Could you explain the structure of these files?
That would be really nice?
The datafiles are all netCDF v4 files, the handy thing about that is that they contain lots of metadata explaining what's going on. I find the hdf5 tools h5ls and h5dump are the most useful to understand what's going on, but there are a lot of netCDF specific tools out there. To understand more about the data files, a good place to start is either downloading one, or have a look at NASA's MERRA2 docs, or have a go with the examples notebooks.
Awesome thanks mate, I am interested in building my own ML models with this data with my GenericML framework, its an abstraction of the ML.NET framework Microsoft uses for many of their internal ML services. Just wondering if you be interested in colaboration with me? I think there are loads of applications for this tech.