LO
CapabilityCognitive automation2026-08-13
Machine-made building footprints meet or exceed hand-drawn quality but vary by place and should never be imported without checking local quality, Microsoft says
GIS analyst / cartographeroccupation page →
Event date / reported
2026-08-13
Evidence stage
CapabilityA demo, benchmark or paper shows the task can be done. Updates what the technology can do — not what employers will do.
Tasks this bears on
Digitising features from imagery
Tracing buildings, roads, water and land cover from aerial and satellite images into map data.
Automating✓ Evidence-backed
Quality checks and field validation
Checking data against the ground and against standards before it is used.
Still human-led≈ Platform inference
Where this applies
Global. Microsoft's open dataset of building footprints extracted by machine learning from imagery covers 225 regions. Its README says its metrics show the data meets or exceeds the quality of hand-drawn footprints, reports precision above 92% and recall between 70.9% and 85.9% by region, and tells users never to import the data into OpenStreetMap without first checking local quality, which varies between rural and urban areas and terrain. The company describing its own dataset.
What this means
Machine-made footprints exist for most of the world — and come with an instruction to check them locally.
What it does not yet show
A vendor's own quality claims; recall varies a lot between regions.
What you can check
Open Microsoft's GlobalMLBuildingFootprints repository and find "meets or exceeds the quality of hand-drawn building footprints".
Does it change the assessment?
No — and this stage does not move it either. A "Capability" record is real evidence, but it does not upgrade a task judgement on its own. The 2 linked judgements above stand where they were.
Source
Microsoft — Global ML Building Footprints (GitHub repository README; update of 2026-08-13) · verified 2026-09-30 · Claude (VOLO agent) · interpreted 2026-09-30 · Claude (VOLO agent)
This source sells the thing it is describing
Product or template: Microsoft Global ML Building Footprints
What the publisher gains from this: Microsoft built the models and publishes the dataset; presenting its quality favourably supports its reputation and platform.
A vendor's own product material never moves a task judgement on this site, and at most one such record exists per occupation. This kind of source can be supplied without limit — a site built from it would be a catalogue of what AI can do, which is the opposite of a record of what has happened.
Primary source — published by the party that did this, or the authority of record. No co-signature needed.