scholarly journals GANSim-3D for conditional geomodelling: theory and field application

2021 ◽  
Author(s):  
Suihong Song ◽  
Tapan Mukerji ◽  
Jiagen Hou ◽  
Dongxiao Zhang ◽  
Xinrui Lyu
Keyword(s):  
Carbon Capture And Storage ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Earth Model ◽  
Global Features ◽  
Probability Map ◽  
Probability Maps ◽  
Earth Models ◽  
Conditioning Data ◽  
Facies Models

Geomodelling of subsurface reservoirs is important for water resources, hydrocarbon exploitation, and Carbon Capture and Storage (CCS). Traditional geostatistics-based approaches cannot abstract complex geological patterns and are thus not able to simulate very realistic earth models. We present a Generative Adversarial Networks (GANs)-based 3D reservoir simulation framework, GANSim-3D, which can capture geological patterns and relationships between various conditioning data and earth models and is thus able to directly simulate multiple 3D realistic and conditional earth models of arbitrary sizes from given conditioning data. In GANSim-3D, the generator, designed to only include 3D convolutional layers, takes various 3D conditioning data and 3D random latent cubes (composed of random numbers) as inputs and produces a 3D earth model. Two types of losses, the original GANs loss and condition-based loss, are designed to train the generator progressively from shallow to deep layers to learn the geological patterns and relationships from coarse to fine resolutions. Conditioning data can include 3D sparse well facies data, 3D low-resolution probability maps, and global features like facies proportion, channel width, etc. Once trained on a training dataset where each training sample is a 3D cube of a small fixed size, the generator can be used for geomodelling of 3D reservoirs of large arbitrary sizes by directly extending the sizes of all inputs and the output of the generator proportionally. To illustrate how GANSim-3D is used for field geomodelling and also to verify GANSim-3D, a field karst cave reservoir in Tahe area of China is used as an example. The 3D well facies data and 3D probability map of caves obtained from geophysical interpretation are used as conditioning data. First, we create a training dataset consisting of facies models of 64×64×64 cells with a process-mimicking simulation method to integrate field geological patterns. The training well facies data and the training probability map data are produced from the training facies models. Then, the 3D generator is successfully trained and evaluated in two synthetic cases with various metrics. Next, we apply the pretrained generator for conditional geomodelling of two field cave reservoirs of Tahe area. The first reservoir is 800m×800m×64m and is divided into 64×64×64 cells, while the second is 4200m×3200m×96m and is divided into 336×256×96 cells. We fix the input well facies data and cave probability maps and randomly change the input latent cubes to allow the generator to produce multiple diverse cave reservoir realizations, which prove to be consistent with the geological patterns of real Tahe cave reservoir as well as the input conditioning data. The noise in the input probability map is suppressed by the generator. Once trained, the geomodelling process is quite fast: each realization with 336×256×96 cells takes 0.988 seconds using 1 GPU (V100). This study shows that GANSim-3D is robust for fast 3D conditional geomodelling of field reservoirs of arbitrary sizes.

scholarly journals An Improved Method of Reservoir Facies Modeling Based on Generative Adversarial Networks

Energies ◽  
2021 ◽  
Vol 14 (13) ◽  
pp. 3873
Author(s):  
Qingbin Liu ◽  
Wenling Liu ◽  
Jianpeng Yao ◽  
Yuyang Liu ◽  
Mao Pan
Keyword(s):  
Synthetic Data ◽  
Oil Field ◽  
Generative Adversarial Networks ◽  
Parameter Distribution ◽  
Good Prospect ◽  
Facies Modeling ◽  
Generative Adversarial Network ◽  
Hard Data ◽  
Reservoir Facies ◽  
Facies Models

