(Press-News.org) TALLAHASSEE, Fla. — Florida State University chemists have created a machine learning tool that can identify the chemical composition of dried salt solutions from an image with 99% accuracy.
By using robotics to prepare thousands of samples and artificial intelligence to analyze their data, they created a simple, inexpensive tool that could expand possibilities for performing chemical analysis. The work was published in Digital Discovery.
“We are living in the age of artificial intelligence and big data,” said co-author Oliver Steinbock, a professor in the FSU Department of Chemistry and Biochemistry. “We thought that if we used sufficiently large databases with enough pictures of different compounds and stains, we could maybe use AI to determine what the composition is.”
The research could make possible cheaper, faster chemical analysis that could be used in space exploration, law enforcement, home testing and more.
HOW IT WORKS
This paper builds on a previous study from Steinbock’s lab in which researchers used machine learning to identify the chemical composition of salt stains from photos. In that study, the researchers analyzed about 7,500 samples, which they prepared by hand.
This paper amplifies that work by using a robot to process samples that were later analyzed by an improved machine learning program. Instead of hand-pipetting samples, the researchers created what they named the Robotic Drop Imager, or RODI, which is capable of preparing more than 2,000 samples per day. That allowed them to build a library of more than 23,000 images — more than three times as large as their original study.
After preparing samples and taking photos, the researchers simplified each image by converting them to grayscale, then extracted 47 features, such as pattern area, brightness and other attributes, which they used in their analysis.
With additional images, the accuracy of their machine learning program increased from around 90% to almost 99%. The researchers also analyzed the initial concentration of the salt solution at five different levels and trained their machine learning program to distinguish among them. The program reached 92% accuracy in identifying the concentration of the solution and the salt’s identity.
“The accuracy demanded in different analyses will vary depending upon the situation,” said paper co-author Amrutha S.V., a postdoctoral researcher. “From my experience, I know that some types of spectroscopy and other analysis methods are expensive and require specialized technical expertise to operate. That’s why I’m excited about the possibility of a simple method — just taking a photo to determine chemical composition. That would be incredibly useful.”
WHY IT MATTERS
Most chemical analysis methods focus on the molecular level, examining atoms, molecules or crystal structures.
“That works great if you have good samples, a few hundred thousand dollars for the instruments and no weight restrictions,” Steinbock said. “But if you want to go on a space mission and ship things to a moon of Saturn, for example, every gram matters. If you can do chemical analysis with a camera, that’s a game changer.’
The project was developed for NASA, which was looking for inexpensive, low-cost, low-weight methods for determining chemical concentrations. Instead of transporting samples to Earth, an extraterrestrial rover equipped with a simple chemistry lab and camera could analyze the chemical composition of materials on site.
Along with space exploration, the method developed in Steinbock’s lab could be used to provide chemical analysis for other applications. The testing relies on minute sample amounts — just a few milligrams — making it valuable in scenarios where obtaining large samples is difficult. Law enforcement could run preliminary tests on suspected drugs, laboratories could test spilled materials for safety, and hospitals without access to a full chemical analysis lab could use it to aid diagnoses for patients.
“This is important because it could democratize chemical analysis,” Steinbock said.
AI: A NEW TOOL FOR RESEARCH
Artificial intelligence promises to transform what is possible in research. Faculty at Florida State University are engaging in innovative projects that push the boundaries of this rapidly developing tool.
FSU’s artificial intelligence efforts are providing tools and insight for faculty in teaching and researching.
“I think it’s very helpful to be at a place where you get this kind of support, and it doesn’t necessarily have to be money, but just appreciation for trying new things,” Steinbock said. “AI is changing how we approach scientific discovery. What once required expensive equipment and specialized expertise can now be done with a simple camera and the right algorithm. This opens up new possibilities — not just for space missions, but for medicine, forensics and beyond.”
Additional co-authors on this paper were Bruno C. Batista of FSU, Jie Yan of Bowie State University and Beni B. Dangi of Florida A&M University. This project was supported by NASA.
###
END
Fan Zhang, PhD, sees artificial intelligence as a pathway to finding an effective way to combat an intractable enemy: rheumatoid arthritis.
Zhang is an assistant professor in the University of Colorado Department of Medicine’s Division of Rheumatology and also is affiliated with the Department of Biomedical Informatics on the CU Anschutz Medical Campus. She recently received a highly competitive grant from the Arthritis Foundation to further her work in harnessing AI to better predict the onset of rheumatoid arthritis (RA) in particular patients, ...
