Prediction Models
Select the desired prediction time range, spatial division (Square - 1 degree grid, District - administrative district boundaries) and scenario.
q01 - Positive scenario, q05 - Baseline, q09 - Negative scenario.
Click on a particular district to observe additional information
-
Observed Value
-
Predicted Value q05
-
Predicted Value q01
-
Predicted Value q09
-
Observed Class
-
Predicted Class q05
-
Predicted Class q01
-
Predicted Class q09
-
Class Difference q05
-
Class Difference q01
-
Class Difference q09
-
MASE q05
-
MASE q01
-
MASE q09
-
RMSE q05
-
RMSE q01
-
RMSE q09
-
Observed Value
-
Predicted Value q05
-
Predicted Value q01
-
Predicted Value q09
-
Observed Class
-
Predicted Class q05
-
Predicted Class q01
-
Predicted Class q09
-
Class Difference q05
-
Class Difference q01
-
Class Difference q09
-
MASE q05
-
MASE q01
-
MASE q09
-
RMSE q05
-
RMSE q01
-
RMSE q09
Assessment Charts
MASE Assessment
The mean absolute scaled error (MASE) is a measure of the accuracy of forecasts. It is the mean absolute error of the forecast values, divided by the mean absolute error of the in-sample one-step naive forecast.
RMSE Assessment
Root-mean-square error (RMSE) is a frequently used measure of the differences between values (sample or population values) predicted by a model or an estimator and the values observed.
Class Difference Assessment
Class Difference shows a share of match/mismatch drought severity between predicted and observed values