Kirchhoff beam migration is a kind of ray-based seismic imaging method boasting the advantages of both high efficiency and high accuracy. In this paper, anisotropic ray tracing will be applied to extend it to an anisotropic seismic imaging method. However, two problems exist in this method for imaging calculation: Firstly, the conventional local plane wave decomposition method has a low computational precision; secondly, the original beam propagator diverges quickly when the propagation distance increases. These two problems can both increase imaging noise, and finally reduce the resolution of the final imaging results. In this paper, the high-resolution anisotropic Kirchhoff dynamic focused beam migration is proposed to solve these two problems. Local plane wave decomposition method considered from the perspective of inversion is employed to obtain higher-quality slant stack data and dynamic focused beam propagator is adopted to control the divergence of beams. Both the anisotropic layer model and Hess model are adopted to test the imaging ability of the new method.

The effectiveness of ground penetrating radar (GPR) in identifying and categorizing diseases that occur underground beneath the surfaces of urban roads is investigated in this study. Both 2D and 3D forward modeling use simulation with the GprMax program to show the response characteristics of common cavity illnesses, which facilitates interpretation in practical situations. The cavity morphology classification accuracy is improved to 90.5% by using convolutional neural networks (CNNs), specifically transfer learning with AlexNet. This method outperforms existing approaches even with minimal data. Four primary types are identified from an analysis of 1965 subsurface cavity data: hollow bodies, empty bodies, loose bodies, and water-rich bodies. These categories are important for evaluating road risks such as voids and subsidence. However, it is still difficult to interpret picture features linked to cavity diseases accurately because of a variety of elements, such as anthropogenic, environmental, and geological influences. However, the accurate interpretation and recognition of image features related to cavity diseases remain challenging. Moreover, there are various factors involved in the formation of underground diseases and cavities, including geological and environmental factors, physical and chemical properties of the geotechnical materials, anthropogenic engineering activity and social population or commercial effects.

Potential field data are of great significance to the study of geological characteristics. Downward continuation of the potential field converts potential field data from a high plane to a low plane. Since this method is mathematically an inverse problem solution, it is unstable. The Tikhonov regularization strategy is an effective means of the downward continuation of the potential field. However, achieving high-precision requirements in the stage of precise geophysical exploration is still challenging. Deep learning can effectively solve unstable problems with excellent nonlinear mapping capabilities. Inspired by this, for the downward continuation of the potential field, we propose a new neural network architecture for downward continuation named D-Unet. This study uses the potential field data of a high horizontal plane and the initial model as the network’s input, with the corresponding low-level data serving as the output for supervised learning. Moreover, we add noise to 10% of the data in the training dataset. Model testing shows that our D-Unet has higher accuracy, validity, and stability. In addition, adding noise to the training data can further improve the robustness of the model. Finally, we use the actual potential data of a particular place in northeast China to test our model and satisfactory results have been obtained.

Kirchhoff beam migration (KBM) is a ray-based seismic imaging method, which can handle multi-arrivals caused by model complexity. Apart from its high imaging precision, it also retains the merits of Kirchhoff migration, such as efficiency, stability, and flexibility. However, two issues should be taken into consideration when this method is expanded to the complicated surface conditions: first, the computational accuracy deficiency of the original local plane-wave decomposition method cannot suit for low signal-to-noise ratio seismic data; second, as the rays traveling, the beam width increases rapidly, which cannot guarantee the computational accuracy of the corresponding grid points’ attribute information. In addition, the insufficient coverage of the beam in the shallow part of the model might affect the imaging quality of this region. Kirchhoff dynamic focused beam migration based on compressed sensing is proposed to resolve these two problems. For the first problem, the local plane-wave decomposition method based on compressed sensing is introduced into KBM to enhance its computational accuracy. To solve the second problem, this paper adopts the dynamic focused beam to replace the original simplified Gaussian beam in the migration method, control the divergence of beam, and increase the coverage of beam in the shallow part of the model. Both Marmousi model and Canadian Foothills model are employed in this paper to test the new migration imaging method.