
Abstract Seismic acquisition design requires identifying an effective acquisition geometry from a large number of possible configurations. Conventional deterministic optimization methods may become computationally expensive for large search spaces, depend on the initial geometry, and explore only a limited subset of possible configurations. This leads to a combinatorial optimization problem that is generally NP-hard. In this study, we investigate reinforcement learning (RL) as an alternative strategy for target-oriented seismic acquisition design. Under the assumption that the target-reflector image is approximately known, we formulate the source-position design as a Markov decision process and solve it using a deep Q-learning algorithm. For source-position optimization, each state in the RL framework represents a candidate source configuration. Each action modifies the current geometry by moving one source position to the left or right. The reward function is defined by the change in an imaging objective function associated with point-spread functions, thereby encouraging acquisition geometries that improve target illumination and image quality. To make the method computationally feasible, we use Kirchhoff modeling and migration with wave-equation-based amplitudes and traveltimes, and precompute point-spread functions for candidate source positions. Numerical examples show that deep Q-learning identifies source configurations that produce higher-quality target-reflector images than uniform and randomly sampled geometries. These results demonstrate the potential of RL for exploring large and nonlinear seismic acquisition-design spaces.
Over the past few years, there has been a significant evolution in SEG’s publications. SEG publishes three peer-reviewed journals: Geophysics, Interpretation, and The Leading Edge, each with a distinctive focus on geophysics (https://seg.org/publications/journals/); a large range of book titles and reference manuals (https://seg.org/publications/books/), and maintains a vast digital library (https://pubs.geoscienceworld.org/seg).
Energy security is reshaping geophysics across the Middle East and beyond. Yogaani Bhatia, SEG Managing Director, Global Strategy and Operations (MEA/Asia Pacific), discusses renewed exploration, growing investment in mining and geological knowledge, and the need to better understand the subsurface. As that investment accelerates, success will depend not only on better technology, but on people who know how to use it.
Abstract Fault zones were treated as finite-width deformation structures rather than discontinuous lines. A cumulative maximum tensor shear attribute, γp,max, was defined from incremental plastic strain and accumulated as a nondecreasing shear-path-length measure. In two dimensions, instantaneous maximum tensor shear corresponded to the radius of the in-plane strain Mohr circle. The component and principal-strain forms were derived, and their factor-of-two relation to engineering shear was made explicit. A monotonic simple-shear example showed that the thickness-averaged cumulative attribute satisfied s=2γ¯p,maxt, whereas nonuniform or rotating deformation required integration across the band. Continuum-discrete element method (CDEM) examples showed high cumulative shear along modeled fault cores and tips, and lower values across distributed deformation zones. The workflow produced registered mechanical targets and structural models suitable for subsequent synthetic-seismic and machine-learning experiments, while remaining subject to small-strain, constitutive, and spatial-resolution limitations.