Spotted at Hackaday is a story on positive reinforcement to train crows to pick up litter:
A Dutch startup wants to teach the crow population to pick up cigarette butts in exchange for bird treats.
The whole Corvidae family of birds is highly intelligent so it shouldn’t be a problem training them that they will get a reward for depositing something the Hominidae family regularly throw on the street where the birds live. This idea is in turn an evolution of the open-source Crow Box.
For some, leveraging the intelligence of animals is more appealing than programming drones which could do the same thing. A vision system mixed with a drone and a manipulator could fulfull[sic] the same function but animals are self-repairing and autonomous without our code. The irony of this project is that, although it's probably fairly easy to train crows to recognize cigarette butts, the implementation hinges on having a vision system that can recognize the butts in order to properly train the crows in the first place.
(Score: 2) by TheLink on Wednesday October 11 2017, @03:59AM
There are benefits of dumping biodegradable trash on land surfaces to actually "biodegrade" compared to having it locked in an anaerobic landfill:
http://newatlas.com/orange-peel-forest-costa-rica/51012/ [newatlas.com]
https://www.princeton.edu/news/2017/08/22/orange-new-green-how-orange-peels-revived-costa-rican-forest [princeton.edu]
It stinks while rotting though so dumping orange or banana peels in your neighbor's garden without permission might not be welcome.
But if 100s of hikers a day scattered their banana peels in a forest while hiking the forest might actually benefit. More "nutritious" food waste might attract bears or other large predators so might wish to be careful about that...
Meanwhile I'm wondering how long it would take for a "significant level" of fungi and bacteria to work out better ways to crack plastic like was done for wood cellulose ages ago.