AI-driven approach reveals hidden hazards of chemical mixtures in rivers

A new method developed by researchers at the University of Birmingham shows how advanced artificial intelligence (AI) methods can help identify potentially harmful chemicals in rivers by monitoring the impact of tiny water fleas (water fleas) in rivers.

The team collaborated with scientists from the China Center for Ecological and Environmental Sciences (RCEES) and the Helmholtz Center for Environmental Research (UFZ) in Germany to analyze water samples from the Chaobai River system near Beijing. The river system is receiving chemical pollutants from many different sources, including agriculture, households and industry.

Professor John Colburn is Director of the Center for Environmental Studies and Justice at the University of Birmingham and one of the senior authors of the paper. He is optimistic that with these early findings, the technology could one day be deployed to regularly monitor water for toxic substances that would otherwise go undetected.

He said: “There are a lot of chemicals in the environment. Water safety cannot be assessed one substance at a time. Now we have the means to monitor the total amount of chemicals in environmentally sampled water to reveal which unknown substances work together to have a negative impact on animals, including humans. toxicity.

The results were published in Environmental Science and Technologyrevealed that certain chemical mixtures can collectively affect important biological processes in aquatic organisms, as measured through their genes. Combinations of these chemicals may cause greater environmental harm than the chemicals alone.

The team used water fleas (Daphnia) as test organisms in their study because these tiny crustaceans are highly sensitive to changes in water quality and share many genes with other species, making them excellent indicators of potential environmental hazards.

“Our innovative approach uses water fleas as a sentinel species to detect potentially toxic substances in the environment,” explains Dr. Xiaojing Li from the University of Birmingham (UoB) and lead author of the study. “By using artificial intelligence methods, we can identify which chemicals may be particularly harmful to aquatic life, even at low concentrations that would not normally be a cause for concern.”

Dr. Jiarui Zhou from the University of Birmingham, co-first author of the paper and the person responsible for the development of the artificial intelligence algorithm, said: “Our approach shows how advanced computational methods can help solve pressing environmental challenges. By analyzing a large number of With simultaneous access to biological and chemical data, we can better understand and predict environmental risks.

Professor Luisa Orsini, another senior author of the study, added: “The key innovation of this study is our data-driven, unbiased approach to uncovering how concentrations of environmentally relevant chemical mixtures cause harm. This is an important step forward in traditional ecotoxicology. Science poses challenges and paves the way for regulation.

Dr Timothy Williams of the University of Birmingham and co-author of the paper also noted: “Typically, aquatic toxicology studies either use high concentrations of a single chemical to determine detailed biological responses, or only identify changes in mortality and reproduction, etc. top effect.

Research results can help improve environmental protection in the following ways:

• Identify previously unknown chemical combinations that pose risks to aquatic life
• Enable more comprehensive environmental monitoring
• Support smarter regulations for chemical discharge into waterways

The research was funded by a Royal Society International Collaboration Award, the European Union’s Horizon 2020 research and innovation program and the Natural Environment Research Council’s Innovative Talent programme.