fbpx
Connect with us

Conservation

Can We Learn To Talk With Whales? Introducing Project CETI

Inspired by “search for extraterrestrial intelligence” or SETI, project leader Dr. David Gruber and an eclectic band of scientists and researchers seek to decipher the language of sperm whales, which might be described as enigmatic aliens living in our midst. To do this, they are applying the latest technology including AI, cryptography, machine learning, and robotics.

Published

on

Header image: Sperm whales socializing. Photo by Brian J. Skerry

Companion story: Exploring Whale Culture: An Interview With NatGeo Photojournalist Brian Skerry

Project CETI (Cetacean Translation Initiative), a non-profit organization, with the help of the 2020 TED Audacious Project, is applying advanced machine learning and gentle robotics to decipher the communication of the world’s most enigmatic ocean species: the sperm whale. In interpreting their voices and hopefully communicating back, we aim to show that today’s most cutting-edge technologies can be used to benefit not only humankind, but other species on this planet. By enabling humans to deeply understand and protect the life around us, we thereby redefine our very understanding of the word “we.”

As with the Earthrise photo from Project Apollo, CETI’s discoveries and progress have the potential to significantly reshape humanity’s understanding of its place on this planet. By regularly sharing our findings with the public—through partners like the National Geographic Society—CETI will generate a deeper wonder for Earth’s matrix of life on earth, and provide a uniquely strong boost to the new phase of broader environmental movement.

Founded and led by scientists, CETI has brought together leading cryptographers, roboticists, linguists, AI experts, technologists and marine biologists to:

● Develop the most delicate robotics technologies, including partnership with National Geographic Society’s Exploration Technology Lab to listen to whales and put their sounds into context.

● Deploy a “Core Whale Listening System,” a novel hydrophone array to study a population of whales in a 20×20 kilometer field site.

● Build on substantial data on the whales’ sounds, social lives, and behavior already obtained by the Dominica Sperm Whale Project.

● Create a bespoke, big data pipeline to examine the recorded data and decode it using advanced machine learning, natural language processing and data science.

● Launch a public interface, data visualization, communications platform and leadership initiative in collaboration with key partners to engage and foster the global community.

WHY SPERM WHALES?

Sperm whales have the largest brains of any species and share traits strikingly similar to humans. They have higher-level functions such as conscious thought and future planning, as well as speech and feelings of compassion, love, suffering and intuition. They live in matriarchal and multicultural societies and have dialects and strong multigenerational family bonds. Modern whales have been great stewards of the ocean environment for more than 30 million years, having been here for five times longer than the earliest hominids. Our understanding of these animals is just beginning.



WHY NOW?

In the late 1960s, scientists, including principal CETI advisor Dr. Roger Payne, discovered that whales sing to one another. His recordings, Songs of the Humpback Whale, sparked the “Save the Whales” movement, one of the most successful conservation initiatives in history. The campaign eventually led to the Marine Mammal Protection Act that marked the end of large-scale whaling and saved several whale populations from extinction.

All this by just hearing the sounds of whales. Imagine what would happen if we could understand them and communicate back. For the first time in history, advances in engineering, artificial intelligence and linguistics have made it possible to understand the communication of whales and other animals more substantially. Our species is at a critical juncture, one where we can work together with the help of compassionate technologies to build a brighter, more connective and equitable future. CETI also hopes to provide a blueprint for future ambitious, collaborative initiatives that can help us on this journey.

