Periodic Reporting for period 1 - SYNCHROMODE (Advanced traffic management solutions for synchronized and resilient multimodal transport services)
Reporting period: 2023-05-01 to 2024-10-31
The European transport sector faces congestion, safety risks, emissions, and inefficiencies, while emerging mobility solutions drive a shift in multimodal traffic management. Addressing these challenges requires a data-driven, integrated approach for efficiency, sustainability, and resilience. SYNCHROMODE is an EU-funded project that aims to develop appropriate ICT tools to enhance multimodal traffic management. It enables data-driven decision-making, helping transport managers balance supply and demand while proactively managing disruptions. By integrating predictive modeling, simulation, optimization, and data quality assessment, SYNCHROMODE enhances real-time monitoring and multimodal coordination across transport networks.
SYNCHROMODE brings together advanced methodologies in several key areas, including:
•Transport network supply and demand modelling to improve understanding of multimodal interactions.
•Simulation and prediction of future traffic states using AI-driven forecasting models.
•Optimization techniques for multimodal traffic management, ensuring network-wide efficiency.
•Standards for data collection, storage, and exchange, enabling seamless integration of various transport data sources.
•New governance models to enhance coordination among transport authorities, operators, and mobility service providers.
•Redefining key performance indicators (KPIs) for assessing the effectiveness of multimodal traffic management strategies.
•Advanced data quality assessment methodologies and imputation techniques, ensuring that real-time and historical transport data is complete, accurate, and reliable.
SYNCHROMODE provides the AI-powered SYNCHROMODE Toolbox, a suite of services that optimize multimodal transport management, enhancing coordination, efficiency, and resilience across urban and regional networks. The Toolbox includes:
1.Transport network-wide data exchange and integration system, ensuring reliable and real-time data sharing across transport stakeholders.
2.Cooperative dashboard for real-time monitoring and prediction, providing transport managers with insights into multimodal traffic conditions and expected network performance.
3.Resilient multimodal transport network and traffic management support tool, enabling operators to mitigate congestion, optimize multimodal flows, and respond effectively to disruptions (e.g. bottlenecks, accidents).
The SYNCHROMODE Toolbox will be validated in three real-world case studies in Thessaloniki (Greece), South Holland (the Netherlands), and Madrid (Spain). These regions provide a diverse set of transport conditions and challenges, enabling the testing and fine-tuning of the developed tools and services using real data from multiple transport modes. The project is transforming multimodal traffic management by shifting from a reactive approach, where interventions address existing congestion and disruptions, to a proactive approach that anticipates and mitigates traffic issues before they arise. Through AI-powered decision-support tools, predictive analytics, and real-time data fusion, SYNCHROMODE enables transport managers to optimize multimodal flows, improve coordination, and reduce disruptions.
SYNCHROMODE brings together advanced methodologies in several key areas, including:
•Transport network supply and demand modelling to improve understanding of multimodal interactions.
•Simulation and prediction of future traffic states using AI-driven forecasting models.
•Optimization techniques for multimodal traffic management, ensuring network-wide efficiency.
•Standards for data collection, storage, and exchange, enabling seamless integration of various transport data sources.
•New governance models to enhance coordination among transport authorities, operators, and mobility service providers.
•Redefining key performance indicators (KPIs) for assessing the effectiveness of multimodal traffic management strategies.
•Advanced data quality assessment methodologies and imputation techniques, ensuring that real-time and historical transport data is complete, accurate, and reliable.
SYNCHROMODE provides the AI-powered SYNCHROMODE Toolbox, a suite of services that optimize multimodal transport management, enhancing coordination, efficiency, and resilience across urban and regional networks. The Toolbox includes:
1.Transport network-wide data exchange and integration system, ensuring reliable and real-time data sharing across transport stakeholders.
2.Cooperative dashboard for real-time monitoring and prediction, providing transport managers with insights into multimodal traffic conditions and expected network performance.
3.Resilient multimodal transport network and traffic management support tool, enabling operators to mitigate congestion, optimize multimodal flows, and respond effectively to disruptions (e.g. bottlenecks, accidents).
The SYNCHROMODE Toolbox will be validated in three real-world case studies in Thessaloniki (Greece), South Holland (the Netherlands), and Madrid (Spain). These regions provide a diverse set of transport conditions and challenges, enabling the testing and fine-tuning of the developed tools and services using real data from multiple transport modes. The project is transforming multimodal traffic management by shifting from a reactive approach, where interventions address existing congestion and disruptions, to a proactive approach that anticipates and mitigates traffic issues before they arise. Through AI-powered decision-support tools, predictive analytics, and real-time data fusion, SYNCHROMODE enables transport managers to optimize multimodal flows, improve coordination, and reduce disruptions.
During the 1st reporting period, the consortium focused on developing the SYNCHROMODE Toolbox and advancing its key objectives.
