WATCHTOWER 2.0 — BASELINE LEARNING
Methodology

No opinions. Just a baseline.

Every part of our pipeline is designed to defeat one accusation: "you only track the aircraft you're already suspicious of."We don't. The machine watches every aircraft, all the time, and the math decides what stands out.

01

Population-scale capture

We log every ADS-B / MLAT detection in the observation zone — not a curated subset. 137,000+ records, 3,995 aircraft, growing.

02

48-hour baseline

Before flagging anything, the system observes for 48 hours to learn what NORMAL looks like for that airspace at that time of day, season, and weather.

03

Statistical anomaly detection

Outliers are scored against the learned distribution. The threshold is published. We don't pick — math picks.

04

Chain of custody

Each record receives a SHA-256 hash linked into a Merkle chain. Any tampering is detectable. Evidence is reproducible by any third party.

05

Bradford Hill scoring

Where we correlate aircraft activity with biometric or witness data, we apply the Bradford Hill criteria (strength, consistency, specificity, temporality, etc.) — the same framework used in epidemiology and courtrooms.

06

Open source by design

Every line of Watchtower 2.0 will be public. The methodology IS the code. Deploy it in your county, get the same answers.

The anti-cherry-picking proof

100%

of detections logged — not just suspicious ones

0%

flagged during baseline window — by design

48h

minimum learning period before any flag is valid