In a study, researchers from the University of Tennesee are making and testing new photocatalysts to mitigate air pollution with the help of AI. Many human activities release pollutants into the air, water and soil. These harmful chemicals threaten the health of both people and the ecosystem. According to the World Health Organization, air pollution causes an estimated 4.2 million deaths annually. Scientists are looking into solutions, and one potential avenue is a class of materials called photocatalysts. When triggered by light, these materials undergo chemical reactions that initial studies have shown can break down common toxic pollutants.

Addressing the issue

The photocatalysts work by generating charged carriers in the presence of light. These charged carriers are tiny particles that can move around and cause chemical reactions. When they come into contact with water and oxygen in the environment, they produce substances called reactive oxygen species. These highly active reactive oxygen species can bond to parts of the pollutants and then either decompose the pollutants or turn them into harmless—or even useful—products.

However, some materials used in the photocatalytic process have limitations. For example, they can't start the reaction unless the light has enough energy—infrared rays with lower energy or visible light won't trigger the reaction.

Another problem is that the charged particles in the reaction can recombine too quickly, which means they join back together before finishing the job. In these cases, the pollutants either do not decompose completely, or the process takes a long time.

To overcome these challenges, scientists are trying to develop new photocatalytic materials that efficiently break down pollutants. They also focus on making sure these materials are nontoxic so that our pollution-cleaning materials don't cause further pollution.

Leveraging AI

Scientists are using automated experimentation and artificial intelligence to determine which photocatalytic materials could be the best candidates for quickly breaking down pollutants. They are making and testing materials called hybrid perovskites, which are tiny crystals about a tenth the thickness of a strand of hair. 

These nanocrystals are organic (carbon-based) and inorganic (non-carbon-based) components. They have a few unique qualities, like their excellent light-absorbing properties, which come from their structure at the atomic level. They're tiny but mighty. They interact with light in fascinating ways to generate many tiny charge carriers and trigger photocatalytic reactions.

Instead of making and testing samples by hand—which takes weeks or months—the team uses smart robots, which can produce and test at least 100 materials within an hour. These small liquid-handling robots can precisely move, mix and transfer tiny amounts of liquid from one place to another. They're controlled by a computer that guides their acceleration and accuracy.

The team also uses machine learning to guide this process. Machine learning algorithms can analyze test data quickly and then learn from that data for the next set of experiments the robots execute. These algorithms can quickly identify patterns and insights in collected data that would normally take longer for a human eye to catch.

According to Mahshid Ahmadi, materials science and engineering researcher at the University of Tennessee, "Our approach aims to simplify and better understand complex photocatalytic systems, helping to create new strategies and materials. By using automated experimentation guided by machine learning, we can now make these systems easier to analyze and interpret, overcoming challenges that were difficult with traditional methods".

Phys Org