Demonstrating Onboard Inference for Earth Science Applications with Spectral Analysis Algorithms and Deep Learning

2025-08-20

AI Summary

To address the challenges of limited downlink bandwidth and poor ground-based processing timeliness for Earth observation satellite data, this study achieves, for the first time on the CogniSAT-6/HAMMER (CS-6) satellite, onboard fusion inference integrating deep learning with spectral analysis algorithms. Leveraging space-qualified neural network acceleration hardware and an edge computing architecture, the system performs real-time on-orbit inference directly on visible–near-infrared hyperspectral imagery, supporting multiple tasks including land-cover classification and anomaly detection. Key contributions are: (1) the first deployment of a lightweight deep learning model synergistically co-executing with physics-driven spectral feature extraction and classification algorithms on radiation-hardened AI hardware; and (2) a >90% reduction in raw data downlink volume, enabling sub-minute observational response latency. This work establishes a validated technical paradigm and engineering pathway for intelligent remote-sensing satellites.

Technology Category

Computer Vision: Remote Sensing / Geospatial AIMachine Learning: Hardware-aware MLIntelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsEconomics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In partnership with Ubotica Technologies, the Jet Propulsion Laboratory is demonstrating state-of-the-art data analysis onboard CogniSAT-6/HAMMER (CS-6). CS-6 is a satellite with a visible and near infrared range hyperspectral instrument and neural network acceleration hardware. Performing data analysis at the edge (e.g. onboard) can enable new Earth science measurements and responses. We will demonstrate data analysis and inference onboard CS-6 for numerous applications using deep learning and spectral analysis algorithms.

Problem

• Demonstrating onboard inference for Earth science applications
• Performing data analysis at the edge using deep learning
• Enabling new Earth science measurements and responses

Innovation

• Onboard inference with deep learning algorithms
• Hyperspectral data analysis using neural networks
• Edge computing for real-time Earth science measurements