Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
For reservoir structural models with obvious nonstationary and heterogeneous characteristics, traditional geostatistical simulation methods tend to produce suboptimal results. Additionally, these methods are computationally resource-intensive in consecutive simulation processes. Thanks to the feature extraction capability of deep learning, the generative adversarial network-based method can overcome the limitations of geostatistical simulation and effectively portray the structural attributes of the reservoir models. However, the fixed receptive fields may restrict the extraction of local geospatial multiscale features, while the gradient anomalies and mode collapse during the training process can cause poor reconstruction. Moreover, the sparsely distributed conditioning data lead to possible noise and artifacts in the simulation results due to its weak constraint ability. Therefore, this paper proposes an improved conditioning spectral normalization generation adversarial network framework (CSNGAN-ASPP) to achieve efficient and automatic reconstruction of reservoir geological bodies under sparse hard data constraints. Specifically, CSNGAN-ASPP features an encoder-decoder type generator with an atrous spatial pyramid pooling (ASPP) structure, which effectively identifies and extracts multi-scale geological features. A spectral normalization strategy is integrated into the discriminator to enhance the network stability. Attention mechanisms are incorporated to focus on the critical features. In addition, a joint loss function is defined to optimize the network parameters and thereby ensure the realism and accuracy of the simulation results. Three types of reservoir model were introduced to validate the reconstruction performance of CSNGAN-ASPP. The results show that they not only accurately conform to conditioning data constraints but also closely match the reference model in terms of spatial variance, channel connectivity, and facies attribute distribution. For the trained CSNGAN-ASPP, multiple corresponding simulation results can be obtained quickly through inputting conditioning data, thus achieving efficient and automatic reservoir geological model reconstruction.
For reservoir structural models with obvious nonstationary and heterogeneous characteristics, traditional geostatistical simulation methods tend to produce suboptimal results. Additionally, these methods are computationally resource-intensive in consecutive simulation processes. Thanks to the feature extraction capability of deep learning, the generative adversarial network-based method can overcome the limitations of geostatistical simulation and effectively portray the structural attributes of the reservoir models. However, the fixed receptive fields may restrict the extraction of local geospatial multiscale features, while the gradient anomalies and mode collapse during the training process can cause poor reconstruction. Moreover, the sparsely distributed conditioning data lead to possible noise and artifacts in the simulation results due to its weak constraint ability. Therefore, this paper proposes an improved conditioning spectral normalization generation adversarial network framework (CSNGAN-ASPP) to achieve efficient and automatic reconstruction of reservoir geological bodies under sparse hard data constraints. Specifically, CSNGAN-ASPP features an encoder-decoder type generator with an atrous spatial pyramid pooling (ASPP) structure, which effectively identifies and extracts multi-scale geological features. A spectral normalization strategy is integrated into the discriminator to enhance the network stability. Attention mechanisms are incorporated to focus on the critical features. In addition, a joint loss function is defined to optimize the network parameters and thereby ensure the realism and accuracy of the simulation results. Three types of reservoir model were introduced to validate the reconstruction performance of CSNGAN-ASPP. The results show that they not only accurately conform to conditioning data constraints but also closely match the reference model in terms of spatial variance, channel connectivity, and facies attribute distribution. For the trained CSNGAN-ASPP, multiple corresponding simulation results can be obtained quickly through inputting conditioning data, thus achieving efficient and automatic reservoir geological model reconstruction.
Oil and natural gas rank first as energy inputs worldwide. Other subsurface resources, such as salt, provide clues to obtaining these natural resources. Salt accumulation areas are subsurface resources used to locate oil and gas fields. Seismic images, which are geological data, provide information for locating underground resources. Manual interpretation of these images requires expert knowledge and experience. This time-consuming and laborious method is also limited by the fact that it cannot be replicated. Deep learning is a very successful method for image segmentation in recent years. Automating the detection of subsurface reserves in seismic images using artificial intelligence methods reduces time, cost and workload factors. In this study, we aim to identify salt areas using U-net architecture on the salt identification challenge shared by TGS (the world’s leading geoscience data company) Salt Identification Challenge on kaggle.com. In addition, the effect of data augmentation methods on the designed system is investigated. The data set used in the system consists of seismic images that are combined together for automatic detection of salt mass. The study aims to obtain the highest accuracy and the lowest error rate to detect salt areas from seismic images. As a result of the study, the IoU (Intersection over Union) value of the system designed without data augmentation method is 0.9390, while the IoU value of the system designed using data augmentation method is 0.9445.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.