High-efficiency and high-quality detection of oil pipeline will significantly reduce environmental pollution and economic loss, so an unconventional oil pipeline anomaly detection convolutional neural network (CNN) algorithm based on attention mechanism is proposed in this article. By taking the simulated ground-penetrating radar (GPR) data as prior knowledge, the structure of the convolutional neural network based on the attention mechanism is constructed, and finally, the location and working condition of the underground oil pipeline are recognized in the simulation data and measured data. The simulation results show that after using the new optimized convolutional neural network, the accuracy rates of the leakage discrimination from horizontal data acquired along the oil pipeline and the classification of the target from longitudinal data acquired perpendicular to the oil pipeline are 94.5% and 84.6%, respectively. Compared with the original convolutional neural network without an attention mechanism, the accuracy rates of the leakage discrimination and the classification of the target are improved by 6.2% and 7.8%, respectively. We further train measured data with an optimized convolutional neural network, results show that compared with a conventional network, the new network can increase the corresponding accuracy rates of the leakage discrimination and the targets classification by 5.4% and 6.9%, reaching 92.3% and 84.4%, respectively. According to our study, the ground-penetrating radar oil pipeline recognition algorithm based on an attention mechanism can well accomplish the identification of underground oil pipelines.

As an emerging geophysical exploration technology in recent years, airborne electromagnetic exploration has the advantages of adapting to diverse terrains, wide coverage, and providing a large amount of electromagnetic data, and can be applied to the rapid collection of large amounts of data. Scenarios are often used in fields such as deep geological structures, mineral resource exploration, and environmental engineering research. However, traditional airborne electromagnetic data inversion technology usually takes a long time to process a large amount of airborne electromagnetic data, and it is difficult to remove the noise in the later signals. Therefore, this paper proposes a multi-task learning network structure based on Transformer. By constraining the two network branches of imaging and denoising, a sub-network with simultaneous denoising and imaging is established to process aeronautical electromagnetic data. The noise test set is introduced for testing. This model achieved a 582.61% signal-to-noise ratio improvement in smooth Gaussian noise denoising, and a 129.69% and 112.74% signal-to-noise ratio improvement in non-smooth Gaussian noise and random impulse noise denoising, respectively. The method proposed in this article overcomes the shortcomings of traditional inversion imaging such as slow speed and low resolution, and at the same time eliminates the influence of noise in airborne electromagnetic data. This is of great significance for the application of deep learning in the field of geophysical exploration.

To address the significant impact of noise on the target detection performance of borehole radar (BHR), a key type of ground-penetrating radar (GPR), a denoising scheme based on the whale optimization algorithm (WOA) for adaptive variational mode decomposition (VMD) and multiscale principal component analysis (MSPCA) is proposed. This study initially conducts the modal decomposition of BHR data using an improved adaptive VMD method based on the WOA; it then automatically selects modes meeting specific frequency band standards. The correlation coefficients between these modes and the original signal are computed, discarding weakly correlated modes before signal reconstruction. Finally, MSPCA further suppresses noise, yielding denoised BHR data. Simulations show that the proposed scheme increases the signal-to-noise ratio by 17.964 dB or higher, surpassing the more established denoising techniques of robust principal component analysis (RPCA), MSPCA, and empirical mode decomposition (EMD), and obtains the most favorable results in terms of the RMSE and MSE metrics. The experimental results demonstrate that the proposed scheme more effectively suppresses vertical and random noise signals in BHR data. Both the numerical simulations and experimental results confirm the effectiveness of this scheme in noise reduction for BHR data.

Crosswell electromagnetic (EM) methods are widely used in subsurface geophysical prospecting because they can achieve more effective long-distance detection than single-well methods. However, a large-diameter borehole is required to increase the magnetic moment of the magnetic dipole source. For the long-distance detection of copper ores, which is usually performed in slim holes, we present a borehole-surface current-injection-based crosswell EM logging method. Considering the cost of deploying casing, we inject a low-frequency AC directly into the ground, and converging current is formed around low-resistance anomalies in the formation. Then, the distribution of the anomalies can be inferred by detecting the low-frequency alternating magnetic field of the converging current in the receiver well. Moreover, to further improve the detection performance, we design a placement scheme for the grounding electrode for multi-anomaly crosswell detection based on the Gauss–Newton inversion algorithm, where the EM responses for different grounding electrode locations are analyzed. Field experiments are conducted using two slim open holes spaced approximately 1000 m apart for the detection of two copper ores. Through the processing and interpretation of measured EM signals, the conductivity imaging results of the crosswell EM method indicate that the measured distribution of anomalies is consistent with prior knowledge obtained from numerous single-well loggings, demonstrating the feasibility of the proposed application for long-distance crosswell EM logging in slim open holes.

The resolving power of metalens telescopes rely on their aperture size. Flat telescopes are advancing with the research on super-resolution confocal metalenses with large aperture. However, the aperture sizes of metalenses are usually bound within hundreds of micrometers due to computational and fabrication challenges, limiting their usage on practical optical devices like telescopes. In this work, we demonstrated a two-step designing method for the design of dual-band far-field super-resolution metalens with aperture sizes from the micro-scale to macro-scale. By utilizing two types of inserted unit cells, the phase profile of a dual-wavelength metalens with a small aperture of 100 μm was constructed. Through numerical simulation, the measured FWHM values of the focal spots of 5.81 μm and 6.81 μm at working wavelengths of 632.8 nm and 1265.6 nm were found to all be slightly smaller than the values of 0.61 λ/NA, demonstrating the super-resolution imaging of the designed metalens. By measuring the optical power ratio of the focal plane and the incident plane, the focusing efficiencies were 76% at 632.8 nm and 64% at 1265.6 nm. Based on the design method for small-aperture metalens, far-field imaging properties through the macro metalens with an aperture of 40 mm were simulated by using the Huygens–Fresnel principle. The simulation results demonstrate confocal far-field imaging behavior at the target wavelengths of 632.8 nm and 1265.6 nm, with a focal length of 200 mm. The design method for dual-band far-field super-resolution metalens with a large aperture opens a door towards the practical applications in the dual-band space telescope system.