Satellite Imagery and AI: A New Era in Ocean Conservation, from Research to Deployment and Impact (Version. 2.0)

TL;DR

This paper presents four open-source computer vision models tailored for satellite data to detect illegal fishing activities, demonstrating their deployment in a real-time global maritime monitoring platform to enhance ocean conservation efforts.

Contribution

It introduces specialized models for various satellite sensors and provides best practices for deploying real-time satellite-based computer vision at a global scale.

Findings

Models are open source and sensor-specific.

Deployed successfully in Skylight platform.

Enable real-time monitoring of illegal fishing.

Abstract

Illegal, unreported, and unregulated (IUU) fishing poses a global threat to ocean habitats. Publicly available satellite data offered by NASA, the European Space Agency (ESA), and the U.S. Geological Survey (USGS), provide an opportunity to actively monitor this activity. Effectively leveraging satellite data for maritime conservation requires highly reliable machine learning models operating globally with minimal latency. This paper introduces four specialized computer vision models designed for a variety of sensors including Sentinel-1 (synthetic aperture radar), Sentinel-2 (optical imagery), Landsat 8-9 (optical imagery), and Suomi-NPP/NOAA-20/NOAA-21 (nighttime lights). It also presents best practices for developing and deploying global-scale real-time satellite based computer vision. All of the models are open sourced under permissive licenses. These models have all been deployed in Skylight, a real-time maritime monitoring platform, which is provided at no cost to users worldwide.