Percepto launches AI solution to analyze vast troves of emissions data
By DRONELIFE Features Editor Jim Magill
Percepto, which has been combining the use of drones and artificial intelligence (AI) technology to collect and analyze methane emissions being released in some of the most prolific oilfields in the world, recently released a new AI product that will enable operators to conduct large-scale emission detection in real time.
The Israel-based company, in partnership with major oil company Chevron, has been engaged in an ongoing pilot program to prove out its technology in two big oil-producing basins in the U.S. West. In the testing program, Percepto conducts optical gas imaging (OGI) surveys of upstream oil and gas operations with autonomous drones.
Using the algorithm of its newly released AI Emission Detector, Percepto can now flag and analyze emissions in real time, allowing emissions monitoring to be conducted on a company-wide level.
“If you think of covering vast areas with drones and analyzing the data manually, you would need a lot of people to analyze hours and hours of videos. The AI basically is a tool to actually do it at scale,” Udi Zohar, Percepto’s chief product officer, said in an interview.
According to a Percepto spokesperson, the company’s AI Emission Detector solves one of the biggest challenges confronted when collecting mass quantities of data — as happens when using autonomous drone systems — that being: who’s going to analyze all that data?
“That’s where AI comes into play. By automating data analysis, Percepto’s clients can scale their use of autonomous drones, knowing the data will be actionable.”
Percepto’s AI system is also capable of generating validated reports that will be aligned with new Environmental Protection Agency methane detection requirements scheduled to take effect next year.
Technology’s uses go beyond oil and gas industry
The AI technology can be expanded to use cases far beyond oil and gas fields, to detect and report on emissions across a broad swath of industries: from automobile plants to mining facilities, chemical plants, refineries, electric transmission and distribution lines, solar farms, and shipping ports and terminals.
“As a customer, you want to actually do it repeatedly, not just inspect assets once a month, but inspect once a week or once a day, and cover a lot of assets in a very big area. Using the AI, we can do that very effectively,” Zohar said.
Percepto’s technology uses the company’s proprietary Air Max OGI drone-in-a-box system and Percepto’s AIM software, which empowers industrial sites to employ drones and robots to automate inspections, emergency response and security.
The drone’s payload includes an OGI camera, and a standard digital RGB camera. The drone’s base station delivers automatic charging and data upload, and includes a heating, ventilation, and air conditioning (HVAC) unit and weather station. The cloud-based software includes geospatial data management, several advanced analytics algorithms, and numerous other operational and safety features.
“We have Nvidia GPU [Graphics Processing Unit] that is installed on the drone and the AI is running in real time and providing data in real time to our people and also to the customer,” Zohar said. By providing the operators with real-time data the system will allow them to maneuver the drone to be better able to respond to gas leaks immediately, instead of having to wait for the data to be analyzed before responding.
“So, let’s say you are flying the drone and the drone detected a leak. Maybe you want to take images or video from different angles or with different cameras. We can do that according to the real-time detection of the tool,” he said.
Zohar said all of Percepto’s drones and software products are compliant with the U.S. National Defense Authorization Act specifications. He added that the company’s AI product can also work with other company’s drones and software systems.
“You can upload to the system drone data that is not ours and use the software capabilities that can manage assets and analyze the images and the videos and send reports,” he said.
In addition to Chevron, which deploys the Percepto technology in its upstream oil and gas operations in the Permian Basin of West Texas, one of the largest oil basins in North America, as well as in its oil-producing assets in Colorado, other oil producers also are adopting Percepto’s technology, Zohar said.
In addition, because the system is scalable, it can be adapted for use by major industrial players as well as companies with much smaller operations, he said.
“We already have smaller customers because in the end, it saves money. These autonomous drones cost less money and can do more inspections per time period than two guys on a truck,” he said. “This is a quicker, safer, more cost-effective way to inspect all of your assets. And you can do it more frequently to more reliably prevent accidents and identify leaks.”
Read more:
Jim Magill is a Houston-based writer with almost a quarter-century of experience covering technical and economic developments in the oil and gas industry. After retiring in December 2019 as a senior editor with S&P Global Platts, Jim began writing about emerging technologies, such as artificial intelligence, robots and drones, and the ways in which they’re contributing to our society. In addition to DroneLife, Jim is a contributor to Forbes.com and his work has appeared in the Houston Chronicle, U.S. News & World Report, and Unmanned Systems, a publication of the Association for Unmanned Vehicle Systems International.
Miriam McNabb is the Editor-in-Chief of DRONELIFE and CEO of JobForDrones, a professional drone services marketplace, and a fascinated observer of the emerging drone industry and the regulatory environment for drones. Miriam has penned over 3,000 articles focused on the commercial drone space and is an international speaker and recognized figure in the industry. Miriam has a degree from the University of Chicago and over 20 years of experience in high tech sales and marketing for new technologies.
For drone industry consulting or writing, Email Miriam.
TWITTER:@spaldingbarker
Subscribe to DroneLife here.
