Self-supervised anomaly detection for Ocean Networks Canada underwater acoustic data using SSAMBA and Mamba-based audio representation learning.
-
Updated
Jun 12, 2026 - Jupyter Notebook
Self-supervised anomaly detection for Ocean Networks Canada underwater acoustic data using SSAMBA and Mamba-based audio representation learning.
Python package for ocean acoustics modeling and data analysis.
Synthetic underwater acoustic waveforms for self-supervised learning. 12,000 5-second clips at 16 kHz covering 4 vessel classes + no-vessel ambient. Non-overlapping shaft rates, blade-gated cavitation bursts, Knudsen-model sea noise. License: TBD by Altair Infrasec Pvt. Ltd. Contact styagi@oravontsystems.com for details
Five LLMs, one physics prompt, one ground truth — a blind benchmark that scores AI-generated 3D underwater acoustic ray-propagation panels against a real BELLHOP3D run on data, not pixels. Vanilla JS + raw WebGL, zero dependencies, one shared harness.
Add a description, image, and links to the ocean-acoustics topic page so that developers can more easily learn about it.
To associate your repository with the ocean-acoustics topic, visit your repo's landing page and select "manage topics."