Google uses AI to spot illegal fishing in seas
Tech giant Google is using image-recognition technology imbued with artificial intelligence to spot illegal fishing in the seas, a report said.
Google uses the technology to identify illegal fishing the same way it teaches a machine to identify a horse or a cat, said Kate E Brandt, Google’s sustainability lead, in the report by Forbes.
In this case, the internet giant’s machine-learning algorithms make use of the publicly broadcast Automatic Identification System (AIS) for shipping to spot illegal fishing. (Machine learning is a subset of artificial intelligence.) Google’s engineers use AIS to plot the course of the ship, read the pattern of its movement and then predict what the ship is doing in the seas.
“All 200,000 or so vessels on the sea at any one time are pinging out this public notice saying ‘this is where I am, and this is what I am going,” Brandt was quoted as saying. This means that at least 22 million data points are generated by AIS, which can be turned into machine intelligence.
“With that dataset, and working with a couple of wonderful NGOs – Oceana and Sky Truth – we were able to create Global Fishing Watch – a real-time heat map that shows where fishing is happening,” Brandt said in the report.
The sustainability lead also said that this has led to positive outcomes such as identification of suspicious activity in waters under the jurisdiction of the Pacific island nation of Kiribati, which include the world’s largest Unesco heritage marine site. Unesco is United Nations Educational, Scientific and Cultural Organization.
“What’s really exciting is that this creates tremendous opportunities for governments and citizens to protect our marine resources. Fishing in those marine reserves is illegal and Global Fishing Watch has been used to protect those reserves,” Brandt was quoted as saying.
Separately, Google is also using artificial intelligence to help people put solar panels on their rooftops. Just by studying images the Google Earth's library, Google can predict the best spot to put up solar panels for maximum power generation.