light shines up through a mechanical device attached to a microscope

Fossil sorting robots will help researchers study oceans and climate

Researchers have developed and demonstrated a robot capable of sorting, processing and identifying microscopic marine fossils. New technology automates a tedious process that plays a key role in advancing our understanding of the world’s oceans and climate – both today and in prehistory.

says Edgar Lobaton, co-author of a research paper on the work and associate professor of electrical and computer engineering at North Carolina State University. “Our goal is to make this tool widely available, so that it can be used by as many researchers as possible to advance our understanding of oceans, biodiversity, and climate.”

The technology, called Forabot, uses robots and artificial intelligence to manipulate the remains of organisms called foraminifera, or wormholes, so that those remains can be isolated, photographed and identified.

Forams are protists, neither plants nor animals, and have been ubiquitous in our oceans for over 100 million years. When the stoma dies, it leaves behind its tiny shells, less than a millimeter across. These shells give scientists an insight into the properties of the oceans as they existed when the ventricles were alive. For example, different species of foramina thrive in different types of ocean environments, and chemical measurements can tell scientists about everything from the chemistry of the ocean to its temperature when the crust formed.

However, evaluating porous shells and fossils is tedious and time consuming. That’s why a team of engineering and paleontological experts developed Forabot to automate the process.

“At this point, Forabot is able to identify six different types of holes, and process 27 forams per hour — but it never gets bored and never gets tired,” says Lobaton. “This is a proof-of-concept prototype, so we will be expanding the number of hole types it can recognize. We are optimistic that we will also be able to improve the number of holes it can process per hour.”

“Also, at this point, Forabot has an accuracy rate of 79% for identifying holes, which is better than most trained humans.”

says Tom Marchetto, co-author of the paper and professor of geosciences at the University of Colorado, Boulder. “By using community-sourced taxonomic knowledge to train the bot, we can also improve the standardization of hole identification across research groups.”

Here’s how Forabot works. First, users must wash and sift a sample from hundreds of holes. This leaves users with a mound of what looks like sand. The sample holes are then placed in a container called an isolation tower. A needle at the bottom of the isolation tower then protrudes through the sample, prying one hole up as it is removed from the tower by suction. Suction pulls the foramina into a separate container called a imaging tower, which is equipped with a high-resolution motorized camera that takes multiple pictures of the hole. After images have been taken, the foramen is again lifted with a needle so that it can be captured by suction and deposited in the relevant container at the sorting station. Forabot’s video in action can be seen at https://www.youtube.com/watch?v=nLkLIghc4Jg.

“The idea is that our AI can use images to identify the type of foramen, and sort them accordingly,” says Lobaton.

“We’re publishing in an open-source journal, and we’re including the diagrams and AI programs in supplementary material to that paper,” adds Lobaton. “I hope people will benefit from it. The next step for us is to expand the types of holes the system can identify and work to improve the operating speed.”

the paper, “Forabot: isolation and imaging of robotic wood foraminiferaIn Open Access Journal Geochemistry, geophysics and geological systems. The corresponding author of the paper is Turner Richmond, a recent Ph.D. Graduated from North Carolina State. The paper was co-authored by Jeremy Cole, Ph.D. NC State graduate; and by Gabriela Dangler, an undergraduate student at NC State.

The work was done with support from the National Science Foundation, under Grant No. 1,829,930.

-Hero-

Note to editors: Study summary follows.

“Forabot: Isolation and Imaging of Automated Wood Foraminifera”

Authors: Turner Richmond, Jeremy Cole, Gabriela Dangler, Michael Daniel and Edgar Lobaton, North Carolina State University; Thomas Marchiato, University of Colorado, Boulder

published: 29 November Geochemistry, geophysics and geological systems

DOI: 10.1029 / 2022GC010689

Summary: Physical examination and sorting of foraminifera is essential in many research laboratories, as foraminifera serve as palaeoenvironmental indicators and chronostrategraphs. In order to obtain the species number from specimens, analyze the chemical compositions, or extract the morphological characteristics of Foraminifera, research laboratories require time and effort from humans in handling and sorting these microscopic fossils. The presented work describes Forabot, an open source system that can physically manipulate individual foraminifera for imaging and isolation with minimal human interaction. The major components for building a Forabot are outlined in this work, with supplementary information available allowing other researchers to build a Forabot with low-cost, readily available components. From a washed and sifted sample of hundreds of foraminifera, Forabot was shown to be able to isolate and image individual holes. The current pipeline timing allows Forabot to process up to 27 foram samples per hour, a rate that can be improved for future classification purposes by reducing image quality and/or quantity. In addition to physical descriptions, image processing pipelines are also reviewed and classified. The proof-of-concept classifier uses a defined VGG-16 grid to achieve a classification accuracy of 79% on the validation set of foraminifera images bundled with Forabot. In conclusion, the researchers can build the system at low cost, handle foraminifera effectively with few errors, provide high-quality images for future research, and classify the types of holes imaged.


#Fossil #sorting #robots #researchers #study #oceans #climate

Leave a Comment

Your email address will not be published. Required fields are marked *