Category Archives: Artificial Intelligence

Why it’s time for Petroleum Geologists and Engineers to move away from generic data scientists

Leave a reply

The industry has finally warmed up to Artificial Intelligence (AI) technologies. This is good news. AI technologies are a great opportunity for operators to increase their efficiency and boost their competitive advantage and safe operations. And, in fact, many have already done just that.

But not every company will deploy AI at the same pace or with the same capabilities. Skills to build meaningful and impactful AI models are still scarce. Also, the people who understand the earth’s and hydrocarbon’s physics are not always the same ones who know how to use “Data Science (DS) and AI” tools. For that reason, some Exploration & Production (E&P)  companies opt for a centralized DS team that has skills in statistics and building AI models. In this centralized model, engineers’ “exploratory” and “what-if” analyses go to a central team to build a predictive model for their hypothesis.

This process is not ideal. It takes longer to reach to an acceptable and final model even when a request is prioritized (long cycle time).  How can you speed it up? While a central DS team may seem to be the only option at the moment, I would argue that eventually those who understand the physics should be the ones building and confirming their own AI and Machine Learning (ML) models. I argue, some of brightest engineering and geoscience ideas are yet to come out to industry, once they learn the tools.

Why Change?

For some petro-proefessionals, learning a new coding language (python for example) is not fun. After all if they wanted to be coders they would be in a different place. We have been there before. The situation is analogous with the old DOS commands days, which were the domain of specialists and enthusiasts. But as soon as software (like Microsoft Office) came out with Graphical User Interface (GUI) – where we clicked and typed a natural language – then the engineers, geologists and the whole world came onboard. Well, AI and ML tools are making that turn and do not require any coding. 

It was no longer a stretch to get petroleum engineers to use Excel spreadsheets, then and it is an expectation now. We should have the same expection for them using advanced analytics, AI and ML tools. 

 

Some suggestions

I leave you with some tips to reach that goal (if you agree with the above premises);

  • Look for advanced analytics tools with graphical user interfaces (as opposed to those that require you learn a new language like python). I like this software’s interface Data Robot, www.datarobot.com
  • Make sure your software can easily connect to data sources – it’s not enough to have a software with good GUI.
  • Automate the flow of information and facilitate access to information – this is key to success, especially for data warehouses/ lakes or hubs.
  • Make sure your users are trained in advanced analytics principles and on the software.  At the very least, engineers should be able to build some basic predictive models.
  • Consider cloud data warehouses and tools to get the power to run large datasets such as logs and seismic. We are following Snowflake https://www.snowflake.com  and MEME SQL https://www.memsql.com/

Certis consults and delivers data services. We are systems agnostic. We focus on helping oil and gas clients set up their backbone data and processes. Find out more about our services

How To Turbocharge Oil & Gas Analyses With Machine Learning and The Right EIM Foundation

Leave a reply

It is generally accepted that good analysis of oil and gas data results in actionable insights, which in turn leads to better profits and growth. With today’s advancements in technology and processing power, more data and better analysis are easily achievable but will require the right EIM (Enterprise Information Management)  foundation to make “all” data available and “analyses-ready”.

The evidence of those analytics are clear and ubiquitous. In an article in JPT (Journal of Petroleum Technology) by Stephen Rassenfoss, “Four Answers To the Question: What Can I Learn From Analytics?”, Devon Energy concludes it is possible to increase production by 25% by drilling the lateral toe-up in Cana-Woodford Shale. Range Resources, responding to a different question and with Machine Learning (ML) analysis, concluded more production in the Marcellus is associated with wells fracked with as much sand volume as the reservoir can handle.

All Data All The Time = More Studies More Return

Looking closer at the article, both studies were based on a relatively small data set; Devon Energy and Range Resources only used 300 and 156 wells respectively.  Both companies stated that a larger data set would help their respective studies. So, why some studies rely on a small population of wells when there are thousands more that could have been included to reach a deeper understanding.

While the answer depends on the study itself, we find two key data”preparation” problems that may contribute to the answer a) data findability/ availability b) data readiness for analyses. In some E&P companies, data preparation can consume over 50% of total study’s time. This is where I believe EIM can make a difference by taking a proactive role.

 Three Strategic EIM Initiatives to Turbocharge Your Organization’s Analytics

Information preparation for exploratory analytics like the above, require Oil and Gas companies to embrace a new paradigm in EIM. The traditional “data management” has its applications but can be rigid and limiting because it requires predefined schemas.

We share our favorite three EIM strategic initiatives to deliver  more, trustworthy and analyses-ready information:

  • Strategic and Selective Information Governance Program – A strong data governance model ensures data can be trusted, correlated and integrated, this is a foundational step and will take standardizing, and mastering key entities and attributes.   Tip: key enabling technology is Master Data Management (MDM)
  •  Multi-Stream Data Correlation – Together with the MDM, “Big Data” technology and processes enable the inclusion and further correlation of data from a variety of streams, without the prejudice of predefined data schema.
  • Collaborative Process and Partnership – From years of lessons learned, we’ve noticed that none of the above will move the needle much at all if implemented in isolation. A collaborative process with the sole purpose of fostering a close partnership between IM engineers/ architects, data scientists, and the business, is what differentiates success from failure. As the organization finds new “nuggets of insights,” the EIM team’s role is to put the necessary structure in place to capture the required data systematically and then infiltrate it into the organization’s DNA.

New analytics are positively changing how we produce and manage oil and gas fields. Companies that invest in getting their EIM foundation right will lead the race among its competition.

Disclosure:

For help on defining and implementing EIM strategy please contact us.
With Petroleum Engineers, Geoscientist, Data Scientists and Enterprise Information Architects on the Certis team, we help companies design and implement EIM solutions that support their business goals. for more information on our services please email us at info@certisinc.com.