Researchers have used deep learning techniques to model how ice crystals form in the atmosphere with much higher precision than ever before. Their paper, published this week in PNAS, hints at the potential for the new method to significantly increase the accuracy of weather and climate forecasting.
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, with more atoms and molecules. It’s this ability to precisely simulate electron interactions that allowed the team to accurately predict physical and chemical behavior.
“The properties of matter emerge from how electrons behave,” says Pablo Piaggi, a research fellow at Princeton University and the lead author on the study. “Simulating explicitly what happens at that level is a way to capture much more rich physical phenomena.”
It’s the first time this method has been used to model something as complex as the formation of ice crystals, also known as ice nucleation. This development may eventually improve the accuracy of weather and climate forecasting, because the formation of ice crystals is one of the first steps in the formation of clouds, which is where all precipitation comes from.
Xiaohong Liu, professor of atmospheric sciences at Texas A&M University, who was not involved in the study, says half of all precipitation events—whether it’s snow or rain or sleet—begin as ice crystals, which then grow larger and result in precipitation. If researchers can model ice nucleation more accurately, it could give a big boost to weather prediction overall.
Ice nucleation is currently predicted based on laboratory experiments. Researchers collect data on ice formation under different laboratory conditions, and that data is fed into weather prediction models under similar real-world conditions. This method works well enough sometimes, but often ends up being inaccurate because of the sheer number of variables in real-world conditions. If even a few factors vary between the lab and actual conditions, the results can be quite different.
“Your data is only valid for a certain region, temperature, or kind of laboratory setting,” Liu says.
Basing ice nucleation on how electrons interact is much more precise, but it’s also extremely computationally expensive. Predicting ice nucleation requires researchers to model at least 4000 to 100,000 water molecules, which even on supercomputers could take years to run. 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.
Using deep learning, however, researchers were able to run the calculations in just 10 days. The time duration 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 ice nucleation models alone won’t make weather forecasting perfect, says Liu. Ice nucleation is only a small but critical component of weather modeling. Other aspects, like understanding how water droplets and ice crystals grow, and how they move and interact together under different conditions, is also important.
Still, the ability to more accurately model how ice crystals form in the atmosphere would significantly improve weather predictions, especially whether it’s likely to rain or snow, and by how much. It could also improve climate forecasting by improving the ability to model clouds, which are vital players in the absorption of sunlight and abundance of greenhouse gasses.
Piaggi says future research could model ice nucleation when there are substances like smoke in the air, which can improve the accuracy of models even more. Because of deep learning techniques, it’s now possible to use electron interactions to model larger systems for longer periods of time.
“That has opened essentially a new field,” Piaggi says. “It’s already having and will have an even greater role in simulations in chemistry and in our simulations of materials.”
Meta’s new AI can make video based on text prompts
Although the effect is rather crude, the system offers an early glimpse of what’s coming next for generative artificial intelligence, and it is the next obvious step from the text-to-image AI systems that have caused huge excitement this year.
Meta’s announcement of Make-A-Video, which is not yet being made available to the public, will likely prompt other AI labs to release their own versions. It also raises some big ethical questions.
In the last month alone, AI lab OpenAI has made its latest text-to-image AI system DALL-E available to everyone, and AI startup Stability.AI launched Stable Diffusion, an open-source text-to-image system.
But text-to-video AI comes with some even greater challenges. For one, these models need a vast amount of computing power. They are an even bigger computational lift than large text-to-image AI models, which use millions of images to train, because putting together just one short video requires hundreds of images. That means it’s really only large tech companies that can afford to build these systems for the foreseeable future. They’re also trickier to train, because there aren’t large-scale data sets of high-quality videos paired with text.
To work around this, Meta combined data from three open-source image and video data sets to train its model. Standard text-image data sets of labeled still images helped the AI learn what objects are called and what they look like. And a database of videos helped it learn how those objects are supposed to move in the world. The combination of the two approaches helped Make-A-Video, which is described in a non-peer-reviewed paper published today, generate videos from text at scale.
