Land motions are significantly widespread in the Yellow River delta (YRD). There is, however, a lack of understanding of the delta-wide comprehensive deformation mode and its dynamic mechanism, especially triggered by groundwater extraction. This paper adopts an integrated analysis of multidisciplinary data of image geodesy, geophysics, geology and hydrogeology to provide insights into Earth surface displacement patterns and dynamics in the YRD. Delta-scale land motions were measured for the first time using L-band ALOS images processed using multi-temporal InSAR, illustrating multiple obvious surface sinking regions and a maximum annual subsidence velocity of up to 130 mm. Then, the InSAR-constrained distributed point source model with optimal kernel parameters, a smoothness factor of 10 and a model grid size of 300 m was established and confirmed to be rational, reliable and accurate for modeling analysis over the YRD. Remarkable horizontal surface displacements, moving towards and converging on a sinking center, were recovered by means of modeling and measured using InSAR, with a maximum rate of up to 60 mm per year, which can trigger significant disasters, such as ground fissures and building damage. In addition, the annual total water storage variation at the delta scale, the most meaningful outcome, can be calculated and reaches a total of approximately 12,010 × 10³ m³ in Guangrao city, efficiently filling the gap of GRACE and in situ investigations for delta-wide aquifer monitoring. Finally, a comparative analysis of time series InSAR measurements, modeling outcomes, and fault and groundwater data was conducted, and the strong agreement demonstrates that faults control aquifer distribution and hence the spatial distribution of groundwater-withdrawal-related regional land subsidence. Moreover, the obvious asymmetric displacements, demonstrating a northeasterly displacement trend, further reveal that faults control aquifer distribution and Earth surface deformation. These findings are useful for understanding the land motion patterns and dynamics, helping to sustainably manage groundwater and control disasters in the YRD and elsewhere worldwide.

The development of remaining oil plays an important role in increasing the late production, and low-grade faults seriously impacts residual oil exploration and development. Low-grade faults have a small fault displacement, brief extension, and strong concealment, which hinders their prediction using the typical semantic segmentation network. To intelligently identify low-grade faults, we designed a codec target edge detection technique. For the network to fully learn the low-grade faults information, we constructed the encoder using dilated convolution. Next, we introduced an attention mechanism to the decoder to improve capture of location information from a shallow network and semantic information from a deep network. Finally, the multi-scale fusion decoder outputs fault information of different scales, which further improves the identification accuracy of low-grade faults. The training model is applied to simulated data and actual seismic data through ablation experiments. The results show that this method can effectively identify low-grade faults and overcomes problems such as blurred fault cross-location, thicker edge contour lines, lower detection accuracy, and less training data. Compared with conventional a Holistically-Nested Edge Detection (HED) and a semantic segmentation (UNet), fault misidentification is reduced, fault continuity is increased, and fault accuracy is improved. providing technical support for the exploration and development of remaining oil and increasing the recovery rate of old oil fields.

Low-grade faults play an important role in controlling oil and gas accumulations, but their fault throw is small and difficult to identify. Traditional low-grade fault recognition methods are time-consuming and inaccurate. Therefore, this study proposes a combination of a simulated low-grade fault sample set and a self-constructed convolutional neural network to recognize low-grade faults. We used Wu’s method to generate 500 pairs of low-grade fault samples to provide the data for deep learning. By combining the attention mechanism with UNet, an SE-UNet with efficient allocation of limited attention resources was constructed, which can select the features that are more critical to the current task objective from ample feature information, thus improving the expression ability of the network. The network model is applied to real data, and the results show that the SE-UNet model has better generalization ability and can better recognize low-grade and more continuous faults. Compared with the original UNet model, the SE-UNet model is more accurate and has more advantages in recognizing low-grade faults.

Random noise adversely affects the signal-to-noise ratio of complex seismic signals in complex surface conditions and media. The primary challenges related to processing seismic data have always been reducing the random noise and increasing the signal-to-noise ratio. In this study, we propose an improved cycle-consistent generative adversarial network (CycleGAN) seismic random noise suppression method. First, the generator replaces the original cycle-consistent generative adversarial network generator network structure with the Unet structure combined with the Resnet structure in order to increase the diversity of seismic data feature extraction and decrease the loss of seismic data details. Second, in order to improve the network’s stability, the feature extraction effect, the event texture preservation effect, and the signal-to-noise ratio, the Least Square GAN (LSGAN) square difference loss is used in place of the conventional generative adversarial network cross-entropy loss. The feasibility of the proposed method was confirmed using model and real seismic data, both of which demonstrated that the improved cycle-consistent generative adversarial network method effectively suppressed random noise in seismic data. In addition, the denoising effect was superior to both the widely used FX deconvolution denoising method and original cycle-consistent generative adversarial network denoising method.

The development of supervised deep learning technology in seismology and related fields has been restricted due to the lack of training sets. A large amount of unlabeled data is recorded in seismic exploration, and their application to network training is difficult, e.g., fault identification. To solve this problem, herein, we propose an end-to-end training data set generative adversarial network Fault2SeisGAN. This network can expand limited labeled datasets to improve the performance of other neural networks. In the proposed method, the Seis-Loss is used to constrain horizon and amplitude information, Fault-Loss is used to constrain fault location information, and the Wasserstein distance is added to stabilize the network training to generate seismic amplitude data with fault location labels. A new fault identification network model was trained with a combination of expansion and original data, and the model was tested using actual seismic data. The results show that the use of the expanded dataset generated in this study improves the performance of the deep neural network with respect to seismic data prediction. Our method solves the shortage of training data set problem caused by the application of deep learning technology in seismology to a certain extent, improves the performance of neural networks, and promotes the development of deep learning technology in seismology.