Little-to-No Industrial Fishing Occurs in Fully and Highly Protected Marine Areas
Jennifer Raynor; Sara Orofino; Christopher Costello; Gavin McDonald; Juan Mayorga; Enric Sala · 2025-07-24
Using AI and satellite-based Earth observation (AIS and SAR), this study analyzes fishing activity within the world’s most strictly protected marine areas. Contrary to widespread belief, it finds minimal industrial fishing in fully and highly protected MPAs—just one fishing vessel per 20,000 km² on average, nine times lower than in unprotected waters. The study emphasizes the value of real enforcement data over IUCN self-reporting, offering a rigorous global baseline for evaluating marine conservation effectiveness.
Jennifer Raynor; Sara Orofino; Christopher Costello; Gavin McDonald; Juan Mayorga; Enric Sala. 2025-07-24. Little-to-No Industrial Fishing Occurs in Fully and Highly Protected Marine Areas. https://www.science.org/doi/10.1126/science.adt9009 (AI & Environment Resource Hub; record paper-351; collection snapshot 2026-09-15).
Classification and context
Included in the original Scientific Paper collection. Labels below are metadata based suggestions. They are not verified findings, claims of effectiveness, or endorsements.
A paper listing is not a quality assessment. Peer review and findings require source-level confirmation. Source link reachable · checked 2026-09-15. Source identity and required metadata verified. The import date is not the original date added.
This study introduces a new foundation model based on the Prithvi-EO Vision Transformer, pre-trained on Sentinel-3 ocean color data, to enhance marine Earth observation. By fine-tuning on chlorophyll and primary production tasks, the model outperforms traditional baselines, showing that self-trained AI can extract detailed spatial patterns from limited labeled data and improve monitoring of ocean ecosystems and climate processes.
arXiv
Shared topics: Research tools and geospatial methods; Water; Biodiversity and ecosystems; Oceans and coasts
CyFi is a command line tool that uses satellite imagery and machine learning to estimate cyanobacteria levels in small, inland water bodies. Cyanobacteria is a type of harmful algal bloom (HAB), which can produce toxins that are poisonous to humans and their pets, and can threaten marine ecosystems.
Source metadata availablefree
Shared topics: Research tools and geospatial methods; Water; Biodiversity and ecosystems; Oceans and coasts
The granite-geospatial-ocean foundation model was jointly developed by IBM and STFC as part of a collaboration with the University of Exeter and Plymouth Marine Lab under the UK HNCDI programme. This pre-trained model supports a range of potential use cases in ocean ecosystem health, fisheries management, pollution and other ocean processes that can be monitored using ocean colour observations.
Source metadata availablefreemium
Shared topics: Water; Biodiversity and ecosystems; Oceans and coasts
