DeepExtremeCubes

Contributing person
datacite.contributor.ContactPerson

Chaonan Ji

Contributing person
datacite.contributor.ContactPerson

Miguel Mahecha

Contributing person
datacite.contributor.ContactPerson

Guido Kraemer

Documentation of the data
datacite.description.TechnicalInfo

- Self-describing Zarr Data - Complete documentation: https://arxiv.org/abs/2406.18179 - see DeepExtremesCubes_Access_v2.ipynb

Additional geographical or spatial references
datacite.geolocation

Global

References to related material
datacite.relatedItem.IsCitedBy

https://arxiv.org/abs/2410.01770

References to related material
datacite.relatedItem.IsDescribedBy

https://arxiv.org/abs/2406.18179

References to related material
datacite.relatedItem.IsSupplementedBy

https://essd.copernicus.org/preprints/essd-2024-396/

Description of the data
datacite.resourceType

This dataset is tailored to map around these extremes, focusing on persistent natural vegetation, and facilitate biosphere dynamics forecasting in response to the compound heatwave and drought extremes. It comprises over 40,000 globally sampled small data cubes (i.e. minicubes) in zarr format, with a spatial coverage of 2.5 by 2.5 km. Each minicube includes (i) Sentinel-2 L2A images, (ii) ERA5-Land variables and generated extreme event cube covering 2016 to 2022, and (iii) ancillary land cover and topography maps.

Type of the data
datacite.resourceTypeGeneral

Dataset

Total size of the dataset
datacite.size

2541048837002

Author
dc.contributor.author

Ji, Chaonan

Author
dc.contributor.author

Fincke, Tonio

Author
dc.contributor.author

Benson, Vitus

Author
dc.contributor.author

Camps-Valls, Gustau

Author
dc.contributor.author

Fernández-Torres, Miguel-Ángel

Author
dc.contributor.author

Gans, Fabian

Author
dc.contributor.author

Kraemer, Guido

Author
dc.contributor.author

Martinuzzi, Francesco

Author
dc.contributor.author

Montero, David

Author
dc.contributor.author

Mora, Karin

Author
dc.contributor.author

Pellicer-Valero, Oscar

Author
dc.contributor.author

Robin, Claire

Author
dc.contributor.author

Söchting, Maximilian

Author
dc.contributor.author

Weynants, Melanie

Author
dc.contributor.author

Mahecha, Miguel

Upload date
dc.date.accessioned

2024-12-19T18:15:30Z

Publication date
dc.date.available

2024-12-19T18:15:30Z

Data of data creation
dc.date.created

2023

Publication date
dc.date.issued

2024-12-19

Abstract of the dataset
dc.description.abstract

With climate extremes' rising frequency and intensity, robust analytical tools are crucial to predict their impacts on terrestrial ecosystems. Machine learning techniques show promise but require well-structured, high-quality, and curated analysis-ready datasets. Earth observation datasets comprehensively monitor ecosystem dynamics and responses to climatic extremes, yet the data complexity can challenge the effectiveness of machine learning models. Despite recent progress in deep learning to ecosystem monitoring, there is a need for datasets specifically designed to analyse compound heatwave and drought extreme impact. Here, we introduce the DeepExtremeCubes database, tailored to map around these extremes, focusing on persistent natural vegetation. It comprises over 40,000 globally sampled small data cubes (i.e. minicubes), with a spatial coverage of 2.5 by 2.5 km. Each minicube includes (i) Sentinel-2 L2A images, (ii) ERA5-Land variables and generated extreme event cube covering 2016 to 2022, and (iii) ancillary land cover and topography maps. The paper aims to (1) streamline data accessibility, structuring, pre-processing, and enhance scientific reproducibility, and (2) facilitate biosphere dynamics forecasting in response to compound extremes.

