{"ID":2850990,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.20228","arxiv_id":"2510.20228","title":"Sparse Local Implicit Image Function for sub-km Weather Downscaling","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.20228","url_pdf":"https://arxiv.org/pdf/2510.20228v1","authors":"[\"Yago del Valle Inclan Redondo\",\"Enrique Arriaga-Varela\",\"Dmitry Lyamzin\",\"Pablo Cervantes\",\"Tiago Ramalho\"]","published":"2025-10-23T05:20:26Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}