61–70 of 128 posts
I love these guys! I helped advise them on their crowdfunding campaign a few years ago. One of my favorite projects. Hey Topher! Are you guys cross checking this with daily satellite imagery? I met with a guy who's company gets a full HD shot of the earth every 24 hours and they'd be happy to give you guys access to the visual data (they also train algorithms on it to detect all sorts of activity). Anyhow, I'll shoot…
What company is this if you dont mind saying?
Someone more familiar with satellites can correct me, but from my understanding you should be able to detect deforestation from real-time satellite data. You alert on changes in the level of greenery in the images. The indicator might trail behind detecting chainsaw noises, but it wouldn't require the mass distribution of detector devices.
Our system is as real-time as it gets. In fact you can download our app right now and listen live to the sounds of the forests:
iOS App http://bit.ly/RFCx-iOS
Android App http://bit.ly/RFCx-Android
Thanks for checking out Rainforest Connection! Seems that there are lots of [appropriate] questions about how well this works in the forest, and how our partners on the ground follow up on alerts. Here’s a recent intervention in Peru that sums up the process: https://twitter.com/lilitjejauregui/status/97585519352188518...
Also, I recall hearing about how some people or villages opt in to deforestation because they are offered a significant amount of money which can be used to feed their kids and provide an education which may help their communities eventually escape the poverty trap. Do you know anything about this, and if true, do you know of any groups trying to help?
Are there methods to change the noise of a chainsaw, as there's money to be made in illegal logging - they'll have the incentive if they're organized, so it would be quiet enough or different enough to potentially sound like it's "outside" of a protected area or not a chainsaw at all?
In fact, the forest is a very loud place and yet we are still able to detect the sound signature of a chainsaw.
You can hear it for yourself here:
iOS App http://bit.ly/RFCx-iOS
Android App http://bit.ly/RFCx-Android
Earlier quoted context omitted.
That's a great question. Actually, one of the sounds that are pretty close to a chainsaw are mosquitos that are circling around our microphones due to the Doppler effect. We found ways of dealing with signals that are close to chainsaws by aggregating multiple models and also a time-based analysis. The system can draw causal/correlative conclusions such as a vehicle is usually present before a chainsaw. If there's no…
How do you quantify the confidence of your model? Do you use a Bayesian model or just the log-likelihood? Because the latter can act strangely in some cases.
Are there methods to change the noise of a chainsaw, as there's money to be made in illegal logging - they'll have the incentive if they're organized, so it would be quiet enough or different enough to potentially sound like it's "outside" of a protected area or not a chainsaw at all?
If and when they do that we will find a way to adapt and detect. The beauty of a real-time system is that you can make changes/improvements remotely without having to go out in the forest again and swap devices out. In fact, the forest is a very loud place and yet we are still able to detect the sound signature of a chainsaw. You can hear it for yourself here: iOS App http://bit.ly/RFCx-iOS Android App http://bit.ly/…
I was thinking and wondering how reasonable as a "next step" in protecting forests to potentially require GPS tracking on all or certain types of chainsaws - it feels like an absurd thought on its own, though it potentially helps solve the problem.
This could then extend tracking to imagery via satellite - via geographic and density changes being detected, knowing where the GPS-tracked and legal work was being done, being able to then eliminate those areas from as high of scrutiny. Perhaps the GPS tracking is then not necessary if you can accurately compare before/after imagery, though could be a useful tool anyway for management to know how efficiently equipment is being used, if it's at where it should be and such.
This reminded me of a story my father once told me. I assume he heard it because his father was part of the Ministry of Forest in Canada a long time ago: I believe it was during a world war (not sure which one) when I could imagine lumber would have been in constant demand. There was a bit of a trick and literal loop-hole that truckers would use. Before being discovered there apparently was a long route where truckers would go through without actually dropping off their lumber - after having gone to the weigh-in point to get paid. They'd continue to drive through the back to return another day with the same load to get paid again; a long drive apparently but still was a money maker..
Earlier quoted context omitted.
How do you quantify the confidence of your model? Do you use a Bayesian model or just the log-likelihood? Because the latter can act strangely in some cases.
I know this is a digression from the current discussion on how well the devices work, but as a stats student who just learned about estimating using log-likelihoods, could you give some more info on how that is inferior to the Bayesian model (since I've heard the exact opposite is true)?
Logging Man, I must have computers on the brain. This isn't about noisy server logs at all.