Jeroen Dries

It looks like we can create a valid process graph from multiple datacubes, as long as we use the same flattener. ``` week = s2cube.aggregate_temporal_period(period="week",reducer="median") month = s2cube.aggregate_temporal_period(period="month",reducer="median") cube1=week.save_result("netCDF") cube2...

so way forward is either updating create_job or a variant of that method that accepts multiple datacubes? or `cube.execute_batch(args..., extra_cubes=[extra_cube1])` or `connection.execute_batch([cube1,cube2]), other args...)`

@ValentinaHutter don't you support signed url's for job results? Afaik, that is the approach the openEO standard recommends to avoid exactly this problem.

my bad, commits got lost, I now fixed it without requiring something in the client But anyway: for tests but also for user logs, it would be convenient that we...

Good point, we probably need to have them in the metadata. However, we were just discussing this internally, and basically we're not sure if there's a good place to do...

yes, multiple properties would imply an AND condition in my interpretation cloudcover is indeed a special case: most search catalogs somehow don't seem to have a problem with specifying this...

Additional use case: selecting input bbox, like what's now done in this eo_utils helper script.

Nice overview! Too bad the newer implementation does not run any faster, it's certainly not the intention to require GPU. Did you compare using the intel-tensorflow, or standard one? Avoiding...

@kvantricht from an openEO perspective this is doable, but should cropsar team perhaps investigate this particular case of (failing) cloud masking? @GriffinBabe did you look at CLP and CLD layers...

Yes, those bands can be found in SENTINEL2_L2A_SENTINELHUB: