Machine Learning and Reservoir Sedimentological Models

We presented our work that uses machine learning to improve oil and gas reservoir sedimentological models. Here are the details:

  • Title: From Cores to an Entire Field: Improving Reservoir Sedimentological Models Using Machine Learning.
  • Authors: Javier Iparraguirre, Carlos Zavala, Mariano Arcuri.
  • Event: 20th International Sedimentological Congress (ISC) .
  • Place: Quebec City, Canada.
  • Date: August, 2018.

Abstract: “The use of accurate sedimentological models in hydrocarbon reservoirs is fundamental to reduce exploration and production risks. The most accurate sedimentological models are those derived from detailed description and interpretation (facies analysis) performed on cores. Unfortunately, many mature fields are characterized by a large number of producing wells with a limited core database. Consequently, precise and accurate sedimentological studies performed on cores are often difficult to apply to the entire field model due to scale problems between well logs and seismic analysis. One possible solution is the definition and calibration of electrofacies from core studies. However, the interpretation of electrofacies maps are often complex and poorly accurate. Machine learning constitutes a useful tool that allows to apply detailed sedimentological studies to a large well log database inside a desired stratigraphic intervals. Algorithms are trained to recognize facies using as input a set of lithologic well logs in the available core intervals. The result consist on a new set of logs (.las files) that contains the inferred facies distribution for the rest of the analyzed reservoir wells. The new predictions allow a fast and accurate mapping of facies, facies associations, and depositional elements in the study area. If facies and depositional elements are populated with results of conventional analysis, it is also possible to generate detailed maps showing changes in porosity and permeability along the entire field. This information contributes to a substantial risk reduction in predicting reservoir quality in undrilled areas. The procedure was successfully applied to different oil fields in Argentina, Mexico and Russia.”