The quantum revolution is slowly arriving, and scientists from the University of Sydney have just demonstrated a necessary feat to help forward quantum technology: They can now use artificial intelligence to predict when a quantum system will get destroyed.

The team used machine learning techniques to predict and prevent when a system will develop decoherence, which is when it becomes too random to be useful. The advanced software architecture can understand the state even when it’s lacking information, which allows researchers to employ countermeasures to make the quantum state last longer.

Published in Nature Communications, the scientists have shown that it can be used on any type of quantum technology without the need for extra hardware.

"Much the way the individual components in mobile phones will eventually fail, so too do quantum systems," senior author Professor Michael J. Biercuk from the University of Sydney said in a statement. "But in quantum technology, the lifetime is generally measured in fractions of a second, rather than years."

The researchers have shown that decoherence can be stopped, but it requires a prediction of how the system is going to fall to pieces. The team’s breakthrough was to teach a computer algorithm the huge number of possibilities in which the demise of a quantum state might happen.

"Humans routinely employ predictive techniques in our daily experience; for instance, when we play tennis we predict where the ball will end up based on observations of the airborne ball," continued Biercuk. "This works because the rules that govern how the ball will move, like gravity, are regular and known. But what if the rules changed randomly while the ball was on its way to you? In that case, it's next to impossible to predict the future behavior of that ball.

"And yet this situation is exactly what we had to deal with because the disintegration of quantum systems is random. Moreover, in the quantum realm observation erases quantumness, so our team needed to be able to guess how and when the system would randomly break. We effectively needed to swing at the randomly moving tennis ball while blindfolded."

Quantum computers promise a future of information analyzed at unprecedented speed, but to get there, we need to make the quantum state stable. This approach provides a practical solution for stability, although a lot more work is necessary.