Generating Geologically Realistic 3D Reservoir Facies Models Using Deep Learning of Sedimentary Architecture with Generative Adversarial Networks
Authors:
- 22 March 2019
- conference paper
- Published by Society of Petroleum Engineers (SPE)
Abstract
This paper proposes a novel approach for generating 3-dimensional complex geological facies models based on deep generative models. It can reproduce a wide range of conceptual geological models while possessing the flexibility necessary toKeywords
This publication has 9 references indexed in Scilit:
- Training‐Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural NetworkWater Resources Research, 2018
- Reconstruction of three-dimensional porous media using generative adversarial neural networksPhysical Review E, 2017
- Context Encoders: Feature Learning by Inpainting2016
- Direct Pattern-Based Simulation of Non-stationary Geostatistical ModelsMathematical Geosciences, 2012
- Multiple-Point Simulations Constrained by Continuous Auxiliary DataMathematical Geosciences, 2008
- The Necessity of a Multiple-Point Prior ModelMathematical Geology, 2006
- Conditional Simulation of Complex Geological Structures Using Multiple-Point StatisticsMathematical Geology, 2002
- Geostatistics for Natural Resources Evaluation1997
- Hierarchical object-based stochastic modeling of fluvial reservoirsMathematical Geology, 1996