In recent decades, extreme weather events have not only become more severe, but also occur more frequently. Close focuses on enabling utilities and energy providers to build models of their power grids and anything that might affect them, such as fires or floods. New South Wales, Australia-based startup Redfern recently launched artificial intelligence and machine learning products that build large-scale network models and assess risks without having to conduct manual surveys.
Since its commercial launch in 2019, Neara has raised a total of AUD$45 million (approximately US$29.3 million) from investors including Square Peg Capital, Skip Capital and Prosus Ventures. Its clients include Essential Energy, Endeavor Energy and SA Power Networks. It also works with Southern California Edison and EMPACT Engineering.
Neara’s AI and machine learning capabilities 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.
Co-founder Jack Curtis tells TechCrunch that billions are spent on utility infrastructure, including maintenance, upgrades and labor costs. When something goes wrong, consumers are immediately affected. When Neara began incorporating AI and machine learning capabilities into its platform, it was to analyze existing infrastructure without manual controls, which it says can often be inefficient, inaccurate and costly.
Next, Neara leveraged its AI and machine learning capabilities so it could build a large-scale model of a utility’s network and environment. The models can be used in many ways, including simulating the effects of extreme weather events on electricity supplies before, after and during an event. This can increase the speed of power restoration, keep utility crews safe and mitigate the effects of severe weather.
“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 the network is being affected by this phenomenon.” Some examples it is Storm Ishawhich left tens of thousands without power in the UK, winter storms which caused massive power outages throughout the United States and Tropical cyclone storms in Australia which leave Queensland’s electricity grid vulnerable.
Using artificial intelligence and machine learning, Neara’s digital models of utility networks can prepare energy providers and the utility for them. Some situations that Neara can predict include where high winds can cause outages and fires, flood water levels that mean grids have to shut down their power, and ice and snow accumulations that can make grids less reliable and resilient .
When it comes to training the model, Curtis says artificial intelligence and machine learning “went into the digital network from the ground up,” with lidar critical to Neara’s ability to accurately simulate weather phenomena. It adds that the AI and machine learning model was trained “on over a million miles of diverse network territory, which helps us capture seemingly small but significant nuances with hyper-accuracy.”
This is important because in scenarios such as a flood, a one-degree difference in elevation geometry can result in inaccurate water levels being modeled, meaning utilities may need to activate power lines before they need to or, on the other hand, to maintain power for longer than is safe.
Neara co-founders Daniel Danilatos, Karamvir Singh and Jack Curtis. Image Credits: Close
Lidar images are recorded by utilities or third party recording companies. Some customers scan their networks to continuously feed new data to Neara, while others use it to get new insights from historical data.
“A key result of ingesting this lidar data is the creation of the digital twin model,” says Curtis. “That’s where the power lies as opposed to raw lidar data.”
Some examples of Neara’s work include Southern California Edison, where his goal is to automatically determine where vegetation is likely to catch fire more accurately than manual surveys. It also helps inspectors tell search teams where to go without putting them in danger. Because utility networks are often huge, different inspectors are sent to different areas, which means multiple sets of subjective data. Curtis says using Neara’s platform keeps the data more consistent.
In the case of Southern California’s Edison, Neara uses lidar and satellite imagery and simulates things that contribute to fire spread through vegetation, including wind speed and ambient temperature. But a few things that make predicting the risk of vegetation more complicated are that utilities often have to answer more than 100 questions for each of the power poles due to regulations and are also required to inspect the transmission systems annually.
In the second 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 is considered one of the worst natural disasters to hit southern Australia. SA Power Networks captured lidar data from the Murray River area and used Neara to run digital flood impact modeling to see how much of its network was damaged and how much risk remained.
This allowed SA Power Networks to complete a report in 15 minutes that analyzed 21,000 stretches of power lines within the flood zone, a process that would otherwise have taken months. Because of this, SA Power Networks was able to reactivate the power lines within five days, compared to the three weeks originally expected.
3D modeling also enabled SA Power Networks to model the potential impact of various levels of flooding on parts of the electricity distribution networks and predict where and when power lines could breach distances or be at risk of power disconnection. After the river level returned to normal, SA Power Networks continued to use Neara’s modeling to help it plan the reconnection of its electricity supply along the river.
Neara is currently doing more machine learning research and development. 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 an emphasis on image recognition and photogrammetry.
The startup is also developing new features with Essential Energy that will help utilities evaluate every asset, including poles, on a grid. Currently, individual assets are evaluated based on two factors: the likelihood of an event such as extreme weather 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 in the case of blackouts during the California wildfires. Essential Energy plans to use Neara to develop a digital grid model that will be able to perform more accurate analysis of assets and reduce risks during fires.
“Essentially, we allow utilities to stay one step ahead of extreme weather by understanding exactly how it will affect their grid, allowing them to keep the lights on and their communities safe,” says Curtis.
