WebJun 12, 2024 · Unlike the conventional inversion method based on physical models, supervised deep-learning methods are based on big-data training rather than prior-knowledge assumptions. During the training stage, the network establishes a nonlinear projection from the multishot seismic data to the corresponding velocity models. WebMay 2, 2024 · Machine learning (ML) methods have been the focus of increasing attention in the geoscience community in recent years. The principal reason for this is the recent rise of deep learning (DL) in almost every field of science and engineering following the great success in computer vision tasks in the early 2010s (Krizhevsky et al. 2012). In the ...
Deep learning inversion with supervision: A rapid and cascaded …
WebAug 7, 2024 · The subsurface velocity model is crucial for high-resolution seismic imaging. Although full-waveform inversion (FWI) is a high-accuracy velocity inversion method, it inevitably suffers from challenging problems, including human interference, strong nonuniqueness, and high computing costs. As an efficient and accurate nonlinear … WebApr 13, 2024 · Abstract. Borehole resistivity measurements are routinely employed to measure the electrical properties of rocks penetrated by a well and to quantify the hydrocarbon pore volume of a reservoir. Depending on the degree of geometrical complexity, inversion techniques are often used to estimate layer-by-layer electrical … boulder county jail in longmont
[1901.07733] Deep-Learning Inversion of Seismic Data
WebMay 1, 2024 · The inversion results show that when dealing with multiple defects of complex shape on a plate-like structure, DLIS methods can reduce the scale of training set effectively compared with other deep learning algorithms in experiment because a good starting model is provided and the nonlinearity between the global minimum and … WebFeb 1, 2024 · The deep-learning-based inversion does not depend on the kernel matrix and depth weighting, especially it can automatically extract useful inversion information without the need for human-curated activities. Compared with conventional inversion methods, deep learning is a data driven process that does not need to deal with non … WebMar 24, 2024 · Simulation results demonstrate that compared with the conventional matched-field inversion (MFI), the CNN with MRP alleviates the coupling between the geoacoustic parameters and is more robust to different source depths in the shallow water environment. ... Liu, H. Niu, Z. Li, and M. Wang, “ Deep-learning source localization … boulder county jobs board