Researchers have designed and demonstrated a robot capable of sorting, manipulating and identifying microscopic marine fossils. The new technology automates a tedious process that plays a key role in advancing our understanding of the world's oceans and climate.
"The beauty of this technology is that it's made with relatively inexpensive off-the-shelf components, and we developed the design and open-source AI software," said Edgar Lobaton, co-author of the paper on the work and assistant professor of electrical and computer engineering at Northern State University. Carolina - Our goal is to make this tool widely available so that as many researchers as possible can use it to advance our understanding of oceans, biodiversity and climate."
The technology, called Forabot, uses robotics and AI to physically manipulate the remains of organisms called foraminifera (from the Latin foraminifera) so they can be examined.
Foraminifera are a clade of unicellular testaceous animals from the protist group and have been distributed in the oceans for over 100 million years. When they die, they leave behind their tiny shells, which in most cases are no more than a millimeter wide. These shells give scientists insight into the characteristics of the oceans during the period when foraminifera were alive. For example, different species lived in different ocean environments, and chemical measurements of shells can tell scientists a lot, from the chemical composition of the ocean to its temperature when the shell formed.
However, evaluating shells and fossils is tedious and time-consuming. That's why a team of engineers and paleooceanographers developed Forabot to automate this process.
“Currently, Forabot is able to identify six different types of foraminifera and process 27 shells per hour,” says Lobaton. “This is a prototype, so we will expand the number of foraminiferal species that it can identify. which it can process per hour. In addition, Forabot currently has a recognition accuracy of 79%, which is better than most trained people."
“Once Forabot is optimized, it will become a valuable research tool that allows students to spend their time more efficiently learning more complex skills,” says Tom Marchitto, co-author of the paper and a professor of geological sciences at the University of Colorado. “Using community taxonomic knowledge to train the robot.” , we can also improve the uniformity of foraminifera identification across research groups."
Share with friends:
Write and read comments can only authorized users