How Neara uses AI to protect utilities from extreme weather

Over the past few decades, extreme weather events have not only become more severe, but also are occurring more frequently. Neera is focused on enabling utility companies and energy providers to build models of their power networks and anything that could impact them, like wildfires or floods. The Redfern, New South Wales, Australia-based startup recently launched AI and machine learning products that build large-scale models of networks and assess risks without doing manual surveys.

Since launching commercially in 2019, Neara has raised a total of $45 million AUD (approximately $29.3 million USD) from investors such as Square Peg Capital, Skip Capital, and Press Ventures. Its customers include Essential Energy, Endeavor Energy, SA Power Networks. It has also partnered with Southern California Edison Company and EMPACT Engineering.

Neera’s AI and machine learning-based features are already part of its technology stack and have been used by utilities around the world, including Southern California Edison, SA Power Networks and Endeavor Energy in Australia, ESB in Ireland, and Scottish Power. Are included.

Co-founder Jack Curtis tells TechCrunch that billions are spent on utilities’ infrastructure, including maintenance, upgrades, and labor costs. When something goes wrong, consumers are immediately affected. When Neara began integrating AI and machine learning capabilities into its platform, the aim was to analyze existing infrastructure without manual inspection, which it says can often be inefficient, inaccurate and costly.

Neera then extended its AI and machine learning features so it could build a large-scale model of the utility’s network and environment. The model can be used in a number of ways, including simulating the impact of extreme weather on power supplies before, after and during an event. This can speed power restoration, keep utility teams safe and reduce the impact of weather events.

“The increasing frequency and severity of severe weather drives our product development more than any single event,” says Curtis. “Recently there has been an increase in severe weather events around the world and this phenomenon is affecting the grid.” Some examples are Hurricane Isha, which left thousands without power in the United Kingdom, the winter storm that caused massive blackouts across the United States, and Tropical Cyclone Stormo in Australia, which weakened Queensland’s power grid.

Using AI and machine learning, Neara’s digital models of utility networks can prepare energy providers and utilities for them. Some of the situations that Neera can predict include where strong winds can cause power outages and wildfires, flood water levels that mean the network needs to shut down its energy and snow. and ice accumulation that can make networks less reliable and resilient.

In terms of training the model, Curtis says that while AI and machine learning were “incorporated into the digital network from the very beginning,” LiDAR is critical to Nearra’s ability to accurately simulate weather events. He further added that its AI and machine learning models were “trained on a diverse network area of ​​over a million miles, helping us capture seemingly small but highly consequential nuances with hyper-accuracy.”

This is important because in scenarios such as flooding, a difference of one degree in elevation geometry can result in inaccurate water level modeling, meaning utilities may need to activate power lines earlier than necessary or, on the other hand, Electricity may have to remain on for longer than scheduled. Safe.

Neara co-founders Daniel Danilatos, Karamvir Singh and Jack Curtis

LiDAR imagery is captured by utility companies or third-party capture companies rather than LiDAR itself. Some customers constantly scan their networks to feed new data into Neera, while others use it to derive new insights from historical data.

“A key result of capturing this LiDAR data is the creation of digital twin models,” says Curtis. “That’s where the power of contrasting raw LiDAR data lies.”

Some examples of Neara’s work include Southern California Edison, where its goal is to “auto-prescribe”, or automatically identify where vegetation could catch fire, compared to manual surveys. It also helps survey teams know where to go without putting inspectors at risk. Because utility networks are often large in scale, different inspectors are dispatched to different areas, which means multiple sets of subjective data. Using Nearra’s platform keeps the data more consistent, says Curtis.

In this Southern California Edison case, Nearra uses LiDAR and satellite imagery to simulate the things that contribute to the spread of wildfire through vegetation, including wind speed and ambient temperature. But one of the things that makes predicting vegetation risk more complicated is that Southern California Edison is required to answer more than 100 questions for each of its power poles due to regulations and it has to recondition its transmission system annually. There is also a need to inspect.

In another example, Neara began working with SA Power Networks in Australia following the 2022-2023 Murray River flood crisis, which affected thousands of homes and businesses and was considered one of the worst natural disasters to hit Southern Australia goes. SA Power Networks obtained LiDAR data from the Murray River region and used Nearra to carry out digital flood impact modeling to see how much damage was done to its network and how much risk remained.

This enabled SA Power Networks to complete a report in 15 minutes, analyzing 21,000 power line extensions within the flood zone, a process that would otherwise have taken months. Because of this, SA Power Networks was able to reactivate power lines within five days, whereas three weeks were originally expected.

3D modeling allowed SA Power Networks to model the potential impact of different flood levels on parts of its electricity distribution network and predict where and when power lines might breach clearances or risk power disconnection . After river levels returned to normal, SA Power Networks continued to use Neerra’s modeling to help plan the reconnecting of its electricity supply along the river.

Neara is currently doing more machine learning R&D. One goal is to help utilities get more value from their existing live and historical data. It also plans to increase the number of data sources that can be used for modeling, with a focus on image recognition and photogrammetry.

The startup is also developing new features with Essential Energy that will help utilities assess each asset in the network, including poles. Individual properties are currently evaluated on two factors: the likelihood of an event such as extreme weather occurring and how well it can hold up under those conditions. Curtis says this type of risk/value analysis is usually done manually and sometimes doesn’t prevent failures, as was the case with blackouts during the California wildfires. Essential Energy plans to use Nearra to develop a digital network model that will be able to more accurately analyze assets and reduce risk during wildfires.

“Essentially, we are allowing utilities to stay one step ahead of extreme weather by understanding how it will impact their networks, allowing them to keep the lights on and keep their communities safe,” says Curtis. “