QIML uses a quantum-trained Q-Prior to enhance classical autoregressive predictions of spatiotemporal chaos, improving accuracy by up to 17.25% and full-spectrum fidelity by up to 29.36% while enabling stable forecasts for 3D turbulent channel flow.
For training we down-sample to Ntraj = 1200 trajectories, each with 256 temporal frames and 128 spatial points, leading to a working tensor of shape (256 , 128) per trajectory
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 1years
2025 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Quantum-Informed Machine Learning for Predicting Spatiotemporal Chaos with Practical Quantum Advantage
QIML uses a quantum-trained Q-Prior to enhance classical autoregressive predictions of spatiotemporal chaos, improving accuracy by up to 17.25% and full-spectrum fidelity by up to 29.36% while enabling stable forecasts for 3D turbulent channel flow.