Distributed Acoustic Sensing (DAS) systems provide rich vibration information for industrial monitoring. However, raw one-dimensional signals are often noisy and exhibit complex and heterogeneous temporal characteristics, making it difficult for traditional models to extract discriminative features and limiting classification performance and generalization. To address these challenges, we propose a DAS signal classification frame-work that integrates dynamic time-frequency representation with a learnable multi-source feature fusion network. First, a dynamic Short-Time Fourier Transform (STFT) method is introduced, which adaptively adjusts the window size and overlap ratio according to the input signal length. This design ensures consistent time-frequency resolution while avoiding distortions caused by padding or resampling, thereby enhancing spectral discriminability. Second, we design MFOFUNet, a dual-branch UNet-based architecture that separately encodes the dynamic spectrograms of intensity and phase channels and integrates them through a multi-stage fusion mechanism. This structure preserves modality-specific complementary information while enabling effective cross-modal interaction. Furthermore, a lightweight learnable fusion module is proposed to adaptively balance the contributions of different modalities at each encoding stage, achieving improved accuracy and stability with minimal additional complexity. In addition, a dual-stage data augmentation strategy is developed, combining 1D signal-level and 2D spectrogram-level enhancements to improve robustness. Extensive experiments on a challenging 10-class DAS dataset demonstrate that the proposed method achieves superior performance, reaching 89.33±4.27% accuracy, 89.02±4.50% F1-score, and 95.57±2.40% mAP under 10-fold cross-validation, outperforming existing mainstream approaches and showing strong potential for industrial sensing applications.

To track the pose of local optical scanners (LOSs) under occlusion and reflection, a robust speckle-textured spherical target and corresponding pose estimation methods are developed in this work, applicable to systems, such as structured light. The proposed method comprises four main stages: first, rigidly attaching the spherical target to a LOS, followed by capturing binocular images and calculating the position of the target; second, generating two panoramic images of the spherical target surface. Third, determining the target's attitude using correlation coefficient analysis matching to panoramic images; and fourth, comprehensive pose determination of the target. To validate the effectiveness of the proposed method under different occlusion and local reflection conditions, the spherical target is rigidly connected to a high-precision six-degree-of-freedom robotic arm in this work. The robotic arm serves a dual purpose: acting as a LOS whose pose is tracked and providing ground truth pose data for accuracy validation. The experimental results demonstrate that the proposed method achieves comparable accuracy under 15% occlusion conditions to state-of-the-art methods under occlusion-free scenarios, providing a valuable reference for existing target-based pose measurement techniques.

This paper introduces a novel multi-sensor fusion SLAM algorithm named FLARE-SLAM, designed for mobile robots operating in complex environments. This algorithm addresses challenges associated with uneven LiDAR measurement signals and their random distribution. First, we enhance the stability of feature extraction by refining the curvature calculation strategy for LiDAR point clouds and incorporating contextual information from the sensor array. Second, we introduce an adaptive residual optimization weight distribution mechanism, grounded in the principle of uniform residual optimization, to boost the algorithm’s adaptability across various environments. Extensive evaluations on the KITTI dataset confirm that FLARE-SLAM constructs a global map with enhanced consistency and accuracy, achieving an absolute trajectory error of 0.53% and an absolute rotation error of 0.19∘/100m. Additionally, we validate the robustness of the algorithm through real-world testing in diverse outdoor and indoor settings.

Most current light detection and ranging (LiDAR)-based simultaneous localization and mapping (SLAM) methods are based on static conditions, but real-world scenarios often violate this prior assumption. To address the existing challenges, this article proposes DO-Removal, an online LiDAR-inertial odometry that removes dynamic objects. Specifically, the method uses ground fitting results as a reference, takes point cloud measurements with significant geometric features as seed points for region growing, and uses clustering results to determine the confidence of dynamic element point cloud segmentation, thereby separating dynamic and static elements. Additionally, this article proposes a multiline LiDAR point cloud feature extraction method that considers context beams simultaneously, enhancing the significance of the extraction results. It also implements a residual optimization function based on distance truncation, distinguishing contributions by confidence, and adaptively weighting features at different distances. Finally, extensive testing was conducted on the KITTI dataset and a self-collected dataset, achieving competitive results with absolute trajectory error and absolute rotation error reduced to 0.51% and 0.19°/100 m, respectively.

Data aggregation is essential in near-ground long chain sensing networks, as it ensures data freshness and stability while extending communication range through path planning and traffic scheduling. However, the dynamic and fragile nature of long-chain networks under near-surface interference—particularly the presence of time-varying network links—poses significant challenges, for which no effective aggregation solution currently exists. This paper focuses on a representative ground-based distributed seismic node long-chain network and introduces a Weight Agnostic Structure-Free (WASF) data aggregation method based on artificial neural networks. WASF regulates packet forwarding paths and waiting times via activation functions and employs shared connection weights to identify the globally optimal aggregation node, thereby enabling efficient data aggregation. Simulation results demonstrate that, compared with state-of-the-art aggregation methods, WASF reduces end-to-end latency and packet loss rate by 11.8% and 9.4%, respectively. Field deployment on GEIWSR-III seismic nodes further confirmed its effectiveness, yielding 84.3% lower energy consumption, 41% reduced latency, and 20.2% fewer packet losses. By enabling structure-free aggregation, WASF provides a reliable reference framework for efficient, robust, and scalable communication in long-chain IoT networks, such as tunnels, pipe galleries, rivers, and railways.

