Finished! Looks like this project is out of data at the moment!
We're happy to announce that our preprint is out, describing our tree mapping research and the (now public) dataset that this project uses! You can find it on arXiv here and check out the models for yourself here. Thanks again for volunteering, your efforts are helping us improve our labels and ultimately improve the state of tree and restoration monitoring.
We've completed the classification stage for this project! To browse other active projects that still need your classifications, check out zooniverse.org/projects.
Label trees to enable and accelerate nature restoration. Contribute to scaling up the protection and restoration of forests around the world.
Learn moreIn this project, we would like you to annotate trees in aerial images, captured by drones. You will be shown an image from our dataset, and you should try to identify every individual tree that you can spot. You don’t have to worry about marking every tree. We will use your labels to help improve and validate our tree detection model. During our beta period, we are trialing two workflows which are very similar, but have different approaches to marking groups of trees.
Zooniverse Talk
Chat with the research team and other volunteers!
Tag trees Statistics
View more statsKeep track of the progress you and your fellow volunteers have made on this project.
Every click counts! Join Tag trees's community to complete this project and help researchers produce important results. Click "View more stats" to see even more stats.
By the numbers
Message from the researcher
Our ability to use machine learning to map global forests is limited by the training data we have. I hope Restor's truly global dataset of tree and canopy maps will bring a positive impact to the community and the world.
Tag treesAbout Tag trees
Scientists at Restor are using Artificial Intelligence (AI) to find trees and track the progress of forest restoration efforts worldwide. We need your help to train and improve our models!
Repairing and restoring nature is vital for halting biodiversity loss and tackling climate change. But a lack of transparency around reforestation projects is eroding the trust needed to increase funding and accelerate & scale projects.
To increase transparency and reduce the time and costs associated with project monitoring, Restor has developed an AI model that identifies trees in photos taken by drones. The model is trained by feeding it thousands of images with pre-labeled trees — and we are looking for volunteers to improve and validate our training data by tagging trees in images.
Although our model already works quite well, we need to be able to demonstrate that it is really detecting trees, and not making confident (and wrong!) predictions. By asking multiple people to tag the trees in our images, we can more confidently measure how accurate our model is across different natural environments.
This is a truly collaborative endeavor, made possible through partnership with restoration and regreening initiatives around the globe and the generous support of Google.org.
Tree vector credit: Designed by brgfx / Freepik