Stratigraphic correlation of well data is cornerstone both in regional syntheses and reservoir modelling workflows. However this task demands high expertise and can be extremely tedious. Practically, geologists often lack time to explore all possible correlation scenarios and assess the corresponding uncertainties.
In this demo project we explore how well correlations can be partially automated and digitally assisted in order to efficiently consider multiple scenarios and evaluate the risk associated.
To do so we rely on an expert system based on a combination of Dynamic Time Warping algorithms and geological rules. We benefit from a strategic partnership with an academic team from the University of Lorraine to use the WeCo technology in this purpose.
With such approach, multiple correlation scenarios can be generated automatically, each one with a score reflecting their respect of input geological rules.
Future work includes adjusting and validating the technology on more operational studies and linking it with other digital tools facilitating the analysis of well data, for instance an assisted interpretation of wireline logs with Machine Learning.