The purpose of texture measurement is to describe and quantify the texture features of pixels in an image. The accuracy of texture measurement plays a crucial role in determining the effectiveness of texture filtering. However, current texture measurement methods face challenges in achieving accurate texture measurement results, particularly for multi-scale texture measurements. This limitation often leads to unsatisfactory texture filtering results, particularly with image details and high-contrast textures. We find that when moving the texture measurement regions for pixels near texture edges further away from the texture edge and keeping the texture measurement regions for pixels far from texture edges unchanged results in an improved accuracy of texture measurement. Based on this observation, we propose a novel texture measurement approach that employs a circular neighborhood with a variable radius as the texture measurement region for each pixel. Furthermore, we proposed an image terrain map model based on a one-pixel texture edge to obtain optimal parameters for texture measurement regions. This model significantly enhances the accuracy of texture measurement at any scale in an image. The experimental results show that the texture filtering method based on our image terrain map model is significantly better than existing methods in terms of edge-preservation, small-structure preservation, and high-contrast texture filtering. Additionally, we presented some applications of the image terrain map model in other areas of image processing to demonstrate its versatility.

Cross-scene classification of remote sensing (RS) imagery faces significant challenges due to large domain discrepancies and diverse imaging conditions, which hinder the acquisition of generalizable multi-modal semantic features. Unsupervised domain adaptation (UDA) has emerged as a promising solution for knowledge transfer across domains. Although prompt learning and vision-language models (VLMs) have recently been employed to enrich cross-modal information and improve the effectiveness of UDA, most existing methods either design prompts solely for the textual modality or employ unidirectional mapping from textual to visual prompts, resulting in insufficient cross-modal fusion. To overcome these limitations, we propose Mutual Cascade Prompting for Probability-Aligned Unsupervised Domain Adaptation in cross-scene classification (MCPPA). Within this framework, the progressive attention interactive prompt (PAIP) module implements a cascade prompt mechanism where, at each layer, visual and textual prompts from the previous stage are mutually updated through a cross-attention module. This mutual learning allows both branches to progressively integrate and reinforce multi-modal information in a deep and hierarchical fashion. Additionally, the category probability discrepancy measure (CPDM) module aligns the probability matrices of source and target domains using the nuclear norm within an adversarial training paradigm, while the feature stability constraint (FSC) module enforces consistency between learnable prompt features and those from the pre-trained model, enhancing overall robustness. Extensive evaluations on 30 transfer tasks across 10 benchmark RS datasets confirm that MCPPA consistently outperforms existing advanced methods, highlighting its effectiveness and broad application potential.

Marine vibrators (MVibs) are increasingly used in seismic surveys due to their precise waveform control, flexible signal design, environmental friendliness, and enhanced low-frequency output. However, their long-duration pilot sweeps introduce challenges not present with traditional airguns—most notably, the Doppler effect. The simulation or correction of phase distortion can be achieved using frequency-wavenumber (F-K) domain dephasing operator equation based on the instantaneous frequency function, while they require sufficient spatial sampling to get the reliable effect. Besides, as a typical coherent noise source, the removal of surface-related multiple greatly determines seismic imaging quality. Although surface-related multiple elimination (SRME) scheme can suppress the interference, moderate phase, timing, amplitude errors, and clutter in predicted signal components are detrimental. We propose an Bayesian primary-multiple separation and Doppler-shift correction iterative framework that assumes the predictions from SRME-type techniques are approximately independent in the shearlet domain and robustly corrects and separates them. In our approach, the energy mismatch between separated and predicted components is effectively controlled. Synthetic and field data examples have shown that its key advancements include: (1) The F-K domain phase distortion operator based on the instantaneous frequency function cleverly matches with the shearlet dictionary to simulate source motion in the sparsity-promoting inversion, reducing computational costs by 35.02 %. (2) The introduction of linear moveout (LMO) overcomes the sensitivity of Doppler-shift correction to spatial aliasing and achieves a 18.0742 dB signal-to-noise ratio (SNR) improvement in phase correction. (3) An improved threshold function is proposed to optimize primary-multiple separation, aiming at the shortcomings of the traditional ones. It outperforms the hard and soft threshold functions regarding average SNR, with improvements of 0.97 % and 6.21 %, respectively. Our approach only requires about 10 iterations to attain the converged solution.

In this article, we proposed a novel binocular positioning method based on a dynamic optical center imaging model to improve the accuracy of binocular positioning. By analyzing the distribution rules of the optical center at various object distances, we construct a new optical imaging model that is better suited for practical binocular positioning tasks. In addition, we develop a corresponding calibration method to accurately determine the model parameters. The experimental results demonstrate that our binocular positioning method outperforms existing methods in terms of spatial positioning and 3-D reconstruction accuracy. Compared to the binocular positioning method based on the traditional pinhole imaging model, our method achieves an 89.8% enhancement in spatial positioning accuracy and a 96.1% improvement in 3-D reconstruction accuracy for target objects. These results present the effectiveness and superiority of our method in binocular positioning applications.

The process of recovering dense depth maps from sparse depth information is prone to edge blurring. This paper proposes an image-guided depth completion algorithm to address this issue. The method uses the edges of the color image as prior constraints to construct an image topography map as an intermediate representation and performs nonlinear adaptive reconstruction based on the image content to adjust the position and scale of the pixel-weighted neighborhood. This approach avoids incorporating depth information with different distributions when estimating missing values, resulting in a full-resolution dense depth map with sharp edges. We conducted a quantitative comparison with state-of-the-art models on the KITTI and MidAir datasets, demonstrating that our algorithm has better performance and robustness in terms of completion accuracy. We also analyzed the impact of sparsity on the algorithm’s performance and its ability to recover fine structures in dense depth results and demonstrated the reconstruction results for sparse data in real-world scenarios.

