WHO BUILDS THIS, AND WHY

About AeroScope

AeroScope began with a plain question, "what is flying over me, and can I trust it?", and a conviction that the answer should be checkable. It is built by one independent researcher, runs entirely on open data, and refuses to dress up rules as magic.

Quick answer. AeroScope is an observer-relative ADS-B airspace surveillance platform built and maintained by Muhammad Uzair, an independent researcher in the Department of Computer Science at COMSATS University Islamabad (ORCID 0009-0002-4104-2680). It fuses more than 60 public ADS-B feeds into a live, explainable picture of the aircraft above any chosen point, scores each one from 0 to 100 for how much attention it deserves, checks whether its broadcast can be trusted, and publishes its anomaly-detection work as an open CC-BY 4.0 dataset. It is free to use, it holds no private or classified feed, and it states its limits in writing.
The problem

Raw ADS-B is a firehose, not an answer

Every airliner, business jet, helicopter and many larger drones announce themselves roughly once a second on 1090 MHz. Dozens of volunteer networks already collect those broadcasts and publish them for free. The data is genuinely open, which is remarkable. The problem is that it arrives as undifferentiated dots.

Conventional flight trackers are built around a different question. They answer "where is flight BA117", which is exactly right if you are meeting someone at an airport. It is the wrong shape of question if you are standing in your garden listening to something circle, or if you are an analyst asking whether the traffic over a particular facility looks normal this week.

AeroScope inverts it. You fix a location and the platform continuously evaluates everything above it: what each aircraft is, how it is behaving, whether its own signal is internally consistent, and which of the dozens overhead actually deserve a second look. That is what "observer-relative" means, and it is the single design decision the whole project follows from.

What it does

From a 1090 MHz broadcast to an explainable picture

Each cycle runs raw positions through an enrichment and detection pipeline before anything reaches the screen. The stages are deliberately boring and inspectable:

StageWhat happens
FusionMore than 60 public ADS-B feeds are polled and merged. Reports of the same airframe from several networks are de-duplicated on the ICAO 24-bit address, so one aircraft is one track rather than three dots. See data sources.
EnrichmentRegistry lookup attaches type designator, operator, engine count and wake category where a record exists. Fields are left blank rather than guessed.
Attention scoringEight weighted, rule-based factors produce a transparent 0 to 100 score: emergency squawk, military hex allocation, proximity to the observer, altitude and speed anomalies, loitering or orbit patterns, integrity-check failures, unregistered identity and drone-like kinematics. Every score shows its contributing factors. Read the scoring method.
IntegrityA DO-260B style check on NIC, NACp, NACv and SIL, a Kalman normalised-innovation test on the trajectory, and self-consistency residuals such as geometric versus barometric altitude. See spoofing detection.
Anomaly consensusSix independent detectors vote. A flag is raised only when at least two agree, which suppresses the false alarms a single detector produces. See behavioural baselines.
DeliveryPositions refresh on a fast loop of about seven seconds, with client-side dead-reckoning between fixes so motion is continuous. The heavier analysis runs on its own cadence of roughly twelve seconds so it never blocks the map.
Principles

How this project holds itself accountable

🔬

Established methods, not hype

The detection stack is deliberately torch-free. It is built on River, scikit-learn, pykalman, OpenAP, stumpy and PyOD, chosen because every flag they raise can be traced back to a rule or a statistic. There is no deep learning and no reinforcement learning. An earlier RL prototype was built, evaluated, found not to justify its opacity, and retired. References to it were removed from this site rather than left to quietly inflate the capability list.

📖

Open and citable

The AeroScope ADS-B Anomaly Benchmark is published under CC-BY 4.0 with 38 documented columns, a reproducible IsolationForest baseline and its limitations stated up front. Publishing the dataset means the detection claims can be checked by someone else rather than simply believed. See research and dataset.

