WEZ RISK ENGINESURVIVABILITY DECISION SUPPORT
SCN CONTESTED-ALPHA · 2 thr
P(SURVIVE) 0.92
LOW RISK
T+00:00:00
C2 DEGRADED

Threat Map — Comparison

LAYER 2

Both maps update live with the settings below.

P(Survive) · Primary0.92Conf 90% · ±0.04
Risk TierLOW RISKClear of envelopes
Cumulative Exposure8%△ +0%
Active Threats2CONTESTED-ALPHA
Top Driver · L4Hi-alt wind disturbance0.12 · Ambient-driven.
Platform & Environment L1 · INPUTS
VelocityM 0.82
G-limit7.0 g
Posture
EW
Wind
Risk Surface L2
Profile
Resolution
RISKlow → high

Scenario Library

SELECT

Click a scenario to load it into the primary (left) map; set the right map with its own picker to compare.

● PRIMARY · LEFT
CONTESTED-ALPHA
Baseline contested corridor. Two overlapping SAM engagement zones (medium + short range) with a closing adversary.
Threats 2Expected risk MODERATE
Set as primary (left map) →
● PRIMARY · LEFT
CONTESTED-BRAVO
Dense IADS. Three zones including a long-range S-400 envelope the route must transit; deepest survivability trough.
Threats 3Expected risk HIGH
Set as primary (left map) →
● PRIMARY · LEFT
CONTESTED-CHARLIE
Permissive edge. Single short-range threat; route skirts the engagement geometry and stays largely clear.
Threats 1Expected risk LOW
Set as primary (left map) →

Model Basis & Methodology

OBJ 1–5

How each Phase I requirement is represented in the engine.

Representative models — Phase I concept. The panels below show how each requirement is understood and translated into the engine's intended methodology. Geometry, probabilities and numbers are illustrative for the feasibility demonstration; physics-based modeling, full uncertainty quantification, 3D maneuvering dynamics and validation are the Phase I / Phase II work products.
Dynamic WEZ ModelingOBJ 1 · WEZConcept · pending validation
SAM site target approach — aspect-dependent Detect & track — sensor coverage Max range (Rmax) NEZ No-Escape Zone · Pk≈1 Missile fly-out — energy vs range launch Rmax Vmax M4.0 · Rmax 40 nm · NEZ 12 nm · seeker FOV 60° · ceiling FL400

Each engagement zone is intended to be generated from weapon parameters — sensor/detection range, kinematic max-range and the inner no-escape zone — with aspect and altitude dependence, rather than authored shapes. Further work: replace illustrative ellipses with a fly-out/energy model and 3D engageable volume.

Survivability Scoring — Engagement Kill ChainOBJ 2 · SCOREConcept · pending validation
Detect0.92 Track0.88 Launch0.95 Intercept0.80 P(hit)0.55 P(kill|hit)0.85 P(killed) ≈ 0.29 P(Survive) P(SURVIVE)0.71

The score is intended to be computed as P(Survive) = 1 − Π(stage probabilities) along the detect→track→launch→intercept→hit→kill chain — not a drawn curve. This makes every score decomposable, which is what feeds the ranked-driver explanation. Further work: derive stage probabilities from the WEZ physics and engagement geometry.

Uncertainty QuantificationOBJ 4 · UQConcept
P(Survive) distribution — Monte Carlo 0.0 0.5 1.0

The ± confidence interval shown across the console is intended to come from propagating input uncertainty — nav error, wind, sensor noise — through the model (Monte Carlo / error propagation), shading the band wider in contested airspace. Further work: wire real input distributions and calibrate coverage.

Driver Attribution — SensitivityOBJ 3 · XAIConcept
baseline P(Survive) Envelope overlap Adversary closure Sensor exposure G-limit Velocity Hi-alt wind ↓ degradesimproves ↑

Ranked drivers are intended to be a model-derived sensitivity of P(Survive) to each input, not a fixed list — the basis for traceable, defensible attribution. Further work: compute local/global sensitivity from the real model.

3D Engageable Volume — Altitude ProfileOBJ 1 · 3DConcept
FL400 FL200 FL000 3D engageable volume exposed segment route vertical profile downrange →

Threat envelopes are a 3D volume with a ceiling; survivability depends on the route's vertical profile through it. Further work: full 3D geometry and altitude-dependent exposure.

Maneuvering Bounds — G-load / Turn RadiusOBJ 1 · DYNConcept
own-ship · M0.82 threat 5 g 7 g 9 g

Evasion respects airframe G-limits and minimum turn radius (r = v²/g√(n²−1)) — a nonholonomic constraint current path-planners often ignore. Further work: 3D nonholonomic maneuver model bounding feasible reroutes.

Transition Architecture — Edge Deployment & Data IngestionOBJ 5 · TRANSITIONConcept
Mission & sensordata feeds Ingest /normalize WEZ Engineedge · ARM / x86 Survivability+ UQ ExplainableHMI Target loop latency budget < 50 ms · runs at the edge with no vehicle hardware or flight-control changes

A modular, software-defined engine intended to ingest representative threat/platform/mission data and run at the edge (ARM/x86), integrating with C2 / mission-planning ecosystems. Further work: real ingestion adapters, edge runtime benchmarking, and integration interfaces.

Validation & Performance HarnessSOW TASK 5Target metrics
Monotonicity
PASS req'd
acceptance: risk ↑ as exposure ↑
CI coverage
≥ 95%
calibration target
Edge runtime
< 25 ms
latency budget · ARM class
Scenario sweep
100+
cases — planned

Phase I defines a validation harness with explicit acceptance targets — monotonicity/sanity checks, confidence-interval calibration, runtime on representative hardware, and an automated scenario sweep. Values shown are targets, not measured results; they will be populated with validated runs against representative threat data.

Explainable Decision Support

LAYER 4
Why this score? — Ranked Drivers

How this score is computed

P(Survive) is the modeled probability the own-ship survives the current threat picture, on a 0–1 scale.

  1. Each factor — engagement-zone overlap, adversary closure, wind disturbance, and sensor exposure — is scored live from the route geometry and conditions.
  2. Factors are ranked by contribution; each bar shows how much that factor is weighing on the assessment right now.
  3. The weighted factors reduce a baseline survivability to produce the P(Survive) score.
  4. Uncertainty in the inputs is carried through to a confidence interval (± CI), which widens in contested airspace.
P(Survive) = baseline − Σ ( weight × factor ), bounded to [0, 1]  ·  ± CI from input uncertainty

Illustrative feasibility model for demonstration — not a validated probability-of-kill computation.

01SAM-1 envelope overlap0.10
02Adversary closure rate0.08
03Hi-alt wind disturbance0.07
04Sensor exposure (route)0.05
Traceable rationale

Own-ship remains clear of modeled engagement envelopes; survivability is driven primarily by ambient conditions. Confidence is high.

Input TraceabilityPROVENANCE
  • Envelope overlap← threat geometry, own-ship position
  • Adversary closure rate← adversary trajectory
  • Hi-alt wind disturbance← environment inputs
  • Sensor exposure← route, EW interference
Confidence note

Uncertainty widens inside contested airspace and narrows once the own-ship clears the engagement zone.

RUNNING
T+00:00T+02:30T+05:00T+07:30T+10:00
Shared timelineT+00:00LOW RISK