General Electric Co. subsidiary Baker Hughes GE is teaming up with Nvidia Corp. to introduce artificial intelligence and data analytics technology to the oil and gas industries.

The initiative aims to make the two energy industries more efficient and predictive by collecting data from drilling operations, seismic activity, sensors and weather patterns. The collaboration will leverage systems powered by Nvidia’s graphics processing unit chips on oil rigs and in the cloud to collect and analyze data related to oil and gas extraction.

“In an oil and gas field there are a lot of sensors and data in remote operations that’s collected, but very little of it is analyzed,” Binu Mathew, global head of digital products for Baker Hughes GE, wrote in a blog post on LinkedIn.

To obtain more knowledge from that data, Baker Hughes GE is working with Nvidia to build “computational models” for “internet of things” systems. The idea is that these models will be able to analyze oil and gas data and provide actionable information to rig operators. The initiative has been ongoing for a year already, said Mathew, who added that the average offshore oil rig generates around a terabyte of data each year from sensors and operational and financial operations.

“With GPU-accelerated analytics, well operators can visualize and analyze massive volumes of production and sensor data such as pump pressures, flow rates and temperatures,” Tony Paikeday, director of product marketing for the NVIDIA DGX portfolio of AI supercomputers, added in a post on Nvidia’s blog. “This can give them better insight into costly issues, such as predicting which equipment might fail and how these failures could affect wider systems.”

The plan is for Bakers Hughes GE to leverage Nvidia’s expertise in AI technology and combine it with its own domain knowledge to create new models and analytics software specifically for oil and gas operations.

“The amount of computing power has been accelerated by Nvidia’s chips, partnerships and overall AI ecosystem,” Mathew said. “We are bringing out knowledge of analytics and the domain.”

To that end, Baker Hughes GE will apply Nvidia’s natural language processing and recursive neural network models to the chipmaker’s DGX computing platform. The companies will later build a range of cloud-based tools for the oil and gas and field production industries, Mathew said. These products will be designed to better predict issues and detect faults, and also deliver diagnostics, he added.

Source: Nvidia

“Using deep learning and machine learning algorithms, oil and gas companies can determine the best way to optimize their operations as conditions change,” Paikeday said. “For example, they can turn large volumes of seismic data images into 3D maps to improve the accuracy of reservoir predictions.”

Main image: 12019/pixabay