Science News

Robots and Artificial Intelligence Help Scientists to Understand the Deep-Sea

Artificial intelligence (AI) could help scientists shed new light on the variety of species living on the ocean floor, according to new research led by the University of Plymouth.

With increasing threats facing the marine environment, scientists desperately need more information about what inhabits the seabed to inform conservation and biodiversity management.

EM1 . montage item rectangular M116 13331848 13109043018173A ray swimming away from the vehicle. The grey ball, left of the ray, is a xenophyophore: the largest known single-celled organism on the planet and one of the most abundant organisms in our images. Image taken by the AutoSub6000 in the North East Atlantic

Autonomous underwater vehicles (AUV) mounted with the latest cameras are now able to collect vast amounts of data, but a bottleneck is still created by humans having to process it.

In a new study published in Marine Ecology Progress Series, marine scientists and robotics experts tested the effectiveness of a computer vision (CV) system in potentially fulfilling that role.

They showed on average it is around 80 percent accurate in identifying various animals in images of the seabed but can be up to 93 percent accurate for specific species if enough data is used to train the algorithm.

This, scientists say, demonstrates CV could soon be routinely employed to study marine animals and plants and lead to a major increase in data availability for conservation research and biodiversity management.

EM2 montage item rectangular M116 13331848 13109017289577A community of various sponges and associated mobile animals. The squat-lobsters are relatively abundant in this area and probably play an important role within the ecosystem. Image taken by the AutoSub6000 in the North East Atlantic

Ph.D. student Nils Piechaud, lead author on the study, said: “Autonomous vehicles are a vital tool for surveying large areas of the seabed deeper than 60 meters (the depth most divers can reach). But we are currently not able to manually analyze more than a fraction of that data. This research shows AI is a promising tool, but our AI classifier would still be wrong one out of five times if it were used to identify animals in our images.

“This makes it an important step forward in dealing with the huge amounts of data being generated from the ocean floor and shows it can help speed up analysis when used for detecting some species. But we are not at the point of considering it a suitable complete replacement for humans at this stage.”

Dr. Kerry Howell, Associate Professor in Marine Ecology and Principal Investigator for the Deep Links project, added: “Most of our planet is deep sea, a vast area in which we have equally large knowledge gaps. With increasing pressures on the marine environment including climate change, it is imperative that we understand our oceans and the habitats and species found within them.

“In the age of robotic and autonomous vehicles, big data, and global open research, the development of AI tools with the potential to help speed up our acquisition of knowledge is an exciting and much-needed advance.”

The study was conducted as part of Deep Links, a research project funded by the Natural Environment Research Council, and led by the University of Plymouth, in collaboration with Oxford University, British Geological Survey and the Joint Nature Conservation Committee.

One of the UK’s national AUVs – Autosub6000, deployed in May 2016 – collected more than 150,000 images in a single dive from around 1200 meters beneath the ocean surface on the north-east side of Rockall Bank, in the North East Atlantic. Around 1,200 of these images were manually analyzed, containing 40,000 individuals of 110 different kinds of animals (morphospecies), most of them only seen a handful of times.

EM 3 montage item rectangular M116 13331848 13109057740065A large starfish (possibly a species of the genus Hymenaster). This animal has only been seen a handful of times, which limits the amount of training material for the AI, making manual analysis more suited to measure its abundance. Image taken by the AutoSub6000 in the North East Atlantic

Researchers then used Google’s Tensorflow, an open access library, to teach a pre-trained Convolutional Neural Network (CNN) to identify individuals of various deep-sea morphospecies found in the AUV images. They then assessed how the CNN performed when trained with different numbers of example images of animals, and different numbers of morphospecies to choose from.

The accuracy of manual annotation by humans can range from 50–95 percent, but this method is slow, and even specialists are very inconsistent across time and research teams. This automated method reached around 80 percent accuracy, approaching the performance of humans with a clear speed and consistency advantage.

This is particularly true for some morphospecies that the algorithms work very well with. For example, the model correctly identifies one animal (a type of xenophyophore) 93 percent of the time.

EM 4 montage item rectangular M116 13331848 13109062349032Some animals attach themselves to rocks. This is also a special case in which the AI cannot disentangle substrate and animals; only a human can interpret these complex features. Image taken by the AutoSub6000 in the North East Atlantic

While the study does not advocate the replacement of manual annotation, it does demonstrate that marine biologists could be able to implement AI for specific tasks if carefully assessing the reliability of their predictions. This would greatly enhance the capacity of scientists to analyze their data.

The researchers say the combination of specialist ecological knowledge with the high-tech AUV’s capacity to survey large areas of the seabed, and the fast data processing capacity of AI, could significantly speed up deep-ocean exploration, and with it our more extensive understanding of marine ecosystems.

Story by University of Plymouth

Journal Reference:

N Piechaud, C Hunt, PF Culverhouse, NL Foster, KL Howell. Automated identification of benthic epifauna with computer vision. Marine Ecology Progress Series, 2019; 615: 15 DOI: 10.3354/meps12925

Our Partners

Frontiers in Marine Science
American Academy of Underwater Sciences

ECO Magazine is a marine science publication committed to bringing scientists and professionals the latest ground-breaking research, industry news, and job opportunities from around the world.

Newsletter Signup

Please type your full name.

Please type your full name.

Invalid email address.

All emails include an unsubscribe link. You may opt-out at any time. Clicking subscribe confirms your acceptance of our privacy policy.