Please select your home edition
Edition
Sailingfast 2018 2 728x90

Science blog: Machine learning and whale song

by Ann Allen, NOAA Fisheries 2 Nov 2018 15:13 UTC
A humpback whale surfaces near Maui Island © Hawaiian Islands Humpback Whale National Marine Sanctuary / Jason Moore

What do you do when you have too much data? It's not a question I've ever had to ask myself in my scientific career, and is rarely a problem when working with hard-to-study animals like whales and dolphins.

But this is exactly the question I found myself asking shortly after starting my new job with the Pacific Islands Fisheries Science Center's Cetacean Research Program in Hawaii in 2017. I was describing my job to my father, who is not a scientist, and trying to convey what we want to do.

We conduct research to understand the health and status of whale and dolphin species around U.S. Pacific Islands and across the Pacific Ocean, a VAST area. One tool we use to monitor elusive whales across this large region is a network of seafloor mounted recorders called high-frequency acoustic recording packages (HARPs).

The HARPs have hydrophones (underwater microphones) that can record the calls of whales and dolphins, as well as any environmental or human-made noise. We deploy HARPs for months to years at a time and we have to retrieve them to obtain data.

So far, our network extends to 13 different recordings sites, of which several have been monitored for a decade or more. This means we now have more than 200 TB of data, or almost 170,000 hours of recordings. If you were to sit and listen to all of that audio straight through it would take you more than 19 years. So if we monitor the whales by listening to their calls in the recordings, how in the world do you ever listen to that much data?

After telling my father all of this, he asked me, "Well why don't you just get those Shazam or Google people to help you? They teach computers to recognize human songs, I bet they can teach it whale song."

I paused. "Well, because it's just not that simple..."

"That's just not how you..."

"Because people have been..."

"Um well y'know, I don't know."

Thus challenged by my dad, I figured I'd find out if those Google people would be interested in teaching their computers to speak whale.

A friend who works for Google put me in contact with their Artificial Intelligence group. They responded almost immediately and enthusiastically; an ocean's worth of data sounded like it would fit in well with their current projects. They already have a lot of machine-learning techniques they've developed for other purposes that they would be excited to put to use for conservation. Machine learning attempts to mimic the learning process of the human brain by teaching a computer to carry out a task, rather than programming it to do the task step by step.

Automatic detection of whale calls isn't a new approach, but designing a good detector can be quite difficult. The ocean is a noisy place, with lots of sounds from wind, waves, fish, and even the recording equipment itself. And humans contribute an ever increasing amount of noise to the ocean, from things like container ships, oil and gas prospecting, military activities, and construction. The whale vocalizations themselves can also sound very different depending on how far away the whale is from the recorder, how it echoes off of the ocean floor and surface, and whether it has a local variation, or dialect, so to speak.

While some whales, such as blue whales and fin whales, make consistent, stereotyped calls that are relatively straightforward to recognize once you've seen some examples, humpback whales have vocalizations that are extremely variable. These calls make up phrases and themes that form songs. The songs change over time, as the whales incorporate new notes or swap the order of phrases, and many populations of humpbacks sing different songs. So how do you teach a computer to recognize whale song when the song keeps changing?

Researchers have been trying to solve this problem for quite a while. So far all the methods developed come with caveats: poor detection rates, a lot of user input to fine tune the detector for each call type and situation, or a high rate of false detections that require someone to go through by hand and pick out the correct detections from the bad ones.

However, there have been a lot of advancements in the last few years in artificial intelligence, and deep-machine learning. You may have noticed that your phone is much better about not making tie bows, I mean typos, when you use voice recognition these days. This is due to advances in machine learning, some made at Google. So with this in mind I figured I would throw Google in the deep end and see if they could come up with a solution to the complex humpback song problem. I gave them a subset of our audio data, with a collection of 'training labels', or humpback whale calls that are marked by a human (me). This training data is how the computer learns what humpback calls look like.

And it turns out that Google's computers are pretty good at recognizing humpback song! In less time than I thought possible (practically gale force speed by academic standards), they sent me timestamps of humpback whale song in our data. The computer isn't perfect yet, we still need to teach it to better recognize different kinds of noise from sites that didn't have as much training data, but it is already doing far better than expected.

