REVIEW 8 cited by
Generative Diffusion-based Downscaling for Climate
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Downscaling, or super-resolution, provides decision-makers with detailed, high-resolution information about the potential risks and impacts of climate change, based on climate model output. Machine learning algorithms are proving themselves to be efficient and accurate approaches to downscaling. Here, we show how a generative, diffusion-based approach to downscaling gives accurate downscaled results. We focus on an idealised setting where we recover ERA5 at $0.25\degree$~resolution from coarse grained version at $2\degree$~resolution. The diffusion-based method provides superior accuracy compared to a standard U-Net, particularly at the fine scales, as highlighted by a spectral decomposition. Additionally, the generative approach provides users with a probability distribution which can be used for risk assessment. This research highlights the potential of diffusion-based downscaling techniques in providing reliable and detailed climate predictions.
Forward citations
Cited by 8 Pith papers
-
Boosting Ensembles for Statistics of Tails at Conditionally Optimal Advance Split Times
Ensemble boosting with a thresholded-entropy rule for choosing the advance split time accurately samples tail probabilities of extreme tracer fluctuations in a quasigeostrophic model.
-
RainShift: A Benchmark for Precipitation Downscaling Across Geographies
RainShift is a global benchmark showing that precipitation downscaling models lose up to 30% accuracy when applied to unseen Global South regions, and input quantile mapping recovers some of that loss.
-
Multimodal Spatiotemporal Atmospheric Data Assimilation with Latent Video Flow-matching
A single latent video flow-matching prior over ERA5, guided by sparse real observations, performs filtering, smoothing, and observation-to-forecast without retraining.
-
FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systems
A hybrid U-Net and Transformer diffusion backbone trained in residual space with a velocity parametrization outperforms baselines on 2D turbulence super-resolution and forecasting, and generalizes zero-shot to unseen ...
-
Domain-Adaptive Climate Downscaling Under Temporal Distribution Shift
Adversarial temporal domain adaptation on LR features improves daily CONUS temperature downscaling under future warming more than statistical bias correction or non-adaptive deep models, especially late-century.
-
Temporal Bridges for Spatial Resolution: Enhancing Climate Data Super-Resolution with Bidirectional Alignment
Bidirectional latent-space temporal alignment, used as a training regularizer, improves climate super-resolution accuracy over ClimaX, VRT, and SwinIR on CMIP6-to-ERA5 downscaling.
-
Physics-Informed Super-Resolution of Atmospheric Data
Adding multi-scale hydrostatic-primitive-equation losses to atmospheric super-resolution models improves reported physical-consistency scores and some reconstruction/event-detection metrics, but the metric and constra...
-
Breaking the Statistical Similarity Trap in Extreme Convection Detection
DART's dual-decoder decomposition with event-weighted training improves the critical success index for extreme convection detection from coarse atmospheric inputs, though the headline IVT ablation lacks statistical support.
Discussion (0). Sign in to comment.