As the reservoir and its attribute distribution are obviously controlled by sedimentary facies, the facies modeling is one of the important bases for delineating the area of high-quality reservoir and characterizing the attribute parameter distribution. There are a large number of continental sedimentary reservoirs with strong heterogeneity in China, the geometry and distribution of various sedimentary microfacies are relatively complex. The traditional geostatistics methods which have shortage in characterization of the complex and non-stationary geological patterns, have limitation in facies modeling of continental sedimentary reservoirs. The generative adversarial network (GANs) is a recent state-of-the-art deep learning method, which has capabilities of pattern learning and generation, and is widely used in the domain of image generation. Because of the similarity in content and structure between facies models and specific images (such as fluvial facies and the images of modern rivers), and the various images generated by GANs are often more complex than reservoir facies models, GANs has potential to be used in reservoir facies modeling. Therefore, this paper proposes a reservoir facies modeling method based on GANs: (1) for unconditional modeling, select training images (TIs) based on priori geological knowledge, and use GANs to learn priori geological patterns in TIs, then generate the reservoir facies model by GANs; (2) for conditional modeling, a training method of “unconditional-conditional simulation cooperation” (UCSC) is used to realize the constraint of hard data while learning the priori geological patterns. Testing the method using both synthetic data and actual data from oil field, the results meet perfectly the priori geological patterns and honor the well point hard data, and show that this method can overcome the limitation that traditional geostatistics are difficult to deal with the complex non-stationary patterns and improve the conditional constraint effect of GANs based methods. Given its good performance in facies modeling, the method has a good prospect in practical application.

scholarly journals Deep Learning-Based Computer-Aided Diagnosis System for Gastroscopy Image Classification Using Synthetic Data

2021 ◽  
Vol 11 (2) ◽  
pp. 760
Author(s):  
Yun-ji Kim ◽  
Hyun Chin Cho ◽  
Hyun-chong Cho
Keyword(s):  
Deep Learning ◽  
Disease Diagnosis ◽  
Computer Aided Diagnosis ◽  
Medical Data ◽  
Classification Model ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Original Training ◽  
Computer Aided ◽  
Aided Diagnosis

Gastric cancer has a high mortality rate worldwide, but it can be prevented with early detection through regular gastroscopy. Herein, we propose a deep learning-based computer-aided diagnosis (CADx) system applying data augmentation to help doctors classify gastroscopy images as normal or abnormal. To improve the performance of deep learning, a large amount of training data are required. However, the collection of medical data, owing to their nature, is highly expensive and time consuming. Therefore, data were generated through deep convolutional generative adversarial networks (DCGAN), and 25 augmentation policies optimized for the CIFAR-10 dataset were implemented through AutoAugment to augment the data. Accordingly, a gastroscopy image was augmented, only high-quality images were selected through an image quality-measurement method, and gastroscopy images were classified as normal or abnormal through the Xception network. We compared the performances of the original training dataset, which did not improve, the dataset generated through the DCGAN, the dataset augmented through the augmentation policies of CIFAR-10, and the dataset combining the two methods. The dataset combining the two methods delivered the best performance in terms of accuracy (0.851) and achieved an improvement of 0.06 over the original training dataset. We confirmed that augmenting data through the DCGAN and CIFAR-10 augmentation policies is most suitable for the classification model for normal and abnormal gastric endoscopy images. The proposed method not only solves the medical-data problem but also improves the accuracy of gastric disease diagnosis.

scholarly journals Improving Skin Lesion Analysis with Generative Adversarial Networks

2020 ◽  
Author(s):  
Alceu Bissoto ◽  
Sandra Avila
Keyword(s):  
Skin Lesion ◽  
State Of The Art ◽  
Synthetic Data ◽  
Clinical Information ◽  
Analysis Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Classification Models ◽  
Adversarial Networks ◽  
Lesion Analysis

Melanoma is the most lethal type of skin cancer. Early diagnosis is crucial to increase the survival rate of those patients due to the possibility of metastasis. Automated skin lesion analysis can play an essential role by reaching people that do not have access to a specialist. However, since deep learning became the state-of-the-art for skin lesion analysis, data became a decisive factor in pushing the solutions further. The core objective of this M.Sc. dissertation is to tackle the problems that arise by having limited datasets. In the first part, we use generative adversarial networks to generate synthetic data to augment our classification model’s training datasets to boost performance. Our method generates high-resolution clinically-meaningful skin lesion images, that when compound our classification model’s training dataset, consistently improved the performance in different scenarios, for distinct datasets. We also investigate how our classification models perceived the synthetic samples and how they can aid the model’s generalization. Finally, we investigate a problem that usually arises by having few, relatively small datasets that are thoroughly re-used in the literature: bias. For this, we designed experiments to study how our models’ use data, verifying how it exploits correct (based on medical algorithms), and spurious (based on artifacts introduced during image acquisition) correlations. Disturbingly, even in the absence of any clinical information regarding the lesion being diagnosed, our classification models presented much better performance than chance (even competing with specialists benchmarks), highly suggesting inflated performances.