Figure 1: An interdisciplinary approach to sperm whale communication that integrates  biology, robotics, machine learning, and linguistics expertise, and comprise the following key  steps. Record: collect large-scale longitudinal multi-modal dataset of whale communication  and behavioral data from a variety of sensors. Process: reconcile and process the multi sensor data. Decode: using machine learning techniques, create a model of whale  communication, characterize its structure, and link it to behavior. Encode & Playback: conduct interactive playback experiments and refine the whale language model. Illustration  © 2021 Alex Boersma.
Figure 2: Sperm whale bioacoustic system. A: Sperm whale head contains the  spermaceti organ (c), a cavity filled with almost 2,000 litres of wax-like liquid, and the junk  compartment (f), comprising a series of wafer-like bodies believed to act as acoustic lenses.  The spermaceti organ and junk act as two connected tubes, forming a bent, conical horn of  about 10m in length and 0.8m aperture in large mature males. The sound emitted by the  phonic lips (i) in the front of the head is focused by traveling through the bent horn,  producing a flat wavefront at the exit surface. B: Typical temporal structure of sperm whale  echolocation and coda clicks. Echolocation signals are produced with consistent inter-click  intervals (of approximately 0.4 sec) while coda clicks are arranged in stereotypical  sequences called ‘codas’ lasting less than 2 sec. Codas are characterized by the different  number of constituent clicks and the intervals between them (called inter-click intervals or  ICIs). Codas are typically produced in multiparty exchanges that can last from about 10  seconds to over half an hour. Each click, in turn, presents itself as a sequence of equally spaced pulses, with inter-pulse interval (IPI) of an order of 3-4 msec in an adult female,  which is the result of the sound reflecting within the spermaceti organ. Illustration © 2021  Alex Boersma.
Figure 3: Comparative size of datasets used for training NLP models (represented by  the circle area). GPT-3 is only partially visible, while the dataset of the Dominica Sperm  Whale Project is a tiny dot on this plot (located at the center of the dashed circle). Shown in  
red is the estimated size of a new dataset planned to be collected in Dominica by Project  CETI, an interdisciplinary initiative for cetacean communication interpretation. The estimate  is based on the assumption of nearly continuous monitoring of 50-400 whales. The estimate  assumes 75-80% of their vocalizations constituting echolocation clicks, and 20-25% being  coda clicks. A typical Caribbean whale coda has 5 clicks and lasts 4 sec (including a silence  between two subsequent codas), yielding a rate of 1.25 clicks/sec. Overall, we estimate it  would be possible to collect between 400M and 4B clicks per year as a longitudinal and  continuous recording of bioacoustic signals as well as detailed behavior and environmental  data.
Figure 4: Schematic of whale bioacoustic data collection with multiple data sources by  several classes of assets. These include tethered buoy arrays (b), which track the whales in  a large area in real-time by continuously transmitting their data to shore (g), floaters (e), and  robotic fishes (d)Tags (c) attached to whales can possibly provide the most detailed  bioacoustic and behavioral data. Aerial drones (a) can be used to assist tag deployment  (a1), recovery (a2) and provide visual observation of the whales (a3). The collected  multimodal data (1) has to be processed to reconstruct a social network of sperm whales.  The raw acoustic data (2) has to be analyzed by ML algorithms to detect (3) and classify (4)  clicks. Source separation and identification (5) algorithms would allow reconstructing  multiparty conversations by attributing different clicks to the whales producing them.  Illustration © 2021 Alex Boersma.

Additional Resources:

Meet The Project CETI Team

Cornell University: Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales by the current scientific members of Project CETI collaboration. April 2021

Harvard School of Engineering: Talking with whales

Project aims to translate sperm whale calls April 2021

National Geographic: Groundbreaking effort launched to decode whale language. With artificial intelligence and painstaking study of sperm whales, scientists hope to understand what these aliens of the deep are talking about. April 2021

National Geographic: David Gruber: Researching with respect and a gentler touch—National Geographic Explorer David Gruber and his team are taking a delicate approach to understanding sperm whales. March 2021

TED Audacious: What if we could communicate with another species? SEP 2020

Simons Institute: Sperm Whale Communication: What we know so far/ Understanding Whale Communication: First steps AUG 2020 with David Gruber

Community

Conservation Through Genetics: Introducing the Marine Genome Project

Published

on

By

Photos courtesy of Marine Genome Project
The image shows a tissue sample of red algae after homogenization to release the DNA from the supernantent
.

The Marine Genome Project (MGP) is a nonprofit organization founded by two avid divers Daniel Ortega and David Mulé with a desire to promote ocean conservation. MGP’s mission is to collect genetic information from marine organisms with the intention of creating science-based educational resources.  MGP plans on achieving this by creating an open source system to aid in preservation projects that spread  awareness about the fragility of marine species and the ecosystems they inhabit. 

Daniel Ortega Cave Diving in Tulum.

Daniel Ortega is in his early twenties. He grew up spending endless hours begging his parents to let him learn how to scuba dive. Like many children figure out at a young age, if he was persistent in bugging his parents, they would eventually give in to the demands. Even if it was just to get him to finally shut up about scuba diving. Daniel got certified at the age of 12 and has been diving ever since, he’s been working full time in the diving industry for 4 years. He currently holds numerous recreational, teaching, and technical diving qualifications including GUE Tech 1 and Cave 1. Daniel has been passionately dedicated to protecting the underwater environment from a young age, and this is what sparked his desire to start The Marine Genome Project (MGP) which is dedicated to protecting the ocean and the species that live within for years to come.