⚖️

Honest about limits

AeroScope ranks attention. It does not judge intent. It sees only what aircraft choose to broadcast, so silent aircraft, most small consumer drones and anything operating without a transponder are invisible to it. Where a capability has an edge, the platform says so in plain language on the limitations page instead of hiding it in a footnote.

Boundaries

What AeroScope is not

Being useful to serious users means being precise about the boundary of the tool. AeroScope is an awareness, research and analysis platform. It is explicitly not the following things:

The author

Built by Muhammad Uzair

AeroScope is designed, written, deployed and maintained by one independent researcher in the Department of Computer Science at COMSATS University Islamabad, Islamabad, Pakistan. Every design decision described on this site, from the choice of a consensus rule over a single classifier to the decision to publish the benchmark openly, traces back to one accountable person rather than an anonymous team.

That is a real limitation on capacity and it is stated openly on the status page. It is also the reason the project can afford to retract a claim the moment it stops being true, which a commercial roadmap usually cannot.

Identity and provenance are published so the work can be attributed and checked: ORCID 0009-0002-4104-2680, the Wikidata entity for the platform, and the open dataset record on Hugging Face.

Who it is for

Five people this was built for

If you areStart with
Curious about your own skyWhat is flying over my house, then open the live map and set your location.
A researcherThe open benchmark dataset and the detector design. The data is CC-BY 4.0 and citable.
A receiver-network operatorData sources for how your feed is used and attributed, and receiver setup if you want to contribute one.
A security or OSINT analystADS-B security and spoof detection, plus the REST and WebSocket API.
Building with AI assistantsThe public MCP endpoint, which lets an assistant query live airspace and this documentation directly.

If you are a researcher, a receiver-network operator, a journalist or an organisation that cares about ADS-B integrity and open aviation data, I would genuinely like to hear from you. Get in touch.

FAQ

Frequently asked questions

Who runs AeroScope?
AeroScope is built and maintained by Muhammad Uzair, an independent researcher in the Department of Computer Science at COMSATS University Islamabad, Pakistan (ORCID 0009-0002-4104-2680). It is a one-person project rather than a company or a staffed team.
Is AeroScope affiliated with any government, military or air navigation service provider?
No. AeroScope has no government, military or ANSP affiliation, funding or data access. It uses only public ADS-B broadcasts republished by volunteer receiver networks, plus public registry and weather sources. It holds no private, restricted or classified feed.
Is AeroScope free, and is there a catch?
It is free to use in a browser with no installation, and the ADS-B Anomaly Benchmark dataset is released under CC-BY 4.0. There is no paid tier being withheld and no user data is sold. The trade-off is stated openly: the service is best-effort with no contractual SLA.
What makes AeroScope different from Flightradar24 or FlightAware?
Those platforms answer where a specific flight is, with large receiver networks, airline scheduling data and polished consumer apps. AeroScope is observer-relative: you fix a location and it evaluates everything overhead, adding a transparent 0 to 100 attention score, DO-260B integrity and spoofing checks, drone heuristics and consensus anomaly detection, plus an open citable dataset. It is a complementary analysis layer rather than a replacement.
Does AeroScope use AI, deep learning or reinforcement learning?
No deep learning and no reinforcement learning. The anomaly layer is deliberately torch-free and built on established libraries: River, scikit-learn IsolationForest, pykalman, OpenAP, stumpy and PyOD, with a consensus rule requiring at least two detectors to agree. An earlier reinforcement-learning prototype was evaluated and retired because its opacity was not justified by its results.
Can I cite AeroScope in academic work?
Yes. Cite the AeroScope ADS-B Anomaly Benchmark v1 by Muhammad Uzair, released under CC-BY 4.0, via its Hugging Face record. The dataset ships 38 documented columns and a reproducible baseline. Author identity is verifiable through ORCID 0009-0002-4104-2680.
How can I verify the claims made on this site?
Every capability described here maps to a page that explains the method, and the open dataset lets you reproduce the detection results independently. Live service health is queryable on the status page, data provenance is listed feed by feed, and known weaknesses are published on the limitations page.