AI Augmented Analytics
With many E&P companies struggling to make sense of their microseismic data and create value with their data acquisition and processing investments, we see it as a necessity to declutter this space with helping our clients to verify the reliability of the information provided for them by microseismic vendors and turn the information into actionable insights. Insights that makes you rethink completion programs and pushes unconventional operations in a new direction. AI augmentation of analytics solutions helps to maximize the actionable insights from your analytics investments, an important step toward data-driven success.
Data Quality Intelligence<sup>TM</sup>
Data Quality IntelligenceTM (DQI) is our proprietary modelling and analytics method for data quality control. Using machine learning classification and regression algorithms augmented with expert opinion, microseismic data quality is measured. Our method brings clarification on reliable vs. unreliable data and provides you with actionable information.
ProSRV<sup>TM</sup>
ProSRVTM is our proprietary modelling and analytics algorithm in which, the collective rock deformation inferred from microseismicity is measured in 4D, outlining a logical estimation of stimulated reservoir volume associated with high potential of production.
EPYFFNI<sup>TM</sup>
EPYFFNITM (read e·piph·a·ny) is our proprietary modelling and analytics method in which the DFN’s connectivity as a proxy for permeability of the fracture network constructed from MTI analysis, is quantified by combining graph theoretical and pattern recognition methods. If the data statistics allow, then Al algorithms will be used to model the MTI response for the rest of the microseismic data which was previously labelled as unqualified for MTI analysis, to construct the complete DFN for the entire pad. If the data is sparse and prediction errors are high, then statistical power law distribution models can be used to gain a better insight into fracture surface area of the percolating DFN.