About This Item

Share This Item

The AAPG/Datapages Combined Publications Database

AAPG Bulletin

Abstract

AAPG Bulletin, V. 106, No. 11 (November 2022), P. 2225-2237.

Copyright ©2022. The American Association of Petroleum Geologists. All rights reserved.

DOI: 10.1306/05112221007

A cross-shape deep Boltzmann machine for petrophysical seismic inversion

Son Dang Phan1 and Mrinal K. Sen2

1Institute for Geophysics, The University of Texas at Austin, Austin, Texas; [email protected]
2Institute for Geophysics, The University of Texas at Austin, Austin, Texas; [email protected]

ABSTRACT

Typical estimation of petrophysical properties in a reservoir volume is carried out by seismic inversion with integration of rock physics models. While this provides good solutions to the original objectives, it is strongly dependent on data-fitting algorithms to create an empirical model during well analyses. To overcome this limitation, a cross-shape deep Boltzmann machine structure is designed by arranging four different restricted Boltzmann machines located at the vertices interconnected via a hidden neuron layer at the center. Four different input data types, including a seismic amplitude and three petrophysical properties logs (porosity, water saturation, and shale volumetric), are used to train the network. Ultimately, six different nonlinear relationships between the inputs are simultaneously captured during the learning process, among which the three connections between target petrophysical logs and seismic amplitudes are used to predict property values. Unlike many conventional deep learning systems, which expect large data for all what-if scenarios into training, this multilayer probabilistic network does not involve any backpropagation, but only requires the anticipated upper and lower bounds of the data and labels for random initializations of Markov chains to reach an equilibrium stage. This makes the algorithm an excellent candidate for solving problems with limited data sets. This approach is robust enough to account for uncertainties while still retaining the generalization outside of the training information. A two-dimensional field data set with limited well coverage is used to demonstrate the capability of this algorithm with accurate reconstruction of geologically plausible petrophysical property sections.

Pay-Per-View Purchase Options

The article is available through a document delivery service. Explain these Purchase Options.

Watermarked PDF Document: $14
Open PDF Document: $24

AAPG Member?

Please login with your Member username and password.

Members of AAPG receive access to the full AAPG Bulletin Archives as part of their membership. For more information, contact the AAPG Membership Department at [email protected].