Predicting Rasters and Covariates
Reference > Predicting Rasters and Covariates
These Datasheets hold the inputs to the 2-Predict stage, which applies the model trained by 1-Train Classifier to new images. A predicting Scenario is usually set up with the training Scenario as a Dependency, so it can find the trained model.
Predicting Rasters
| Field | Description |
|---|---|
| Timestep | Integer identifying the image (labelled with the Raster group name set in Terminology). Outputs are reported by this value. |
| Predicting Raster | A multi-band raster to classify. It must have the same bands, in the same order, as the training rasters. |
Covariates
| Field | Description |
|---|---|
| Covariate Raster | A single-band raster covering the predicting area. Enter the same covariates, in the same order, as in Training Rasters and Covariates. |
| Data Type | Continuous for numeric values, or Categorical for class codes. Must match the type used in training. |
The pre-processing chosen in Advanced Classifier Options (band name override, rounding, normalization and contextualization) is applied to these rasters in the same way as in training.