19 March 2020 in Interpretation
Seismic fault interpretation is one of the key steps for seismic structure interpretation, which is a time-consuming task and strongly depends on the experience of the interpreter. Aiming to automate fault interpretation, we have considered it as an image segmentation issue and adopt a solution using a residual UNet (ResUNet), which introduces residual units to UNet. Using the ResUNet model, we develop a fault-versus-azimuth analysis based on offset vector tile data, which, as common-azimuth seismic data, provide more detailed and useful information for interpreting seismic faults. To avoid manual efforts for picking training labels and the inaccuracy introduced by different interpreters, we use synthetic seismic data with a random number of faults with different locations and throws as the training and validation data sets. ResUNet is finally trained using only synthetic data and tested on field data. Field data applications show that the proposed fault-detection algorithm using ResUNet can predict seismic faults more accurately than coherence- and UNet-based approaches. Moreover, geologic fault interpretation results computed using common-azimuth data exhibit higher lateral resolution than those computed using poststack seismic data.
10 November 2021 in IEEE Transactions on Geoscience and Remote Sensing
Sedimentary cycle division is an important step for sequence stratigraphy analysis. For the division of sedimentary cycle using seismic data, a key issue is characterizing the changes of dominant frequencies caused by the changes of stratum thickness with high accuracy and high resolution. The synchrosqueezing transform (SST) can provide a time–frequency (TF) representation with high resolution by synchrosqueezing the TF spectrum, which helps the sedimentary cycle identification. Unfortunately, it is a hard task to choose an appropriate basic wavelet, which influences the accuracy of the SST to characterize the sedimentary cycle. To solve this issue, we construct a synchrosqueezing optimal basic wavelet transform (SOBWT) to optimally characterize the sedimentary cycle. We first propose a criterion to construct the basic wavelet of SST by deriving the dominant frequency location condition and defining the similarity coefficient condition of the basic wavelet. Then, we introduce the optimal basic wavelet (OBW) to construct the basic wavelet that satisfies the dominant frequency location condition and the similarity coefficient condition. Note that we term the SST with a basic wavelet that satisfies the dominant frequency location condition and the similarity coefficient condition as the SOBWT. Finally, we apply the proposed SOBWT to synthetic and field data to testify its validity and effectiveness and compare it with conventional SST-based methods. The application results illustrate that it is much more convenient and easier for the sedimentary cycle division based on the SOBWT results.
16 May 2022 in IEEE Transactions on Geoscience and Remote Sensing
Random noise attenuation (NA) is a key step in seismic field data processing. With the rise of artificial intelligence, deep learning (DL) algorithms are gradually introduced into seismic random noise suppression. The most commonly used DL paradigm takes mean squared error (MSE) as loss function, the default assumption is that its error term obeys independently identically distribution (IID) Gaussian, and its noise level involved preset-hyperparameters in the local area of data cannot be adjusted adaptively in the training phase. This leads to the poor generalization of deep denoiser on Non-IID noises. In this study, we propose a DL framework based on Non-IID pixel-wise Gaussian noise modeling, which integrates NA and noise level estimation into a unique Bayesian framework. The framework can adaptively characterize the noise and data distribution in the local area of noisy data through the variational inference (VI) technique, which allows the network to see more noises of varying degrees and learn effective information from them. Thus, our proposed framework called VI-Non-IID inclines to have better noise characterization and generalization capabilities, which brings better performance on seismic field NA. Furthermore, we conduct a series of experiments on seismic synthetic and field data to test the performance of two implementations of VI-Non-IID: VI-Non-IID (Unet) and VI-Non-IID denoising convolution network (DnCNN). A lot of results validate the superiority of our proposed VI-Non-IID framework. Specifically, VI-Non-IID can explicitly predict the denoised data and its corresponding noise level map simultaneously, and succeed in attenuating unknown field noises while preserving the useful seismic signals.
4 June 2020 in IEEE Geoscience and Remote Sensing Letters
Continuous wavelet transform (CWT) is an effective tool for seismic time-frequency (TF) analysis. Selecting a matched wavelet to the analyzed seismic wavelet is a key issue for accurately characterizing TF features of seismic data. The three-parameter wavelet (TPW) can match different seismic wavelets by adjusting the three parameters. However, it is difficult to select appropriate parameters for matching TPW to seismic wavelets in real applications. In this letter, we propose a basic wavelet construction method by using the TPW and the deep learning network. The proposed workflow first builds a mapping relationship between seismic wavelet and seismic data by using the alternating iterative deep neural network (AIDNN). Based on this relationship, we then estimate a seismic wavelet. Using the estimated seismic wavelet, we can finally construct an analytical basic wavelet by matching the TPW to the extracted wavelet. Note that we named the TPW with optimal parameters as the optimal basic wavelet (OBW), and its wavelet transform is OBWT. To demonstrate the validity and effectiveness of the proposed approach, we apply it to synthetic traces and field data for characterizing their TF features. The results show that OBWT preserves the amplitude better and has a higher resolution than the CWT with mismatched basic wavelets to the seismic wavelet, which is helpful for seismic data analysis in the future.
22 September 2021 in Geophysics
Seismic acoustic-impedance (AI) inversion, which estimates the AI of the reservoir from seismic and other geophysical data, is a type of nonlinear inverse problem that faces the local minima issue during optimization. Without requiring an accurate initial model, global optimization methods have the ability to jump out of local minima and search for the optimal global solution. However, the low-efficiency nature of global optimization methods hinders their practical application, especially in large-scale AI inversion problems (AI inversion with a large number of traces). We have developed a new intelligent seismic AI inversion method based on global optimization and deep learning. In this method, global optimization is used to generate data sets for training a deep-learning network, and it is used to first accelerate and then surrogate global optimization. In other words, for large-scale seismic AI inversion, global optimization only inverts the AI model for a few traces, and the AI models of most traces are obtained by deep learning. The deep-learning architecture that we used to map from the seismic trace to its corresponding AI model is established based on U-Net. Because the time-consuming global optimization inversion procedure can be avoided for most traces, this method has a significant advantage over conventional global optimization methods in efficiency. To verify the effectiveness of our method, we compare its performance with the conventional global optimization method on 3D synthetic and field data examples. Compared to the conventional method, our method only needs approximately one-tenth of the computation time to build AI models with better accuracy.
8 March 2022 in Journal of Applied Geophysics