Channel detection using deep learning

April 24, 2022 Examples No comments

A new paper is added to the collection of reproducible documents: Automatic channel detection using deep learning

We propose a method based on an encoder-decoder convolutional neural network for automatic channel detection in 3D seismic volumes. We use two architectures borrowed from computer vision which are SegNet for image segmentation together with Bayesian SegNet for uncertainty measurement. We train the network on 3D synthetic volumes and then apply it to field data. We test the proposed approach on a 3D field dataset from the Browse Basin, offshore Australia and a 3D Parihaka seismic data in New Zealand. Applying the weights estimated from training on 3D synthetic volumes to a 3D field dataset accurately identifies channel geobodies without the need for any human interpretation on seismic attributes. Our proposed method also produces uncertainty volumes to quantify the trustiness of detection model.

Azimuthal anisotropic moveout using DTW

October 25, 2021 Documentation No comments

A new paper is added to the collection of reproducible documents: Quantifying and correcting residual azimuthal anisotropic moveout in image gathers using dynamic time warping

We propose and demonstrate a novel application of dynamic time warping (DTW) for correcting residual moveout in image gathers, enhancing seismic images, and determining azimuthal anisotropic orientation and relative intensity when moveout is caused by wave propagation through a media possessing elliptical horizontally transverse isotropy (HTI). The method functions by first using DTW to determine the sequences of integer shifts that most closely match seismic traces within an image gather to the gather’s stack, and then applying those shifts to flatten the gather. Flattening shifts are fitted to an ellipse to provide an approximation for the orientation and relative strength of elliptical HTI anisotropy. We demonstrate the method on synthetic and 3D field data examples to show how it is able to (1) correct for residual azimuthal anisotropic moveout, (2) accurately recover high frequency information and improve feature resolution in seismic images, and (3) determine the anisotropic orientation while providing a measure of relative strength of elliptic anisotropy. We find that while the method is not intended to replace anisotropic processing techniques for moveout correction, it has the ability to inexpensively approximate the effects of such operations while providing a representation of the elliptic HTI anisotropy present within a volume.

Jim Jennings

October 18, 2021 Celebration No comments

A new inductee in the Madagascar Hall of Fame is Jim Jennings.

You can read Jim’s story here.

Jeff Godwin

October 18, 2021 Celebration No comments

A new inductee in the Madagascar Hall of Fame is Jeff Godwin.

You can read Jeff’s story here.

Yang Liu

September 27, 2021 Celebration No comments

A new inductee in the Madagascar Hall of Fame is Yang Liu.

You can read Yang’s story here.

Vladimir Bashkardin

September 23, 2021 Celebration No comments

A new inductee in the Madagascar Hall of Fame is Vladimir Bashkardin.

You can read Vladimir’s story here.

Tutorial on time-frequency analysis

September 15, 2021 Examples No comments

The example in rsf/tutorials/timefreq reproduces the tutorial from Matt Hall on time-frequency decomposition.

The tutorial was published in the June 2018 issue of The Leading Edge.

The Madagascar version was created by Sarah Greer. Madagascar users are encouraged to try improving the results.

Hall of Fame

August 31, 2021 Celebration No comments

A new wiki page, Hall of Fame, honors those individuals who made particularly important contributions to Madagascar and the Madagascar community.

The first two honorees are Nick Vlad and Pengliang Yang.

Please submit nominations for other major contributors.

Online Conference

May 5, 2021 Celebration No comments

The first ever worldwide Madagascar conference will take place on June 21-27, 2021. The participation is free of charge.

The conference program will be announced later. Meanwhile, please indicate the level of your interest in participation by filling a form on the website.

Enhancements to Python interface

April 9, 2021 Systems No comments

Several enhancements have been added to Madagascar’s Python interface.

Behind the scene, temporary files are created, and Madgascar programs run in the usual way, but, for the user, they appears like native Python functions. This way, the full power of Madagascar becomes available to people who prefer to work on data analysis projects in a Python environment.

  • However, there is no good reason to abandon Madagascar’s use of SCons for managing data analysis workflows even when working in a Python framework. Because SConstruct scripts are written in Python, they are easy to adapt for including Python functions in place of command-line instructions. See an example of using Keras with SCons or an example of using PyTorch with SCons.

In deep learning projects, the training data, the neural-network model, and the testing data can be treated as files and handled effectively through SCons workflows while mixing with Madagascar commands and workflows.

  • Plotting with Matplotlib may offer some advanced functionality in comparison with Vplot, such as the possibility of using $\LaTeX$ code in figure labels. It is now possible to use Matplotlib plots in papers reproducible with Madagascar through an application of sfmatplotlib. The figures will be saved in the PDF format and included in reproducible papers in the usual way. See an example.

The main advantage of continuing to use Vplot is the availability of sfvplotdiff, a key tool for reproducibility testing and continuous integration.

Madagascar users are invited to try the new functionality and contribute to its further development.