Abstract: An inversion method for seismic wavelets and reflection coefficients, in which it is assumed that the seismic wavelets have compact support, and are smooth, and the reflection coefficients are relatively sparse. Corresponding optimization problems for the inversion of seismic wavelet and reflection coefficient sequence are constructed. By using alternating iteration, the joint inversion problem of the seismic wavelets and the reflection coefficients, which is based on compact smoothness and relative sparsity, is divided into a seismic wavelet inversion subproblem and a reflection coefficient inversion subproblem. The two subproblems are solved using a proximal algorithm. A system for implementing the inversion method is also provided herein.

Abstract: An automatic seismic facies identification method based on combination of Self-Attention mechanism and U-shape network architecture, including: obtaining and preprocessing post-stack seismic data to construct a sample training and validation dataset; building an encoder through an overlapped patch merging module with down-sampling function and a self-attention transformer module with global modeling function; building a decoder through a patch expanding module with linear upsampling function, the self-attention transformer module, and a skip connection module with multilayer feature fusion function; building a seismic facies identification model using the encoder, the decoder, and a Hypercolumn module, where the seismic facies identification model includes a Hypercolumns-U-Segformer (HUSeg); and building a hybrid loss function; iteratively training the seismic facies identification model with a training and validation set; and inputting test data into a trained identification model to obtain seismic facies co

Abstract: An automatic seismic facies identification method based on combination of Self-Attention mechanism and U-shape network architecture, including: obtaining and preprocessing post-stack seismic data to construct a sample training and validation dataset; building an encoder through an overlapped patch merging module with down-sampling function and a self-attention transformer module with global modeling function; building a decoder through a patch expanding module with linear upsampling function, the self-attention transformer module, and a skip connection module with multilayer feature fusion function; building a seismic facies identification model using the encoder, the decoder, and a Hypercolumn module, where the seismic facies identification model includes a Hypercolumns-U-Segformer (HUSeg); and building a hybrid loss function; iteratively training the seismic facies identification model with a training and validation set; and inputting test data into a trained identification model to obtain seismic facies co

Abstract: A seismic time-frequency analysis method based on generalized Chirplet transform with time-synchronized extraction, which has higher level of energy aggregation in the time direction and can better describe and characterize the local characteristics of seismic signals, and is applicable to the time-frequency characteristic representation of both harmonic signals and pulse signals, comprising the steps of processing generalized Chirplet transform with time-synchronized extraction for each seismic signal to obtain a time spectrum by: carrying out generalized Chirplet transform, calculating group delay operator and carrying out time-synchronized extraction on seismic signals, thereby the boundary and heterogeneity structure of the rock slice are more accurately and clearly shown and subsequence seismic analysis and interpretation are facilitated.

Abstract: The present disclosure provides a method of high-resolution amplitude-preserving seismic imaging for a subsurface reflectivity model, including: performing reverse time migration (RTM) to obtain an initial imaging result, performing Born forward modeling on the initial imaging result to obtain seismic simulation data, and performing RTM on the seismic simulation data to obtain a second imaging result; performing curvelet transformation on the two imaging results, performing pointwise estimation in a curvelet domain, and using a Wiener solution that matches two curvelet coefficients as a solution of a matched filter; and applying the estimated matched filter to the initial imaging result to obtain a high-resolution amplitude-preserving seismic imaging result.

Abstract: A model-driven deep learning-based seismic super-resolution inversion method includes the following steps: 1) mapping each iteration of a model-driven alternating direction method of multipliers (ADMM) into each layer of a deep network, and learning proximal operators by using a data-driven method to complete the construction of a deep network ADMM-SRINet; 2) obtaining label data used to train the deep network ADMM-SRINet; 3) training the deep network ADMM-SRINet by using the obtained label data; and 4) inverting test data by using the deep network ADMM-SRINet trained at step 3). The method combines the advantages of a model-driven optimization method and a data-driven deep learning method, and therefore the network has the interpretability; and meanwhile, due to the addition of physical knowledge, the iterative deep learning method lowers requirements for a training set, and therefore an inversion result is more reliable.

Abstract: Disclosed herein is a method of stripping a strong reflection layer based on deep learning. The method establishes a direct mapping relationship between a strong reflection signal and seismic data of a target work area through a nonlinear mapping function of the deep neural network, and strips a strong reflection layer after the strong layer is accurately predicted. A mapping relationship between the seismic data containing the strong reflection layer and an event of the strong reflection layer is directedly found through training parameters. In addition, this method does not require an empirical parameter adjustment, and only needs to prepare a training sample that meets the actual conditions of the target work area according to the described rules.

Abstract: A model-driven deep learning-based seismic super-resolution inversion method includes the following steps: 1) mapping each iteration of a model-driven alternating direction method of multipliers (ADMM) into each layer of a deep network, and learning proximal operators by using a data-driven method to complete the construction of a deep network ADMM-SRINet; 2) obtaining label data used to train the deep network ADMM-SRINet; 3) training the deep network ADMM-SRINet by using the obtained label data; and 4) inverting test data by using the deep network ADMM-SRINet trained at step 3). The method combines the advantages of a model-driven optimization method and a data-driven deep learning method, and therefore the network has the interpretability; and meanwhile, due to the addition of physical knowledge, the iterative deep learning method lowers requirements for a training set, and therefore an inversion result is more reliable.

Abstract: Disclosed herein is a method of stripping a strong reflection layer based on deep learning. The method establishes a direct mapping relationship between a strong reflection signal and seismic data of a target work area through a nonlinear mapping function of the deep neural network, and strips a strong reflection layer after the strong layer is accurately predicted. A mapping relationship between the seismic data containing the strong reflection layer and an event of the strong reflection layer is directedly found through training parameters. In addition, this method does not require an empirical parameter adjustment, and only needs to prepare a training sample that meets the actual conditions of the target work area according to the described rules.

Abstract: The present disclosure provides a method of high-resolution amplitude-preserving seismic imaging for a subsurface reflectivity model, including: performing reverse time migration (RTM) to obtain an initial imaging result, performing Born forward modeling on the initial imaging result to obtain seismic simulation data, and performing RTM on the seismic simulation data to obtain a second imaging result; performing curvelet transformation on the two imaging results, performing pointwise estimation in a curvelet domain, and using a Wiener solution that matches two curvelet coefficients as a solution of a matched filter; and applying the estimated matched filter to the initial imaging result to obtain a high-resolution amplitude-preserving seismic imaging result.

Abstract: A seismic time-frequency analysis method based on generalized Chirplet transform with time-synchronized extraction, which has higher level of energy aggregation in the time direction and can better describe and characterize the local characteristics of seismic signals, and is applicable to the time-frequency characteristic representation of both harmonic signals and pulse signals, comprising the steps of processing generalized Chirplet transform with time-synchronized extraction for each seismic signal to obtain a time spectrum by: carrying out generalized Chirplet transform, calculating group delay operator and carrying out time-synchronized extraction on seismic signals, thereby the boundary and heterogeneity structure of the rock slice are more accurately and clearly shown and subsequence seismic analysis and interpretation are facilitated.