DeepMind Applies Neural Network to Solving DFT Chemistry Problems – HPCwire

A team of researchers from DeepMind reported in Science last week that applying deep learning to DFT (density function theory) computation produced more accurate results than DFT alone.

In their abstract, the researchers noted, “DM21 accurately models complex systems such as hydrogen chains, charged DNA base pairs, and diradical transition states. More crucially for the field, because our methodology relies on data and constraints, which are continually improving, it represents a viable pathway toward the exact universal functional.”  DFT is a computational quantum mechanical modelling method used in physics, chemistry and materials science to investigate the electronic structure (principally the ground state) of many-body systems, in particular atoms, molecules, and the condensed phases. It is notoriously computationally intensive.

There’s a good short account of the work in Nature today, written by Davide Castelvecchi. Here’s a brief excerpt.

“The DeepMind team has made probably the most ambitious attempt yet to deploy AI to calculate electron density, the end result of DFT calculations. “It’s sort of the ideal problem for machine learning: you know the answer, but not the formula you want to apply,” says Aron Cohen, a theoretical chemist who has long worked on DFT and who is now at DeepMind.

“The team trained an artificial neural network on data from 1,161 accurate solutions derived from the Schrödinger equations. To improve accuracy, they also hard-wired some of the known laws of physics into the network. They then tested the trained system on a set of molecules that are often used as a benchmark for DFT, and the results were impressive, says (Anatole) von Lilienfeld (scientist at the University of Vienna). “This is the best the community has managed to come up with, and they beat it by a margin,” he says.

“One advantage of machine learning, von Lilienfeld adds, is that although it takes a massive amount of computing power to train the models, that process needs to be done only once. Individual predictions can then be done on a regular laptop, vastly reducing their cost and carbon footprint, compared with having to perform the calculations from scratch every time.”

Nature also noted that since its beginnings in the 1960s, DFT has become one of the most widely used techniques in the physical sciences: “[An investigation by Nature’s news team in 2014 found that, of the top 100 most-cited papers, 12 were about DFT. Modern databases of materials’ properties, such as the Materials Project, consist to a large extent of DFT calculations.” DeepMind plans to release its for anyone to use. For now, the model applies mostly to molecules and not to the crystal structures of materials, but future versions could work for materials, too.

Link to Science paper, https://www.science.org/doi/10.1126/science.abj6511

Link to Nature article, https://www.nature.com/articles/d41586-021-03697-8?utm_source=Nature+Briefing&utm_campaign=b0bda6ba48-briefing-dy-20211210&utm_medium=email&utm_term=0_c9dfd39373-b0bda6ba48-46067094

Spread the love

Leave a Reply

Your email address will not be published.

DeepMind Applies Neural Network to Solving DFT Chemistry Problems – HPCwire

A team of researchers from DeepMind reported in Science last week that applying deep learning to DFT (density function theory) computation produced more accurate results than DFT alone.

In their abstract, the researchers noted, “DM21 accurately models complex systems such as hydrogen chains, charged DNA base pairs, and diradical transition states. More crucially for the field, because our methodology relies on data and constraints, which are continually improving, it represents a viable pathway toward the exact universal functional.”  DFT is a computational quantum mechanical modelling method used in physics, chemistry and materials science to investigate the electronic structure (principally the ground state) of many-body systems, in particular atoms, molecules, and the condensed phases. It is notoriously computationally intensive.

There’s a good short account of the work in Nature today, written by Davide Castelvecchi. Here’s a brief excerpt.

“The DeepMind team has made probably the most ambitious attempt yet to deploy AI to calculate electron density, the end result of DFT calculations. “It’s sort of the ideal problem for machine learning: you know the answer, but not the formula you want to apply,” says Aron Cohen, a theoretical chemist who has long worked on DFT and who is now at DeepMind.

“The team trained an artificial neural network on data from 1,161 accurate solutions derived from the Schrödinger equations. To improve accuracy, they also hard-wired some of the known laws of physics into the network. They then tested the trained system on a set of molecules that are often used as a benchmark for DFT, and the results were impressive, says (Anatole) von Lilienfeld (scientist at the University of Vienna). “This is the best the community has managed to come up with, and they beat it by a margin,” he says.

“One advantage of machine learning, von Lilienfeld adds, is that although it takes a massive amount of computing power to train the models, that process needs to be done only once. Individual predictions can then be done on a regular laptop, vastly reducing their cost and carbon footprint, compared with having to perform the calculations from scratch every time.”

Nature also noted that since its beginnings in the 1960s, DFT has become one of the most widely used techniques in the physical sciences: “[An investigation by Nature’s news team in 2014 found that, of the top 100 most-cited papers, 12 were about DFT. Modern databases of materials’ properties, such as the Materials Project, consist to a large extent of DFT calculations.” DeepMind plans to release its for anyone to use. For now, the model applies mostly to molecules and not to the crystal structures of materials, but future versions could work for materials, too.

Link to Science paper, https://www.science.org/doi/10.1126/science.abj6511

Link to Nature article, https://www.nature.com/articles/d41586-021-03697-8?utm_source=Nature+Briefing&utm_campaign=b0bda6ba48-briefing-dy-20211210&utm_medium=email&utm_term=0_c9dfd39373-b0bda6ba48-46067094

Spread the love

Leave a Reply

Your email address will not be published.