the French National Research Agency to pioneer sustainable multimodal mobility hub networks. My research focuses on learning-based optimization in transport and energy, specifically enabling seamless zero-emission multimodal mobility. I specialize in Graph Neural Networks, Deep Learning, and Operations Research to solve complex problems in transport network design, traffic simulation, and geospatial data analysis. I serve as Associate Editor of Transportation Engineering (Elsevier), a journal dedicated to advancing open and reproducible research in transportation science, and on the Steering Committee of the RERITE Working Group, advancing reproducible research practices in transportation engineering.

Education

PhD, Transportation Science & Technology

Delft University of Technology

MSc, Industrial and Systems Engineering

Istanbul Sehir University

BSc, Industrial Engineering

Istanbul Sehir University

Interests

Graph Neural Networks Deep Learning Transport Network Design Optimization & Operations Research Intelligent Transportation Systems Geospatial Data Analysis Explainable Graph Neural Networks AI Foundation Models on Geospatial Domain Zero-Emission Mobility
Featured Publications
A Discrete Event Simulation of Teleoperated Driving in Road Freight Transport: The Fleet Sizing Problem featured image

A Discrete Event Simulation of Teleoperated Driving in Road Freight Transport: The Fleet Sizing Problem

Teleoperated driving (TOD) enables humans to operate vehicles remotely during challenging scenarios, offering a promising transition path toward full automation in freight …

avatar
Bahman Madadi
•
A hybrid deep-learning-metaheuristic framework for bi-level network design problems featured image

A hybrid deep-learning-metaheuristic framework for bi-level network design problems

This paper presents a novel hybrid framework combining deep learning with metaheuristic optimization to solve bi-level network design problems. Traditional optimization approaches …

avatar
Bahman Madadi
•
Design and Optimization of Road Networks for Automated Vehicles featured image

Design and Optimization of Road Networks for Automated Vehicles

This PhD dissertation addresses the design and optimization of road networks to accommodate automated vehicles (AVs). The research develops methodologies for network-level …

avatar
Bahman Madadi
•
Optimizing Road Networks for Automated Vehicles with Dedicated Links, Dedicated Lanes, and Mixed-Traffic Subnetworks featured image

Optimizing Road Networks for Automated Vehicles with Dedicated Links, Dedicated Lanes, and Mixed-Traffic Subnetworks

This research explores different infrastructure strategies for integrating automated vehicles into existing road networks, comparing three approaches: dedicated links (entire roads …

avatar
Bahman Madadi
•
A bi-level model to optimize road networks for a mixture of manual and automated driving: An evolutionary local search algorithm featured image

A bi-level model to optimize road networks for a mixture of manual and automated driving: An evolutionary local search algorithm

This paper presents a bi-level optimization model and evolutionary local search algorithm for optimizing road networks during the transition period when both manual and automated …

avatar
Bahman Madadi
•
Recent Publications
(2026). A Discrete Event Simulation of Teleoperated Driving in Road Freight Transport: The Fleet Sizing Problem. Transportation Research Interdisciplinary Perspectives.
(2025). Scenarios of automated driving based on a switchboard for driving forces - an application to the Netherlands. EJTIR, 25, 24–44.
(2024). A hybrid deep-learning-metaheuristic framework for bi-level network design problems. Expert Systems with Applications, 243, 122814.
(2021). Multi-stage optimal design of road networks for automated vehicles with elastic multi-class demand. Computers and Operations Research, 136.
Recent Talks
A Framework for Road Authorities to Assess Their Readiness to Support Connected and Automated Driving featured image

A Framework for Road Authorities to Assess Their Readiness to Support Connected and Automated Driving

Framework for assessing road authority readiness for CAV support

I Guy
•
Exploring Artifacts Availability in Transportation Research Using Large Language Models featured image

Exploring Artifacts Availability in Transportation Research Using Large Language Models

Using LLMs to explore artifact availability in transportation research

J Ji
•
Explainable Graph neural networks for traffic assignment and road network design featured image

Explainable Graph neural networks for traffic assignment and road network design

Conference presentation on explainable GNNs for network design

avatar
Bahman Madadi
•
A hybrid deep-learning-metaheuristic framework for bi-level network design problems featured image

A hybrid deep-learning-metaheuristic framework for bi-level network design problems

Presentation on hybrid DL-metaheuristic approach to network design

avatar
Bahman Madadi
•
A connected and automated vehicle readiness framework to support road authorities for C-ITS services featured image

A connected and automated vehicle readiness framework to support road authorities for C-ITS services

Framework for road authorities to assess CAV readiness for C-ITS services

avatar
Bahman Madadi
•