Full waveform inversion (FWI) seeks a subsurface parameter model that optimally matches the true state by minimizing the differences between synthetic and observed data. However, when starting from a rough initial model, FWI is often limited by the weak low-frequency energy of the observed data and the difficulty of matching surface-related multiples (SRMs), especially when the source wavelet is not readily available. Source wavelet errors also affect the general inversion result. We propose a multiscale virtual wavefield waveform inversion (VWWI) based on multidimensional interferometric retrieval (MDIR) to mitigate these challenges. We use MDIR to retrieve the virtual response from the up- and down-going wavefields separated from the original data and infer the velocity using the virtual response instead of the original data. MDIR integrates the source functions using multidimensional cross correlation (MDCC) and then suppresses the source imprints from the original data through multidimensional deconvolution (MDD). The retrieved virtual responses have a broader bandwidth and are dominated by primary reflection events. It addresses simultaneously three major challenges that FWI faces through a one-time data retrieval. Assigning self-setting source functions with different dominant frequencies to the virtual response allows the extraction of virtual observed data to different frequency bands for multiscale velocity inversion. Considering the possible amplitude distortion and the computational cost, we propose the hybrid source cross-correlation objective function adapted to VWWI. Numerical examples of well-known models representing weak and strong scattering media show that the proposed VWWI method can stably achieve wide-scale velocity modeling from macroscopic background to delicate structures.

The accuracy of microseismic source localization depends largely on the quality of the velocity model. Due to the anisotropy of the rock mass, the current uniform velocity model is no longer sufficient for high-precision localization. Additionally, the time-varying property of the velocity model will influence the accuracy of the estimated source location. Focusing on these challenges, we propose an iterative source location estimation and simplified anisotropic velocity inversion method based on the neural network algorithm and dynamic reduction of solution interval. We first introduce a simplified anisotropic velocity model and establish an objective function for source localization. The t-distribution is embedded in the neural network algorithm to increase the probability of jumping out of the local optimum. In each iteration, the solution interval is narrowed down and then the source location is estimated by the neural network algorithm. The initial solution interval is determined from the inversion results of the uniform velocity model. The performance of the proposed method is evaluated by the numerical and blasting experiments. The location accuracy of the proposed method is at least 40% higher than that of the conventional method. Test results indicate that our method is effective to locate the sources in the areas with heterogeneous and complex media.

Passive source seismic interferometry is a cost-effective geophysical method that converts noise signals into valuable information. The fidelity of the resultant common-shot gather is pivotal for effective imaging. The quality of reconstructed records via seismic interferometry directly correlates with the duration of background noise observation. However, practical applications often encounter difficulties in obtaining stable and usable long-duration observations of noise-based passive seismic records. Short-duration observations may introduce spurious physical events, thereby compromising the reliability of seismic wavefield imaging and geological interpretation. In this study, we introduce MDUNETR, an advanced passive data reconstruction network amalgamating Transformer and Multi-scale Dense Blocks (MDB) to enhance accuracy. By integrating Transformer and MDB, the network effectively captures both global and local information. Utilizing the MDUNETR network, we can reconstruct accurate passive source interferometric seismic records from short-duration noise interference signals. This overcomes the time limitations imposed by seismic interferometry on the original noise records. Theoretical data applications demonstrate the stability and fidelity of the seismic records reconstructed by this network, ensuring reliable results.

The pivotal role of seismic velocity inversion in oil and gas exploration and geological research has been widely acknowledged. However, conventional methods face challenges such as strong reliance on initial models and high computational costs. Based on the mode of seismic event generation, seismic data can be classified into active seismic data and passive seismic data, which collectively constitute the multisource data discussed in this article. Velocity inversion based on deep learning primarily relies on active seismic data, training neural networks to learn the mapping between seismic records and subsurface velocities. In contrast, signals in passive seismic data typically originate from noise at certain depths within the Earth, encompassing valuable information about deep subsurface structures that is crucial for velocity inversion, thus presenting a potential complement to active seismic data. This study proposes a seismic velocity inversion method that combines active and passive seismic data, utilizing deep learning techniques to adaptively integrate data from both sources, enabling joint inversion. The proposed neural network architecture combines transformer and convolutional neural network (CNN), enhancing the accuracy and robustness of velocity inversion.

