Oftentimes when working with regional magnetic surveys from multiple sources, we encounter resolution continuity issues, which makes 2D interpretation more challenging. The loss in resolution of anomalies borders and lack of texture in the gridded data, can cause issues to the interpreter. This talk sets the basis of using currently available deep learning architecture to train a model for special resolution enhancement.

Recent advancement in image processing and deep learning have led to the development of neural networks capable of increasing images resolution using and adversarial learning strategy (Wang, X et al., 2018). In this deep learning model, available high-resolution grids with their low-resolution counter parts are used to train an encoder-decoder network to reconstruct the high-resolution from their starting point. Once the network is sufficiently trained it is then possible to apply it to upscale low-resolution images without existing ground truth high resolution counter part. This approach uses Generative Adversarial Networks or GAN’s, a relatively new class of machine learning frameworks designed in 2014 (Goodfellow, I. et al). A generator network is used to construct images that are then passed through a discriminator network which tries to discriminate between real images and fake images produced by the generator. Given a training set, this technique learns to generate higher resolution data with the same statistics as the training set.

Once the general model is trained on high-resolution/low-resolution pairs, it is possible to refine it to the area of interest and use it to upscale low resolution survey patches. This will help in refining anomaly edges and increase the accuracy of the structural interpretation conducted by the geologist. This approach is proposed as an alternative to the commonly used downward continuation filters used in the industry.

Jean-Philippe Paiement is our Director of Global Consulting. He brings 15 years of mineral exploration experience including expertise in geostatistics applied to structural, geological, and geochemical modelling and interpretation; specializing in non-linear interpolation and simulation. Jean-Philippe has developed multiple workflow and novel approaches to reduce interpretational risks of geological data. He has a wide range of experience in mineral resource estimation for precious metals, base metals and industrial minerals across diverse geological environments around the world. In 2016, he pioneered the application of Machine Learning to the mineral exploration industry in winning the Integra GoldRush challenge by application of machine learning to mineral deposit targeting. He is skilled in the application of machine learning to overcome geological and geophysical challenges; by combining geological knowledge and both supervised learning and deep learning. Before joining Mira Geoscience, he obtained an MSc from Laval University. Jean-Philippe is based in Quebec-City.

Latest news

Software tips
March, 01 2019

Create array property from scalar properties

This command, found in GOCAD's Property menu, creates a multi-dimensional array property from user-selected properties...
Read more
Software tips
April, 01 2019

Operations on array properties

In GOCAD, this command, found in the Property menu, allows the user to perform various operations (scaling, DC shift...
Read more
Software tips
June, 07 2021

Dynamically turn on/off classes in scatter plots

In Geoscience INTEGRATOR, you can turn on/off classes in scatter plots...
Read more
Software tips
June, 03 2019

Preview files in the Maps/plans/sections page

See the list of layers of your .dwg and .dxf files. Image sneak peeks are also available...
Read more
Software tips
October, 15 2019

Used v/s available themes

In Geoscience INTEGRATOR, the Theme drop down menu shows a filtered list of those containing data sets by default...
Read more
Software tips
April, 03 2020

Using hot keys

Use hot keys in GOCAD Mining Suite to optimize your experience to help navigate the interface and execute commands more quickly and easily. Try them out!
Read more
Software tips
October, 01 2021

Snapshot grid sections

In GOCAD Mining Suite quickly take snapshots of your Voxet sections using the snapshot tool...
Read more
Software tips
October, 07 2019

Drag-and-drop files into a 3D compilation

In Geoscience ANALYST, you can create a 3D compilation by simply dragging your data right into the Viewport...
Read more
Geoscience ANALYST
May, 05 2021

3D seismic data and survey designer tools

Coming soon to Geoscience ANALYST, tools for hard rock seismic...
Read more
Geoscience ANALYST
September, 28 2021

New release – Geoscience ANALYST v3.4

Coming soon to Geoscience ANALYST, SEG-Y 2D importers, compute the inertia curve for K-means clustering, expanded connections to VP Geophysics, SimPEG, and Python...
Read more
Online training
October, 04 2021

Using Geoscience ANALYST for unsupervised learning (basics) – Masterclass

Learn how to get data from Geoscience ANALYST to Python and perform unsupervised learning on data...
Read more
Software tips
April, 03 2019

Bounding boxes in the viewer

Coloured bounding boxes are used to highlight volumes in the Viewport: A purple box surrounds your current selection...
Read more

Please contact our team for additional information about our products and services