Scientists use artificial intelligence to eavesdrop on dolphins

[Judi Lynn]

Algorithm enables research team to sift through millions of echolocation clicks made by marine mammals in the Gulf of Mexico
Josh Gabbatiss Science Correspondent 5 hours ago

Scientists have developed an algorithm to monitor the underwater chatter of dolphins with the help of machine learning.

Using autonomous underwater sensors, researchers working in the Gulf of Mexico spent two years making recordings of dolphin echolocation clicks.

The result was a data set of 52 million click noises.

To sort through this vast amount of information, the scientists employed an “unsupervised” algorithm that automatically classified the noises into categories.

More:
http://www.independent.co.uk/news/science/artificial-intelligence-dolphin-eavesdrop-scientist-ai-gulf-mexico-a8099676.html

[Judi Lynn]

1. Can data save dolphins? How scientists are using NASA data to study link between solar storms and an

Can data save dolphins? How scientists are using NASA data to study link between solar storms and animal beachings
December 8, 2017 by Lina Tran

The age-old mystery of why otherwise healthy dolphins, whales and porpoises get stranded along coasts worldwide deepens: After a collaboration between NASA scientists and marine biologists, new research suggests space weather is not the primary cause of animal beachings—but the research continues. The collaboration is now seeking others to join their search for the factors that send ocean mammals off course, in the hopes of perhaps one day predicting strandings before they happen.
 
Scientists have long sought the answer to why these animals beach, and one recent collaboration hoped to find a clear-cut solution: Researchers from a cross-section of fields pooled massive data sets to see if disturbances to the magnetic field around Earth could be what confuses these sea creatures, known as cetaceans. Cetaceans are thought to use Earth's magnetic field to navigate. Since intense solar storms can disturb the magnetic field, the scientists wanted to determine whether they could, by extension, actually interfere with animals' internal compasses and lead them astray.

During their first investigation, the scientists—from NASA's Goddard Space Flight Center in Greenbelt, Maryland; the International Fund for Animal Welfare, or IFAW; and the Bureau of Ocean Energy Management, or BOEM—were not able to hammer down a causal connection.

"We've learned so far there is no smoking gun indicating space weather is the primary driver," said Goddard space weather scientist Antti Pulkkinen. "But there is a sense that geomagnetic conditions may be part of a cocktail of contributing factors."

Read more at: 
https://phys.org/news/2017-12-dolphins-scientists-nasa-link-solar.html

[InAbLuEsTaTe]

2. Interesting. Maybe some of these highly intelligent mammals could be convinced to run for Congress.

[Judi Lynn]

3. AI eavesdrops on dolphins and discovers six unknown click types

Computer program picked out the noises from underwater recordings of 52 million echolocation signals
BY MARIA TEMMING 2:00PM, DECEMBER 7, 2017



A new computer program has an ear for dolphin chatter.

The algorithm uncovered six previously unknown types of dolphin echolocation clicks in underwater recordings from the Gulf of Mexico, researchers report online December 7 in PLOS Computational Biology. Identifying which species produce the newly discovered click varieties could help scientists better keep tabs on wild dolphin populations and movements.

Dolphin tracking is traditionally done with boats or planes, but that’s expensive, says study coauthor Kaitlin Frasier, an oceanographer at the Scripps Institution of Oceanography in La Jolla, Calif. A cheaper alternative is to sift through seafloor recordings — which pick up the echolocation clicks that dolphins make to navigate, find food and socialize. By comparing different click types to recordings at the surface — where researchers can see which animals are making the noise — scientists can learn what different species sound like, and use those clicks to map the animals’ movements deep underwater.

But even experts have trouble sorting recorded clicks, because the distinguishing features of these signals are so subtle. “When you have analysts manually going through a dataset, then there’s a lot of bias introduced just from the human perception,” says Simone Baumann-Pickering, a biologist at the Scripps Institution of Oceanography not involved in the work. “Person A may see things differently than person B.” So far, scientists have only determined the distinct sounds of a few species.

More:
https://www.sciencenews.org/article/ai-eavesdrops-dolphins-and-discovers-six-unknown-click-types

[Duppers]

4. Most interesting articles.

Perhaps humans can learn something and are able to help. Thank you for posting these.

My son works in "machine learning" btw - I sent this thread's link to him.