Antinoise Learning and Coalitional Game GAN

2021 ◽  
Author(s):  
Hongyou Chen ◽  
Hongjie He ◽  
Fan Chen ◽  
Yiming Zhu
Keyword(s):  
Image Quality ◽  
Real Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Coalitional Game ◽  
Generative Adversarial Network ◽  
Adversarial Learning ◽  
Network Convergence ◽  
The Stability ◽  
Zero Sum

Adversarial learning stability has an important influence on the generated image quality and convergence process in generative adversarial networks (GANs). Training dataset (real data) noise and the balance of game players have an impact on adversarial learning stability. In the gradient backpropagation of the discriminator, the noise samples increase the gradient variance. It can increase the uncertainty in the network convergence progress and affect stability. In the two-player zero-sum game, the game ability of the generator and discriminator is unbalanced. Generally, the game ability of the generator is weaker than that of the discriminator, which affects the stability. To improve the stability, an antinoise learning and coalitional game generative adversarial network (ANL-CG GAN) is proposed, which achieves this goal through the following two strategies. (i) In the real data loss function of the discriminator, an effective antinoise learning method is designed, which can improve the gradient variance and network convergence uncertainty. (ii) In the zero-sum game, a generator coalitional game module is designed to enhance its game ability, which can improve the balance between the generator and discriminator via a coalitional game strategy. To verify the performance of this model, the generated results of the designed GAN and other GAN models in CELEBA and CIFAR10 are compared and analyzed. Experimental results show that the novel GAN can improve adversarial learning stability, generate image quality, and reduce the number of training epochs.

scholarly journals Viscous Effects in the Solid Earth Response to Modern Antarctic Ice Mass Flux: Implications for Geodetic Studies of WAIS Stability in a Warming World

2020 ◽  
Vol 33 (2) ◽  
pp. 443-459 ◽  
Author(s):  
E. Powell ◽  
N. Gomez ◽  
C. Hay ◽  
K. Latychev ◽  
J. X. Mitrovica
Keyword(s):  
Mass Flux ◽  
Crustal Deformation ◽  
Earth Model ◽  
Elastic Model ◽  
West Antarctica ◽  
Viscous Effects ◽  
Quarter Century ◽  
Viscosity Models ◽  
Earth Models ◽  
Warming World

AbstractThe West Antarctic Ice Sheet (WAIS) overlies a thin, variable-thickness lithosphere and a shallow upper-mantle region of laterally varying and, in some regions, very low (~1018 Pa s) viscosity. We explore the extent to which viscous effects may affect predictions of present-day geoid and crustal deformation rates resulting from Antarctic ice mass flux over the last quarter century and project these calculations into the next half century, using viscoelastic Earth models of varying complexity. Peak deformation rates at the end of a 25-yr simulation predicted with an elastic model underestimate analogous predictions that are based on a 3D viscoelastic Earth model (with minimum viscosity below West Antarctica of 1018 Pa s) by ~15 and ~3 mm yr−1 in the vertical and horizontal directions, respectively, at sites overlying low-viscosity mantle and close to high rates of ice mass flux. The discrepancy in uplift rate can be reduced by adopting 1D Earth models tuned to the regional average viscosity profile beneath West Antarctica. In the case of horizontal crustal rates, adopting 1D regional viscosity models is no more accurate in recovering predictions that are based on 3D viscosity models than calculations that assume a purely elastic Earth. The magnitude and relative contribution of viscous relaxation to crustal deformation rates will likely increase significantly in the next several decades, and the adoption of 3D viscoelastic Earth models in analyses of geodetic datasets [e.g., Global Navigation Satellite System (GNSS); Gravity Recovery and Climate Experiment (GRACE)] will be required to accurately estimate the magnitude of Antarctic modern ice mass flux in the progressively warming world.

