A solar filament is an enormous stream of incandescent plasma suspended above the active surface of the
Sun by looping magnetic fields. Seen
against the solar disk it looks dark only because it’s a little cooler, and so
slightly dimmer, than the solar photosphere. Suspended above the solar limb the same structure
looks bright when viewed against the blackness of space and is called a solar prominence. A filaprom would be both of course, a stream of
magnetized plasma that crosses in front of the solar disk and extends beyond the Sun’s edge. In this hydrogen-alpha close-up of the Sun captured on
June 22, active region AR3038 is near the center of the frame. Active
region AR3032 is seen at the far right, close to the Sun’s western limb. As AR3032 is carried by rotation toward the Sun’s visible edge, what was once a giant
filament above it is now partly seen as a prominence, How big is AR3032’s
filaprom? For scale planet Earth is shown near the top right corner.
Researchers
from Carnegie Mellon University and Los Alamos National Laboratory have used
machine learning to create a model that can simulate reactive processes in a
diverse set of organic materials and conditions.
"It's a tool that can be used to
investigate more reactions in this field," said Shuhao Zhang, a graduate
student in Carnegie Mellon University's Department of Chemistry. "We can
offer a full simulation of the reaction mechanisms."
Zhang is the first author on the paper
that explains the creation and results of this new machine learning model
titled "Exploring the Frontiers of Chemistry with a General Reactive
Machine Learning Potential," published in Nature
Chemistry.
Though researchers have simulated
reactions before, previous methods had multiple problems. Reactive force field
models are relatively common, but they usually require training for specific
reaction types. Traditional models that use quantum mechanics, where chemical
reactions are simulated based on underlying physics, can be applied to any
materials and molecules, but these models require supercomputers to be used.
This new general machine learning
interatomic potential (ANI-1xnr), can perform simulations for arbitrary
materials containing the elements carbon, hydrogen, nitrogen and oxygen and
requires significantly less computing power and time than traditional quantum
mechanics models. According to Olexandr Isayev, associate professor of
chemistry at Carnegie Mellon and head of the lab where the model was developed,
this breakthrough is due to developments in machine learning.
A simulation demonstrates the reactions that the
ANI-1xnr can produce. ANI-1xnr can simulate reactive processes for organic
materials, such as as carbon, using less computing power and time than
traditional simulation models. The video is courtesy of Carnegie Mellon
University's Shuhao Zhang, first author on "Exploring the Frontiers of
Condensed-Phase Chemistry with a General Reactive Machine Learning
Potential." Credit: Shuhao Zhang, Carnegie Mellon University
"Machine learning is emerging
as a powerful approach to construct various forms of transferable atomistic
potentials utilizing regression algorithms. The overall goal of this project is
to develop a machine learning method capable of predicting reaction energetics
and rates for chemical processes with high accuracy, but with a very low
computational cost," Isayev said.
"We have shown that
those machine learning models can be trained at high levels of quantum
mechanics theory and can successfully predict energies and forces with quantum mechanics accuracy and an increase in speed of as much as
6–7 orders of magnitude. This is a new paradigm in reactive simulations."
Researchers tested ANI-1xnr on
different chemical problems, including comparing biofuel additives and tracking
methane combustion. They even recreated the Miller experiment, a famous
chemical experiment meant to demonstrate how life originated on Earth. Using
this experiment, they found that the ANI-1xnr model produced accurate results
in condensed phase systems.
Zhang said that the model could
potentially be used for other areas in chemistry with further training.
"We found out it can be
potentially used to simulate biochemical processes like enzymatic reactions," Zhang said. "We didn't design it to be
used in such a way, but after modification it may be used for that
purpose."
In the future, the team plans to
refine ANI-1xnr and allow it to work with more elements and in more chemical
areas, and they will try to increase the scale of the reactions it can process.
This could allow it to be used in multiple fields where designing new chemical
reactions could be relevant, such as drug discovery.
Zhang and Isayev were joined by
Małgorzata Z. Makoś, Ryan B. Jadrich, Elfi Kraka, Kipton Barros, Benjamin T.
Nebgen, Sergei Tretiak, Nicholas Lubbers, Richard A. Messerly and Justin S.
Smith in this study.