Prediction Of Ground Deformation Research Articles

Time Series Prediction of Reservoir Bank Slope Deformation Based on Informer and InSAR: A Case Study of Dawanzi Landslide in the Baihetan Reservoir Area, China

Reservoir impoundment significantly impacts the hydrogeological conditions of reservoir bank slopes, and bank slope deformation or destruction occurs frequently under cyclic impoundment conditions. Ground deformation prediction is crucial to the early warning system for slow-moving landslides. Deep learning methods have developed rapidly in recent years, but only a few studies are on combining deep learning and landslide warning. This paper proposes a slow-moving landslide displacement prediction method based on the Informer deep learning model. Firstly, the Sentinel-1 (S1) data are processed to obtain the cumulative displacement time-series image of the bank slope by the Small-BAseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) method. Then, combining data on rainfall, humidity, and horizontal and vertical distances of pixel points from the water table line, this study created a dataset with landslide displacement as the target feature. After that, this paper improves the Informer model to make it applicable to our dataset. This study chose the Dawanzi landslide in the Baihetan reservoir area, China, for validation. After training with 50-time series deformation data points, the model can predict the displacement results of 12-time series deformation data points using 12-time series multi-feature data, and compared with the monitoring values, its Mean Square Error (MSE) was 11.614. The results show that the multivariate dataset is better than the deformation univariate data in predicting the displacement in the large deformation zone of bank slopes, and our model has better complexity and prediction performance than other deep learning models. The prediction results show that among zones I–IV, where the Dawanzi Tunnel is located, significant deformation with the maximum deformation rate detected exceeding –100mm/year occurs in Zones I and III. In these two zones, the initiation of deformation relates to the drop in water level after water storage, with the deformation rate of Zone III exhibiting a stronger correlation with the change in water level. It is expected that deformation in Zone III will either remain slow or stop, while deformation in Zone I will continue at the same or a decreased rate. Our proposed method for slow-moving landslide displacement forecasting offers fast, intuitive, and economically feasible advantages. It can provide a feasible research idea for future deep learning and landslide warning research.

Analysis and prediction of ground deformation in Yinxi Industrial Park based on time-series InSAR technology.

Monitoring ground deformation in industrial parks is of great importance for the economic development of urban areas. However, limited research has been conducted on the deformation mechanism in industrial parks, and there is a lack of integrated monitoring and prediction models. Therefore, this study proposes a comprehensive monitoring and prediction model for industrial parks, utilizing time-series Interferometry Synthetic Aperture Radar (InSAR) technology and the Whale Optimization Algorithm-Back Propagation (WOA-BP) neural network algorithm. Taking Yinxi Industrial Park in Baiyin District as a case study, we used 68 scenes of Sentinel-1A ascending and descending orbit data from June 2018 to April 2021. The Stanford Method for Persistent Scatterers-Permanent Scatterers (StaMPS-PS) and the Small Baseline Subsets-Interferometry Synthetic Aperture Radar (SBAS-InSAR) technologies were employed to obtain the surface deformation information of the park. The deformation information obtained by the two technologies was cross-validated in terms of temporal and spatial distribution, and the vertical and east-west deformation of the park was obtained by combining the ascending and descending orbit data. The results show that the deformation feature points in the line of sight (LOS) direction obtained by the two technologies have a high consistency in spatial distribution, using the ascending orbit data as an example. Additionally, the SBAS-InSAR technology was used to obtain the east-west and vertical deformation results of the park after merging the ascending and descending orbit data for the same period. It was found that the park is mainly affected by vertical deformation, with a maximum subsidence rate of 14.67mm/yr. The subsidence areas correspond to the deformation positions observed in field survey photos. Based on the ascending orbit deformation data, the two technologies were validated with 585 points of the same latitude and longitude, and the coefficient of determination R2 was found to be 0.82, with a root mean square error (RMSE) of 2.20mm/a. The deformation rates were also highly consistent. Due to the 47% increase in the number of sampling points provided by the StaMPS-PS technique compared to the SBAS-InSAR technique, the former was found to be more applicable in the industrial park. Based on the ground deformation mechanism in the park, we combined the StaMPS-PS technique with the WOA-BP neural network to construct a deformation zone prediction model. We conducted predictive studies on the deformation zones of buildings and roads within the park, and the results showed that the WOA-optimized BP neural network achieved higher accuracy and lower overall error compared to the unoptimized network. Finally, we analyzed and discussed the geological conditions and inducing factors of ground deformation in the park, providing a reference for a better understanding of the deformation mechanism and early warning of disasters in the industrial park.

