physics.ao-phFeb 18, 2026

CASCADE: Cross-scale Advective Super-resolution with Climate Assimilation and Downscaling Evolution

Authors: Alexander Kovalenko

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Super-resolution of geophysical fields presents unique challenges beyond natural image enhancement: fine-scale structures must respect physical dynamics, conserve mass and energy, and evolve coherently in time. These constraints are especially critical for extreme events, where rare, localized, high-intensity features drive impacts and where temporally inconsistent "hallucinated" detail can misrepresent hazards. We introduce CASCADE (Cross-scale Advective Super-resolution with Climate Assimilation and Downscaling Evolution), a framework that reframes spatiotemporal super-resolution as an explicit transport process across scales. Rather than hallucinating high-frequency content per pixel, CASCADE reconstructs fine structure by iteratively advecting coarse information along learned, flow-conditioned velocity fields through semi-Lagrangian warping. The architecture decomposes motion into resolved (large-scale) and subgrid (unresolved) components, mirroring the closure problem in numerical weather prediction, and enforces low-resolution consistency through an assimilation-style innovation step. Evaluated on SEVIR radar data for 4x super-resolution of severe convective storms, CASCADE outperforms strong baselines across both continuous metrics (PSNR, SSIM, MAE) and threshold-based skill scores (CSI, HSS, POD) while providing interpretable diagnostics through visualizable velocity and correction fields. By encoding advection as the fundamental operator rather than learning it implicitly, CASCADE produces temporally coherent, physically consistent, and mass-conserving reconstructions well suited to advection-dominated extremes in atmospheric and oceanic applications.

Figures & tables

Figure 1: Varification metrics: CSI (top left), FAR (top right), HSS (bottom left), POD (bottom right).
MethodPSNR ↑\uparrowSSIM ↑\uparrowMAE ↓\downarrowCSI L↑{}_{\mathrm{L}}\uparrowCSI M↑{}_{\mathrm{M}}\uparrowCSI H↑{}_{\mathrm{H}}\uparrowHSS M↑{}_{\mathrm{M}}\uparrow
Bilinear31.700.93360.010190.9130.9020.8310.941
Bicubic33.560.95090.008140.9290.9190.8690.951
U-Net (baseline)35.330.96370.006760.9490.9300.8910.958
CASCADE-DD (ours)35.880.96930.006160.9550.9330.8950.960
Table 1: Quantitative evaluation of 4 ×\times super-resolution on SEVIR VIL radar data. Best results in bold .
Figure 2: Leared storm advection flow.
 Classical deep SRCASCADE
Core operationPer-pixel regressionTransport (semi-Lagrangian warp)
Temporal informationNone (single frame)NN -frame flow estimation / time-stepping
ConservationNot enforcedApproximate by construction + LR loss
InterpretabilityBlack-box decoderVisualisable velocity fields + innovation
Temporal coherenceNot guaranteed (flickering)Built-in via state advection
Architecture biasTranslation equivariance (CNN)Transport equivariance + scale decomposition
Table 2: Structural comparison between classical deep SR and the CASCADE framework.
More in this topic

Image Super-Resolution

Image super-resolution reconstructs high-resolution images from lower-resolution observations, balancing detail, fidelity, and computational cost.

See all 248 papers

Explore similar work

CardsList
Apr 23, 2026

A Scale-Adaptive Framework for Joint Spatiotemporal Super-Resolution with Diffusion Models

