Eye on AI Weekly Research Watch
On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
· 2 min · Season 1
Show notes
Oil spills, algal blooms, and sediment floods harm marine ecosystems, and satellites could flag them early, but downlink bandwidth and onboard compute are limited. The authors propose a pipeline for multiand hyperspectral satellites: a self-supervised encoder compresses imagery into a compact latent space, and an anomaly detector flags deviations from normal sea patterns, compared against Isolation Forest, One-Class SVM, and Local Outlier Factor. Designed for embedded CPUs and AI accelerators, it prioritizes transmitting critical information. It is already integrated in missions including…
Website: share.transistor.fm
