A Physics-Guided Deep Learning Method for Temporal InSAR Surface Deformation Monitoring and Prediction: A Case Study of Lishi District, Shanxi Province, China.
Saved in:
| Title: | A Physics-Guided Deep Learning Method for Temporal InSAR Surface Deformation Monitoring and Prediction: A Case Study of Lishi District, Shanxi Province, China. |
|---|---|
| Authors: | Zhang, Bing1 (AUTHOR) zhangbing@lntu.edu.cn, Du, Yongjie1,2 (AUTHOR), Song, Weidong1 (AUTHOR), Zhang, Jichao1,2 (AUTHOR), Sun, Hongchang2 (AUTHOR), Ren, Dongfeng1 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1553. 22p. |
| Subjects: | Deep learning, Radar interferometry, Land subsidence, Time, Hazard signs, Deformations (Mechanics) |
| Geographic Terms: | China, Shanxi Sheng (China) |
| Abstract: | Highlights: What are the main findings? The CMTF-P2P method proposed in this study can better preserve the evolution characteristics and spatial distribution patterns of land surface deformation time series. In independent validation, it achieved better results, with RMSE = 0.43 mm and R2 = 0.92. Its overall performance is superior to comparative models such as iTransformer, LSTM, DLinear, PatchTST, TimesNet and N-BEATS. Ablation experiments show that multiple factors such as rainfall, soil, and mining subsidence areas have significant complementary effects. Meanwhile, causal STL decomposition, event stage characteristics, multi-branch network structure, and incremental cumulative consistency constraints jointly improve prediction accuracy and stability, with the 7 × 7 neighborhood scale showing the best prediction performance. What are the implications of the main findings? Combining causal decomposition, physical constraints, multi-source driving information, and deep learning can effectively improve the reliability and stability of InSAR deformation prediction. This method can provide technical support for surface subsidence monitoring, hazard identification, and risk early warning. Surface deformation is characterized by long-term accumulation and significant spatial differences, commonly inducing ground fissures and structural damage to roads and buildings, and in severe cases, causing collapses and other accidents that directly threaten human life. Reliable deformation monitoring and prediction are of great significance for early warning and infrastructure safety. Synthetic aperture radar interferometry (InSAR) technology can be used to acquire high-spatiotemporal-resolution temporal observations of surface deformation over a large area, but research on surface deformation prediction using InSAR temporal images is still relatively limited. Therefore, in this study, we used Sentinel-1 temporal imagery as the data foundation. Firstly, small baseline subset (SBAS)-InSAR inversion was used to obtain the line-of-sight-oriented cumulative deformation sequence and subsidence rate results. Based on this, the causal multi-trend fusion patch-to-point (CMTF-P2P) surface deformation prediction framework was developed. This framework effectively separates the long-term trends and short-term fluctuations in the deformation sequence through causal decomposition; introduces external drivers such as rainfall and event phase characteristics to enhance the temporal expression; and utilizes patch-to-point fusion of neighborhood spatial information to improve the spatial continuity and the ability to characterize local differences. Experimental results show that the method has an RMSE of 0.43 mm and an R2 of 0.92, outperforming time-series deformation prediction models such as LSTM and iTransformer. Compared with traditional models that learn overall change patterns from historical time series, this paper alleviates the confusion between trends and volatility using causal STL decomposition, making the model's expression of long-term trends and seasonal and short-term fluctuations in volatility clearer; event phase encoding enhances the model's ability to characterize sudden disturbances and phased responses to events; the patch-to-point structure incorporates spatiotemporal information within the neighborhood, enhancing the model's ability to apply spatiotemporal information; multi-branch collaborative modeling enhances the model's ability to characterize multi-scale temporal features; and incremental cumulative consistency constraints enhance the physical consistency of the prediction results. [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.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 194141078 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Physics-Guided Deep Learning Method for Temporal InSAR Surface Deformation Monitoring and Prediction: A Case Study of Lishi District, Shanxi Province, China. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Bing%22">Zhang, Bing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> zhangbing@lntu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Du%2C+Yongjie%22">Du, Yongjie</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Song%2C+Weidong%22">Song, Weidong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Jichao%22">Zhang, Jichao</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sun%2C+Hongchang%22">Sun, Hongchang</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ren%2C+Dongfeng%22">Ren, Dongfeng</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. May2026, Vol. 18 Issue 10, p1553. 