Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes
ObjectiveDeep excavated expansive soil canal slopes frequently exhibit significant deformation and poor stability due to the combined effects of excavation unloading, wet-dry cycles, and groundwater level fluctuations. Influenced by multiple environmental factors, the deformation mechanisms of these...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Editorial Department of Journal of Sichuan University (Engineering Science Edition)
2025-01-01
|
| Series: | 工程科学与技术 |
| Subjects: | |
| Online Access: | http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202500163 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849325065976414208 |
|---|---|
| author | ZHANG Yuhan HU Jiang LI Xing |
| author_facet | ZHANG Yuhan HU Jiang LI Xing |
| author_sort | ZHANG Yuhan |
| collection | DOAJ |
| description | ObjectiveDeep excavated expansive soil canal slopes frequently exhibit significant deformation and poor stability due to the combined effects of excavation unloading, wet-dry cycles, and groundwater level fluctuations. Influenced by multiple environmental factors, the deformation mechanisms of these slopes are complex and demonstrate spatiotemporal heterogeneity. Deformation serves as a direct indicator of slope stability, making the analysis of deformation patterns and trends essential for assessing stability. In current engineering practice, deformation data are primarily obtained through discrete point-based monitoring, which captures information only at critical cross-sections or localized areas of the slope. This approach leaves unmonitored zones with limited coverage and creates blind spots in deformation assessment. Moreover, dense deployment of monitoring points not only increases construction challenges but also significantly raises project costs. Thus, a key challenge in long-distance canal slope safety monitoring lies in improving deformation monitoring coverage and cost-effectiveness while maintaining precision. InSAR technology offers high spatiotemporal resolution, broad coverage, non-contact monitoring capability, and adaptability to complex terrain, addressing many limitations of conventional point-based methods. This study integrates Small Baseline Subset InSAR (SBAS-InSAR) with traditional deformation monitoring techniques to acquire multi-scale deformation data, enabling analysis from broad areas to localized sections. Furthermore, a self-explaining neural network (SENN) model incorporating an attention mechanism is developed to predict canal slope deformation. The model investigates the deformation characteristics, dominant controlling factors, and evolutionary mechanisms of deep excavated expansive soil slopes, facilitating multi-source data-driven analysis of deformation and its influencing factors. This approach provides scientific support for safety monitoring and stability evaluation of canal slopesMethodsFirst, SBAS-InSAR was employed to process Sentinel-1A satellite imagery, extracting time-series deformation data. The derived displacements were projected onto the vertical direction and cross-validated against ground-based vertical displacement measurements to assess the reliability of the SBAS-InSAR results. Based on this validation, deformation rate thresholds were established to identify high-risk canal segments, enabling an analysis of the overall slope deformation trends. Subsequently, a SENN model incorporating an attention mechanism was developed to predict slope deformation. Key influencing factors—including groundwater level, canal water level, air temperature, precipitation, and time-dependent effects—were selected as input variables. The SENN model autonomously extracts critical features and dynamically assigns weights to each factor, thereby predicting cumulative displacements along both the satellite Line-of-Sight (LOS) direction and the inclinometer A-direction. This approach facilitates a comprehensive analysis of deformation patterns at the slope surface and various subsurface depths, while elucidating the dominant controlling factors governing expansive soil canal slope behavior.Results and Discussions The study focused on a deep excavated expansive soil canal section (Stake 8+886~12+921) of a major water diversion project, yielding the following key findings: 1) The analysis of 128 Sentinel-1A images from March 2017 to December 2021 revealed that the deformation data obtained through SBAS-InSAR method showed less than 3mm discrepancy with surface vertical displacement measurements at monitoring points (fourth-stage berm at 9+363 and third-stage berm at 11+400), with consistent deformation trends, confirming the reliability of SBAS-InSAR for canal slope deformation monitoring. 2) The study section exhibited LOS deformation rates ranging from -10 to 24 mm/a, demonstrating overall uplift characteristics, with positive LOS deformation showing annual increase. Using a 10 mm/a threshold, critical deformation zones were identified, particularly in the 11+806~12+921 section where most areas experienced deformations exceeding 40 mm, reaching a maximum of 97 mm. 3) Inclinometer measurements indicated maximum displacements of 49.51 mm at 4.5m depth below the orifice at the second-stage berm (11+715), 63.80mm at 1m below the first-stage berm (11+762), and 67.51 mm at 1.5 m depth of the third-stage berm (11+762), with deformation extending to 13.5 m below the orifice. 