The first file is a csv containing the daily SWE indicator estimates for several Alpine basins resulting from a targeted machine learning model developed for the Snowpower solution (and described here). The model was trained on fine-scale SWE data that were previously averaged over each watershed, standardized, and finally shifted in order to avoid negative values. For this reason we refer to such training data, and consequently to our results published in this Dataset, as SWE indicator, as they maintain the seasonality and spatial patterns that are typical of SWE, albeit without dimensional units. Our SWE indicator data can thus be used as input for machine learning and deep learning models.

The second file is a PNG image showing the Alpine watershed sover which our SWE indicator has been estimated. Each watershed is identified by a code (ID). Basins with multiple IDs include smaller basins that were accounted for in the SnowPower solution: intersections between basins are shown on the map with a brighter color.