NaN values in my classification

[ABraun]

this can have several reasons:

• pixels are classified as NaN because their confidence is too low
• pixels are classified as NaN because one of the input bands is NaN at this location
• the training areas for this class are not large enough (or contain too inhomogenous signatures

Have you seen these discussions?

• Not classified pixel
• Random forest classification problem with mixing classes
• Polarimetric Classification NaN problem
• Random Forest NAN at Confidence values below 0.5
• Multi-temporal Random Forest - NaN pixels