Over the past few decades, electromagnetic field signals have been widely used to develop data interpretation methods for the ground controlled source electromagnetic (CSEM) method in the frequency domain. However, identifying anomalous features from these signals remains challenging, as the intensity of the signals linked to these anomalies is weaker. To address this issue, this paper presents an inversion algorithm that utilizes apparent resistivity data to enhance anomaly detection. Due to the high computational complexity and memory demands of 3D CSEM inversion modeling, many real-world surveys are interpreted using 1D inversion schemes, which simplifies the modeling process but may limit accuracy. A quasi-2D inversion imaging technique based on the tracking balance operator (hereafter referred to as QITB) is introduced to balance efficiency and interpretive accuracy. Rather than performing 3D inversion, QITB applies 1D modeling in a structured framework to approximate 3D subsurface structures. This imaging-focused algorithm eliminates the need for complex 3D computations while maintaining high accuracy in identifying subsurface anomalies. Numerical simulations demonstrate that wide-field apparent resistivity is significantly more effective than electric field data in highlighting subsurface anomalies. Inversion results from synthetic data show that QITB identifies anomalies and yields more accurate estimates of burial depth. In contrast, conventional 1D inversion without the tracking balance operator, although capable of fitting 3D data, fails to approximate the true 3D model closely. In conclusion, QITB is an innovative and efficient method for rapidly interpreting 3D ground CSEM data, combining computational efficiency with reliable subsurface structure identification.

With the advancements of three-component seismic instruments, much valuable information about source distributions and subsurface structures can be utilized to improve passive surface-wave imaging with anthropogenic seismic noise in urban environments. Current passive surface-wave methods, however, are mainly concerned with the Rayleigh waves in the vertical (Z) component, often neglecting the useful dispersion information in the radial (R) and transverse (T) components, particularly in higher modes of surface waves. So, we introduced the common-midpoint two-station analysis (CMP-TS) to extract the multimode dispersion curves of Rayleigh and Love waves from three-component noise recordings using multicomponent ambient seismic noise cross-correlations (ZZ, RR, and TT components). Results from synthetic data sets from given models show that the CMP-TS method is able to retrieve higher-mode Rayleigh waves from the RR component and improve the multimode dispersion measurements of Rayleigh waves by the summation of the ZZ and RR spectrograms. Besides, this method can extract multimode dispersion curves of Love waves with high resolution from the TT component. We applied the CMP-TS method to process three-component field data and retrieved the dispersion curves of Rayleigh waves with the fundamental and the first higher modes, as well as Love waves with the fundamental, the first, and second higher modes. The S-wave velocity model is constructed by inverting the fundamental and higher mode data and validated through borehole S-wave velocity measurements.

In recent years, deep learning techniques have increasingly been applied to gravity inverse problems, and ResU-Net++ has demonstrated significant success in density-detail preservation during image segmentation and feature extraction. However, its large parameter space and high computational demand make it prone to overfitting. Diffusion models, conversely, excel at generating detailed samples and handling noisy data but generally underperform in segmentation tasks compared to ResU-Net++. To address these challenges, we propose ResDM-Net++, a novel framework that integrates the essential modules of ResU-Net++ into a diffusion model while embedding geophysical insights throughout. Specifically, we employ multi-channel gravity inputs obtained from physically forward-modeled density distributions to ensure that both localized and global subsurface features are learned. Moreover, rather than applying a generic denoising approach, the diffusion component is carefully adapted to retain the inherent spatial correlations of geophysical data, thus improving inversion stability and mitigating overfitting risks. Finally, ResDM-Net++ further embeds physics-based constraints into both the encoder-decoder path and the diffusion steps, forging a synergy between robust denoising and domain-focused feature extraction. Numerical study shows that ResDM-Net++ accurately recovers subsurface density anomalies, exhibiting clear model boundaries and minimal fitting errors. In field applications, it successfully delineates the F2 salt dome in Norway’s Nordkapp Basin with boundaries closely matching seismic interpretations, underscoring ResDM-Net++’s effectiveness in gravity data analysis, structural reconstruction, and inversion in both synthetic and real-world scenarios.

