Data Science for the Digital Subsurface

About us

We are a London-based consultancy founded in 2016 to explore the potential of data science and machine learning to transform the way we analyse data in the upstream oil and gas industry.

Informed by more than 25 years experience of research and development in reservoir geophysics, reservoir modelling, geostatistics, and software engineering, we have a unique perspective on the role of these enabling technologies in geoscience workflows.

We deliver consultancy, software, and training, enabling clients to exploit this key technology for the digital subsurface.


Our background in reservoir geoscience, statistics, and computer science is key to our application of machine learning to the subsurface.

We develop practical solutions to the challenges posed by spatial prediction and data integration in the subsurface: sparse data, spatial correlation, unlabelled data, quality control, uncertainty quantification, and multiple data types and vintages.

We think the future is interpretable machine learning models not black-box ones.


R&D in machine learning, geostatistical reservoir modelling, stochastic seismic inversion, uncertainty analysis, exploratory data analysis.

  • Python, R and MATLAB for data science projects.
  • C/C++ for commercial product development in the computational geosciences.
  • Plug-in development using C# .Net and Ocean for Petrel.
  • Recent Projects

    Petrophysical Interpretation

    Quality control and log reconstruction for massive well datasets.

    Production Data Analysis

    Clustering wells by similarity in decline curves.

    Unconventional Resources

    Evaluating relationships between production, seismic attributes, and hydraulic fracture stimulation design.