An Unexpectedly Large Count of Trees in the West African Sahara and Sahel - Bassin Arachidier au Sénégal

This dataset provides georeferenced polygon vectors of individual tree canopy geometries for dryland areas in West African Sahara and Sahel that were derived using deep learning applied to 50 cm resolution satellite imagery. More than 1.8 billion non-forest trees (i.e., woody plants with a crown size over 3 m2) over about 1.3 million km2 were identified from panchromatic and pansharpened normalized difference vegetation index (NVDI) images at 0.5 m spatial resolution using an automatic tree detection framework based on supervised deep-learning techniques. Combined with existing and future fieldwork, these data lay the foundation for a comprehensive database that contains information on all individual trees outside of forests and could provide accurate estimates of woody carbon in arid and semi-arid areas throughout the Earth for the first time.

Date (Revision): 2022-05-17T19:08:39

Edition: 1.0

Edition date: 2015-01-01

Identifier: https://doi.org/10.3334/ORNLDAAC/1832

Principal investigator

NASA ORNL DAAC - NASA

Status: Completed

Principal investigator

NASA ORNL DAAC - NASA

Maintenance and update frequency: As needed

General

remote sensing
vegetation map
deep learning
Very High spatial resolution optical imagery

GEMET - INSPIRE themes, version 1.0

Land cover

GEMET - Concepts

GCMD Keywords viewer

TETIS Thesaurus, version 1.0 21112019

Biodiversité

Use limitation: Credits: Brandt, M., C.J. Tucker, A. Kariryaa, K. Rasmussen, C. Abel, J.L. Small, J. Chave, L.V. Rasmussen, P. Hiernaux, A.A. Diouf, L. Kergoat, O. Mertz, C. Igel, F. Gieseke, J. Schöning, S. Li, K.A. Melocik, J.R. Meyer, S. Sinno, E. Romero, E.N. Glennie, A. Montagu, M. Dendoncker, and R. Fensholt. 2020. An unexpectedly large count of trees in the West African Sahara and Sahel. ORNL DAAC, Oak Ridge, Tennessee, USA. https://doi.org/10.3334/ORNLDAAC/1832. This dataset is openly shared, without restriction, in accordance with the EOSDIS Data Use Policy: https://earthdata.nasa.gov/earth-observation-data/data-use-policy?_ga=2.213474524.955659520.1604914682-676515214.1576510456

Access constraints: unrestricted

Use constraints: unrestricted

Classification: Unclassified

User note: unclassified

Classification system: no classification in particular

Handling description: description

Spatial representation type: Vector

Distance: 50 cm

Metadata language: English

Character set: UTF8

Topic category

Environment
Imagery base maps earth cover
Biota

Begin date: 2005-11-01T00:00:00Z

End date: 2018-03-31T00:00:00Z

Supplemental Information: some additional information

Reference system identifier: EPSG / 32628

Distribution format

GeoPackage, ESRI Shapefile ( 1.0 )

OnLine resource: Vector Layer WARNING: 15Gb!! ( file for download )

OnLine resource: Geopackage ( file for download )

OnLine resource: NASA African trees tilemap ( file for download )

OnLine resource

utm_28_tiles ( OGC:WMS )

WMS Service

OnLine resource

utm_29_tiles ( OGC:WMS )

WMS Service

Hierarchy level: Dataset

Conformance result

Alternate title: This is is some data quality check report

Date (Publication): 2022-05-17T19:08:39

Explanation: some explanation about the conformance

Pass: Yes

Conformance result

Date (Publication): 2010-12-08T12:00:00

Explanation: See the referenced specification

Pass: Yes

Conformance result

Date (Publication): 2008-12-04T12:00:00

Explanation: See the referenced specification

Pass: Yes

Statement: The mapping of woody plants at the level of single trees was achieved by the use of satellite data at very high spatial resolution (0.5 m) from DigitalGlobe satellites, combined with modern machine-learning techniques. More than 50,000 DigitalGlobe multispectral images from the QuickBird-2, GeoEye-1, WorldView-2 and WorldView-3 satellites, were collected from 2005–2018 (in November to March) from 12° to 24° N latitude within Universal Transverse Mercator zones 28 and 29 (provided under the NextView license from the National Geospatial Intelligence). Normalized difference vegetation index (NDVI) images were used to distinguish tree crowns from the non-vegetated background because the images were taken from a period during which only woody plants are photosynthetically active in the study area. A set of decision rules was applied to select images for the mosaic, consisting of 25 × 25 km tiles. This resulted in 11,128 images that were used for the study. The neural network model (UNet; publicly available at https://doi.org/10.5281/zenodo.3978185) was used to automatically segment the tree crowns—that is, to detect tree crowns in the input images. The segmented areas were then converted to polygons for counting the trees and measuring their crown size. Using machine learning coupled to training data of 89,899 manually delineated and annotated trees, the location of individual trees over 1,300,000 km2 and their crown area were determined from the input images. Every tree with a crown area >3 m2 was enumerated resulting in 1,837,565,501 trees.