Data from public transport systems are a crucial component of environmentally sensitive mobility management. Timetable and real-time information, combined with operational data, support not only digital passenger information services but also traffic simulations, AI-based forecasting and adaptive traffic management strategies. Through practical applications in Leipzig and Landau in der Pfalz, the AIAMO research project demonstrates how the intelligent integration of public transport, traffic and environmental data can unlock new opportunities for efficient and environmentally sensitive mobility management.

Public transport forms the backbone of sustainable urban mobility. Buses, trams and rail services efficiently accommodate large passenger volumes, significantly reducing both emissions and land consumption. At the same time, public transport plays a central role in multimodal mobility systems, enabling pedestrians and travellers with bicycles or e-scooters to use the same transport services, while private motorised transport and shared mobility offerings can be interconnected through Park-and-Ride facilities.

To ensure that these systems operate reliably, data-driven and environmentally sensitive mobility management is becoming increasingly important. Timetable, operational and real-time forecast data generated by transport operators provide valuable information for traffic management as well as digital applications such as traffic simulations and AI-based forecasting models. The effective use of these applications depends on the availability of standardised data.

Public transport offers considerable potential for reducing transport-related emissions. Owing to the high carrying capacity of buses and rail vehicles, emissions per passenger can be significantly lower than those associated with private motor vehicles, particularly when occupancy rates are high. To fully realise this potential, public transport must be systematically integrated into traffic management measures. Decisions concerning speed regulations, traffic routing and traffic signal control have a direct impact on the operational performance of bus and tram services.

However, the attractiveness of public transport depends largely on service quality. Key factors include the accessibility of stops and stations, service frequency and operational reliability. Delays, service cancellations and long headways can substantially reduce the attractiveness of public transport and encourage passengers to switch to private vehicles. To minimise delays, targeted priority measures for public transport vehicles—such as traffic signal priority or dedicated lanes—can help stabilise journey times and improve overall system reliability.

Digitalisation has also transformed public transport operations. Passenger information is now predominantly delivered through digital channels, including mobile applications, web-based journey planning systems and dynamic passenger information displays at stops and stations. These systems rely on extensive datasets covering routes, stops, timetables and current operational conditions.

For transport planners, timetable data also provide an important basis for analysing service quality. The standardisation of these datasets is of critical importance, as only harmonised data structures enable demand analyses, service planning and real-time journey information to be integrated, exchanged and published across operator and regional boundaries. A key element of this standardisation is the precise geographical referencing of stops and stations. By assigning accurate geospatial coordinates, stops can be displayed on digital maps and incorporated into automated routing systems.

In Germany, standardised timetable data are provided, among others, via the DELFI e. V. platform (Durchgängige Elektronische Fahrgastinformation). These data are available in formats such as GTFS (General Transit Feed Specification) and NeTEx (Network Timetable Exchange). GTFS has established itself internationally as a de facto standard for timetable data and contains fundamental information on routes, stops, and arrival and departure times. NeTEx, by contrast, enables a more detailed description of the vehicles in operation, transport networks and underlying operational structures.

In addition to static timetable data, real-time information is becoming increasingly important. On-board computers in vehicles capture positional and temporal data and compare them with the scheduled timetable. Deviations from scheduled performance are then reported to passenger information systems as real-time predictions. Current forecasts for departures, delays or service disruptions are continuously updated during operations, thereby enabling dynamic journey planning (see Fig. 1).

The importance of real-time predictions is increasing—but does the quality of these forecast messages improve at the same rate? Comparing forecast data with ground-truth operational data from on-board systems, which record actual arrival and departure times, enables an assessment of forecast accuracy.

Within the AIAMO research project, real-world data from Leipziger Verkehrsbetriebe (LVB) are used to analyse the accuracy of real-time predictions. The results show that deviations are typically within a tolerance range of approximately one minute, although in some cases significantly larger discrepancies occur. Using AI-based methods, such deviations can be systematically analysed and classified. These enriched and modelled datasets are then integrated into the AIAMO system via the integration layer of AIAMOnexus. The AIAMOnexus links data sources from multiple domains—including local air quality sensors, traffic counting systems, floating car data and weather forecasts—and prepares them for use in advanced AI applications.

The development of digital twins of transport systems represents a key application of mobility data for environmentally sensitive mobility management in urban areas. In such systems, the real-world transport network is replicated in a simulation that is continuously updated with live data.

Within the AIAMO project, the German Aerospace Centre (Deutsches Zentrum für Luft- und Raumfahrt e. V., DLR) uses timetable and real-time information to integrate public transport into traffic simulations such as SUMO (Simulation of Urban Mobility). This enables buses and rail services to be represented as active participants in the analysis of the overall transport system. Simulation tools such as SUMO make it possible to assess different scenarios, including the impact of construction works, changes in traffic regulations or large-scale events on traffic flow and network utilisation. Such simulations allow the ex ante evaluation of measures affecting private transport and their implications for public transport operations.

Another application of data-driven traffic management is the prediction of traffic-relevant events within the transport network. In particular, level crossings with barriers can, once closed, create congestion situations affecting both private transport and bus services (see Fig. 2).

In the AIAMO pilot region of Landau in der Pfalz, timetable and real-time data from regional rail services are combined with traffic count data from road traffic control systems in order to forecast barrier closures and assess their impact on traffic flow. Traffic control systems, such as traffic signal installations, can then be adjusted to reduce congestion and stabilise traffic conditions.

In the AIAMO project, public transport timetable and real-time data are combined with traffic count data from road traffic control systems, including inductive loop detectors embedded in the carriageway. On this basis, barrier closures can be predicted using AI methods when they become relevant for traffic management. Relevance is determined by the current network load in the affected area. The objective is to enable timely adjustments to traffic signal control in order to improve traffic flow and air quality.

Digital data from public transport are increasingly becoming a central resource for transport planning and environmentally sensitive mobility management. Timetable data, real-time information and operational datasets from transport operators enable detailed analysis, simulation and situation-based forecasting. At the same time, a mutual interaction between private transport and road-based public transport is evident. For a realistic assessment of transport systems, additional data sources such as traffic count data or floating car data are therefore required.

By integrating these heterogeneous data sources, complex traffic processes can be modelled and represented in digital twins, which, combined with data-driven forecasting and intelligent traffic management systems, can further enhance the reliability and performance of public transport. Ultimately, the AIAMO research project demonstrates that environmentally sensitive and intermodal mobility management in cities and municipalities can only be achieved through the availability of data from all areas of urban infrastructure. Within this system, public transport data form a central pillar.

The AIAMO research project combines the latest advances in artificial intelligence (AI) with concrete, practical applications in the field of intermodal and multimodal mobility. It aims to use mobility data efficiently to optimise traffic management in urban and rural areas, minimise CO₂ emissions while improving quality of life for citizens. AIAMO develops and applies AI models for the analysis and optimisation of mobility data. By integrating previously unused datasets and intelligently linking and analysing them, new opportunities for sustainable mobility are created.

The project is funded by the German Federal Ministry for Digital and State Modernisation (Bundesministerium für Digitales und Staatsmodernisierung, BMDS) with €16.7 million. The consortium, led by ITS Germany e. V., brings together 14 partners from science, research and industry—including T-Systems, Theis Consult, Fraunhofer IML, Bosch, the German Aerospace Centre (DLR), the Helmholtz Centre for Environmental Research, highQ, FKFS, TEQYARD, Yunex Traffic, SWARCO, and Schlothauer & Wauer—to develop innovative solutions addressing both urban and rural mobility needs.