TheResearch Briefis a short take about interesting academic work.
Thecomputer model we createdis 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.
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 apublic database of shipwrecks.
This imagery contains huge areas with no shipwrecks, as well as the occasional shipwreck.
It’s free, every week, in your inbox.
These projects are able to find a handful of shipwrecks that are in the area immediately surrounding the drone.
This will help the model get really good at recognizing many different types of shipwrecks.
This will allow us to check the models accuracy more carefully.
Im 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.
