This dataset is based on Landsat remote sensing imagery and obtained desert area images through preprocessing algorithms such as radiometric calibration and atmospheric correction. The sand dune crests were extracted manually through visual interpretation. The deserts covered in the dataset mainly include the Taklamakan Desert, the Junggar Basin Desert (the desert in the Junggar Basin), the Badain Jaran Desert, the Tengger Desert, the Kumtag Desert, the Qaidam Basin Desert, the Kubuqi Desert, and the Wulanbuhu DesertAtyrau desert,Karakum desert,Kavir desert,Kharan desert,Kyzylkum desert,Lut desert,Moinkum desert,Registan desert,Thar desert. It contains five periods from 2000 to 2020. This sand dune crest dataset provides a basis for the extraction of sand dune crests and the study of sand dune movement patterns in desert areas of China.
Landsat Images: Download from the websites of the United States Geological Survey (https://www.usgs.gov/) and Geospatial Data Cloud (http://www.gscloud.cn/).
1. Pre-processing of Remote Sensing Data：Radiometric calibration, atmospheric correction, image stitching, cropping, color correction
2. Artificial annotation method to extract sand ridges：The edge annotation software tool based on PyQt5 was used to manually label the cropped images with sand ridge lines, which became the training set of the model.
3. Manual Vectorization and Entering of Attribute Data：The training set is flipped and rotated in 16 directions to get 32 times the data set.
The average accuracy of the marked sand ridges is within 1 pixel (30 m).
| # | number | name | type |
| 1 | 2022YFF0711702-04 | National key R & D plan |
This work is licensed under
CC BY 4.0 (Creative Commons Attribution 4.0 International License).
CSTR:11738.11.NCDC.NIEER.DB6903.2025
10.12072/ncdc.nieer.db6903.2025