Tanmay Gupta, a computer vision research scientist at the Allen Institute for Artificial Intelligence, says Meta’s results are promising. The videos it’s shared show that the model can capture 3D shapes as the camera rotates. The model also has some notion of depth and understanding of lighting. Gupta says some details and movements are decently done and convincing.
However, “there’s plenty of room for the research community to improve on, especially if these systems are to be used for video editing and professional content creation,” he adds. In particular, it’s still tough to model complex interactions between objects.
In the video generated by the prompt “An artist’s brush painting on a canvas,” the brush moves over the canvas, but strokes on the canvas aren’t realistic. “I would love to see these models succeed at generating a sequence of interactions, such as ‘The man picks up a book from the shelf, puts on his glasses, and sits down to read it while drinking a cup of coffee,’” Gupta says.
The Download: Amazon’s home-guarding robot, and covid’s violent legacy
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology.
Amazon has a new plan for its home robot Astro: to guard your life
The news: Amazon announced yesterday that its home robot, Astro, will be getting a slew of major updates aimed at further embedding it in homes—and in our daily lives.
The details: The new features offer more home monitoring. Astro will be able to watch pets and send a video feed of their activities to users, for example. But the robot will also be able to wander around the house to keep an eye on rooms and entry points. Amazon also announced a new collaboration between Astro and the Ring home security camera system designed to protect areas outside the home from possible break-ins.
Why it matters: Ring’s approach to surveillance hasn’t been without controversy. It’s reasonable to ask whether combining Astro’s ability to roam around a house with Ring’s established surveillance system might create even more problems than either product did in their previous iterations. Read the full story.
The pandemic created a “perfect storm” for Black women at risk of domestic violence
Starr Davis was smitten when she met a handsome stranger with flawless skin and a wide smile in March 2020. He was charming and persistent; but their whirlwind romance took a major turn when she fell pregnant. His aggressive behavior started to make her uncomfortable, but he was the father of her child.
He became physically abusive a few weeks after she moved in with him. He forbade her from setting foot outside, saying it was to protect her and their unborn child from covid. With no friends or close family nearby for support, she suffered in silence.
Covid seems to have made things worse for many women experiencing violence at home. Anti-domestic-violence advocates point to dramatic increases in calls to shelters and support groups, and many care workers say this increase in domestic violence seems to have disproportionately affected Black women like Davis. Read the full story.
—Chandra Thomas Whitfield
Podcast: AI births digital humans
In the latest episode of our podcast, In Machines We Trust, we dig into the world of digital twins: AI-powered replicas designed to capture the physical look and expressions of real humans. But although the entertainment industry is embracing them, they raise familiar, thorny questions about ownership and digital rights. Listen to it on Apple Podcasts, or wherever else you usually listen.
I’ve combed the internet to find you today’s most fun/important/scary/fascinating stories about technology.
