Artificial intelligence enables strategic hydropower planning across Amazon basin

indigenous fishermen at a river rapids in the Amazon

Fishermen gaffing catfish at the Madeira River rapids in the state of Rondônia, Brazil. These rapids are now completely submerged, and a nearby downstream dam prevents migratory fish species from reaching Bolivia and Peru, where some of them spawn.

Adapted from a story by Tom Fleischman at Cornell University

The development of hydropower dams along the vast Amazon River Basin in South America is supporting agricultural and industrial interests and bringing infrastructure and purported prosperity to millions of people – but at what cost?

An international collaboration of scientists, including Colorado State University river ecologist N. LeRoy Poff, has spent the last several years studying the massive, ongoing expansion of hydropower across the Amazon, including how best to minimize social and environmental harms in attaining hydropower production goals. A new study published in the journal Science focuses on tradeoffs between energy generation from proposed dams and a suite of ecosystem services supplied by rivers throughout the Amazon Basin.

The work, led by Cornell University and including 40 co-authors from several institutions, employed state-of-the-art computation and artificial intelligence to illustrate the importance of strategic planning at the whole-basin scale. Rather than working on a dam-by-dam basis, whole-basin planning shows which proposed dams introduce the most socio-environmental harm relative to their energy production.

The paper, “Reducing adverse impacts of Amazon hydropower expansion,” is co-authored by Poff, University Distinguished Professor in the Department of Biology. A sought-after expert in hydroecology and environmental flow needs for rivers, Poff worked with the team to provide ecological perspective on how river flow changes from dams will affect fisheries production and floodplain health. Poff and colleagues traveled the Amazon River and participated in ongoing research on sediment movement, while also visiting large fish markets that are sustained by the river-floodplain ecosystem and the local people who depend on it.

“The paper makes the case that international cooperation is essential for reducing adverse impacts of hydropower expansion in transboundary river basins such as the Amazon ­– a key missing element of infrastructure planning globally that undercuts future environmental sustainability,” Poff said.

Two dozen partner institutions

The Cornell-led study encompassed two dozen academic institutions in the U.S., Europe and South America, along with nongovernmental organizations, including The Nature Conservancy and the Wildlife Conservation Society.

The project considered six socio-environmental criteria for optimization of the energy-environment tradeoff for the more than 350 proposed hydroelectric dams in the Amazon basin: river flow, river connectivity, sediment transport, fish diversity, greenhouse gas emissions, and energy production.

The work sought not only to minimize the total environmental impact associated with dam construction, but also to reveal lost benefits from 158 existing hydropower dams in the basin, originally placed without coordinated planning that considered their cumulative negative effects. Calculating all the potential solutions, the researchers said, yields a number that is “greater than the number of atoms in the entire universe,” according to computer scientist Carla Gomes, a co-lead of the study at Cornell.

Coordinated planning

The paper shows that the historical lack of strategic coordinated planning has resulted in forgone environmental benefits, and it lays out four key strategies for reducing environmental damage from future dam construction. The first, and perhaps most basic, is that multi-objective optimization provides an effective “first filter” to identify the many dam sites that would yield disproportionately negative results.

The second key idea complements the first: Simultaneous consideration of multiple criteria is essential for identifying the least detrimental projects with respect to ecosystem services – the benefits that healthy rivers provide, such as fisheries, biodiversity, floodplain agriculture and undisrupted navigation routes.

Third, basin-wide analysis is essential for minimizing forgone ecosystem service benefits. Planning at smaller scales can yield misleading outcomes, missing some of the damage incurred by some hydropower dams when evaluated at the scale of the entire Amazon basin.

Finally, international cooperation in hydropower planning is paramount for reducing negative environmental outcomes. The researchers show that some seemingly good solutions from the perspective of individual countries might in reality be harmful when the entire Amazon basin is considered.

The Department of Biology is in the College of Natural Sciences.