Rock Physical Modeling of Tight Sandstones Based on Digital Rocks and Reservoir Porosity Prediction From Seismic Data

Shear wave velocity plays an important role in both reservoir prediction and pre-stack inversion. However, the current deep learning-based shear wave velocity prediction methods have certain limitations, including lack of training dataset, poor model generalization, and poor physical interpretability. In this study, the theoretical rock physics models are introduced into the construction of the labeled dataset for deep learning algorithms, and a forward simulation of the theoretical rock physics models is utilized to supplement the dataset that incorporates geological and geophysical knowledge. This markedly increases the physical interpretability of the deep learning algorithm. Theoretical rock physics models for two different types of reservoirs, i.e., conventional sandstone and tight sandstone reservoirs, are first established. Then, a full-sample labeled dataset is constructed using these two types of theoretical rock physics models to traverse the elasticity parameter space of the two types of reservoirs through random variation and combination of parameters in the theoretical models. Finally, based on the constructed full-sample labeled dataset, four parameters (P-wave velocity, clay content, porosity, and density) that are highly correlated with the shear wave velocity are selected and combined with a deep neural network to build a deep shear wave velocity prediction network with good generalization and robustness, which can be directly applied to field data. The errors between the predicted shear wave velocity using the deep neural network and the measured shear wave velocity data in the laboratory and the logging data in three real field work areas are less than 5%, which are much smaller than the errors predicted by both Han’s and Castagna’s empirical formula. Furthermore, the prediction accuracy and generalization performance are better than those of these two common empirical formulas. The forward simulation based on theoretical models supplements the training dataset and provides high-quality labels for machine learning. This can considerably improve the interpretability and generalization of models in real applications of a machine learning algorithm.

Section: Theoretical Rock Physics Modeling For Multi-type Reservoirsmentioning

confidence: 99%

Shear wave velocity prediction based on deep neural network and theoretical rock physics modeling

Feng

Zeng²,

Xu³

et al. 2023

“…Under 100% water saturation, the nuclear magnetic resonance (NMR) T 2 spectrum of each core sample was produced using the NUMAG's C12-010 V low-field NMR spectrometer. The three-dimensional pictures of nano-and micron-scale pores were characterized using CT scanning technology (Wu et al, 2020b(Wu et al, , 2020cLiu et al, 2022b;Guo et al, 2022;Liu et al, 2022), which facilitated the analysis of the marl micropores and their three-dimensional connectivity. An Ultra XRM-L200 microscope was used to perform a threedimensional CT scan of the full-diameter core samples (XRM).…”

Section: Pore-throat Structure Analysismentioning

confidence: 99%

Reservoir characteristics and factors influencing shahejie marl in the shulu sag, bohai bay basin, eastern China

Fu²,

Zhu³

et al. 2022

Shahejie marl in the Shulu Sag is a crucial resource for unconventional hydrocarbon exploration in China. Although breakthroughs have been made in tight oil exploration in this area, the mechanisms underlying the formation of this marl reservoir and factors controlling its ‘sweet spots’ have not been thoroughly studied. To understand the pore structure characteristics and factors influencing the marl reservoir, we analyzed core samples from Wells ST1 and ST3. A series of experiments was conducted on the samples, such as X-ray diffraction, focused ion beam scanning electron microscopy, micro-CT, and total organic carbon test. Additionally, the physical properties of different marl rock fabrics were studied with auxiliary tests, such as mercury intrusion capillary pressure analyses, nuclear magnetic resonance, porosity and permeability tests, and thin-section observation. The results revealed that the marl reservoir is characterized by low porosity (1.61%) and low permeability (2.56mD). The porosity and permeability (1.61% and 3.26mD) of laminated marl were better than those (0.92% and 1.68mD) of massive marl. Clay minerals and quartz content in laminated (11.8 and 8.2%) was less than in massive marl (16.2 and 13.3%). The marl pores include intercrystalline pores, dissolution pores, and microfractures. Additionally, the laminated marl pores were primarily distributed along the dark lamina, with good connectivity. A few isolated and uniform holes were observed in the massive marl. Influenced by rock fabric and mineral composition, layered fractures were mainly developed in the laminated marl, while structural fractures were the main type of microfractures in the massive marl. The primary sedimentary mechanism was the main geological action underlying the differences in marl rock fabric; this mechanism affects the physical properties of the marl reservoir, which are key factors to be considered when searching for the marl reservoir ‘sweet spots’. Particular attention should be paid to these factors during tight oil exploration and development in similar sedimentary basins.

“…Rock classification is the basis for studying geological reservoir characteristics and plays an essential role in vast fields, such as geotechnical engineering, mineralogy, petrology, rock mechanics, and mineral resource prospecting (Karimpouli and Tahmasebi, 2019;Guo et al, 2022;Houshmand et al, 2022). The efficiency of rock classification is closely associated with the efficiency of geological surveys and therefore needs urgent attention.…”

Section: Introductionmentioning

confidence: 99%

Rock image classification using deep residual neural network with transfer learning

Chen

Su²,

Chen³

et al. 2023

Rock image classification is a significant part of geological research. Compared with traditional image classification methods, rock image classification methods based on deep learning models have the great advantage in terms of automatic image features extraction. However, the rock classification accuracies of existing deep learning models are unsatisfied due to the weak feature extraction ability of the network model. In this study, a deep residual neural network (ResNet) model with the transfer learning method is proposed to establish the corresponding rock automatic classification model for seven kinds of rock images. ResNet34 introduces the residual structure to make it have an excellent effect in the field of image classification, which extracts high-quality rock image features and avoids information loss. The transfer learning method abstracts the deep features from the shallow features, and better express the rock texture features for classification in the case of fewer rock images. To improve the generalization of the model, a total of 3,82,536 rock images were generated for training via image slicing and data augmentation. The network parameters trained on the Texture Library dataset which contains 47 types of texture images and reflect the characteristics of rocks are used for transfer learning. This pre-trained weight is loaded when training the ResNet34 model with the rock dataset. Then the model parameters are fine-tuned to transfer the model to the rock classification problem. The experimental results show that the accuracy of the model without transfer learning reached 88.1%, while the model using transfer learning achieved an accuracy of 99.1%. Aiming at geological engineering field investigation, this paper studies the embedded deployment application of the rock classification network. The proposed rock classification network model is transplanted to an embedded platform. By designing a rock classification system, the off-line rock classification is realized, which provides a new solution for the rock classification problem in the geological survey. The deep residual neural network and transfer learning method used in this paper can automatically classify rock features without manually extracting. These methods reduce the influence of subjective factors and make the rock classification process more automatic and intelligent.