Generative adversarial network as a stochastic subsurface model reconstruction
- PDF / 7,881,389 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 84 Downloads / 263 Views
ORIGINAL PAPER
Generative adversarial network as a stochastic subsurface model reconstruction Leonardo Azevedo 1
&
Gustavo Paneiro 1
&
Arthur Santos 1 & Amilcar Soares 1
Received: 19 July 2019 / Accepted: 20 May 2020 # Springer Nature Switzerland AG 2020
Abstract In geosciences, generative adversarial networks have been successfully applied to generate multiple realizations of rock properties from geological priors described by training images, within probabilistic seismic inversion and history matching methods. Here, the use of generative adversarial networks is proposed not as a model generator but as a model reconstruction technique for subsurface models where we do have access to sparse measurements of the subsurface properties of interest. We use sets of geostatistical realizations as training datasets combined with observed experimental data. These networks are applied to reconstruct nonstationary sedimentary channels and continuous elastic properties, such as P-wave propagation velocity, in the presence and absence of conditioning data. The reconstruction examples shown herein can be considered a post-processing step applied after seismic inversion and performed at those locations where the convergence of the inversion is low, and therefore, the inverted models are associated with high uncertainty. The application examples show the suitability of generative adversarial networks in learning the spatial structure of the data from sets of geostatistical realizations. The generated models reproduce the first- and second-order statistical moments and the spatial covariance matrix of the training dataset. Keywords Generative adversarial network . Stochastic modeling . Model reconstruction
1 Introduction Hydrocarbon accumulations correspond to natural resources of great importance for the modern society. In hydrocarbon exploration and production, numerical three-dimensional models of the subsurface rock properties (i.e., porosity, geological facies, fluid saturations) are central pieces of information in field development and decision-making. These models describe the spatial distribution of the subsurface geological properties of * Leonardo Azevedo [email protected] Gustavo Paneiro [email protected] Arthur Santos [email protected] Amilcar Soares [email protected] 1
CERENA/DECivil, Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049-001 Lisboa, Portugal
interest and are built based on several sources of information (e.g., geological, geophysical, petrophysical, and engineering data). Besides the quantitative description of the reservoir’s properties, these models should allow assessing the associated spatial uncertainty and variability, which is frequently done by generating multiple stochastic realizations of the same property through geostatistical simulation under the same assumptions about data and spatial continuity patterns [16]. As part of the geo-modeling workflow, geostatistical simulation tools (i.e., stochastic seq
Data Loading...
