Quantum Reservoir Computing with Physics-Informed Correction for Reduced-Order PDE Forecasting

• Reduced-order forecasting of Burgers and KS combines nonlinear PDE dynamics with machine-learning rollout challenges, including steep gradients and spatiotemporal chaos.Source: §1 · p. 1
• Reservoir computing trains mainly a linear readout while retaining nonlinear reservoir dynamics, whereas PINNs impose PDE residual constraints but can be fragile in convection-dominated or chaotic systems.Source: §1 · p. 1
• The proposed two-stage architecture uses QRC for fast latent-space proposal rollouts and a PINN-based corrector for local projection toward lower-residual trajectories.Source: §1 · p. 2
• The evaluation reports a reduced-order QRC+PIC pipeline and finds consistent improvement over QRC alone on KS, while Burgers shows that simple autoregressive baselines can remain highly competitive.Source: §1 · p. 2

• Naive PINNs can be difficult to optimize for convection-dominated, multiscale, or chaotic long-horizon problems, motivating local rather than global physics-informed correction.Source: §2.1 · p. 2
• Echo state networks are efficient because only the readout is trained, and prior work demonstrates reservoir forecasting for large spatiotemporally chaotic systems including KS.Source: §2.2 · p. 2
• Physics-informed ESN variants add residual-based penalties to improve predictability and hidden-state reconstruction in chaotic systems.Source: §2.2 · p. 2
• Output-projection methods provide a conceptual precedent for PIC, which uses a preliminary forecast as a strong prior and moves it toward physical consistency without discarding the fast proposal trajectory.Source: §2.4 · p. 3

Burgers

• Burgers combines nonlinear transport and diffusion with steep gradients and serves here as a numerically stable, lower-difficulty sanity check.Source: §3.1 · p. 3

Kuramoto–Sivashinsky

• KS is a canonical testbed for spatiotemporal chaos and machine-learning-based forecasting, making it the primary benchmark for chaotic reduced-order forecasting.Source: §3.2 · p. 4

Reduced-order representation

• Both PDEs are represented in a reduced-order latent space obtained by proper orthogonal decomposition.Source: §3.3 · p. 4
• The mean field and POD modes are learned from training trajectories, while QRC, ESN, and autoregressive baselines forecast the same coefficient representation for fair state-space comparison.Source: §3.3 · p. 4

Stage I: Quantum reservoir proposal

• The QRC encodes normalized reduced-order coefficients into quantum reservoir features and uses a ridge-regression readout to generate next-step proposals.Source: §4.1 · p. 4
• Although trained with teacher forcing, the QRC is evaluated under closed-loop rollout for validation and testing.Source: §4.1 · p. 4

Stage II: Physics-informed correction

• The correction stage takes local proposal windows and reconstructed fields as inputs, producing residual-corrected trajectories through a small neural correction.Source: §4.2 · p. 4
• The PINN-style corrector is trained on short windows with a composite loss combining data and physics-informed terms.Source: §4.2 · p. 4
• At test time, the corrector sees only proposal windows, so the correction is autonomous and does not use hidden test-time truth anchoring.Source: §4.2 · p. 5

Design rationale

• The proposal–correction split lets PINN refinement focus on local physics consistency instead of full chaotic trajectory generation.Source: §4.3 · p. 5

• Experiments use trajectory-level train/validation/test splits, training-set-only POD and normalization, five random seeds, validation-only tuning, and held-out test reporting.Source: §5.1 · p. 5
• The evaluation keeps rollout conditions and reduced-order representations fixed when comparing proposal-only and proposal-plus-correction models.Source: §5.1 · p. 5

Baselines

• The baseline set includes Persistence, Ridge-AR, MLP-AR, PI-MLP, ESN, ESN+PIC, QRC, and QRC+PIC.Source: §5.2 · p. 5
• The comparison tests QRC proposal competitiveness, the effect of physics-informed correction, and whether any quantum benefit remains against strong classical reduced-order baselines.Source: §5.2 · p. 5

• Reported metrics include mean ± standard deviation for field-level RMSE, NRMSE, and PDE residual, with additional horizon, valid-prediction-time, and spectral measures where available.Source: §5.3 · p. 6

QRC+PIC Pipeline

• The QRC+PIC workflow generates rollout predictions with a quantum reservoir and refines them using a physics-informed corrector.Source: Figure 2 · p. 6

Primary benchmark: Kuramoto–Sivashinsky

• QRC+PIC improves QRC in RMSE, NRMSE, and physics residual on the main KS benchmark.Source: §6.1 · pp. 6–7
• Margins against strong simple baselines are small on KS, and Ridge-AR remains slightly stronger.Source: §6.1 · p. 7
• QRC+PIC substantially outperforms the ESN-family baselines in the reported KS configuration without establishing quantum-model superiority.Source: §6.1 · p. 7

Auxiliary benchmark: Burgers

• In the smoother Burgers reduced-order regime, persistence and simple autoregressive baselines remain strong, while QRC+PIC still improves over QRC alone.Source: §6.2 · p. 7
• Burgers is treated as an auxiliary sanity-check benchmark rather than the paper’s main result.Source: §6.2 · p. 7

Ablation and sensitivity analysis

• Correction quality is sensitive to configuration and loss balancing across the reported ablation sweeps.Source: §6.3 · pp. 7–8

• The main KS result supports QRC proposals improved by local physics-informed correction, rather than a monolithic quantum PINN.Source: §7 · p. 8

Benchmark scope

• Burgers is best treated as an auxiliary benchmark for debugging, visualization, and sanity checks because the main chaotic forecasting story belongs to KS.Source: §7 · p. 8

Baseline interpretation

• Strong classical baselines must remain because Ridge-AR shows that low-dimensional reduced-order dynamics can remain surprisingly linear.Source: §7 · p. 9

Method interpretation

• The PIC is a local physics-informed corrector, not a full PINN solver for the PDE from scratch.Source: §7 · p. 9

• The best overall KS result remains close to a simple linear baseline.Source: §8 · p. 9
• Burgers does not showcase strong quantum advantage because smooth reduced-order regimes can favor persistence or linear AR models.Source: §8 · p. 9
• The QRC is a pure-state simulated reservoir rather than hardware execution or a noisy quantum device.Source: §8 · p. 9
• KS correction quality is sensitive to configuration and physics-loss balancing across the reported ablation dimensions.Source: Figure 5 · p. 10

• The pipeline uses a pure-state QRC for closed-loop proposals and a PINN-based corrector for local refinement in field space.Source: §9 · p. 10
• On KS, the corrector consistently improves the QRC proposal under multi-seed, validation-only evaluation.Source: §9 · p. 10
• Burgers verifies pipeline robustness while showing that easy reduced-order regimes can favor trivial local baselines.Source: §9 · p. 10
• QRC proposals with local physics-informed correction are a viable reduced-order SciML architecture when physically consistent competitive forecasting matters more than headline quantum advantage.Source: §9 · p. 10