Companies Team Up To Bring Digital Twins for Oil and Gas to Life
To deliver digital twin technology for the upstream oil and gas markets, the Doris Group, Schneider Electric, and AVEVA are entering into a strategic partnership.
Video: Data-Driven Approach Adds Different Dimension
Morag Watson, senior vice president of digital science and engineering at BP, reveals how a data-driven approach can add a different dimension and where BP is on the digital curve.
ConocoPhillips Deploys Low-Code Tech To Boost Bottom Line
ConocoPhillips has deployed a low-code platform called Mendix to cut costs and increase efficiency, making it the first major oil and gas producer to use such technology across the company.
The Buzz About Drones: More Safety, Less Cost To Inspect FPSOs
A recent test proved the feasibility of using LiDAR on remote-controlled drones to create 3D maps of the inside of tanks, increasing the safety and efficiency of inspections.
3D Reality Capture Can Simplify Upgrades of Oil, Gas Facilities
Three-dimensional seismic technology helped unlock more subsurface secrets for oil and gas operators. Now, 3D technology can be used in scanning, a cutting-edge technology that engineers can use to plan upgrades to oil and gas assets virtually.
Artificial Intelligence Improves Business Outcomes for Offshore E&P
Despite streams of data being available on platforms about the condition of topside and drilling equipment, most experts agree that only a small fraction of such data is used. Whether for a fleet or single platform, AI can transform an offshore enterprise.
Open Standards Can Create a Safe Path to Digitalization
To keep pace with the digital age, the critical infrastructure and automation industries are looking beyond today’s control systems for new, common technologies to help balance requirements for uptime with digital technologies. Open standards can help.
Data Transformation: Standardization vs. Normalization
Increasing accuracy in models is often obtained through the first steps of data transformations. This guide explains the difference between the key feature-scaling methods of standardization and normalization and demonstrates when and how to apply each approach.
The DNA of AI Success: What It Looks Like and How to Get It
The AI journey starts with a single step, but too many companies take the wrong first step.
A Top Machine-Learning Algorithm Explained: Support Vector Machines
Support vector machines are powerful for solving regression and classification problems. You should have this approach in your machine-learning arsenal, and this article provides all the mathematics you need to know. It's not as hard you might think.
Sealed Wellbores and the Unlikely “Breakthrough” Behind Cheap, Accurate Fracture Diagnostics
When engineers went searching for clues on how fractures move beneath the surface, they expected to uncover important learnings. They did not know they were on the path to a new invention.
Multilevel Strategies Improve History Matching of Complex Reservoir Models
The complete paper explores the use of multilevel derivative-free optimization for history matching, with model properties described using principal component analysis (PCA) -based parameterization techniques.
Model Error Estimation Improves Forecasting
The results of the authors’ research showed promising benefits from the use of a systematic procedure of model diagnostics, model improvement, and model-error quantification during data assimilations.
New Modeling and Simulation Techniques Optimize Completion Design and Well Spacing
Proper lateral and vertical well spacing is critical for efficient development of unconventional reservoirs. Much research has focused on lateral well spacing but little on vertical spacing, which is challenging for stacked-bench plays such as the Permian Basin.
From Models of Galaxies to Atoms, Simple AI Shortcuts Speed Up Simulations by Billions of Times
Modeling immensely complex natural phenomena such as how subatomic particles interact or how atmospheric haze affects climate can take hours on even the fastest supercomputers. Now, work posted online shows how AI can easily produce emulators that can accelerate simulations by billions of times.
Machine-Learning-Based Early-Warning System Maintains Stable Production
This paper describes an accurate, three-step, machine-learning-based early warning system that has been used to monitor production and guide strategy in the Shengli field.
Dynamometer-Card Classification Uses Machine Learning
The complete paper explains the steps taken to improve surveillance of beam pumps using dynamometer-card data and machine-learning techniques and reviews lessons learned from executing the operator’s first artificial intelligence project.
List of Top 10 Artificial Intelligence, Machine Learning Research Articles Looks to the Future
Many predictions have been made about what advances are expected in the field of artificial intelligence and machine learning. This column reviews a “data set” based on what researchers were apparently studying at the turn of the decade to take a fresh glimpse into what might come to pass in 2020.
