JOTGLNet: A Guided Learning Network with Joint Offset Tracking for Multiscale Deformation Monitoring.
Saved in:
| Title: | JOTGLNet: A Guided Learning Network with Joint Offset Tracking for Multiscale Deformation Monitoring. |
|---|---|
| Authors: | Ni, Jun1 (AUTHOR), Bao, Siyuan1,2 (AUTHOR), Liu, Xichao1,3 (AUTHOR), Du, Sen1,2 (AUTHOR) dusen@ucm.es, Tao, Dapeng1,2 (AUTHOR), Zhan, Yibing3 (AUTHOR) |
| Source: | Remote Sensing. Oct2025, Vol. 17 Issue 19, p3340. 25p. |
| Subjects: | Phase-shifting interferometry, Radar interferometry, Artificial neural networks, Displacement (Mechanics) |
| Abstract: | Highlights: What are the main findings? JOTGLNet integrates pixel offset tracking (OT) with interferometric phase for the first time, enabling comprehensive and accurate ground subsidence monitoring. A dual-path-guided learning network uses interferograms as the primary input and OT features as auxiliary information, enhancing robustness across various deformation scenarios. What is the implication of the main finding? The integration of OT and interferometric phase provides a novel approach for precise subsidence monitoring, improving hazard prevention in mining areas. The dual-path network's robustness to diverse deformation cases offers a reliable tool for real-world SAR-based monitoring under challenging conditions. Ground deformation monitoring in mining areas is essential for hazard prevention and environmental protection. Although interferometric synthetic aperture radar (InSAR) provides detailed phase information for accurate deformation measurement, its performance is often compromised in regions experiencing rapid subsidence and strong noise, where phase aliasing and coherence loss lead to significant inaccuracies. To overcome these limitations, this paper proposes JOTGLNet, a guided learning network with joint offset tracking, for multiscale deformation monitoring. This method integrates pixel offset tracking (OT), which robustly captures large-gradient displacements, with interferometric phase data that offers high sensitivity in coherent regions. A dual-path deep learning architecture was designed where the interferometric phase serves as the primary branch and OT features act as complementary information, enhancing the network's ability to handle varying deformation rates and coherence conditions. Additionally, a novel shape perception loss combining morphological similarity measurement and error learning was introduced to improve geometric fidelity and reduce unbalanced errors across deformation regions. The model was trained on 4000 simulated samples reflecting diverse real-world scenarios and validated on 1100 test samples with a maximum deformation up to 12.6 m, achieving an average prediction error of less than 0.15 m—outperforming state-of-the-art methods whose errors exceeded 0.19 m. Additionally, experiments on five real monitoring datasets further confirmed the superiority and consistency of the proposed approach. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? JOTGLNet integrates pixel offset tracking (OT) with interferometric phase for the first time, enabling comprehensive and accurate ground subsidence monitoring. A dual-path-guided learning network uses interferograms as the primary input and OT features as auxiliary information, enhancing robustness across various deformation scenarios. What is the implication of the main finding? The integration of OT and interferometric phase provides a novel approach for precise subsidence monitoring, improving hazard prevention in mining areas. The dual-path network's robustness to diverse deformation cases offers a reliable tool for real-world SAR-based monitoring under challenging conditions. Ground deformation monitoring in mining areas is essential for hazard prevention and environmental protection. Although interferometric synthetic aperture radar (InSAR) provides detailed phase information for accurate deformation measurement, its performance is often compromised in regions experiencing rapid subsidence and strong noise, where phase aliasing and coherence loss lead to significant inaccuracies. To overcome these limitations, this paper proposes JOTGLNet, a guided learning network with joint offset tracking, for multiscale deformation monitoring. This method integrates pixel offset tracking (OT), which robustly captures large-gradient displacements, with interferometric phase data that offers high sensitivity in coherent regions. A dual-path deep learning architecture was designed where the interferometric phase serves as the primary branch and OT features act as complementary information, enhancing the network's ability to handle varying deformation rates and coherence conditions. Additionally, a novel shape perception loss combining morphological similarity measurement and error learning was introduced to improve geometric fidelity and reduce unbalanced errors across deformation regions. The model was trained on 4000 simulated samples reflecting diverse real-world scenarios and validated on 1100 test samples with a maximum deformation up to 12.6 m, achieving an average prediction error of less than 0.15 m—outperforming state-of-the-art methods whose errors exceeded 0.19 m. Additionally, experiments on five real monitoring datasets further confirmed the superiority and consistency of the proposed approach. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs17193340 |
