mlsanityData to 14 Oct 2026

Sparse Local Implicit Image Function for sub-km Weather Downscaling

arXiv 2510.20228 ↗First posted 23 Oct 2025cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce SpLIIF to generate implicit neural representations and enable arbitrary downscaling of weather variables. We train a model from sparse weather stations and topography over Japan and evaluate in- and out-of-distribution accuracy predicting temperature and wind, comparing it to both an interpolation baseline and CorrDiff. We find the model to be up to 50% better than both CorrDiff and the baseline at downscaling temperature, and around 10-20% better for wind.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

16 of 24 references.

References · 16

  1. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  2. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  3. 2023ClimaX: A foundation model for weather and climatecited by 337
  4. 2023Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscalingcited by 110
  5. 2020Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Networkcited by 70
  6. 2024DiffDA: a Diffusion Model for Weather-scale Data Assimilationcited by 61
  7. 2024Generative Data Assimilation of Sparse Weather Station Observations at Kilometer Scalescited by 27
  8. 2024Wind speed super-resolution and validation: from ERA5 to CERRA via diffusion modelscited by 15
  9. 2024MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modelingcited by 12
  10. 2022Deep generative model super-resolves spatially correlated multiregional climate datacited by 9
  11. 2024On the Effectiveness of Neural Operators at Zero-Shot Weather Downscalingcited by 5
  12. 2025Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observationscited by 5
4 more
  1. 2024Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approachescited by 4
  2. 2025Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecastingcited by 3
  3. 2024TAUDiff: Highly efficient kilometer-scale downscaling using generative diffusion modelscited by 2
  4. 2024Continuous latent representations for modeling precipitation with deep learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026WindINR: Latent-State INR for Fast Local Wind Query and Correction in Complex Terraincited by 0