Data-driven Discovery of Snow Cover Parameterization

All data were derived from High Mountain Asia UCLA Daily Snow Reanalysis, Version 1, and were preprocessed for training symbolic regression models in convenience. Train and test data are range from water years of 1999-2012, and of 2013-2016. All NaN value were removed from data and shape as [Sample, feat]. The dataset contains preprocessed dimensonless features (namely *d.npy) The name and unit of each feature of 2) were listed in sequence as follows:1. Snow depth / ground roughness (=0.01m)2. 1 / snow density3. Snow water equivalent / max value of snow water equivalent4. Air temperature / 273.155. Specific humidity6. 200 / Standard deviation of sub-grid topography The name and unit of target were listed as follows:1. Snow cover fraction [%]