search

BigDataWUR / AgML-CY-Bench

CY-Bench (Crop Yield Benchmark) is a comprehensive dataset and benchmark to forecast crop yields at subnational level. CY-Bench standardizes selection, processing and spatio-temporal harmonization of public subnational yield statistics with relevant predictors. Contributors include agronomers, climate scientists and machine learning researchers.
https://cybench.agml.org/
Other
18 stars 8 forks source link

#316, #336, #268 crop season refactor, time series interpolation and aggregation #337

Closed krsnapaudel closed 2 months ago

krsnapaudel commented 2 months ago

I tried to rewrite parts of alignment and dataset.

Removing the alignment of eos_date to end of year makes the code clean. Now we have to make sure everything works.

krsnapaudel commented 2 months ago

With the latest update, validation of AgML workshop results works.

krsnapaudel commented 2 months ago

Some notes:

  1. Interpolation fills in NAs from the first observation onwards. Currently using "linear" interpolation.
  2. Aggregation is possible to "week" or "dekad".
  3. We need to ensure same number of time steps even after interpolation and aggregation. This is implemented in __getitem__() of TorchDataset.