nowcasting_dataset
nowcasting_dataset copied to clipboard
Prepare batches of data for training machine learning solar electricity nowcasting data
## Detailed Description Add weather observation data such as temperature, wind speed & direction, rainfall, humidity, and irradiance from sources such as: - [ ] #80 - [ ] Ground-based...
I've looked into it here for SatFlow: https://github.com/openclimatefix/satflow/issues/7 it seems we can read in the Nimrod files from the Met Office using [iris](https://scitools.org.uk/iris/docs/v2.4.0/iris/iris/fileformats/nimrod.html) Its at a 1km for the UK,...
## Detailed Description Perceiver IO doesn't need all the data to be perfectly aligned. Might be best for nowcasting_dataset to _never_ resample. If the user needs resampled data then resample...
## Detailed Description Now that nowcasting dataset can handle different durations for different modalities, we could try adding electricity demand data to the inputs, and try predicting demand. (in the...
## Detailed Description Right now, we save the data and location of PV systems that we have readings from. Adding the physical locations of all PV systems, including those we...
We currently use a _lot_ of disk space for satellite images and NWPs. It's possible that we can get away with _far_ smaller file sizes without hurting forecasting performance. But...
## Detailed Description The code currently loads invidual training examples, one-at-a-time, and then joins them into a batch. But it's possible that it might be faster to execute, and the...
## Detailed Description Implement `config` fields to allows users to specify the geographic bounds of the dataset (e.g. "just produce examples over the UK.") ## Context Soon, we should have...