Passive surface wave exploration using urban high-frequency noise has been studied extensively. As the main noise source of the urban environment, vehicle noise can generate higher frequency surface waves, thus enhancing detection resolution. However, the existing methods usually hope to obtain more stable dispersion imaging results by collecting ambient noise for a longer period, resulting in high acquisition costs. To further enhance the efficiency of geological surveys, we propose a method that utilizes vehicle noise coda waves for geological investigations. We conducted numerical simulations of vehicle noise and proposed a method for calculating segment duration. We successfully captured the tail waves of vehicle noise and obtained high-quality surface wave signals through phase-weighted stacking (PWS). This method can obtain reliable dispersion curves by utilizing very short-duration vehicle noise. The vehicle noise from Jinan Metro Line R3 and Qingdao Metro Line 6 are collected, and data processing is conducted using the method proposed in this article. The results show that this method can obtain the underground dispersion curve using 10 s or even a few seconds of data, and has the advantages of higher mode surface waves being more developed and having strong resistance to interference noise. The validity and reliability of the proposed method were verified by comparing the results obtained using this method with those obtained from traditional methods and geological data. It provides a means for rapid and accurate on-site investigation by utilizing vehicle noise with ultra-short durations.

Incorporating multiple perspectives makes joint inversion of multiple geophysical data sets an effective way for improving the accuracy of imaging complex geological structures. In this article, drawing inspiration from the inherent nonlinear mapping abilities of deep learning (DL), we introduce a groundbreaking joint inversion framework and network named JointInvNet. Unlike end-to-end networks that directly map geophysical data to models, we propose a hybrid inversion framework that combines insights from the physical laws with data-driven learning, which iteratively updates the independently inverted results simultaneously via JointInvNet. In particular, it is assumed that different geophysical parameters change on both sides of the geological boundary, and the Laplace convolution operator is used to extract boundary information and provide structural constraints for the loss function. To demonstrate the advantages over traditional separate inversion and cross-gradient inversion, numerical experiments are performed on seismic and resistivity data. As illustrated by visual and quantitative comparisons, JointInvNet could lead to satisfactory inversion results, with excellent agreement with ground-truth models and good generalization ability to more complex models. Moreover, weight settings between seismic and resistivity model parameters and applicability when structural similarity assumptions do not hold are discussed to illustrate the potential of the proposed method.

The high-resolution waveform inversion for seismic velocities is gaining increasing interest as we start to deal with complex structures. Although full waveform inversion (FWI) has been used for several years, obtaining high-resolution velocity models still presents many obstacles, such as the high computational cost and the limited bandwidth of the data. Thus, we propose a deep learning (DL)-based algorithm to build high-resolution velocity models using low-resolution velocity models, migration images, and well-log velocities as inputs. The well information, specifically, helps enhance the resolution with ground-truth information, especially around the well. These three inputs are fed to an improved neural network, a variant of U-Net, as three channels to predict the corresponding true velocity models, which serve as labels in the training. The incorporation of well velocities from several locations is crucial for improving the resolution of the output model. Numerical experiments on complex models demonstrate the robust performance of this network and the crucial role that well information plays, especially in generalizing the approach to models that differ from the trained ones and achieving superior performance compared with FWI.

The direct-current (DC) resistivity method is a commonly used geophysical technique for surveying adverse geological conditions. The resistivity model can be reconstructed from data by inversion, which is an important step in geophysical surveys. However, the inversion problem is a serious one that can easily lead to incorrect results. Deep learning (DL) provides new avenues for solving inverse problems, and these methods have been widely studied. Currently, most DL inversion methods for resistivity are purely data-driven and depend heavily on labels (real resistivity models). However, real resistivity models are difficult to obtain through field surveys. As an inversion network may not be effectively trained without labels, we built an unsupervised learning resistivity inversion scheme based on the physical law of electric field propagation. First, a forward modeling process was embedded into the network training to convert the predicted resistivity model to predicted data, and form a data misfit with the observation data. Unsupervised training independent of labels was realized using the data misfit as a loss function. Moreover, a dynamic smoothing constraint was imposed on the loss function to alleviate the ill-posed inverse problem. Finally, a transfer learning scheme was employed to adapt the network trained with simulated data to field data. Numerical simulations and field tests showed that the proposed method can accurately locate and depict geological targets.

