Semi-Supervised Seismic Impedance Inversion With Convolutional Neural Network and Lightweight Transformer

Seismic impedance inversion has yielded significant results through the use of deep learning. Currently, convolutional module-based networks also achieve noteworthy results. However, deep learning requires a large amount of labeled data for training to enhance inversion accuracy. In addition, the deep learning method, being end-to-end, overlooks forward and adjoint problem knowledge during seismic impedance inversion and fails to integrate geophysical constraints. Therefore, this article proposes a semi-supervised deep learning method to address these issues. Specifically, this method includes an inverse model and a forward model. The inverse model, a deep learning fusion model named CLWTNet, combines a multiscale convolutional neural network (MSCNN) and a lightweight transformer. CLWTNet captures multiscale local and global information, addressing the limitations of traditional convolutional networks that only capture partial information due to their limited receptive fields. Moreover, CLWTNet uses dilated convolution, transposed self-attention, and residual modules to enhance computational efficiency and stability. The forward model, a 1-D convolutional network, generates seismic traces from predicted impedances. These traces are then compared with the input seismic traces to inform the learning process of the inverse model. This approach also mitigates the challenge of limited labeled data. Testing with the SEAM synthetic model and field data demonstrates that the prediction accuracy and lateral continuity of the network surpass that of similar neural networks. In field dataset tests, this network demonstrates superior performance over three similar networks in predicting impedance. The network is characterized by its excellent lateral continuity and high resolution.