Reproduce “Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Anirudh Avireddy, Manmeet Singh, Shivanshi Singh, Ayush Raj, Saptarishi Dhanuka, Parthasarathi Mukhopadhyay, Sandeep Juneja
SDA uses a conditional diffusion model to generate fine-scale 2-m temperature fields, then guides sampling toward sparse observations without retraining for each observation mask. In tests on 32 AORC 2022 patches, with 1% of valid cells revealed, its hidden-cell RMSE was 0.318 K, below the nearest-anomaly-plus-climatology baseline’s 0.431 K. The result concerns synthetic AORC reveals, not independent station truth.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.