The passive seismic interferometry (SI), harnessing ambient noise or unconventional seismic sources, has garnered widespread attention in the fields of Earth science and resource exploration. Conventional SI requires several assumptions to be satisfied, including uniform distribution of subsurface sources, an adequate number of sources, and long recording periods. However, these assumptions often fall short in real-world scenarios, leading to suboptimal reconstruction quality and subsequently impacting imaging results. Therefore, we propose a passive SI method with deep transfer learning. This method can extract real-time empirical Green’s functions directly from noisy datasets without prior preprocessing. Importantly, this technique goes beyond simple data retrieval; it demonstrates the ability to accurately reconstruct the entire wavefield. We establish a joint transformer-CNN network and conduct supervised training on intricate velocity models. Subsequently, we employ transfer learning to fine-tune the model, adapting it to new data that differ from the training dataset. Notably, our method requires only a small amount of data and can be applied to other velocity models without additional training for new neural networks. The validity of our method is demonstrated through a series of numerical experiments. Compared to conventional methods, real-time passive SI offers greater efficiency and accuracy in reconstructing subsurface structural response.

Full-waveform inversion (FWI) of deep seismic reflection (DSR) data is an important tool to obtain the high-resolution velocity structures of the earth’s crust. Due to complex source excitation conditions and wavefield characteristics, FWI of land DSR data faces more difficulties than offshore applications. Aiming at the difficulty of large-volume land explosive source estimation, we propose a double-time-shift waveform inversion method, which can obtain accurate source functions in the presence of inaccurate near-surface velocities and strong interference. In order to improve the stability of FWI on land DSR data, a dual multiscale waveform inversion strategy based on frequency band and waveform is constructed, which can sequentially recover the large-scale and fine-scale velocity structure information of the subsurface medium. Numerical tests on the modified Marmousi model demonstrate that the method proposed in this article can obtain relatively accurate source functions and velocity models under complex conditions such as inaccurate near-surface velocity, noise, and strong near-offset interference. The proposed method is applied to the first DSR profile in the Kumkol Basin, and fine-scale velocity structures shallower than 6 km are successfully obtained, revealing the uplift, fault distribution, and stratigraphic sedimentation characteristics inside the basin, which all support the view that the Kumkol Basin may have good oil and gas prospects.

In passive source seismic surveys, signal continuity and signal-to-noise ratios have always tended to be low. On the one hand, since passive-source seismic surveys are often used for large-scale illumination of subsurface formations, the distances between receivers and sampling point intervals tend to be large. On the other hand, interference from coherent noise and spurious in-phase axes is unavoidable in passive source reconstruction recordings because of the signal originating from noise in the subsurface. All these problems lead to the continuity and signal-to-noise ratio of the virtual shot reconstructed from passive source seismic surveys are not guaranteed, which affects further processing and seriously limits the application of passive source seismic surveys. The traditional interpolation reconstruction methods cannot take noise suppression into account, or require additional operations to achieve both interpolation reconstruction and denoising. Based on this, this paper utilizes the powerful data processing ability of convolutional neural networks to design a global multi-scale fusion residual shrinkage network (GMF-RS) to solve the above passive source seismic exploration problem. It is tested that the trained network not only eliminates coherent noise and false events, but also improves the continuity in horizontal and vertical directions, enhances and extracts the effective signals, and provides better virtual shot records for subsequent seismic data processing. In addition, we designed a dual-input network and introduced active source seismic records as a complement to the passive source virtual seismic records, so that the processed waveforms can show better details.