Reconstruction of complete seismic data is a crucial step in seismic data processing, which has seen the application of various convolutional neural networks (CNNs). These CNNs typically establish a direct mapping function between input and output data. In contrast, diffusion models which learn the feature distribution of the data, have shown promise in enhancing the accuracy and generalization capabilities of predictions by capturing the distribution of output data. However, diffusion models lack constraints based on input data. In order to use the diffusion model for seismic data interpolation, our study introduces conditional constraints to control the interpolation results of diffusion models based on input data. Furthermore, we improving the sampling process of the diffusion model to ensure higher consistency between the interpolation results and the existing data. Experimental results conducted on synthetic and field datasets demonstrate that our method outperforms existing methods in terms of achieving more accurate interpolation results, with SSIM outperforming existing methods by 4.1% and SNR by 24%. Our implementation is available at https://github.com/WAL-l/Reconstruction.

In geophysical exploration methods, the Semi-Airborne Transient Electromagnetic (SATEM) technique offers substantial exploration depth and the capability to acquire precise underground characteristics. However, the SATEM signal received by the induction coil has a low amplitude in the middle and late stages and is susceptible to various noise effects. Although a variety of conventional denoising methods are available today, their performance is often unsatisfactory, necessitating manual adjustments of the denoising outcomes. With the emergence of deep learning in various fields, several SATEM denoising neural network models have been proposed. However, these models are discriminative model and focus on modeling conditional probabilities, with insufficient generalization capabilities when faced with small data sets. On the other hand, the Variational Diffusion Model (VDM) is a generative model that captures the joint distribution and exhibits excellent generalization capabilities. Building upon this premise, we explored a VDM-based denoising approach for SATEM. Nevertheless, due to the uncontrollable nature of the results generated by VDM, it is not possible to use VDM directly for denoising SATEM signals. To address this issue, we introduce the VDM-based denoiser with constraints, which incorporates guiding conditions to constrain the model and generate desired denoising results, and proposed a new SATEM signal denoising network called TEMSGnet. To further enhance the practical applicability of our method in real-world scenarios, we incorporate a wavelet transform-based supervised fine-tuning strategy. Experimental results demonstrate that TEMSGnet achieves effective denoising performance on both synthetic and real datasets. Furthermore, through inversion, TEMSGnet can more accurately approximate the true subsurface characteristics, thereby effectively reflecting the denoised outcomes. The code is available at https://github.com/woldier/TEMSGnet.

Semi-airborne transient electromagnetic (EM) method is an effective exploration tool in complex environment due to its utilization of unmanned aerial platforms for data collection. With the escalating demands of detection accuracy, the conventional one-dimensional (1D) inversion is no longer sufficient. Over the last two decades, there has been rapid development in three-dimensional (3D) EM inversions. For semi-airborne transient EM method, it usually has a substantial number of receiver stations. To obtain accurate 3D solutions, one has to refine the grids near the receiver points, which causes huge number of grids and reduces computational efficiency. Thus, the computational complexity is one of primary factors restricting the practicality of 3D inversions. In this paper, we have developed an approach using decoupled meshes. This method uses a serial of meshes to parallelly calculate the forward modeling and Jacobian information, with one mesh containing only a subset of receiver points. This scheme aims to decrease the number of grids and improve the efficiency. After that, we map the results to an overarching inversion mesh using the node cloud technique and renew the model parameters. We check our algorithm via both synthetic and field data. Numerical experiments show that the decoupled mesh inversion method can effectively recover the location and resistivities of the anomalies under the complex topography. When compared with the conventional inversion method, the decoupled mesh inversion method can significantly reduce the calculation time.

In recent years, much attention has been paid to using deep learning techniques for land seismic first break (FB) picking. Among these, the deep learning-based 3-D FB picking method has shown stronger noise resistance than the 2-D method, as it simultaneously considers the correlation of FBs in both crossline and inline directions. In existing studies, whether using 2-D or 3-D methods, they are often regarded as a binary semantic segmentation problem of pre- and post-FB (PPFB). The FB time is determined by dividing the image with a binary classification mask. However, due to the instability of the decision threshold setting of the PPFB mask strategy, different thresholds can cause different FB picking results. Considering this, we propose a two-channel (2C) mask strategy that utilizes the feature interaction between a strip-like mask and a line-like mask to predict the confidence of FBs in seismic traces, thus realizing the FB picking with uniqueness. In addition, to enhance the global feature acquisition capability of the network, we construct a 3-D FB picking network USwinNet based on Swin Transformer, which establishes a larger receptive field through a multistage self-attention (SA) mechanism. Experimental results demonstrate that our method significantly improves the picking accuracy compared to existing methods. It also exhibits strong generalization capabilities, making it more suitable for practical engineering under complex geological conditions.

