EN
Talk to AIR NEXUS
MenuClose
Talk to AIR NEXUS

Airspace Intelligence Platform

See the airspace as a system.

One connected platform that reads the airspace through many sources, and keeps every conclusion tied to the evidence behind it.

Evidence levelE1Architecture Defined

Explore the Architecture

Many inputs are not yet one understanding.

Each source sees the airspace through its own narrow window. The platform is designed to hold what each one can and cannot say, side by side.

  • RF gives a directionA bearing from a passive node says where to look, not how far away the object is.
  • PCL gives a rangeA bistatic range ellipse says the object lies somewhere on a curve, not what the object is.
  • EO gives a viewAn image can suggest a class, but only for what is in view and in light.
  • Source A
  • Source B
  • Source C
Comparing sources: Data table
ItemSource ASource BSource C
Agreement825870
Freshness648852
Completeness907060
Comparing sources CH03Data status: Synthetic dataEvidence level: E0 · ConceptQuestion answered: How do sources compare?A dot plot places three example sources on three measures, agreement, freshness and completeness, so that the sources can be read side by side without a spider chart.Limitation: The three measures are relative scores in an example, not benchmarks.

The system in four bands.

Observe, understand, preserve, deliver. Each band hands data to the next together with its quality, so nothing is added without a trail.

  1. ObserveMany sources, kept as observations with their time and quality.
  2. UnderstandCorrelation, fusion and one unified state, with confidence kept apart from evidence.
  3. PreserveA time-aware twin that remembers how each state was reached.
  4. DeliverGoverned outputs: a view, an alert, an API, a replay.
Data flow: Data table
StageValue
1Sources
2Model
3Policy
4Interface
5Consumer
6Audit
Data flow CH13Data status: IllustrativeEvidence level: E0 · ConceptQuestion answered: How does data flow through the architecture?A pipeline of six stages, from sources to audit, shows how data moves through the model, the policy and the interface to the consumer, with a record kept at the end.Limitation: A conceptual flow. It does not describe a deployed system.

From observation to state.

Four steps turn separate observations into one state the platform can defend. Each has its own page.

  • Observe from many sourcesPassive and cooperative sources enter as observations, not conclusions.
  • CorrelateA candidate link is proposed only when time and geometry agree.
  • FuseLinked observations become one supported track, never forced when they disagree.
  • Hold one stateOne unified state per object, with unknown objects kept unknown.

Context and confidence travel with the state.

A state without its context or its confidence is a claim. These two steps keep the claim honest.

  • Classification and contextA class is a decision with its own confidence, and it can stay open.
  • Confidence and uncertaintyConfidence is shown as a band that widens when evidence thins.

A twin that remembers.

The Airspace Digital Twin keeps ten layers of one living state. Open it to see them, switch them and replay how the state was reached.

The ten layers

  • TW01Base environment
  • TW02Observations and sources
  • TW03Tracks and unified state
  • TW04Classification and context
  • TW05Confidence
  • TW06Evidence and provenance
  • TW07Environmental context
  • TW08System health
  • TW09History and replay
  • TW10Network and integration

Open the Digital Twin

Every state carries its evidence.

Provenance is the chain from a source to a stored state. It is what lets a reviewer ask how the platform knew.

Follow the provenance chain

When the system degrades, the claim softens.

A source can slow, stall or return. The platform is designed to say so, and to weaken what it claims before it loses what it knows.

  1. NormalObservations arrive on time and the claim is stated at full strength.
  2. DelayedA source arrives late. The state is marked as older than it looks.
  3. StaleNothing new arrives. The last state is kept, labelled stale, and never shown as current.
  4. Claim softensThe confidence band widens and the wording weakens before the picture fades.
  5. RecoversThe source returns. The gap stays in the history, and the state is restored step by step.
  • Normal
  • Degraded
  • Unavailable
System health over time: Data table
Time (relative)Component 1Component 2Component 3
1NormalNormalNormal
2NormalNormalNormal
3NormalNormalNormal
4NormalNormalUnavailable
5NormalNormalUnavailable
6NormalDegradedNormal
7NormalDegradedNormal
8DegradedNormalNormal
9DegradedNormalDegraded
10NormalNormalNormal
11NormalNormalNormal
12NormalNormalNormal
System health over time CH07Data status: Synthetic dataEvidence level: E0 · ConceptQuestion answered: How has system health changed?Three bands, one for each of three example components, show normal, degraded and unavailable periods as different fills and patterns, so state never depends on colour alone.Limitation: Periods are invented and say nothing about any real component.

Data status: Synthetic demonstration

The operations console, with its history.

The same synthetic scenario as the home page, now with a timeline you can scrub, the contribution of each source and the confidence over time. Pick any object and every panel follows.

Scenario time 01:04

Scenario timeline

Move to any moment. Every panel shows the state as it was known then.

Event timeline

Panoramic EO/IR strip

Tags mark the objects the EO channel sees. Select a tag or a row.

Situation view

RF gives a direction only. PCL gives range ellipses. A wider ellipse means a wider confidence band.

Observation table

TimeTrackClassSourcesConfidenceEvidenceFreshness
00:08Small drone 78%RFEOHighCorroboratedFresh
00:16Aircraft 93%PCLRFHighCorroboratedFresh
00:28Bird-like 54%EOMediumSingle sourceFresh
00:40UnknownPCLEOLowUnresolvedFresh
00:56Aircraft 81%PCLEOHighCorroboratedFresh

Selected object

A zoomed, grey, thermal-looking crop of a small multirotor aircraft against a hazy sky. It shows no real object.

T1 Small drone 78%

Track
T1 · Small drone 78%
Sources
RFEO
Confidence band
High
Evidence
Corroborated
Known then
00:16
Freshness
Fresh

Source contribution

  • RF2
  • PCL3
  • EO4

Objects each source holds at this moment. One object can be held by several sources.

Confidence over time

The band of each object, from its first observation. A band that narrows is not a proof.

System health

  • RFAvailable
  • PCLAvailable
  • EOAvailable

Demonstration states of the three sources. Health is not confidence.

Synthetic demonstration image. It shows no real place.

Delivery and scale.

What the platform holds leaves it through governed outputs, and the same model is designed to grow from one site to a region.

  • Data and API integrationOutputs carry their evidence and their limits, so a success response is not read as a valid fact.
  • Site-to-region scaleLocal context is kept as the picture widens, so a region is many sites and not one blur.
From site to region: Data table
StageValue
Site8
Local5
District3
Region1
From site to region CH18Data status: IllustrativeEvidence level: E0 · ConceptQuestion answered: How does it scale from site to region?Four nested levels, site, local, district and region, show how detail is abstracted step by step as the view widens, with fewer marks at each larger level.Limitation: Levels are abstract. No real site, boundary or coverage is drawn.

Where the work stands.

Three projects sit under this platform. Each states its own evidence level, and none claims more than the evidence supports.

  • Airspace Intelligence Core PlatformThe platform itself: state, twin, evidence and delivery.Evidence level E1 Architecture Defined
  • Multi-Sensor Fusion EngineHow linked observations become one supported track.Evidence level E0 Concept
  • Airspace Data Intelligence APIGoverned outputs for other systems.Evidence level E0 Concept

Walk through the platform with us.

Tell us about your airspace and we will show how the platform is designed to hold it.

Talk to AIR NEXUSSee the evidence