Low-Frequency Model Prediction of Acoustic Impedance Based on Spatiotemporal Gated Recurrent Unit Fusion Network

The absence of low-frequency (LF) component in seismic records leads to non-uniqueness in inversion, making the building of a reasonable LF model crucial for achieving high-precision acoustic impedance inversion. Artificial intelligence (AI) techniques represented by Gated Recurrent Unit (GRU) have shown favorable performance in the building of LF model. However, the problems of neural network overfitting and poor generalization due to small sample sizes remain challenging. We propose a neural network framework for LF model prediction towards small sample sizes. The framework utilizes the GRU as the basic unit and fully considers the long-term dependence in the time series of the LF model to ensure the integrity of vertical long-wavelength information. In order to improve the horizontal continuity of the LF model, a spatio-temporal feature fusion module is designed to convert the multi-trace data into potential vectors containing spatial information. Moreover, the seismic envelope and the initial model serve as prior information to guide the neural network, which is helpful for the network to yield stable predictions. In the synthetic and field data testing phase, spatial perturbations are introduced on the original data, it can generate more diverse labeled data. Experimental results demonstrate the predicted model on the basis of the initial model exhibit richer frequency components, more complete geological structures, and greater consistency with seismic records, and the predicted LF model of acoustic impedance not only aligns with the structural and depositional patterns of the area but also matches the measurements from a validation well.