Real Detection Data

298,800 Photos. 700+ Flights. Every Detection.

This isn't a simulation. This is every AI detection from every flight over San Francisco — 700+ flights across five neighborhoods, from December 2021 to April 2024.

700+
Flights
Photos Analyzed
Dumpsites Detected
311 Reports Filed
Sequence 1
The Volume
Every bar is a flight day. 700+ flights across 154 days — some days had multiple flights across different neighborhoods. Red shows trash detections. Some days captured 50,000+ photos.

The AI model analyzed every photo — classifying what it saw as trash or not trash. Early on, the detection rate was low. The model was learning. By mid-2023, it was finding dumpsites in 40-50% of targeted flight photos.

Sequence 2
The Signal
Detection rate per flight day. Dot size shows photo volume. Early flights found trash in 1-3% of photos. By 2023, the mature model hit 30-52%. The signal got louder.

Why the rate climbs

Two things happened simultaneously: the AI model improved through training on real Bayview data, and the flight paths were refined to focus on confirmed dumping corridors. The combination — a smarter model flying smarter routes — is why the detection rate increased 15× over the program's lifetime.

Every detection has a GPS coordinate. 9,590 confirmed trash detections, each one placed on the map of Bayview-Hunters Point. The pattern is unmistakable — the same streets, the same corners, the same blocks.

Sequence 3
The Map
Dim blue dots show the full flight coverage area — Mission, Dogpatch, Excelsior, Portola, Bernal Heights, Bayview, and Hunters Point. Red dots are confirmed trash. The concentration in Bayview is unmistakable.

What the map reveals

The densest clusters aren't random. They correspond to specific infrastructure: dead-end streets, highway underpasses, vacant lots adjacent to commercial zones, and corners where DPW trucks have limited access. These aren't sites where people dump once — they're sites where people dump repeatedly, because the conditions that enable dumping persist. Detection identifies the pattern. Enforcement changes the conditions.

Detection without action is surveillance. Detection with action is infrastructure. Every confirmed dumpsite was automatically filed as a 311 cleanup request — no human intervention required.

Sequence 4
The Response
311 cleanup reports generated per flight day. Only sites large enough to dispatch a crew, not already reported in the last 48 hours, and on the public right-of-way. Intelligent triage, not 311 spam.

4,801 triaged reports

Not every detection became a report. Only sites meeting three criteria: (1) large enough to warrant a crew dispatch, (2) not already reported in the prior 48 hours, and (3) on the public right-of-way, not touching buildings. Each report included GPS coordinates, timestamped aerial photo, and AI-classified waste type. Intelligent triage — not 311 spam.

Behind every data point is a flight. Some mornings, one quick pass. Some days, three separate flights — morning, midday, evening — covering different routes. The operational tempo tells its own story.

Sequence 5
The Operations
Every dot is a flight day. Height shows duration. Size shows photo count. Color shows context: amber = multi-route day, red = 100+ trash detections. July 2022 was the most intense period — multiple flights per day across Bayview, Mission, Excelsior, and Dogpatch.

One person. 700+ flights.

Every flight was planned, executed, and processed by a single operator. The drone launched from neighborhood streets. Photos were analyzed in real time. 311 reports were filed automatically — but only for sites that were large enough, not recently reported, and on the public right-of-way. No city department, no fleet of vehicles, no team of inspectors — one person with a drone and an AI model covered more ground than the city's entire enforcement apparatus.

This dataset is the proof. Not a demo, not a projection, not a pitch deck statistic. 298,800 photos. 700+ flights. 9,590 confirmed dumpsites. 4,801 cleanup requests — each one triaged for size, recency, and location before filing. All from five neighborhoods in one city.

Now imagine an entire city.