cs.CVNov 16, 2026

A Seismic Foundation Model for Dense Feature Extraction

Authors: Zhixiang Guo, Xinming Wu, Yimin Dou, Hui Gao, Siyao Zhao, He Huang, Wei Liu

Organizations: Laboratory of Seismology and Physics of the Earth’s Interior, School of Earth and Space Sciences, University of Science and Technology of China, Hefei 230026, China. · State Key Laboratory of Precision Geodesy, University of Science and Technology of China, Hefei 230026, China. · Mengcheng National Geophysical Observatory, University of Science and Technology of China, Hefei 230026, China. · School of Artificial Intelligence, Anhui University of Science and Technology, Hefei 231131, China

Abstract

Deep-learning-based seismic interpretation is constrained by scarce high-quality annotations, and most existing models are trained separately for individual tasks. We present SeisDFE, a 7B-parameter seismic foundation model for dense feature extraction, pretrained on 5.34 million 2D images derived from more than 500 seismic volumes. A three-stage pretraining strategy, combining discriminative self-supervised learning, Gram feature anchoring, and multi-resolution adaptation, improves feature discriminability while preserving spatial coherence. With its encoder frozen, SeisDFE supports seismic facies classification, salt detection, fault detection, and relative geologic time estimation. It outperforms existing seismic foundation models on all four tasks and a natural-image-pretrained model on all but fault detection, with the largest gains under scarce supervision: using only two annotated sections of the F3 dataset, it improves whole-volume mIoU by 12-19 percentage points over the baselines. The learned features remain effective with task-specific decoders and extend to synthetic-to-field transfer and sparse 3D geobody interpretation. These results show that large-scale seismic pretraining organizes geological information into dense representations that are directly reusable across interpretation tasks.

Figures & tables

Explore similar work

CardsList
  1. Are Seismic Foundation Models More Than Glorified Feature Extractors?

    Oct 27, 2026Laura Laurenti, David Liu, Brian Kulis +2Time-Series Foundation ModelsSelf-Supervised Time Series Representation Learning

  2. Domain-Guided Prompting of the Segment Anything Model for Seismic Interpretation: The Role of Attributes, Visualization, and Hybrid Prompts

    Jun 14, 2026Aniq Ahmad, Heather Bedle, Ahmad MustafaPromptable Image SegmentationVision Foundation Model Adaptation

  3. Parameter-Efficient Adaptation of Pre-Trained Vision Foundation Models for Active and Passive Seismic Data Denoising

    Apr 30, 2026Jiahua Zhao, Umair bin Waheed, Jing Sun +3Test-Time AdaptationVision Foundation Model Adaptation