Making bikes count for climate and health

Cycling is crucial for public health, improving air quality, and promoting sustainable urban living. But cycling volume data is often scarce, as most cities rely only on a few isolated counting stations. In a new study, PhD candidate Silke Kaiser, Assistant Professor of Computer Science and Public Policy Lynn Kaack (Data Science Lab/Centre for Sustainability), and Nadja Klein (Karlsruhe Institute of Technology) examine how limited bicycle traffic data can be used to predict street-level cycling volumes across entire cities.

Despite the growing importance of traffic data for urban planning, data on bicycle volume remains underexplored. Kaiser and Kaack’s study tackles this gap by applying machine learning to diverse data sources – including counting station data, newly available data such as crowdsourced cycling, and bike-sharing data, as well as traditional indicators such as infrastructure and weather – to estimate bicycle volumes across Berlin.

Kaiser explains, “For locations without direct cycling counts, combining machine learning models with multi-source data allows us to predict cycling volumes with a very reasonable margin of error.” The study also finds that short-term sample counts can be beneficial for even more precise estimates: “With just ten days of sample counts per location, we can further halve the margin of error.”

These estimates support evidence-based decisions on infrastructure improvements, enabling policymakers to prioritise high-traffic areas and justify investments in cycling networks. While the research focusses on Berlin, its insights are applicable to cities worldwide. As urban areas strive for sustainability, data-driven approaches like these can guide planning, ensuring resources are allocated where they have the most significant impact.

The article, titled “From counting stations to city-wide estimates: Data-driven bicycle volume extrapolation”, was published in Environmental Data Science. The publication received funding from the European Union’s Horizon Europe research and innovation programme under Grant Agreement number: 101057131 — CATALYSE — HORIZON-HLTH-2021-ENVHLTH-02

You can read the full paper here

The Hertie School is not responsible for any content linked or referred to from these pages. Views expressed by the author/interviewee may not necessarily reflect the views and values of the Hertie School.