Abstract
Conditional facies modeling combines geological spatial patterns with different types of observed data, to build earth models for predictions of subsurface resources. Recently, researchers have used generative adversarial networks (GANs) for conditional facies modeling, where an unconditional GAN is first trained to learn the geological patterns using the original GAN’s loss function, then appropriate latent vectors are searched to generate facies models that are consistent with the observed conditioning data. A problem with this approach is that the time-consuming search process needs to be conducted for every new conditioning data. As an alternative, we improve GANs for conditional facies simulation (called GANSim) by introducing an extra condition-based loss function and adjusting the architecture of the generator to take the conditioning data as inputs, based on progressive growing of GANs. The condition-based loss function is defined as the inconsistency between the input conditioning value and the corresponding characteristics exhibited by the output facies model, and forces the generator to learn the ability of being consistent with the input conditioning data, together with the learning of geological patterns. Our input conditioning factors include global features (e.g., the mud facies proportion) alone, local features such as sparse well facies data alone, and joint combination of global features and well facies data. After training, we evaluate both the quality of generated facies models and the conditioning ability of the generators, by manual inspection and quantitative assessment. The trained generators are quite robust in generating high-quality facies models conditioned to various types of input conditioning information.
Similar content being viewed by others
References
Borji A (2018) Pros and cons of GAN evaluation measures. arXiv e-prints arXiv:1802.03446
Chan S, Elsheikh AH (2017) Parametrization and generation of geological models with generative adversarial networks. arXiv e-prints arXiv:1708.01810
Chan S, Elsheikh AH (2019) Parametric generation of conditional geological realizations using generative neural networks. Comput Geosci. https://doi.org/10.1007/s10596-019-09850-7
Clerici A, Perego S (2016) A set of GRASS GIS-based shell scripts for the calculation and graphical display of the main morphometric parameters of a river channel. Int J Geosci. https://doi.org/10.4236/ijg.2016.72011
Demir U, Unal G (2018) Patch-based image inpainting with generative adversarial networks. arXiv preprint arXiv:1803.07422
Dumoulin V, Belghazi I, Poole B, Mastropietro O, Lamb A, Arjovsky M, Courville A (2016) Adversarially learned inference. arXiv e-prints arXiv:1606.00704
Dupont E, Zhang T, Tilke P, Liang L, Bailey W (2018) Generating realistic geology conditioned on physical measurements with generative adversarial networks. arXiv e-prints arXiv:1802.03065
Gan Z, Henao R, Carlson D, Carin L (2015) Learning deep sigmoid belief networks with data augmentation. J Mach Learn Res 268–276
Goodfellow I, Yoshua Bengio AC (2016) Deep learning. MIT press, Cambridge
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks. arXiv e-prints arXiv:1406.2661
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of Wasserstein GANs. arXiv e-prints arXiv:1704.00028
Isola P, Zhu J-Y, Zhou T, Efros AA (2016) Image-to-image translation with conditional adversarial networks. arXiv e-prints arXiv:1611.07004
Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of GANs for improved quality, stability, and variation. arXiv e-prints arXiv:1710.10196
Karras T, Laine S, Aila T (2018) A style-based generator architecture for generative adversarial networks. arXiv e-prints arXiv:1812.04948
Laloy E, Hérault R, Jacques D, Linde N (2018) Training-image based geostatistical inversion using a spatial generative adversarial neural network. Water Resour Res. https://doi.org/10.1002/2017WR022148
Larochelle H, Murray I (2011) The neural autoregressive distribution estimator. In: Proceedings of the 14th international conference on artificial intelligence and statistics (AISTATS 2011)
Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z, Shi W (2016) Photo-realistic single image super-resolution using a generative adversarial network. arXiv e-prints arXiv:1609.04802