Nearly all global datasets from satellite missions have been instrumental in advancing research on regional and global-scale underground density structures. However, satellite gravity inversion faces challenges such as instability, multiple solutions, and low resolution due to the ill-posed nature of the problem. Methods like depth-weighting and different norms improve resolution but can introduce instability and noise sensitivity, requiring further refinement for optimal results. This article proposes a novel gravity inversion method in spherical coordinates, employing dynamically re-weighting matrix to enhance inversion resolution. Initially, weights are assigned to each tesseroid based on cross-correlation coefficients, forming an initial model weighting matrix. This matrix is then iteratively optimized by minimizing two regularized objective functions that incorporate the kernel matrix and observed data, refining the weights distribution to better approximate the actual geological situation. Synthetic model studies demonstrate that this method significantly improves the resolution of inversion results, particularly in identifying gently dipping density anomalies. Application of this method to the India-Asia collision zone reveals consistent subduction plate geometry with previous studies, validating its practicality and effectiveness in imaging intricate density patterns. This approach offers a substantial advancement in gravity inversion techniques, providing clearer and more accurate geological models.

Seismic data noise processing is an important part of seismic exploration data processing, and the effect of noise elimination is directly related to the follow-up processing of data. In response to this problem, many authors have proposed methods based on rank reduction, sparse transformation, domain transformation, and deep learning. However, such methods are often not ideal when faced with strong noise. Therefore, we propose to use diffusion model theory for noise removal. The Bayesian equation is used to reverse the noise addition process, and the noise reduction work is divided into multiple steps to effectively deal with high-noise situations. Furthermore, we propose to evaluate the noise level of blind Gaussian seismic data using principal component analysis to determine the number of steps for noise reduction processing of seismic data. We train the model on synthetic data and validate it on field data through transfer learning. Experiments show that the proposed method can identify most of the noise with less signal leakage. This has positive significance for high-precision seismic exploration and future seismic data signal processing research.

Electromagnetic (EM) methods are widely used in geophysical exploration. Different EM methods offer varying detection depths and resolutions. Magnetotelluric (MT) typically provides information about deep structures, whereas controlled-source EM (CSEM) is more effective in imaging shallow targets. To enhance the resolution of subsurface structures, a joint inversion of MT and CSEM data is proposed. In this article, we combine MT and CSEM data and perform joint inversion using the limited-memory Broyden–Fletcher–Goldfarb–Shanno (L-BFGS) algorithm. To balance the two data types, we propose a data weighting scheme based on the square root of the ratio of the number of data points. To improve the accuracy of forward responses and the reliability of the inversion, we use a high-order adaptive finite-element forward modeling method. The forward modeling mesh and inversion mesh are decoupled to prevent the over-parameterization of the inversion mesh. In addition, this approach uses an algorithm based on posteriori error estimators to guide the adaptive refinement process of the forward modeling mesh. The accuracy and efficiency of the forward modeling method are verified using a layered model. The inversion results of two complex models demonstrate that the joint inversion method offers superior resolution compared to standalone inversions.

For a long time, the 2-D and 3-D Magnetotelluric (MT) forward modeling is mainly accomplished by computational methods. Traditional methods are time consuming due to the large amounts of discrete grids and slow solution of the matrix equation. Therefore, finding a fast forward modeling algorithm remains a major concern. In recent years, deep learning has provided new ways to accomplish this goal. Most existing deep learning-based MT forward modeling are performed on 2-D data, and there is a lack of research on the feasibility of 3-D problems. this paper constructs a large-scale 3-D MT dataset; employs a deep neural network suitable for 3-D MT data patterns, and improving the training efficiency through a transfer learning strategy for similar tasks, that can predict the apparent resistivity and phases in different polarization directions, and realizes fast and high-precision 3-D MT deep learning forward modeling. The experimental quantitative metrics show that the mean relative errors of apparent resistivity and phase are 0.6042% and 0.2423%, respectively, and the mean absolute errors are 1.6726 and 0.0994, respectively. When applying the method to geoelectric models that are more complex than the training set, accurate forward modeling results validate its generalization ability. The research may provide methodological and data support for larger-scale 3-D MT forward modeling in the future.

