IN PRACTICE
Sensors Driven by Machine Learning Sniff Out Gas Leaks
A new study confirms the success of a natural-gas leak-detection tool pioneered by Los Alamos National Laboratory scientists that uses sensors and machine learning to locate leak points at oil and gas fields, promising new automatic, affordable sampling across a vast natural gas infrastructure.
Neural Networks Help Classify Reservoirs by Recognizing Cuttings Lithologies
Advances during the past decade in using convolutional neural networks for visual recognition of discriminately different objects means that now object recognition can be achieved to a significant extent.
Machine-Learning-Assisted Approach Analyzes Slug-Flow Root Cause
The complete paper discusses the successful application of a data-driven approach to analyze production data and identify root causes of slugging in a subsea production system on the Norwegian Continental Shelf.
Equinor Shares Data From Northern Lights Well
The Northern Lights project will disclose data sets from the confirmation Well 31/5-7 Eos drilled in the North Sea and completed earlier this year.
Machine-Learning Image Recognition Enhances Rock Classification
Automated image-processing algorithms can improve the quality and speed in classifying the morphology of heterogeneous carbonate rock. Several commercial products have produced petrophysical properties from 2D images and, to a lesser extent, from 3D images.
Machine-Learning Approach Determines Spatial Variation in Shale Decline Curves
The complete paper describes an automated machine-learning approach to determine the spatial variation in decline type curves for shale gas production, based on existing data of production, completion, and geological parameters.
Compositional Simulation, Artificial Intelligence Optimize Water Injection
The complete paper discusses optimization of a development plan involving low-salinity water injection.
Johan Sverdrup’s Digital Operations Drive Efficiency, Safety
The complete paper describes the development of the “digital field worker” at Johan Sverdrup, an initiative that has changed the approach toward not only construction and completion but also operations.
A Digital Approach to Reducing Human Error
As companies begin to embrace the concepts of digitalization and big data, the main challenge remains: How do we make a step change in reducing human error in heavily paper-based operating and maintenance procedures?
Saving Lives With Statistics: An Introduction to Data Science in Workplace Safety
Recent advances in data technology and machine learning have disrupted many businesses and processes and can lead to a new paradigm in workplace safety as well. This case study demonstrates the application of data science and predictive analytics to aid the health, safety, and environment function.
Using a Digital Twin in Predictive Maintenance
Often it is too difficult to create the fault conditions necessary for training a predictive maintenance algorithm on the actual machine. A digital twin generates simulated failure data, which can then be used to design a fault-detection algorithm.
Developing Technologies Can Lower Subsea Tieback Cost
The traditional subsea tieback model is evolving, supported by advances in flow assurance that allow tiebacks over much longer distances and by the introduction of new technologies that increase overall cost effectiveness.
Integration of Formation Evaluation Data Overcomes Offshore Coring Challenges
A well was drilled into a prospective unconventional mudstone play offshore Norway. Two of five coring runs were successful while the rest yielded little to no core recovery. Subsequent investigation of the core substantiated that the coring issues largely had natural causes.
Application of Multizone Water Injection Downhole Flow Control Completions With Fiber-Optic Surveillance
A multizone water-injection project has ultimately proved a method of using intelligent completion interval-control valves in place of traditional sand-control completions in soft sand reservoirs.
Adaptive Drilling Application Uses AI To Enhance On-Bottom Drilling Performance
An intelligent drilling optimization application performs as an adaptive autodriller. In the Marcellus Shale, ROP improved 61% and 39% and drilling performance, measured as hours on bottom, improved 25%.
Incorporating Constraints Improves Least-Squares Multiwell Deconvolution
In the complete paper, the authors reduce nonuniqueness and ensure physically feasible results in multiwell deconvolution by incorporating constraints and knowledge to methodology already established in the literature.
Spatiotemporal Clustering-Based Formulation Aids Multiscale Modeling
In the complete paper, a novel hybrid approach is presented in which a physics-based nonlocal modeling framework is coupled with data-driven clustering techniques to provide a fast and accurate multiscale modeling of compartmentalized reservoirs.
Learnings Applied to Reservoir Simulation of Unconventional Plays
In the complete paper, the authors revisit fundamental concepts of reservoir simulation in unconventional reservoirs and summarize several examples that form part of an archive of lessons learned.
SwRl Uses AI To Detect, Quantify Small Methane Leaks
Machine learning enables fast, cost-effective, and accurate methane emissions detection in remote areas.
Multiple-Source Data Provide Insight Into Hydraulic Fracture Geometries
The complete paper demonstrates the benefits of honoring data measurements from a multitude of potential sources to help engineers do a better job of including more diagnostics into routine operations to provide additional insight and result in improved models and completion designs.
