International

https://seg.zoom.us/webinar/register/WN_IkCzXT6aT8mE5qY_3YR0yg

Topic

Update structural Models in Real Time using Machine Learning

Description

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.

Time

Jun 25, 2020 08:00 AM in Central Time (US and Canada)

https://seg.zoom.us/webinar/register/WN_Fc-YD7ScSZevv-Nw4iN7xw

Topic

Simple Applications of Machine Learning in Subsurface Characterization

Description

Dr. Misra will present few case studies on the use of machine learning techniques. In the first case study, neural network models generate NMR T2 distribution in the absence of NMR logging tool. In the second case study, simple data-driven models generate compressional and shear travel time logs in the absence of sonic logging tool. In the third case study, machine learning assisted the segmentation of SEM images of shale samples. This segmentation method involves two steps, feature extraction from SEM images followed by random forest classification of each pixel in the SEM image. In the fourth case study, machine learning was used to process CT scan images to predict the subsurface geomechanical properties.

Time

May 28, 2020 08:00 AM in Central Time (US and Canada)

https://seg.zoom.us/webinar/register/WN_TfNBjh2dRBahnusg623fMQ

You can build your own models: Why you don't need to be scared of doing your own data science

Description

There are two ends of the "AI" spectrum that are often presented. On one end, AI is going to solve the world's problems one slide deck at a time. On the other, a PhD physicist will give you a "quick" run-through of a 4-hour deep learning with tensorflow in Python tutorial. In this session, we aim to land right in the middle of those two and provide a layman's view to getting started with data science and machine learning. Almost everyone has data and problems, but many don't have the expertise in technologies like Python or R to feel confident in getting started with machine learning. In this session, we will aim to help you better understand the concepts used in machine learning, how to set up problems, how to analyze and interpret your data, and finally, how to build models that can drive business value without ever needing to know Python or R.

Time

Apr 30, 2020 08:00 AM in Central Time (US and Canada)

https://seg.zoom.us/webinar/register/WN_EtdnImjCTFWdRc2teFvWIw

Topic

The Fundamentals of Microseismic Monitoring

Description

In this webinar, participants will be exposed to the fundamental concepts of microseismic acquisition, processing, and interpretation in unconventional reservoirs. Through understanding the fundamental concepts of earthquake seismology, the common pitfalls and best practices within the industry associated with this technology are discussed.

Time

Apr 22, 2020 12:00 PM in Central Time (US and Canada)

https://www.knowledgette.com/p/automating-seismic-data-analysis-and-inte...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1, Wednesday, April 22, 2020, 8 pm to 9 pm US Central Time Register Here

Session 2, Tuesday, May 12, 2020, 11 am to 12 pm US Central Time Register Here

Abstract:

Recent developments in artificial intelligence and machine learning can automate different tasks in data analysis. I will discuss the quest for automation by tracking the development of automatic picking algorithms, from velocity picking in seismic processing to horizon picking in seismic interpretation. We will search for the limits of automation to discover the distinguishing qualities that separate human geophysicists from machines.

The automatic picking algorithm follows the analogy between picking trajectories in images with variable intensities and tracking seismic rays in the subsurface with variable velocities. Picking trajectories from local similarity panels generated from time shifts provides an effective means for measuring local shifts between images, with practical applications in time-lapse and multicomponent image registration, matching seismic with well logs, and data compression using the seislet transform. In seismic interpretation, automatic picking finds additional application for tracking fault surfaces, salt boundaries, and other geologic features.

The power of automatic picking is further enhanced by novel deep learning algorithms. The deep learning approach can use a convolutional neural network trained on synthetically generated images to detect geologic features in real images with an unmatched level of performance in both efficiency and accuracy. The lessons to learn from these developments include not only the potential for automation, harvested through artificial neural networks and modern computing resources, but also the potential for human ingenuity, harvested through professional networks.

https://www.knowledgette.com/p/automating-seismic-data-analysis-and-inte...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1, Wednesday, April 22, 2020, 8 pm to 9 pm US Central Time Register Here

Session 2, Tuesday, May 12, 2020, 11 am to 12 pm US Central Time Register Here

Abstract:

Recent developments in artificial intelligence and machine learning can automate different tasks in data analysis. I will discuss the quest for automation by tracking the development of automatic picking algorithms, from velocity picking in seismic processing to horizon picking in seismic interpretation. We will search for the limits of automation to discover the distinguishing qualities that separate human geophysicists from machines.

