Paper Category: AI/ML in Satellite Data Missions
-
Embedding Machine-Learned Anomaly Detection into Relevance-Driven Mission Operations Workflows
Anomaly detection has become a central application of machine learning in satellite operations; however, when applied in isolation, machine learning based detections alone are insufficient to support scalable mission operations. As fleets grow, operators face increasing cognitive load not from anomaly frequency, but from the need to interpret weak signals, correlate them with operational context,…
-
Operational Implications of Dynamic Power Throttling on High-Performance LEO Edge Computing
The integration of high-performance COTS (Customer Of The Shelf) processors, such as the Nvidia Jetson Orin NX, into SmallSat architectures enables advanced on-orbit edge computing but introduces significant power management challenges. Standard manufacturer power profiles typically require system reboots and lack the granularity needed to respond to dynamic LEO (Low Earth Orbit) energy constraints, such…
-
Low SWaP Flight Board for High-Speed On-Board Data Handling, Processing and AI Inference
The continuous increase in payload data volume and mission autonomy requirements is driving the need for increasingly advanced on-board data handling and processing technologies in satellite systems. In particular, next-generation Earth observation, telecommunications, and distributed space architectures require high-performance processing capabilities to enable real-time data reduction, intelligent decision-making, and efficient use of downlink resources. Within…
-
Payload Operation using On-Board Vision Language Model
The rapid maturation of multimodal vision-language models (VLMs) has significantly expanded artificial intelligence applications at the edge, including spaceborne systems. In this work, we present one of the first demonstrations of deploying a compact vision-language model directly on a very-high-resolution Earth-observation satellite payload processor [1], enabling autonomous on-orbit scene understanding and near real-time decision-making. This…
-
Seeing Through the Haze: Simulation-Driven Atmospheric Analysis and On-board Dehazing for Robust LEO/VLEO Earth Observation
Atmospheric attenuation and cloud cover remain a primary bottleneck for optical Earth Observation (EO) mission operations, often rendering downlinked data unusable and straining limited bandwidth budgets. This work presents a novel framework to improve actionable intelligence by integrating real-time atmospheric assessment and image restoration directly into the onboard image processing chain. To overcome the scarcity…