SVInvNet: A Densely Connected Encoder-Decoder Architecture for Seismic Velocity Inversion

This study presents a deep learning (DL)-based approach to the seismic velocity inversion problem, focusing on both noisy and noiseless training datasets of varying sizes. Our seismic velocity inversion network (SVInvNet) introduces a novel architecture that contains a multiconnection encoder-decoder structure enhanced with dense blocks. This design is tuned to effectively process time series data, which is essential for addressing the challenges of nonlinear seismic velocity inversion. For training and testing, we created diverse seismic velocity models, including multilayered, faulty, and salt dome categories. We also investigated how different kinds of ambient noise, both coherent and stochastic, and the size of the training dataset affect learning outcomes. SVInvNet is trained on datasets ranging from 750 to 6000 samples and is tested using a large benchmark dataset of 12 000 samples. Despite its fewer parameters compared to the baseline model, SVInvNet achieves superior performance with this dataset. The performance of SVInvNet was further evaluated using the OpenFWI dataset and Marmousi-derived velocity models. The comparative analysis clearly reveals the effectiveness of the proposed architecture.