Researchers at UCL (University College London) have developed a new approach that combines quantum computing with artificial intelligence to better predict how complex physical systems behave over time. Their study shows that this hybrid method outperforms the most advanced AI models that rely only on traditional computing.
The findings, published in Science Advances, could lead to more accurate models of how liquids and gases move and interact (fluid dynamics). These types of predictions are essential in fields such as climate science, transportation, medicine, and energy production.
The team attributes the improved results to the way quantum computers store and process information. Traditional computers rely on bits that are either 1 or 0. In contrast, quantum computers use qubits, which can exist as 1, 0, or any value in between. In addition, qubits can influence each other, allowing even a small number of them to represent a vast range of possible states.
Professor Peter Coveney, senior author from UCL Chemistry and the Advanced Research Computing Centre, explained: “To make predictions about complex systems, we can either run a full simulation, which might take weeks – often too long to be useful – or we can use an AI model which is quicker but more unreliable over longer time scales.
“Our quantum-informed AI model means we could provide more accurate predictions quickly. Making predictions about fluid flow and turbulence is a fundamental science challenge but it also has many applications. Our method can be used in climate forecasting, in modeling blood flow and the interaction of molecules, or to better design wind farms so they generate more energy.”
To read more, click here.