khundman/telemanom

A framework for using LSTMs to detect anomalies in multivariate time series data. Includes spacecraft anomaly data and experiments from the Mars Science Laboratory and SMAP missions.

51
/ 100
Established

This tool helps operations engineers and mission controllers monitor critical systems by automatically identifying unusual patterns in sensor data. You provide historical sensor readings (telemetry) for a system, and it outputs a report highlighting specific timeframes when the system's behavior deviated from the norm, helping you proactively detect and address potential issues.

1,152 stars. No commits in the last 6 months.

Use this if you need to automatically detect anomalies in continuous, multi-stream sensor data, especially for systems like spacecraft or industrial machinery where unexpected behavior can have significant consequences.

Not ideal if your data is not time-series based, you have very little historical data, or you need to perform root-cause analysis rather than just anomaly detection.

spacecraft-operations telemetry-monitoring system-health predictive-maintenance sensor-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,152

Forks

262

Language

Jupyter Notebook

License

Last pushed

Jan 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/khundman/telemanom"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.