Daily Progress Report
While computer vision models can be trained to quickly identify areas of the rainforest that have been significantly damaged, signs of deforestation can be challenging for a computer to see at first. It takes human eyes to properly classify images in order to build models that can detect the subtle differences between satellite imagery. For every image that you select as an area of deforestation in our crowdsourcing project, SAS and our partners get closer to building a model that can alert governments and conservation organizations.
From Earth Day, April 22, 2020, through October, citizen scientists like yourself across 95 countries have classified over 43,000 satellite images of the Amazon rainforest. Our work is not finished. We have expanded the Amazon coverage into Peru and an area of Brazil to continue enriching the model training.
By continuing to combine SAS AI technology, your human input, and our partner’s expertise, we will build upon this knowledge to identify where changes are occurring over time. This could one day help predict where deforestation is likely to happen next.
Note: The results below are based on crowdsourced consensus, meaning multiple agreements from citizen scientists like yourself are required to be reflected as one result. The results are provided in the charts below, which are updated twice daily.
Assessments to Date
We currently have approximately 90,000 images that need to be classified through crowdsourcing. Here’s our progress so far and how much more we need to do.
This map shows several smaller segments of the Amazon rainforest we are using to build our AI model. By using image data from this ecologically diverse territory, we are giving our model a wide variety of examples so that it can one day learn to detect human impact anywhere in the Amazon. Here's our progress in classifying images.
Area Coverage to Date
Over the course of this project, we will evaluate as many as 807,000 square kilometers of the Amazon. Here's our progress to date.