Machine learning can reduce worries about nanoparticles in food
While crop yields have increased dramatically thanks to nanotechnology in recent years, alarms about the health risks posed by nanoparticles in fresh produce and grains have also increased. In particular, nanoparticles entering the soil through irrigation, fertilizers and other sources have raised concerns about whether plants absorb these tiny particles enough to cause toxicity.
In a new study published online in the journal Environmental sciences and technologies, researchers at Texas A&M University used machine learning to assess the main properties of metal nanoparticles that make them more likely to be taken up by plants. The researchers said their algorithm could tell how many plants are accumulating nanoparticles in their roots and shoots.
Nanoparticles are a growing trend in several fields, including medicine, consumer products and agriculture. Depending on the type of nanoparticle, some have favorable surface properties, charge, and magnetism, among other characteristics. These qualities make them ideal for a number of applications. For example, in agriculture, nanoparticles can be used as antimicrobials to protect plants from pathogens. Alternatively, they can be used to bind to fertilizers or insecticides and then timed to release slowly to increase plant uptake.
These agricultural practices and others, such as irrigation, can cause nanoparticles to build up in the soil. However, with the different types of nanoparticles that might exist in soil and an incredibly high number of terrestrial plant species, including food crops, it is not clear whether certain properties of nanoparticles make them more likely to be taken up by. some plant species than others.
“As you can imagine, if we are to test for the presence of every nanoparticle for every plant species, that’s a huge number of experiments, which takes a lot of time and is very expensive,” said Xingmao “Samuel” Ma, associate professor in the Department of Civil and Environmental Engineering at Zachry. “To give you an idea, silver nanoparticles alone can have hundreds of different sizes, shapes and surface coatings, and therefore, experimentally testing each, even for a single plant species, is impractical.”
Instead, for their study, the researchers chose two different machine learning algorithms, an artificial neural network and gene expression programming. They first trained these algorithms on a database created from previous research on different metal nanoparticles and the specific plants in which they accumulated. In particular, their database contained the size, shape, and other characteristics of different nanoparticles, as well as information on how much of these particles were taken up from soil or nutrient-enriched water in the plant body.
Once trained, their machine learning algorithms could correctly predict the likelihood of a given metal nanoparticle accumulating in a plant species. Additionally, their algorithms revealed that when plants are in a nutrient-enriched or hydroponic solution, the chemical composition of the metal nanoparticle determines the propensity for accumulation in roots and shoots. But if plants grow in the soil, the organic matter and clay content of the soil is the key to uptake of nanoparticles.
Ma said that while machine learning algorithms can make predictions for most food crops and land plants, they might not be ready for aquatic plants yet. He also noted that the next step in his research would be to determine whether machine learning algorithms could predict the uptake of nanoparticles from leaves rather than roots.
“It’s completely understandable that people are worried about the presence of nanoparticles in their fruits, vegetables and grains,” Ma said. “But instead of not fully using nanotechnology, we would like farmers to harvest them. many advantages offered by this technology while avoiding potential food safety problems. “
Other contributors include Xiaoxuan Wang, Liwei Liu, and Weilan Zhang from the Department of Civil and Environmental Engineering.
This research is partially funded by the National Science Foundation and the Taiwan Ministry of Science and Technology as part of the graduate students study abroad program.