4) LOS direction deformation was primarily influenced by groundwater level, canal water level and time-dependent effects, with groundwater level exerting greater influence on right-bank deformation while canal water level more significantly affected left-bank deformation. At the third-stage berm (11+762), A-direction deformation was predominantly time-dependent, followed by temperature effects, with minimal influence from canal water level and rainfall. Groundwater level significantly affected surface soils but had reduced impact on deeper layers. Shallow deformations in expansive soil slopes were mainly controlled by groundwater level, temperature and time effects, while displacements below 3.5 m depth showed stronger correlation with temperature and time effects. 5) The 11+700~11+800 section exhibited ongoing surface and internal deformation, with right-bank slopes showing significantly greater deformation due to higher groundwater levels compared to left-bank slopes. Deformation magnitudes were greater in first to fourth stage slopes than in fifth and sixth stage slopes. Deformation mechanisms varied with depth: deeper soils, constrained by overburden pressure, were less affected by groundwater fluctuations, while shallow soils showed significant sensitivity to both groundwater level variations and temperature changes. The study demonstrates that uplift deformation in this canal section results from combined effects of excavation unloading and hydro-mechanical coupling in expansive soils.ConclusionsThe SBAS-InSAR technique effectively monitors large-scale canal slope deformation trends, overcoming the spatial limitations inherent in conventional point-based monitoring methods that suffer from restricted coverage and sparse measurement points. The attention-mechanism-based SENN prediction model demonstrates high accuracy in forecasting slope deformation patterns while quantitatively assessing the relative contributions of various influencing factors. This multi-source data integration approach provides comprehensive insights into the deformation mechanisms of expansive soil canal slopes and their controlling factors, thereby offering a scientific basis for slope safety monitoring. The research outcomes not only serve as valuable references for long-term monitoring and engineering management of expansive soil canal slopes but also propose innovative methodologies for safety monitoring of similar engineering projects. The demonstrated technical framework exhibits significant practical value for engineering applications, particularly in addressing deformation monitoring challenges in large-scale water conveyance infrastructure. |
| format | Article |
| id | doaj-art-c683e39d59c6473c8b1b7d2cc8e21a9d |
| institution | Kabale University |
| issn | 2096-3246 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Editorial Department of Journal of Sichuan University (Engineering Science Edition) |
| record_format | Article |
| series | 工程科学与技术 |
| spelling | doaj-art-c683e39d59c6473c8b1b7d2cc8e21a9d2025-08-20T03:48:31ZengEditorial Department of Journal of Sichuan University (Engineering Science Edition)工程科学与技术2096-32462025-01-0111398096380Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal SlopesZHANG YuhanHU JiangLI XingObjectiveDeep excavated expansive soil canal slopes frequently exhibit significant deformation and poor stability due to the combined effects of excavation unloading, wet-dry cycles, and groundwater level fluctuations. Influenced by multiple environmental factors, the deformation mechanisms of these slopes are complex and demonstrate spatiotemporal heterogeneity. Deformation serves as a direct indicator of slope stability, making the analysis of deformation patterns and trends essential for assessing stability. In current engineering practice, deformation data are primarily obtained through discrete point-based monitoring, which captures information only at critical cross-sections or localized areas of the slope. This approach leaves unmonitored zones with limited coverage and creates blind spots in deformation assessment. Moreover, dense deployment of monitoring points not only increases construction challenges but also significantly raises project costs. Thus, a key challenge in long-distance canal slope safety monitoring lies in improving deformation monitoring coverage and cost-effectiveness while maintaining precision. InSAR technology offers high spatiotemporal resolution, broad coverage, non-contact monitoring capability, and adaptability to complex terrain, addressing many limitations of conventional point-based methods. This study integrates Small Baseline Subset InSAR (SBAS-InSAR) with traditional deformation monitoring techniques to acquire multi-scale deformation data, enabling analysis from broad areas to localized sections. Furthermore, a self-explaining neural network (SENN) model incorporating an attention mechanism is developed to predict canal slope deformation. The model investigates the deformation characteristics, dominant controlling factors, and evolutionary mechanisms of deep excavated expansive soil slopes, facilitating multi-source data-driven analysis of deformation and its influencing factors. This approach provides scientific support for safety monitoring and stability evaluation of canal slopesMethodsFirst, SBAS-InSAR was employed to process Sentinel-1A satellite imagery, extracting time-series deformation data. The derived displacements were projected onto the vertical direction and cross-validated against ground-based vertical displacement measurements to assess the reliability of the SBAS-InSAR results. Based on this validation, deformation rate thresholds were established to identify high-risk canal segments, enabling an analysis of the overall slope deformation trends. Subsequently, a SENN model incorporating an attention mechanism was developed to predict slope deformation. Key influencing factors—including groundwater level, canal water level, air temperature, precipitation, and time-dependent effects—were selected as input variables. The