Advanced Transportation Demand Modeling: Generating an Enriched Synthetic Population from Dynamic Data

With the rise of new technologies and the rapid evolution of transportation modes, understanding mobility behaviors becomes a significant challenge to optimize infrastructure, anticipate transportation demand, and guide public policies. However, traditional approaches struggle to capture the diversity and dynamics of transportation flows, hence the need to rethink their modeling. This thesis aims to develop an innovative approach to generate an enriched synthetic population, intelligently integrating various sources of more recent dynamic data. This advancement will allow a better understanding of individual movements and anticipate urban and interurban mobility changes. The main research steps include:
1.    Analysis of existing approaches: Study current transportation demand modeling methods and identify their limitations.
2.    Exploration of data sources: Inventory and analyze dynamic data (GPS traces, traffic counts, transport ticket validations, etc.) to extract mobility patterns (Origin/Destination, trajectories, flows).
3.    Comparison with mobility surveys: Compare these dynamic data with surveys to identify discrepancies and biases.
4.    Correction of discrepancies: Propose a method to correct/adjust these gaps between dynamic data and traditional surveys.
5.    Enrichment of the synthetic population: Develop an approach based on data fusion or deep learning to refine the representation of individuals and their mobility behaviors.
6.    Comparative evaluation: Compare the results obtained with classical methods based on relevant performance indicators.
 

IFP Energies nouvelles is a French public-sector research, innovation and training center. Its mission is to develop efficient, economical, clean and sustainable technologies in the fields of energy, transport and the environment. For more information, see our WEB site. 
IFPEN offers a stimulating research environment, with access to first in class laboratory infrastructures and computing facilities . IFPEN offers competitive salary and benefits packages.  All PhD students have access to dedicated seminars and training sessions. 
 

Academic requirements    University Master degree or engineering diploma in Transport, Computer Science, Applied Mathematics, or Economics      
Language requirements    English level B2 (CEFR)     
Other requirements    Transport systems modeling, Data analysis, Python/R