The painting designed by AI could reduce the suffocating effect of the urban heat island in cities and reduce air conditioning bills, said scientists, because automatic learning accelerates the creation of new materials for everything, from electric motors to capture carbon.
Material experts have used artificial intelligence to formulate new coatings that can keep buildings between 5 ° C and 20 ° C cooler than normal painting after exposure to midday sun. They could also be applied to cars, trains, electrical equipment and other objects that will require more cooling in a world that warms up.
Using automatic learning, researchers from universities in the United States, China, Singapore and Sweden have designed new paint formulas set to best reflect the sun’s rays and emit heat, according to a study evaluated by peers published In the scientific journal Nature.
This is the latest example of the AI used to skip traditional test approaches and error in scientific advances. Last year, the British company Matnex used AI to create a new type of permanent magnet used in electric vehicle engines to avoid the use of rare land metals, the mining of which is at high carbon intensity.
Microsoft has released AI tools to help researchers quickly design new inorganic materials – often crystalline structures used in solar panels and medical implants. And there are hopes that new materials better capture carbon in the atmosphere and to make more effective batteries.
The research on painting was carried out by academics at the University of Texas in Austin, Shanghai Jiao Tong University, at the National University of Singapore and at Umeå University in Sweden. He found that the application of one of the many new compatible paintings AI on the roof of a four -story building could save electricity equivalent to 15,800 kilowatt hours per year in a warm climate like Rio de Janeiro or Bangkok. If the paint was applied to 1,000 blocks, this could save enough electricity to supply more than 10,000 air conditioning units for a year.
Yuebing Zheng, professor at the University of Texas and co-leader of the study, said: “Our automatic learning framework represents a leap forward in the design of thermal meta-emitters.
He said that a month of work in design new equipment was underway in a few days using AI and that new materials that have never been discovered by trials and errors were created.
“Now we follow the automatic learning outlet, [its instructions for] The structure and type of material that we should use, and we can do things without going through many design and manufacturing test cycles. »»
Dr. Alex Ganose, professor of chemistry at the Imperial College in London, who also uses automatic learning to design new materials, “said:” Things move very quickly in this space. In the past year, there have been so many startups that have tried to use the generator for materials. ”
He said the process of designing a new material could require the calculation of millions of potential combinations. The AI allows scientists of materials to pass the previous restrictions in computing power. It also means that the traditional process of creating equipment, then testing its properties, can be reversed, scientists capable of saying to AI which properties they want from the start.