Random noise greatly affects the quality of transient electromagnetic (TEM) signals in urban environments, leading to reduced detection accuracy. The effectiveness of denoising methods such as filtering or modal decomposition is limited by manually selecting parameters, and some noises are bound to be retained. In this letter, a novel approach combining reptile search algorithm (RSA) optimized variational mode decomposition (VMD) with deep neural network (DNN) is proposed to identify and eliminate noise. First, RSA is used to select key parameters in VMD. Then, based on the optimized parameters, the noisy signal is decomposed into different intrinsic mode functions (IMFs) via VMD, and the cross-correlation (CC) coefficient is used to select and reconstruct the effective signal. To solve the problem of residual noise, the convolutional neural network (CNN) and long short-term memory are combined to extract the time-related features of the data and further improve the signal-to-noise ratio (SNR). RSA-VMD-DNN is a denoising method that is better suited for random noise in nonlinear and nonstationary TEM signals. It can effectively select and reconstruct signals while eliminating residual noise. The results show its great potential for improving the accuracy and reliability of TEM detection.

Distributed optical fiber acoustic sensing (DAS) is a rapidly developed seismic acquisition technology with the advantages of low cost, high resolution, high sensitivity, small interval, etc. Nonetheless, consecutively missing cases often appear in real seismic data acquired by the DAS system due to some factors, including optical fiber damage and inferior coupling between cable and well. Recently, some deep-learning (DL) seismic interpolation methods based on convolutional neural networks (CNN) have shown impressive performance in regular and random missing cases but still remain the consecutively missing case a challenging task. The main reason is that the weight sharing makes it difficult for CNN to capture enough comprehensive features. In this article, we propose a transformer-based interpolation method, called seismic interpolation transformer (SIT), to deal with the consecutively missing case. This proposed SIT is an encoder-decoder structure connected by some U-shaped swin-transformer (UST) blocks. In the encoder and decoder part, the multihead self-attention (MSA) mechanism is used to capture global features which is essential for the reconstruction of consecutively missing traces. The UST blocks are utilized to perform feature extraction operations on feature maps with different resolutions. Moreover, we introduce the SSIM loss to optimize the training process of SIT. In experiments, this proposed SIT outperforms A-Net and swin-transformer (ST). Moreover, ablation studies also demonstrate the advantages of new network architecture and loss function.

Seismic exploration is a crucial method for studying underground geological structures and oil/gas resources. However, the presence of various noise sources during seismic wave propagation hinders accurate interpretation and imaging. To address this challenge, effective denoising methods are essential. In recent years, deep learning, particularly Convolutional Neural Networks (CNNs), has shown promise in seismic data processing. Nevertheless, CNNs have limitations in capturing long-range dependencies and global coherence. As an alternative, we propose a Transformer-based model called Seismic Data Denoising Transformer (SDT) for seismic signal processing. By leveraging self-attention mechanisms, the SDT model overcomes the limitations of CNNs and effectively captures long-range features for seismic signal reconstruction. We also introduce a novel self-supervised pretraining strategy using a large-scale dataset to further enhance performance. Experimental results demonstrate the advantages of SDT in complex seismic noise attenuation and preserving weak signal amplitudes. The proposed method exhibits promising potential for real-world seismic data applications.

Marine vibrators have gained preference in seismic acquisition recently due to their superior waveform control, repeatability, and reduced environmental impact. Such sources excite for several seconds, while the source vessel is moving, thereby creating the Doppler effect. Phase corrections for the Doppler shift can be achieved through deconvolution techniques. They assume using extensions of the standard convolutional model to model geometry motion. However, such operations generate aliasing artifacts under coarse spatial sampling. Additionally, due to incomplete and uneven coverage of acquisition systems and dead traces, real seismic data always have some missing traces, which affects the performance of multichannel algorithms such as multiple separations, wave-equation-based imaging, inversion, and Doppler-shift correction. To remedy these issues, a new derivation of the weighted projection onto convex sets (WPOCS) reconstruction and Doppler-shift correction method is presented from the iterative shrinkage-thresholding (IST) algorithm, under the sparsity constraint. It interpolates, corrects for the Doppler shift, and denoises irregularly sampled marine vibrator data simultaneously in a sparse inversion framework that promotes sparsity of the data in a 3-D curvelet domain. To prevent alias in the transform domain thus achieving arbitrary undersampling rate, an improved jittered undersampling method is proposed, leading to high-fidelity wavefield reconstruction and precise Doppler-shift correction during the sparsity-promoting process. Moreover, a weighted trace reinsertion strategy is defined to facilitate denoising noisy seismic volumes. Finally, aiming at the shortcomings of the traditional threshold functions, we propose an improved threshold function to better implement noise attenuation and wavefield reconstruction. Synthetic and field data examples verify our approach’s effectiveness.

