How AI/ML can help companies in the Oil & Gas industry?
Hello everyone!
In this article, I will describe artificial intelligence(AI) and machine learning(ML) applications in the Oil & Gas industry. But first, let’s take a look at the definition of learning.
Learning is a long-term change in a person’s behavior as a result of experiences. For a knowledge and skill to be accepted as learning, it must make a behavioral change and this change in behavior must be long-term. (Wikipedia)
As mentioned above, learning is long term. But for a machine or a system with enough data, this is the opposite.
Machine learning is a scientific field of study that develops various algorithms and techniques to enable computers to learn like humans. Fueled by data, these algorithms build and learn their own logic based on the data!
Well, “What is AI?”
Artificial intelligence (AI) is a collection of technologies that includes machine learning (ML), natural language processing (NLP), and robotics that allow machines to sense, interpret, act and learn data to aid decision‐making. (EY)
Artificial intelligence has a long history. But it began in the year 1950 when the British Mathematician Alan Turing asked the famous question “can machines think?”
Artificial intelligence (AI), as the most important technology of today, is rapidly entering industries, creating significant potential for innovations and growth. Most organizations aren’t utilizing the potential of AI/ML; they’re just at the start of their AI/ML journeys. Logically, what should be holding companies back is a lack of talent. But, in fact, it’s a lack of understanding of the possibilities, particularly among executives of larger enterprises.
Oil and gas, mining, and construction companies are the latecomers to digitalization but they are also getting more and more dependent on AI solutions. This is partly because it’s seen as a risky, unproven technology and it requires highly skilled programmers and data scientists. But it’s also because it requires a sustained, long-term investment of dollars that many companies simply couldn’t afford during the downturn.
AI in the petroleum industry
The petroleum (oil and gas) industry divides into upstream, mid- stream, and downstream. (D. Koroteev and Z. Tekic)
AI helps oil and gas companies assess the value of specific reservoirs, customize drilling and completion plans according to the geology of the area, and assess the risks of each individual well. In addition, downstream operations can be optimized to minimize costs and maximize spreads.
The upstream summarizes the sub-surface (mining) part of the industry, including exploration followed by the field development and production of the crude oil/gas. Midstream stands for transportation of oil and gas, and downstream is for refinery i.e., production of fuels, lubricants, plastics, and other products. (D. Koroteev and Z. Tekic)
Exploration and Production
- Forecast total recoverable reserve volumes
- Analyze exploration and reservoir data
- Model well spacing and field development plans
- Optimize lateral and frac design
- Model and simulate various proppant and fluid loading options
- Create lifetime well production models and more effective production forecasts
- Set bidding strategies for lease blocks based on market behaviors
Midstream and Refining
- Forecast long-term commodity input and product market price
- Provide capital planning and risk evaluation for better long-term decisions
- Optimize commodity trading and hedging strategies
- Improve reliability risk modeling for refining and processing assets
- Maximize labor productivity and wrench time
- Enhance asset scheduling for refining and processing operations
- Optimize pipeline scheduling for product flows
Oil Field Services and Equipment
- Optimize drilling, completion equipment scheduling, and fleet management
- Manage and optimize supply chains
- Optimize procurement strategies for proppant, water, and other consumables
- Identify root causes and drivers of non-productive time
- Forecast customer demand and drilling activity in the medium- and long-term
- Enhance back-office and invoicing/billing processes
- Automate financial controls for high-volume transactions
AI-focused studies are aiming to speed up these stages. Classical machine learning and deep learning are dominant approaches used in AI applications in the upstream sector and the whole oil and gas industry. They are used in solving classification, clustering, or regression types of problems.
Additionally, hybrid modeling, where physics-driven models are used together with machine learning algorithms, is present in industrial applications.
The applications of AI and machine learning (ML) in the oil & gas industry are many, and some of them can really make a difference in a sector that is seeking to renew itself. The costs could be cut using predictive analytics, big data, and ML in upstream oil & gas activities.
Some of the AI application areas in the oil & gas industry:
- Human resources (hire to retire)
- Finance (cost allocations)
- Maintenance (truck engine maintenance planning and execution)
- Subsurface (well data analysis)
- Environment, health and safety (safety assessments and root cause analysis)
- Inventory management (material replenishment planning and optimization)
Let’s have a look at some of the most interesting current use cases and applications of AI and ML in the oil & gas industry.
