arXiv subjects

Liangsheng He

Publications and source records attributed to Liangsheng He.

3 recordsLinked to original sources

arXiv2026

Tensor Train Decomposition-based 3D Implicit Full Waveform Inversion with Multi-scale Structural Similarity

Three-dimensional full waveform inversion (3DFWI) is a powerful technique for reconstructing high-resolution subsurface velocity models. However, its application is often limited by high memory requirements, computational costs, and sensitivity to cycle skipping. To overcome these challenges, we propose a novel tensor train (TT) decomposition-based 3D implicit full waveform inversion framework (TT-3DIFWI) combined with a multi-scale structural similarity (M-SSIM) objective function. In this framework, the 3D velocity model is represented by TT decomposition as a product of a series of low-rank core tensors. Then, three axis-specific implicit neural network representations (INR) based on one-dimensional vector coordinates as input are constructed to predict these core tensors, rather than directly predicting the velocity model. This INR reparameterization method based on TT decomposition can significantly reduce the memory consumption of INR training while maintaining the accuracy and resolution of the 3D velocity model reconstruction. Meanwhile, the low-rank structure of TT decomposition also ensures the structural consistency of the reconstruction velocity, thereby improving the accuracy and continuity of the inversion result. Furthermore, the M-SSIM objective function can compare the multi-scale structural differences between predicted and observed data, and utilize the ultra-low frequency features to reduce cycle skipping. Numerical experiments on synthetic and challenging land datasets demonstrate that TT-3DIFWI with M-SSIM achieves accurate and continuous velocity reconstruction, even with poor initial models or missing low-frequency data.

physics.geo-ph↗

arXiv2025

Fast ground penetrating radar dual-parameter full waveform inversion method accelerated by hybrid compilation of CUDA kernel function and PyTorch

This study proposes a high-performance dual-parameter full waveform inversion framework (FWI) for ground-penetrating radar (GPR), accelerated through the hybrid compilation of CUDA kernel functions and PyTorch. The method leverages the computational efficiency of GPU programming while preserving the flexibility and usability of Python-based deep learning frameworks. By integrating customized CUDA kernels into PyTorch's automatic differentiation mechanism, the framework enables accurate and efficient inversion of both dielectric permittivity and electrical conductivity. Experimental evaluations on synthetic data and real wavefield data demonstrate that the proposed method achieves dual-parameter FWI for GPR data while maintaining high accuracy. Moreover, the framework is flexible and extensible, supporting optional regularization strategies such as total variation and multi-scale inversion. These features make the proposed approach a practical and scalable framework for rapid GPR-based subsurface imaging in applications including civil engineering, environmental monitoring, and geophysical exploration.

physics.geo-ph↗

arXiv2025

MS_ATpV-FWI: Full Waveform Inversion based on Multi-scale Structural Similarity Index Measure and Anisotropic Total p-Variation Regularization

Full waveform inversion (FWI) is a high-resolution seismic inversion technique popularly used in oil and gas exploration. Traditional FWI employs the $l_2$ norm measurement to minimize the misfit between observed and predicted seismic data. However, when the background velocity is inaccurate or the seismic data lacks low-frequency components, the conventional FWI suffers from cycle skipping, leading to inaccurate inversion results. This paper introduces a multiscale structural similarity index measure (M-SSIM) objective function for FWI. We also incorporate anisotropic total p-variation regularization (ATpV) to further improve the accuracy of FWI. M-SSIM extracts multi-scale structural features of seismic data in terms of both phase and amplitude. These features can reduce the risk of cycle skipping and improve the stability of FWI. Additionally, ATpV applies structural constraints to the velocity gradients, which helps suppress artifacts and preserve the sharp boundaries of geological formations. We propose to use the automatic differentiation (AD) to efficiently and stably optimize this novelly introduced FWI objective function. Both synthetic and field seismic data demonstrate that the proposed method accurately characterizes complex subsurface velocity structures, even when the background velocity is crude, the data lacks low-frequency components, or contains noise.

physics.geo-ph↗