Deep-learning video super-resolution has progressed rapidly, but climate applications typically super-resolve (increase resolution) either space or time, and joint spatiotemporal models are often designed for a single pair of super-resolution (SR) factors (upscaling spatial and temporal ratio between the low-resolution sequence and the high-resolution sequence), limiting transfer across spatial resolutions and temporal cadences (frame rates). We present a scale-adaptive framework that reuses the same architecture across factors by decomposing spatiotemporal SR into a deterministic prediction of the conditional mean, with attention, and a residual conditional diffusion model, with an optional mass-conservation (same precipitation amount in inputs and outputs) transform to preserve aggregated totals. Assuming that larger SR factors primarily increase underdetermination (hence required context and residual uncertainty) rather than changing the conditional-mean structure, scale adaptivity is achieved by retuning three factor-dependent hyperparameters before retraining: the diffusion noise schedule amplitude beta (larger for larger factors to increase diversity), the temporal context length L (set to maintain comparable attention horizons across cadences) and optionally a third, the mass-conservation function f (tapered to limit the amplification of extremes for large factors). Demonstrated on reanalysis precipitation over France (Comephore), the same architecture spans super-resolution factors from 1 to 25 in space and 1 to 6 in time, yielding a reusable architecture and tuning recipe for joint spatiotemporal super-resolution across scales.

Max Defez, Filippo Quarenghi, Mathieu Vrac +2

Faculty of Geosciences and Environment University of Lausanne Lausanne, VD, Switzerland · Laboratory for Climate and Environmental Sciences Gif-sur-Yvette, France · Department of Computer Science University of California Irvine, California, United States of America

Video Super-ResolutionConditional Diffusion ModelsClimate Downscaling
AskPDF
Apr 1, 2026

Super-Resolving Coarse-Resolution Weather Forecasts With Flow Matching

Machine learning-based weather forecasting models now surpass state-of-the-art numerical weather prediction systems, but training and operating these models at high spatial resolution remains computationally expensive. We present a modular framework that decouples forecasting from spatial resolution by applying learned generative super-resolution as a post-processing step to coarse-resolution forecast trajectories. We formulate super-resolution as a stochastic inverse problem, using a residual formulation to preserve large-scale structure while reconstructing unresolved variability. The model is trained with flow matching exclusively on reanalysis data and is applied to global medium-range forecasts. We evaluate (i) design consistency by re-coarsening super-resolved forecasts and comparing them to the original coarse trajectories, and (ii) high-resolution forecast quality using standard ensemble verification metrics and spectral diagnostics. Results show that super-resolution preserves large-scale structure and variance after re-coarsening, introduces physically consistent small-scale variability, and achieves competitive probabilistic forecast skill at 0.25° resolution relative to an operational ensemble baseline, while requiring only a modest additional training cost compared with end-to-end high-resolution forecasting.

Aymeric Delefosse, Anastase Charantonis, Dominique Béréziat

Inria, ARCHES, Paris, France · Sorbonne Université, CNRS, LIP6, Paris, France

Weather ForecastingProbabilistic Forecasting
AskPDF
Jul 21, 2026

Physics-Informed Super-Resolution of Atmospheric Data

In the context of global warming, extreme events have become more frequent and intense, making their trustworthy detection and forecasting more important than ever. Yet, atmospheric observations lack sufficient spatial resolution, motivating atmospheric data downscaling as a way to reconstruct high-resolution data from coarse observations. This task is now being formulated as a super-resolution (SR) problem with machine learning methods featuring high efficiency. Nevertheless, it remains unclear whether the super-resolved atmospheric data still satisfies fundamental physics governing the Earth system, raising concerns about their trustworthiness in climate-related applications. In this work, we address this challenge by constraining SR models to respect hydrostatic primitive equations that represent multivariate atmospheric physics. First, we propose a Physics-Informed Super-Resolution (PISR) method involving multi-scale physics-informed objectives based on primitive equations. PISR favors the SR outputs to respect these equations and therefore naturally encodes inter-variable relationships. In addition, we propose a metric called Normalized Physical Consistency (NPC) derived from said primitive equations to measure the physical consistency of super-resolved data. Experiments on ERA5, CERRA, and COSMO demonstrate that PISR enhances the reconstruction fidelity by improving physical consistency, SR accuracy, and downstream detection of extreme events, as demonstrated by case studies in heatwaves and extreme winds.

Chang Xu, Gencer Sumbul, Hugo Porta +3

EPFL, Switzerland · University of Cambridge, England

Climate ModelingPhysics-Informed MLImage Super-Resolution
AskPDF