Spring snow depth over pan-Arctic sea ice derived from AMSR2 using machine learning methods (2013-2023)

Overview

This dataset provides daily estimates of snow depth over pan-Arctic sea ice for the spring seasons from 2013 to 2023, using Advanced Microwave Scanning Radiometer 2 (AMSR2) data. A novel machine learning based framework has been developed for AMSR2 snow depth retrieval that combines the machine learning models of K-Nearest Neighbors, Extremely Randomized Trees (Extra Trees), and TabNet using a newly defined data fusion method.

Filename: YYYY-MM-dd [Year-Month-Day]

Parameter(s):  Snow detph (cm) /  Snow detph uncertainty (cm)

AMSR2_Merged: Merged snow depth estimation for KNN, Extra Trees and TabNet.

AMSR2_Merged_Uncertainty: Uncertainty in the merged snow depth estimate, calculated as the weighted standard deviation.

AMSR2_KNN: Snow depth estimation using KNN.

AMSR2_ExtraTrees: Snow depth estimation using Extra Trees.

AMSR2_TabNet: Snow depth estimation using TabNet.

Platform(s):  GCOM-W satellite

Sensor(s): Advanced Microwave Scanning Radiometer 2 (AMSR2)

Data Format(s): NetCDF

Temporal Coverage: 1 March 2013 to 30 April 2023 (March and April only)

Temporal Resolution: 1 day

Spatial Resolution: 25 km × 25 km

Spatial Reference System(s): NSIDC Sea Ice Polar Stereographic North (EPSG:3411)

Spatial Coverage:  N:90 S:0 E:180 W:-180