Beschreibung: In Irrgang et al. (2020), we have trained a convolutional neural network to perform a so-called downscaling task. This downscaling aims to recover the fine-structure continental water storage distribution on the South American continent from coarse-resolution space-borne gravimetry observations. Here, we share data sets that were used for training the neural network, namely (1) monthly pairs of gridded terrestrial water storage anomalies (TWSA) of the South American continent and (2) surface water storage anomalies (SWSA) in the Amazonas region for the time period 2003-2019. TWSAs were used as target (output) values of the neural network and were derived from the Land Surface Discharge Model (LSDM, Dill, 2008). The corresponding input values were calculated by spatially smoothing the TWSA fields with a 600 km Gaussian filter. After training the neural network over the time period of 2003 to 2018, its performance was tested and compared to LSDM for the subsequent year 2019.

Beschreibung: This dataset contains predictions of Earth orientation parameters (EOP) submitted during the Second Earth Orientation Parameters Prediction Comparison Campaign (2nd EOP PCC). The 2nd EOP PCC has been carried out by Centrum Badań Kosmicznych Polskiej Akademii Nauk CBK PAN in Warsaw in cooperation with the GFZ German Research Centre for Geosciences in Potsdam (Germany) and under the auspices of the International Earth Rotation and Reference Systems Service (IERS) within the IERS Working Group on the 2nd EOP PCC. The purpose of the campaign was to re-assess the current capabilities of EOP forecasting and to find most reliable prediction approaches. The operational part of the campaign lasted between September 1, 2021 and December 28, 2022. Throughout the duration of the 2nd EOP PCC, registered campaign participants submitted forecasts for all EOP parameters, including dX, dY, dPsi, dEps (components of celestial pole offsets), polar motion, differences between universal time and coordinated universal time, and its time-derivative length-of-day change. These submissions were made to the EOP PCC Office every Wednesday before the 20:00 UTC deadline. The predictions were then evaluated once the geodetic final EOP observations from the forecasted period became available. Each participant could register more than one method, and each registered method was assigned an individual ID, which was used, e.g., for file naming. The dataset contains text files with predicted parameters as submitted by campaign participants and MATLAB file which is a database with all correct predictions from each participant loaded into a structure.