Weather-related power outages in the US have doubled in the last decade, and they’re more than just an annoyance. They can disrupt access to clean water, food and health care, as well as communication systems and transportation.
But power companies have a new ally: AI. Startups in the AI sector are tackling long-time challenges, which include everything from parenting to mortality. And now we can add power outages to the list, thanks to 2-year-old Rhizome, which was founded to bring climate-related intelligence to the utility sector.
Rhizome helps predict the likelihood of a power outage during an extreme weather event and outlines what can be done to prevent such outages in the first place.
The platform uses global climate models and historical weather data to assess specific geographic areas. Then it looks at datasets from utility companies, including information about their physical assets, such as the age and condition of poles, transformers and cables, as well as the historical record of outages in the area, to understand the pattern of failure from extreme weather events to date.
Rhizome uses this weather and asset data to predict the likelihood of future failures in extreme weather given existing system conditions.
“Think about the power line that goes down in your neighborhood,” said Rhizome CEO Mishal Thadani. “We can assess risk on that whole power line so that the utility can prioritize if they need to make some sort of investment — whether they underground it, whether they should replace the poles, whether they should trim the trees along that power line and so on and so forth.”
The Washington, DC-based startup can feed new weather/climate datasets into the model, along with data about outages and asset updates, so Rhizome has what Thadanicalleda constantly updating picture of risk for a given utility company.
“Think of this as an engine that’s continuously running and getting continuously updated,” he said.
There’s a lot of stress on the US grid today. That’s in part because our national grid is old and aging quickly.
On top of this, we’re seeing more severe weather, like storms, extreme temperatures and tornadoes, and follow-on disasters like wildfires and flooding, which are also increasing in intensity.
“Our grid is experiencing these things at a higher pace and is also experiencing things that we’ve never seen before,” Thadani said.
That includes the 2021 winter storm in Texas that caused the grid to go down for more than a week.
Thadani saw a need for utility companies to use new tools to evaluate the impact of extreme weather on the grid so they can optimize the investments they’re making to withstand these events while keeping customer affordability in mind.
“Utilities can’t go out and spend billions and billions of dollars without having real-world impacts for everyday people who are trying to pay their bills,” Thadani said.
Another goal is to help utility companies design a grid that is stable and safe, so we have a stronger foundation on which to build as we transition to alternate sources of power like solar and wind.
“The energy transition totally fundamentally relies on the reliability and resilience of the grid,” Thadani said.
Rhizome has partnerships with utility companies in the Northeast and Pacific Northwest and plans to expand in both the US and Canada.
Though Rhizome is focused on the power sector, Thadani said the platform can assess risk on any three-dimensional asset, making it applicable to additional industries like telecom, oil, gas and even insurance.
“Insurance companies are underwriting all of these assets and are going to need to understand what’s going to be the changing risk profile,” Thadani said.
This is one of a series of short profiles of AI startups, to help you get a handle on the landscape of artificial intelligence activity going on. For more on AI, see our new AI Atlas hub, which includes product reviews, news, tips and explainers.
Editors’ note: CNET used an AI engine to help create several dozen stories, which are labeled accordingly. The note you’re reading is attached to articles that deal substantively with the topic of AI but are created entirely by our expert editors and writers. For more, see our AI policy.
