Formation evaluation

Technique Improves Neural Network Training To Quantify Rock Properties From Seismic

This paper describes the application of a synthetic seismic-catalog-generation method followed by application of a neural network on a seismic data set for an oil-producing field in the North Sea.

Stepwise schematic of the presented work flow using a rock-physics-guided data-science technique.
Fig. 1—Stepwise schematic of the presented work flow using a rock-physics-guided data-science technique to improve neural network training to quantify rock properties from seismic data accurately.

The success or failure of neural networks in discerning rock properties through a quantitative approach from seismic data and associated seismic attributes is dependent on the amount of available data. Past researchers developed a hybrid theory-guided-data-science (TGDS) technique that augmented the amount of data used for training. This paper shows the application of this method of TGDS-based synthetic seismic catalog generation followed by the application of a deep feed-forward neural network (DFNN) to a real seismic data set for a commercially oil-producing field in the North Sea.


Machine-learning algorithms have been used for several applications in the field of reservoir characterization. Using neural network techniques for supervised learning applications to predict log properties from seismic and seismic attributes is an established technique.

Restricted Content
We're sorry, but this content is reserved for SPE Members. If you are a member, please sign in at the top of the page for access. If you are not a member and you find JPT content valuable, we encourage you to become a part of the SPE member community.