In this paper, we propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way to address this ill-posed seismic inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong non-uniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model as well as the timevarying property of seismic data. To approach these challenges, we propose an end-to-end Seismic Inversion Networks (SeisInvNet for short) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup and global context of its corresponding seismic profile. Then from enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our proposed SeisInv dataset according to various evaluation metrics, and the inversion results are more consistent with the target from the aspects of velocity value, subsurface structure and geological interface. In addition to the superior performance, the mechanism is also carefully discussed, and some potential problems are identified for further study. Index Terms-Seismic inversion, Deep neural networks.
We used a novel iterative estimation scheme for separation of blended seismic data from simultaneous sources. The scheme is based on an augmented estimation problem that can be solved by iteratively constraining the deblended data using shaping regularization in the seislet domain. We formulated the forward modeling operator in the commonreceiver domain, in which two sources were assumed to be blended using a random time-shift dithering approach. The nonlinear shaping-regularization framework offered some freedom in designing a shaping operator to constrain the model in an underdetermined inverse problem. We designed the backward operator and the shaping operator for the shaping-regularization framework. The backward operator can be optimally chosen as half of the identity operator in the two-source case, and the shaping operator can be chosen as coherency-promoting operator. The high performance deblending effect of the iterative framework was tested on three numerically blended synthetic data sets and one numerically blended field data set. Compared with alternative f-k domain thresholding and f-x predictive filtering, seislet-domain soft thresholding exhibits the most robust behavior.
Random noise attenuation always played an important role in seismic data processing. One of the most widely used methods for suppressing random noise was [Formula: see text] predictive filtering. When the subsurface structure becomes complex, this method suffered from higher prediction errors owing to the large number of different dip components that need to be predicted. We developed a novel denoising method termed [Formula: see text] empirical-mode decomposition (EMD) predictive filtering. This new scheme solved the problem that makes [Formula: see text] EMD ineffective with complex seismic data. Also, by making the prediction more precise, the new scheme removed the limitation of conventional [Formula: see text] predictive filtering when dealing with multidip seismic profiles. In this new method, we first applied EMD to each frequency slice in the [Formula: see text] domain and obtained several intrinsic mode functions (IMFs). Then, an autoregressive model was applied to the sum of the first few IMFs, which contained the high-dip-angle components, to predict the useful steeper events. Finally, the predicted events were added to the sum of the remaining IMFs. This process improved the prediction precision by using an EMD-based dip filter to reduce the dip components before [Formula: see text] predictive filtering. Synthetic and real data sets demonstrated the performance of our proposed method in preserving more useful energy.
Automatic waveform classification and arrival picking methods are widely studied to reduce or replace the manual works. Machine learning based methods, especially neural networks, and clustering based methods have shown great potentials in previous studies. However, most of the existing methods are sensitive to noise. The convolution neural networks (CNNs), developed from the traditional neural networks, have been successfully applied in many different fields, but are rarely studied in seismic waveform classification. In this paper, we propose a novel antinoise CNN architecture for waveform classification and also propose to combine k‐means clustering (KC) with CNN classification to pick arrivals (CNN‐KC). Seismic data are sampled to 1‐D vectors using a specific time window. Using the trained CNN classifier, these 1‐D vectors are classified into two categories: waveform and nonwaveform. With the constraint of the first waveform, CNN‐KC can pick the arrival more accurately. We also apply the proposed methods to the synthetic microseismic data with different noise levels and the actual field microseismic data to test their robustness. CNNs perform much better than the traditional multilayer perceptron on the waveform classification of the noisy microseismic data. Based on the analysis of the CNN internal architecture, we also conclude that the main reason that CNN is insensitive to noise is the convolution and pooling layers which behave like smooth operation in some ways. The final results show that the CNN and CNN‐KC are effective and robust methods for waveform classification and arrival picking.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.