基于多维度映射深度学习的地磁干扰抑制方法及系统

By employing a geomagnetic interference suppression method based on multi-dimensional mapping deep learning and utilizing the WPT-IncepResGRU denoising network model, the problem of insufficient denoising accuracy of geomagnetic signals is solved, achieving efficient denoising and data quality improvement of geomagnetic signals.

CN122194322BActive Publication Date: 2026-07-17CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA UNIV OF GEOSCIENCES (WUHAN)
Filing Date
2026-05-15
Publication Date
2026-07-17

Smart Images

  • Figure CN122194322B_ABST
    Figure CN122194322B_ABST
Patent Text Reader

Abstract

本申请属于电子信息、人工智能与地球物理交叉领域，具体公开了一种基于多维度映射深度学习的地磁干扰抑制方法及系统。将待处理的地磁数据输入至地磁数据分类模型中，获取无噪声的数据片段以及含噪声的地磁数据片段；将含噪声的地磁数据片段分段扩充处理后再维度转换，获取二维含噪地磁数据；将二维含噪地磁数据输入至地磁数据去噪模型中，获取二维数据去噪结果；再对二维数据去噪结果进行维度逆转换，获取一维去噪时间序列，并对其进行裁剪重构；将无噪声的数据片段与裁剪重构后的去噪数据进行组合，获取完整去噪后的地磁时间序列。本申请降低了计算复杂度，且提升了网络处理效率，为后续的时序建模和信号重建提供了清晰的数据表示。
Need to check novelty before this filing date? Find Prior Art