28 October 2019 in Geophysics
Seismic structural interpretation involves highlighting and extracting faults and horizons that are apparent as geometric features in a seismic image. Although seismic image processing methods have been proposed to automate fault and horizon interpretation, each of which today still requires significant human effort. We improve automatic structural interpretation in seismic images by using convolutional neural networks (CNNs) that recently have shown excellent performances in detecting and extracting useful image features and objects. The main limitation of applying CNNs in seismic interpretation is the preparation of many training data sets and especially the corresponding geologic labels. Manually labeling geologic features in a seismic image is highly time-consuming and subjective, which often results in incompletely or inaccurately labeled training images. To solve this problem, we have developed a workflow to automatically build diverse structure models with realistic folding and faulting features. In this workflow, with some assumptions about typical folding and faulting patterns, we simulate structural features in a 3D model by using a set of parameters. By randomly choosing the parameters from some predefined ranges, we are able to automatically generate numerous structure models with realistic and diverse structural features. Based on these structure models with known structural information, we further automatically create numerous synthetic seismic images and the corresponding ground truth of structural labels to train CNNs for structural interpretation in field seismic images. Accurate results of structural interpretation in multiple field seismic images indicate that our workflow simulates realistic and generalized structure models from which the CNNs effectively learn to recognize real structures in field images.
16 March 2020 in Geophysics
Constructing a relative geologic time (RGT) image from a seismic image is crucial for seismic structural and stratigraphic interpretation. In conventional methods, automatic RGT estimation from a seismic image is typically based on only local image features, which makes it challenging to cope with discontinuous structures (e.g., faults and unconformities). We have considered the estimation of 2D RGT images as a regression problem, where we design a deep convolutional neural network (CNN) to directly and automatically compute an RGT image from a 2D seismic image. This CNN consists of three parts: an encoder, a decoder, and a refinement module. We train this CNN by using 2080 pairs of synthetic input seismic images and target RGT images, and then we test it on 960 testing seismic images. Although trained with only synthetic images, the network can generate accurate results on real seismic images. Multiple field examples show that our CNN-based method is significantly superior to conventional methods, especially in dealing with complex structures such as crossing faults and complicatedly folded horizons, without the need of any manual picking.
22 September 2021 in Geophysical Journal International
SUMMARY: Subsurface velocity model building is a crucial step for seismic imaging. It is a challenging problem for conventional methods such as full-waveform inversion (FWI) and wave equation migration velocity analysis (WEMVA), due to the highly nonlinear relationship between subsurface velocity values and seismic responses. In addition, traditional FWI and WEMVA methods are often computationally expensive. In this paper, we propose to apply a deep learning technique to construct subsurface velocity models automatically from common-image gather (CIG) volumes. In our method, pairs of synthetic velocity models and CIG volumes are generated to train a convolutional neural network. Our proposed network achieves promising results on different synthetic data sets. The training performance of several commonly used loss functions is also studied.
12 September 2021 in Journal of Geophysical Research: Solid Earth
Extracting horizons and detecting faults in a seismic image are basic steps for structural interpretation and important for many seismic processing schemes. A common ground of the two tasks is to analyze seismic structures and they are related to each other. However, previously proposed methods deal with the tasks independently, and challenge remains in each of them. We propose a volume‐to‐volume neural network to estimate a relative geologic time (RGT) volume from a seismic volume, and this RGT volume is further used to simultaneously interpret horizons and faults. The network uses U‐shaped framework with attention mechanism to systematically aggregate multi‐scale information and automatically highlight informative features, and achieves high prediction accuracy with affordable computational costs. To train the network, we build thousands of 3‐D noisy synthetic seismic volumes and corresponding RGT volumes with realistic and various structures. We introduce a loss function based on structure similarity to capture spatial dependencies among seismic samples for better optimizing the network, and use multiple reasonable assessments to evaluate the predicted results. Trained by using synthetic data, our network outperforms the conventional approaches in recognizing structural features in field data examples. Once obtaining an RGT volume, we can not only obtain seismic horizons by simply extracting RGT constant surfaces but also detect faults that are indicated by lateral RGT discontinuities. To be able to deal with large seismic volumes, we further propose a workflow to first estimate sub‐volumes of RGT and merge them to obtain a full RGT volume without boundary artifacts.
21 March 2022 in IEEE Transactions on Neural Networks and Learning Systems
Accurate estimation of reservoir parameters (e.g., permeability and porosity) helps to understand the movement of underground fluids. However, reservoir parameters are usually expensive and time-consuming to obtain through petrophysical experiments of core samples, which makes a fast and reliable prediction method highly demanded. In this article, we propose a deep learning model that combines the 1-D convolutional layer and the bidirectional long short-term memory network to predict reservoir permeability and porosity. The mapping relationship between logging data and reservoir parameters is established by training a network with a combination of nonlinear and linear modules. Optimization algorithms, such as layer normalization, recurrent dropout, and early stopping, can help obtain a more accurate training model. Besides, the self-attention mechanism enables the network to better allocate weights to improve the prediction accuracy. The testing results of the well-trained network in blind wells of three different regions show that our proposed method is accurate and robust in the reservoir parameters prediction task.
21 October 2022 in Interpretation
We have proposed a deep neural network-based framework for seismic facies classification. We implement two different neural networks based on the architectures of DeepLabv3+ and generative adversarial network for segmentation and compare the mapping results from seismic reflection data to lithologic facies. DeepLabv3+ predictions have sharper boundaries between the predicted facies whereas generative adversarial network output has a better continuity of predicted facies. We incorporate uncertainty analysis into the workflow using a Bayesian framework. The proposed approach consisting of joint analysis of predicted facies from multiple networks along with uncertainty in prediction accelerates the interpretation process by reducing the need for human intervention and also lessens individual biases that an interpreter may bring. We determine the effectiveness of the proposed algorithm by testing on field data examples, and we find that the proposed workflow classifies facies accurately. This may potentially enable the development of depositional environment maps in areas of low well density.