Smart Tourism Evaluation, Prediction and Sustainable Development - STEPS
Project Description
This interdisciplinary project, STEPS, aims to foster sustainable tourism in alpine regions by integrating data-driven analysis and human geography. Using pilot destinations, the project seeks to monitor and predict visitor flows, assess their impact on local resources, and support informed decision-making through digital tools. By combining qualitative geographic analyses with computational techniques, the project addresses data gaps and institutional challenges, ultimately providing practical solutions for local stakeholders.
At CDS Group, we focus on predicting and simulating mobility flows over entire transport systems, which include multiple transport modes and the use of diverse and distributed data sources. A key area is the development of machine learning techniques—especially distributed learning—to overcome challenges such as data sparsity, privacy constraints across stakeholders, and the fusion of heterogeneous datasets [1-3]. These prediction models form the basis for digital twin applications, which simulate real-world mobility systems and enable the evaluation of future scenarios and intervention strategies in a virtual environment. Digital twins are designed to support data-driven decision-making for the case studies [4]. It also offers a dynamic and visual representation of the transport and tourist system.
Potential thesis topics include:
• Distributed learning for mobility prediction
• Data fusion of distributed multimodal transport data
• Digital twin modeling of multimodal transport systems for scenario planning
References:
[1] C. Li and W. Liu, ‘Multimodal Transport Demand Forecasting via Federated Learning’, IEEE Trans. Intell. Transport. Syst., vol. 25, no. 5, pp. 4009–4020, May 2024, doi: 10.1109/TITS.2023.3325936.
[2] Y. Liang, G. Huang, and Z. Zhao, ‘Joint demand prediction for multimodal systems: A multi-task multi-relational spatiotemporal graph neural network approach’, Transportation Research Part C: Emerging Technologies, vol. 140, p. 103731, Jul. 2022, doi: 10.1016/j.trc.2022.103731.
[3] A. I. Subah, S. T. Quadir, T. R. Rhythy, and A. Raihan, ‘A Systematic Review on Forecasting Passenger Flows of Multimodal Transportation System Integrating Metro’, 2024.
[4] D. Wu et al., ‘Digital Twin Technology in Transportation Infrastructure: A Comprehensive Survey of Current Applications, Challenges, and Future Directions’, Applied Sciences, vol. 15, no. 4, p. 1911, Feb. 2025, doi: 10.3390/app15041911.