Tropical forests provide habitat for most of the world’s known terrestrial plant and animal species. These ecosystems are under increasing threat worldwide. During the last few decades, several million hectares of humid tropical forest were lost each year. Despite the proliferation of new remote sensing technologies, information about the status of world’s forest is limited and unevenly distributed.
The immense task of protecting for future generations an adequate share of world’s remaining forest is outside the reach of traditional conservation strategies alone. It calls for collective action to complement existing initiatives.
ForestWatchers proposes a new paradigm in conservationism, based on the convergence of volunteer computing/thinking with free (or donated) catalogs of high-resolution Earth imagery.
This citizen science project aims at making 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 is an international partnership between the Brazil’s National Institute for Space Research (INPE), the Federal University of Sao Paulo, the Citizen Cyberscience Centre (CCC) and the Open Society Foundations.
Based on the collaboration with INPE (leaders in deforestation monitoring and responsible for the DETER program in the Amazon basin — Real Time Deforestation Detection System), ForestWatchers.net has recently released a first application, an alpha version, where everyone is invited to collaborate with us.
The application tries to reflect one of the first steps carried out by the experts at INPE when they assess deforestation for a given area of the forest.
In this first step, the experts compare several satellite images from the same area using pictures from different days. Why? Because some days some parts of the selected area will be fully or partially covered by clouds making impossible to analyze the deforestation. For this reason, the experts “cut & copy” the good areas creating a “collage”, or composite image, that will be almost “cloud-free”. This final image will be used in the next steps to study and analyze the deforestation of the area.
The ForestWatchers application gives you the option to participate and become one of these experts as you will be able to choose from different days which are the best parts of the image for creating the final one. With the collaboration of many volunteers this step could be done much faster and probably better.
The application has been built using the open source crowd-sourcing framework PyBossa (developed by the Citizen Cyberscience Centre and the Open Knowledge Foundation).
PyBossa is a free, open-source, platform for creating and running crowd-sourcing applications that utilize online assistance in performing tasks that require human cognition, knowledge or intelligence such as image classification, transcription, geocoding and more!
In this specific case, the first application is using PyBossa to run image classification or pattern recognition, while the next applications will involve geocoding tasks where the users will actually report where are deforested areas using the images that the volunteers have previously classified.