Saved in:
Bibliographic Details
Main Authors: Lin, Jacob, Gryspeerdt, Edward, Clark, Ronald
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.19431
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908675254255616
author Lin, Jacob
Gryspeerdt, Edward
Clark, Ronald
author_facet Lin, Jacob
Gryspeerdt, Edward
Clark, Ronald
contents 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 ($<10\%$) against collocated radar measurements. Code and data are available on our project page https://cloud4d.jacob-lin.com/.
format Preprint
id arxiv_https___arxiv_org_abs_2511_19431
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
Lin, Jacob
Gryspeerdt, Edward
Clark, Ronald
Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
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 ($<10\%$) against collocated radar measurements. Code and data are available on our project page https://cloud4d.jacob-lin.com/.
title Cloud4D: Estimating Cloud Properties at a High Spatial and Temporal Resolution
topic Computer Vision and Pattern Recognition
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2511.19431