The automatic picking algorithm follows the analogy between picking trajectories in images with variable intensities and tracking seismic rays in the subsurface with variable velocities. Picking trajectories from local similarity panels generated from time shifts provides an effective means for measuring local shifts between images, with practical applications in time-lapse and multicomponent image registration, matching seismic with well logs, and data compression using the seislet transform. In seismic interpretation, automatic picking finds additional application for tracking fault surfaces, salt boundaries, and other geologic features.

The power of automatic picking is further enhanced by novel deep learning algorithms. The deep learning approach can use a convolutional neural network trained on synthetically generated images to detect geologic features in real images with an unmatched level of performance in both efficiency and accuracy. The lessons to learn from these developments include not only the potential for automation, harvested through artificial neural networks and modern computing resources, but also the potential for human ingenuity, harvested through professional networks.

https://www.knowledgette.com/p/biogeophysics-exploring-earth-s-subsurfac...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1, Thursday, April 30, 2020, 11 am to 12 pm Eastern Daylight Time Register Here

Session 2, Monday, September 21, 2020, 4 pm to 5 pm Eastern Daylight Time Register Here

Abstract:

Microorganisms are found in almost every conceivable niche of the Earth from hydrothermal vents in the deep ocean basins to the cold subglacial lakes of ice sheets. As such, microorganisms have played an important role in transforming Earth systems (e.g., accelerating mineral weathering), global climate change, and mediating different biogeochemical cycles over most of Earth’s 4 billion history. In-situ microbial-rock interactions are dynamic and occur at both temporal and spatial scales that prove difficult to investigate at resolutions needed to fully understand them, thus necessitating the need for the development of noninvasive tools/sensors to interrogate these processes. Interestingly, these microbial-rock interactions modulate changes in physical properties in the rocks, generating measurable geophysical signatures that can be recorded with conventional geophysical sensors (e.g., seismic, magnetics, electromagnetics). The recognition of these microbial-catalyzed changes in geophysical signatures resulted in the development of biogeophysics: the study of the physical changes in earth materials catalyzed by microorganisms. In this presentation, I will provide examples of how geophysical tools are used to sense subsurface microbial activity, from cell growth and biofilm formation to biomineralization and biogeochemical cycling of metals to the monitoring of bioremediation and their use for investigating oilfield microbial processes and the search for life on other planets. Challenges and limitations also will be highlighted, and potential for future advancements in the field will be discussed.

https://www.knowledgette.com/p/biogeophysics-exploring-earth-s-subsurfac...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1, Thursday, April 30, 2020, 11 am to 12 pm Eastern Daylight Time Register Here

Session 2, Monday, September 21, 2020, 4 pm to 5 pm Eastern Daylight Time Register Here

Abstract:

Microorganisms are found in almost every conceivable niche of the Earth from hydrothermal vents in the deep ocean basins to the cold subglacial lakes of ice sheets. As such, microorganisms have played an important role in transforming Earth systems (e.g., accelerating mineral weathering), global climate change, and mediating different biogeochemical cycles over most of Earth’s 4 billion history. In-situ microbial-rock interactions are dynamic and occur at both temporal and spatial scales that prove difficult to investigate at resolutions needed to fully understand them, thus necessitating the need for the development of noninvasive tools/sensors to interrogate these processes. Interestingly, these microbial-rock interactions modulate changes in physical properties in the rocks, generating measurable geophysical signatures that can be recorded with conventional geophysical sensors (e.g., seismic, magnetics, electromagnetics). The recognition of these microbial-catalyzed changes in geophysical signatures resulted in the development of biogeophysics: the study of the physical changes in earth materials catalyzed by microorganisms. In this presentation, I will provide examples of how geophysical tools are used to sense subsurface microbial activity, from cell growth and biofilm formation to biomineralization and biogeochemical cycling of metals to the monitoring of bioremediation and their use for investigating oilfield microbial processes and the search for life on other planets. Challenges and limitations also will be highlighted, and potential for future advancements in the field will be discussed.

https://www.knowledgette.com/p/generalized-sampling-and-gradiometry-chan...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1: Monday, April 20, 2020, 4 pm to 5 pm Zurich time Register Here

Session 2: Tuesday, May 5, 2020, 4 pm to 5 pm Zurich time Register Here

Abstract:

