Deep learning-based seismic facies analysis enhanced with geophysical knowledge

Seismic facies analysis plays a key role in stratigraphy and has developed rapidly in the context of deep-learning methods. However, seismic facies analysis cannot be regarded solely as an image segmentation or classification task because doing so would ignore geophysicists’ prior knowledge of seismic interpretation. Seismic parameters summarized by geophysicists were included in the seismic facies analysis model. Seismic parameters were used to calibrate the different seismic facies units, and well-logging data and sequence stratigraphy were integrated to perform geologic interpretation and establish a training data set. A multihead seismic parameter classification (MSPC) model was then established to divide the seismic facies units. A seismic facies geologic interpretation (SFGI) model was constructed for the geologic interpretation of seismic facies units, and an end-to-end seismic facies analysis model was designed based on the MSPC model and the SFGI model. Our model effectively improves the accuracy of seismic interpretation, solves the intra-facies noise problem, and is easy to train and use.