Multi-attribute Deep Learning Using Wavelet Scattering Transform for Seismic Lithology Interpretation

Seismic lithology interpretation based on seismic data is an important task to delineate oil and gas reservoirs. However, this is an extremely unstable work when only utilizing seismic data, which would result in multiple solutions. We suggest a multi-attribute deep learning (MADL) workflow for seismic lithology interpretation. To implement the proposed model, we first propose to apply the wavelet scattering transform (WST) to seismic data for multi-scale features extraction. Note that the WST has local deformation stability and translation invariance for analyzing seismic data, which would be proven to promote seismic lithology interpretation. Next, the MADL model is suggested to combine the multi-scale features extracted by the WST and seismic data simultaneously, which can improve the accuracy of seismic lithology interpretation. Afterward, the Res-UNet, which incorporates residual blocks into the UNet, is introduced to avoid the over-fitting of the proposed MADL model. Finally, a 2-D post-stack field data is adopted to test the effectiveness of the suggested MADL model for seismic lithology interpretation.