An AI system which can predict depositional facies. Save both cost and time for an equivalent quality
Data-driven, re-producible and
consistent results throughout an entire field
Most interpretations are largely subjective because they are based primarily on well logs, which are non-diagnostic for facies interpretation, integrated with minimal core data. However, a new hybrid approach which combines machine learning and an expert system generates data-driven, reproducible and consistent results for facies prediction across an entire field, which significantly reduces uncertainties when building a conceptual model derived from facies distribution.
Able to deal with a huge dataset including many wells
One of the greatest challenges for depofacies interpreters is that they normally have to work on many wells in the same field. Depofacies predictor on i2G is basically done by the computer so they can work with hundreds of well simultaneously which can save a significant amount of time.
Compensates for insufficient data for depositional environment interpretation
Unlike most machine learning models, the prediction is made considering data samples in the context of depositional units. First, the Gamma Ray curve is divided into different depositional units by tracking Gamma Ray value changes. The machine then automatically assigns to each depositional unit a Gamma Ray shape, lithofacies, boundary type and its stacking pattern with adjacent units. These parameters are integrated with a machine learning model built on core data from the studied basin plus any relevant biostratigraphic and then passed through an expert system containing a set of fuzzy rules to yield final probabilities curves for each of depositional facies. The facies above and below each unit, along with the style of each unit boundary, and their associated facies, are determined by looping back through the expert system after making the initial facies assignments, which produces a coherent stratigraphic succession. Outputs include predictions of the three most likely depositional facies for each unit and their respective probabilities.