analiza aiqbench
This research introduces DREMnet, a novel deep learning framework utilizing RWKV architectures and contextual embedding techniques specifically designed for denoising semi-airborne transient electromagnetic signals. By disentangling signal content from noise context, the model addresses critical interpretability gaps in existing single-mapping approaches while improving subsurface structure identification accuracy. This advancement represents a significant step forward in applying machine learning to geophysical data processing where traditional parameter selection methods fall short.
DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal
arXiv:2503.22223v2 Announce Type: replace Abstract: The semi-airborne transient electromagnetic method (SATEM) is capable of conducting rapid surveys over large-scale and hard-to-reach areas. However, the acquired signals are often contaminated by complex noise, which can compromise the accuracy of subsequent inversion interpretations. Traditional denoising techniques primarily rely on parameter selection strategies, which are insufficient for processing field data in noisy environments. With the advent of deep learning, various neural networks have been employed for SATEM signal denoising. However, existing deep learning methods typically use single-mapping learning approaches that struggle to effectively separate signal from noise. These methods capture only partial information and lack interpretability. To overcome these limitations, we propose an interpretable decoupled representation learning framework, termed DREMnet, that disentangles data into content and context factors, enabling robust and interpretable denoising in complex conditions. To address the limitations of CNN and Transformer architectures, we utilize the RWKV architecture for data processing and introduce the Contextual-WKV mechanism, which allows unidirectional WKV to perform bidirectional signal modeling. Our proposed Covering Embedding technique retains the strong local perception of convolutional networks through stacked embedding. Experimental results on test datasets demonstrate that the DREMnet method outperforms existing techniques, with processed field data that more accurately reflects the theoretical signal, offering improved identification of subsurface electrical structures.
Abstract:The semi-airborne transient electromagnetic method (SATEM) is capable of conducting rapid surveys over large-scale and hard-to-reach areas. However, the acquired signals are often contaminated by complex noise, which can compromise the accuracy of subsequent inversion interpretations. Traditional denoising techniques primarily rely on parameter selection strategies, which are insufficient for processing field data in noisy environments. With the advent of deep learning, various neural networks have been employed for SATEM signal denoising. However, existing deep learning methods typically use single-mapping learning approaches that struggle to effectively separate signal from noise. These methods capture only partial information and lack interpretability. To overcome these limitations, we propose an interpretable decoupled representation learning framework, termed DREMnet, that disentangles data into content and context factors, enabling robust and interpretable denoising in complex conditions. To address the limitations of CNN and Transformer architectures, we utilize the RWKV architecture for data processing and introduce the Contextual-WKV mechanism, which allows unidirectional WKV to perform bidirectional signal modeling. Our proposed Covering Embedding technique retains the strong local perception of convolutional networks through stacked embedding. Experimental results on test datasets demonstrate that the DREMnet method outperforms existing techniques, with processed field data that more accurately reflects the theoretical signal, offering improved identification of subsurface electrical structures.
Machine Learning (cs.LG)
arXiv:2503.22223 [cs.LG]
(or arXiv:2503.22223v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2503.22223 Focus to learn more arXiv-issued DOI via DataCite
IEEE Transactions on Geoscience and Remote Sensing, vol. 64, pp. 1-12, 2026, Art no. 5907212
https://doi.org/10.1109/TGRS.2026.3680901 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 323 cuvinte
Subiecte conexe
Interpretable Deep Learning Paradigm for Airborne Transient Electromagnetic Inversion
arXiv · 23 iul. 2026
$\texttt{findr}$: Transparent and Fair Credit Risk Decisions through Semi-Structured Regressions
arXiv · 27 aug. 2026
Cavity QED links quantum and classical thermodynamics in new model
Quantum Zeitgeist · 31 aug. 2026
An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modeling
arXiv · 8 oct. 2026