Marine vibrators have been favored by seismic acquisition in recent years because of their greater waveform control, repeatability, and lower environmental damage. However, it presents a processing challenge not found with airguns: the Doppler effect. The current industry standard method for source motion correction is based on spatiotemporal filtering or frequency–wavenumber (F-K) domain division. However, both correction methods generate spatial aliasing when the shot interval is coarse. The passage presents a deconvolution–interpolation method implemented in the F-K domain to correct moving marine vibrator data. By deploying a linear composite operator within the sparse inversion framework, including a mask function, an F-K domain convolution operator, a sampling matrix, and a dictionary mapping seismic data to a basis function, the method achieves interpolation, correction, and noise attenuation simultaneously of noisy Doppler-shifted marine vibrator data under coarse shot interval in the F-K domain. The power function threshold model is proposed to be deployed in the fast iterative soft-thresholding algorithm (FISTA) for inversion, thus leading to a substantial saving of iterations. Furthermore, the mask function preserves the effective spectrum during beyond-alias interpolation and denoising. Finally, the amount of observed data involved during the inversion process can be halved by utilizing the conjugate symmetry of the real signal Fourier transform. We demonstrate the impact of the Doppler effect and its correction under coarse shot interval on seismic data and structural imaging, while considering the interference of noise. Synthetic and field data examples verify the effectiveness of our method in mitigating the aforementioned disturbances.

Domain adaptation (DA) has recently made tremendous progress in remote sensing image scene classification. Particularly, open-set DA (OSDA) has attracted increasing attention, wherein the target domain includes unknown classes. However, existing OSDA methods assume that the source samples or the parameters of the source model are available, which is not practical due to concerns about digital privacy and portability issues. Addressing this, we investigate a more realistic and challenging open-set DA scenario for remote sensing image scene classification, where the unlabeled target domain is only provided with a black-box source predictor (i.e., only model predictions are accessible). To address this problem, we devise an Open-set Knowledge distillation framework with neighboRhood similarity regularization and uncertAinty modeling called OKRA. Specifically, we introduce a neighborhood similarity regularization to facilitate the open-set knowledge distillation (KD) using local neighborhood information. Furthermore, we propose an energy-based uncertainty modeling (UM) strategy for open-set recognition, which can effectively discriminate known and unknown target data without any thresholding. Empirical results on six cross-scene scenarios built from three datasets verify that OKRA is effective and practical for remote sensing image scene classification, outperforming existing data-dependent OSDA methods by a large margin.

Seismic data reconstruction is always an essential step in the field of seismic data processing. Effective reconstruction methods can obtain high-density information at low-cost and also recover missing seismic data. Due to the strong feature extraction ability, convolutional neural network (CNN) has shown remarkable performance in numerous fields of data processing and been gradually applied to seismic data reconstruction. However, most of CNN-based methods applied to seismic data reconstruction only consider features in single scale or just utilize simple interactions between different scales, which is likely to result in performance degradation when facing complex and extremely incomplete seismic data. To further promote the performance of CNN-based methods in seismic data reconstruction, a novel multiscale enhanced attention network (MSEA-Net) is proposed based on the self-enhanced scheme. In general, MSEA-Net has a multiscale architecture which can significantly improve the processing accuracy by fusing the potential features in different-resolution seismic data. From the basis, a parallel sparse residual block is designed and applied in MSEA-Net to enhance processing efficiency and avoid overfitting issues. In addition, a dense spatial attention block is also introduced to the network to further reinforce the effective features, thereby strengthening the reconstruction performance. Experimental results demonstrate that our proposed network can effectively reconstruct incomplete seismic data including regular missing data, irregular missing data, and even consecutively missing data with big gap, which is superior than exist interpolation methods including commonly used U-Net.

Recently, a number of deep learning (DL) methods are developed to attenuate the noise in seismic data. Most of them show good performance under a common precondition: the training and testing data are drawn from the same distribution. However, it is challenging to acquire sufficient noise training data whose distribution is same as the noise presented in the testing seismic data; we call such noise data with same distribution as target-domain noise. To address this issue, we propose a promising DL paradigm for seismic data denoising based on transfer learning and seismic noise modeling. We firstly utilize a Green-function-based modeling method for seismic noise to generate a massive amount of synthetic noise which is similar to real seismic noise. Secondly, the high-authenticity synthetic noise is used as the pre-training data in source domain. Finally, we utilize limited real target-domain noise data to fine-tune the partial trainable parameters of pre-trained model and thus transferring it into target domain. This proposed DL paradigm gets rid of the need for enough target-domain noise data, so as to extend the application scope of DL-based method in seismic data denoising. Moreover, we design a novel network architecture based on multi-cascade structure and attention mechanism. This DL paradigm shows extremely similar denoising performance to that of using a large amount of target-domain noise data in both synthetic and real examples, demonstrating its potential in mitigating the dependence of DL-based seismic denoising methods on target-domain noise data.

The transient electromagnetic (TEM) method is a geophysical exploration method commonly used in the detection of subsurface structures. Underground conductivity information at different depths can be obtained by interpreting the observed time-varying TEM data. Three-dimensional forward modeling is important for studying TEM responses and is also essential for inversion. The calculation accuracy of mesh-based forward modeling methods, such as the finite volume method (FVM) and finite element method (FEM), is greatly affected by the quality of the mesh. In this paper, a TEM forward modeling method based on a meshless generalized finite difference method (GFDM) is proposed. It is based on the Taylor expansion and weighted least squares fitting. In the GFDM, a partial derivative of the unknown parameter in the governing equation is expressed as a linear combination of the function values of support points. Numerical integration is not required during the forward modeling process, which simplifies the program implementation and increases the numerical calculation efficiency. In this paper, a three-dimensional GFDM forward modeling method for simulating ground wire source TEM data is investigated; a corresponding program is developed, and the correctness of the code is verified through several three-dimensional models. By comparing the forward modeling results of this method with those of the FEM, it is verified that the GFDM offers higher computational speed and lower memory requirements.

