Artificial intelligence (AI) has the potential to transform the energy sector in the coming decade, boosting electricity demand from data centres around the world while also unlocking opportunities to cut costs, enhance competitiveness and reduce emissions, according to a new report from the IEA
The IEA’s special report Energy and AI argues that, while the increase in electricity demand for data centres is set to drive up emissions, this increase will be small in the context of the overall energy sector and could potentially be offset by emissions reductions enabled by AI if adoption of the technology is widespread. Additionally, as AI becomes increasingly integral to scientific discovery, the report finds that it could accelerate innovation in energy technologies such as batteries and solar PV.
“With the rise of AI, the energy sector is at the forefront of one of the most important technological revolutions of our time,” said Dr Fatih Birol, IEA executive director. “AI is a tool, potentially an incredibly powerful one, but it is up to us – our societies, governments and companies – how we use it.”
AI applications in oil and gas supply can help play a role in energy transitions by ensuring that sufficient supplies are available at lower cost and with lower emissions, the IEA says.
Early adopters
The report notes that oil and gas companies have been among the earliest adopters of new technologies to boost exploration and production. In 2000, 11 supercomputers operated by oil and gas companies ranked among the world’s 500 fastest. By 2024, this number had increased to 24, and total computing capacity has grown at almost 70% annually, outpacing the broader supercomputing industry. Companies including TotalEnergies, Petrobras and Aramco are developing new supercomputer capabilities for applications across exploration and production, operations and safety and emissions management; Eni’s latest supercomputer is currently the fifth fastest in the world.
Oil and gas companies are also investing and partnering with AI experts to develop bespoke tools for their industry, with ADNOC announcing the completion of a trial of an AI agent based on a 70bn-parameter large language model that is reported to have improved the accuracy of seismic processing by 70%, along with other improvements.
Various applications
AI has various applications in the sector, the report notes, including for subsurface data processing, reservoir simulation, remote operations, predictive maintenance, regulatory compliance, leak detection and automation.
In exploration and development, the use of AI in seismic processing improves interpretation and image quality and makes it up to 90% better at classification. It can also help to determine where precisely to drill production wells. AI can also enhance the accuracy and speed of processes for reservoir simulation models. The use of deep learning algorithms allows faster loading and processing of large volumes of data from multiple sources, which are entered into simulation models. Physics-informed machine learning has enhanced the ability to model more complex reservoir behaviour.
In the realm of operations and safety, various AI and machine learning techniques are being applied to production forecasting. Recently, Exxon-Mobil’s AI-powered demand forecasting model was reported to have reduced forecast errors by 25%. The use of AI can also allow operations, monitoring and control to be carried out remotely. A typical oil platform hosts tens of thousands of sensors, generating terabytes of data. Analysing and leveraging this data from a centralised remote location can increase efficiency and safety and reduce the costs of operations. Cloud computing facilitates the remote analysis of datasets, remote operational decisions and the creation of digital twins.
In terms of cost reduction, AI-led interventions could reduce the costs of finding, developing and operating a new deepwater offshore project by up to 10%, the IEA estimates.
In the area of emissions reduction, AI is being deployed to boost data processing techniques to detect and quantify emissions. For example, automated AI-driven methane emitter monitoring systems using two satellites were recently deployed at the International Methane Emissions Observatory’s Methane Alert and Response System, the IEA notes.
A particularly promising area is in rapidly detecting fugitive emissions, which comprise around 20% of methane emissions from oil and gas operations. These leaks can usually be repaired quickly once found. Leak detection and repair programmes, involving optical gas imaging cameras or the use of airborne and satellite observations can be enhanced with AI, allowing large amounts of data collected to be processed much more quickly.
Another important possible deployment of AI is to improve the planning of CCUS projects; by enhancing reservoir models, additional computing power and AI can provide more certainty around the efficacy and costs of long-term CO2 storage, the IEA notes.
Transforming oil and gas operations with AI
AI has applications throughout the value chain in the oil and gas sector. (Image source: Adobe Stock)
