State-owned oil and gas company Saudi Aramco has unveiled its first generative AI (GenAI) model, Aramco Metabrain AI, at the annual LEAP tech conference in Riyadh, Saudi Arabia, on 4 March. 

Aramco’s AI model is a pioneering technology in the industrial sector. It has 250 billion parameters that are adjustable during training to generate outputs or make predictions. The AI was trained using seven trillion data points, collecting more than 90 years of company history.

Amin H Nasser, CEO of Saudi Aramco, said the AI model would analyse drilling plans, geological data, historic drilling time and costs as well as recommend the most ideal well options.

He added that for the company’s downstream business, “metabrain will have the capability to provide precise forecasts for refined products, including pricing trends, market dynamics and geopolitical insights”. 

Aramco plans to develop a version with 1 trillion parameters by the end of this year.

The company is currently digitising its newest facilities as well as its oldest oil processing facility in Abqaiq, which is more than 80 years old.

“The utilisation of AI, data analytics, robotics and the Internet of Things at Abqaiq has enhanced operations in many ways, including robotics and 4IR technology to do mundane or potentially hazardous tasks,” Nasser added. 

The World Economic Forum has recognised four of Aramco's facilities as 'Manufacturing Lighthouses' for their extensive use of 4IR (technologies of the fourth industrial revolution, or Industry 4.0) solutions. 

Its Uthmaniyah Gas Plant, one of the world’s largest gas processing plants, uses AI solutions to “increase productivity while enhancing the reliability of its facilities”. Aramco said that using drones and wearable technologies at the plant to inspect pipelines and machinery has helped cut inspection times by 90%.