Artificial-Intelligence-Driven Timelines Help Optimize Well Life Cycle
This paper discusses how oil and gas companies are using a new generation of AI-driven applications powered by computational-knowledge graphs and AI algorithms to create a digital knowledge layer for oil and gas wells that provides a timeline of significant well events.
Addressing Challenges in Rig-Based Drilling Advisory System Deployment
The complete paper presents a process used to successfully implement a rig-based drilling advisory system (RDAS) across a mixed group of rig contractors.
Digitalization: Upstream's Silver Bullet?
The size of the digital prize is large. But deploying digital technologies at scale is proving harder than first thought. A report from Wood Mackenzie presents lessons from digitalization's early adopters.
How Digital Disruption Is Reshaping the Upstream Supply Chain
Digitalization is now a staple of boardrooms and plays a key role in corporate strategies. It brings equal measures of opportunity and threat. A report from Wood Mackenzie takes a look at how it will affect different categories of the supply chain.
Digital Twins Strive To Bring It All Together
Digital twins are powerful combinations of models and data that “age” throughout the lifecycle of an asset as they gather and integrate data from the field. This technology is a quantum leap from earlier efforts at modeling complex systems.
Digital Transformation: Who Should Lead?
Should that outside hotshot lead your digital transformation work or an insider who knows more about the culture and customers?
Stop Explaining Black Box Models and Use Interpretable Models Instead
The two main takeaways from this paper: First, it underscores the difference between explainability and interpretability and presents why the former may be problematic. Second, it provides some great pointers for creating truly interpretable models.
Why Scientists Need To Be Better at Data Visualization
The scientific literature is riddled with bad charts and graphs, leading to misunderstanding and worse. Avoiding design missteps can improve understanding of research.
Is Digitization the Fourth Stage of the Hydrocarbon Revolution?
The use of technology has helped ensure the profitability of the oil and gas industry despite a 50% fall in prices in 5 years. The key question, however, is whether the digital revolution can answer the sector’s biggest challenge: how to secure future production.
IIoT and Field Apps: The Future of the Industrial Connected Worker
Harnessing the industrial Internet of things has arguably become the biggest strategic priority for industrial companies in the race to gain competitive advantage through digital transformation.
Data Is Not the New Oil
Equating data to oil might make sense at first glance, given the data-driven success of tech companies, but the analogy breaks down as soon as you dig a little deeper.
Engineering + Data Science: The Missing Duo
One can almost guarantee that every engineer will consistently come into contact with data, no matter the engineer’s focus. Often, the data available to engineers is expansive; yet many are unequipped to handle it. Why then are data scientists not integrated into engineering teams at all levels?
Reshaping Business With Artificial Intelligence Means Closing the Gap Between Ambition and Action
Disruption from artificial intelligence (AI) is here, but many company leaders aren’t sure what to expect from AI or how it fits into their business model. Yet, with change coming at breakneck speed, the time to identify your company’s AI strategy is now.
Overcoming Deep Learning Stumbling Blocks
The sixth annual Deep Learning Summit in London saw industry leaders, academics, researchers, and innovative startups present the latest technological advancements and industry application methods in the field of deep learning.
Oil and Gas Transactions Require Special Cybersecurity Considerations
One of the foremost threats companies face today is that posed by cybercriminals, and the unique vulnerabilities of companies in the oil and gas sector create heightened cybersecurity risks for those pursuing transactions in the sector.
As Oil and Gas Data Multiply, so Do the Cybersecurity Threats
Saudi Aramco, BP, and Schlumberger pride themselves on staying at the forefront of digital technology development and deployment. But an equally daunting challenge for the industry heavyweights is keeping their ever-expanding digital systems secure.
Internet of Things Strategies for the Energy Sector
Whether thinking about managing oil and gas or other infrastructure facilities or considering industrial efficiency, you may be pondering how the Internet of things can be used. Forward-thinking strategies include not just staying on top of regulatory changes but also influencing them.
Why Data Visualization Is the Most Important Skill in a Data Analyst's Arsenal
Visually displaying data makes it much more accessible, and this is critical for identifying the weaknesses of an organization, accurately forecasting trading volumes and sale prices, and making the right business choices.
Statistical Modeling vs. Machine Learning: What’s the Difference?
