elvonedigital twinScenario
Drone
Environment
Sensors
elvone Fusion
Sensor contribution
Detection timeline
Real / Recorded
Radar detections, RF detections and EO observations logged against a timestamped recorded event.
DATA SOURCE TO BE CONNECTED
elvone Fusion
Time-align, correlate and fuse heterogeneous observations into a common 3D track.
4 sensors → 1 fused track
Physics Engine
Generate controlled scenarios using drone dynamics, terrain, weather and sensor models.
Ground truth → sensor observations → elvone
Simulated Result
Before
96.2%
Detection confidence, all sensors nominal
After
20.4%
Detection confidence, current sensor mix
Track continuity
100.0%
Baseline: 99.8% with all sensors nominal
Pilot Performance
12 / 12
Detection rate
11 / 12
Classification
98.4%
Track continuity
6.2 m
Median position error
1.8 s
Median detection time
4.1 s
Median classification time
0.7%
False tracks
100%
Events replayed
Illustrative simulation results — replace with measured pilot data.
Where the digital twin gets its environmental context. Nothing here is fabricated: unconnected sources are labelled, not invented.
Geospatial
Saudi terrain, buildings, imagery and geographic layers.
GEOSA
Weather
Historical/current environmental conditions including wind and temperature.
Saudi National Center for Meteorology
Aviation
Terrain and obstacle information where appropriately licensed.
Saudi aviation information
Sensor data
Real recorded data, public research datasets, and synthetic sensor observations.
DATA SOURCE TO BE CONNECTED
Real World
elvone Core
Digital Twin
Validation
Start with a Saudi digital twin. Connect recorded sensor data. Calibrate the model. Then validate elvone against real operational conditions.