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

Models to predict residuals #314

Closed krsnapaudel closed 2 months ago

krsnapaudel commented 3 months ago

Results from the tests in test_sklearn_res_model.

wheat, NL
SklearnRidge {'normalized_rmse': 46.580503359405306, 'mape': 0.4609527947990617}
RidgeRes {'normalized_rmse': 8.889014393017845, 'mape': 0.07504003260704183}
maize, NL
SklearnRidge {'normalized_rmse': 26.811863051267885, 'mape': 0.2509442813866165}
RidgeRes {'normalized_rmse': 15.15826412121472, 'mape': 0.13247367245168623}

Benchmark results:

wheat, NL
                   normalized_rmse      mape
model
AverageYieldModel         7.505560    0.066450
LinearTrend               7.681298    0.068056
RidgeRes                  9.306816    0.083924
SklearnRidge             99.518835    0.994273

maize, NL
                   normalized_rmse      mape
model
AverageYieldModel        15.315272    0.138884
LinearTrend              15.510216    0.140453
RidgeRes                 25.740722    0.238284
SklearnRidge             17.551521    0.160509