Scientists from Nanjing University and Columbia University have developed advanced soil models to detect cadmium, a toxic heavy metal, in wheat grains, which will help improve food safety.

According to a summary of the research provided by the Chinese Academy of Sciences, which was posted on Phys.org, researchers stated that wheat in China — where the study was conducted — often contains cadmium levels above safe limits, despite strict government regulations.

To address the issue, the team built predictive soil models using data from 311 paired soil and wheat samples taken across China. They employed various mathematical and scientific techniques to identify the most suitable model for predicting cadmium thresholds, per food safety regulations, which are set at 0.1 milligrams per kilogram for wheat grain.

Researchers found that the Extremely Randomized Trees (ERT) machine learning model performed better than the others in terms of accuracy and resilience.

Perhaps the most exciting find of the study was that the new cadmium thresholds the team calculated using the models "proved more effective in predicting grain safety than current national standards, offering a refined and cost-efficient alternative to blanket soil remediation."

"Our goal was to create a practical tool that farmers and regulators can use to assess wheat safety directly from soil data," Professor Xueyuan Gu, co-author of the study, which was published in Eco-Environment & Health, said. "The machine learning models and new thresholds we developed are not just academic exercises — they can be integrated into field management systems and national monitoring programs."

Gu said that collecting more data in other regions could further improve the models' accuracy and have important implications for sustainable land management and food safety standards as soil databases are updated.

The models will enable farmers and authorities to test for cadmium using standard soil tests, making them a practical and cost-effective tool to ensure the safety of wheat crops.

And since long-term exposure to cadmium can cause significant health issues, including kidney and lung damage, cancer, and other ailments, per the European Commission and the National Cancer Institute, it's crucial to develop methods that can predict levels of the heavy metal before it can contaminate our food supplies.

Using machine learning models offers a straightforward, data-driven solution that could have far-reaching impacts as the technology is scaled up in the future.

Do you worry about having toxic forever chemicals in your home? Majorly 😥 Sometimes 😟 Not really 😐 I don't know enough about them 🤷 Click your choice to see results and speak your mind.

Meanwhile, scientists have been working on ways to make wheat crops drought-resistant, as the changing climate is making it harder to grow many staple foods.

One type of modified wheat developed by Argentina's Bioceres Crop Solutions has been approved for production in the United States — the world's fourth-largest wheat producer. Once field trials are completed and the wheat can be grown commercially, it will help bolster our food supplies and make farmers' jobs much easier.

Join our free newsletter for weekly updates on the latest innovations improving our lives and shaping our future, and don't miss this cool list of easy ways to help yourself while helping the planet.