itb-nz logo
Story image

Human judges vital in crowdsourced campaign to track deforestation

22 Apr 2020

Earth Day celebrates its 50th anniversary today – and to celebrate, two technology companies are banding together to create algorithms that help people better understand the planet.

The International Institute for Applied Systems Analysis (IIASA) and analytics firm SAS are creating artificial intelligence (AI) based algorithms with the help of crowdsourcing.

The two companies believe it’s best to start with human intelligence, which is why they are launching an online app that asks people – citizen scientists, artists, engineers, or professional data scientists, and anyone who’s game enough – to take part in the crowdsourced project.  

Volunteers must review and judge images of untouched rainforests, and rainforests that may be affected by human development.

When the volunteers identify regions that have been affected by human development, they can help to make the AI algorithms learn and to become smarter.

IIASA and SAS explain that it is easy for a person to tell a river from a road, but an AI model will not know the difference until it is trained from human knowledge.

Results also ensure that the crowdsourcing app focuses the attention of human judges where their expertise is most needed. 

The organisations say that the model will allow for increased efficiency of a volunteer human force that best makes use of their attention and insights for a broad array of projects aimed at monitoring and measuring important global change matters.

The IIASA is known for its systems analysis capabilities to help understand major challenges for humanity, and the organisation says it is placing a spotlight on the issue of deforestation. It wants to know how AI can explain how Earth’s ecosystems interconnect.

“Today, our systems are changing rapidly, approaching levels that exceed existing human experiences, scientific understanding and traditional modelling capabilities, making it increasingly difficult for humans to intervene efficiently, effectively and in a timely manner,” IIASA says in a statement.

“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,” adds IIASA CEO Albert van Jaarsveld.

The crowdsourcing partnership is fuelled by the Data for Good movement. The movement encourages the use of data meaningful ways to drive positive global change.

Head to sas.com/rainforest to categorise images that show signs of deforestation and help models learn and improve at each iteration.