Using artificial intelligence to locate risky dams

August 24, 2018 by Sarah Fecht, State of the Planet
New York State areas and infrastructure at risk during rare but severe floods. Credit: Byungjin So via ArcGIS

In the U.S., 15,498 of the more than 88,000 dams in the country are categorized as having high hazard potential—meaning that if they fail, they could kill people. As of 2015, some 2,000 of these high hazard dams are in need of repair. With a hefty price tag estimated at around $20 billion, those repairs aren't going to happen overnight.

A project out of the Columbia Water Center aims to help guide the process of repairing or decommissioning these dams. The team is pinpointing the riskiest dams, using climate models, GIS data, and to predict the likelihood that rainfall will overtop a dam and cause significant downstream damages to population and . "We can tell which dams should be repaired first, and which ones need to be monitored closely to plan for emergencies," said Byungjin So, a postdoctoral researcher working on the project.

The work is particularly urgent as America's dams continue aging and as climate change increases the chances of heavy rains and flooding. Most of these dams are now older than their original design life, and their condition is not always well monitored. Maintenance of these old dams is also a concern, as was shown by the near failure of the tallest dam in the country, the Oroville Dam, last year in California. The failure of the spillway led to the evacuation of 200,000 people as well as disruptions to the downstream water supply. The repair cost has now reached $1 billion, whereas prior maintenance and repair costs were estimated in the low millions of dollars.

First Steps

The projections start with climate data. So works with to understand atmospheric circulation and moisture patterns across space and time. In particular, he looks at winds that pick up water as they move across the Pacific Ocean on their way toward California. "For now we are only working with California," explained So, "but later we will consider the whole U.S."

Using artificial intelligence to locate risky dams
The Columbia Water Center is analyzing the atmospheric circulation and moisture patterns that influence California’s precipitation levels. The line colors indicate specific humidity. Credit: Byungjin So

Next, he uses artificial intelligence to determine whether those moisture and circulation patterns will actually translate into rainfall. Analyzing data from 1980 to 2017, the A.I. is using deep learning to recognize which patterns typically lead to rainfall in California. It then categorizes an incoming weather system as "rain" or "no rain" with 95 percent accuracy.

Finally, So must predict whether the rainfall could lead to dam failure. He will use elevation maps, dam heights, dam storage capacity, and runoff calculations to predict whether the rain could overtop the dam. Meanwhile, demographic data will reveal the people and critical infrastructure that could be at risk downstream.

What Comes Next

For now, the A.I. only classifies weather events into wet or dry. Eventually, So wants to have it classify events with more detail, such as "low rainfall" and "high ."

In addition, he's currently working on combining the artificial intelligence component into the climate model, and plans to finish that piece of the project in October. The assessment model for the dams, which is slated to be finished next year, will map the transportation, electricity generation, population and water/wastewater treatment infrastructure that could be impacted if each of the dams considered were to fail. Machine learning methods will also use rigorous simulations of dam failure dynamics from a few selected dams to project how any of the 88,000 potential dam failures could lead to downstream inundation and damage.

So hopes the model will be ready to advise decision-makers in the real world—and help protect people and infrastructure—by 2020.

Explore further: Study finds big savings in removing dams over repairs

Related Stories

Study finds big savings in removing dams over repairs

May 28, 2018

A new study by Portland State University researchers finds billions of dollars could be saved if the nation's aging dams are removed rather than repaired, but also suggests that better data and analysis is needed on the factors ...

A potential downside to the beaver's comeback

October 28, 2015

The Eurasian beaver was brought back from near extinction and now thrives across Europe. But this conservation success story may have had at least one unintended and potentially harmful consequence. Scientists report in ACS' ...

Recommended for you

Inert nitrogen forced to react with itself

March 21, 2019

Constituting over 78 % of the air we breathe, nitrogen is the element found the most often in its pure form on earth. The reason for the abundance of elemental nitrogen is the incredible stability and inertness of dinitrogen ...

Two-step path to shrinking worker bee gonads

March 21, 2019

The dramatic difference in gonad size between honey bee queens and their female workers in response to their distinct diets requires the switching on of a specific genetic program, according to a new study publishing March ...

Plant immunity cut to size

March 21, 2019

An international team based in Ghent, Belgium (VIB-UGent Center for Plant Systems Biology) and Basel, Switzerland (University of Basel), found a link between a class of enzymes and immune signals that is rapidly triggered ...


Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.