20 May 2021

This E-lecture: "Automated top and base salt interpretation using machine learning" describes a new automated workflow based on machine learning which can significantly reduce the amount of manual interpretation of the top and the base salt boundaries. Manual interpretation of salt boundaries on large seismic surveys with complex salt geometry is a time-consuming task. The interpreters typically need to scan through the seismic volume and pick surface control points line-by-line. It can take more than a month to complete a top or a base of salt interpretation. In this new method, two convolutional neural nets are designed to detect the top and the base of salt boundaries and the training data are picked as 2D images on two manual interpretations in a specific seismic survey. The trained networks are then evaluated both on the seismic data used in the training and on another seismic data not used in the training. In both cases we can produce a top and base salt interpretation that covers the main parts of the corresponding manual interpretations. The results can be further improved by adding more training data. This new automated workflow has the potential to reduce the interpretation turnaround time of both top and base of salt from approximately a month or more and down to hours.

View more E-Lectures   Read Paper in EarthDoc    Join EAGE today!

Access to recent EarthDoc material is free of charge for EAGE members.