A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net
Gravity and gravity gradient data serve as fundamental inputs for geophysical resource exploration and geological structure analysis. However, traditional denoising methods—including wavelet transforms, moving averages, and low-pass filtering—exhibit signal loss and limited adaptability under comple...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7956 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850076990046994432 |
|---|---|
| author | Bing Liu Houpu Li Shaofeng Bian Chaoliang Zhang Bing Ji Yujie Zhang |
| author_facet | Bing Liu Houpu Li Shaofeng Bian Chaoliang Zhang Bing Ji Yujie Zhang |
| author_sort | Bing Liu |
| collection | DOAJ |
| description | Gravity and gravity gradient data serve as fundamental inputs for geophysical resource exploration and geological structure analysis. However, traditional denoising methods—including wavelet transforms, moving averages, and low-pass filtering—exhibit signal loss and limited adaptability under complex, non-stationary noise conditions. To address these challenges, this study proposes an improved U-Net deep learning framework that integrates multi-scale feature extraction and attention mechanisms. Furthermore, a Laplace consistency constraint is introduced into the loss function to enhance denoising performance and physical interpretability. Notably, the datasets used in this study are generated by the authors, involving simulations of subsurface prism distributions with realistic density perturbations (±20% of typical rock densities) and the addition of controlled Gaussian noise (5%, 10%, 15%, and 30%) to simulate field-like conditions, ensuring the diversity and physical relevance of training samples. Experimental validation on these synthetic datasets and real field datasets demonstrates the superiority of the proposed method over conventional techniques. For noise levels of 5%, 10%, 15%, and 30% in test sets, the improved U-Net achieves Peak Signal-to-Noise Ratios (PSNR) of 59.13 dB, 52.03 dB, 48.62 dB, and 48.81 dB, respectively, outperforming wavelet transforms, moving averages, and low-pass filtering by 10–30 dB. In multi-component gravity gradient denoising, our method excels in detail preservation and noise suppression, improving Structural Similarity Index (SSIM) by 15–25%. Field data tests further confirm enhanced identification of key geological anomalies and overall data quality improvement. In summary, the improved U-Net not only delivers quantitative advancements in gravity data denoising but also provides a novel approach for high-precision geophysical data preprocessing. |
| format | Article |
| id | doaj-art-66ed2c9d5e6142939853ee2a594dcf9c |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-66ed2c9d5e6142939853ee2a594dcf9c2025-08-20T02:45:53ZengMDPI AGApplied Sciences2076-34172025-07-011514795610.3390/app15147956A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-NetBing Liu0Houpu Li1Shaofeng Bian2Chaoliang Zhang3Bing Ji4Yujie Zhang5School of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Electrical Engineering, Naval University of Engineering, Wuhan 430033, ChinaSchool of Mathematics and Physics, China University of Geosciences, Wuhan 430074, ChinaGravity and gravity gradient data serve as fundamental inputs for geophysical resource exploration and geological structure analysis. However, traditional denoising methods—including wavelet transforms, moving averages, and low-pass filtering—exhibit signal loss and limited adaptability under complex, non-stationary noise conditions. To address these challenges, this study proposes an improved U-Net deep learning framework that integrates multi-scale feature extraction and attention mechanisms. Furthermore, a Laplace consistency constraint is introduced into the loss function to enhance denoising performance and physical interpretability. Notably, the datasets used in this study are generated by the authors, involving simulations of subsurface prism distributions with realistic density perturbations (±20% of typical rock densities) and the addition of controlled Gaussian noise (5%, 10%, 15%, and 30%) to simulate field-like conditions, ensuring the diversity and physical relevance of training samples. Experimental validation on these synthetic datasets and real field datasets demonstrates the superiority of the proposed method over conventional techniques. For noise levels of 5%, 10%, 15%, and 30% in test sets, the improved U-Net achieves Peak Signal-to-Noise Ratios (PSNR) of 59.13 dB, 52.03 dB, 48.62 dB, and 48.81 dB, respectively, outperforming wavelet transforms, moving averages, and low-pass filtering by 10–30 dB. In multi-component gravity gradient denoising, our method excels in detail preservation and noise suppression, improving Structural Similarity Index (SSIM) by 15–25%. Field data tests further confirm enhanced identification of key geological anomalies and overall data quality improvement. In summary, the improved U-Net not only delivers quantitative advancements in gravity data denoising but also provides a novel approach for high-precision geophysical data preprocessing.https://www.mdpi.com/2076-3417/15/14/7956U-Netgravitygravity gradientdata noise reduction |
| spellingShingle | Bing Liu Houpu Li Shaofeng Bian Chaoliang Zhang Bing Ji Yujie Zhang A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net Applied Sciences U-Net gravity gravity gradient data noise reduction |
| title | A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net |
| title_full | A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net |
| title_fullStr | A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net |
| title_full_unstemmed | A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net |
| title_short | A Gravity Data Denoising Method Based on Multi-Scale Attention Mechanism and Physical Constraints Using U-Net |
| title_sort | gravity data denoising method based on multi scale attention mechanism and physical constraints using u net |
| topic | U-Net gravity gravity gradient data noise reduction |
| url | https://www.mdpi.com/2076-3417/15/14/7956 |
| work_keys_str_mv | AT bingliu agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT houpuli agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT shaofengbian agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT chaoliangzhang agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT bingji agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT yujiezhang agravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT bingliu gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT houpuli gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT shaofengbian gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT chaoliangzhang gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT bingji gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet AT yujiezhang gravitydatadenoisingmethodbasedonmultiscaleattentionmechanismandphysicalconstraintsusingunet |