Home

Machine Learning

29 Apr

2nd Edition: Geological Process-Based Forward Modeling AAPG Call For Abstracts Expires in 11 days

litutmMedium

View All Deadlines ...

Deep Learning/Machine Learning Technical Interest Group (TIG)

Explorer Emphasis Article By David Brown

2024 Energy Industry Forecasts and Trends to Watch

Analysts, consultants and government agencies have issued their outlook for oil and gas and the rest of the energy industry for 2024. This time around their confidence level is lower than usual, with significant unknowns in supply, demand and price. Here's what to expect and trends to watch.

Added on 01 February, 2024

Explorer Geophysical Corner By Aria Abubakar,Haibin Di,Sunil Manikani,Tao Zhao

How Deep Learning Can Accelerate Offshore Wind Farm Site Characterization

To achieve net-zero carbon emissions by 2050, the demand for renewable energy is increasing exponentially, with offshore wind farms as one potential area of investment. Offshore wind farm development requires effective mapping of near subsurface for turbine foundation design and construction, which faces many challenges related to seafloor topography mapping, shallow geohazard detection, structure interpretation and modeling, soil type analysis and geotechnical property estimation, among other considerations.

Added on 01 February, 2023

Explorer Geophysical Corner By Carolina Crovetto,Fabián Scazziota,Juan Moirano,Kurt Marfurt,Luis Vernengo,Ritesh Sharma,Satinder Chopra

Choice of Attributes for Unsupervised Seismic Facies Classification

With the increasing size of the seismic data volumes, machine learning applications have been found to accelerate the discrimination of seismic facies used in the identification of geologic patterns, defining stratigraphy and the direct indication of hydrocarbons. Many practitioners have demonstrated the application of dimensionality reduction tools such as principal component analysis and independent component analysis, or clustering techniques. Some of these are available in several commercial interpretation software packages.

Added on 01 November, 2022

Explorer Emphasis Article By David Brown

Geophysics Industry Shrinks as Tech Advances

Consider the geophysics sector of the industry a shrink-to-fit enterprise where misery might be starting to bring its own relief, and business is improving after recent years of financial ups and downs. With, admittedly, more downs than ups. Higher oil and gas prices this year have brought either a spark of enthusiasm or a glimmer of hope to many geophysical companies. And the technical side of geophysics has continued to advance strongly despite the business challenges.

Added on 01 October, 2022

Explorer Geophysical Corner By David Lubo-Robles,Deepak Devegowda,Heather Bedle,Kurt Marfurt,Matthew Pranter,Vikram Jayaram

How Humans and Computers Can Distinguish Seismic Facies

Some aspects of seismic interpretation, such as picking horizons and well-imaged faults, can be easily explained to a new interpreter. Other aspects, such as recognizing carbonate buildups, karst collapse, mass transport processes or volcanic intrusions, require not only an understanding of the underlying geologic processes, but also an understanding of their 3-D seismic data response. Although an experienced interpreter might be adept in using seismic data to map each of these features, they might also be challenged in explaining to the novice interpreter in a quantitative manner how they constructed their map or geobody.

Added on 01 September, 2022

Learn! Blog By Susan Nash

Smart Geosteering Continues to Break New Ground

Geosteering innovations continue to have dramatic breakthroughs in accuracy, efficiency, and real-time monitoring capabilities, thanks to pioneering work in analytics with new algorithms and approaches to machine learning. Welcome to an interview with Hugh Winkler, who will also be presenting at AAPG's U-Pitch New Technology Showcase, at IMAGE.

Added on 17 August, 2022

Explorer Geophysical Corner By Alexandro Vera-Arroyo,Heather Bedle

Data Conditioning Tools for Preservation of Structure and Stratigraphy

Data conditioning tools are necessary to improve seismic interpretation, which is particularly important when examining legacy data. The tools typically adopted for the purpose are structure-oriented filtering and random noise suppression. While these methods can help improve structural or stratigraphic interpretations, they can also impact amplitude anomalies if they are not done with care, which can present problems when examining seismic data for direct hydrocarbon indicators. The examples presented herein demonstrate the advantages and disadvantages associated with these data conditioning tools.

Added on 01 August, 2022

Explorer Emphasis Article By David Brown

A View to Innovation

This year’s International Meeting for Applied Geoscience and Energy, beginning August 28 in Houston, doesn’t have a single, overarching theme. But one concept keeps popping up again and again: Innovation. AAPG and the Society of Exploration Geophysicists, in conjunction with SEPM, are hosts for the second annual IMAGE meeting. It’s designed as a broad-interest event, with 30 key topic areas ranging – alphabetically – from acquisition and survey design to structure, tectonics and geomechanics. As an AAPG/SEG-sponsored event, IMAGE will include several sessions related to geological analysis, imaging and interpretation.