The source wavelet is the initial condition of wavefield forward modelling, so its accuracy has a direct impact on the quality of full waveform inversion and reverse time migration. At present, the source wavelet estimation method based on wave equation, such as the reverse-time propagation algorithm and the L2 norm waveform inversion method, are all affected by the data quality and shallow velocity accuracy. In this paper, a robust source wavelet inversion method based on correlation norm waveform inversion is proposed. The near-offset direct waves are used to construct the cross-correlated objective function. The gradient expression is deduced by taking the source wavelet as the unknown. The proposed method only needs to invert short-time near-offset direct waves, so it has high computational efficiency. The cross-correlation objective function is mainly used to invert the phase information of the source wavelet, which is not sensitive to the data amplitude error, so it is more robust than the existing methods. Numerical examples show that the proposed method can still provide reliable source wavelets even when the velocity model is inaccurate, the data contains noise and there are bad traces. We also obtain high-quality source function inversion results by applying the proposed method to land deep reflection seismic data.

Recognition of microseismic events is the primary task of microseismic monitoring. Aiming at the low signal-to-noise ratio (SNR) of weak microseismic events and the high cost of labeling them, an unsupervised learning method for recognizing microseismic events is proposed. The method first recognizes microseismic events from monitoring data segments by simultaneous deep clustering and then performs a second clustering to further pick the first arrival times of the detected microseismic events by multistage deep clustering. The networks in this two-step clustering framework are built on a newly designed residual shrinkage dense block (RSDB). To better suppress the noise in microseismic data, RSDB adds a densely connected hybrid dilated convolution and an improved threshold module to the deep residual shrinkage network. The autoencoder built by the RSDB and U-Net architecture is combined with simultaneous deep clustering and multistage deep clustering to recognize microseismic events and their first arrival times, respectively. Finally, tests on the synthetic data and field microseismic data demonstrate the feasibility and superiority of the proposed method.

Traditional full waveform inversion (FWI) highly depends on sufficient low-frequency data or a good initial model. Passive seismic data contain rich low-frequency components, and passive seismic FWI using virtual source data by seismic interferometry (SI) is a promising method. However, the distribution of passive sources in the subsurface is always inhomogeneous, which will lead to artifacts in the reconstruction results by SI using cross-correlation (CC). SI by multidimensional deconvolution (MDD) can counteract the source inhomogeneity but requires the separation of the reference wavefields, which is difficult to achieve for noise source data. To mitigate this problem, we propose an improved SI method by linear Radon transform based multidimensional deconvolution (LRTMDD). The interferometric point-spread function can be extracted more accurately and efficiently in the linear Radon domain, thus improving the reconstruction results. The passive virtual source full waveform inversion (PVSFWI) based on LRTMDD is further proposed, which can effectively use the low-frequency information in the virtual source data to invert the macroscopic velocity structures even in the case of inhomogeneous source distributions, and without the need to estimate the virtual source wavelets. A joint multi-source FWI strategy is proposed to solve the problem of missing low-frequency data suffered by active source FWI. Numerical experiments on the Marmousi model and the SEG/EAGE overthrust model show that the proposed methods can fully combine the respective advantages of multisource seismic data to stably achieve high-accuracy velocity models in the case of inhomogeneous passive source distributions and the lack of low-frequency data in active seismic data.

Least-squares reverse time migration (LSRTM) aims to produce a high-quality migration image of complex geological structures. However, the weaker deep seismic reflections are often masked by the overlying strata in migration images. Therefore, it is difficult for the LSRTM to image the deeper structures. This letter proposes a phase-amplitude LSRTM (PA-LSRTM) in the time-frequency domain to improve the migration image of deep seismic reflections and subsalt structures. The PA-LSRTM is formulated as an inverse problem that minimizes the time-frequency phase-amplitude difference between the predicted and observed data. The seismic data was initially transformed into the time-frequency domain to establish a PA-LSRTM misfit. An amplitude factor was then introduced in the time-frequency misfit to weaken the weights of amplitude components. In this case, it emphasized the similarity of phase components. Furthermore, the sparsity promotion method was combined with a simultaneous source technique to increase the computational efficiency and reduce the crosstalk noise. The PA-LSRTM with sparsity promotion (SPA-LSRTM) misfit can finally be solved using a Fast Iterative Shrinkage-Thresholding Algorithm (FISTA). The numerical and marine field data tests demonstrate that the SPA-LSRTM can effectively produce a high-resolution image of deep structures.

