Vessel names are taken directly from the AIS message a vessel broadcasts. Transmitters sometimes have errors or are not always properly configured. In some cases, we are able to match vessels to fishing registries and will use the name from there.
Global Fishing Watch believes that transparency of fishing activity is key to achieving sustainable global fisheries. Proper fisheries management is key to securing the incomes of fishers in the long term, including small scale fishing vessels which constitute a great proportion of some nations’ fishery. In the case of Indonesia, over 90% of the country’s [...]
No. Commercial fishing fleets are already using sophisticated technology such as helicopters, tracking beacons, fish-finding sonar and even fish forecasts based on satellite data to find and catch fish. Global Fishing Watch shows where fishing activity has apparently occurred; it doesn’t predict where fish are likely to be in the future. The 72-hour time lag [...]
The VMS data remains under the ownership of the respective national authorities and we cannot release it publicly beyond displaying it on our map.
The raw AIS data we use is commercial data and we cannot make it freely available to the public. However, we have created a sample dataset of labeled anonymized AIS data that can be used to train fishing prediction models. For some projects, you may need access to detailed position data for individual vessels that [...]
To download our data or access our code, log into our data portal with your Global Fishing Watch account (same info as your globalfishingwatch.org/map login) and select the dataset that you would like to download. Data are also available via Google’s BigQuery and Earth Engine platforms. See our data blog for more information on accessing [...]
The AIS data you see spans from January 1, 2012 to 72 hours prior to the present time. VMS data is published with a delay agreed on with the specific government. VIIRS data is published with a 12 hour lag.
Every point on the map is apparent fishing activity as recognized by our algorithm.
The Global Fishing Watch detection algorithm is a best effort to mathematically identify “apparent fishing activity” by using machine learning at a global scale. It is based on thousands of “training segments” that humans with expertise in fishing have manually classified. Just like humans, the algorithm will make some mistakes. Over time, this will continue [...]
Global Fishing Watch processes data using machine learning to identify where and when fishing is occurring on a global scale. We’re employing a class of machine learning models called neural networks (NNs) to help us process all those AIS or VMS messages and to help us determine commercial fishing activity based on the vessel’s movements [...]
We get our data from a combination of commercial and government sources. For satellite and terrestrial vessel-tracking AIS data, we buy the data from commercial satellite operators Spire, ORBCOMM and exactEarth. We also receive VMS vessel tracking data directly from participating countries. We use satellite imagery that is produced by NASA, The Earth Observation group [...]
We are working with several countries to publish their VMS data and others are working towards committing to publish their VMS data.
No matter what the industry, increasing transparency is always met with some anxiety from some corners. These are the concerns we’ve heard: Sharing VMS is an invasion of privacy and it reveals fishing grounds to competitors. Larger vessels fishing are already required to reveal this information by carrying publicly broadcast AIS. In addition, vessels fishing [...]
Global Fishing Watch believes that fishing should be fully transparent. Transparency does not have to be instantaneous. A delay to the public dissemination is entirely reasonable, but the dissemination must contain the information needed to make the activity of the vessel and the catch clearly understood. It is the fact that fishers are aware that [...]
Global Fishing Watch displays vessel locations from AIS data with a 72 hour lag. VMS data is redacted slightly, aggregated and delayed in the public map. Being displayed in Global Fishing Watch does not compromise a vessel’s commercial catch – commercial fishing fleets are already using sophisticated technology such as helicopters, tracking beacons, fish-finding sonar [...]