Structure-Guided Deep Learning for Depth-Domain Seismic Impedance Inversion

Deep learning (DL) has demonstrated significant potential for direct seismic impedance inversion in the depth domain. However, conventional DL frameworks often adopt a trace-by-trace strategy, which fails to account for the spatial coherence of subsurface structures, leading to lateral discontinuities and a lack of geological guidance. To address these limitations, we propose a Dip-constrained Multi-trace Deep learning framework (DMDNN) for depth-domain seismic inversion. This approach integrates structural dip as a geological prior through a sliding window mechanism to quantify the spatial continuity of strata, thereby providing the explicit geological guidance missing in traditional methods. Unlike the standard multi-trace input paradigm, the proposed method establishes physical correlations between adjacent traces via an implicit lateral constraint mechanism in the loss function, enabling effective multi-trace collaborative inversion even with single-trace inputs. Furthermore, a Huber loss function is employed for label constraints to enhance the framework’s resilience to seismic noise, offering superior stability over standard Mean Square Error (MSE) metrics. Extensive evaluations on synthetic and field datasets demonstrate that, with properly calibrated weights for the structural dip loss and constraint window sizes, the DMDNN significantly enhances lateral continuity and vertical resolution while maintaining high geological plausibility. By reducing dependency on large-scale training samples, this method provides a robust and geologically consistent pathway for reservoir characterization in complex structural zones.