scholarly journals Unpaired Low-Dose CT Denoising Network Based on Cycle-Consistent Generative Adversarial Network with Prior Image Information

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Chao Tang ◽  
Jie Li ◽  
Linyuan Wang ◽  
Ziheng Li ◽  
Lingyun Jiang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Radiation Dose ◽  
Prior Information ◽  
Low Dose ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Widespread Application ◽  
Image Information ◽  
Low Dose Ct ◽  
One To One

The widespread application of X-ray computed tomography (CT) in clinical diagnosis has led to increasing public concern regarding excessive radiation dose administered to patients. However, reducing the radiation dose will inevitably cause server noise and affect radiologists’ judgment and confidence. Hence, progressive low-dose CT (LDCT) image reconstruction methods must be developed to improve image quality. Over the past two years, deep learning-based approaches have shown impressive performance in noise reduction for LDCT images. Most existing deep learning-based approaches usually require the paired training dataset which the LDCT images correspond to the normal-dose CT (NDCT) images one-to-one, but the acquisition of well-paired datasets requires multiple scans, resulting the increase of radiation dose. Therefore, well-paired datasets are not readily available. To resolve this problem, this paper proposes an unpaired LDCT image denoising network based on cycle generative adversarial networks (CycleGAN) with prior image information which does not require a one-to-one training dataset. In this method, cyclic loss, an important trick in unpaired image-to-image translation, promises to map the distribution from LDCT to NDCT by using unpaired training data. Furthermore, to guarantee the accurate correspondence of the image content between the output and NDCT, the prior information obtained from the result preprocessed using the LDCT image is integrated into the network to supervise the generation of content. Given the map of distribution through the cyclic loss and the supervision of content through the prior image loss, our proposed method can not only reduce the image noise but also retain critical information. Real-data experiments were carried out to test the performance of the proposed method. The peak signal-to-noise ratio (PSNR) improves by more than 3 dB, and the structural similarity (SSIM) increases when compared with the original CycleGAN without prior information. The real LDCT data experiment demonstrates the superiority of the proposed method according to both visual inspection and quantitative evaluation.

Validity of Resolving the 785 km Discontinuity in the Lower Mantle with P′P′ Precursors?

2020 ◽  
Vol 91 (6) ◽  
pp. 3278-3285
Author(s):  
Baolong Zhang ◽  
Xiangfang Zeng ◽  
Jun Xie ◽  
Vernon F. Cormier
Keyword(s):  
Lower Mantle ◽  
Forward Modeling ◽  
Earth Model ◽  
Frequency Content ◽  
Waveform Data ◽  
Mantle Discontinuities ◽  
The Earth ◽  
Earth Models ◽  
Beamforming Technique ◽  
Ray Paths

Abstract P ′ P ′ precursors have been used to detect discontinuities in the lower mantle of the Earth, but some seismic phases propagating along asymmetric ray paths or scattered waves could be misinterpreted as reflections from mantle discontinuities. By forward modeling in standard 1D Earth models, we demonstrate that the frequency content, slowness, and decay with distance of precursors about 180 s before P′P′ arrival are consistent with those of the PKPPdiff phase (or PdiffPKP) at epicentral distances around 78° rather than a reflection from a lower mantle interface. Furthermore, a beamforming technique applied to waveform data recorded at the USArray demonstrates that PKPPdiff can be commonly observed from numerous earthquakes. Hence, a reference 1D Earth model without lower mantle discontinuities can explain many of the observed P′P′ precursors signals if they are interpreted as PKPPdiff, instead of P′785P′. However, this study does not exclude the possibility of 785 km interface beneath the Africa. If this interface indeed exists, P′P′ precursors at distances around 78° would better not be used for its detection to avoid interference from PKPPdiff. Indeed, it could be detected with P′P′ precursors at epicentral distances less than 76° or with other seismic phases such as backscattered PKP·PKP waves.

scholarly journals FD-GAN: Generative Adversarial Networks with Fusion-Discriminator for Single Image Dehazing

