Breaking News:

Asian Oil Imports Dropped in April

How Artificial Intelligence Could Help Transform The Oil Industry

While the oil and gas industry has had its share of ups and downs over the past decade, many financial institutions are banking on a very slow growth of oil prices in 2017. Though some believe that the efficiency gains that the oil industry can capture are quickly coming to an end, this sentiment is only capturing hard technology specifically related to oil and gas.

To help bring the O&G industry to the 21st century, technology from other industries needs to be incorporated, using many hard-earned years of expertise and different lines of thinking. Oilprice previously mentioned incorporating food industry technology to increase safety standards when fracking, but incorporating technology from the IT industry is something that the O&G industry as a whole can benefit from. Whether its neural networks, machine learning, fuzzy logic, case-based reasoning or expert systems, AI has the potential to transform the industry.

Upstream upstarts

When remote sensors are connected to wireless networks, data can be collected and centrally analysed from even the most exotic locations. According to the consulting firm McKinsey, there is $50 billion of savings and increased profits in the O&G supply chain to be had by adopting AI. As an example, using AI algorithms to more accurately sift through signals and noise in seismic data can decrease dry wellhead development by 10 percent. This type of technology was brought into the fortune 500 earlier this week when Intel acquired Nervana Systems, an Indian-American San Diego based startup, who was using this technology to increase operational efficiency in oil exploration.  Now with Intel's muscle, super-majors can look to have this technology implemented across the board.

Real-time, big data

Although the O&G industry has been using data to analyse downhole conditions, as the costs of implementation come down, these technologies are being used on smaller and smaller wells. These types of implementations can help provide early warning signals of problems before they happen.

When drilling a hole, machine learning software takes into consideration a plethora of different factors such as seismic vibrations, thermal gradients, and strata permeability, along with more traditional data such as pressure differentials. According to four-year old Seattle-based startup Seeq, this helps to drive drilling decisions such as direction and speed in real time to optimize the drilling operation, and can predict failure of equipment such as semi-submersible pumps (ESPs) to lower unplanned downtime and equipment costs.

Machines doing the learning

On a macro scale, deep machine learning can help to increase the awareness of macroeconomic trends to drive investment decisions in exploration and production (E&P). Economic conditions and even weather patterns can be taken into consideration to determine where investments should take place, as well as the intensity of production. Companies like Kpler have been using geotracking of vessels to help operators make better decisions by using historical trends compared to current trajectories of energy vessels. This type of data can help to determine trends in the energy shipping industry. Related: Merrill Lynch Expects A 46% Jump In Oil Prices By June 2017

Fuzzy decisions

Fuzzy logic is an AI mechanism to drive decisions when data is incomplete or unreliable. If an algorithm is designed with a certain number of inputs, fuzzy logic can help overcome deficiencies when one or more sensors is providing spurious or inconsistent data. Fuzzy logic can also help with reservoir characterization, infill drilling, and well simulation where data needs to be extrapolated, or signals need to be gleaned from noise in the data.

Innovate or die

Today's O&G industry has been transformed by two downturns in the industry in one decade. Although the adoption of new hard technology such as directional drilling and hydraulic fracturing brought on fracking, the O&G industry needs to continue this trend in today's low-price market to survive. AI has the potential to differentiate between those that continue to thrive, and those that are left behind through complacency.

By Matt Slowikowski for Oilprice.com

More Top Reads From Oilprice.com:

Back to homepage


Loading ...

« Previous: Saudis Allow Foreign Investors to Buy Aramco IPO Shares

Next: 'Epic' Oil Rally Reverses On Diminishing Supply Outages »

Matt Slowikowski

Matt Slowikowski is the founder of the energy analytics blog enernomics.org. He specializes in economic analysis of the energy industry and energy projects. More