Then there is glass, a strange intermediate substance that has puzzled physicists for decades. Take a snapshot of the molecules in the glass. They look like fluid disorders. But most molecules hardly move, making this material as hard as a solid.
Glass is formed by cooling some liquid. However, why do the molecules in the liquid drop sharply at a certain temperature, but the structural arrangement has not changed significantly (this phenomenon is called glass transition)? So far, people haven't figured out what caused the glass to be so hard.
Now, researchers at DeepMind, an artificial intelligence company owned by Google, have used AI to study the changes of molecules in glass with hardening. DeepMind's artificial neural network can only use its physical structure at a time? Snapshot? To predict how molecules move over a long time scale. According to Victor of DeepMind? Bapst's point of view, even if the microstructure of glass looks featureless, it may be more predictive of kinetics than people think. ?
Peter who studies glass transition at the University of Sydney? Harold agreed. He said, this paper? More telling than previous papers on glass hardness? ,? Is the structure dynamically encoded in some way? So glass is not as messy as liquid after all.
Forecast trend
In order to understand the microscopic changes leading to glass transition, physicists need to relate two kinds of data: how the molecules in glass are arranged in space and how they move (slowly) with time. One way to relate these substances is to relate them to a quantity called dynamic trend: given the current position of a group of molecules, how many molecules they may move at a specific time in the future. This developing quantity comes from using Newton's law to calculate molecular trajectories, starting with many different random initial velocities, and then averaging the results together.
By simulating these molecular dynamics, computers can generate "trend maps" of thousands of glass molecules, but only on the time scale of one trillionth of a second. By definition, molecules in glass move very slowly. Julio, a condensed matter physicist at Paris Normal University, France? Biroli said that calculating their trends to the level of a few seconds or more "is impossible for ordinary computers because it takes too much time".
More importantly, Biroli said, understanding what structural features (if any) may lead to molecular tendency in glass only through these simulations does not give physicists much insight.
DeepMind researchers set out to train an AI system to predict the characteristics of glass without actually running the simulation, and tried to understand the sources of these characteristics. They use a special artificial neural network, which takes a graph (a group of nodes connected by lines) as input. Each node in the graph represents the three-dimensional position of a molecule in glass. Lines between nodes indicate the distance between molecules. Bapst said, because the neural network changes its structure to reflect the structure of its input? Study? , so? Graphical neural network is very suitable for representing the interaction of particles? .
Bapst and his colleagues first used the simulation results to train their AI system: they created a virtual glass cube containing 4096 molecules, simulated the evolution of molecules based on 400 unique starting positions at different temperatures, and calculated the inertia of particles. After training neural networks to accurately predict these trends, the researchers then put 400 previously invisible particle configurations (glass molecular configurations? Snapshot? ) into a well-trained network.
Using only these structural snapshots, neural networks can predict molecular characteristics at different temperatures with unprecedented accuracy. Compared with the latest machine learning prediction method, the prediction distance for the future will reach 463 times.
Related clues
Biroli said that DeepMind neural network can predict the future motion of molecules only by its snapshot of the current structure, which provides a powerful new method for exploring the dynamics of glass and other materials.
However, what pattern does the network detect in these snapshots to make predictions? The system can't easily reverse engineer to determine the preventive measures it learned during the training process, which is a common problem for researchers trying to use AI for scientific research. But in this case, they found some clues.
According to AgnieszkaGrabska-Barwinska, a team member, the graphic neural network learned what coding physicists call the correlation length pattern. That is to say, as DeepMind's graphical neural network reorganizes itself to reflect the training data, it shows the following trend: when the prediction trend is at a higher temperature (the molecular movement looks more like a liquid than a solid, but not a solid), for the prediction of each node, the network relies on information from neighboring nodes (there are two or three connections in the figure). But at a lower temperature close to the glass transition, the number (correlation length) increases to 5.
Thomas, a physicist of the DeepMind team? Thomas Keck said: As the temperature drops, we find that the network extracts information from its bigger and bigger neighbors? . ? At these different temperatures, the glass looks exactly the same with the naked eye. But with the application of our AI technology, the graphic neural network has seen something different. ?
The increase of correlation length is a sign of phase transition, in which particles change from disorder to ordered arrangement, and vice versa. For example, this happens when the atoms in a piece of iron line up to magnetize the iron. As the block approaches this transition, each atom affects the atoms farther and farther away in the block.
For a physicist like Biroli, the ability of neural network to understand the correlation length and incorporate it into the prediction shows that some hidden order will inevitably be formed in the glass structure during the glass transition. Peter, a glass expert at Rice University? Wolins said that the relevant length of machine learning provides evidence that when a material becomes glassy, it will? Close to thermodynamic phase transition? .
However, the knowledge obtained by neural network cannot be easily converted into new equations. Puhimi, head of DeepMind Science Team? PushmeetKohli said: We can't say,? Oh, actually, our network is studying this correlation. Can I provide you with a formula? . ? For some glass physicists, this warning limits the practicality of graphic neural networks. ? Can this be explained in human terms? ? Wolins said,? They didn't do it. That doesn't mean they can't do it in the future. ?