The data set of land use map of national key prevention areas in Heihe oasis includes the land use of Jinta County and Gaotai County in Gansu Province in 2013, 2014, 2015, 2016 and 2017, with the format of xlsx. The data is named in the form of "key management area + administrative area + year + land use statistics table", such as "key management area ×× County ×× year soil" Statistical table of land utilization ". The classification system of land use includes 8 first class, 22 second class and 2 third class.
The data source is Landsat TM and ETM + data, mainly obtained from USGS (https://glovis.usgs.gov/), and a few from China geospatial data cloud (http://www.gscloud.cn/)
Based on ecognition software platform, the method of object-oriented computer automatic classification and manual visual interpretation is used to extract the land use data of the study area year by year. Then three methods are used to verify the data accuracy: field sample point survey, high-resolution image recognition and Google Earth sample point recognition. Finally, according to the classification standard of land use, the statistical table of land use is obtained.
Remote-sensing images are pre-processed by radiation correction, orthorectification, and fusion and mosaic. The actual surface area corresponding to the minimum map area is not less than 0.1hm2, the polygons have no overlap, no gaps, and the map properties are not vacant or redundant. Before interpreting remote sensing images, the remote sensing imagery, typical surveys, and field comparison methods are used to establish the land use remote sensing interpretation marks. Based on the remote sensing image, combined with the interpretation mark, the land use type is extracted. Interpretation of interpretation results: extract no less than 5% of the total patch for verification. The number and results of field verification samples meet the requirements of the Technical Specifications for Remote Sensing Monitoring of Soil and Water Conservation (SL592-2012). For verification maps, 10% are selected as verification samples for field verification.
This work is licensed under a
Creative
Commons Attribution 4.0 International License.
CSTR:11738.11.ncdc.HHSTBC.2020.201
10.12072/ncdc.HHSTBC.db0031.2021