You are Home   »   News   »   View Article

CGG GeoSoftware adds machine learning applications using Python ecosystems

Tuesday, November 19, 2019

GeoSoftware, part of CGG's Geoscience division, has announced that machine learning technology in Python ecosystems will be available in upcoming releases of its flagship HampsonRussell and Jason reservoir characterization solutions.

Already attracting considerable industry interest in GeoSoftware's PowerLog petrophysical software, Python ecosystems in HampsonRussell and Jason will let experts and data scientists completely customize machine learning and reservoir characterization workflows by using extensively available Python machine learning libraries and also their own proprietary code.

Python ecosystems allow users to efficiently research and test various state-of-the-art machine learning workflows for proof-of-concept or commercial projects. Scripts and workflows directly access well, horizon and seismic data for use in machine learning, deep learning, visualization and numerical analysis. G&G experts and data scientists can use Ecosystem workflows pre-built by CGG or they can build their own new reservoir characterization workflows using the latest open source machine learning packages, such as Google's TensorFlow.

HampsonRussell and Jason users, even those with limited expertise in machine learning or Python scripting, will now benefit from complete control over input data and analysis output. With Python ecosystems, users can process data with pre-built or client-proprietary Python scripts or Jupyter notebooks, and store input and output data in either a HampsonRussell or Jason project database or a shared directory. Python ecosystem functionality will seamlessly integrate with the application's data stores and viewers, eliminating the need to export, reformat and reload data.

Kamal al-Yahya, Senior Vice President, Software & Smart Data Solutions, said: 'CGG already led the market by introducing Python ecosystem technology in PowerLog. We are now extending its benefits to the wider community of HampsonRussell and Jason users to enable effective research and application of machine learning technologies in reservoir characterization workflows. This new capability is another example of our commitment to innovation and making new technologies accessible to the industry, for generalists and experts alike.'



Associated Companies
» CGG
comments powered by Disqus

CREATE A FREE MEMBERSHIP

To attend our free events, receive our newsletter, and receive the free colour Digital Energy Journal.

FEATURED VIDEO

Clustering Considerations in the Machine Learning Workflow – Examples with Exploration Data
Philip Lesslar
from Precision DM

DIGITAL ENERGY JOURNAL

Latest Edition Jul-Aug 2019
Aug 2019

Download latest and back issues

COMPANIES SUPPORTING ONE OR MORE DIGITAL ENERGY JOURNAL EVENTS INCLUDE

Learn more about supporting Digital Energy Journal