A Frequency-Aware Dynamic Knowledge Distillation Framework: An Effective Tool for Bridging Low- and High-Frequency Seismic Information
Abstract
Seismic data contain rich information across different frequency bands, with low-frequency components primarily characterizing large-scale geological structures and high-frequency components preserving fine-scale seismic details. Effectively integrating these frequency-dependent components is essential for seismic feature learning to better preserve structural continuity and fine-scale details. Knowledge distillation provides an effective means for transferring informative representations from high-quality data. However, existing distillation-based frameworks usually treat seismic features in a full-band manner, ignoring relationships across frequency bands and thereby limiting the coordinated transfer of low- and high-frequency knowledge. To bridge low- and high-frequency seismic features through knowledge distillation, we propose a frequency-aware dynamic knowledge distillation framework (FADKD-Net), which establishes a teacher-student learning framework and performs frequency-aware knowledge transfer between low- and high-frequency bands. Specifically, FADKD-Net decomposes seismic features into low- and high-frequency components and performs targeted distillation to exploit their complementary information. Low-frequency distillation guides the student model to learn stable structural priors, thereby improving the overall continuity of seismic events. Meanwhile, high-frequency distillation enhances detailed feature modeling and improves the representational capability for complex and small-scale structures. Furthermore, a cross-domain feature alignment strategy is proposed to reduce distributional discrepancies across different surveys and enhance the transferability of the seismic representations learned by FADKD-Net.
Related
- Medium-entropy metal-organic framework-integrated catalytic distillation system for near 100% urea removal
- Integrating causal knowledge with satellite and glider data: a novel framework for marine water quality simulation
- Web-messaging-based dissemination of urban rainfall and flood information: a Telegram bot framework
- Non-stationary low-flow frequency analysis with mixed Weibull components and Copula-based dependence framework
- From data availability to evidence sufficiency. PIH MS as an auditable framework for diagnosing hydrogeological knowledge gaps in Mato Grosso do Sul, Brazil
BibTeX
@misc{ma2026frequencyaware,
title = {{A Frequency-Aware Dynamic Knowledge Distillation Framework: An Effective Tool for Bridging Low- and High-Frequency Seismic Information}},
author = {Jun Ma and Xinyang Wang and Xintong Dong},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.00828},
eprint = {2609.00828},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00828},
}
RIS
TY - UNPB
TI - A Frequency-Aware Dynamic Knowledge Distillation Framework: An Effective Tool for Bridging Low- and High-Frequency Seismic Information
AU - Jun Ma
AU - Xinyang Wang
AU - Xintong Dong
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.00828
UR - https://arxiv.org/abs/2609.00828
AB - Seismic data contain rich information across different frequency bands, with low-frequency components primarily characterizing large-scale geological structures and high-frequency components preserving fine-scale seismic details. Effectively integrating these frequency-dependent components is essential for seismic feature learning to better preserve structural continuity and fine-scale details. Knowledge distillation provides an effective means for transferring informative representations from high-quality data. However, existing distillation-based frameworks usually treat seismic features in a full-band manner, ignoring relationships across frequency bands and thereby limiting the coordinated transfer of low- and high-frequency knowledge. To bridge low- and high-frequency seismic features through knowledge distillation, we propose a frequency-aware dynamic knowledge distillation framework (FADKD-Net), which establishes a teacher-student learning framework and performs frequency-aware knowledge transfer between low- and high-frequency bands. Specifically, FADKD-Net decomposes seismic features into low- and high-frequency components and performs targeted distillation to exploit their complementary information. Low-frequency distillation guides the student model to learn stable structural priors, thereby improving the overall continuity of seismic events. Meanwhile, high-frequency distillation enhances detailed feature modeling and improves the representational capability for complex and small-scale structures. Furthermore, a cross-domain feature alignment strategy is proposed to reduce distributional discrepancies across different surveys and enhance the transferability of the seismic representations learned by FADKD-Net.
ER -