There is so much new, important information we can learn from just knowing when there is humpback whale song throughout our dataset. In the Pacific Islands region, very little is known about humpback whale presence, seasonality, daily singing behavior, or population structure outside of the main Hawaiian Islands. We do not even know if humpback whales ever journey to some of the smaller and more remote uninhabited islands. With this data we can start to address these questions. Additionally, because our dataset spans more than a decade, knowing when and where humpback whales are singing will give us information on whether or not the animals have changed their distribution over the years, especially in relation to increasing human activity in some areas.

The possibilities don't stop there. We're now interested in teaching the computer to find other species of whales and dolphins in our recordings. The hope is that if we give the computer enough examples of different whale calls it will learn to generally recognize 'whale' sounds and get better at distinguishing between whale species and also between 'whale' and 'ship' or other noise. My hope is that in the future Google will provide us with a tool that scientists can directly use. A tool that we can provide new data, from a new location, and training labels for a new type of whale call, and it can then tell us where those calls are in the rest of the data.

So, if you're a scientist with acoustic data and labelled whale calls and want to help teach Google how to speak whale, whale then give us a call!

Check out more details of the story from the Google side:

Related Articles

OK Dinghy Worlds at Lake Garda overall
Andrew Mills wins after a epic week for the 212 helms Britain's Andrew Mills has won the 2025 OK Dinghy world championship after an epic week of racing on Lake Garda. With only one race possible on the final day, the result was academic to Mills, who was already discarding a second. Posted on 19 Sep
Black Foils: New boards and rudders for Geneva
Black Foils hope for a better weekend after test racing in light winds on Lake Geneva New boat configurations, fresh water and forecast light wind conditions leading to different crew numbers are set to make for a unique weekend as SailGP hits Geneva for the first time. Posted on 19 Sep
Formia to Host 450+ Sailors for ILCA Master Worlds
Sailors from 31 nations have arrived in Italy The 2025 ILCA Master World Championships officially kicked off today in Formia, Italy. This year's event has drawn over 450 sailors from 31 nations, making it one of the largest gatherings of the ILCA Master community worldwide. Posted on 19 Sep
Switzerland SailGP Team ready to go 'all in'
Team is in full fight mode ahead of its long-awaited home debut this weekend The Switzerland SailGP Team is in full fight mode ahead of its long-awaited home debut this weekend at the Rolex Switzerland Sail Grand Prix, taking place between 15:30 - 17:00 on Saturday 20 - Sunday 21 September in Geneva. Posted on 19 Sep
North Sails Ferrari Hypersail apparel partnership
Bringing together two iconic brands at the forefront of performance and innovation North Sails today announced a multi-year partnership with Ferrari that brings together two iconic brands at the forefront of performance and innovation in sailing and motorsport. Posted on 19 Sep
SailGP prepares for high-stakes Lake Geneva debut
A weekend of tactical, light-air racing on the horizon The Rolex Switzerland Sail Grand Prix begins tomorrow with a weekend of tactical, light-air racing on the horizon. All twelve national teams hit the water today, getting in essential practice laps in the only freshwater venue of the season. Posted on 19 Sep
Emirates GBR ready for jeopardy on Lake Geneva
Strategist Hannah Mills looking to pick the right shifts Fresh from a win in Saint-Tropez last weekend, Emirates GBR is ready for jeopardy on Lake Geneva as SailGP prepares for the second event of the back-to-back European double-header, the Rolex Switzerland Sail Grand Prix. Posted on 19 Sep
Ibiza JoySail Day 2
A race around the island of Formentera with its dramatic coastline A brisk easterly wind greeted the 22-strong fleet on the second day. With a scheduled race around the island of Formentera, the fleet left the dock mid-morning to ensure reaching the start line some 13nm from the 'home' of the regatta in Marina Ibiza. Posted on 19 Sep
37 days to the Transat Café L'or
72 boat fleet includes 18 female skippers On Sunday, October 26, at 2pm local time the 72 boats registered for the 17th edition of the TRANSAT CAFÉ L'OR Le Havre Normandie will set sail on the most famous double-handed transatlantic race. Posted on 19 Sep
Uncertainty reigns across Biscay in Défi Azimut
A cracking start for Charal, leading the fleet off the Glénans archipelago Doubt lingers this Thursday regarding the intentions of the wind gods off the coast of Lorient, Brittany. Will the fleet have enough breeze to fill their sails throughout the rectangular course concocted by Race Management? Posted on 19 Sep
Doyle_SailWorld_728X90px_SY BOTTOMAllen SailingArmstrong 728x90 - Wing FG Board Range - BOTTOM