@article{Liu2026, 
author = {Ying-Tian Liu and Yong Li and Jun-Heng Peng and Jian-Yong Xie and Xian-Qiong Chen},
title = {Semi-supervised learning for AVO inversion with bidirectional spatial feature constraints},
year = {2026},
journal = {Petroleum Science},
volume = {23},
number = {5},
pages = {2501-2526},
keywords = {AVO inversion, Deep learning, Spatial feature constraints, Semi-supervised learning},
url = {https://www.sciopen.com/article/10.1016/j.petsci.2026.01.005},
doi = {10.1016/j.petsci.2026.01.005},
abstract = {Prestack amplitude variation with offset (AVO) inversion using one-dimensional convolutional neural networks often lacks lateral continuity. While two-dimensional methods improve this, they are limited to unidirectional spatial correlations from well to non-well locations. To overcome these limitations, we propose a semi-supervised learning approach with bidirectional spatial feature constraints (BSFC-SSL). Our method introduces a label-annihilation operator and a dedicated spatial feature network to establish bidirectional information flow between well and non-well locations, thereby capturing more complex spatial patterns in seismic data. Integrated with semi-supervised learning and low-frequency constraints, the BSFC-SSL framework enhances both stability and generalization. Experiments on synthetic and field data demonstrate that our method achieves superior lateral continuity and inversion accuracy compared to conventional one- and two-dimensional deep learning techniques.}
}