Machine learning is a hot topic across multiple disciplines, especially as databases become larger and more available. MRCI is exploring applications to help solve subsurface challenges such as CO2 storage quantities, enhanced oil recovery potential, data integration, and improved geologic characterization. Machine learning and data analytics concepts can be overwhelming, but Battelle Senior Research Leader, Srikanta Mishra, and collaborators break this down in a “jargon-lite” manner in their latest paper: “Robust Data-Driven Machine-Learning Models for Subsurface Applications: Are we there yet?”. Their paper, which was published in the recent issue of Journal of Petroleum Technology (JPT), the general interest monthly publication for the 150,000+ worldwide members of the Society of Petroleum Engineers, overviews the application of machine-learning techniques and examines the current standing for managing subsurface energy such as oil and gas, carbon sequestration, and geothermal energy. Follow the link below to read the full article!