Permafrost Distribution Dataset over Eurasian at 1 km Resolution (2000–2020)

Based on 1749 permafrost and non permafrost sites, multiple high-resolution environmental factors such as temperature, precipitation, snow days, altitude, and soil properties were integrated, and the optimal feature combination and random forest model were used for modeling and prediction. After 40 rounds of 5-fold cross validation evaluation, the model achieved an accuracy of 0.936 and an F1 value of 0.936, demonstrating good generalization performance. On this basis, a permafrost distribution dataset covering the Eurasian continent was constructed, providing spatial prediction results for five time periods of 2000, 2005, 2010, 2015, and 2020 with a spatial resolution of 1 km. The permafrost distribution map generated by the dataset has good spatial continuity and can accurately reflect the permafrost distribution pattern in high latitude and high altitude areas. This data can provide basic support for permafrost change analysis, carbon release risk assessment, regional climate response simulation, and ecological environment monitoring. This dataset contains five predictions of permafrost distribution in the Eurasian continent, covering the years 2000, 2005, 2010, 2015, and 2020. The spatial resolution is 1 km and the EPSG: 4326 geographic coordinate system is used. Each period of data is a GeoTIFF raster file, and the raster values are described as follows: 1. Permafrost soil; 0: Non permafrost or invalid areas. The naming convention for each data file is unified as Permafrost_ distribution_YYYY.tif. Among them, YYYY represents the specific year, such as Permafrostdistribution_2000.tif. The data covers the Eurasian continent, with a latitude and longitude range of -25 ° E to 180 ° E and 25 ° N to 82 ° N. The data size is controlled within a publicly shareable range and is compressed and stored in int8 format for easy download and quick processing by users. The data can be loaded and used on platforms such as QGIS, ArcGIS, Python, etc., and supports joint analysis with other grid factors.