Locating microseismic sources in time is a challenging problem in microseismic monitoring. In order to improve the accuracy and efficiency of locating sources, this paper presents a method for locating microseismic sources using deep reinforcement learning. We first construct and train a convolutional autoencoder to preprocess the seismic records in the microseismic waveform database. Then, the problem of locating the source is described as a Markov decision process for the application of deep reinforcement learning. We decompose the task of locating the source into three subtasks and design the critical elements of deep reinforcement learning. Three agents independently learn optimal policies for their respective subtasks in the framework of a deep Q-network (DQN) and jointly determine the precise location of the microseismic source. Finally, we evaluate the proposed method using synthetic data generated from the Marmousi model and the 3D velocity model. The experiment results indicate that the proposed method can locate microseismic sources efficiently and accurately.

The performance of the microseismic monitoring technique depends greatly on the accuracy of microseismic event localization. Recently, machine learning (ML) methods have been extensively implemented for the localization of microseismic events. These neural networks are typically trained using numerous microseismic events labeled with known source locations. Obtaining enough microseismic events with good source locations can be difficult and costly. To overcome this shortcoming, we present a microseismic events localization method using semi-supervised generative adversarial networks (GANs). We utilize limited labeled seismograms and large amounts of unlabeled seismograms to train the semi-supervised GANs, thus improving the prediction ability of the networks. Finally, we evaluate the performance of the proposed method using synthetic microseismic data and field data. Comparison with the supervised learning methods on the same microseismic data shows that the proposed method can significantly improve the accuracy of locating microseismic sources in the lack of sufficient source labels.

Least-squares reverse time migration (LSRTM) attempts to produce a high-quality image for complicated subsurface structures. However, large amplitude discrepancies between the synthetic and observed seismic data are problematic for high-resolution imaging. Alternatively, correlative LSRTM (CLSRTM) misfit has been proposed to improve the imaging quality of complicated structures. However, the CLSRTM ignores the local characteristics of the 2-D seismic data. Thus, we developed a 2-D local correlative misfit for LSRTM (2-D-LCLSRTM) to improve the imaging resolution. In this case, a 2-D sliding window was used to obtain local-scale seismic data. A 2-D correlation method was then used to measure the similarity between the local-scale synthetic and observed data. Consequently, the 2-D-LCLSRTM misfit could reduce amplitude constraints and emphasize phase similarity, which has a potential for improving deep structure as it can boost weak seismic signals. To suppress the migration artifacts, we incorporated the sparsity promotion method with the 2-D-LCLSRTM misfit and used the fast iterative shrinkage-thresholding algorithm (FISTA) to solve it iteratively. In the numerical examples, a Marmousi model, a Salt model, and a marine field seismic dataset were used to test the effectiveness of the 2-D-LCLSRTM method. Compared with the commonly used RTM and sparsity promotion-based CLSRTM methods, the 2-D-LCLSRTM with sparsity promotion can better image deep reflectors and obtain high-resolution imaging results.

Time-frequency analysis can reveal local variations and allow for separation of phase and amplitude information of nonstationary seismic waveforms. Seismic signals are used since long as a robust tool for inversion of underground structures, as has been the practice in geophysical exploration. However, the mixing of phase and amplitude in seismic data increases the nonlinearity of seismic inversion. The authors first use Gabor transform to separate the phase and amplitude information of envelope data, and then introduce an adaptive factor into the misfit function to redistribute the weight of phase and amplitude information for direct envelope inversion (DEI) in the time-frequency domain. By adopting this procedure, greater flexibility can be achieved in operating the local phase of envelope and waveform spectra to enhance stability of multiscale phase inversion. For DEI, the direct envelope Fréchet derivative is used, and thus, no weak scattering assumption is imposed on the joint multiscale DEI of phase and amplitude (PADEI). Compared with the DEI method, the PADEI can better recover the deeper parts of salt-bottom and subsalt structures by boosting the signal energy and weakening the nonlinearity of the waveform inversion.