Advancing Multi-Actor Cooperation Models (Objective 1)
•Nine workshops across the three case studies (Madrid, South Holland, Thessaloniki) and participation from over 150 stakeholders.
•Defined governance structures tailored to local needs, adapting the SOCRATES 2.0 framework for multimodal operations.
•Mapped roles, responsibilities, and decision-making structures for improving multimodal traffic management strategies.
Interoperable Data Solutions and Enhancing Data Quality (Objective 2)
•Developing algorithms for mobility pattern reconstruction from heterogeneous transport data sources, with validation against ground truth data.
•Creating the SYNCHROMODE Data Exchange Repository, enabling harmonized and efficient data sharing among partners.
•Implementing an advanced data quality assessment methodology, including imputation techniques for incomplete or inconsistent data.
Simulation-Based Assessment of Multimodal Traffic Strategies (Objective 3)
•A conceptual simulation architecture integrating demand-supply interaction models, optimization strategies, and predictive analytics.
•Evaluation of "What-If" scenarios (e.g. congestion due to city-wide events, emergency incidents, road disruptions).
AI-Based Optimization for Multimodal Transport Networks (Objective 4)
•Identification and formulation of six key optimization problems.
The SYNCHROMODE Toolbox (Objective 5)
•Completion of the reference and technical architecture.
•Development of dashboard mock-ups.
•Mapping interdependencies between modules ensuring seamless integration within the Toolbox.
Advancing Multi-Actor Cooperation Models (Objective 1)
•Nine workshops across the three case studies (Madrid, South Holland, Thessaloniki) and participation from over 150 stakeholders.
•Defined governance structures tailored to local needs, adapting the SOCRATES 2.0 framework for multimodal operations.
•Mapped roles, responsibilities, and decision-making structures for improving multimodal traffic management strategies.
Interoperable Data Solutions and Enhancing Data Quality (Objective 2)
•Developing algorithms for mobility pattern reconstruction from heterogeneous transport data sources, with validation against ground truth data.
•Creating the SYNCHROMODE Data Exchange Repository, enabling harmonized and efficient data sharing among partners.
•Implementing an advanced data quality assessment methodology, including imputation techniques for incomplete or inconsistent data.
Simulation-Based Assessment of Multimodal Traffic Strategies (Objective 3)
•A conceptual simulation architecture integrating demand-supply interaction models, optimization strategies, and predictive analytics.
•Evaluation of "What-If" scenarios (e.g. congestion due to city-wide events, emergency incidents, road disruptions).
AI-Based Optimization for Multimodal Transport Networks (Objective 4)
•Identification and formulation of six key optimization problems.
The SYNCHROMODE Toolbox (Objective 5)
•Completion of the reference and technical architecture.
•Development of dashboard mock-ups.
•Mapping interdependencies between modules ensuring seamless integration within the Toolbox.
SYNCHROMODE delivers data-driven multimodal traffic management solutions through four key innovations integrated into its Toolbox, enhancing network efficiency, coordination, analytics, and optimization. Significant progress has been made in:
1.Advanced KPIs for Multimodal Mobility Assessment
•Developed passenger-centric and system-wide indicators incorporating big data analytics for assess service accessibility, travel patterns, and multimodal coordination.
2.Enhanced Data Fusion for Multimodal Network Management
•Established a structured data exchange repository, ensuring seamless integration and harmonization of multimodal transport data.
•Developed data fusion techniques for traffic pattern reconstruction.
•Advanced methodologies for assessing and enhancing the quality of the multimodal transport data.
3.Predictive Modelling, Simulation, and Incident Detection
•Integrated machine learning with simulation models to enhance traffic state prediction, bottleneck identification, and incident detection.
•Developed a hybrid simulation-based and data-driven approach, improving the accuracy of demand and supply predictions across the case studies.
4.AI-Powered Transport Network Optimization
•Implemented model-based optimization and deep reinforcement learning to improve real-time transport decision-making.
•Designed and formulated six scalable optimization solutions.
1.Advanced KPIs for Multimodal Mobility Assessment
•Developed passenger-centric and system-wide indicators incorporating big data analytics for assess service accessibility, travel patterns, and multimodal coordination.
2.Enhanced Data Fusion for Multimodal Network Management
•Established a structured data exchange repository, ensuring seamless integration and harmonization of multimodal transport data.
•Developed data fusion techniques for traffic pattern reconstruction.
•Advanced methodologies for assessing and enhancing the quality of the multimodal transport data.
3.Predictive Modelling, Simulation, and Incident Detection
•Integrated machine learning with simulation models to enhance traffic state prediction, bottleneck identification, and incident detection.
•Developed a hybrid simulation-based and data-driven approach, improving the accuracy of demand and supply predictions across the case studies.
4.AI-Powered Transport Network Optimization
•Implemented model-based optimization and deep reinforcement learning to improve real-time transport decision-making.
•Designed and formulated six scalable optimization solutions.