ForestWatchers Lets Anyone Monitor A Patch of Forest

teleyinex writes "ForestWatchers.net is a citizen project with the goal of making it possible for anyone (locals, volunteers, NGOs, governments, etc), anywhere in the world, to monitor selected patches of forest across the globe, almost in real-time, using a computer connected to the Internet. The project has recently released a first alpha web application (built using the open source crowdsourcing PyBossa framework) where volunteers can participate by classifying satellite images of one area of the Amazon basin."

Re:Automated

[TapeCutter]

After clicking a few images, I thought the same thing myself. From the half dozen image sets I clicked on it would probably be better to find the one with the least white/gray shades. In other projects like this I have seen (eg: GalaxyZoo), you are asked to do a job that humans really can do better and faster than computers, but "the most green" should be fairly trivial, the only real issue would be the the size of the image archive but they must be managing that already to be able to put this up.

Not trying to troll here, the AC has a good question and I'm genuinely curious as to why they feel automation isn't an option for this task?

Re:Automated

[fuzzyfuzzyfungus]

I'm inclined to wonder if, perhaps, they feel that there is some PR/exposure value to having humans, ideally a fairly large number of vaguely-environmentally-interested-but-not-overly-clueful ones, exposed to the images.

Based on a quick look at the journals, researchers are already using satellite data to study the area(where possible, apparently wholesale slash-and-burn is easy to see, targeted logging of high-value trees rather trickier); but that sort of research has pretty limited circulation. If you already have a serious interest in how screwed the Amazon is, there are people you can ask; but the profile of the issue isn't that high.

Assuming that an algorithm for efficiently crunching and classifying satellite data for forest health purposes were available, that'd definitely be a worthy addition to the literature; but it would also have a very good chance of dying without a ripple among everyone outside the field. Big, machine classified, datasets are a valuable tool for understanding the world; but they just don't have the affective punch of seeing it.