1 Sweden has found a new leak in the Nord Stream pipeline
Russia is still denying any responsibility for attacking the gas pipeline, as the number of known leaks reaches four. (BBC)
+ Finding someone to blame is easier said than done. (Wired $)
+ The methane leak is likely to be the biggest ever, by far. (AP News)
+ The country’s tech imports have collapsed under sanctions. (Insider $)
+ Russia hasn’t been honest about the state of the pipeline for quite some time. (Slate $)
2 A bionic pancreas could solve one of the biggest challenges of diabetes
An algorithm takes over the arduous job of counting carbohydrates. (MIT Technology Review)
3 Crypto is still in crisis
Senior executives are still departing major firms, and investors are still wary. (Bloomberg $)
+ Do Kwon, the missing Terraform boss, has called the case against him ‘unfair.’ (Bloomberg $)
+ Crypto is weathering a bitter storm. Some still hold on for dear life. (MIT Technology Review)
4 A teenager died after a telehealth provider prescribed him antidepressants
The company failed to obtain consent from the minor’s parents. (WSJ $)
5 China’s chipmakers are being investigated
Which is dealing the industry’s dreams of self-sufficiency a heavy blow. (FT $)
+ Corruption is sending shock waves through China’s chipmaking industry. (MIT Technology Review)
+ There are no chip reserves. (Vox)
6 What it’s like being trapped in a driverless car
The vehicles work pretty well—until they don’t. (NYT $)
+ The big new idea for making self-driving cars that can go anywhere. (MIT Technology Review)
7 How good bacteria can fight malnutrition
Food that rebalances malnourished microbiomes can help children to grow. (Economist $)
+ Choanoflagellates are tiny creatures that also harbor bacteria communities. (The Atlantic $)
8 Tech startups are helping to rebuild Bosnia
Its up-and-coming businesses want to reverse the war-scarred nation’s brain drain. (Rest of World)
9 TikTok is making it harder for record execs to discover new musicians
There’s plenty of chaff to separate from the wheat. (The Guardian)
+ A car-renting couple have been tracking their customers on the platform. (Motherboard)
+ Investors are growing tired of chasing TikTok-style social apps. (The Information $)
10 The CIA is investing in tech to resurrect mammoths
It uses CRISPR gene editing to create optimized genetic code. (Intercept)
Quote of the day
“Everything is possible if you’re brave.”
—Katherin Bestandig, a regular at the Bam Bam Beach Bitcoin Bar in Lagos, Portugal, describes her bold approach to investing in volatile cryptocurrency to the New York Times.
The big story
Why the balance of power in tech is shifting toward workers
Something has changed for tech giants. Even as they continue to hold tremendous influence in our daily lives, a growing accountability movement has begun to check their power. Led in large part by tech workers themselves, a movement seeking reform of how these companies do business has taken on unprecedented momentum, particularly in the past year.
Concerns and anger over tech companies’ impact in the world is nothing new, of course. What’s changed is that workers are increasingly getting organized. Read the full story.
We can still have nice things
+ Ever feel like you’re being watched?
+ It’s up to you, New York!
+ Forget the gym, all the coolest cats are bouldering these days.
+ Lizzo visiting the Library of Congress to play a priceless flute is the serotonin boost I needed today.
+ A helpful reminder that all on LinkedIn is not as it seems (thanks Beth!)
How AI is helping birth digital humans that look and sound just like us
Jennifer: And the team has also been exploring how these digital twins can be useful beyond the 2D world of a video conference.
Greg Cross: I guess the.. the big, you know, shift that’s coming right at the moment is the move from the 2D world of the internet, into the 3D world of the metaverse. So, I mean, and that, and that’s something we’ve always thought about and we’ve always been preparing for, I mean, Jack exists in full 3D, um, You know, Jack exists as a full body. So I mean, Jack can, you know, today we have, you know, we’re building augmented reality, prototypes of Jack walking around on a golf course. And, you know, we can go and ask Jack, how, how should we play this hole? Um, so these are some of the things that we are starting to imagine in terms of the way in which digital people, the way in which digital celebrities. Interact with us as we move into the 3D world.
Jennifer: And he thinks this technology can go a lot further.
Greg Cross: Healthcare and education are two amazing applications of this type of technology. And it’s amazing because we don’t have enough real people to deliver healthcare and education in the real world. So, I mean, so you can, you know, you can imagine how you can use a digital workforce to augment. And, and extend the skills and capability, not replace, but extend the skills and, and capabilities of real people.
Jennifer: This episode was produced by Anthony Green with help from Emma Cillekens. It was edited by me and Mat Honan, mixed by Garret Lang… with original music from Jacob Gorski.
If you have an idea for a story or something you’d like to hear, please drop a note to podcasts at technology review dot com.
Thanks for listening… I’m Jennifer Strong.