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
April, 13 2021

Finding data sets by tags and neighbourhoods

In Geoscience INTEGRATOR, you can can lookup data sets by the tags they carry and the neighbourhoods they cover...
Read more
Software tips
August, 03 2020

Have you Scene this?

In GOCAD Mining Suite v19, you can save the view as a Scene by right-clicking on the 3D Viewer > (Scene) Save As…
Read more
Software releases
June, 14 2023

New release – Geoscience ANALYST 4.2

This release includes an extended range of import and export filters that enable better interoperability, it also...
Read more
Geoscience ANALYST
January, 19 2021

Depth-to-basement inversion using geometry and homogeneous VPmg inversion

Past event - View here or on our YouTube channel...
Read more
Software tips
January, 25 2021

Display multiple Voxet sections

In GOCAD Mining Suite, you can create additional sections, hide/show them, use the slider and arrow to position them along the Voxet, and delete them...
Read more
Software tips
February, 10 2020

Fourier filters

This new Geoscience ANALYST Pro feature allows you to apply Fourier filters on 2D grids using the basic geophysics tools...
Read more
Case studies
April, 16 2019

Gold Fields Cave Rocks, Australia

An interactive approach to forward modelling and inversion. Exploration is becoming harder, with greater...
Read more
Software tips
October, 12 2020

Create regions – Crossplot 2D

In GOCAD Mining Suite you can filter data dynamically before creating regions and save the filters as templates for later use...
Read more
Software tips
July, 20 2020

Data set summaries

In Geoscience INTEGRATOR The Data set explorer provides simple, immediate ‘dashboard’ access to all the data sets, and their summary information...
Read more
Software tips
May, 11 2020

Copying objects between Workspaces

In Geoscience ANALYST objects can be copied from one Workspace to another by using Ctrl+C and Ctrl+V...
Read more
Mineral systems interpretation and targeting
December, 07 2020

Using comment field entries in drillhole databases to automatically re-log lithologies

This approach uses the comment field of the logging table to extract general topics that can then be used as learning features in a supervised machine learning classification approach.
Read more
Case studies
December, 05 2019

Rapid and accurate mapping

We explain how automated generation of alteration maps using radiometric data is well-suited to large-footprint mineral systems...
Read more

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