Advancing Production Flow Profiling With Subatomic Fingerprints and Big-Data Analytics
This paper describes a smart-tracer-portfolio testing and design solution for multistage hydraulic fracturing that will, write the authors, enable operators to reduce operating cost significantly and optimize production in shale wells.
Artificial Intelligence Optimizes Oil and Gas Production
An AI-based application enabled operators to preempt ESP failures while optimizing production.
Machine Learning and Artificial Intelligence Complement Condition Monitoring
Time-stamped data anomalies can lead to more-accurate identification and faster diagnosis.
Deep-Learning Techniques Classify Cuttings Volume of Shale Shakers
A real-time deep-learning model is proposed to classify the volume of cuttings from a shale shaker on an offshore drilling rig by analyzing the real-time monitoring video stream.
Intelligent Completion Installations Instrumental in Brazilian Presalt Development
The complete paper presents a discussion of the use of intelligent well completion in Santos Basin Presalt Cluster wells.
Fatigue Prediction for Extended Riser Life and Improved Vessel-Response Analysis
This paper presents a fatigue-prediction methodology designed to extend the life of unbonded flexible risers and improve the accuracy of floating production, storage, and offloading vessel response analysis.
Artificial Intelligence, 3D Scanning Being Used To Improve Safety at Oil and Gas Sites
AltaML has announced a partnership with engineering and design firm Kleinfelder in which the two companies will pair 3D reality scans of facilities with artificial intelligence to look for potential problems and risks.
Researchers Are Improving Resolution in 3D Data Collected by Drones
Researchers with the National Center for Airborne Laser Mapping at the University of Houston are creating a set of algorithms that would allow users to more-precisely align data sets collected at different times and reliably estimate changes between images captured at different times.
Just How Much Energy Will Edge Data Centers Consume?
An estimate says data centers, including edge sites, will soon use four times the energy all data centers used in 2018. Can it be true?
Rapid Forecast Calibration Using Nonlinear Simulation Regression With Localization
The industry increasingly relies on forecasts from reservoir models for reservoir management and decision making. However, because forecasts from reservoir models carry large uncertainties, calibrating them as soon as data come in is crucial.
Well-Completion System Supported by Machine Learning Maximizes Asset Value
In this paper, the authors introduce a new technology installed permanently on the well completion and addressed to real-time reservoir fluid mapping through time-lapse electromagnetic tomography during production or injection.
A Drilling Automation Idea a Driller Could Appreciate
A group of people who really care how drillers code the memos added to the daily drilling report is the data scientists—who find that the coded tags do not match the activity. A program that helps drillers code is one of three technologies featured in a JPT series on drilling measurement innovation.
Hyperspectral Imaging and Artificial Intelligence Combine To Augment Detection of Methane Leaks
A system proposed by researchers at the University of California, Santa Barbara, uses hyperspectral imaging and machine learning to detect the specific wavelength of methane emissions.
Egyptian Petroleum Ministry, Schlumberger Introduce Subsurface Digitizing Platform
Egypt Upstream Gateway, a national project for digitizing subsurface information and delivering a digital subsurface platform, will build on Schlumberger’s GAIA digital subsurface platform.
Meet Spot, the Quadruped Robot for Offshore Inspections
Aker BP showcased the Spot robot recently. Spot will be part of the company's initiative that will explore how robotics systems can be used to make offshore operations safer.
Eni Unveils New Supercomputing System
The company claims the supercomputer, known as HPC5, is the world’s most powerful for industrial use.
Fugro Wins Contest With Machine-Learning Model for Pile-Driving Prediction
Using the supplied data set of cone penetration test results, competing teams had to predict the number of hammer blows required to drive the pile a given unit of depth in the North Sea.
Real-Time Data From Wired Drillpipe Leads to Improvement in Drilling Performance
This paper shows how high-frequency, real-time drilling data from wired drillpipe has helped optimization of drilling performance and achievement of additional improvements in the New Mexico Delaware Basin.
Satellite Service Provider Offers Free Visualization of Methane Emissions
GHGSat announced a new service for visualizing greenhouse-gas emissions. The interactive online resource will be freely available and will be formally launched during COP26 in November.
Heavy-Oil Steamflood Validates Machine-Learning-Assisted Model
This paper updates a previous case study and presents the results of actual implementation of an optimized steam-injection plan based on the model framework.
Artificial Intelligence Transforms Offshore Analog Fields Into Digital Fields
This paper details how artificial intelligence was used to capture analog field-gauge data with a dramatic reduction of cost and an increase in reliability.
Field Trial of Cloud-Connected Wireless Completion System
This paper describes the development and field trials of a cloud-connected, wireless intelligent completion system that enables long-term monitoring and interval control to enhance production management by connecting the user wirelessly from the desktop to downhole inflow-control valves.
