Toward Artifact-Free Impedance Inversion by a Semi-Supervised Network With Super-Resolution and Attention Mechanism

Estimating the subsurface impedance properties is an essential process in seismic exploration and reservoir characterization. The accuracy and efficiency of impedance inversion have been greatly improved by semi-supervised methods. However, existing semi-supervised inversion methods treat poststack seismic traces as independent sequential time series, which causes accumulated prediction errors along the time axis and horizontally noncontinuous seismic events. We propose a semi-supervised impedance inversion network. The new contribution includes two perspectives: 1) an attention mechanism is utilized to derive data-adaptive weights from both the time and positional axes, which largely reduces the artifacts in conventional semi-supervised impedance inversions and 2) a super-resolution module is implemented to reconcile the dimensional inconsistency between seismic data and the resultant impedance profile. By testing on the Marmousi2 model, the SEG advanced modeling (SEAM), as well as the field data, we show that the newly added modules can largely reduce the artifacts and improve the prediction accuracy for acoustic impedance.