I keep getting this error when I'm using the 'Predict to raster' Prediction Type in the Forest-based Classification and Regression tool:
'Problem extracting values from a.img using origin location [x,y]'
The given origin location is not on a NoData area, it's value is: Stretch.Pixel Value 0.016262
Is the issue that it's in the ERDAS Imagine format? Should I make it a GRID or .tif? Every raster is defined in the same GCS and the same PCS. Additionally, the data frame is in the same GCS & PCS.
The Forest-based Classification and Regression tool works fine in the 'Train only' Prediction Type mode.
Any help is greatly appreciated.