Remote Sensing Imagery Improves Safety and Logistics of Arctic Operations
Many forms of remote sensing imagery can be used, along with data sets and the resultant products, to improve the efficiency and safety of upstream oil and gas operations on the North Slope of Alaska.
Machine Learning Analysis Based on Big Data for Eagle Ford Shale
This paper investigates the most important independent variables, including petrophysics and completion parameters, to estimate ultimate recovery with a machine-learning algorithm. A novel machine-learning model based on random forest regression is introduced to predict estimated ultimate recovery.
Peer-Reviewed Journal Continues Dive Into Data Analytics
The December issue of the peer-reviewed SPE Journal includes a spotlight section on data analytics, presenting paper SPE 195698, “Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm.”
Company Launches World’s First Live 3D Subsea Streaming Technology
Rovco’s stereo camera technology system sends images and 3D models of assets from the seabed to computer browsers in any location, offering users instantaneous access to information during inspection or construction.
Engineering Diagram Processing Featured in Worley and Arundo Global Hub for Advanced Analytics
Using deep-learning and computer-vision techniques, the software recognizes all instances of specific instruments, valves, lines, and other features in a P&I diagram in seconds.
Microsoft Announces AI Center of Excellence for Energy in UAE
Microsoft announced that it will open an AI Center of Excellence for Energy in the United Arab Emirates—a global first for the company—to empower organizations in the industry in accelerating digital transformation and equipping their workforce with AI skills.
How "the Couch" Is Supporting ExxonMobil's Sprint to Digital Transformation
The company is relying on DevOps and agile to hit a bold growth goal by 2025: doubling profits without changing prices.
Louisiana Petrochemical Plants Look to Drones, Handheld Devices, Virtual Reality Technology
ExxonMobil is expanding its Baton Rouge polyolefins plant in a $500 million investment and tapped King Crow Studios, along with 3D Media and Pixel Dash, for the training effort—a sign of an emerging collaboration in Louisiana between tech-driven startups and the industrial sector.
Aker BP Uses Data Intelligently To Cut Planned Maintenance in Half
The company used a maintenance optimization plan from Lloyd's Register for the centrifugal pumps and fire and gas detectors on a floating production, storage, and offloading vessel in the Norwegian Sea.
Bandwidth of Nanotechnology in the Oil Field Widens
Nanotechnology has great potential to reduce cost, increase production, and even improve the sustainability of E&P operations. But, where do we stand in terms of potential vs. reality? And, is the industry ready and willing to use the technology?
Data-Driven Analytics Provide Novel Approach to Performance Diagnosis
This work describes a heuristic approach combining mathematical modeling and associated data-driven work flows for estimating reservoir-pressure surfaces through space and time using measured data.
Artificial Intelligence Improves Seismic-Image Reconstruction
Seismic imaging provides vital tools for the exploration of potential hydrocarbon reserves and subsequent production-planning activities. The acquisition of high-resolution, regularly sampled seismic data may be hindered by physical or financial constraints.
Data-Driven Tool Uses Amplitude-Based Statistics To Identify Seismic Fractures
The authors present a novel data-driven tool for fast fracture identification in post-stack seismic data sets.
Emerson Accelerates Digital Transformation of Oil and Gas Industry With Cloud-Hosted Software Suite on Microsoft Azure
The engineering and technology company announced its entire exploration and production software suite is now available on the cloud, enabling oil and gas companies to take advantage of digital technologies securely and to model and optimize production better.
Natural Language Processing Enables Better Operational Risk Management
Equinor is working on a natural language processing tool that could combine data sources and help planners anticipate the issues that affect onsite operational safety.
Permian Space Race: Satellites Become Latest Tool for Competitive Shale Play
At least a half dozen energy data firms are offering satellite imaging of the 75,000-sq-mile oil field to provide intelligence to energy companies on activities including the appearance of drilling pads and hydraulic fracturing ponds and the movements of drilling rigs and crews across the Permian.
Parallel Simulation and Cloud Computing Can Optimize Large-Scale Field Development
The complete paper discusses a study in which the authors propose a joint field-development and well-control-optimization work flow using high-performance parallel simulation and commercial cloud computing.
Gazprom Neft Develops Supercomputer To Simulate Siberian and Arctic Fields
The Russian company has built a computing cluster in St. Petersburg designed to generate digital twins of oil fields. The new distributed-computing system is capable of processing more than 100 gigabits per second, speeding up the digital-modeling process five-fold.
Establishing a Drone Business With the FAA's Part 107 in Oil and Gas
Drones have entered the oil and gas domain as a more comprehensive method of inspection—providing not only a flexible and cost-effective way to conduct inspections but also a data-intensive structure for inspecting assets in a nondestructive manner.
