What follows is the framework behind every FlySafe score — the signal classes we ingest, the principles that shape each output, and the coverage we stand behind. The methodology itself — how those signals are weighted, how thresholds adapt per FIR, and how the model fuses them — is proprietary and continuously refined. We publish the foundation in full; the recipe stays closed by design.
Output
For each Flight Information Region (FIR) in our active set, we produce a numerical risk index (0–100), a discrete risk level (low / moderate / high / critical), per-factor breakdown, and a confidence tier reflecting our observational coverage of that FIR. Multi-horizon outputs cover 24h, 7d, and 30d windows. Threshold-crossings are emitted as webhooks on supported plans.
Who produces this
Briefings, reports, and airline safety profiles on FlySafe are authored by FlySafe Editorial — the accountable editorial function of FlySafe, not an individual claiming to be a subject-matter authority. We name a team rather than a personal byline because airspace-safety information is high-stakes: what matters is the process and the sources, which we publish in full below.
How the desk works: primary sources are ingested and cross-validated by class (see the signal stack below), numerical indices are computed automatically, and every published briefing passes editorial validation gates before it goes live. Text is drafted from the cited source material and checked against it — we do not publish claims we cannot trace to a named public source.
FlySafe is an independent company founded by Evgeny Padezhnov; FlySafe Editorial operates within it. Corrections and source questions are welcome at [email protected] — we update published material when better data appears.
Signal stack
Inputs are organised into seven signal classes. Each class admits multiple primary sources for redundancy and is cross-validated where mandates overlap.
- 01Regulatory bulletins. Conflict-zone advisories, SFARs, ICAO state letters, prohibitory NOTAMs from national civil aviation authorities.
- 02Aircraft telemetry. ADS-B state vectors, position-integrity reports (NIC / NACp), traffic-density anomalies.
- 03GNSS interference. Position-integrity degradation aggregated to airspace cells, cross-referenced against pilot reports and operator advisories.
- 04Conflict & geopolitical events. Curated event streams with location, severity, and category attribution.
- 05Natural hazards. Tropical cyclone tracks, volcanic ash advisories, wildfire detection, seismic activity.
- 06Operator signals. Public airline routing changes, suspensions, advisory disclosures, ops-group bulletins.
- 07Market signals. War-risk premium movement, coverage withdrawals, underwriter advisories where publicly disclosed.
Each class has its own ingestion cadence, ranging from minutes (telemetry, regulatory feeds) to weekly (market signals). Source diversity is treated as a feature, not a redundancy.
Design principles
A handful of opinionated choices shape every output. These are not implementation details; they are positions we have committed to.
A FIR closed by aerial strike, a FIR ground-stopped by a typhoon, and a FIR struck by an ATC labour dispute carry materially different operational implications. Most public indices conflate these. We do not.
Every FIR carries a coverage tier that reflects how observable it is via independent telemetry. A quiet ADS-B feed in an oceanic FIR is not the same evidence as a quiet feed over a major hub. Our confidence label propagates this distinction to the API consumer.
The system is validated against an independently assembled, multi-signal event ground truth of documented airspace closures across multiple categories — conflict, cyclone, volcano, sanctions, ATC action, pandemic. Predictions are graded with per-region hold-out splits, not pooled accuracy that flatters Middle-East-only performance.
We build on authoritative, independently verifiable feeds and combine them with our own analytics and partner-contributed datasets. Publishing the signal classes keeps outputs auditable; the fusion, weighting and calibration stay proprietary. We do not ingest classified intelligence, restricted military communications, or non-public regulatory deliberations — which keeps outputs reproducible and avoids the policy exposure of classified inputs.
The scoring engine evolves. The API contract does not. Output shapes are versioned (v1 / v3) and breaking changes follow a public deprecation policy. Internal model versions are documented in the roadmap.
Coverage
Coverage expands by partner request and as observational density permits. Single-source FIRs are flagged at lower confidence rather than scored aggressively.
What we do not claim
- ×We are not a certified aviation service provider. Outputs are computational summaries of public signals, not advisory products under any regulatory framework.
- ×We do not replace operational documents. Crew NOTAM briefings, SIGMETs, and AIPs remain authoritative. Our role is integration, not substitution.
- ×We do not predict zero-history events. Black-swan onsets have a latency equal to the fastest underlying signal we observe. We model recurrence and escalation, not novelty.
- ×We do not disclose the model. Weights, calibration, and feature engineering are proprietary. Outputs are auditable; internals are not.
Known limitations
- ·Source latency. Regulatory bulletins lag the underlying event by hours; market signals by days. Our latency claim is per-class, not global.
- ·Observation gaps. ADS-B receiver density is uneven; oceanic and certain African / Pacific FIRs have lower confidence by design.
- ·Historical depth. Score history is deeper for some FIRs than others. Rather than back-fill or smooth, every score carries its scoring version and a confidence field that reflects live signal density.
- ·Cause attribution. Auto-tagging of closure cause uses automated extraction over curated source text. We grade extraction quality continuously and accept tagged-but-uncertain rather than untagged.
- ·Forecast indices know "where", not "when". On a 2024–2026 walk-forward test the index ranks the FIRs where closures later occur well, but the timing of a new closure is not predictable from our inputs: alerts fire far more often than closures follow. Treat the index as a ranking, not a prediction. The documented current state — which regulator document is in force, since when, for whom, with the archived text — is the primary output.
What FlySafe does not do
- ·We do not tell you whether to fly. We reproduce what regulators and states have published, with the date, the applicability (which operators it binds) and the archived text, so that your own assessment under EASA ORO.GEN.200 / ICAO Doc 10084 has a dated, verifiable source.
- ·We do not employ analysts. Open-source news is matched automatically and marked for relevance by a language model; it is a lead to a primary source, not an assessment.
- ·We do not carry NOTAMs. Where a state closes its own airspace we cite the state's own notice or document; where only a NOTAM exists, the status says so and points you to the official AIS.
- ·"None found" means no document in the sources we check (listed with each report) — never "safe".
For technical evaluators
The output surface is the verifiable artefact. Evaluation paths:
- · Sandbox API access — sample the output shape on real data, no commitment.
- · Public roadmap — shipped capabilities and forward direction, with engine version markers.
- · Per-request audit log on supported plans — every score has a traceable input snapshot timestamp.
FlySafe provides automated computation of numerical indices from publicly available data. Indices are raw computational output and do not represent opinions, assessments, recommendations, or advice of any kind. They do not replace official NOTAMs, SIGMETs, AIPs, or communications from aviation authorities. Each operator is responsible for their own independent assessment. See Terms of Service.
Last reviewed: October 2026