David Kroodsma

Today Global Fishing Watch releases the first version of our global database of anchorages. This database contains over 100,000 locations where AIS transmitting vessels congregated and includes large industrial ports, smaller fishing harbors, and individual docks and piers. For more information regarding the development of this dataset, ways in which you can contribute to its […]

Based on a lengthly review of refrigerated cargo vessels, we have just updated our transshipment data. You can read about the update here or download the slightly updated report and data here. The overall story of transshipments, as Nate notes in this post, is unchanged. This is a very rich dataset, giving the time and duration of thousands of

We published a logistic regression model for fishing localization a while a go as a python library built on top of scikit-learn. In this blog-post I’ll give you a quick introduction to how it can be used. The data we’re going to use is an AIS track exported from Google’s BigQuery, containing the columns timestamp (seconds since epoch), course (degrees) and speed (knots).

Today we published our initial research on transshipment at sea. Transshipment at sea is where a fishing vessel offloads its catch to a refrigerated cargo vessel (or “reefer”) far from port. You can download a copy of our report via this link. The image above was created by our data scientist Nate Miller, who has spent

For the first release of Global Fishing Watch, we included only vessels that had more than 1000 positions in a given year, and broadcast their identity as fishing vessels 100 percent of the time in their AIS identity messages. The list of these mmsi can be seen here. However, many vessels have fewer than 1000 position

Background One of the main outputs of the Global Fishing Watch project is the interactive map of global fishing. This map presented some particular challenges to implement. This blog post is about these challenges and our solutions to them. Vessel tracks are derived from time series data, that is, ordered points, each of which each have

The sample vessel track below shows position broadcasts of the Jin Sheng No.2, a Chinese fishing vessel with mmsi number 413270430. Over three weeks in March of 2015, this vessel steamed from the central Pacific to the coast of Japan, Korea, and China. While moving, a vessel broadcasts its position via AIS every 2 to