SENN model autonomously extracts critical features and dynamically assigns weights to each factor, thereby predicting cumulative displacements along both the satellite Line-of-Sight (LOS) direction and the inclinometer A-direction. This approach facilitates a comprehensive analysis of deformation patterns at the slope surface and various subsurface depths, while elucidating the dominant controlling factors governing expansive soil canal slope behavior.Results and Discussions The study focused on a deep excavated expansive soil canal section (Stake 8+886~12+921) of a major water diversion project, yielding the following key findings: 1) The analysis of 128 Sentinel-1A images from March 2017 to December 2021 revealed that the deformation data obtained through SBAS-InSAR method showed less than 3mm discrepancy with surface vertical displacement measurements at monitoring points (fourth-stage berm at 9+363 and third-stage berm at 11+400), with consistent deformation trends, confirming the reliability of SBAS-InSAR for canal slope deformation monitoring. 2) The study section exhibited LOS deformation rates ranging from -10 to 24 mm/a, demonstrating overall uplift characteristics, with positive LOS deformation showing annual increase. Using a 10 mm/a threshold, critical deformation zones were identified, particularly in the 11+806~12+921 section where most areas experienced deformations exceeding 40 mm, reaching a maximum of 97 mm. 3) Inclinometer measurements indicated maximum displacements of 49.51 mm at 4.5m depth below the orifice at the second-stage berm (11+715), 63.80mm at 1m below the first-stage berm (11+762), and 67.51 mm at 1.5 m depth of the third-stage berm (11+762), with deformation extending to 13.5 m below the orifice. 4) LOS direction deformation was primarily influenced by groundwater level, canal water level and time-dependent effects, with groundwater level exerting greater influence on right-bank deformation while canal water level more significantly affected left-bank deformation. At the third-stage berm (11+762), A-direction deformation was predominantly time-dependent, followed by temperature effects, with minimal influence from canal water level and rainfall. Groundwater level significantly affected surface soils but had reduced impact on deeper layers. Shallow deformations in expansive soil slopes were mainly controlled by groundwater level, temperature and time effects, while displacements below 3.5 m depth showed stronger correlation with temperature and time effects. 5) The 11+700~11+800 section exhibited ongoing surface and internal deformation, with right-bank slopes showing significantly greater deformation due to higher groundwater levels compared to left-bank slopes. Deformation magnitudes were greater in first to fourth stage slopes than in fifth and sixth stage slopes. Deformation mechanisms varied with depth: deeper soils, constrained by overburden pressure, were less affected by groundwater fluctuations, while shallow soils showed significant sensitivity to both groundwater level variations and temperature changes. The study demonstrates that uplift deformation in this canal section results from combined effects of excavation unloading and hydro-mechanical coupling in expansive soils.ConclusionsThe SBAS-InSAR technique effectively monitors large-scale canal slope deformation trends, overcoming the spatial limitations inherent in conventional point-based monitoring methods that suffer from restricted coverage and sparse measurement points. The attention-mechanism-based SENN prediction model demonstrates high accuracy in forecasting slope deformation patterns while quantitatively assessing the relative contributions of various influencing factors. This multi-source data integration approach provides comprehensive insights into the deformation mechanisms of expansive soil canal slopes and their controlling factors, thereby offering a scientific basis for slope safety monitoring. The research outcomes not only serve as valuable references for long-term monitoring and engineering management of expansive soil canal slopes but also propose innovative methodologies for safety monitoring of similar engineering projects. The demonstrated technical framework exhibits significant practical value for engineering applications, particularly in addressing deformation monitoring challenges in large-scale water conveyance infrastructure.http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202500163expansive soilcanal slopeInSARdeformationSENNattention mechanism |
| spellingShingle | ZHANG Yuhan HU Jiang LI Xing Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes 工程科学与技术 expansive soil canal slope InSAR deformation SENN attention mechanism |
| title | Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes |
| title_full | Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes |
| title_fullStr | Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes |
| title_full_unstemmed | Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes |
| title_short | Multi-source Data-driven Analysis of Deformation and Influencing Factors for Expansive Soil Canal Slopes |
| title_sort | multi source data driven analysis of deformation and influencing factors for expansive soil canal slopes |
| topic | expansive soil canal slope InSAR deformation SENN attention mechanism |
| url | http://jsuese.scu.edu.cn/thesisDetails#10.12454/j.jsuese.202500163 |
| work_keys_str_mv | AT zhangyuhan multisourcedatadrivenanalysisofdeformationandinfluencingfactorsforexpansivesoilcanalslopes AT hujiang multisourcedatadrivenanalysisofdeformationandinfluencingfactorsforexpansivesoilcanalslopes AT lixing multisourcedatadrivenanalysisofdeformationandinfluencingfactorsforexpansivesoilcanalslopes |