I asked this question on GIS StackExchange and got no result, so I'll try here.
I've computed the JM separation values for my training classes for Sentinel-2 image classification. I understand that JM separation values range between 0-2. Most of my values are above 1.9, but some are down as far as 1.4.
I've been unable to find any resources which would tell me what a "good" number is. I've checked the references in the answer on this post, and a few others besides, but I can't seem to get a simple answer. I assume that a good/acceptable number is likely to depend on a lot of things, but are there any general guidelines for satellite remote sensing? Or guidelines generally?