Recording seismic data involves moving from a continuous signal to a discretized data representation. The rules governing sampling of bandlimited signals and their reconstruction were pioneered by Swedish-born mathematician Harry Nyquist who studied transmission of telegraph signals in limited bandwidth channels in the 1920s. Together with Claude Shannon among others, both at Bell laboratories, he laid the foundations of information theory. The Nyquist-Shannon sampling theorem states that a bandlimited signal can be perfectly reconstructed at arbitrary points in between samples from an infinite sequence of equidistant samples provided that there were more than two samples per minimum period when the data were sampled. The Nyquist-Shannon sampling theorem of course applies to seismic data sampled on the Earth’s surface as such data are bandlimited constrained to a cone in the frequency-wavenumber domain bounded by the minimum velocity at the recording locations. The less well-known generalized sampling theorem by Athanasios Papoulis from 1977 teaches that if different filtered versions of the original bandlimited data (filtered before sampling/decimation), the classical Nyquist-Shannon sampling criterion can be less strict. The generalized sampling theorem has direct applications for acquisition of exploration seismic data for instance resulting in considerable efficiency gains in the acquisition of surface seismic data. In addition the topic of simultaneous source acquisition can be described in a generalized sampling theorem context.

Similar to acquisition efficiency advances offered by the generalized sampling theorem, wavefield gradiometry also benefits from different data types (combinations of spatial gradients) of the underlying wavefield that are exploited to derive information that would not be available in conventional wavefield recordings (e.g., to determine whether recordings correspond to P- or S-waves, determining slowness of arrivals, etc.). Recently, an increased interest in rotational seismology is one example of wavefield gradiometry advances.

Starting with the pioneering work by Harry Nyquist, I will discuss acquisition and processing of seismic data. I will focus on recent developments building on Papoulis’ generalized sampling theorem including examples from signal-apparition-based simultaneous source acquisition as well as seismic data acquisition on the moon and on Mars where logistics is severely limited benefitting significantly from advanced multi-measurement acquisition with foundations in wavefield gradiometry.

https://www.knowledgette.com/p/generalized-sampling-and-gradiometry-chan...

Format: Virtual Webinar. 45 min. presentation followed by 15 min. Q&A

Please note that two sessions will be given at different dates listed below.

Session 1: Monday, April 20, 2020, 4 pm to 5 pm Zurich time Register Here

Session 2: Tuesday, May 5, 2020, 4 pm to 5 pm Zurich time Register Here

Abstract:

Recording seismic data involves moving from a continuous signal to a discretized data representation. The rules governing sampling of bandlimited signals and their reconstruction were pioneered by Swedish-born mathematician Harry Nyquist who studied transmission of telegraph signals in limited bandwidth channels in the 1920s. Together with Claude Shannon among others, both at Bell laboratories, he laid the foundations of information theory. The Nyquist-Shannon sampling theorem states that a bandlimited signal can be perfectly reconstructed at arbitrary points in between samples from an infinite sequence of equidistant samples provided that there were more than two samples per minimum period when the data were sampled. The Nyquist-Shannon sampling theorem of course applies to seismic data sampled on the Earth’s surface as such data are bandlimited constrained to a cone in the frequency-wavenumber domain bounded by the minimum velocity at the recording locations. The less well-known generalized sampling theorem by Athanasios Papoulis from 1977 teaches that if different filtered versions of the original bandlimited data (filtered before sampling/decimation), the classical Nyquist-Shannon sampling criterion can be less strict. The generalized sampling theorem has direct applications for acquisition of exploration seismic data for instance resulting in considerable efficiency gains in the acquisition of surface seismic data. In addition the topic of simultaneous source acquisition can be described in a generalized sampling theorem context.

Similar to acquisition efficiency advances offered by the generalized sampling theorem, wavefield gradiometry also benefits from different data types (combinations of spatial gradients) of the underlying wavefield that are exploited to derive information that would not be available in conventional wavefield recordings (e.g., to determine whether recordings correspond to P- or S-waves, determining slowness of arrivals, etc.). Recently, an increased interest in rotational seismology is one example of wavefield gradiometry advances.

Starting with the pioneering work by Harry Nyquist, I will discuss acquisition and processing of seismic data. I will focus on recent developments building on Papoulis’ generalized sampling theorem including examples from signal-apparition-based simultaneous source acquisition as well as seismic data acquisition on the moon and on Mars where logistics is severely limited benefitting significantly from advanced multi-measurement acquisition with foundations in wavefield gradiometry.