Due to unexpected environmental variations and poor consistencies in land data acquisition, complex near-surface seismograms are usually polluted unreasonably with a low signal-to-noise ratio (SNR). These complicated circumstances bring more challenges in identifying accurate first arrivals for the following wave-equation traveltime (WT) inversion. Recently, the autoencoder (AE) is a typical unsupervised learning network, whose basic principle is to compress the input seismic data for their intrinsic features in the latent space with an encoder and, thereafter, to decipher these features for seismic profiles as the output with a decoder. This process is fully automatic with high stability and is not very sensitive to data quality. In this article, we propose an elastic WT inversion algorithm based on the AE method (AEWT) to invert the$P$-velocity model. Compared with the standard WT, the AEWT method automatically extracts the intrinsic features of the refractions with AE as reference data for the misfit functionals. Feature images in the latent space show similar but intensified sensitivity to the traveltimes with respect to velocity perturbations. We present one synthetic and two field data tests for comparing the proposed AEWT and the standard WT tomograms to investigate the locations of a buried fault and the depth of a buried sinkhole. All these experiments demonstrate that the proposed elastic AEWT method can reduce errors caused by low SNR and obtain a more reliable and stable$P$-velocity tomogram.

Random noise attenuation is an essential step to improve the signal-to-noise ratio (SNR) of seismic data. Deep learning for seismic data denoising is dominated by supervised methods that require noise-free data as training targets. It is usually time-consuming and laborious to obtain such clean seismic data, and the effectiveness of the noise attenuation is difficult to be guaranteed. Therefore, we propose a novel unsupervised learning method that learns from noisy data. The method is based on two salient features of seismic data: 1) valid signals of adjacent seismic traces that are spatially correlated and 2) random noise that is spatially independent and unpredictable. An end-to-end deep convolutional neural network (CNN) was constructed to solve the denoising task. Adjacent traces of seismic data, which contain similar seismic phases and interface features, were used as the inputs and labels of the training set. The mapping of spatial correlation can be learned by the CNN so that valid signals from raw seismic data are predicted, while random noise is suppressed for unpredictability. Synthetic and field data were applied to the proposed CNN denoising model. The experimental results demonstrate the effectiveness of random noise attenuation while preserving amplitude compared with two commonly used state-of-the-art denoising methods.

A DNN architecture referred to as GPRInvNet was proposed to tackle the challenges of mapping the ground-penetrating radar (GPR) B-Scan data to complex permittivity maps of subsurface structures. The GPRInvNet consisted of a trace-to-trace encoder and a decoder. It was specially designed to take into account the characteristics of GPR inversion when faced with complex GPR B-Scan data, as well as addressing the spatial alignment issues between time-series B-Scan data and spatial permittivity maps. It displayed the ability to fuse features from several adjacent traces on the B-Scan data to enhance each trace, and then further condense the features of each trace separately. As a result, the sensitive zones on the permittivity maps spatially aligned to the enhanced trace could be reconstructed accurately. The GPRInvNet has been utilized to reconstruct the permittivity map of tunnel linings. A diverse range of dielectric models of tunnel linings containing complex defects has been reconstructed using GPRInvNet. The results have demonstrated that the GPRInvNet is capable of effectively reconstructing complex tunnel lining defects with clear boundaries. Comparative results with existing baseline methods also demonstrated the superiority of the GPRInvNet. For the purpose of generalizing the GPRInvNet to real GPR data, some background noise patches recorded from practical model testing were integrated into the synthetic GPR data to retrain the GPRInvNet. The model testing has been conducted for validation, and experimental results revealed that the GPRInvNet had also achieved satisfactory results with regard to the real data.

We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way of addressing this ill-posed inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong nonuniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model, as well as the time-varying property of seismic data. To tackle these challenges, we propose end-to-end seismic inversion networks (SeisInvNets) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup, and the global context of its corresponding seismic profile. From the enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct a velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our synthesized and proposed SeisInv data set according to various evaluation metrics. The inversion results are more consistent with the target from the aspects of velocity values, subsurface structures, and geological interfaces. Moreover, the mechanism and the generalization of the proposed method are discussed and verified. Nevertheless, the generalization of deep-learning-based inversion methods on real data is still challenging and considering physics may be one potential solution.

The inverse problem of electrical resistivity surveys (ERSs) is difficult because of its nonlinear and ill-posed nature. For this task, traditional linear inversion methods still face challenges such as suboptimal approximation and initial model selection. Inspired by the remarkable nonlinear mapping ability of deep learning approaches, in this article, we propose to build the mapping from apparent resistivity data (input) to resistivity model (output) directly by convolutional neural networks (CNNs). However, the vertically varying characteristic of patterns in the apparent resistivity data may cause ambiguity when using CNNs with the weight sharing and effective receptive field properties. To address the potential issue, we supply an additional tier feature map to CNNs to help those aware of the relationship between input and output. Based on the prevalent U-Net architecture, we design our network (ERSInvNet) that can be trained end-to-end and can reach a very fast inference speed during testing. We further introduce a depth weighting function and a smooth constraint into loss function to improve inversion accuracy for the deep region and suppress false anomalies. Six groups of experiments are considered to demonstrate the feasibility and efficiency of the proposed methods. According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints, and depth weighting function together achieve the best performance.