Added on 01 August, 2022

Learn! Blog By Susan Nash

Wellbore Stability Above All: Interview with Cory Fehr, Integrity Insitu

As drilling conditions evolve with new technologies, wellbore stability is more important than ever. Welcome to an interview with Cory Fehr, Integrity Insitu. Cory and his team have invented a tool that can conduct downhole tests to assure wellbore stability and integrity.

Added on 07 July, 2022

Explorer Geophysical Corner By Diana Salazar-Florez,Heather Bedle

The Importance of Parameterization in Machine Learning

It is well known that machine learning is based on complex statistics and programming, which for most of us, are not straightforward. When it comes to choosing the best technique, either supervised or unsupervised, the decision might not be easy and sometimes may even be overwhelming. Where do you even begin? Luckily, much research has been done recently to help geologists find an ideal starting algorithm, or the best machine-learning package. Here we discuss how just focusing on your choice of parameterization in a given machine-learning algorithm is one easy way to obtain better results without having to switch from technique to technique.

Added on 01 July, 2022

Webinar By Sunil Garg

London, England

Wednesday, 1 July 2020, 12:00 p.m.–1:00 p.m.

Machine Learning Workflow

This presentation and demonstration will focus on a machine learning workflow in the upstream Oil and Gas domain to predict formation tops by applying artificial intelligence and machine learning techniques to learn the well logs signatures. This deep learning model provides high quality predictions to aid the geologists in picking lithology markers consistently and in an accelerated fashion thus boosting their operational efficiency. The self-learning model, which is a unique differentiator of dataVediK and encompasses the detection of outliers and data quality issues and their subsequent validation and suggested corrections to improve the quality of data in an automated fashion during the model training process. The demo will then showcase a real-time drilling solution built using this ML model, whereby the formation tops are predicted, and the structural model is updated automatically as the GR log is acquired.

Added on 07 July, 2020

Webinar By Adrien Bisset

Virtual Webinar

Monday, 9 November 2020, 12:00 p.m.–1:00 p.m.

An A.I. Augment Information System Rooted in Earth Science

Belmont develops Sandy. An AI accelerated platform dedicated to identifying risks and opportunities by fusing subjective human interpretations within an objective digital representation of the world. Sandy can make sense of a large corpus of information, automatically organising the knowledge it contains and making it ready for your daily utilisation to build a solid cognitive foundation of your projects. Discover how in this talk.

Added on 05 November, 2020

Webinar By Chad Hammond,David Fosberg,Hugh Winkler,Larry R. Davis,Susan Nash

Virtual Webinar

Wednesday, 24 June 2020, 7:00 p.m.–8:30 p.m.

Pivoting Week 8: New Directions in Automation

Join us for the 'New Directions in Automation' webminar. Where the opportunities are now, and how to pivot and take advantage of them. Webinar will be presented via Zoom 7:00pm to 8:30pm CDT, 24 June 2020.

Added on 15 June, 2020

Webinar By Suri Bhat

Virtual Webinar

Wednesday, 28 October 2020, 12:00 p.m.–1:00 p.m.

Utilize and Exploit Data Remotely Using the Cloud and Deep Learning

There are many studies that talk about the economies of scale associated to cloud storage that make it so cheap. Yet oil and gas companies managing petabytes of seismic data are not jumping on the cloud storage bandwagon. In this talk, Suri Bhat, Vice President of Sales and Marketing at Bluware, will explore why moving petabytes of seismic data to the cloud is difficult. He will share some of the true costs of managing large data sets in the cloud and why it doesn’t add significant business value. In the same way that lifting and shifting legacy tools and services to the cloud yields little value, moving seismic data to the cloud also yields little value. It isn’t until applications, workflows and even the data storage formats are re-engineered that real business value and even cost saving can be found. He will explore how this is possible today with open file formats. Webinar presented via Zoom on 28 October 2020 at 12:00 London time (UTC-0)

Added on 14 October, 2020

View All Online Training ...

DL Abstract By Shane Prochnow

Subsurface Machine Learning Approaches at Hydrocarbon Recovery and Resource Forecasting for Unconventional Reservoir Systems

This presentation is a survey of subsurface machine learning concepts that have been formulated for unconventional asset development, described in the literature, and subsequently patented. Operators that utilize similar subsurface machine learning workflows and other data modelling techniques enjoy a competitive advantage at optimizing the development of unconventional plays.

Request a visit from Shane Prochnow!

Added on 14 September, 2023

Machine Learning

Other Interests

See Also ...

STAY CONNECTED: