Author Archives: misz

BikeNetKit launched for designing bicycle networks

We just launched bikenetkit.org – the platform visualizing our free, open-source Python tools for designing well-connected bicycle infrastructure. The platform covers 412 cities in Europe – Check it out!

After 8 years of researching the topic together with 17 amazing collaborators, and a year of focused programming by Manuel, Michael, and several other NERDS / ex-NERDS including Anastassia, Carlson, Clément, Mariana, and web/viz development by renown Data Design expert Moritz Stefaner / Truth & Beauty as part of the Innovation Explorer grant we won last year and the EU project JUST STREETS, our platform BikeNetKit is now online and ready for use.

See ITU’s promo video:

And our short explainer:

BikeNetKit is a collection of free, open-source Python software tools to help plan and develop bicycle networks, developed collaboratively at github.com/BikeNetKit. It turns our past 8 years of research efforts into polished software tools. Urban planners and citizens can run them on their own city with their own data, exploring many scenarios to make safe cycling happen.

The kit comes for now with 5 tools packaged as Python libraries: GrowBikeNet, LinkBikeNet, FixBikeNet, SortBikeNet, and superblockify. Further, it comes with BikeNetLib which offers general utilities for researching or working with bicycle networks.

For BikeNetLib we have also set up our own overpass server with the added side-effect of facilitating university education for geospatial data science at ITU and elsewhere.

We are happy if BikeNetKit grows into a wider community effort from the bicycle network/mobility/urbanist community. If you would like to contribute, have a look at: https://github.com/BikeNetKit

Even just trying it out and giving us feedback is very helpful. If you like this project, you can help us by following BikeNetKit on LinkedIn, Mastodon, Bluesky, or Youtube, and feel free to tell your urban planners and politicians about it.

Thanks for spreading the word, and enjoy the ride! 🚲

NERDS / BikeNetKit at the Digital Tech Summit

Yesterday, Michael presented at the Digital Tech Summit our ongoing innovative efforts for BikeNetKit, the bicycle network planning and visualization platform which launches on Monday at bikenetkit.org

The Digital Tech Summit is Denmark’s largest AI and digital transformation expo with hundreds of participants. Michael’s talk and live demo was titled “BikeNetKit: Open Bicycle Network Algorithms for boosting the Green Transition of European Cities”. Below some impressions:

Download the slides here: https://michael.szell.net/downloads/talk_szell2026bob.pdf

Next time BikeNetKit will be presented at Kortdage in Aalborg, on Nov 19th.
Stay tuned for BikeNetKit’s launch on monday!

New NERDS publication on right-wing votes and bike network delays

Right-wing Votes Relate to Delays in Bicycle Network Development, by C. Sebastiao & M. Szell, published in Findings

Paris has implemented only 43% of its 2021-2026 bicycle network plan by its 2026 deadline, but the delays are not equally distributed. Correlating political voting and bicycle infrastructure data, we find that boroughs with a higher share of right-wing votes are also boroughs with the largest delays in bicycle infrastructure development. Although the number of voting units is only 17, this correlation is remarkably strong and significant. At the city scale, for each additional 1% of right-wing votes, we find 0.86% less protected bicycle lanes built.

We have successfully held our first retreat

With NERDS hitting 7 years old and growing over 30 people, it has been long overdue to hold our first retreat. We did so last week at the AI Pioneer Center, in the old astronomic observatory inside Copenhagen’s beautiful botanic garden (plus awesome dinner at Food Club Nørrebro), organized by Jonas, Jan, and Toine.

The retreat was a wonderful event that deepened our social ties, where we learned much more about each other, and discussed what works well or what does not work so well at NERDS.

On all levels, from faculties to long-term NERDS and visitors, we identified issues we want to improve, including diversity and hiring, more internal exchange, website updates, or more formalized tasks with ownership (and PhD duty credits). It was great to see though that we do not have any serious social issues – to the contrary, the retreat was a confirmation of how well we all get along, and how nice a research group can be. ❤️

In the coming weeks we are going to get to work to implement the short-term-implementable issues, keep pushing for improving our long-term issues to make NERDS an even better place, and definitely aim to make the NERDS retreat a recurring experience!