BALTIMORE, March 18, 2025— A new study led by Kennedy Krieger Institute’s Center for Autism Services, Science and Innovation (CASSI) finds that a community-based screening model is helping children receive autism diagnoses faster, particularly in underserved communities.
The research, published in Pediatric Investigation, highlights how the Rapid Interactive Screening Test for Autism in Toddlers (RITA-T) is making early autism identification more accessible for families facing barriers to care. RITA-T is a quick, interactive tool that assesses developmental skills often delayed in autism, such as social engagement, ...
Women with blood pressure levels in a range considered clinically normal during pregnancy but no mid-pregnancy drop in blood pressure face an increased risk of developing hypertension in the five years after giving birth. These women—about 12% of the population studied—would not be flagged as high-risk by current medical guidelines, but the new findings could help identify them as candidates for early intervention. The findings were just published in the Journal of the American College of Cardiology: Advances.
Funded in part by the National Institutes of Health, researchers collected data on blood pressure and other health factors ...
Since becoming only the second Alzheimer’s-modifying drug to gain American Federal Drug Administration approval in 2023, sales of lecanemab, known by its brand name Leqembi, have risen steadily, reaching $87-million USD in the last quarter of 2024.
In its Phase 3 clinical trial, lecanemab slowed cognitive decline by 27 per cent overall, yet one subset of data suggested little to no benefit in females, though the cause of the difference was not clear. An FDA committee voted unanimously that the Phrase 3 trial verified the clinical benefit of lecanemab. Even so, several follow-up papers focused on the trial’s apparent sex difference result to cast doubt on ...
TAMPA, Fla. (Mar. 18, 2025) — Moffitt Cancer Center researchers have discovered a promising new vaccine strategy for treating a specific type of breast cancer. The innovative approach targets human epidermal growth factor receptor 2-positive, estrogen receptor-negative (HER2-positive, ER-negative) breast cancer and has shown encouraging results in a recent pilot study. Published in npj Breast Cancer, the study combined the HER2-targeting dendritic cell vaccines with standard chemotherapy, demonstrating both safety and positive response rates.
The study enrolled 30 patients with stage 2 and stage 3 HER2-positive, ...
Toronto - Despite a very uncertain economic climate, investors can at least feel confident that audited financial reports are more reliable thanks to the spread of international standards.
New research led by a researcher at the University of Toronto’s Rotman School of Management shows that the quality of financial audits increasing in countries which have adopted the International Standards on Auditing, or ISA, issued through the International Federation of Accountants, the accounting profession’s worldwide body.
“We show improvement in audit quality, on average,” said researcher Ole-Kristian Hope, the Deloitte Professor of Accounting at the Rotman School. However, ...
Internal displacement in Syria was used by the Assad regime to reshape the country’s political and social landscape, a new study shows.
The forceful movement of people was systematically employed alongside indiscriminate violence, the research says.
This was not just a consequence of war, but a strategy to depopulate key areas and repopulate them to create new political and social realities. This tactic extended the impact of displacement beyond the immediate conflict, embedding it as a long-term political tool with lasting post-war ...
Over the past two decades, Haiti has endured the devastation of two catastrophic earthquakes — first in 2010 and again in 2021. Each disaster left behind widespread destruction: buildings reduced to rubble, entire communities displaced and an overwhelming loss of life. A major factor in the severity of these tragedies was the widespread structural failure of poorly designed buildings, many of which were not constructed to withstand the powerful tremors.
Marc-Ansy Laguerre, a postdoctoral associate in civil and environmental engineering at Rice University, ...
Why do people living in democratic countries vote for political candidates who openly violate democratic standards? A new study by a University of Notre Dame researcher found that diverse understandings of democracy among voters can lead to votes for authoritarian-leaning political leaders.
“A considerable variety in democratic views leads part of the electorate to overlook violations of democratic norms such as minority rights protection or restraints on executive power,” said Marc Jacob, assistant ...
CLEVELAND—Brain implants hold immense promise for restoring function in patients with paralysis, epilepsy and other neurological disorders.
But a team of researchers at Case Western Reserve University has discovered that bacteria can invade the brain after a medical device is implanted, contributing to inflammation and reducing the device’s long-term effectiveness.
The groundbreaking research, recently published in Nature Communications, could improve the long-term success of brain implants now that a target has been identified to address.
“Understanding the role of bacteria in implant ...