Case Study: Mapping Informal Urban Mobility with Open Data
Informal transportation networks—minibuses, motorcycle taxis, shared vans, and water transport—are essential to mobility in the Global South, yet they remain largely invisible in urban planning.
This case study examines how open data, machine learning, and participatory mapping are making these networks visible, improving urban mobility planning.
Why Informal Transport Remains Unmapped
Despite handling billions of trips, informal networks are often missing from transport databases:
Traditional surveys undercount informal mobility by 300-400%.
Multi-leg journeys (e.g., 2.8 transfers per commute in Kampala) are hard to track.
This data gap leads to poor investment decisions, like Nairobi’s 2019 BRT project, which displaced 40,000 matatu workers due to a lack of employment data.
OpenStreetMap-based initiatives like the Million Neighborhoods Map help fill this gap, achieving 89% accuracy in mobility mapping.
Open Data Solutions
Crowdsourced Cartography
Digital Matatus (Nairobi) – Mapped 137 routes, revealing 4.2x denser transit than official maps.
GTFS-Flex – Supports variable stops and demand-based routing, successfully mapped 94% of Manila’s jeepney routes.
Deep learning on satellite imagery - A model trained on Sentinel-2 identified informal hubs in Dar es Salaam with 82% accuracy.
Graph neural networks (GNNs) -Predicted Bogotá’s fuel-protest-induced network adaptations with 89% accuracy.
What Defines Informal Transit?
Dynamic routes – Adapt to demand rather than fixed schedules.
Decentralized ownership – Run by small entrepreneurs.
Flexible payments – Integrated with local economic practices.
For example, in Dar es Salaam, daladala minibuses adjust their routes in real time based on passenger density, creating an intricate transport web that formal buses cannot navigate.
Shadow networks aren’t problems to be solved—they’re resources to be integrated. Cities that merge formal and informal mobility data achieve 23% higher transport equity scores. New protocols like Mobility Data Specification 2.0 now accommodate informal transit patterns.
To build resilient urban transit, we must embrace technology-driven, community-led solutions that recognize the power of informal mobility networks.
Integrating Formal and Informal Transit
Inclusive Transport Planning
Cape Town – Integrated taxi ranks at BRT stations, reducing duplicate routes by 22% and improving commutes by 18%.
Bogotá – Digital Twin model mapped 17,000 informal buses, leading to new bike lanes in high-density corridors (+14% cycling share).
Data Governance Models
Nairobi Mobility Data Trust – Informal operators own their data while contributing anonymized insights. Led to a 37% increase in night services and 62% faster emergency responses.
Malaysia’s MyGDX – Integrated informal transit with census data, directing RM 480M to underserved areas.