Connect with us

Drone Below

Drone Analytics And AI Saving Big Dollars on Solar Farms

Aerospec's thermal images of a solar farm


Drone Analytics And AI Saving Big Dollars on Solar Farms

Aerospec's thermal images of a solar farm | Aerospec/Youtube

Drone Analytics And AI Saving Big Dollars on Solar Farms


Drone inspection and analysis in the energy sector is a significant industry, with representatives from that sector making up nearly 25% of attendees at last year’s Interdrone UAV industry conference.

In the renewables industry, they are being used used to save both big bucks and lots of time.

A graduate student from the Kellogg School of Management at Northwestern University (NU) has demonstrated how, by using a thermal imaging camera mounted on a drone, he can reduce the inspection time of a solar farm the size of 90 football fields from one month down to a mere three days.

Speaking with a journalist from NU, he explained that he is refining an algorithm to identify solar panels that are not performing at their optimum. Flying the drone at an altitude of 200 feet,he captured a sea of geometric pink, purple and yellow thermal images of a Nevada solar farm. A glaring white spot tells him that his algorithm has correctly identified a malfunctioning panel.

“This hot spot tells us that part of the panel is not performing correctly,” he told NU in an article on

Images of solar panels taken with an infrared thermal-imaging camera. White hot spots mark damaged cells that need replacement

Images of solar panels taken with an infrared thermal-imaging camera. White hot spots mark damaged cells that need replacement | Credit: Northwestern University

Li is CEO of Aerospec Technologies, a drone inspection and analytics company, which grew out of his interest in drones. Before starting the company, he had tried building and selling them, and providing drones as a service.

But it was safety that led him to develop his specialised drone analytics company, when working as an energy consultant he heard that eleven workers died at a drilling rig.

“I kept thinking, if we can keep our people out of harm’s way and send robots to do the most dangerous jobs, why aren’t we doing that?” said Li.

Enrolement in an entrepreneurship course at Kellogg called New Venture Launch enabled Li to solidify his business model, and the foundations for Aerospec Technologies began to take shape.

A successful entry in NU’s flagship business plan competition, VentureCat, brought in $5000 in seed funding when he won the energy category.

Linking up with leaders at campus incubator The Garage, Li was able to focus on Aerospec’s day-to-day operations.

Aerospec Technologies team at The Garage, Northwestern's incubator space

Aerospec Technologies team at The Garage, Northwestern’s incubator space | Credit: Northwestern University

By hiring interns at NU who were studying artificial intelligence and machine learning, Li is reaching his goal of making solar farms more efficient, safer, and ultimately, more predictable.

“During an annual checkup, it can take a maintenance crew a month to walk through and survey part of a 450,000-panel solar site, the size of 90 football fields, and weeks to analyze the data,” he told NU. “In comparison, it takes our drones only three days to fly over a site of the same size, and just minutes to process the data in a way that allows the operator to know the percentage of the site that needs repairs and the cost to his bottom line.”

By predicting outages and maintenance needs before they even happen, Aerospec’s predictive algorithm will save even more money. He estimates that the algorithm could mean an extra $336 million for the solar and wind industries, and supply power to 800,000 more homes with renewable energy each year.

“It costs a lot of money and a lot of manpower to detect an outage and restore power,” says Li. “We are able to confidently say, 80 percent of the time, that this panel at this site will go out within the next two months.”

Currently the largest player in industrial analytics is General Electric’s Predix platform, but Aerospec has the potential to make a real impact in the energy sector, specifically in regard to data collection and specialization.

Collection of data from Aerospec’s solar clients allows Li to train the algorithm in prescriptive analytics, thereby developing and recommending best practices for the entire solar industry. This method involves the use of AI to envisage scenarios such as panel malfunctions and then prescribe solutions, meaning that Aerospec can detect what might go wrong, as well as what to do before it happens.

“If someone wants to build a solar farm in a state where we work, they can come to us because we have data on millions and millions of solar panels over multiple years,” said Li. “Based on historical data, we can tell them where they should build, how they should angle their panels for maximum output, and what reflective coating they should use on their panels, based on weather.”

The future of Aerospec lies not only in solar farms, but also wind farms, said Li. With many current clients also owning wind farms, Li sees room for expansion across the renewable sector.

He has high hopes for developing more ways drones can be useful to a range of common problems.

“We know the impact that our technology can have on the energy industry,” says Li. “But we also know that the applications for the world are endless.”

How useful was this post?

Click on a star to rate it!

Average rating 5 / 5. Vote count: 1

No votes so far! Be the first to rate this post.

As you found this post useful...

Follow us on social media!

We are sorry that this post was not useful for you!

Let us improve this post!

Tell us how we can improve this post?

Cite this article as: Sarah Whittaker, "Drone Analytics And AI Saving Big Dollars on Solar Farms," in, March 29, 2018,

More in AI

Back To Base (B2B)




The Latest on DJI

The Drone Wire

To Top