Featured Products

Source Cooperative is a Radiant Earth project

3D Clouds · TACO · Source Cooperative | Source Cooperative

3D Clouds

This repository hosts the AI-ready datasets for the paper "Global 3D Reconstruction of Clouds & Tropical Cyclones." It contains paired 2D geostationary imagery (GOES, MSG, Himawari) and 3D vertical profiles (CloudSat/CALIPSO) used to train ML models for 3D cloud reconstruction, with a dedicated dataset for tropical cyclones.

Product Details

Visibility: Public
Owner: TACO
Created: 29 Dec 2025
Last Updated: 29 Dec 2025

Product Contents

root

finetune

msi

README

Cloud 3D - MSG/SEVIRI Finetuning Dataset

MSG/SEVIRI finetuning subset from the Global 3D Cloud Reconstruction Dataset. Contains colocated pairs of Meteosat Second Generation (MSG) SEVIRI geostationary imagery with CloudSat radar profiles for supervised 3D cloud structure reconstruction. Each sample includes: multispectral SEVIRI imagery (12 spectral channels + satellite/solar angles), CloudSat vertical profiles as ground truth, and a colocation mask indicating valid CloudSat footprint pixels. 256x256 pixel patches in Cloud-Optimized GeoTIFF format. Temporal coverage spans 2006-2020, providing the longest continuous record among the three geostationary sensors in the Cloud3D dataset.

Dataset Information

Version: 0.1.0

License: CC-BY-4.0

Keywords: cloud microphysics, 3d reconstruction, geostationary satellites, MSG, SEVIRI, Meteosat, CloudSat, remote sensing, tropical cyclones, deep learning

Tasks: regression, foundation-model

Dataset Overview

Partitions: 104 files Spatial coverage: [-50.78, -42.57, 50.37, 42.62] (WGS84) Temporal coverage: 2006-06-12 to 2020-08-26

Dataset Structure (Root-Sibling Uniform Tree)

Root: FOLDER (181,653 samples)

Hierarchy:

Level 1: FILE → FILE (363,306 samples)

Metadata Fields

LEVEL0

Field	Type	Description
`id`	`string`	Unique sample identifier within parent scope. Must be unique among siblings.
`type`	`string`	Sample type discriminator (FILE or FOLDER).
`stac:crs`	`string`	Coordinate reference system (WKT2, EPSG, or PROJ)
`stac:tensor_shape`	`list<item: int64>`	Raster dimensions [bands, height, width]
`stac:geotransform`	`list<item: double>`	GDAL affine transform
`stac:time_start`	`timestamp[us]`	Start timestamp (μs since Unix epoch, UTC)
`stac:centroid`	`binary`	Center point in EPSG:4326 (WKB)
`stac:time_end`	`timestamp[us]`

LEVEL1

Field	Type	Description
`id`	`string`	Unique sample identifier within parent scope. Must be unique among siblings.
`type`	`string`	Sample type discriminator (FILE or FOLDER).
`geotiff:stats`	`list<item: list<item: float>>`	Per-band statistics (List[List[Float32]]): categorical mode returns class probabilities, continuous mode returns [min, max, mean, std, valid%, p25, p50, p75, p95]
`taco:header`	`binary`	Binary TACOTIFF header (35 bytes + tile counts) for fast reading without IFD parsing
`internal:current_id`	`int64`	Current sample position at this level (0-indexed). Enables O(1) random access and relational JOINs (ZIP, FOLDER, TACOCAT).
`internal:parent_id`	`int64`	Foreign key referencing parent sample position in previous level (ZIP, FOLDER, TACOCAT).
`internal:relative_path`	`string`

Usage

Python

R

Julia

Data Providers

EUMETSAT — producer https://www.eumetsat.int European Space Agency (ESA) — licensor https://www.esa.int source.coop — host https://source.coop

Dataset Curators

Name	Organization	Email
Cesar Aybar	Universitat de València	cesar.aybar@uv.es
Shirin Ermis	University of Oxford	—
Lilli Freischem	University of Oxford	—
Stella Girtsou	National Observatory of Athens	—
Kyriaki-Margarita Bintsi	Harvard Medical School	—
Emiliano Diaz Salas-Porras	Universitat de València	—
Michael Eisinger	European Space Agency	—
William Jones	University of Oxford	—
Anna Jungbluth	European Space Agency	—
Benoit Tremblay	Environment and Climate Change Canada	—

Publications & Citations

If you use this dataset in your research, please cite:

DOI: 10.48550/arXiv.2511.04773

Ermis, S., Aybar, C., Freischem, L., Girtsou, S., Bintsi, K.-M., Diaz Salas-Porras, E., Eisinger, M., Jones, W., Jungbluth, A., & Tremblay, B. (2025). Global 3D Reconstruction of Clouds & Tropical Cyclones. Tackling Climate Change with Machine Learning Workshop at NeurIPS 2025.

Primary publication describing the dataset and methodology

BibTeX

Generated with ❤️ using TacoToolbox v0.23.3