- Exploration
Armed with AI, operators can better understand their reservoirs and minimize geologic risk. There is tremendous, but untapped, value in the data collected today. Operators can use it to make better exploration and production decisions, and optimize acquisition strategies with better forecasts of lease transaction prices.
- Drilling and Completions
AI has proven to be very effective at improving well design, drilling execution, and completion execution. Producers can maximize ROI for every well by optimizing well placement and well spacing to maximize resource recovery, designing wells to optimize recovery and total cost, and predicting sub-surface risks.
- Production
Accurate daily, monthly, and lifetime well production forecasts are critical for a successful production. Machine learning can help to optimize flow rates, pressure, and other variables for maximum lifetime well production. Plus, anomaly detection capabilities allow operators to anticipate well issues in advance before they cut off production.
- Gathering and Transportation
AI helps operators forecast product flow, demand, and price to make long-term capital decisions based on product supply-demand imbalances and local market price spread. They can also model right-of-way (ROW) acquisition costs and improve planning and routing with more informed estimates of easement costs.
- Processing and Refining Maintenance
In order to optimize processing and refining processes, operators are using AI for shutdown planning at their refineries. They can model and quantify the risk of failure for key equipment in the critical path during maintenance shutdowns to make more informed decisions about scope, reduce total shutdown cost, and improve equipment reliability.
- Corporate and Back-office
AI can have a huge impact on the front lines, but its impact behind the scenes can be just as powerful. Operators use AI to forecast commodity prices for capital project planning, risk management, and marketing activities, as well as anticipating potential health and safety risks. It has also proven effective at automating high-volume vendor invoice analysis and processing to reduce costs and identify errors.
- Predictive assets maintenance:
Predictive maintenance solutions are currently the principal application of this technology. They help operators improve operational safety and turn higher profit margins at the same time. AI models that can predict equipment failure are available across all the streams of the oil & gas industry as they reduce the risk of costly accidents, minimize operating expenses by reducing downtime, and improve compliance with safety standards.
- Improving the health and efficiency of Bobs(Blowout Preventers)
BOPs are a fundamental piece of equipment that is responsible for keeping the seal in place in the most difficult conditions of pressure, or against uncontrolled flow/formation kicks that may occur during drilling.
Digital companies such as Deepwater Subsea are currently harnessing the power of AI and ML to understand the condition of BOPs in real-time and reduce rig non-productive time (NPT). Through pattern recognition, the AI may leverage all the available rig data coming from faults, alarms, and subsea control systems. BOP pressure testing is the core of this technology which uses the data analytics platform TrendMiner. It is used on rigs across the Gulf for customers such as Chevron, Pacific Drilling, and TransOcean. TrendMiner collects all trends and compares them to optimal performance profiles. (Alta ML)
- Better Forecasts and Optimized Financial Planning
Having the right product in the right place at the right time is key to increasing their fulfillment levels and lowering working capital at the same time. AI can predict demand for a specific product for a region, helping companies make sure they have the right supply to serve customer orders on time, and know on which strategic regions they want to focus. Companies running gas stations may, for example, reap the benefits of predicting their demand for consumer goods (snacks, drinks, other products), reducing their inventory capital and safety stocks to release a larger working capital.
- Transferring Critical Human Knowledge
When people retired, their knowledge and know-how is lost, and new employees must rely on procedural information that is often buried under hundreds of thousands of pages of documentation. IBM used its Watson AI technology to create a digital assistant that could help all less-experienced employees during their day-to-day work. The AI was fed with over 600,000 pages of documentation, reports, and even correspondence about drilling operations and is now able to provide expert-level answers to all the most common types of questions asked by technicians. (IBM)
- Detecting Natural Oil Seeps with Smart Underwater Robots
Oil from underwater seeps can damage the environment, both because they can release methane and other light hydrocarbons in the atmosphere and because the slicks can form tarballs and mats that may eventually come ashore. Tapping these seeps, on the other hand, can both protect the ecosystem and provide oil & gas operators with a profitable source of energy.
Conclusion
There are a lot of other interesting applications of AI in the oil & gas sector that still need to be discovered and developed. But most of them are not specific products to this industry. Mostly, simulation and optimization techniques, predictive methods, and data analysis are getting used in this sector. If you want to use AI, there is still time for it.
I think the oil(petroleum) industry will gradually start to leave its place for renewable energy sources. Therefore, maybe the application area will gradually decrease, but we will still be committed to this sector for a long time. As a result, artificial intelligence applications will improve themselves according to the changing conditions. We will often use artificial intelligence to save money and time on various issues and for nature-friendly studies. What do you think?
