Now is the time…..
Oil and Gas is no stranger to Digital. The fact is, Digital fields have been in existence for some time in many large companies. However, with the current glut that the Oil Industry is in, there is a much stronger business case to leverage the data generated from the Digital infrastructure optimally.
Now is the perfect time for Oil and Gas companies to evaluate what are the opportunity areas that can be transformed by leveraging AI.
Remember this, leveraging AI does not mean that you end up replacing human expertise entirely with Artificial Intelligence. In most cases, AI will augment natural intelligence to accelerate analysis or improve the quality of human decision making.
So let us explore some opportunity areas at a high level in this article.
The number of contracts and agreements in an average upstream Oil and gas org is in thousands. And the challenge is- they are all different, often with unique clauses, triggers, and riders. Since they are written by legal professionals, they are hard to understand, and knowing which of those contracts are approaching key milestones is next to impossible.
Leveraging Deep Learning, you can create centralized “Intelligent” contract hubs that can help you manage the legal aspect of your contracts. Imagine using AI to quickly find out which contracts need attention and why and to recommend actions to management.
Geological Data Interpretation
The main objective of the acquisition and analysis of geological and geophysical (G&G) data is the development of maps to identify areas favorable for the accumulation of hydrocarbons. The G&G data is analyzed to develop a basic knowledge of the geologic history of an area and its effects on hydrocarbon or strategic/critical minerals generation, distribution, and accumulation within the planning area.
The primary source of the data and information used by the Resource Evaluation Program are seismic surveys and wells logs acquired by the oil and gas industry.
As with many other fields, AI applied to seismic data can significantly change how geological interpretation is done. The way I see it, the future of geologic interpretation will be split into more routine, largely AI led work and high-end, complex, creative human-led work.
Figuring out optimal drilling location is another example of leveraging AI. Research shoes that engineers spend upwards of 40% of their time assembling the data to set up a drilling program (Woodside Petroleum study). They need mind boggling number of data points like:
- Data from prior drilling campaigns
- Actual costs
- Infrastructure costs
- Infrastructure locations
- Nearby well logs
- Seismic data
- Geological interpretation
AI can help expedite this significantly, leaving only “expert” level tasks to the engineers. AI can take over tasks like:
- BHA behavior monitoring
- ROP improvement by managing bitwear
- Frictional drag and load transfer monitoring
- DS vibrations monitoring
- Estimation of hole cleaning efficiency
- Thurst and drilling torque production
Field Service Management
A complex Oil company operations deals with thousnds of tickets from field companies for services rendered. Humans have to manually look at them, figur out which site they apply to, assign the right account codes etc. Compliance reporting for commodities like water and emissions generate its own share of document pile. Often, il companies end up employing more accouning and water-usage compliance teams than Geologists.
AI can help here by converting field tickets into accurate data, quickly and accurately. By using language processing to convert and interpret the text, Identify and extract the right data, feed that data into the right systems,and make decisions to accept or dispute charges.
Oil and Gas industry is no stranger to Digital Twin. If you visit a Geology/Reservoir team at an Oil and Gas company, you will see Digital, multidimensional simulation models and resource models.
One of the truly great breakthroughs afforded by digital innovation in oil and gas is the ability to create a fully functioning digital twin of just about any asset or of an entire business. These newer versions include many layers of data that work together to provide a rich, fully integrated, and analytically deep software version of the asset or business.
Advances in AI and technology now allow Oil and Gas companies to build an end to end Digital Twin that can leverage complex modeling of the real world using AI based algorithms, in real time. Data generated by these twins can also feed into Predictive Analytics algorithms for optimal asset utilization. Digital Twins can now be made more robust by including:
- The engineering content (diagrams, specifications, and configurations) that describes the physical asset in digital terms for the engineering disciplines
- The maintenance history (timing, procedures performed, parts installed, and installers) that provides insight into the ability of the asset to perform to its potential
- The physical constraints of the various assets (operating capacities, throughputs, and pressures) that restrict how each asset physically behaves; the operating parameters of the assets (input energies, consumables, by-products, and emissions), which constrain the asset’s performance;
- The financial aspects of the assets (fixed build cost and operating cost per unit) that yield the economics of the business
- The uncertain elements (customer demand, weather events, or supply disruption) that comprise the real-world conditions with which the business must cope.
Based on individual research and experience. Views expressed are my own.