How to Place Vertiport Locations in Any City Using Geospatial Machine Learning
| Source: Towards Data Science
Tags: geospatial ML, K-means, urban air mobility, vertiport, urban planning, Lagos
A detailed Lagos case study applies K-means clustering, road-proximity weighting, and airspace constraint screening to identify optimal vertiport locations — demonstrating how geospatial ML handles situations where real trip demand data is unavailable.
Details
This 52-minute Towards Data Science article presents a complete, reproducible pipeline for identifying electric air taxi landing sites in Lagos, Nigeria. The author starts with a population-density raster, runs K-means clustering to find candidate locations, then filters results against two practical constraints: airport safety buffers around Murtala Muhammed International Airport and areas with poor road or transit access. The methodology iterates through a common real-world ML problem: optimizing on an observable proxy (population concentration) when the true objective (trip demand) is unavailable. The pipeline adds road and transit proximity as secondary signals, uses real-world geodesic distances rather than raw map degrees, and re-validates final candidates after spacing adjustments. The article is honest about limitations — the output is a ranked shortlist for further investigation, not a construction plan. Lagos was chosen specifically because data gaps make it a harder case than data-rich cities. The techniques generalize to any city where trip origin-destination data is absent.