Nowcast array maximal value

[giszters]

Dear Georgy, I've been playing recently with provided example and found out, that I always end with nwcst prediction array that has maximal value around 1.219. No matter what RY_latest maximum precipitation was provided. Is tere something that I'm missing? Some kind of 'descaling' or 'denormalization' possibly?

[hydrogo]

Dear @giszters, I suppose that you are right and it could be related to preprocessing routines that are pretty complex, i.e., scaling, taking log, etc. Good luck!

[JKupzig]

Did you find a solution, @giszters ? I'm facing the same problem.

[omyhao]

Dear Georgy, I‘m facing the same problem, this is the newest colab demo with just some data source url updated.

https://colab.research.google.com/drive/1KXrnsmAf9Za1SC0PKw6LF102p0uQ4xgU#scrollTo=PTzKBwBRPXNd

I hope to get your help or any idea with nwcst array maximal value 1.219

Sincerely

[omyhao]

maybe this is the reason why 1.219 occurs /examples/RainNet_Training.ipynb class Dataset(tf.keras.utils.Sequence): .... y = np.squeeze(data_preprocessing(np.array(self.dataset[self.keys[i+3]])[np.newaxis,:,:]))

[omyhao]

i+3 should be i+4