Daniel couldn’t have started The Marine Genome Project without his friend and fellow GUE Tech 1 and Cave 1 teammate, Dave Mulé. As one of the founders of The Marine Genome Project, Dave’s work has been crucial in guiding its behind-the-scenes infrastructure. As a practicing lawyer and avid diver, his talents have been well suited to building MGP’s support structures. 

David Mulé.

The duo have talked about what their future in diving would look like for years. They tossed around the idea of everything from opening their own dive shop, to buying a vessel to turn into a research diving vessel. While years ago they didn’t have the idea that you see today, one thing was for sure: it was going to involve diving and protecting their favorite place on earth, the ocean.

After a few years, the team settled on starting MGP. Daniel noticed two common factors that he felt were lacking in some of the other major organizations dedicated to ocean conservation.  First, was the lack of transparency in the conducted research and how the data was being used to help marine ecosystems. Daniel is a firm believer in the philosophy that if you can’t understand the solution, you can’t understand the problem.  The second factor was the lack of community involvement. Many major organizations are not efficient at involving the community in their work.  MGP believes in actively involving communities in every step of its mission and scientific process. 

MGP wants everybody to understand and appreciate how genetics can be used as a vital tool for marine conservation.  Although science may seem confusing to many, it does not have to be that way. Genetics in simple terms is the study of genes and genetic variation of organisms. The field of genetics is often confusing and misunderstood by those who are not trained in the field; but, as Daniel would say “if I can do it, you can do it.”

To allow our communities to better participate, MGP started a page on its website called the “Science Spot.” The page breaks down the scientific methods and procedures used by our research team into bite sized chunks. The team wanted to lower the barrier of entry into science and marine preservation work. On this page people can learn everything from what genetic information is to how it is collected. 



Let’s talk about the geeky side of our mission. DNA is the instructions determining what an organism might look like, what it might eat, how long it might live, and other vital information. DNA is made up of a five carbon sugar phosphate group with a nitrogenous base made up of nucleotides. The nucleotides in DNA are A,T,G,C. These Nucleotides pair together to form a base pair. The nucleotides follow rules, such as, A pairs only to T and G pairs only to C, except in RNA then A pairs to U which substitutes in place of T. The ordered reading of these base pairs is what allows us to see how an organism’s cell would function. 

The photo shows a run of DNA extracted from marine algae, in a visualization process called Gel Electrophoresis. Sometimes the runs don’t turn out great, as extracting viable DNA from plants is notoriously difficult as seen by the smearing and damaged DNA.

Now that we have a basic understanding of what DNA is, we need to learn how to visualize it. Visualizing DNA used to be extremely difficult. The machines would take up half a room, run for months on end, and cost exorbitant amounts of money. With the passing of time, things have changed; whole genomes can be sequenced in the field and with devices as big as your mobile phone. One that we use is a Nanopore sequencer. It works by using a flow cell with many little microscopic holes in it which sits in an electro-resistant membrane attached to electrodes. When these nucleotides pass through the nanopore membrane, the current in the membrane is distrusted, creating an electrical reading. This reading is then translated to the corresponding nucleotides. 

This information can then be read and compared to known sequences to detect changes in nucleotide sequences. This can help researchers better understand the effects of external environmental stressors on the heritability of genes among other uses. With the collected information MGP is able to provide data supporting potential detrimental damage to marine environments, with possible avenues that can be pressured for solutions.

With the fast pace changes we are seeing in science and technology, we now have more tools at our fingertips for protecting our underwater world. At the end of the day, the idea behind MGP was to bring a mutual respect and love for the environment to the general public. When we can respect and love something we are more willing to protect it. The Marine Genome Project team would like to encourage everybody to get involved in your community in protecting the sites that we cherish everyday, so others can cherish the sites tomorrow. 

For more information see: Marine Genome Project (MGP)

The eventual goal for MGP is to move into collecting tissue samples of marine vertebrates such as the French Grunts seen above. These vertebrate species can give us valuable insights into the overall health of the ecosystem, and provide possible tracking metrics for measuring changes in the ecosystem due to external stressors.
Continue Reading

Thank You to Our Sponsors

Subscribe

Education, Conservation, and Exploration articles for the diving obsessed. Subscribe to our monthly blog and get our latest stories and content delivered to your inbox every Thursday.

Latest Features