Three-dimensional seismic interpretation and property estimation is essential for subsurface mapping and characterization, in which machine learning. particularly supervised convolutional neural network (CNN), has been extensively implemented for improved efficiency and accuracy in the past few years. However, in most seismic applications, the amount of available expert annotations often is limited, which raises the risk of overfitting a CNN, particularly when only seismic amplitudes are used for learning. In such a case, the trained CNN would have poor generalization capability, causing the interpretation and property results of obvious artifacts, limited lateral consistency, and thus restricted application to following interpretation/modeling procedures. Our study proposes addressing such an issue by using relative geologic time (RGT). which explicitly preserves the large-scale of seismic patterns, to constrain a seismic interpretation and/or property estimation CNN. Such constrained learning is enforced twofold: (1) from the perspective of input, the RGT is used as an additional feature channel besides seismic amplitude, and more innovatively (2) the CNN has two output branches, with one for matching the target interpretation or properties and the other for reconstructing the RGT. In addition, multiplicative regularization is used to facilitate the simultaneous minimization of the target-matching loss and the RGT-reconstruction loss. The performance of such an RGT-constrained CNN is validated by two examples, facies identification in the Parihaka data set and property estimation in the F3 Netherlands data set. Compared with those purely from seismic amplitudes, the facies and property predictions using the proposed RGT constraint demonstrate significantly reduced artifacts and improved lateral consistency throughout a seismic survey.
展开▼
