cs.LGNov 11, 2026

A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning

Authors: Gen Li, Zhaoyun Zong, Diqiong Jiang, Man Tang

Organizations: State Key Laboratory of Deep Oil and Gas, China University of Petroleum (East China), Qingdao 266580, China. · College of Computer Science and Technology, China University of Petroleum (East China), Qingdao 266580, P. R. China.

Abstract

Deep-learning-based seismic impedance inversion commonly requires retraining for each target survey, which may generalize poorly beyond the conditioning locations when well control is extremely sparse. We propose a transferable three-dimensional inversion framework that separates offline learning from target-survey deployment. A masked autoencoder first learns seismic structural representations from unlabeled multi-survey data, after which the frozen encoder is incorporated into an inversion network trained on synthetic geological models with sparse-well-derived low-frequency priors. During deployment, the complete inversion network remains fixed; the available conditioning well is used only to construct the low-frequency prior and align the global impedance range. Experiments on the Overthrust model show that the proposed method achieves the lowest full-volume NRMSE and reduces the P95 trace-wise NRMSE from 0.1310 to 0.1074 relative to the best target-trained baseline, indicating fewer localized large errors under different well locations. In a field survey with one conditioning well and three blind wells, it reduces the mean blind-well NRMSE by 20.95% relative to the target-trained U-Net while maintaining the highest correlation. These results demonstrate that the proposed framework transfers useful impedance information beyond the conditioning location with low deployment cost and without retraining the inversion network.

Explore similar work

Jul 23, 2026

Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imaging

Acoustic impedance imaging is a fundamental yet severely ill-posed problem in subsurface analysis: the seismic wavelet is unknown, observations are band-limited, and labeled well-log samples are extremely scarce (typically <1% of all traces). Existing semi-supervised deep learning methods mitigate few-shot problem by incorporating forward modeling, yet they either rely on inaccurate prior wavelet assumptions or introduce auxiliary networks, leading to unstable optimization and degraded performance. We propose RD-SCL, a novel framework that integrates regularized deconvolution with semi-supervised cross-learning. At its core lies a differentiable, closed-form first-order Tikhonov deconvolution operator that dynamically estimates the latent wavelet in the frequency domain during training, providing stable physics-guided feedback without explicit auxiliary networks and fixed wavelet priors. Building on this operator, we design a symmetric cross-learning that enforces consistency between predictions on labeled and unlabeled data, thereby effectively exploiting abundant unlabeled traces. Extensive experiments on the SEAM and Marmousi 2 benchmarks demonstrate that RD-SCL consistently outperforms state-of-the-art supervised and semi-supervised methods, achieving substantial gains with lower computational cost. With only 56.5k learnable parameters and competitive runtime, RD-SCL offers a practical, physically consistent, and efficient solution for acoustic impedance imaging.
Sep 28, 2026

Physical Cross-Modal Masked Autoencoding for Seismic-to-Well Representation Learning

Learning from scientific measurements often requires aligning modalities with different spatial support and resolution. Subsurface characterization is an extreme dense-sparse problem in which 3D seismic provides volumetric but indirect measurements and well logs provide high-resolution 1D measurements at sparse borehole locations. We introduce a physically grounded cross-modal masked autoencoder (CM-MAE) for seismic-to-well representation learning. The model jointly tokenizes seismic volumes and well-log depth patches, embeds both modalities in continuous physical coordinates using four-axis rotary position embeddings, and reconstructs masked targets with a cross-modal decoder. Sparse Mixture-of-Experts layers provide modality-specific capacity while dense attention allows information exchange between modalities. Pretraining uses 23 seismic volumes covering approximately 178,000 square km across U.S. offshore and onshore basins, together with approximately 92,000 wells. Matched-mask ablations show strongly asymmetric information flow. Seismic context improves held-out well-log reconstruction by 9.73%, while well-log context improves seismic reconstruction by 0.65%. We evaluate seismic-only pseudo-log predictions against independent interpreter-drawn salt-geobody masks to determine whether they contain geologic signal. Across offshore U.S. surveys, compressional-slowness-derived salt scores reach an AUROC of 0.910. In onshore basins, predicted compressional slowness preserves formation-scale structure and partial relative organization in an unseen survey despite calibration drift. CM-MAE learns useful seismic-to-well representations under extreme modality asymmetry, although absolute pseudo-log calibration remains survey-dependent.
Mar 16, 2026

Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method

Seismic inversion is a core problem in geophysical exploration, where traditional methods suffer from high computational costs and are susceptible to initial model dependence. In recent years, deep generative model-based seismic inversion methods have achieved remarkable progress, but existing generative models struggle to balance sampling efficiency and inversion accuracy. This paper proposes an end-to-end fast seismic inversion method based on Conditional Rectified Flow[1], which designs a dedicated seismic encoder to extract multi-scale seismic features and adopts a layer-by-layer injection control strategy to achieve fine-grained conditional control. Experimental results demonstrate that the proposed method achieves excellent inversion accuracy on the OpenFWI[2] benchmark dataset. Compared with Diffusion[3,4] methods, it achieves sampling acceleration; compared with InversionNet[5,6,7] methods, it achieves higher accuracy in generation. Our zero-shot generalization experiments on Marmousi[8,9] real data further verify the practical value of the method. Experimental results show that the proposed method achieves excellent inversion accuracy on the OpenFWI benchmark dataset; compared with Diffusion methods, it achieves sampling acceleration while maintaining higher accuracy than InversionNet methods; experiments based on the Marmousi standard model further verify that this method can generate high-quality initial velocity models in a zero-shot manner, effectively alleviating the initial model dependency problem in traditional Full Waveform Inversion (FWI), and possesses industrial practical value.