Quantum-informed machine learning for predicting spatiotemporal chaos with practical quantum advantage
Open Access
- 17 April 2026
- journal article
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (16) , eaec5049
Abstract
We introduce a quantum-informed machine learning (QIML) framework for modeling the long-term behavior of high-dimensional chaotic systems. QIML combines a one-time, offline-trained quantum generative model with a classical autoregressive predictor for spatiotemporal field generation. The quantum model learns a quantum prior (Q-Prior) that guides the representation of small-scale interactions and improves the modeling of fine-scale dynamics. We evaluate QIML on the Kuramoto-Sivashinsky equation, two-dimensional Kolmogorov flow, and the three-dimensional turbulent channel flow used as a realistic inflow condition. Across these systems, QIML improves predictive distribution accuracy by up to 17.25% and full-spectrum fidelity by up to 29.36% relative to classical baselines. For turbulent channel inflow, the Q-Prior is trained on a superconducting quantum processor and proves essential: without it, predictions become unstable, whereas QIML produces physically consistent long-term forecasts that outperform leading partial differential equation solvers. Beyond accuracy, QIML offers a memory advantage by compressing multimegabyte datasets into a kilobyte-scale Q-Prior, enabling scalable integration of quantum resources into scientific modeling.Keywords
All Related Versions
This publication has 96 references indexed in Scilit:
- Quantum Support Vector Machine for Big Data ClassificationPhysical Review Letters, 2014
- Applied KoopmanismChaos: An Interdisciplinary Journal of Nonlinear Science, 2012
- Three-dimensional lattice Boltzmann model for immiscible two-phase flow simulationsPhysical Review E, 2012
- Quantum Algorithm for Linear Systems of EquationsPhysical Review Letters, 2009
- Straight velocity boundaries in the lattice Boltzmann methodPhysical Review E, 2008
- Multifractal Statistics of Lagrangian Velocity and Acceleration in TurbulencePhysical Review Letters, 2004
- Multiple–relaxation–time lattice Boltzmann models in three dimensionsPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2002
- An overview of statistical learning theoryIEEE Transactions on Neural Networks, 1999
- Proof of the Quasi-Ergodic HypothesisProceedings of the National Academy of Sciences, 1932
- Proof of the Ergodic Theorem.1931