Research ยท Benchmarks
Benchmarks
Held-out evaluation suites for orbital ML and distributed compute. Train on the open datasets, submit predictions for the held-out test inputs, and compare against baselines - we evaluate results, not methods.
Orbital Intelligence
OrbML-Predict
Orbit determination from sparse observations.
ConjunctionNet
Conjunction probability estimation.
ManeuverDetect
Maneuver detection and timing.
SatClass
Satellite classification.
ReentryPredict
Re-entry time prediction.
Distributed Compute
FedSpace
Federated learning across orbital nodes.
PartitionBench
Model partitioning under node heterogeneity.
SyncSchedule
Synchronization under intermittent links.
CompressionBench
Gradient compression efficiency.
How to participate.
Get the training and validation sets from the data portal, use any approach - ML, physics-based, or hybrid - then upload predictions for the test inputs. We score against held-out labels and return results.