摘要：Gap filling is required for temporally and spatially consistent records of land surface temperature from satellite data due to clouds or snow cover. Land surface state, frozen versus unfrozen conditions, can be, however, captured globally with satellite data obtained by microwave sensors. The number of frozen days per year has been previously proposed to be used for permafrost extent determination. This suggests an underlying relationship between number of frozen days and mean annual ground temperature (MAGT). We tested this hypothesis for the Northern Hemisphere north of 50∘ N using coarse-spatial-resolution microwave satellite data (Metop Advanced SCATterometer – ASCAT – and Special Sensor Microwave Imager – SSM/I; 12.5 and 25 km nominal resolution; 2007–2012), which provide the necessary temporal sampling. The MAGT from GTN-P (Global Terrestrial Network for Permafrost) borehole records at the coldest sensor depth was tested for validity in order to build a comprehensive in situ data set for calibration and validation and was eventually applied. Results are discussed with respect to snow water equivalent, soil properties, land cover and permafrost type. The obtained temperature maps were classified for permafrost extent and compared to alternative approaches. An R2 of 0.99 was found for correlation between and MAGT at zero annual amplitude provided in GTN-P metadata and MAGT at the coldest sensor depth. The latter could be obtained with an RMSE of 2.2 ∘C from ASCAT and 2.5 ∘C from SSM/I surface state records using a linear model. The average deviation within the validation period is less than 1 ∘C at locations without glaciers and coastlines within the resolution cell in the case of ASCAT. The exclusion of snow melt days (available for ASCAT) led to better results. This suggests that soil warming under wet snow cover needs to be accounted for in this context. Specifically Scandinavia and western Russia are affected. In addition, MAGT at the coldest sensor depth was overestimated in areas with a certain amount of organic material and in areas of cold permafrost. The derived permafrost extent differed between the used data sets and methods. Deviations are high in central Siberia, for example. We show that microwave-satellite-derived surface state records can provide an estimation of not only permafrost extent but also MAGT without the need for gap filling. This applies specifically to ASCAT. The deviations among the tested data sets, their spatial patterns as well as in relation to environmental conditions, revealed areas which need special attention for modelling of MAGT.
