AI Used for Strategic Planning of Dam Placement Across Amazon Basin Without Impacting the Environment

A few years ago, biologist Alexander Flecker went to computer scientist Carla Gomes with an ambitious suggestion: Utilize AI and other tools, in partnership with a diverse group of Amazon river basin experts, to figure out how to meet hydropower requirements with the least amount of impact on the environment.

AI Used for Strategic Planning of Dam Placement Across Amazon Basin Without Impacting the Environment.
The Rio Santiago, a free-flowing river in the Andean Amazon with large hydropower dams in planning stages. Image Credit: Alvaro del Campo/The Field Museum.

The plan was to begin with the many proposed hydropower dams in the Marañón River basin, in Ecuador and Peru. At approximately 1,100 miles long, the Marañón is one of South America’s largest free-flowing rivers, and one of the main headwaters of the 4,345mile-long Amazon River.

Going through huge portfolios involving the location of dozens of dams, with each impacting the other as well as the river’s flow, was a massive request.

Gomes’ reply? Why not deal with the whole Amazon basin — about 2.4 million square miles, over a third of the continent?

As we got more excited, I thought, ‘Let’s keep pushing, let’s go big’. I felt that we could really develop these AI techniques to scale to the entire Amazon basin.

Carla Gomes, Computer Scientist and Ronald C. and Antonia V. Nielsen Professor, Ann S. Bowers College of Computing and Information Science, Cornell University

Flecker and Gomes co-led the project and are corresponding authors of the article “Reducing Adverse Impacts of Amazon Hydropower Expansion,” which was published on February 17th in Science. The article features 40 co-authors from over two dozen academic institutions in the United States, Europe and South America, together with NGOs including The Nature Conservancy and the Wildlife Conservation Society.

What makes this work special is that we’re bringing together so many different areas of expertise, and real Amazon experts, in areas such as ecology, fisheries biology, hydrology, social science, and computer science and AI. For us, that’s been incredibly exciting.

Alexander Flecker, Biologist and Professor, Department of Ecology and Evolutionary Biology, College of Agriculture and Life Sciences, Cornell University

This study stresses the need for strategic planning at the scale of the whole Amazon basin and pushes the frontiers of the work Gomes and Flecker published in 2019 guided by former Cornell Atkinson postdoctoral fellow Rafael Almeida, also a co-author of this study, that sought to enhance a selection of dams in the Amazon basin with reference to decreasing greenhouse gas emissions.

This research is considerably more ambitious in offering insights into the world’s largest and most biodiverse transboundary river basin, which covers eight countries.

The project takes into consideration six socio-environmental criteria for optimization of the over 350 proposed hydroelectric dams in the Amazon basin:

  • Sediment transport
  • River flow
  • Fish diversity
  • River connectivity
  • Greenhouse gas emissions
  • Energy production

Furthermore, not only does the present study aim to enhance new dam selection, but it also seeks to expose lost benefits from the 158 current hydropower dams in the basin, initially positioned without coordinated planning that considered their aggregate negative effects. Assessing all the possible solutions, the scientists said, produces a number that is “greater than the number of atoms in the entire universe,” Gomes said.

We are talking about more than 3 million riverine segments, combined with more than 500 dams, and multiple criteria,” Gomes said. “So not only do we have to try to organize the solutions in terms of energy, we want to compare them in terms of all the criteria. The computational requirements are formidable.”

Flecker, in truth, thought it was more than just arduous.

“I didn’t think it would be possible,” said Flecker, who has carried out wide-ranging research in the Caribbean and Latin America. “As someone who has spent a lot of time in South America, and knowing just how huge (the Marañón) is, I really didn’t think that it was realistic.”

Gomes and her team of computer scientists formulated a very efficient “divide and conquer” approximation algorithm to discover the best as well as the worst options, which could be removed from consideration.

The team’s method establishes what is known as the “Pareto-optimal frontier” — the portfolios of dam configurations that reduce negative effects covering all six criteria for any specified level of aggregate hydropower yield. The method removes lower-quality solutions.

The article reveals that the historical lack of tactical coordinated planning has caused environmental benefits to be missed, and proposes four main strategies for decreasing environmental damage from dam constructions in the future. The first, and maybe most basic, is that multi-objective enhancement offers an effective “first filter” to locate the many dam sites that would produce predominantly negative results.

A key is getting the worst dams off the table, and that’s really critical and something that gets neglected. And it took us a while to realize that we had this tool for doing that.

Alexander Flecker, Biologist and Professor, Department of Ecology and Evolutionary Biology, College of Agriculture and Life Sciences, Cornell University

The second main strategy complements the first: Concurrent consideration of numerous criteria is very important for recognizing the least damaging projects in relation to ecosystem services — the advantages that healthy rivers offer, such as biodiversity, fisheries, floodplain agriculture and undisturbed navigation routes.

“As more environmental criteria are included,” Flecker said, “fewer dams remain that can be considered relatively low impact, pointing to the need for examining many different objectives simultaneously.”

Third, basin-wide assessment is crucial for reducing forgone ecosystem service benefits. Planning at smaller scales can produce ambiguous results, missing some of the damage suffered by certain hydropower dams when assessed at the scale of the whole Amazon basin.

Remarkably, some dams that are always in the optimal solutions when evaluated for the Marañón subbasin alone are, in fact, never in the optimal solutions when analyzing the entire Amazon.

Suresh Sethi, Study Co-Author and Associate Professor of Natural Resources and Environment (CALS), Cornell University

Finally, global cooperation in hydropower planning is vital for decreasing negative environmental results. They reveal that some apparently good solutions from the viewpoint of individual nations might in reality be quite damaging when the whole Amazon basin is taken into consideration.

As director of Cornell’s Institute for Computational Sustainability, Gomes is very aware of the significance of this study.

“It is really a pleasure and uniquely rewarding that we are using computer science and AI to address this sustainability challenge,” she said. “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?”

Other Cornell co-authors include Peter McIntyre, associate professor of natural resources and environment (CALS); Scott Steinschneider, assistant professor of biological and environmental engineering (BEE; CALS); M. Todd Walter, professor of BEE; Cornell Presidential Postdoctoral Fellow Sebastian Heilpern ’10; Qinru Shi, a Ph.D. student in the field of applied math; Brendan Rappazzo, a Ph.D. student in the field of computer science; and Yexiang Xue, Ph.D. ’18, currently an assistant professor at Purdue University.

Contributors were from over 25 academic and non-academic institutions from the United States, France, Brazil, Ecuador, Colombia and Peru.

This research received support 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.

Journal Reference:

Flecker, A., et al. (2022) Reducing adverse impacts of Amazon hydropower expansion. Science.


Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Azthena logo powered by Azthena AI

Your AI Assistant finding answers from trusted AZoM content

Your AI Powered Scientific Assistant

Hi, I'm Azthena, you can trust me to find commercial scientific answers from

A few things you need to know before we start. Please read and accept to continue.

  • Use of “Azthena” is subject to the terms and conditions of use as set out by OpenAI.
  • Content provided on any AZoNetwork sites are subject to the site Terms & Conditions and Privacy Policy.
  • Large Language Models can make mistakes. Consider checking important information.

Great. Ask your question.

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.