Fossil-sorting robot to make it easier to study oceans, climate

Researchers at North Carolina State University have developed and demonstrated a robot capable of sorting, manipulating and identifying microscopic marine fossils. Such fossils are key to understand of the world’s oceans and climate of today and in the prehistoric past. 

A paper on the research, Forabot: Automated Planktic Foraminifera Isolation and Imaging, was published in the open-access journal Geochemistry, Geophysics, Geosystems. 

Read more: Oceans Great Dying 2.0: Earth’s climate moderator is warming, faster

Foraminifera, also called forams, are very simple micro-organisms that secrete a tiny shell, a little longer than a millimetre. The organisms have existed in our oceans for more than 100 million years. When forams die, they leave behind their shells. 

Examining their shells give scientists insights into the characteristics of the oceans from a time when the forams were alive.

Different types of foram species thrive in different ocean environments and chemical measurements can tell scientists everything from the ocean’s chemistry to its temperature when the shell was being formed.

Physical inspection and sorting of forams can require human time and effort. The team of engineering and paleoceanography experts developed the robot, called Forabot, to automate the tedious process, according to a statement on the university website. 

Forabot has an accuracy rate of 79 per cent for identifying forams, which is better than most trained humans, stated Edgar Lobaton, co-author of a paper on the work and associate professor of electrical and computer engineering at North Carolina State University. 

“At this point, Forabot is capable of identifying six different types of foram and processing 27 forams per hour — but it never gets bored and it never gets tired,” Lobaton said further. 

The robot’s AI uses images to identify the type of foram and sorts it accordingly. It has the potential to be a valuable piece of research equipment, allowing student ‘foram pickers’ to spend their time learning more advanced skills, according to the developers.

Read more: Researchers identified over 5,500 new viruses in the ocean, including a missing link in viral evolution

“By using community-sourced taxonomic knowledge to train the robot, we can also improve the uniformity of foram identification across research groups,” stated Tom Marchitto, co-author of the paper and professor of geological sciences at the University of Colorado, Boulder. 

“We’re publishing the research in an open-source journal and are including the blueprints and AI software in the supplementary materials,” Lobaton added. “Hopefully, people will make use of it.” 

The next step is to expand the types of forams the system can identify and work on optimising the operational speed, he added.