稀疏井约束下可迁移预训练 3D 地震阻抗反演框架
A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning
搞地震勘探的可以看看这篇：传统方法每换一个工区都要重新训练模型，井数据又少得可怜。这篇用掩码自编码器预训练加冻结编码器，部署时完全不重训，Overthrust 数据上 P95 误差从 0.1310 降到 0.1074，盲井验证误差还降了 20.95%。
一篇 arXiv 论文提出可迁移的 3D 地震阻抗反演框架，将离线学习与目标勘探区部署分离。核心机制是用掩码自编码器从无标注多勘探区数据中学习地震结构表征，再把冻结的编码器嵌入反演网络，用稀疏井导出的低频先验在合成地质模型上训练。部署时整个反演网络保持固定，条件井仅用于构建低频先验并对齐全局阻抗范围，无需针对目标区重新训练。
在 Overthrust 模型实验中，该方法取得全体积最低 NRMSE，P95 道级 NRMSE 从 0.1310 降到 0.1074，相比最佳目标区训练基线减少了局部大误差。在实际勘探数据上，仅用 1 口条件井、3 口盲井验证时，盲井平均 NRMSE 相比目标区训练的 U-Net 降低 20.95%，同时保持最高相关性。
传统深度学习阻抗反演通常要为每个目标勘探区重新训练，在井控极稀疏时容易泛化失败。该框架以低部署成本实现了超出条件井位置的阻抗信息迁移，对勘探地球物理的产业化部署有直接参考价值。
A Transferable Pretrained 3D Model for Impedance Inversion with Sparse-Well Prior Conditioning
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include 阻抗反演, masked autoencoder, 地球物理, 深度学习.
Source attribution: curated from arXiv cs.LG (@Gen Li, Zhaoyun Zong, Diqiong Jiang, Man Tang).