nowcasting_dataset icon indicating copy to clipboard operation
nowcasting_dataset copied to clipboard

Prepare batches of data for training machine learning solar electricity nowcasting data

Results 101 nowcasting_dataset issues
Sort by recently updated
recently updated
newest added

I have a feeling that NWP puts the dims in this order: y, x. Whilst satellite puts the dims in order x, y. Even if the dims are in different...

enhancement

## Detailed Description Maybe we should _always_ validated the on-disk batches? (Let's wait for PR #300 to be merged before working on this)

enhancement

Not super-urgent. For now we can just use the same variable names we've used in the past.

enhancement

## Detailed Description Include the forecast horizon of each NWP timestep in the output batches. ## Context As a general rule, NWPs get less skillful the longer the forecast horizon....

enhancement
data

## Detailed Description At the moment, we use NWPs with an init time at or just before the start datetime of the historical data for each example. Instead, we should...

enhancement

## Detailed Description Would be useful to have a method to drop 'padded' pv systems. These are padding out zero so that the dataset can be save in an efficient...

enhancement

Related issues: - #138 - #86

refactoring

Our code for downloading and converting satellite data lives in the Satip repo. Our code for downloading and converting other data sources (NWP, GSP PV, etc.) lives in this repo....

discussion
data

int16 for both NWP & satellite? Maybe even uint8 (and use 0 for NaN???)