Sharon Goldman 
The massive, beautiful tree canopies of the western United States, which can grow dangerously close to power lines, can quickly start devastating wildfires. In fact, 70% of power outages are caused by vegetation, and that number increased 19% year-on-year from 2009 to 2020. The second largest wildfire in California history, The Dixie Fire, was ignited when power lines made contact with a fir tree.
Could AI-driven solutions help prevent wildfires before they start by analyzing tree growth that can trigger them? Hitachi Energy, the global technology company based in Zurich, Switzerland, says yes.
AI is critical to a sustainable energy future
Hitachi Energy, formerly known as Hitachi ABB Power Grids (name changed last October), is currently focused on “good energy for a sustainable energy future”. One area of concern was how to position itself to serve off-grid customers and support industries that have interconnection assets spread across large geographic areas such as power, telecom, water, gas pipelines and rail. This includes utility companies dealing with thousands of miles of growing vegetation.
“These industries all have similar problems managing their mile-long assets,” Bryan Friehauf, SVP of enterprise software solutions at Hitachi Energy, told VentureBeat. “For example, you need to keep trees off railroad tracks and roads, and off gas lines and other critical infrastructure.”
Three trends have made the use of geospatial and AI-enabled technology crucial, he explained: aging infrastructure, siled systems and climate change. “It can be difficult or dangerous to view or manage assets under these conditions,” he said.
Inspection of trees to prevent forest fires and power outages
To address these challenges, Hitachi Energy today announced a new AI-driven solution, Hitachi Vegetation Manager, as part of the company’s new Lumada Inspections Insights offering. The company claims it is “the first closed-loop solution of its kind for vegetation resource planning that leverages artificial intelligence and advanced analytics to improve the accuracy and effectiveness of an organization’s vegetation activities and planning efforts.”
The solution, which uses algorithms developed at one of the company’s R&D centers in Japan, captures images of trees and forests from a variety of visual sources, including photos, videos and imagery from industry-leading Maxar satellites. By combining the imagery with climate, ecosystem and cutting plan data, as well as machine learning algorithms, Hitachi Vegetation Manager provides utilities with network-wide visibility and better insights so companies can improve decision-making.
Satellites take pictures, AI analyzes them
“Because satellites capture images remotely and AI analyzes them, we can better optimize and plan for problem areas,” Friehauf said. “This will also reduce management program costs and emissions by minimizing truck and helicopter travel, and ultimately minimize vegetation-caused outages and fires.”
Using AI to track and analyze vegetation is especially important for utilities around the world facing unprecedented climate-related challenges. In 2021, global wildfires are estimated to have generated a total of 6,450 megatons of CO2 Equivalent – around 148% more than total EU fossil fuel emissions in 2020.
According to John Villali, director of research at IDC Energy Insights, inspection, planning and monitoring are “among the most critical tasks that utilities undertake to maintain the reliability and resilience of the power grid. Hitachi Energy’s AI-driven solution, he explained, empowers utilities to improve decision-making, optimize operations, and “as a result, meet their reliability, safety and sustainability goals.”
Utilities are more willing to embrace AI
Historically, the utility industry, as a highly regulated sector, has not been a leader for AI and other emerging technologies, said Phil Gruber, general manager, energy/industrial utilities at Hitachi Vantara, Hitachi’s IT service management company. “The utilities industry tends to be very cautious, and for good reason, and generally isn’t at the forefront of using technology, but it’s starting to dabble,” he said.
One problem is that organizations often feel they don’t have enough high-quality data to start using AI or ML. “A lot of our conversations with customers revolve around picking them up where they are with their data sets,” said Gruber. “We often find that they have enough data to really improve their decision-making and outcomes.”
But Hitachi Energy’s solution means utilities no longer need arborists to walk miles of transmission lines to identify each species, Friehauf explained. Once species data has been fed into the model, including location and details like soil quality, the algorithm can use weather precipitation data, analyze the growth profile of tree species, and predict where growth will and will not occur.
“Of course, precipitation is not homogeneous, so even within the same district there can be areas that receive more precipitation than others,” Friehauf said. “The tool can show that even though you’ve cut back certain vegetation, you might have to redo it earlier because it rains a lot, or if you’re in a drought, you need to know how drought-resistant a species is.”
Overall, “Hitachi Vegetation Manager gives you a very accurate forecast of how this vegetation will grow,” Friehauf said. “This is important not only for utility companies dealing with wildfire or power outage risks, but for anyone who needs to manage vegetation around their linear assets.”
