Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.13395 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910835528433664 |
|---|---|
| author | Huang, Tianye Li, Aopeng Li, Xiang Zhang, Jing Xian, Sijing Zhang, Qi Lu, Mingkong Chen, Guodong Xiong, Liangming Hu, Xiangyun |
| author_facet | Huang, Tianye Li, Aopeng Li, Xiang Zhang, Jing Xian, Sijing Zhang, Qi Lu, Mingkong Chen, Guodong Xiong, Liangming Hu, Xiangyun |
| contents | Distributed acoustic sensor (DAS) technology leverages optical fiber cables to detect acoustic signals, providing cost-effective and dense monitoring capabilities. It offers several advantages including resistance to extreme conditions, immunity to electromagnetic interference, and accurate detection. However, DAS typically exhibits a lower signal-to-noise ratio (S/N) compared to geophones and is susceptible to various noise types, such as random noise, erratic noise, level noise, and long-period noise. This reduced S/N can negatively impact data analyses containing inversion and interpretation. While artificial intelligence has demonstrated excellent denoising capabilities, most existing methods rely on supervised learning with labeled data, which imposes stringent requirements on the quality of the labels. To address this issue, we develop a label-free unsupervised learning (UL) network model based on Context-Pyramid-UNet (CP-UNet) to suppress erratic and random noises in DAS data. The CP-UNet utilizes the Context Pyramid Module in the encoding and decoding process to extract features and reconstruct the DAS data. To enhance the connectivity between shallow and deep features, we add a Connected Module (CM) to both encoding and decoding section. Layer Normalization (LN) is utilized to replace the commonly employed Batch Normalization (BN), accelerating the convergence of the model and preventing gradient explosion during training. Huber-loss is adopted as our loss function whose parameters are experimentally determined. We apply the network to both the 2-D synthetic and filed data. Comparing to traditional denoising methods and the latest UL framework, our proposed method demonstrates superior noise reduction performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_13395 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unsupervised CP-UNet Framework for Denoising DAS Data with Decay Noise Huang, Tianye Li, Aopeng Li, Xiang Zhang, Jing Xian, Sijing Zhang, Qi Lu, Mingkong Chen, Guodong Xiong, Liangming Hu, Xiangyun Sound Machine Learning Audio and Speech Processing Signal Processing Optics Distributed acoustic sensor (DAS) technology leverages optical fiber cables to detect acoustic signals, providing cost-effective and dense monitoring capabilities. It offers several advantages including resistance to extreme conditions, immunity to electromagnetic interference, and accurate detection. However, DAS typically exhibits a lower signal-to-noise ratio (S/N) compared to geophones and is susceptible to various noise types, such as random noise, erratic noise, level noise, and long-period noise. This reduced S/N can negatively impact data analyses containing inversion and interpretation. While artificial intelligence has demonstrated excellent denoising capabilities, most existing methods rely on supervised learning with labeled data, which imposes stringent requirements on the quality of the labels. To address this issue, we develop a label-free unsupervised learning (UL) network model based on Context-Pyramid-UNet (CP-UNet) to suppress erratic and random noises in DAS data. The CP-UNet utilizes the Context Pyramid Module in the encoding and decoding process to extract features and reconstruct the DAS data. To enhance the connectivity between shallow and deep features, we add a Connected Module (CM) to both encoding and decoding section. Layer Normalization (LN) is utilized to replace the commonly employed Batch Normalization (BN), accelerating the convergence of the model and preventing gradient explosion during training. Huber-loss is adopted as our loss function whose parameters are experimentally determined. We apply the network to both the 2-D synthetic and filed data. Comparing to traditional denoising methods and the latest UL framework, our proposed method demonstrates superior noise reduction performance. |
| title | Unsupervised CP-UNet Framework for Denoising DAS Data with Decay Noise |
| topic | Sound Machine Learning Audio and Speech Processing Signal Processing Optics |
| url | https://arxiv.org/abs/2502.13395 |