The mixedLp-norm, 0 ≤p≤ 2, stabilization algorithm is flexible for constructing a suite of subsurface models with either distinct, or a combination of, smooth, sparse, or blocky structures. This general purpose algorithm can be used for the inversion of data from regions with different subsurface characteristics. Model interpretation is improved by simultaneous inversion of multiple data sets using a joint inversion approach. An effective and general algorithm is presented for the mixedLp-norm joint inversion of gravity and magnetic data sets. The imposition of the structural cross-gradient enforces similarity between the reconstructed models. For efficiency the implementation relies on three crucial realistic details; (i) the data are assumed to be on a uniform grid providing sensitivity matrices that decompose in block Toeplitz Toeplitz block form for each depth layer of the model domain and yield efficiency in storage and computation via 2D fast Fourier transforms; (ii) matrix-free implementation for calculating derivatives of parameters reduces memory and computational overhead; and (iii) an alternating updating algorithm is employed. Balancing of the data misfit terms is imposed to assure that the gravity and magnetic data sets are fit with respect to their individual noise levels without overfitting of either model. Strategies to find all weighting parameters within the objective function are described. The algorithm is validated on two synthetic but complicated models. It is applied to invert gravity and magnetic data acquired over two kimberlite pipes in Botswana, producing models that are in good agreement with borehole information available in the survey area.

Existing intelligent driving technology often has difficulty balancing smooth driving and fast obstacle avoidance, especially when the vehicle is in a non-structural environment and is prone to instability during emergencies. Therefore, this study proposed an autonomous obstacle avoidance control strategy that can effectively guarantee vehicle stability based on an Attention-long short-term memory (Attention LSTM) deep learning model with the idea of humanoid driving. First, we designed the autonomous obstacle avoidance control rules to guarantee the safety of unmanned vehicles. Second, we improved the autonomous obstacle avoidance control strategy combined with the stability analysis of special vehicles. Third, we constructed a deep learning obstacle avoidance control based on the Attention-LSTM network model through experiments, and the average relative error of this system was 14.95%. Finally, the stability and accuracy of this control strategy were verified numerically and experimentally. The method proposed in this study can ensure that the unmanned vehicle can successfully avoid obstacles while driving smoothly.

Electric vehicle (EV) is the core part of future automobile technology, and safe and reliable wireless power transfer (WPT) technology is the key link to improve the intelligent driving technology of EV. In this paper, the uncertainty quantification method is proposed to guide the optimization design of WPT structure, so as to improve the efficiency of WPT. First this paper establishes a surrogate model of WPT efficiency based on the adaptive sparse polynomial chaos expansion, and the uncertainty of EVs WPT transmission efficiency is quantified, the computational efficiency is improved by about 8.4 times. Then the surrogate model is combined with the global sensitivity analysis method to quantify the impact of different variables in WPT on efficiency and screen out the variables with greater impact. Finally, this paper uses the improved marine predators algorithm to optimize the selected WPT system structure parameters. Considering the uncertainty, the average efficiency of the optimized WPT system is increased from 73.43% to 94.64%. Compared with other optimization methods, it proves that the method in this paper can optimize WPT more efficiently, and significantly improve the transmission efficiency.

Many deep learning methods have been proposed to classify moving targets from seismic signals in recent years. However, the existing deep models are all designed based on the “end-cloud” framework, in which real-time data processing is difficult because of communication delays. To address this problem and achieve on-site target classification, we propose a novel edge intelligence-oriented method, named compressed sensing-edge convolutional neural network (CS-ECNN). In this method, the acquired seismic signals are first mapped onto a compressed domain using CS. This operation reduces data dimensions, while being able to retain the vast majority of valuable seismic features. Following that, a convolutional neural network is employed to extract implicit features directly from the compressed seismic measurements and then classify the feature vectors. To evaluate the proposed method, the seismic data recorded in DARPA’s SensIT project are used as a case study. The experimental results demonstrate that the proposed model is edge-matched, and it achieves comparable classification accuracy to the state-of-the-art cloud-based models with only 1/10 computation time.

Due to the strong nonstationary characteristics of seismic signals, energy criteria-based methods are not robust for detecting moving targets, especially in data with low SNRs. To address this problem, we propose a new method for detecting ground moving target based on fractal dimension (FD) theory named FD-based support vector machine (FD-SVM). In this method, seismic signals are first measured by fractals, which can effectively extract seismic nonlinear features. These fractal features are then fed into an SVM to distinguish moving targets from noise. Two data sets are used to evaluate the proposed method. One is a set of seismic signals induced by wheeled and tracked vehicles. The other is a set of seismic signals generated by human footsteps. Experimental results demonstrate that the proposed FD-SVM algorithm achieves promising results on both data sets. Compared with the benchmark methods, the FD-SVM algorithm achieves a better precision rate, recall rate, and F1 score.

There are many conventional methods that have been applied in transient electromagnetic (TEM) random noise suppression such as stacking-averaging. But, when the TEM system works in urban areas with strong noise, these methods are not effective due to the extremely low signal-to-noise ratio (SNR). We propose a new method combining the minimum noise fraction (MNF) algorithm and deep learning. The MNF and the deep neural network (DNN) are used to extract the complex features of signals from the noisy signal data. After using MNF to improve the SNR of TEM to a certain extent, the convolutional neural network (CNN) and gated recurrent unit (GRU) were used to extract spatial and temporal features of the signal, and the training was guided by the double loss function. To verify the effectiveness of the method, we have done quantitative experiments on synthetic noise and field noise respectively. The experimental results show that our method achieves the most advanced performance.

