2026-10-11T06:54:09Z https://www.scidb.cn/oai

10.57760/sciencedb.010ga 2026-09-04T17:33:40Z

2026-09-04 GF6RTSChange2021–2025: A GF-6 Long-Term Dataset for Retrogressive Thaw Slump Deep Learning Change Detection doi:10.57760/sciencedb.010ga en This dataset was assembled for long-term change detection of retrogressive thaw slumps (RTSs). It contains five GF-6 PMS acquisitions of the same area, spanning 2021–2025, together with pixel-level reference labels. The images are four-band GeoTIFFs in WGS 84 / UTM zone 46N (EPSG:32646). Every image has 10,000 columns and 9,000 rows at a 2 m ground sampling distance, giving an approximately 20 km × 18 km footprint (about 360 km²) and an area of 4 m² per pixel. The dataset has identical dimensions, CRS, and affine transform. They can therefore be compared pixel-to-pixel on a single analysis grid. The full interval from 03 February 2021 to 22 October 2025 is 1,722 d. The successive gaps are 660, 365, 332, and 365 d. Seasonal consistency reduces interannual differences caused by illumination, phenology, surface wetness, and atmosphere. The date embedded in each product name follows the YYYY_MMDD convention. The five source images were processed in ENVI through radiometric correction, atmospheric correction, orthorectification, and pansharpening. Radiometric correction placed sensor measurements on a comparable radiometric scale; atmospheric correction reduced residual path effects; orthorectification addressed terrain and acquisition geometry; and pansharpening combined multispectral information with fine spatial detail to provide the 2 m, four-band analysis imagery. Following geometric alignment, all five images underwent a common relative radiometric correction and histogram matching. The purpose was to map the dates into a shared radiometric domain and suppress non-surface variation arising from acquisition conditions, residual atmosphere, and sensor-response differences. The operation leaves the common grid unchanged and modifies only the radiometric comparability of pixel values. Semantic-segmentation outputs served as initial candidates, after which individual RTS objects were visually checked, revised, and manually delineated to create inventory-style binary masks. Both masks were standardised to uint8 values 0 and 1: class 1 denotes RTS and class 0 denotes background, former NoData, or other invalid values. No mixed NoData category remains in the binary training masks. Long-Term; Change Detection; Deep Learning; 2021–2025; Retrogressive Thaw Slump Yi Yuan Wei Huang Guiyun Zhou EMBARGO https://creativecommons.org/licenses/by-nc/4.0/ dataset Science Data Bank