Artificial intelligence has invented hundreds of materials that don't exist yet
Scientists have developed an artificial intelligence algorithm that can predict the structure and properties of more than 31 million materials that do not yet exist. Independent.
The AI tool called M3GNet could lead to the discovery of new materials with exceptional properties, according to the team that created it at the University of California, San Diego.
A study detailing the new AI tool was published Nov. 28 in the scientific journal Nature Computational Science.
M3GNet was able to instantly populate a vast database of as-yet-unsynthesized materials that engineers are already analyzing in their hunt for more energy-hungry electrodes for lithium-ion batteries used in everything from smartphones to electric vehicles.
The Matterverse.ai database and the M3GNet algorithm could potentially expand the space for materials research by orders of magnitude.
UC San Diego professor of nanoengineering Shew Ping Ong described M3GNet as "AlphaFold for materials".
AlphaFold is an artificial intelligence algorithm developed by Google DeepMind for protein structure prediction. To create an equivalent for materials, Ong and his team combined many-body graph neural networks to create a deep learning architecture that works universally and with high accuracy for all elements of the periodic table.
The properties of a material are determined by the arrangement of its atoms. However, existing approaches to obtaining such a circuit are either prohibitively expensive or inefficient for many elements, reports NewsWise.
“Like proteins, we need to know the structure of a material in order to predict its properties,” said Professor Ong.
“We truly believe that M3GNet is a transformative tool that can greatly enhance our ability to explore new chemical properties and material structures,” he added.
You may be interested in: top New York news, stories of our immigrants, and helpful tips about life in the Big Apple - read it all on ForumDaily New York.
The team now plans to significantly expand the amount of materials in the database while continuing to explore what materials could be useful for future scientific discoveries.
It is estimated that over a million of the 31 million materials in the Matterverse.ai database are stable enough to be used.
Read also on ForumDaily:
stdClass Object ([term_id] => 1 [name] => Miscellaneous [taxonomy] => category [slug] => no_theme)Miscellanea
stdClass Object ([term_id] => 13992 [name] => Likbez [taxonomy] => category [slug] => poleznaja-informatsija)Educational program
stdClass Object ( [term_id] => 32067 [name] => AI [taxonomy] => post_tag [slug] => isksstvennyj-intellekt )artificial intelligence
stdClass Object ( [term_id] => 32068 [name] => new materials [taxonomy] => post_tag [slug] => novye-materialy )new materials
Do you want more important and interesting news about life in the USA and immigration to America? - support us donate! Also subscribe to our page Facebook. Choose the "Display Priority" option and read us first. Also, don't forget to subscribe to our РєР ° РЅР ° Р »РІ Telegram - there are many interesting things. And join thousands of readers ForumDaily Woman и ForumDaily New York - there you will find a lot of interesting and positive information.