The improving performance of high-resolution magnetic instruments has propelled the refined detection of small targets of different shapes. The traditional method is to extract target-related features through some empirical formulas, and then classify the targets visually. Such manually designed formulas have limited feature expression ability. Also, the results interpreted by different people may vary. Although machine learning was later applied to the task, which avoided the link of manual judgment, the accuracy and robustness were not strong. In this paper, an end-to-end Region Convolutional Neural Network (R-CNN) is proposed to identify targets with little human intervention. Considering the differences between magnetic signals and natural images in terms of scenario, target and imaging, improvements to R-CNN meta-architecture are required. Specifically, magnetic tensor gradient (MTG) data with grid cells are transformed into 2-D matrix, which is then enhanced by pseudo-color coding for mapping. Given the self-built dataset, we design a Two-stage Fine-grained (TSFG) R-CNN to excavate effective deep-level features of targets. PointRend is used here to predict the high-quality edge segmentation of targets. Experiment results show that the proposed method provides a useful way for the detection of multi-scale, multi-shape and multi-depth magnetic targets, even under the case of magnetic field superimposition.

The current magnetic localization technology based on magnetic tensor gradient (MTG) information mostly focuses on single-object localization using a tensor gradiometer, which cannot be applied to more common scenarios where there are multiple objects in the test area and their number changes over time. The difficulty is that magnetic detection is a “blind” experiment. The lack of prior information will lead to poor accuracy, slow inversion speed, or even failure. This letter presents a novel method to estimate the information of multiple objects, including their number, trajectory, and magnetic moment. Specifically, an improved isolation forest algorithm is used to predetermine the best possible number, center coordinates, and magnetic moments of the objects from the rough solution set obtained by the magnetic tensor gradiometer array. Given the above prior conditions, we can safely get the accurate estimation of the objects by formulating a suitable cost function between the measured magnetic data and those theoretically calculated based on the extended multiple magnetic dipole mathematical model. The results of the simulation experiment show that the proposed method provides a useful way for multiobject localization.

Moving ground-target detection system is widely used to monitor illegal activities of pedestrians and vehicles. However, existing detection methods are restricted by the power consumption in hardware and are usually based on some single feature of the seismic signal, which leads to low detection accuracy and false alarms. To address these issues, we propose a new moving ground-target detection method for detecting the weak seismic signals generated by distant moving ground targets. This method combines an adaptive strategy and support vector machines (SVMs). Both time- and frequency-domain features of seismic signals are considered in the detection method. Additionally, we carry out field experiments to evaluate the performance of the proposed method. The results show that the proposed moving ground-target detection method can detect distant moving ground targets and avoid false alarms as many as possible, which indicates good performance.

Moving target recognition is a critical task for a variety of applications, ranging from environmental monitoring to regional security protection. Recently, many deep learning (DL) methods have been proposed to recognize the seismic features of moving targets. However, the established DL algorithms are mainly challenged by time-consuming feature extraction and lack of robustness. In this article, a novel moving target recognition method [Compression Observation-Seismic DL (CO-SDL)] is proposed to solve the above two problems simultaneously. CO-SDL first uses a measurement matrix to project the seismic signal onto a compressed domain and obtain compressed seismic measurements. This operation removes redundant data while retaining valuable seismic information and suppressing noise energy. Following that, CO-SDL efficiently and stably extracts deep nonlinear features from compressed seismic measurements and then accurately classifies the feature vectors. To evaluate the proposed method, a comprehensive seismic dataset is developed. This dataset covers six types of common moving targets, and the SNR ranges of all signal types are greater than 15 dB. The proposed method and the benchmark methods are tested on this dataset. Experimental results prove that the presented CO-SDL method is ten times faster than the state-of-the-art methods with comparable accuracy. Furthermore, the CO-SDL method shows the strongest robustness.

Seismic background noise often damages the desired signals, thereby resulting in some artifacts in the seismic imaging that follows. Since about 2016, some supervised-deep-learning methods have shown impressive performance in seismic data denoising, but they usually only consider single-scale features and neglect the multi-scale strategy. To further reinforce their denoising performance, a novel multi-scale convolutional neural network (CNN) combined with spatial attention mechanism, called multi-scale spatial attention denoising network (MSSA-Net), is proposed to tell weak reflected signals apart from strong seismic background noise. Unlike conventional single-scale CNNs, this proposed MSSA-Net can achieve the extraction of multi-scale features which is beneficial for the suppression of strong noise and the recovery of weak reflected signals. Specifically, MSSA-Net contains a principal denoising network and two auxiliary networks. The former utilizes the widen convolution composed of multiple parallel convolution layers with different kernel sizes to capture the informative multi-scale features; the latter two leverage up and down sampling to extract local fine and global coarse features, respectively. Furthermore, a spatial attention block is adopted to fuse these multi-scale features, thereby distinguishing weak reflected signals from strong seismic background noise. Multiple experiments of synthetic and real seismic records demonstrate the effectiveness of MSSA-Net. In addition, compared with two classical single-scale CNNs, MSSA-Net performs better in signal recovery, indicating the positive effect of multi-scale strategy.

Considering the viscoelastic anisotropy and electrical depression characteristics of the complex geological media, we introduce the generalized standard linear solid (GSLS) model to describe the relaxation effect of the solid skeleton and the Cole-Cole model to describe the frequency dependence of electric conductivity. The seismoelectric model of the poro-viscoelastic anisotropic medium was constructed, and the corresponding wave and diffusion equations in the time domain were derived. We then analyze the characteristics of seismoelectric wavefields in viscoelastic transverse isotropic (TI) media with a homogenous model, a two-layer model and a layered-model with depression. Results show that the TI anisotropy, viscosity of fluid, tilt angle all have significant effects on the propagation of seismoelectric waves in the homogenous model. The strong attenuation of seismoelectric waves in the two-layer model shows the validity of the relaxed skeleton and frequency dependent conductivity used in our approach, which could also effectively capture the reflection and transmission phenomena in the seismic and associated EM fields in the layered model with depression.

