Harnessing Machine Learning

Make your workflows
as smart as you

Data science and machine learning will not be replacing skilled geoscientists. It takes geoscience expertise to recognize which tools are best suited for each specific E&P challenge and how best to apply them. Our GeoSoftware experts have handpicked the most effective machine and deep learning technologies and put them at your fingertips. PowerLog® native Python extensions and HampsonRussell™ applications featuring the latest neural network technologies will enable you to gain deeper insight into your data.

Enjoy faster, smarter workflows where machine learning automates the mundane and provides a new toolkit for you to create better facies predictions, more accurate reservoir property estimates and subsurface models with more realistic reservoir details.

Bigger and Better Facies Classification

Petrophysical analysis and facies classification is seeing significant gains from the application of machine learning. Facies clusters defined for a play using unsupervised analysis on a few selected wells can be applied rapidly via supervised classification to large numbers wells across the play bringing a new scale and accuracy. PowerLog native Python extensions puts these machine learning tools at your fingertips.

More Accurate Reservoir Properties, Faster

The estimation of reservoir properties is normally undertaken using seismic inversion results. However, neural networks are providing opportunities to take an alternative and direct data-driven approach. HampsonRussell first introduced neural networks into their software 20 years ago. Today they have an increasingly advanced toolkit featuring techniques such as probabilistic and deep feed-forward networks which can be deployed on your reservoir characterization projects.

Cloud Flexibility

We are migrating our GeoSoftware technology to the Cloud. “Lift-and-shift” of all of our GeoSoftware products to Microsoft Azure has already been completed. Our digitalization technology roadmap will see support for scaling out CPU-intensive computations  and creating native applications so you can take full advantage of the elasticity offered by the cloud environment for compute and storage.