Prediction of Subsurface NMR T2 Distributions in a Shale Petroleum System Using Variational Autoencoder-Based Neural Networks

Li, Hao; Misra, Siddharth

doi:10.1109/lgrs.2017.2766130

Cited by 63 publications

(20 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many empirical methods have been proposed for the estimation of permeability based on the characteristic parameters of the T 2 distribution in downhole NMR applications, including the Schlumberger-Doll Research (SDR) method and the Timur-Coates method (Daigle & Dugan, 2009;Liu et al, 2017;Liu et al, 2019;Timur, 1968). However, existing NMR-based methods for S wb and permeability estimations generally require the inversion of the NMR echo data to obtain the T 2 distribution, which is an ill-posed problem of the Fredholm equation of the first kind (Li & Misra, 2017;Venkataramanan et al, 2002;Venkataramanan et al, 2010;Zou et al, 2015). Small changes in the measured NMR echo data due to noise can result in large differences in the T 2 distribution.…”

Section: Introductionmentioning

confidence: 99%

Nuclear Magnetic Resonance Characterization of Petrophysical Properties in Tight Sandstone Reservoirs

2020

View full text Add to dashboard Cite

Permeability and bound water saturation (Swb) are key parameters reflecting the petrophysical properties of porous rocks. Nuclear magnetic resonance (NMR) has proved to be effective in investigating the properties of porous media. However, estimating Swb and the permeability in tight sandstone reservoirs based on conventional NMR methods, which requires the inversion of NMR echo data to obtain the transverse relaxation time (T2) distribution, proves to be a challenging task. In this study, a method is proposed to estimate Swb and the permeability in tight sandstone reservoirs based on the direct analysis of NMR echo data, thus avoiding the inversion process. A total of 20 tight sandstone samples from the Ordos Basin in China was taken for laboratory NMR measurements. The kernel function of the echo data was used to characterize the ratio distribution of bound water volume to pore volume for different pore sizes. Following this, an echo data calibration method was applied to estimate Swb without the inversion of the T2 distribution, and the window method was used to reduce the impact of noise in the echo data. Furthermore, models for estimating permeability were proposed based on the determined windows of the NMR echo data in the Swb estimation. The reliability of the proposed method for estimating Swb and permeability was verified by comparing the estimated and experimental results. Our study provides an efficient method for the estimation of petrophysical parameters in porous rocks based on the direct analysis of NMR echo data.

show abstract

Section: Introductionmentioning

confidence: 99%

Nuclear Magnetic Resonance Characterization of Petrophysical Properties in Tight Sandstone Reservoirs

2020

View full text Add to dashboard Cite

show abstract

“…The detailed comparison between different methods is shown in Table 3. Part (1) of Table 3 shows the LVQ classification accuracies under different sub-feature-extraction-methods that make up the DLVM, their values varies with different Classification accuracy % (10), and MIE(100) can better characterize S1 and S5. The EMD-AE and TIR have a good effect on the classification of S2 and S4.…”

Section: Lvq Accuracymentioning

confidence: 99%

“…Numerous methods have been proposed for the feature extraction and classification in the field of petroleum operation decision-making and system diagnosis [4], such as coastal oil tank detection [5], oil spill detection [6], pipeline leakage detection [7], tool wear prediction [8], and working status inspection [9]. Li [10] used nuclear magnetic resonance to investigate the internal structure of geomaterials filled with fluid. Firoozabadi [11] built a wellprediction model based on a pressure drop.…”

Section: Introductionmentioning

confidence: 99%

“…Ahmadi [16] proposed a welltesting identification model for the pressure transient test data using the concept of shapelets. Xu [10] extracted the features by a three-level wavelet packet transform (WPT) from the resultant force converted from thrust and torque. Zheng [17] analyzed the real-time mud signals and designed a feature extraction method based on the intrinsic mode functions through the ensemble empirical mode decomposition (EMD).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Deep Vector Learning Model Applied for Oil-Well-Testing Feature Mining, Purification and Classification

Feng

Ren

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Well-testing stage analysis is an important way for oilfield operation state decision-making and reservoir management. However, due to the variability and nonlinearity of the downhole data caused by the complex exploration activities and the differences of petroleum type and geological conditions, the classical methods are ineffective in feature extraction, learning network construction, and classifier optimization. In this work, we propose a new well-testing stage classification method based on a deep vector learning model (DVLM). The novelty of this study lies in the combination of multi-feature extraction, deep learning and feature vector mapping. The proposed method can overcome the problems of poor feature representation ability and poor classification model generalization ability in the existing machine learning methods, which mainly caused by the non-optimized training network structure and the unreasonable classifier design,. Firstly, the initial features are obtained by four classical methods. Then a five layers deep belief network embedded with the mutual information coefficient method is implemented for further feature extraction and purification. Finally, the optimized learning vector quantization classifier outputs the predicted tags. For model training and testing 572 field samples total of 4004 data streams are used. By considering the classification errors and accuracy metrics, the neurons number of deep learning network and the classifier are tuned, and an optimal and stable framework is obtained. Comparative experimental results with several classical integration models show that the proposed model achieves the highest classification accuracy of 98.065% as well as the least of features (nine). The results demonstrate that the proposed model has excellent performance in improving the classification accuracy and completing the feature compression. Moreover, the proposed model has very important practical significance for guiding the automatic analysis and processing oil and gas data. INDEX TERMS Well-testing stage analysis; Feature extraction; Deep belief network; Learning vector quantization.

show abstract

“…The VAEs have met with great success in recent years in several applicative areas including anomaly detection [6][7][8][9], text classification [10], sentence generation [11], speech synthesis and recognition [12][13][14], spatio-temporal solar irradiance forecasting [15] and in geoscience for data assimilation [2]. In other respects, the two major application areas of the VAEs are the biomedical and healthcare recommendation [16][17][18][19], and industrial applications for nonlinear processes monitoring [1,3,4,[20][21][22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Adversarial Variational Autoencoder

Zemouri

2020

MAKE

View full text Add to dashboard Cite

We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we use a consistency principle for deep features. The main contributions are threefold. Firstly, our approach perfectly combines the two models, i.e., GAN and VAE, and thus improves the generation and reconstruction performance of the VAE. Secondly, the VAE training is done in two steps, which allows to dissociate the constraints used for the construction of the latent space on the one hand, and those used for the training of the decoder. By using this two-step learning process, our method can be more widely used in applications other than image processing. While training the encoder, the label information is integrated to better structure the latent space in a supervised way. The third contribution is to use the trained encoder for the consistency principle for deep features extracted from the hidden layers. We present experimental results to show that our method gives better performance than the original VAE. The results demonstrate that the adversarial constraints allow the decoder to generate images that are more authentic and realistic than the conventional VAE.

show abstract

Prediction of Subsurface NMR T2 Distributions in a Shale Petroleum System Using Variational Autoencoder-Based Neural Networks

Cited by 63 publications

References 6 publications

Nuclear Magnetic Resonance Characterization of Petrophysical Properties in Tight Sandstone Reservoirs

Nuclear Magnetic Resonance Characterization of Petrophysical Properties in Tight Sandstone Reservoirs

Automatic Deep Vector Learning Model Applied for Oil-Well-Testing Feature Mining, Purification and Classification

Semi-Supervised Adversarial Variational Autoencoder

Contact Info

Product

Resources

About