Leinonen J, Guillaume A, Yuan T (2019) Reconstruction of cloud vertical structure with a generative adversarial network. Geophys Res Lett. https://doi.org/10.1029/2019GL082532
Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv e-prints arXiv:1411.1784
Mosser L, Dubrule O, Blunt MJ (2017) Reconstruction of three-dimensional porous media using generative adversarial neural networks. Phys Rev E. https://doi.org/10.1103/PhysRevE.96.043309
Mosser L, Dubrule O, Blunt MJ (2018a) Stochastic reconstruction of an oolitic limestone by generative adversarial networks. Transp Porous Media. https://doi.org/10.1007/s11242-018-1039-9
Mosser L, Kimman W, Dramsch J, Purves S, De la Fuente Briceño A, Ganssle G (2018b) Rapid seismic domain transfer: seismic velocity inversion and modeling using deep generative neural networks. In: 80th EAGE conference and exhibition 2018: opportunities presented by the energy transition
Mosser L, Dubrule O, Blunt MJ (2020) Stochastic seismic waveform inversion using generative adversarial networks as a geological prior. Math Geosci. https://doi.org/10.1007/s11004-019-09832-6
Nesvold E, Mukerji T (2019) Geomodeling using generative adversarial networks and a database of satellite imagery of modern river deltas. In: Petroleum geostatistics. European Association of Geoscientists & Engineers, Vol 2019, No. 1, pp 1–5
Pyrcz MJ, Deutsch CV (2014) Geoestatistical reservoir modeling. Oxford university press
Reed S, Akata Z, Yan X, Logeswaran L, Schiele B, Lee H (2016) Generative adversarial text to image synthesis. arXiv e-prints arXiv:1605.05396
Rezende DJ, Mohamed S, Wierstra D (2014) Stochastic backpropagation and approximate inference in deep generative models. In: 31st International conference on machine learning, ICML 2014
Song S, Mukerji T, Hou J (2020) Geological facies modeling based on progressive growing of generative adversarial networks (GANs). EarthArXiv. https://doi.org/10.31223/osf.io/ycufs
Sun AY (2018) Discovering state-parameter mappings in subsurface models using generative adversarial networks. Geophys Res Lett. https://doi.org/10.1029/2018GL080404
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Van Den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016a) WaveNet: a generative model for raw audio. arXiv e-prints arXiv:1609.03499
Van Den Oord A, Kalchbrenner N, Vinyals O, Espeholt L, Graves A, Kavukcuoglu K (2016b) Conditional image generation with PixelCNN decoders. arXiv e-prints arXiv:1606.05328
Zhang TF, Tilke P, Dupont E, Zhu LC, Liang L, Bailey W (2019) Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks. Pet Sci. https://doi.org/10.1007/s12182-019-0328-4
Zhong Z, Sun AY, Jeong H (2019) Predicting CO2 plume migration in heterogeneous formations using conditional deep convolutional generative adversarial network. Water Resour Res. https://doi.org/10.1029/2018wr024592
Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision
Zuo C, Yin Z, Pan Z, MacKie EJ, Caers J (2020) A tree-based direct sampling method for stochastic surface and subsurface hydrological modeling. Water Resour Res. https://doi.org/10.1029/2019WR026130
Acknowledgements
We acknowledge the sponsors of the Stanford Center for Earth Resources Forecasting (SCERF) and support from Prof. Steve Graham, the Dean of the Stanford School of Earth, Energy and Environmental Sciences. Some of the computing for this project was performed on the Sherlock cluster. We would like to thank Stanford University and the Stanford Research Computing Center for providing computational resources and support that contributed to these research results. Codes, data, and some results of this work are available at the GitHub site (https://github.com/SuihongSong/GeoModeling_Conditional_ProGAN).
Funding
Funding was provided by the National Natural Science Foundation of China (42072146).
Author information
Authors and Affiliations
Corresponding author
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Song, S., Mukerji, T. & Hou, J. GANSim: Conditional Facies Simulation Using an Improved Progressive Growing of Generative Adversarial Networks (GANs). Math Geosci 53, 1413–1444 (2021). https://doi.org/10.1007/s11004-021-09934-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11004-021-09934-0