qsh-satellite-opssat-ad

OPS-SAT segment anomaly detector

gradient-boosted trees over 18 published per-segment features + sampling

Part of QSMPC-QKD-QHE-AI-Hybrid, a quantum-safe orchestration demo. This is the plaintext model for the satellite_comms use case. No code path evaluates this model under encryption; what each use case encrypts, if anything, is stated in the notes below.

Measured performance

Published baselines this is measured against

• Target metric: AUC PR
• Baseline to beat: 0.979 - FCNN, best of the 30 algorithms benchmarked in Ruszczak et al., Scientific Data 12 (2025), on this dataset's own test split (AUC PR 0.979, F1 0.946, MCC 0.932). XGBOD reaches 0.975 and RF+ICCS 0.963.
• Published ceiling: 0.979 - FCNN, the best AUC PR among the 30 baselines Ruszczak et al. benchmarked on this split; no higher published AUC PR was found.
• Companion metric shown alongside: f1 - reported together because the aggregate figure can look healthy while the class that matters is not.

Training data

• Dataset: OPS-SAT-AD
• Licence: CC-BY-4.0
• Source: https://doi.org/10.5281/zenodo.12588359 (licence read 2026-10-31)
• Attribution (CC-BY-4.0): Ruszczak, Kotowski, Evans & Nalepa, 'The OPS-SAT benchmark for detecting anomalies in satellite telemetry', Scientific Data 12, 710 (2025), doi:10.1038/s41597-025-05035-3, CC BY 4.0. Data: Ruszczak, B., Kotowski, K., Nalepa, J. & Evans, D., 'OPSSAT-AD - anomaly detection dataset for satellite telemetry', Zenodo (2024), doi:10.5281/zenodo.12588359 (version 1).

2,123 annotated telemetry segments across 9 channels from ESA's OPS-SAT CubeSat, 20.4% anomalous, with 18 published per-segment features plus a sampling metadata column, and the benchmark's own train/test split. That split is stratified random, not temporal, so scores on it do not measure generalisation over time. Ruszczak et al., Scientific Data 12 (2025). CC BY 4.0, which permits redistributing the data with credit; the per-segment feature table is about 507 KB, the raw segment file much larger. A different task from ESA-ADB: segment classification, not forecasting, so its score is not comparable with the Telemanom model's and neither is the other's baseline. Pinned to version 1 (Zenodo record 12588359), the files this project downloads; version 2 (record 15108715) changes the files and adds a LICENSE file.

Notes and limitations

Segment CLASSIFICATION on real OPS-SAT telemetry, which is a different task from the Telemanom forecaster above: this one is scored against the 30 algorithms published with the dataset, not against persistence, and the two numbers must not be read as a comparison. Chosen because its corpus is CC BY 4.0 and small, so the whole test partition can be redistributed alongside the weights. The benchmark's split is stratified random, so these scores do not measure generalisation over time. The published ONNX graph reproduces the scikit-learn model on the test partition, so its accuracy there is the 0.9660 recorded here, and the browser's re-score reproduces it. Until Round 86 the evaluation sample rounded every feature to 6 decimals, which flipped 8 of the 529 decisions: the re-score read 0.9509, and this note blamed the export.

Honest scope

This model is published as part of a research proof of concept, not as a production system. Numbers above are what this repository measured on the split described, with the code in scripts/train/. Where a figure is carried from the literature rather than measured here, it is labelled as such.