AI could optimize hydroelectric dams in the Amazon

Artificial intelligence (AI) isn’t just transforming the world — it’s helping protect and preserve the future of the Amazon River.

Rapid hydropower expansion has radically altered the Amazon River. When the natural flow of a river is altered, there are often serious, cascading changes. Now, AI and other computer science tools can help reduce these adverse and devastating effects on the environment, according to new research published in Science.

FIU researcher Elizabeth Anderson was a part of a collaborative team of scientists from across the United States, Europe and South America who examined how cutting-edge technology can inform more sustainable and strategic planning. Their goal was to inform planning for hydropower dams across the Amazon Basin — a timely issue, seeing as there are currently more than 350 proposed hydroelectric dams in the Amazon basin.

“The Amazon is the world’s largest and most biodiverse river system, home to more freshwater fish species than any other place on Earth. At the same time, an estimated 47 million people live in the Amazon Basin, and their lives are intertwined with rivers in so many ways—socially, economically, and culturally," said Anderson, an FIU associate professor of Earth and Environment and researcher in the Institute of Environment.

AI and other technology illustrated and examined tradeoffs between energy generation from proposed hydropower dams and critically important ecosystem services supplied by rivers throughout the Amazon Basin. The team focused on several criteria for the optimization of proposed hydroelectric dams in the Amazon Basin, including river flow and connectivity, sediment transport, fish diversity, greenhouse gas emissions and energy production — and also outline key strategies for reducing environmental damage from future dam construction.

“It is really a pleasure and uniquely rewarding that we are using computer science and AI to address this sustainability challenge,” said Carla Gomes, a computer scientist and director of Cornell University’s Institute for Computational Sustainability. “AI is being used by Wall Street, by social media, for all kinds of purposes – why not use AI to tackle serious problems like sustainability?”

Gomes, Anderson and the researchers emphasize that international cooperation is key to successful, sustainable hydropower planning. After all, what might seem like a good solution for one country might actually be harmful when considering the overall impact to the entire Amazon basin.

The paper, which drew on Anderson’s extensive work on Amazon rivers, was led by Gomes and Cornell biologist Alexander Flecker. FIU helped play a role in developing the initial ideas for the project on a field visit to the Amazon in 2015, and hosted one of the project workshops in Miami in 2018.

The research is the result of a collaboration between more than 25 academic and non-academic institutions from the U.S., Brazil, Colombia, Ecuador, France and Peru, well as conservation organizations including The Nature Conservancy and the Wildlife Conservation Society. It was supported by grants from the National Science Foundation, the Cornell Atkinson Center for Sustainability’s Academic Venture Fund and the Army Research Office’s Defense University Research Instrumentation Program. Anderson’s participation was also supported by The MacArthur Foundation.