I agree, nevertheless it's exciting to see some progress being made (see the heart flow and iSchemaView companies cited below). Incidentally, there is a new angle to the radiologists push back - interventional radiologist are generally quite in favor of automating reads. This year IR is its own specialty, but coupled to three years of DR training. This is the speciality that I'm entering. I want to be an interventionalist while advocating for the adoption of machine learning systems on the diagnostic side.

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.

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.

I'm not sure if there was more to your story that you missed. Was your software successful? Is it in use today? Is automation widespread in the study of Amazonian deforestation?

Software not being used all over the place does not mean the software is bad, generally.

No. No. No. :-)

The new means of production has now been realized and the need to replace capitalism is now at hand. Hackers of the World Unite!

How did your software work, what techniques was it using, and what was the surrounding context relating to the data that was fed in and the output the model gave?

There might be some interesting things that can be learned from this kind of info and applied to the current status quo (I'm definitely not arguing that there is a sociopolitical element).

There were a bunch of papers: http://www.sciencedirect.com/science/article/pii/0888613X949...