Physics-guided Fully Convolutional Network using attenuation information for viscoacoustic velocity model prediction
Abstract
Abstract Accurate seismic velocity model reconstruction remains challenging in attenuative media because conventional data-driven approaches generally infer subsurface properties from seismic waveforms without explicitly exploiting information associated with seismic energy dissipation. This limitation is particularly relevant in complex geological settings, where attenuation may provide complementary physical information for velocity estimation. In this study, we investigate an attenuation-informed Fully Convolutional Network (FCN) for predicting viscoacoustic velocity models. Unlike learning-based approaches primarily designed to estimate the quality factor (Q), the proposed method uses attenuation-related information as an auxiliary input feature to assist velocity model reconstruction. A dataset of 10,000 velocity models derived from the Marmousi II model was used for training, with five finite-difference-generated shot gathers associated with each model. The attenuation parameter matrices corresponding to the seismic data were incorporated into the FCN training process, while an otherwise equivalent FCN trained without this additional information was adopted as the baseline. The reconstructed models were also compared with a Full-Waveform Inversion (FWI) result. For the numerical experiment considered, incorporating attenuation information reduced the global velocity RMSE from 0.0237 for the conventional FCN to 0.0204 for the proposed configuration, corresponding to an…
Read the paper
Related studies
- Current state and future directions for deep learning based automatic seismic fault interpretation: A systematic review
- Physics of Partially Saturated Porous Media: Residual Saturation and Seismic-Wave Propagation
- Modern Imaging Using Seismic Reflection Data
- Effects of marine seismic surveys on free-ranging fauna: a systematic literature review
- A review of the recent seismic activity in the southern part of egypt (upper egypt)
- A review of research on mechanism of seismic attenuation and energy compensation
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.