Closed AlexandreRebiere closed 8 months ago
Is there any ability to combine some of these datasets? Or should each file be mapped to a single zarr store?
Actually no... each file is named for a certain reason and used at different moments in the algorithm. Each file may have to exist in its own zarr...
Closing this as wontfix due to inactivity.
Dataset Name
The SubseasonalRodeo Dataset
Dataset URL
https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/IHBANG
Description
A benchmark dataset for training and evaluating subseasonal forecasting systems—systems predicting temperature or precipitation 2-6 weeks in advance—in the western contiguous United States. This dataset gathers various datas concerning precipitation and temperature, used in the Rodeo forecasting model.
Size
The datasets consists of 160 Mb files in a total of 10 GB.
License
Unknown
Data Format
HDF
Data Format (other)
.h5
Access protocol
HTTP(S)
Source File Organization
The source files aren't quite organized in this dataset. It gathers datas of different parameters (precipitation, wind, temperature...) from different eras.
Example URLs
Authorization
No; data are fully public
Transformation / Processing
There's nothing to modify in this dataset. The forecasting model is able to work with this dataset. No more analysis is needed.
Target Format
Other
Comments
they have to keep the same name and the same format (.h5)