Artificial intelligence (AI) software firm SparkCognition is collaborating with Shell to accelerate the pace of imaging and exploration of subsurface structures using generative AI technology. The companies plan to use advanced AI algorithms to process large amounts of data and automate analysis.
“Innovation is crucial in the quest for a net-zero future, and the oil and gas industry will play a vital role in this effort. Breakthroughs, like the use of AI for exploration, are instrumental to meeting the growing energy demands today as we work to reduce our carbon footprint tomorrow,” said Lord John Browne, chairman of SparkCognition.
The traditional approach to subsurface imaging and data analysis is time-intensive and costly, relying on terabytes of data, high-performance computing, and complex physics-based algorithms to analyze and identify exploration opportunities. The generative AI approach being developed by Shell and SparkCognition uses deep learning to generate subsurface images using far fewer seismic shots than traditionally necessary—as little as 1% in completed field trials—while preserving subsurface image quality.
The collaboration is part of Shell’s broader digital transformation strategy, which seeks to use technology to improve safety, efficiency, and sustainability across Shell operations.
“We are committed to finding new and innovative ways to reinvent our exploration ways of working,” said Gabriel Guerra, Shell vice president of innovation and performance. “Partnering with SparkCognition and leveraging their expertise in generative AI is opening an exciting opportunity to deliver a new wave of innovations at Shell.”
The generative AI approach being used for oil and gas exploration is being applied to other complex problems where a reduction of data and time can have significant implications. This includes opportunities in on-shore exploration, satellite imaging for weather patterns, national security, and threat assessment.
“Generative AI for seismic imaging can positively disrupt the exploration process and has broad and far-reaching implications across industries—driving greater efficiencies, lower cost, and accentuating sustainability initiatives,” said Bruce Porter, chief science officer at SparkCognition.