GENERATE: Model-based generation of small-scale mobility demand data

Mobility demand, measured in terms of modal split and traffic volume, forms the data basis for a wide range of decisions in politics and public administration and is therefore a fundamental transport statistic. At the same time, the data situation in Austria—particularly at the municipal level, which is relevant for transportation policy—must be described as challenging: existing national data sources are severely limited in their spatial and temporal granularity, and state-level surveys are available only in Upper Austria, Salzburg, and Vorarlberg. For the majority of Austria, mobility demand at the municipal level is therefore neither known nor quantifiable. This complicates the targeted management of mobility patterns or the development of new mobility services, especially in the lower-tier network. In light of the climate crisis and the associated costs of inaction, it is also becoming increasingly important to improve the data situation regarding burden sharing. This includes a comprehensive metric for municipal mobility performance that makes the degree of achievement of transportation and climate policy goals quantitatively measurable and transparently highlights responsibilities that are perceived as lacking. In this way, effective measures, strategies, and control mechanisms can be informed by evidence.

GENERATE addresses this challenge and develops a novel approach to close these data gaps. By innovatively linking existing data sources, it enables the synthesis of comprehensive and frequently updated data layers on modal split and traffic volume at the municipal level. The methodological framework for this is based on the impact models of the predecessor projects ACTIV8! and ACTIV8II, which explain the municipal modal split using local and regional attributes. GENERATE stands out as the first systematic approach that creates genuine added value by integrating transportation and non-transportation data without requiring large-scale surveys. The self-learning GENERATE model enables the continuous integration of new data to improve and update the findings. The resulting data not only provide in-depth insights into mobility demand but also allow for the assessment of the effects of measures in transportation and environmental policy.

Although this approach is not intended to completely replace empirical surveys, it offers a cost-effective way to synthesize missing data at frequent intervals. Based on this data, locally and regionally tailored, user-oriented mobility services can be developed, and spatial and transportation planning can be better integrated to advance the core strategies of the mobility master plan: “Avoid” and “Shift.” To integrate the project results into real-world use cases, planning, and management processes, stakeholders from various groups are involved through concrete use cases and as members of the project advisory board. These include decision-makers from administration and politics at various federal levels, planners, providers of mobility services, stakeholders from the R&D sector, as well as umbrella organizations and the Federal Environment Agency as a key data provider for the mobility transition. The range of potential applications and the diverse interest in this project proposal demonstrate its relevance.