 

New NERDS publication on transport network growth

The trade-off between directness and coverage in transport network growth, by C. Sebastiao, A. Vybornova, A.R. Vierø, L.M. Aiello & M. Szell, published in Applied Network Science

We systematically study the growth of connected planar networks, quantifying functionality of the growing network structure. We compare random growth with various greedy and human-designed, manual growth strategies. We evaluate our results via the fundamental performance metrics of directness and coverage, finding non-trivial trade-offs between them. Manual strategies fare better than greedy strategies on both metrics, while random strategies perform worst and are unlikely to be Pareto efficient. Centrality-based greedy strategies tend to perform best for directness but are worse than random strategies for coverage, while coverage-based greedy strategies can achieve maximum global coverage as fast as possible but perform as poorly for directness as random strategies. Directness-based greedy strategies get stuck in local optimum traps. These results hold for a number of stylized urban transport network topologies. Our insights are crucial for applications where the order in which links are added to a spatial network is important, such as in urban or regional transport network design problems.

Manuel Knepper has joined NERDS

We welcome our latest NERDS member: Manuel Knepper.

Manuel, who is already guest at NERDS since a few months, joins now as a research assistant for one year, after having finished a master in data science here at ITU with Michele and Anastassia on predicting cyclist flows with machine learning methods.

Manuel will work with Michael and Anastassia on the recently won InnoExplorer grant as research software engineer to turn raw bicycle network algorithms into packaged Python software usable for urban planners, helping us close the gap between research and policy/application. Manuel’s background, his thesis, and also his industry experience with data and software engineering makes him a perfect fit for this role. Besides, Manuel will also be teaching assistant for the geospatial data science course in spring.

We are excited to have you with us, Manuel. Welcome!

Identity improvements to NERDS

Happy new year! 🎉
We have two cosmetic updates to announce, part of a broader move for an improved identity and strategy.

First, we shall hencefort be called Networks, Data, and Society (NERDS) instead of the old NEtwoRks, Data, and Society (NERDS). It is a tiny simplification at Hamming-distance 2 🤓 that eases writing our group name. AlSo LoOkS mUcH BeTtEr!

Second, we have rearranged group members on our people page into permanent members (PermaNERDS) and long-time members (LongoNERDS). This was done so we could add the following text:

At NERDS we do not have one boss for good reasons. Instead, leadership is distributed among all permanent members, in exchange with non-permanent members. We have one rotating group representative / contact person, marked below with a star *.

This shared leadership has always been the case at NERDS, so nothing has changed. It was just not clear previously from the website and could have lead to confusion because most other research groups in academia follow the classical one-PI-on-top-all-the-rest-below model. Internationally, given our size, structure, and impact, it would be more appropriate to call NERDS a research “center”, “institute”, or “collective”, but for historical reasons at ITU we are considered a “group”.

These updates are the outcome of a recent NERDS faculty meeting, where we also set out to implement more social/teambuilding events to strengthen even more our already high commitment to wellbeing, and to improve steering processes towards clarifying our long-term strategies and visions.

Finally, as ITU is in the process of finding a new webhosting solution for research group web pages, we might see bigger, but probably also just stylistic, updates to our website later this year.

We wish you a fulfilling 2026! 🖖

NERDS win Innoexplorer Grant!

Michael Szell, supported by Anastassia Vybornova and Manuel Knepper, have won a 1-year “Innoexplorer” grant by the Innovation Fund Denmark, of DKK 1.4 million (~EUR 188,000), for a project to turn raw bicycle network algorithms into polished software. Congratulations to the team of Michael, Manuel and Anastassia! 🥳

The project Bicycle network planning for a greener future made in Denmark: From network growth algorithms to user-friendly planning software has two goals: 1) take existing algorithms from our bicycle network research that we developed in the past years, and turn them into software that is usable by urban planners, 2) visualize the solutions on a web platform to guide urban planners on their usage. Innoexplorer in general aims to close the gap between research and policy with targeted short-term funding, to arrive at commercially viability. This easy applicability is also exactly what our bicycle network research was lacking so far.

The project will hire 2 people for one year: A research software engineer, and a web developer. We are already in the process of hiring our existing visitor Manuel Knepper for the first position, to start from January 2026. The web developer is planned to start from March 2026. Further, the project will be supported by Anastassia Vybornova, who has herself developed several of the algorithms, and by two external urbanism / visualization experts. We hope that the Innovation Fund’s support will ultimately enable more people to enjoy the benefits of cycling!