3.1.1. NMA Dataset

The meteorological radar at NMA collects data at every 6 min (240 acquisitions per day) at nine elevation angles. Every collection at every elevation is a matrix of floating point numbers and contains 460 × 460 = 211,600 data points, ranging from 0 to 70. A custom cleaning process was applied to the raw radar from NMA and the cleaned data were used in the experiments. The data were stored in .NetCDF (network common data form) files [42] and each collection (for each elevation and each radar product) was stored in a separate file (460 × 460 × 240 × 9 = 457,056,000 data points for a single product for an entire day).

Figure 4 summarizes the reflectivity radar product for all elevation levels and all acquisitions during one full day and highlights the area that is covered by the radar, both in terms of raw data and geographical location (projected onto the map).

**Figure 4.** A visualization of the data points that are missing for all acquisitions at all elevation levels during an entire day in the NMA dataset for the reflectivity product. On the left, there is a visualization of the data matrix, in which each red pixel indicates that the value is present all day for all elevations. On the right, there is a visualization of the missing data projected onto the map, in which the red color indicates that the values are missing all day for all acquisitions at all elevation levels.

The histogram in Figure 5 reveals the imbalance between the larger values and smaller values and also highlights the fact that during the cleaning process, the data points were grouped into categories ([0–5), [5–10), [10–15)...). There were significantly fewer high values (> 50 usually indicated severe meteorological phenomena) than small values (the x axis used a logarithmic scale) and this imbalance in the data made the prediction problem more difficult.

**Figure 5.** A histogram of the non-missing values in the NMA dataset for the entire region for a whole day, including all acquisitions at all elevations. A logarithmic scale was used on the OY axis.