Machine Learning Can Make Mooring Safer and More Cost Effective
Concern has been growing in the oil and gas industry about the high frequency of mooring line failures. While physical tension sensors can be difficult and costly to maintain, machine learning has shown to be a more-accurate and less-costly method for structural integrity assessment.
Data Mining Effective for Casing-Failure Prediction and Prevention
This paper is part of an ongoing effort to minimize the likelihood of failure using data-mining and machine-learning algorithms.
Big Data vs. Diverse Data: Confidential Databases Lack Performance Benchmarks
A study by a real-time monitoring company showed that many coiled-tubing strings are retired with a lot of life left in them. It suggested companies could lower costs by using pipe for a longer time and could benefit from multicompany studies showing how their decisions compare to the competition.
Surface Drilling Data Can Help Optimize Fracture Treatment in Real Time
This paper presents a unique work flow that addresses in real time the challenges of perforation and fracture-treatment design while accounting for the lithologic and stress variability along the wellbore and its surroundings.
Digital Transformation Increases Value in an Omani Thermal EOR Asset
A thermal asset in Oman is characterized by a large-scale steam-drive/cyclic-steam-soak development project, underpinned by extensive data gathering.
Computational Model Predicts Breakdown Pressures in Unconventional Plays
This paper presents a newly developed model to predict the breakdown pressures in cased and perforated wells.
Artificial Intelligence Can Reduce ESP Failures
Electrical-submersible-pump (ESP) technology predominates available artificial-lift options. The risk of ESP failures can be reduced greatly with the right combination of advanced technologies, such as combining artificial intelligence with a cloud-based autonomous surveillance system.
Machine Learning Optimizes Duvernay Shale-Well Performance
This paper discusses how machine learning by use of multiple linear regression and a neural network was used to optimize completions and well designs in the Duvernay shale.
ABS Unveils Guide for Using Smart Technology in Marine and Offshore Industries
The first set of notations of its kind helps owners and operators qualify and use smart functions to manage asset health and performance.
$1 Million Gift From ConocoPhillips Will Enhance Data Science Offerings at University of Houston
Demand is growing at the University of Houston and others from students who want to study data science; from researchers who produce, interpret, or otherwise work with reams of data; and from industry, which needs a data science-savvy workforce.
GHGSat Readies Launch of Second Emissions-Monitoring Satellite
The new satellite will build on the success of the company's demonstration satellite Claire, which has performed over 2,500 observations of oil and gas facilities as well as other natural and industrial sources of carbon dioxide and methane.
Integrating Geomechanical Data Optimizes Completions Design
This paper demonstrates how engineers can take advantage of their most-detailed completions and geomechanical data by identifying trends arising from past detailed treatment analyses.
Digital Transformation Pushes Companies To Rethink How They Work
With new digital platforms and technologies driving the industry in the near future, organizations are examining the ways in which their established work flows may help or hinder their ability to adopt and adapt.
Oil Companies Must Learn To Share
Like a fast-declining oil well, the value of propriety software is short-lived. Technological advances drive down the value of programs, many of which were never unique.
Machine-Learning Approach Identifies Wolfcamp Reservoirs
This paper discusses a project with the objective of leveraging prestack and poststack seismic data in order to reconstruct 3D images of thin, discontinuous, oil-filled packstone pay facies of the Upper and Lower Wolfcamp formation.
How To Find the Right Data System for Equipment Inspections
Inspection data management system software can help companies bolster their mechanical integrity programs, but choosing the wrong software can have a lasting impact on a company’s operations. So, what goes into finding the right software for your needs?
Companies Are Failing in Their Efforts To Become Data-Driven
Leading corporations seem to be failing in their efforts to become data-driven. This is a central and alarming finding of NewVantage Partners’ 2019 Big Data and AI Executive Survey.
As Expectations Grow, Data Analytics Faces Hurdles
Expectations from data analytics in the upstream sector continue to evolve. Although the number and diversity of applications continue to increase, the adoption at the assetwide level faces well-known barriers and challenges.
Simulation Algorithm Benefits by Connecting Geostatistics With Unsupervised Learning
A new geostatistics modeling methodology that connects geostatistics and machine-learning methodologies, uses nonlinear topological mapping to reduce the original high-dimensional data space, and uses unsupervised-learning algorithms to bypass problems with supervised-learning algorithms.
Face-Detection Algorithm Handles Big Data To Help Identify Candidates for Restimulation
This paper demonstrates the viability of a production-data-classification approach adapted from real-time face detection for identifying restimulation candidates.
New Method for Predicting Production Boosts Accuracy for Carbonate Reservoirs
This paper proposes a new method of economic prediction on the basis of expert library and oilfield databases. The method takes into account geological factors and the effect of production factors on the economic prediction.
STAY CONNECTED
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.
ADVERTISEMENT
POPULAR NOW
ADVERTISEMENT
