THE STUDENT ARC
Studio courses run on the corridor the way a teaching hospital runs on a ward: a real place, live data, consequences that matter. Over one semester, every student works all six stations of a functioning data ecosystem — and leaves having operated one, not just read about it.
The Rivanna River corridor in Charlottesville is implementation #1. Courses are open to students from Architecture, Landscape Architecture, Public Health, Environmental Science, Data Science, and beyond.
From raw field capture to public contribution — every student touches the full loop.
Fly drone transects, ride the 360° bike loops, paddle the LiDAR canoe passes. Every capture lands auto-tagged: location, device, conditions, contributor.
Raw imagery and point clouds move through the intake pipeline into a cloud object store as COG, GeoParquet, and STAC. Students build — and break — real data infrastructure, safely.
Species ID, canopy and trail-condition classification, seasonal change, cross-sections — deterministic GIS beside model-driven workflows, and the judgment of when to trust each.
Studio questions posed to the corridor intelligence come back with caveats and confidence levels. Data becomes design briefs; briefs become proposed interventions.
Students confirm or correct the model's classifications on site; their judgment becomes training signal. This loop is what makes the corpus trustworthy.
Verified layers publish to the public corridor dataset; analyses ship as documented, reproducible notebooks. Work that outlasts the semester.
Cloud-native data engineering on a live geospatial workload · applied AI/ML with verification discipline · open spatial standards (COG · GeoParquet · STAC) · cross-disciplinary collaboration across design, health, and ecology · and the confidence to direct AI tools rather than defer to them.
These students are the builders enterprises will hire — trained from day one on cloud-native patterns, operating a real workload end to end. A partner's contribution lands in three durable places: the reference architecture of a teaching module designed to replicate across studios, corridors, and institutions; a growing public open dataset; and a visible showcase of applied AI in education. Natural surfaces for partnership: architecture working sessions, research and education credits, open-data hosting, and guest engineering sessions with the studio.