A research team from University College London reports in Science Advances that integrating a quantum computer with an AI model improves predictions for complex systems beyond what classical computing can achieve, with a focus on long-term forecasts in fluid dynamics.

Looking ahead, the work aims to scale to larger datasets, apply the method to real-world problems, and establish a provable theoretical framework underlying the approach.

Current quantum hardware faces limits such as extreme sensitivity to environmental disturbances and the need for ultra-low temperatures, which constrains widespread everyday use at present.

The experiments used a 20-qubit IQM quantum computer connected to powerful classical resources at the Leibniz Supercomputing Centre, conducted under low-temperature conditions.

The method processes data by first using a quantum computer to extract invariant statistical patterns, which then guide training of a classical AI model, enabling significant memory efficiency.

Results indicate practical quantum advantage with potential applications in climate forecasting, blood flow modeling, molecular interactions, and wind farm optimization, signaling broader implications for simulations in science and engineering.

Industry context shows growing interest and early real-world experiments, including efforts like Google’s molecular predictions and university–industry collaborations on AI and quantum-enabled drug discovery.

Quantum effects such as entanglement and superposition allow the quantum component to compactly represent complex system states, contributing to the observed performance gains.

Researchers acknowledge challenges related to reliability and dataset sizes but remain hopeful about real-world applications as quantum hardware improves.

Coauthors note that even today’s small, noisy quantum devices can enhance conventional machine-learning algorithms when integrated judiciously with classical supercomputers.

Funding support comes from UCL, EPSRC, IQM Quantum Computers, and the Leibniz Supercomputing Centre, reflecting broad institutional backing.

A practical form of quantum advantage is demonstrated by having AI handle data processing while the quantum computer tackles a hard computational step, then returning results to the AI for final processing.