The ground-source airborne time-domain electromagnetic (GATEM) method is an effective electromagnetic exploration technology. The actual geological medium has rough characteristics; however, the current inversion methods for GATEM data are mostly based on homogeneous medium and extract only resistivity information. In this article, a neural network (NN) is served as extracting the two parameters of resistivity and roughness for rough medium. The structural parameter selection of NN has no fixed formula and is often related to experience. The NN has difficulty converging to the target accuracy if the structural parameters are not selected properly. To realize high-precision inversion of GATEM data, this article introduces Rademacher complexity to limit the generalization error and improve the generalization ability of the NN. Above all, a sample set of the GATEM response, resistivity, and roughness of the rough medium is established. In the next place, a fully connected NN structure is constructed, and a highly generalized NN is obtained by using Rademacher complexity. Then the mapping relationships are established through training, and the NN method is served as inverting the resistivity and roughness. The initial NN and the highly generalized NN are used to invert the GATEM response of rough medium for typical geological models. The results of the highly generalized NN based on Rademacher complexity are closer to the real models. The method is applied to the GATEM field data in Zhuxianzhuang, Anhui Province, China, and the results are consistent with the geological data.

Surface nuclear magnetic resonance (sNMR) can directly and quantitatively detect groundwater, but its application in urban environments faces problems, such as low signal-to-noise ratios (SNRs) and difficulties in laying the coils. This study presents a rotational sNMR measurement scheme to accurately image a frozen urban lake. Through synthetic data experiments, we first demonstrate that sNMR data measured with six rotations can accurately invert underground water-bearing structures. Even when the environmental noise is high, this scheme can reflect the distribution of the water content in a frozen lake. Moreover, due to the small coil size, the inversion result is less affected by the underground resistivity. In field experiments, a large amount of high-quality sNMR data with average SNRs up to 12.8 dB were obtained from a high-noise environment using three reference coils. The 2-D distributions of the water content in the ice, water, and mud layers of the frozen lake were determined using the data measured from six rotations. The water content in the lake was found to be approximately equal to 1 m3/m3. Although there are still some problems with the measurements, such as inaccurate relaxation times and low resolutions in deep areas, further improvements in sNMR and the rotational detection scheme can facilitate the application of this approach to urban groundwater detection.

Surface monitoring of microseismic monitoring events is generally challenging because microseismic data have a low signal-to-noise ratio (SNR). Traditional event-detection methods struggle to detect weak microseismic events. A variance fractal dimension (VFD) method for automatic microseismic event detection via multitrace energy envelope stacking (MTEES) is introduced. In the first stage, we propose a processing microseismic data method based on the MTEES method. It increases the energy of weak microseismic data to avoid missed and false microseismic detection. Furthermore, it can greatly improve computational efficiency to satisfy real-time processing requirements. In the second stage, the VFD algorithm is applied to the data processed in the first stage to improve the feasibility and validity of microseismic event detection. A simulation test with perforation data shows the reliability of the new method in the automatic detection of microseismic events. In addition, we demonstrate that analogous results can be obtained when perforation data are not available by introducing a novel approach based on synthetic correction time. The new approach is particularly useful when perforation data are not recorded, representing a significant advantage over previous approaches. We describe the application of the novel method to a real microseismic data example from monitoring hydraulic fracture treatments in Shanxi Province, China, with and without perforation data. The new method yields improvement in microseismic event detection for microseismic monitoring. Therefore, we find a wide range of applications requiring analysis of microseismic data.

Suppressing random noise in seismic data is a significant problem in seismic data processing. Often, there is serious aliasing between the effective signal and random noise, affecting the identification of weak signals, and even resulting in great difficulties in the suppression of conventional seismic signals. We propose an improved attention-guided convolutional neural network (ADNet) to eliminate seismic interference noise. After a sufficient amount of training, the network removes noise by transferring seismic data features learned from a synthetic dataset to tests with complex field data. Our workflow consists of four parts. First, in the model, we improve the feature enhancement module (FEM) and attention module (AM), increase the convergence speed, and enhance the expressive ability. Second, we use 2-D synthetic data to verify the ability of the model to suppress noise in seismic records. Third, we use 2-D real seismic data to further verify the denoising effect of the improved ADNet. Fourth, we convert the 3-D simulated seismic data and field data into 2-D data for processing and reorganize the 2-D denoising results into 3-D data. By comparing the noise suppression outcomes of several classic denoising methods, simulations and actual experiments show that the improved ADNet effectively maintains the signal amplitude, reduces the network depth, and better suppresses seismic noise. Hence, we believe that our model can be widely applied in the field of seismic data processing.

The effect of magnetic viscosity (MV) has continued to be observed with the development and application of the time-domain electromagnetic method (TDEM). Field and laboratory data show that the MV effect is characterized by a -1±0.4 scope power-law delay in the late stage of electromagnetic response. Research on the MV effect can improve the detection accuracy of TDEM and assist in prospecting for ferromagnetic minerals. Most of the studies are based on the Chikazumi susceptibility model and the one-dimensional modeling method. However, the late-stage electromagnetic response shows a -1 power-law delay, which is inconsistent with the measured data. The log-uniform distribution of relaxation time τ in the Chikazumi model is not always appropriate. This study considers the Cole-Cole susceptibility model with a log-normal distribution of relaxation time. The three-dimensional (3D) modeling method of the MV effect is raised based on the rational function approximation algorithm and recursive convolution technique; the control equations and iterative process were adjusted based on finite-different time-domain (FDTD) method. The effectiveness was verified via half-space and layered models; the effects of susceptibility parameters on the response were clarified; moreover, the MV effect of the 3D anomalous model was analyzed. Our method can model the fractional propagation process of the MV effect more efficiently and help to improve the prospecting accuracy of the TDEM method under complex magnetic geological conditions.

