Arts and Culture

AI spots shipwrecks from the ocean surface – and even from the air

A group of underwater drivers excavate a shipwreck

Underwater archaeology cab be dangerous and expensive. Image: via REUTERS

Leila Character
Doctoral student in Geography, The University of Texas at Austin College of Liberal Arts
The Big Picture
Explore and monitor how Science is affecting economies, industries and global issues
A hand holding a looking glass by a lake
Crowdsource Innovation
Get involved with our crowdsourced digital platform to deliver impact at scale
Stay up to date:


  • In collaboration with the US Navy’s Underwater Archaeology Branch, an academic developed a new AI model that detects shipwrecks.
  • Geographer Leila Character was able to detect the wrecks with up 92% accuracy.
  • Underwater archaeology is dangerous and expensive but a model mapping all shipwrecks above the surface can reduce times, costs and risks.
  • Character explains how they created the tool and what impact it can expect to have.

The big idea

In collaboration with the United States Navy’s Underwater Archaeology Branch, I taught a computer how to recognize shipwrecks on the ocean floor from scans taken by aircraft and ships on the surface. The computer model we created is 92% accurate in finding known shipwrecks. The project focused on the coasts of the mainland U.S. and Puerto Rico. It is now ready to be used to find unknown or unmapped shipwrecks.

The first step in creating the shipwreck model was to teach the computer what a shipwreck looks like. It was also important to teach the computer how to tell the difference between wrecks and the topography of the seafloor. To do this, I needed lots of examples of shipwrecks. I also needed to teach the model what the natural ocean floor looks like.

Conveniently, the National Oceanic and Atmospheric Administration keeps a public database of shipwrecks. It also has a large public database of different types of imagery collected from around the world, including sonar and lidar imagery of the seafloor. The imagery I used extends to a little over 14 miles (23 kilometers) from the coast and to a depth of 279 feet (85 meters). This imagery contains huge areas with no shipwrecks, as well as the occasional shipwreck.

Have you read?
a picture showing ocean floor scans
Of these four ocean floor scans, the top two panels clearly show shipwrecks, but the shipwrecks in the bottom two panels, marked by red arrows, could easily be mistaken for natural features. Image: National Oceanic and Atmospheric Administration

Why it matters

Finding shipwrecks is important for understanding the human past – think trade, migration, war – but underwater archaeology is expensive and dangerous. A model that automatically maps all shipwrecks over a large area can reduce the time and cost needed to look for wrecks, either with underwater drones or human divers.

The Navy’s Underwater Archaeology Branch is interested in this work because it could help the unit find unmapped or unknown naval shipwrecks. More broadly, this is a new method in the field of underwater archaeology that can be expanded to look for various types of submerged archaeological features, including buildings, statues and airplanes.

What other research is being done in this field

This project is the first archaeology-focused model that was built to automatically identify shipwrecks over a large area, in this case the entire coast of the mainland U.S. There are a few related projects that are focused on finding shipwrecks using deep learning and imagery collected by an underwater drone. These projects are able to find a handful of shipwrecks that are in the area immediately surrounding the drone.


How is the World Economic Forum ensuring the responsible use of technology?

What’s next

We’d like to include more shipwreck and imagery data from all over the world in the model. This will help the model get really good at recognizing many different types of shipwrecks. We also hope that the Navy’s Underwater Archaeology Branch will dive to some of the places where the model detected shipwrecks. This will allow us to check the model’s accuracy more carefully.

I’m also working on a few other archaeological machine learning projects, and they all build on each other. The overall goal of my work is to build a customizable archaeological machine learning model. The model would be able to quickly and easily switch between predicting different types of archaeological features, on land as well as underwater, in different parts of the world. To this end, I’m also working on projects focused on finding ancient Maya archaeological structures, caves at a Maya archaeological site and Romanian burial mounds.

Don't miss any update on this topic

Create a free account and access your personalized content collection with our latest publications and analyses.

Sign up for free

License and Republishing

World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.

The views expressed in this article are those of the author alone and not the World Economic Forum.

Related topics:
Arts and CultureNature and Biodiversity
World Economic Forum logo
Global Agenda

The Agenda Weekly

A weekly update of the most important issues driving the global agenda

Subscribe today

You can unsubscribe at any time using the link in our emails. For more details, review our privacy policy.

Robot rock stars, pocket forests, and the battle for chips - Forum podcasts you should hear this month

Robin Pomeroy and Linda Lacina

April 29, 2024


About Us



Partners & Members

  • Join Us

Language Editions

Privacy Policy & Terms of Service

© 2024 World Economic Forum