Underground porosity is important in many earth sciences and engineering fields, including hydrocarbon reservoir characterization and geothermal energy production. Popular methods largely rely on the analysis of lithological core data, well logs, and seismic inversion methods. While these methods are reliable, they are also time-consuming, expensive, and difficult to implement. In addition, seismic inversion has nonlinearity, data dimensionality, and non-uniqueness issues. However, deep learning (DL) can provide a more flexible, efficient, and accurate capability by mapping directly from seismic attributes to underground porosity. Therefore, we trained several DL models with different optimization functions. In the training steps, we labeled every seismic attribute data point with its corresponding porosity derived from the well logs. In contrast to popular ensemble techniques, we proposed a weighted prediction approach based on the strengths of each model. Testing results showed a coefficient of determination (R ² ) of 0.94345 and a Pearson’s correlation coefficient of 0.9725 between the measured model and the model of the proposed approach, versus 0.9681 and 0.9716 for the best single and popular ensemble models, respectively. Further, we tested the effectiveness of our method using real seismic data from the North Sea. With a Pearson’s correlation value of 0.9743, the inverted model ranges from 27 to 35%, compared to the reference model, which has an overall range of 20 to 33%.These results provide insights into the potential of the proposed method and its applicability to any other seismic volume to determine spatially varying underground porosity from seismic attributes directly.

Conventional curvelet-domain denoising methods suppress random noise by thresholding the amplitude of curvelet coefficients, which makes it hard to distinguish weak seismic signals from random noise because they share the same characteristic of weak amplitude in the curvelet domain. Here we put forward an innovative weak seismic signal enhancement method taht can distinguish weak seismic signals from random noise. After compressive sampling, the curvelet coefficients of weak seismic signals show significant amplitude reduction, whereas random noise does not. We take advantage of this characteristic and design a sensitivity coefficient, the absolute ratio of curvelet coefficients before and after compressive sampling. The sensitivity coefficient can distinguish weak seismic signals from random noise in the curvelet domain better than thresholding the amplitude of curvelet coefficients. The results of synthetic and field seismic data applications both indicate that our method outperforms the conventional curvelet-domain denoising method on weak seismic signal enhancement.

Using data from 186 stations belonging to the USArray Transportable Array, a three‐dimensional shear wave velocity model for the southeastern United States is constructed for the top 180 km by a joint inversion of receiver functions and Rayleigh wave phase velocity dispersion computed from ambient noise and teleseismic earthquake data. The resulting shear wave velocity model and the crustal thickness and Vp/Vs () measurements show a clear spatial correspondence with major surficial geological features. The distinct low velocities observed in the depth range of 0–25 km beneath the eastern Gulf Coastal Plain reflect the thick layer of unconsolidated or poorly consolidated sediments atop the crystalline crust. The low (1.70–1.74) and slow lowermost crustal velocities observed beneath the eastern Southern Appalachian Mountains (including the Carolina Terrane and Inner Piedmont) relative to the adjacent Blue Ridge Mountains and Valley and Ridge can be interpreted by lower crustal delamination followed by relamination. The Osceola intrusive complex in the central Suwannee Terrane has similar crustal characteristics as the eastern Southern Appalachian Mountains and thus can similarly be attributed to crustal delamination/relamination processes. The Grenville Province and adjacent areas possess relatively high values which can be attributed to mafic intrusion associated with crustal extension in a recently recognized segments of the eastern arm of the Proterozoic Midcontinent Rift.