Gerald Stanje

About

Gerald Stanje is a researcher at the forefront of spacecraft health monitoring, specializing in anomaly detection and data-driven analysis of telemetry from long-duration robotic space missions. His work bridges the gap between automated machine learning and expert human oversight, developing mixed-method approaches that make satellite and probe operations safer and more efficient. In his most-cited paper, “An Approach To Mode and Anomaly Detection with Spacecraft Telemetry Data” (2020, 15 citations), Stanje introduces a framework that combines unsupervised learning with human-in-the-loop validation to identify subtle deviations in time-series data. His earlier work, “An Application of Data Driven Anomaly Identification to Spacecraft Telemetry Data” (2016, 8 citations), demonstrates how temporal segmentation and clustering can reveal nominal operational modes, enabling faster, more accurate anomaly flagging. Though his citation counts are modest, Stanje’s contributions are highly practical, directly supporting mission operations by reducing manual inspection burdens. His research is essential reading for engineers and data scientists working in aerospace diagnostics, offering a scalable path toward autonomous spacecraft monitoring.

Research Focus

Key Achievements

Top Papers

1. 1
   An Approach To Mode and Anomaly Detection with Spacecraft Telemetry Data

   15 citations · 2020
2. 2
   An Application of Data Driven Anomaly Identification to Spacecraft Telemetry Data

   8 citations · 2016

Key Collaborators

Contact & Links