Road collapse and underground water inrush accidents pose a serious threat to urban safety and development. Transient electromagnetic (TEM) method is an effective geophysical method for detecting urban underground space. However, due to the complexity of urban geological environment, the conventional TEM detection methods are difficult to meet the needs of efficient and high-resolution detection of urban underground space. To solve this problem, an adaptive high-resolution (AHR) TEM detection method based on pseudoseismic wavelet transform technology is proposed in this study. The simulation results show that compared with the conventional technologies, the AHR detection method can more accurately reflect the resistivity distribution information in complex geological environment. The proposed method is implemented to detect an urban underground cavity, and the imaging results are consistent with the actual results. The research results will provide technical support for the early warning of road collapse and water inrush in urban industrial development.

In modern seismic data acquisition, real-time data collection is a challenging task due to bandwidth limitations in wireless communications. In this letter, we propose a novel compressive data gathering scheme using generative adversarial networks, named GAN-CDG, to improve the efficiency of data gathering. Instead of collecting the originally acquired data, GAN-CDG gathers data projections in wireless geophone networks. Data compression and load-balanced relay transmission are utilized during the projection process. To speed up the formation of projections, the shortest path routing tree (SPRT) is constructed, which achieves the minimum end-to-end time delay. The sparse domain of seismic signals and its reconstruction mapping are learned by sparsity-constrained adversarial networks. The testing results demonstrate that projections with high compression ratios (e.g., 16) are gathered efficiently with the SPRT. Then, original seismic signals can be reconstructed accurately (over 30 dB) from the projections using the adversarial model, which outperforms the state-of-the-art method.

As the signal-to-noise ratio (SNR) of surface microseismic monitoring data is generally low and large, traditional detection and picking algorithms cannot satisfy the real-time and high accuracy to processing. Therefore, a Fast Akaike information criterion (Fast-AIC) algorithm is proposed for microseismic event automatic detection and first arrival time picking. First, an automatic detection method of microseismic events based on multitrace energy stacking is proposed, to avoid the missed detection and false detection in conventional automatic detection methods. Second, the Fast-AIC algorithm is developed by mathematical derivation from the Vector Auto-regressive (VAR-AIC algorithm), to improve the efficiency of first arrival time picking of microseismic signals. Finally, the new method and three other conventional first arrival time picking methods are tested on microseismic monitoring data from a hydraulic fracture site in Shanxi, China. We have found that the new method has the highest picking accuracy and computational efficiency.

A new method for detecting risk of tunnel water-induced disasters using magnetic resonance sounding (MRS) is proposed in this letter. The method utilizes magnetic resonance signals that are generated directly from hydrogen protons to achieve the purpose of detecting risk of tunnel water-induced disasters directly and quantitatively. This letter evaluates the potential of this method based on a systematic study involving forward modeling, numerical experiments, and a large-scale physical model test. The relationship between the magnetic resonance signal response in the tunnel and the position and water content of water-bearing structures is obtained by the forward modeling. In the numerical examples, the inversion results are in agreement with the synthetic model. In the physical model test, the inversion results can accurately locate the water-bearing structure, and the water content linearly decreases with the water level of the water-bearing structure, which verifies the feasibility and effectiveness of predictions made based on the MRS data. These results demonstrate that tunnel MRS can be used to anticipate water-induced disasters.

The small impact of the geomagnetic field enables a magnetic tensor gradiometer to be easily installed on the flight platform for airborne geophysical exploration, especially for the detection of shallow buried mines and magnetic moving targets. Using the fluxgates as the core components, the gradiometer has the advantages of wide temperature range, low cost, and high resolution, but has the disadvantage of relatively low accuracy. This is because of the scale factor error, the nonorthogonal error, the misalignment, the zero offset, the dynamic error in a fluxgate, and the inconsistency among the error of fluxgates. In this letter, a correction method for a towed airborne magnetic tensor gradiometer is proposed that is composed of four fluxgates arranged in a cross-shaped structure. The theoretical framework of the proposed method is based on the static error model and the dynamic characteristics of single fluxgate, the feature that the gradient tensor of the geomagnetic field at high altitude is approximately zero, and on the phenomenon that the unchanged tensor rotation as a result of nonuniform magnetic field on the ground can indicate the inconsistency of the scale factors among different tensor components. The actual flight results using a helicopter have demonstrated and validated the performance and effectiveness of the proposed method. The improvement ratios of the field tensor components are from 359.6 to 1765, and the RMS of each component has reached to the level of 1 nT/m.

Breath training is an important part in the pronunciation recovery process, we simulate the fluent of air in the the upper respiratory tract, use computational fluid dynamic to build the impaired hearing children's pronunciation recovery system, and we have tasted the reliability of the system by experimental. We study the two parts in the breath process by the dynamic fluid computational method, and build the 3D model for the breath process. The results can be used to direct the pronunciation training for impaired hearing children. One can evaluate the trainer's breath process according the model, to find the weaking part in the process, to direct it. It will be useful in the pronunciation recovery process.