The stark contrast in density between geological layers is a fundamental aspect in the examination of basic geological structures. The delineation between the crystalline basement and sedimentary layers, moreover, is pivotal in the pursuit of strategic energy resources, such as petroleum and natural gas. Traditional full space density inversion, however, is beleaguered by issues of stability and resolution, impeding the accurate characterization of the sharp density interface. To rectify these shortcomings, we introduce an innovative methodology for estimating 2-D depth-to-basement and overlying density distribution, employing a deep neural network with a leaky rectified linear unit as an activation function. Evaluation of the proposed method on simulated sedimentary basin models underscores its superior ability to discern complex geometries of basin boundaries and overlying density, despite the presence of various degrees of Gaussian noise. In practical application to the Poyang basin, the relief of the Cretaceous basement is proficiently recovered through vertical gravity field data, with validation provided by corresponding seismic sections and well-established stratigraphic markers.

The inversion of logging-while-drilling (LWD) measurements using deep learning (data-driven approach) is a rapidly growing topic of interest in well geosteering. Deep learning (DL) inversion constructs a complex nonlinear mapping from data to model and has extremely high inversion efficiency. A purely data-driven approach requires large amounts of representative training samples from both the model and data spaces to build robust networks, which may not conform to the physical constraints of the problem. The lack of physical knowledge can limit the effectiveness of DL networks when applied to new scenarios. The regularization inversion (physics-driven approach) is a very efficient local optimization technique but is prone to be trapped into local minima, and the inversion results cannot be obtained in real-time. We propose a coupled physics-driven and data-driven approach to address this issue and construct a DL workflow. A 2.5D model including dip, fault, and anisotropic formation is considered to evaluate the proposed method. Comparing the inversion imaging performance of the proposed physics-driven approach with the traditional residual network (ResNet) shows a significant improvement in the accuracy of the reconstructed resistivity model. Finally, the robustness is evaluated by adding a noise generalization network.

The application of neural networks to seismic first break (FB) picking research has been developed for many years. Numerous multitrace FB picking methods based on convolutional neural networks (CNNs) have been proposed. Among them, the pickup method of semantic segmentation networks based on fully convolutional networks (FCNs) is proven to have stronger noise immunity. However, when in the data with drastic variations in the FBs between local adjacent traces, because of the feature extraction method of FCNs for convergence information around the data, the network output feature edge tends to smooth, which leads to a flattening of the FBs of the multitrace pickup, which is not conducive to picking traces with drastic intertrace FB variations. Therefore, we use Transformer, a weight-transfer model that relies on the self-attention (SA) mechanism to calculate weights between input and output data, to extract FB features. The 2-D seismic data are flattened into a 1-D sequence along the time dimension of the trace and input to the network, and the spatial information of the FBs of the adjacent traces is considered without disrupting the time-series semantic information. The correlation between any element of the sequence and other elements is calculated to obtain the sequence feature weights. We use Swin Transformer as the backbone and combine the features of U-shaped networks to design an end-to-end FB picking network—STUNet. The results show that STUNet has higher FB picking accuracy than current FCNs and is more effective in local adjacent traces where the FB time variation is drastic.

Automatic extraction of high-precision roads from remote sensing images is crucial for path planning and road monitoring. However, there is room to improve the accuracy and generalization of existing methods in segmentation due to the challenges posed by ground object occlusion and complex backgrounds. Most existing methods rely on convolutional neural networks (CNNs), but the limitations of convolution prevent direct semantic interaction at a distance. In contrast, Mix-Transformer obtains long-term modeling capability through the self-attention mechanism, and inspired by it, we propose a multiscale self-adaptive network (UMiT-Net) based on the U-shaped structure. First, UMiT-Net extracts global features with the efficient Mix-Transformer backbone. Second, the dilated attention module (DAM) is used in the bottleneck of the network to fuse semantic features further to ensure the connectivity of the road. Third, in the decoder, to improve the accuracy of road segmentation, we construct the multiscale self-adaptive module (MSAM), which summarizes rich scene understanding from dense contexts with strip windows conforming to road morphology, and embed an edge enhancement module (EEM) to correct road edges. Finally, we design patch expanding (PE), which solves the problem of heavy computation of upsampling due to high resolution. The experimental results show that our UMiT-Net is substantially ahead of other state-of-the-art methods and has a significant improvement in generalization ability.