Public reference to this page
dc.identifier.uri

https://opara.zih.tu-dresden.de/handle/123456789/1186

Public reference to this page
dc.identifier.uri

https://doi.org/10.25532/OPARA-703

Publisher
dc.publisher

Universität Leipzig

Licence
dc.rights

Attribution 4.0 Internationalen

URI of the licence text
dc.rights.uri

http://creativecommons.org/licenses/by/4.0/

Specification of the discipline(s)
dc.subject.classification

3::34::313::313-01

Specification of the discipline(s)
dc.subject.classification

2::21::202::202-02

Specification of the discipline(s)
dc.subject.classification

4::44::409::409-05

Specification of the discipline(s)
dc.subject.classification

3::34::315

Title of the dataset
dc.title

DeepExtremeCubes

Research instruments
opara.descriptionInstrument

ERA5

Research instruments
opara.descriptionInstrument

Sentinel 2

Research instruments
opara.descriptionInstrument

Landsat

Research instruments
opara.descriptionInstrument

ESA CCI

Research instruments
opara.descriptionInstrument

Copernicus DEM

Underlying research object
opara.descriptionObject.NonPhysicalObject

Extreme Events

Software
opara.descriptionSoftware.ResourceProcessing

Zarr

Software
opara.descriptionSoftware.ResourceProcessing

https://github.com/DeepExtremes/minicube-generation

Software
opara.descriptionSoftware.ResourceProcessing

python

Project abstract
opara.project.description

Climate extremes are on the rise, which is one of the most critical manifestations of climate change. Compound events can drive a combination of spatial and/or temporal hazards, and the instantaneous effect and long-term impact on society and the environment are typically much higher than a single event on its own. However, the multi-dimensional nature of compound events leads to a series of methodological challenges. The Deep-Extremes project aims at - Focusing on compound heat and drought events on a global scale, detecting based on long-term climate and land-surface data, combining EO archives and other observation data, with methods tailored to multivariate event detection. - Sampling a subset of large events in the Sentinel era and zooming into the events and in unaffected areas around the event with high-dimensional “mini-cubes”. - Training complementary deep-learning methods for prediction and understanding dynamics in such events. - Implementing the tested and validated workflow in a cloud environment and developing it further based on community feedback. - Engaging with the community via workshops and science discussions to further develop the proposed framework. The project is funded by the European Space Agency (ESA), part of the AI4SCIENCE activity. The first AI4SCIENCE ITT focuses on Extreme Events, Multi-Hazards and Compound Events, and contributes to the ESA Extremes and Natural Disasters Science Cluster.

Public project website(s)
opara.project.publicReference

https://eo4society.esa.int/projects/deep-extremes/

Public project website(s)
opara.project.publicReference

https://rsc4earth.de/project/deepextremes/

Public project website(s)
opara.project.publicReference

https://opensciencedata.esa.int/projects/deep-extremes/collection

Project title
opara.project.title

DeepExtremes
Files
Original bundle
Now showing 1 - 10 of 10
Loading...
Thumbnail Image
Name:
Africa.zip
Size:
371.19 GB
Format:
Unknown data format
Description:
Contains all cubes located in Africa. md5sum 11e6360b65f51adff7dd4be4ca0b4586 Africa.zip
Loading...
Thumbnail Image
Name:
archive_listing.txt
Size:
707.3 MB
Format:
Plain Text
Description:
Loading...
Thumbnail Image
Name:
Asia.zip
Size:
519.85 GB
Format:
Unknown data format
Description:
Contains all cubes located in Asia. md5sum 805f3022c4d1b2d6924a31b3a19a82ae Asia.zip
Loading...
Thumbnail Image
Name:
DeepExtremesCubes_Access_v2.ipynb
Size:
1 MB
Format:
Unknown data format
Description:
Example notebook showing how to access the data. md5sum 3d0bd700b2a147b5ded0f6063d1265e8 DeepExtremesCubes_Access_v2.ipynb
Loading...
Thumbnail Image
Name:
Europe.zip
Size:
499.95 GB
Format:
Unknown data format
Description:
Contains all cubes located in
Loading...
Thumbnail Image
Name:
example.zip
Size:
67.98 MB
Format:
Unknown data format
Description:
Contains a single cube for testing access. md5sum 133131eb0192d5482a8746e1392cdaa8 example.zip
Loading...
Thumbnail Image
Name:
mc_registry_v6.csv
Size:
16.66 MB
Format:
Comma-Separated Values
Description:
Contains extra metadata on the cubes. 58d20476e5533976125bccd3526c5437 mc_registry_v6.csv
Loading...
Thumbnail Image
Name:
North_America.zip
Size:
467.62 GB
Format:
Unknown data format
Description:
Contains all cubes located in North America. md5sum 8e456df98a1532d7aa279e7ec738d3a9 North_America.zip
Loading...
Thumbnail Image
Name:
Oceania.zip
Size:
43.25 GB
Format:
Unknown data format
Description:
Contains all cubes located in Oceania. md5sum 489e5ed4f430f2405723c02abb779753 Oceania.zip
Loading...
Thumbnail Image
Name:
South_America.zip
Size:
463.9 GB
Format:
Unknown data format
Description:
Contains all cubes located in South America. md5sum 902c4d0bb4daf62ef86ae28cfe1b92eb South_America.zip
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
4.66 KB
Format:
Item-specific license agreed to upon submission
Description:
Attribution 4.0 International