Long-term, large-scale ocean observing systems, including the Ocean Observatories Initiative (OOI), Ocean Networks Canada (ONC), Argo, GO-BGC, and IOOS networks, among others, generate high-density, multi-stream datasets at a volume and complexity that increasingly exceed the capacity of traditional analysis approaches. Advances in artificial intelligence (AI) and machine learning (ML) offer powerful tools for rapidily processing these data at scale and reveal patterns and scientific insights that would otherwise remain undetected. We invite contributions highlighting observatory science enhanced by AI and ML, including but not limited to: seismic and acoustic event detection; computer vision applications; integration with modeling and data assimilation workflows; quality assurance, quality control, and anomaly detection; autonomous platform control, data reduction and adaptive sampling; and cross-platform data synthesis. Work addressing model interpretability, training data limitations, and reproducibility is especially encouraged. Contributions are welcome across disciplines, including physical oceanography, biogeochemistry, marine ecology, and solid Earth science.
Submit and Abstract for this Session
Primary Convener:
- Katharine Bigham
- University of Washington Seattle Campus
Conveners:
- Ben Biffard
- Ocean Networks Canada, University of Victoria
- Martin Scherwath
- University of Victoria
Student/Early Career Convener:
- Ada Carter
- University of Washington Seattle Campus