Stephan Rasp

Keep xarray attributes and dtype after regridding

3

Currently, the regridding seems to delete the attributes of the original dataset. I assume the happens during `xr.apply_ufunc`. Is there any reason not use `keep_attrs=True`? Similarly, all data is converted...

Next steps: 1. Find out exactly which models are cumulative and when 2. Build download pipeline for non-cumulative models (output format 6h accumulations cumulative like HRRR) 3. Build detect function...

Train a categorical model

5

It might make sense to also look into a Metnet-style categorical model. I am pretty sure that this would work. It would be a) a good baseline and b) a...

Improve GAN

9

Here is a new thread for discussing how to proceed with the GAN experiments. For the first results see #29 Current status: - Working on precip-to-precip TIGGE to MRMS -...

Data download pipeline

19

After switch to Azure - [x] Download TIGGE control and ensemble data - [x] Download MRMS data - [ ] Download HRRR/HREF data Data period is controlled by available MRMS...

Define evaluation metrics and compute baseline scores

9

Steps: - [x] Interpolation baseline - [x] RMSE score - [x] FSS - [x] Compute further deterministic scores ( F1) - [x] Think about the design of how to call...

Improve upscaling CNN

1

Following on from #12 we can now try to improve the upscaling CNN (i.e. with MSE instead of GAN loss). Here are a few ideas: - [ ] Include more...

See title.

As the title says.