At times, it may seem that machine learning can be performed without a sound statistical background, but this does not take in to account many difficult nuances. Code written to make machine learning easier does not negate the need for an in-depth understanding of the problem.
IBM Reveals New Hack To Infiltrate Corporate Networks
Nicknamed “warshipping,” the hacking technique allows remote infiltration of corporate networks by hiding a remote-controlled scanning device designed to penetrate a wireless network inside a package.
Photogrammetry Offers a Snapshot of a Digitalized Future
Photogrammetry—stitching together images to create photorealistic 3D models—can be part of a larger industrial digitalization strategy that aims to liberate data from its silos, connect it to other relevant information, and make it available to the workers who need it.
Hamiltonian Neural Networks Show Benefits Over Regular Neural Networks
Hamiltonian neural networks draw inspiration from Hamiltonian mechanics, a branch of physics concerned with conservation laws and invariances. By construction, these models learn conservation laws from data, revealing major advantages over regular neural networks on a variety of physics problems.
Random Forests Vs. Neural Networks: Which Is Better and When?
Random Forest and Neural Network are the two widely used machine-learning algorithms. What is the difference between the two approaches? When should one use Neural Network or Random Forest?
Katy, Texas, Is Now Home to One of the World’s Fastest Supercomputers
The 21st century oil and gas industry thrives on hardcore computing power, crunching data derived from seismic testing to find oil deep in the ground and below the sea. Now, an Australian company will fire up a digital behemoth in a data center near the Houston suburb.
Data Science vs. Decision Science
Data science and decision science are related but still separate fields, so, at some points, it might be hard to compare them directly. This article attempts to show the commonalities, differences, and specific features of data science and decision science.
Bias Can Cause Machine Learning To Stumble
Machine learning (ML) finds patterns in data. "AI bias" means that it might find the wrong patterns. Meanwhile, the mechanics of ML might make this hard to spot.
Data as Prior/Innate Knowledge for Deep Learning Models
Rapid advances in deep learning continue to demonstrate the significance of end-to-end training with no a priori knowledge. However, when models need to do forward prediction, most AI researchers agree that incorporating prior knowledge with end-to-end training can introduce better inductive bias.
The Path to Artificial Super Intelligence
Dubbed the technology of the decade, AI has been the catchphrase on every futurist’s tongue. From customer support chatbots to smart assistants, AI has begun to transform numerous industry verticals.
Souped-Up Search Engines Wrangle Drilling, Completions Data
Fed by big data loads from big operators, a university consortium and software firm are each working to make upstream data access as quick and easy as a Google search.
Is the Cloud Mature Enough for High-Performance Computing?
Data volumes are growing at an exponential rate. How can high-performance computing solutions help operators manage these volumes? Will faster, stronger processors and cloud computing solutions be the answer?
What Difference Does 99% Accuracy Make Over 95%? Not Much
Instinctively, we feel that greater accuracy is better and all else should be subjected to this overriding goal. This is not so. While there are a few tasks for which a change in the second decimal place in accuracy might actually matter, for most tasks, this improvement will be irrelevant.
Telling a Good Data Story Through Visualization
While the visual element is key, the core strategic component of data visualization is the ability to unlock the story in the data.
Digital Transformation Is Changing the Face of Visual Inspection
As we move to digitize our visual inspections with a variety of image-capture devices, fully understanding the strengths and limitations of the approach is important to move truly from a qualitative to a quantitative assessment with confidence.
Statistics: P Values Are Just the Tip of the Iceberg
Ridding science of shoddy statistics will require scrutiny of every step, not merely the last one.
Machine Learning vs. Data Science: What's the Difference?
When you think of “data science” and “machine learning,” do the two terms blur together? This article will clarify some important and often-overlooked distinctions between the two to help better focus learning and hiring.
Functional Data Engineering: A Modern Paradigm for Batch Data Processing
Batch data processing is extremely challenging. It’s time-consuming, brittle, and often unrewarding. This story explores how applying the functional programming paradigm to data engineering can bring clarity to the process.
Don't miss out on the latest technology delivered to your email monthly. Sign up for the Data Science and Digital Engineering newsletter. If you are not logged in, you will receive a confirmation email that you will need to click on to confirm you want to receive the newsletter.
07 August 2020
03 August 2020
03 August 2020