[seanlinmt]

You are right that work in these areas tend not to be hampered by technology. It sometimes may even be hazardous to ones health considering the value of timber. 20 years ago is a long time ago, GIS must be still at its infancy then. These days one could pull free satellite images from NASA and probably could just diff images if not for those pesky clouds. Oh wait actually I think NASA does do earth imagery at various spectral ranges, https://www.odysseyofthemind.com/aster.htm.

Curious to know what sort of methods you used then if you don't mind sharing.

[neves]

Excuse me for the delay to answer.

The best results were with backpropagation neural networks: http://www.sciencedirect.com/science/article/pii/0888613X949...

But we also used fuzzy logic neural networks with genetic algorithms: http://ieeexplore.ieee.org/document/712156/?reload=true

It were 24 years ago.