Oil and gas operators have never had access to so much information. Modern assets generate huge volumes of data every day, from maintenance records and inspection reports to operational and alarm data.
Buried within it are early signs of potential issues, as well as opportunities to improve performance. The challenge has always been recognising these signals early enough and acting on them.
However, this is getting harder by the day. Oil and gas assets are ageing, and complexity is growing but engineers are being asked to make faster decisions, often without all the information. Meanwhile, the volume of data being generated has grown sharply.
AI is starting to help address that problem. It’s already being used in areas like predictive maintenance, optimisation and process modelling, helping engineers work through large volumes of data and spot patterns that would otherwise be missed.
This gives engineers a way to compare current operating conditions against previous scenarios, helping them make decisions more quickly. But in a safety-critical industry, speed is not the main issue. Engineers need to trust the output.
Data is not the problem
For most operators, the issue isn’t a lack of data, it’s fragmentation. Information is often spread across different systems, from control platforms and maintenance tools to spreadsheets, or with teams working in isolation.
In some cases, the most important knowledge still sits with individuals rather than in the data itself. Engineers rarely have a complete, real-time view of what’s happening across an asset, which is why having more data doesn’t necessarily lead to better decisions.
The trust problem
Even when the data challenge is addressed, another issue is making sure that engineers can understand not just what an AI system is recommending, but why.
This is where many current AI approaches fall short. Large language models are good at generating responses, but these are not based on real physics. They work by recognising patterns in data, which means they can sound convincing even when they’re wrong.
This creates a fundamental problem in oil and gas engineering environments, where decisions will have a direct safety implication. A recommendation that sounds reasonable is not enough if it can’tbe verified.
Many people are already sceptical towards AI tools, thanks to their experiences with clunky earlier generations that failed to deliver on their promises. So it’s important that the output is not only right, but also explainable.
Moving beyond the black box
This is why the recent shift towards ‘physics-informed’ AI models is an important development. Rather than relying purely on statistical and predictive patterns, these models rely on real physical and chemical principles that govern the world around us.
Conventional AI models predict what’s likely to happen based on historical data, but real engineering is based on understanding constraints, relationships between different variables in a system, and things like cause and effect. Physics-informed AI brings these approaches together and allows models to generate outputs that are grounded in reality.
Not only do these types of models consider real world conditions, but their outputs can be tested against real simulations, validated against known behaviour, and traced back to their underlying assumptions.
This gives engineers the confidence to assess a recommendation with credibility before acting on it. It also means that, instead of acting as a standalone ‘black-box’ decision maker, the AI tool becomes part of an engineering workflow to support human judgement rather than replacing it.
From theory to application
This is where partnerships between engineering specialists and AI developers are becoming increasingly important. While AI technology has advanced rapidly, the challenge in oil and gas is applying it in a way that engineers can trust.
KBR has been working with Applied Computing to combine AI models with decades of engineering expertise. Rather than relying on pattern recognition or prediction, the approach uses physics-informed AI, allowing recommendations to be grounded in engineering principles and validated against known operating conditions.
One of the first applications of this partnership is INSITE 3.0, an AI-enabled platform used in production environments. The system combines operational plant data with an understanding of process chemistry and engineering constraints, to identify anomalies and highlight opportunities for optimisation.
Keeping humans in the loop
Even with more advanced models, human oversight is still essential. AI can highlight patterns and test different scenarios, but it can’t take responsibility for decisions.
It’s possible to look at this in three ways. At the most basic level, AI can be used to monitor conditions and flag anomalies. Next, it can be used in a more advisory role, to suggest actions that engineers can evaluate. Finally, and only in limited cases, AI may be used to optimise specific processes automatically, within tightly defined boundaries.
Even then, experienced engineers are still needed to interpret the results, assess the risk and make the final decision.
A shift in skills and mindset
As AI becomes more embedded, it’s also changing the skills required. Engineers need to understand how these models work, where they fall short and how to validate the output.
This requires a wider cultural shift. Organisations will need to upskill their workforce, and that won’t happen overnight. Some will move faster than others, but adoption will ultimately come down to trust in high-risk environments.
AI has clear potential in oil and gas, particularly in areas such as asset integrity, optimisation and operational planning. But its impact will not come from automation alone. It will come from improving the way decisions are made, through better visibility, validation and trust.
