Surface Wave Inversion Using a Multi-Information Fusion Neural Network

In noninvasive near-surface investigations, with the emergence of massive seismic datasets, surface wave inversion using deep learning (DL) can efficiently attain the shear-wave velocity (Vs) model. Existing researches on DL inversion, however, cannot handle the inversion nonuniqueness effectively. The geological constraint is only reflected in their training dataset. The input of their neural networks only contains dispersion curves (DCs), and thus, the density and compressional-wave velocity (Vp) need self-learning. To decrease the nonuniqueness, we propose a multiinformation fusion neural network (MFNN) in which we add the Vp, density, and sensitivity as parts of the input. To verify the effectiveness of the MFNN, we used a synthetic test and fieldwork, which both contain data from six regions to conduct multiregion simultaneous inversions. We compared the inversion results of the MFNN with the results of a convolutional neural network (CNN) and the ground truth. In the two experiments, although the calculated DCs based on the inverted Vs model from all the methods match well with the observed ones, only the inverted Vs from the MFNN successfully reflect the actual Vs structure and locate the high-velocity layer and low-velocity layer accurately. The constraints on the Vp, density, and sensitivity thus effectively reduce the nonuniqueness of inversions.