Friday, September 29, 2023

Deep learning can almost perfectly predict how ice forms

Must read

Shreya Christina
Shreya has been with for 3 years, writing copy for client websites, blog posts, EDMs and other mediums to engage readers and encourage action. By collaborating with clients, our SEO manager and the wider team, Shreya seeks to understand an audience before creating memorable, persuasive copy.

Researchers have used deep learning techniques to model how ice crystals form in the atmosphere with much higher precision than ever before. Their paperpublished this week in PNAS, points to the potential for the new method to significantly increase the accuracy of weather and climate forecasts.

The researchers used deep learning to predict how atoms and molecules behave. First, deep learning models were trained on small-scale simulations of 64 water molecules to help them predict how electrons in atoms interact. The models then replicated those interactions on a larger scale, using more atoms and molecules. It is this ability to accurately simulate electron interactions that allowed the team to accurately predict physical and chemical behavior.

“The properties of matter arise from how electrons behave,” said Pablo Piaggi, a researcher at Princeton University and the study’s lead author. “Explicitly simulating what happens at that level is one way to capture much richer physical phenomena.”

It is the first time this method has been used to model something as complex as ice crystal formation, also known as ice nucleation. This development could ultimately improve the accuracy of weather and climate predictions, because the formation of ice crystals is one of the first steps in the formation of clouds, where all precipitation comes from.

Xiaohong Liu, a professor of atmospheric sciences at Texas A&M University, who was not involved in the study, says half of all precipitation events — be it snow, rain or sleet — start as ice crystals, which then grow larger and result in precipitation. . If researchers can more accurately model ice nucleation, it could give a big boost to weather forecasting overall.

Nucleation of ice is currently predicted based on laboratory experiments. Researchers collect data on ice formation under various laboratory conditions, and that data is fed into weather forecasting models under comparable real-life conditions. This method works well enough sometimes, but is often inaccurate due to the sheer number of variables in real-world conditions. If even a few factors differ between the lab and the actual conditions, the results can be quite different.

“Your data is only valid for a certain region, temperature, or kind of lab environment,” Liu says.

Basing ice nucleation on how electrons interact is much more accurate, but it is also extremely computationally expensive. To predict ice nucleation, researchers need to model at least 4,000 to 100,000 water molecules, which can take years to run even on supercomputers. And even that would only be able to model the interactions for 100 picoseconds, or 10-10 seconds, not enough to observe the ice nucleation process.

However, using deep learning, researchers were able to perform the calculations in just 10 days. The length of time was also 1,000 times longer — still a fraction of a second, but just enough to see the ice nucleation process.

Of course, more accurate models of ice formation alone won’t make weather forecasts perfect, Liu says. Nucleation of ice is only a small but crucial part of weather modeling. Other aspects, such as understanding how water droplets and ice crystals grow, and how they move and interact under different conditions, are also important.

Still, the ability to more accurately model how ice crystals form in the atmosphere would greatly improve weather forecasts, especially whether it is likely to rain or snow, and by how much. It could also improve climate forecasting by improving the ability to model clouds, which are key players in the absorption of sunlight and the abundance of greenhouse gases.

Piaggi says future research could model ice nucleation when there are substances like smoke in the air, which could further improve the accuracy of models. Thanks to deep learning techniques, it is now possible to use electron interactions to model larger systems for longer periods of time.

“That essentially opened up a new field,” Piaggi says. “It is already playing and will play an even greater role in simulations in chemistry and in our simulations of materials.”

More articles

Latest article