{"ID":2837757,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.19431","arxiv_id":"2511.19431","title":"Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution","abstract":"There has been great progress in improving numerical weather prediction and climate models using machine learning. However, most global models act at a kilometer-scale, making it challenging to model individual clouds and factors such as extreme precipitation, wind gusts, turbulence, and surface irradiance. Therefore, there is a need to move towards higher-resolution models, which in turn require high-resolution real-world observations that current instruments struggle to obtain. We present Cloud4D, the first learning-based framework that reconstructs a physically consistent, four-dimensional cloud state using only synchronized ground-based cameras. Leveraging a homography-guided 2D-to-3D transformer, Cloud4D infers the full 3D distribution of liquid water content at 25 m spatial and 5 s temporal resolution. By tracking the 3D liquid water content retrievals over time, Cloud4D additionally estimates horizontal wind vectors. Across a two-month deployment comprising six skyward cameras, our system delivers an order-of-magnitude improvement in space-time resolution relative to state-of-the-art satellite measurements, while retaining single-digit relative error ($\u003c10\\%$) against collocated radar measurements. Code and data are available on our project page https://cloud4d.jacob-lin.com/.","short_abstract":"There has been great progress in improving numerical weather prediction and climate models using machine learning. However, most global models act at a kilometer-scale, making it challenging to model individual clouds and factors such as extreme precipitation, wind gusts, turbulence, and surface irradiance. Therefore,...","url_abs":"https://arxiv.org/abs/2511.19431","url_pdf":"https://arxiv.org/pdf/2511.19431v2","authors":"[\"Jacob Lin\",\"Edward Gryspeerdt\",\"Ronald Clark\"]","published":"2025-11-24T18:59:37Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"physics.ao-ph\"]","methods":"[\"Transformer\"]","project_urls":"[\"https://cloud4d.jacob-lin.com/\"]","has_code":false,"code_links":[{"ID":606715,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2837757,"paper_url":"https://arxiv.org/abs/2511.19431","paper_title":"Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution","repo_url":"https://github.com/linjacob2/cloud4d","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0},{"ID":606716,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2837757,"paper_url":"https://arxiv.org/abs/2511.19431","paper_title":"Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution","repo_url":"https://github.com/nerfies/nerfies.github.io","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}