Important announcement of COVID 19 - Click here

International

Automating seismic data analysis and interpretation

Tuesday, May 12, 2020
11 AM (US Central Time)
12 PM (US Central Time)

Date

Time (AWST)

Time (ACST)

Time (AEST)

13/05/2020

00:00:00

01:30:00

02:00:00

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.

Automating seismic data analysis and interpretation

Wednesday, April 22, 2020
8 PM (US Central Time)
9 PM (US Central Time)

Date

Time (AWST)

Time (ACST)

Time (AEST)

23/04/2020

09:00:00

10:30:00

11:00:00

 

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.

Biogeophysics: Exploring Earth’s subsurface biosphere using geophysical approaches

Monday, September 21, 2020
4 PM (US Eastern Daylight Time)
5 PM (US Eastern Daylight Time)

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.

Biogeophysics: Exploring Earth’s subsurface biosphere using geophysical approaches

Thursday, April 30, 2020
11 AM (US Eastern Daylight Time)
12 PM (US Eastern Daylight Time)

Date

Time (AWST)

Time (ACST)

Time (AEST)

1/05/2020

23:00:00

00:30:00

01:00:00

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.

Generalized sampling and gradiometry: Changing the rules of the information game

Tuesday, May 5, 2020
4 PM (Zurich)
5 PM (Zurich)

Date

Time (AWST)

Time (ACST)

Time (AEST)

6/05/2020

22:00:00

23:30:00

00:00:00

 

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.

Generalized sampling and gradiometry: Changing the rules of the information game

Monday, April 20, 2020
4 PM (Zurich)
5 PM (Zurich)

Date

Time (AWST)

Time (ACST)

Time (AEST)

21/04/2020

22:00:00

23:30:00

00:00:00

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.

Deep learning for seismic interpretation

Thursday, April 16, 2020
0900 (India)
1000 (India)

https://www.knowledgette.com/p/deep-learning-for-seismic-interpretation

 

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, Tuesday, April 14, 2020, 10 am to 11 am Beijing time Register Here

Session 2, Thursday, April 16, 2020, 9 am to 10 am IST time (India) Register Here

 

Abstract:

Seismic interpretation involves detecting and extracting structural information, stratigraphic features, and geobodies from seismic images. Although numerous automatic methods have been proposed, seismic interpretation today remains a highly time-consuming task which still requires significant human efforts. The conventional seismic interpretation methods or workflows are not automated or intelligent enough to efficiently or accurately interpret the rapidly increasing seismic data sets, which leaves significantly more data uninterpreted than interpreted.

We improve automatic seismic interpretation by using CNNs (convolutional neural networks) which recently have shown the best performance in detecting and extracting useful image features and objects. One main limitation of applying CNNs in seismic interpretation is the preparation of many training data sets and especially the corresponding geologic labels. Manually labeling geologic features in a seismic image is highly time-consuming and subjective, which often results in incompletely or inaccurately labeled training images. To solve this problem, we propose a workflow to automatically build diverse geologic models with geologically realistic features. Based on these models with known geologic information, we further automatically create numerous synthetic seismic images and the corresponding ground truth of geologic labels to train CNNs for geologic interpretation in field seismic images. Accurate interpretation results in multiple field seismic images show that the proposed workflow simulates realistic and generalized geologic models from which the CNNs effectively learn to recognize real geologic features in field images.

In this lecture, I would like the share you with our research experience on the following topics:

Automatic preparation of training data sets and labels;

CNN for fault detection, fault orientation estimation, and fault surface construction;

CNN for relative geologic time and seismic horizons;

CNN for seismic geobody tracking;

CNN-based multitask learning in seismic interpretation.

Deep learning for seismic interpretation

Tuesday, April 14, 2020
10 AM (Beijing)
11 AM (Beijing)

https://www.knowledgette.com/p/deep-learning-for-seismic-interpretation

 

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, Tuesday, April 14, 2020, 10 am to 11 am Beijing time Register Here

Session 2, Thursday, April 16, 2020, 9 am to 10 am IST time (India) Register Here

 

Abstract:

Seismic interpretation involves detecting and extracting structural information, stratigraphic features, and geobodies from seismic images. Although numerous automatic methods have been proposed, seismic interpretation today remains a highly time-consuming task which still requires significant human efforts. The conventional seismic interpretation methods or workflows are not automated or intelligent enough to efficiently or accurately interpret the rapidly increasing seismic data sets, which leaves significantly more data uninterpreted than interpreted.

We improve automatic seismic interpretation by using CNNs (convolutional neural networks) which recently have shown the best performance in detecting and extracting useful image features and objects. One main limitation of applying CNNs in seismic interpretation is the preparation of many training data sets and especially the corresponding geologic labels. Manually labeling geologic features in a seismic image is highly time-consuming and subjective, which often results in incompletely or inaccurately labeled training images. To solve this problem, we propose a workflow to automatically build diverse geologic models with geologically realistic features. Based on these models with known geologic information, we further automatically create numerous synthetic seismic images and the corresponding ground truth of geologic labels to train CNNs for geologic interpretation in field seismic images. Accurate interpretation results in multiple field seismic images show that the proposed workflow simulates realistic and generalized geologic models from which the CNNs effectively learn to recognize real geologic features in field images.

In this lecture, I would like the share you with our research experience on the following topics:

Automatic preparation of training data sets and labels;

CNN for fault detection, fault orientation estimation, and fault surface construction;

CNN for relative geologic time and seismic horizons;

CNN for seismic geobody tracking;

CNN-based multitask learning in seismic interpretation.

Advances in Marine Seismic Data Acquisition Workshop

Wednesday, December 2, 2020
0800
1900

2-day workshop on 2 - 3 December 2020.

The workshop will bring together all aspects of marine seismic acquisition, highlighting advances in technologies and methodologies. It will focus on the science of data acquisition covering a broad range of topics, from advances in survey design to developments in seismic source, streamer and Ocean Bottom Seismic technology and its configurations, in order to address both exploration and development objectives. Workshop attendees will have a valuable opportunity to discuss among experts the future vision in domains such as machine learning, artificial intelligence and robotization.

Pages