The Dahongshan deposit is influenced by pronounced structural controls and intrusions, and its model of mineralization resulting from volcanic sedimentation has faced criticism for an extended period. To describe the deep structure and distribution characteristics of the ore deposit, and to investigate its ore-forming process and metallogenic model, this study employs the gravity, magnetic, and controlled source audio-magnetotelluric data with different scales to independently recover the density, magnetization intensity, and electrical resistivity for shedding light on the deep structure and mineralization distribution of the deposit. The inversion results show the presence of a giant intrusion extending up to 6 km deep within the deposit. The distribution of iron-rich ore bodies and deposit are controlled by the basement tilting and faults, with the deposit exhibiting a U-shaped distribution and the mineral body occurring in a lens-like shape. Additionally, the electrical results indicate the presence of high-resistance magma along faults that intrude the deposit. We propose that the deposit is a magmatic-related deposit, with a deep intrusion believed to be the residual source body from early rift intrusion, providing the source for mineralization of the deposit. The characteristics of the deposit controlled by east-west and north-south structures and the lenticular orebody distribution indicate that the deposit is closely influenced by regional structure and magmatism of fault intrusion. The mineralization model is proposed to be a result of the coordinated actions of structural, magmatic, and regional dynamic background for the breakup and convergence of supercontinents.

The accurate and efficient forward modeling of the transient electromagnetic (TEM) method requires proper mesh generation, which influences both calculation speed and response accuracy. This paper presents a three-dimensional (3D) TEM forward modeling method that achieves high accuracy by using a frequency-domain to time-domain transformation strategy and adaptive mesh refinements in the frequency-domain. Specifically, an interpolation-based Fourier transform method is employed to reduce the number of computed frequencies in the frequency-domain, resulting in significant efficiency improvement without compromising accuracy. Furthermore, the method incorporates unstructured tetrahedral meshes and an adaptive finite element algorithm based on posterior error estimators to enhance the accuracy of the frequency-domain response calculation. The proposed method is applied to the widely used long-offset TEM (LOTEM) system. The accuracy of the method is verified by comparing the simulated response of a layered model with the analytical solution. Additionally, the effectiveness of the algorithm is tested using three 3D models. Cross-validation results with other popular open-source codes demonstrate that the proposed method can achieve high accuracy and efficiency for both simple and complex models.

The study and assessment of the subsurface density distribution are vital for mining and oil & gas exploration. This can be achieved by the three-dimensional (3D) inversion of the observed gravity and gravity gradiometry (GG) data. Due to the ill-posedness of the geophysical inverse problem, the nonuniqueness and instability of solutions represent the main difficulties in inversion. In recent years, convolutional neural networks, especially U-net technology, have found wide applications in image processing, recognition, and reconstruction. This paper proposes using this method for fast reconstruction of the subsurface density models based on the ResUnet technology. The developed new method was examined on two 3D synthetic gravity and gravity gradiometry datasets inversion. The results show that the ResUnet network can reconstruct the density anomaly with sharp boundaries and is robust to the noise, making the solution stable.

Neural networks (NNs) are efficient tools for rapidly obtaining geoelectric models to solve magnetotelluric (MT) inversion problems. Training an NN with strong predictive power requires numerous training samples to prevent underfitting. To reduce the computational burden of generating a large number of training samples, this work analyzes the influence of the sample features and distribution on the training effect for an NN and proposes an efficient method of sample generation. This innovative method consists of three steps: 1) geoelectrically simplifying the features; 2) removing unnecessary features on the basis of realistic geological characteristics; and 3) mapping the samples to a higher-dimensional space. Numerical examples based on simple stratified models show that the number of samples can be reduced to below one-millionth of the original number while improving the predictive effect of the NN. The performance and effectiveness for processing more complex structures are verified by the inversion results obtained for a public data set, COPROD2. We conclude that this advanced method can generate high-quality training samples at a greatly reduced computational cost. The analysis of the sample features and distribution not only advances the state of research on the use of machine learning in geophysical inversion but also is a forward-looking study on the mechanisms of underfitting, tracing the source of these phenomena back to the training samples used.

Semi-airborne transient electromagnetic (SATEM) method has been efficiently used recently in geophysical exploration due to its relatively portability compared to the standard airborne surveys. However, the SATEM data are often complicated by induced polarization (IP) effects manifesting as abnormal decay and sign reversal in the responses. The IP information can be extracted from SATEM data by joint inversion of the electromagnetic data into the electrical resistivity and IP parameters described in Cole-Cole model. In this paper, we introduce a quasi-two-dimensional inversion scheme to recover the resistivity and IP parameters from SATEM responses by (1) a fast semi-analytical method for Jacobian matrix calculation; and (2) a staged inversion strategy with lateral constraints. The methodology is examined on two synthetic polarized models. Our study indicates that the proposed scheme can improve inversion stability and recover the underground resistivity and IP property distributions.