AI in Oil and Gas Industry

0
227

“The oil and gas industry is facing a rapidly changing digital landscape that requires cutting-edge technologies to cultivate growth and success.”

Per Harald Kongelf, Improvement senior vice president at Aker BP.

Artificial intelligence had widely spread in the last decades and invaded all major industries in a short period of time since its inception. The energy industry, however, has only recently begun integrating it.

The following article discusses artificial intelligence, its two subfields used in the oil and gas supply chain and their beneficial applications.

Artificial intelligence is the theory and development of computer systems able to perform tasks normally requiring human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages [1]. It is subdivided into twelve main subfields, two of which are of particular importance to the oil and gas industries due to their relevance, which are Machine learning and Data Science.

Machine learning provides systems with the ability to automatically learn and improve from experience without being explicitly programmed. it focuses on the development of computer programs that can access data and use it to learn for themselves [2].

Data science, plainly put, is the study of where information comes from, what it represents and how it can be turned into a valuable resource in the creation of business and IT strategies. Mining large amounts of structured and unstructured data to identify patterns can help an organization rein in costs, increase efficiencies, recognize new market opportunities and increase the organization’s competitive advantage [3].

These two subdomains are tightly linked to oil and gas compared to the rest because they offer optimizations and precision in upstream and midstream oil and gas phases. Below are some examples of the application of machine learning and data science in the oil and gas supply chain:

  • Geophysical evaluation and design

Machine learning can be implemented to construct accurate geological models that enable sifting through noise and signals of seismic data and obtain precise information about the surface and allows prediction of what lays beneath before drilling, using high-performance computers and modern analysis and modeling software.

If ever embedded, this technology is assumed to reduce the number of dry wellheads by 10%. One actual example of this application is the cloud-based geoscience platform “Sandy” developed by the Houston-based technology start-up Belmont Technology. The platform allows interpreting geology, geophysics, historic and reservoir projects information, creating unique “knowledge-graphs. In January 2019 BP invested in this start-up to boost the company’s AI potential.

  1. Drilling Operations

By summing up all factors related to the drilling phase, data scientists will be able to create a complex model that enables effective optimization of drilling operations through learning from the collected data for a more accurate workflow. Besides, it will automate these operations and reduce the workers who carry out complex tasks hence being prone to erroneous outcomes. Implementing this technology will reduce both the costs and the time needed to accomplish this operation. In early 2017, Anadarko Petroleum Corporation fast-tracked the development of an in-house real-time data analytics system to optimize the drilling process on their wells [4].

  1. Maintenance

Machine learning’s main role in maintenance is to predict errors, possibly, before their occurrence at every stage of the supply chain and precisely detect the faults in the equipment, an example of this is the Industrial Internet of the Things (IIoT) platform, Predix, created by General Electric Digital which provides an analytics library and framework for predictive anomaly detection. Such models will surely improve productivity by reducing the time spent on error detection and maintenance.

  1. Decision making and Energy Purchases Customer Market

Employing deep learning, natural language processing, and computer vision can help develop predictive models like SAS Enterprise Miner software that provides descriptive modeling based on all the data collected which helps industries make better decisions and give clearer insights about the companies future plans.

The applications of Artificial intelligence don’t narrow down to these few examples only, they span a vast set of other technologies and platforms.

Major oil and gas companies always seek innovation and many are already deploying AI solutions, resulting in an exponential growth to their income and productivity which must certainly serve as a lesson and a success story for other corporations to take this major leap towards fully digitizing thisindustry.

Manel Bouazza

References:

  1. : Artifical Intelligence, Oxford dictionary.
  2. : What is Machine Learning? 
  3. : What is Data Science? 
  4. : Anadarko fast-tracks development, implementation of real-time data analytics system to optimize drilling process.

 

LEAVE A REPLY

Please enter your comment!
Please enter your name here