2020 ◽  
Vol 34 (07) ◽  
pp. 10729-10736 ◽  
Author(s):  
Yu Dong ◽  
Yihao Liu ◽  
He Zhang ◽  
Shifeng Chen ◽  
Yu Qiao
Keyword(s):  
Training Data ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Single Image ◽  
Image Dehazing ◽  
Atmospheric Scattering ◽  
Color Distortion ◽  
Adversarial Networks ◽  
End To End ◽  
Single Image Dehazing

Recently, convolutional neural networks (CNNs) have achieved great improvements in single image dehazing and attained much attention in research. Most existing learning-based dehazing methods are not fully end-to-end, which still follow the traditional dehazing procedure: first estimate the medium transmission and the atmospheric light, then recover the haze-free image based on the atmospheric scattering model. However, in practice, due to lack of priors and constraints, it is hard to precisely estimate these intermediate parameters. Inaccurate estimation further degrades the performance of dehazing, resulting in artifacts, color distortion and insufficient haze removal. To address this, we propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing. With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts. Moreover, we synthesize a large-scale training dataset including various indoor and outdoor hazy images to boost the performance and we reveal that for learning-based dehazing methods, the performance is strictly influenced by the training data. Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

scholarly journals Ensuring electronic medical record simulation through better training, modeling, and evaluation

2019 ◽  
Vol 27 (1) ◽  
pp. 99-108 ◽  
Author(s):  
Ziqi Zhang ◽  
Chao Yan ◽  
Diego A Mesa ◽  
Jimeng Sun ◽  
Bradley A Malin
Keyword(s):  
Structural Properties ◽  
Medical Center ◽  
Evaluation Criteria ◽  
Training Dataset ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Privacy Measures ◽  
Wide Scale ◽  
Privacy Risks ◽  
Low Prevalence

Abstract Objective Electronic medical records (EMRs) can support medical research and discovery, but privacy risks limit the sharing of such data on a wide scale. Various approaches have been developed to mitigate risk, including record simulation via generative adversarial networks (GANs). While showing promise in certain application domains, GANs lack a principled approach for EMR data that induces subpar simulation. In this article, we improve EMR simulation through a novel pipeline that (1) enhances the learning model, (2) incorporates evaluation criteria for data utility that informs learning, and (3) refines the training process. Materials and Methods We propose a new electronic health record generator using a GAN with a Wasserstein divergence and layer normalization techniques. We designed 2 utility measures to characterize similarity in the structural properties of real and simulated EMRs in the original and latent space, respectively. We applied a filtering strategy to enhance GAN training for low-prevalence clinical concepts. We evaluated the new and existing GANs with utility and privacy measures (membership and disclosure attacks) using billing codes from over 1 million EMRs at Vanderbilt University Medical Center. Results The proposed model outperformed the state-of-the-art approaches with significant improvement in retaining the nature of real records, including prediction performance and structural properties, without sacrificing privacy. Additionally, the filtering strategy achieved higher utility when the EMR training dataset was small. Conclusions These findings illustrate that EMR simulation through GANs can be substantially improved through more appropriate training, modeling, and evaluation criteria.

A THEORETICAL STUDY OF INDUCED ELECTRICAL POLARIZATION

Geophysics ◽  
1957 ◽  
Vol 22 (3) ◽  
pp. 688-706 ◽  
Author(s):  
Richard H. Frische ◽  
Haro von Buttlar
Keyword(s):  
Ground Water ◽  
Theoretical Study ◽  
Polarization Potential ◽  
Potential Difference ◽  
Electrode Configuration ◽  
Laboratory Model ◽  
Earth Model ◽  
Mathematical Solution ◽  
Electrical Polarization ◽  
Earth Models

A mathematical solution is obtained and numerically evaluated for determining the depth to a saturated aquifer when prospecting for ground water by induced electrical polarization. In a horizontally stratified earth model consisting of a nonpolarizable overburden and an underlying, infinitely deep polarizable layer, the induced‐polarization potential difference for a Wenner electrode configuration is nearly independent of the resistivity contrast. The computation agrees with results from a laboratory model tank and with a field curve. This justifies confidence in the validity of the results obtained from the model tank on earth models too complex for computation.

Sign in / Sign up

Export Citation Format

Share Document