R.I.P.
๐ป
Ghosted
Longwang: Zero-Shot Global Spatiotemporal Precipitation Downscaling with a Latent Generative Prior
May 17, 2026 ยท Grace Period ยท + Add venue
Authors
Yue Wang, Daniele Visioni
arXiv ID
2605.17603
Category
physics.ao-ph
Cross-listed
cs.LG
Citations
0
Abstract
High-resolution precipitation information is essential for climate impact assessment, yet global climate models remain too coarse to resolve key small-scale processes. Existing machine learning downscaling methods often require paired low- and high-resolution data for supervised learning, are tied to fixed regions or scale factors during inference, and can be computationally expensive to train and run in physical space. Here we introduce Longwang, a zero-shot latent generative framework for global spatiotemporal precipitation downscaling. Longwang learns a context-conditioned latent generative prior and combines it with a physically informed observation operator through posterior sampling, enabling daily O(10 km) precipitation fields to be generated from monthly O(100 km) inputs. On ERA5 reanalysis, Longwang outperforms standard posterior sampling with an unconditional generative prior in reconstructing fine-scale spatial patterns, preserving temporal coherence, and recovering extreme precipitation intensities. The framework further generalizes to historical climate simulations and future climate projections under substantial distribution shift.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ physics.ao-ph
R.I.P.
๐ป
Ghosted
Neural General Circulation Models for Weather and Climate
R.I.P.
๐ป
Ghosted
Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variability
R.I.P.
๐ป
Ghosted
Source localization in an ocean waveguide using supervised machine learning
R.I.P.
๐ป
Ghosted
A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
R.I.P.
๐ป
Ghosted