SAS and IIASA Create Crowd-Driven AI App to Track Deforestation
Forest losses have again captured the public eye over the last year through a series of horrific fires in the Amazon, Australia and the West Coast of the United States. Globally, many losses – including the fires in the Amazon – are attributable to deforestation, particularly illegal deforestation. Now, SAS has teamed up with the International Institute for Applied Systems Analysis (IIASA) to combat the scourge of deforestation using crowd-driven AI.
SAS and IIASA are launching an online app powered by crowdsourced observations. When users launch the app (accessible at http://sas.com/rainforest), they’ll be presented with an aerial image of a section of a rainforest segmented into nine squares. Then, they’ll be asked to select which of those squares, if any, show signs of human development – for instance, roads, which are often created by illegal logging operations to transport machinery in and trees out. Once an image is classified, the user can then continue on, classifying as many as they like.
The project launched with more than 44,000 satellite images, over 38,000 of which have now been classified by volunteer users from 80 countries around the world. The resulting data – covering more than 135,000 square miles of rainforest so far – is being used to train AI algorithms, helping them better understand how to identify those features in satellite imagery and differentiate them from similar features (e.g. roads versus rivers).
“Since image analysis is an important first step for the accurate assessment and projection of deforestation, we are asking people to see what technology can’t see, by examining and reporting on images of smaller incremental forestry incursions worldwide,” said Albert van Jaarsveld, CEO of IIASA. “Crowdsourcing helps improve the AI algorithms, expediting what used to take years to analyze, thus helping to drive vital policy responses to protect our forests more quickly.”
SAS and IIASA are targeting the app at a wide range of casual and professional users ranging from students and classrooms to engineers. For IIASA, the exercise is a proof of concept for broader applications of AI in ecological concerns around the world.
“The urgency required to address these transformations requires the application of best of breed technology solutions. That’s why we turned to SAS,” said Albert van Jaarsveld, CEO at IIASA. “By combining the power of our environmental science research platforms, SAS’ AI and computer vision technologies, and the sheer intellectual power of concerned citizens, we will develop AI models that will exponentially increase the value of human insights and strive to deliver near real-time assessment of global environmental change.”