{"id":378799,"date":"2021-12-09T22:00:03","date_gmt":"2021-12-09T19:00:03","guid":{"rendered":"https:\/\/en.buradabiliyorum.com\/simulating-matter-on-the-nanoscale-with-ai\/"},"modified":"2021-12-09T22:00:03","modified_gmt":"2021-12-09T19:00:03","slug":"simulating-matter-on-the-nanoscale-with-ai","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/simulating-matter-on-the-nanoscale-with-ai\/","title":{"rendered":"#Simulating matter on the nanoscale with AI"},"content":{"rendered":"

“#Simulating matter on the nanoscale with AI<\/strong>”<\/p>\n

\n
\n
\n
\n \"nanotechnology\"
\n Credit: Pixabay\/CC0 Public Domain
\n <\/figcaption><\/figure>\n<\/p><\/div>\n<\/div>\n

In a paper published today in the scientific journal Science<\/a>,<\/i> DeepMind demonstrates how neural networks can be used to describe electron interactions in chemical systems more accurately than existing methods.<\/p>\n

\n <\/p>\n<\/section>\n

Density Functional Theory, established in the 1960s, describes the mapp<\/a>ing between electron density and interaction energy. For more than 50 years, the exact nature of mapping between electron density and interaction energy\u2014the so-called density functional\u2014has remained unknown. In a significant advancement for the field, DeepMind has shown that neural networks can be used to build a more accurate map of the density and interaction between electrons than was previously attainable. <\/p>\n

By expressing the functional as a neural network and incorporating exact properties into the training data, DeepMind was able to train the model to learn functionals free from two important systematic errors\u2014the delocalisation error and spin symmetry breaking\u2014resulting in a better description of a broad class of chemical reactions. <\/p>\n

In the short term, this will empower researchers with an improved approximation of the exact Density Functional for immedia<\/a>te use through the availability of our code. In the long term, it is another step showing deep learning’s promise in accurately simulating matter at the quantum mechanical level\u2014which may enable material design in a computer by allowing researchers to explore questions about materials, medicines, and catalysts at the nanoscale level.<\/p>\n

“Understanding technology<\/a> at the nanoscale is becoming increasingly crucial in helping us tackle some of the major challenges of the 21st century, from clean electricity to plastic pollution,” says James Kirkpatrick, Research Scientist at DeepMind. “This research is a step in the right direction towards enabling us to better understand the interactions between electrons, the glue that holds molecules together.”<\/p>\n

With the aim of accelerating progress in the field, DeepMind has made the paper, and open-sourced code freely available.<\/p>\n\n

\n

New way to simulate hydrogen storage efficiency of materials\n <\/p><\/div>\n

\n
\n More information:<\/strong>
\n James Kirkpatrick et al, Pushing the Frontiers of Density Functionals by Solving the Fractional Electron Problem, Science<\/i> (2021). DOI: 10.1126\/science.abj6511<\/a>. www.science.org\/doi\/10.1126\/science.abj6511<\/a><\/p><\/div>\n

Provided by
\n DeepMind<\/p>\n

<\/p>\n

\n

Citation<\/strong>:
\n Simulating matter on the nanoscale with AI (2021, December 9)
\n retrieved 9 December 2021
\n from https:\/\/phys.org\/news<\/a>\/2021-12-simulating-nanoscale-ai.html<\/p>\n

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
\n part may be reproduced without the written permission. The content is provided for information purposes only.<\/p><\/div>\n<\/p><\/div>\n