Google looks to AI to help save the coral reefs
What specific AI tool did Google develop to aid marine biologists in studying coral reef ecosystems?
Google developed an AI tool called SurfPerch to aid marine biologists in studying coral reef ecosystems3. This tool was created in collaboration with Google Research and DeepMind and was trained on thousands of hours of audio reef recordings3. It allows scientists to "hear reef health from the inside," track reef activity at night, and monitor reefs in deep or murky waters3.
How does the SurfPerch AI tool function to assess the health of coral reefs?
The SurfPerch AI tool, developed by Google and DeepMind, functions to assess the health of coral reefs by analyzing underwater audio recordings. Trained on thousands of hours of audio reef recordings, SurfPerch can detect the diversity and patterns of behavior of animals on reefs, allowing scientists to "hear reef health from the inside." This innovative tool can track reef activity at night and even survey reefs in deep and murky waters.
The project began by inviting the public to listen to reef sounds via the web, resulting in a "bioacoustic" dataset focused on reef health. By crowdsourcing this activity, Google was able to create a library of new fish sounds that were used to fine-tune the AI tool. Now, SurfPerch can be quickly trained to detect any new reef sound, making it a powerful tool for understanding and conserving coral reef ecosystems.
How did the crowdsourced bioacoustic data contribute to the development of the SurfPerch AI tool?
The crowdsourced bioacoustic data contributed significantly to the development of the SurfPerch AI tool. Visitors to Google's Calling in our Corals website listened to over 400 hours of reef audio from sites around the world and were told to click when they heard a fish sound. This resulted in a "bioacoustic" dataset focused on reef health. By crowdsourcing this activity, Google was able to create a library of new fish sounds that were used to fine-tune the AI tool, SurfPerch. This process allowed for the efficient analysis of new datasets and opened new opportunities to understand reef communities and conservation efforts.