This data is based on actual measured sample data of underground ice reserves obtained through mechanical/manual drilling and exploration pits. A random forest regression model is used to conduct spatial prediction modeling with measured volumetric water content (VWC) as the dependent variable and multiple environmental factors as independent variables. The model prediction results are output as grid data for different depth layers (2m above, 2-5m, 5m below), and finally synthesized and produced a map of permafrost underground ice storage at the research area scale. The data format is GeoTIFF, with a spatial resolution of approximately 30m and a projection of WGS1984_ Albers.
Field sampling data: based on underground ice content measurement data obtained from on-site mechanical/manual drilling and exploration pits in the Genhe River Basin on the western slope of the Greater Khingan Range; The environmental factor data comes from spatial datasets such as climate, soil, terrain, vegetation types, etc.
Environmental data: sourced from multi-source spatial datasets such as climate, soil, and terrain downloaded from the Google Earth Engine (GEE) platform and authoritative websites, used as model predictive variables.
Using Python and ArcGIS tools to process environmental factor data, a random forest regression model was used to predict the spatial ice content of 3-layer underground ice volume, and statistical analysis was conducted in conjunction with permafrost thickness data.
Model validation: The five fold cross validation method is used to evaluate the prediction accuracy of the random forest model and ensure its reliability.
Spatial consistency check: Use ArcGIS to visually check and logically analyze the generated raster data, ensuring that the spatial distribution of permafrost underground ice storage conforms to regional distribution patterns and has no significant outliers.
| # | number | name | type |
| 1 | 2022FY100700 | Survey of Permafrost Conditions and Freeze-Thaw Damage in the High-Latitude Regions of Northeast China | Basic Resource Survey Project |
This work is licensed under
CC BY 4.0 (Creative Commons Attribution 4.0 International License).
CSTR:11738.11.NCDC.NIEER.DB7250.2026
10.12072/ncdc.nieer.db7250.2026