22p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Radar+interferometry%22">Radar interferometry</searchLink><br /><searchLink fieldCode="DE" term="%22Land+subsidence%22">Land subsidence</searchLink><br /><searchLink fieldCode="DE" term="%22Time%22">Time</searchLink><br /><searchLink fieldCode="DE" term="%22Hazard+signs%22">Hazard signs</searchLink><br /><searchLink fieldCode="DE" term="%22Deformations+%28Mechanics%29%22">Deformations (Mechanics)</searchLink> – Name: SubjectGeographic Label: Geographic Terms Group: Su Data: <searchLink fieldCode="DE" term="%22China%22">China</searchLink><br /><searchLink fieldCode="DE" term="%22Shanxi+Sheng+%28China%29%22">Shanxi Sheng (China)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? The CMTF-P2P method proposed in this study can better preserve the evolution characteristics and spatial distribution patterns of land surface deformation time series. In independent validation, it achieved better results, with RMSE = 0.43 mm and R2 = 0.92. Its overall performance is superior to comparative models such as iTransformer, LSTM, DLinear, PatchTST, TimesNet and N-BEATS. Ablation experiments show that multiple factors such as rainfall, soil, and mining subsidence areas have significant complementary effects. Meanwhile, causal STL decomposition, event stage characteristics, multi-branch network structure, and incremental cumulative consistency constraints jointly improve prediction accuracy and stability, with the 7 × 7 neighborhood scale showing the best prediction performance. What are the implications of the main findings? Combining causal decomposition, physical constraints, multi-source driving information, and deep learning can effectively improve the reliability and stability of InSAR deformation prediction. This method can provide technical support for surface subsidence monitoring, hazard identification, and risk early warning. Surface deformation is characterized by long-term accumulation and significant spatial differences, commonly inducing ground fissures and structural damage to roads and buildings, and in severe cases, causing collapses and other accidents that directly threaten human life. Reliable deformation monitoring and prediction are of great significance for early warning and infrastructure safety. Synthetic aperture radar interferometry (InSAR) technology can be used to acquire high-spatiotemporal-resolution temporal observations of surface deformation over a large area, but research on surface deformation prediction using InSAR temporal images is still relatively limited. Therefore, in this study, we used Sentinel-1 temporal imagery as the data foundation. Firstly, small baseline subset (SBAS)-InSAR inversion was used to obtain the line-of-sight-oriented cumulative deformation sequence and subsidence rate results. Based on this, the causal multi-trend fusion patch-to-point (CMTF-P2P) surface deformation prediction framework was developed. This framework effectively separates the long-term trends and short-term fluctuations in the deformation sequence through causal decomposition; introduces external drivers such as rainfall and event phase characteristics to enhance the temporal expression; and utilizes patch-to-point fusion of neighborhood spatial information to improve the spatial continuity and the ability to characterize local differences. Experimental results show that the method has an RMSE of 0.43 mm and an R2 of 0.92, outperforming time-series deformation prediction models such as LSTM and iTransformer. Compared with traditional models that learn overall change patterns from historical time series, this paper alleviates the confusion between trends and volatility using causal STL decomposition, making the model's expression of long-term trends and seasonal and short-term fluctuations in volatility clearer; event phase encoding enhances the model's ability to characterize sudden disturbances and phased responses to events; the patch-to-point structure incorporates spatiotemporal information within the neighborhood, enhancing the model's ability to apply spatiotemporal information; multi-branch collaborative modeling enhances the model's ability to characterize multi-scale temporal features; and incremental cumulative consistency constraints enhance the physical consistency of the prediction results. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>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.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194141078 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18101553 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 22 StartPage: 1553 Subjects: – SubjectFull: Deep learning Type: general – SubjectFull: Radar interferometry Type: general – SubjectFull: Land subsidence Type: general – SubjectFull: Time Type: general – SubjectFull: Hazard signs Type: general – SubjectFull: Deformations (Mechanics) Type: general – SubjectFull: China Type: general – SubjectFull: Shanxi Sheng (China) Type: general Titles: – TitleFull: A Physics-Guided Deep Learning Method for Temporal InSAR Surface Deformation Monitoring and Prediction: A Case Study of Lishi District, Shanxi Province, China. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Zhang, Bing – PersonEntity: Name: NameFull: Du, Yongjie – PersonEntity: Name: NameFull: Song, Weidong – PersonEntity: Name: NameFull: Zhang, Jichao – PersonEntity: Name: NameFull: Sun, Hongchang – PersonEntity: Name: NameFull: Ren, Dongfeng IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 05 Text: May2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 10 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
