A team based at Princeton University has accurately simulated the initial steps of ice formation by applying AI to solve equations that govern the quantum behavior of individual atoms and molecules. The study was published in the journal Proceedings of the National Academy of Science.  

According to the paper published, the resulting simulation describes how water molecules transition into solid ice with quantum accuracy. This level of accuracy, once unreachable due to the amount of computing power it would require, became possible when the researchers incorporated deep neural networks, a form of AI, into their methods.  

The ability to model the initial steps in freezing water, a process called ice nucleation, could improve the accuracy of weather and climate modelling and other processes like flash-freezing food. 

The new approach enables the researchers to track the activity of hundreds of thousands of atoms over time periods that are thousands of times longer, albeit still just fractions of a second than in early studies. 

Underlying quantum mechanical laws were formulated to predict the physical movement of atoms and molecules. As a result, quantum mechanical laws dictate how atoms bind to each other to form molecules and how molecules join with each other to form everyday objects.  

But quantum mechanical calculations are complex and take tremendous amounts of computing power. AI provided an attractive potential solution. Researchers train a neural network for its similarities to the workings of the human brain to recognize a comparatively small number of selected quantum calculations. Once trained, the neural network can calculate the forces between atoms that it has never seen before with quantum mechanical accuracy. 

According to Pablo Debenedetti, Princeton’s dean for research, this work provides one of the best ice nucleation studies.