Bayesian ensemble methods for predicting ground deformation due to tunnelling with sparse monitoring data

Numerous analytical models have been developed to predict ground deformations induced by tunneling, which is a critical issue in tunnel engineering. However, the accuracy of these predictions is often limited by errors and uncertainties resulting from model selection and parameter fittings, given the paucity of monitoring data in field settings. This paper proposes a novel approach to estimate tunnelling-induced ground deformations by applying Bayesian model averaging to several representative prediction models. By accounting for both model and parameter uncertainties, this approach enables more realistic predictions of ground deformations than individual models. Specifically, our results indicate that the Gonzalez-Sagaseta model outperforms other models in predicting ground surface settlements, while the Loganathan-Poulos model is most suitable for predicting subsurface vertical and horizontal deformations. Importantly, our analysis reveals that when monitoring data are sparse, model uncertainties may contribute up to 78.7% of the total uncertainties. Thus, obtaining sufficient data for parameter fitting is crucial for accurate predictions. The proposed method in this study offers a more realistic and efficient prediction of tunnelling-induced ground deformations.

Ground deformation prediction induced by shield tunnelling considering existing multi-story buildings

Ground deformation prediction induced by shield tunnelling considering existing multi-story buildings

Modelling the Structure and Anisotropy of London Clay Using the SA_BRICK Model

Several constitutive models had been developed by other researchers to cover the main features of mechanical behaviour of natural overconsolidated clays, such as the nonlinear stress–strain response at small and large strains, and the recent stress history effect. Kinematic hardening models include these features to facilitate realistic predictions of soil–structure interaction. This paper presents the further development of a kinematic hardening model BRICK that includes anisotropy and the influence of soil structure on the mechanical behaviour of a natural clay. High quality laboratory tests were used to calibrate the input parameters of the model in a single element configuration, and a documented boundary value problem of tunnel excavation was used to validate the model in finite element calculations. A comprehensive comparative study between the predictions of different kinematic hardening models, using two different software packages, was carried out. It was observed that the SA_BRICK model is in fair agreement with the observed data and gives improved predictions in comparison to other kinematic hardening models, particularly in terms of narrowness of the settlement trough above the tunnel. Advanced predictions of ground deformations caused by tunnel excavations can be effectively used to mitigate possible damage of existing structures affected by tunnelling in an urban environment.

Analytical Solution on Ground Deformation Caused by Parallel Construction of Rectangular Pipe Jacking

Pipe jacking has been widely used in urban underground engineering construction in recent years. Prediction of ground deformation caused by pipe jacking is particularly important for the safety of construction. With regard to the densely arranged pipes used in the pipe roof structure method, an analytical model of stratum disturbance caused by jacking of parallel rectangular pipes is proposed on the basis of Mindlin’s displacement solution and the stochastic medium theory. The influencing factors such as soil loss, additional thrust on the excavation face, friction between pipe jacking machine and soil, friction between subsequent pipes and soil, and the grouting pressure were comprehensively considered. Then, a 3D numerical simulation and a case study were conducted. The results showed consistent agreement with the analytical solution, and the proposed method can take into account the asymmetry of surface settlement curve induced by construction. A discussion of the ground deformation law shows that the proposed approach can reasonably predict the ground deformation and provide a reference for relevant pipe jacking construction.

Ground Deformation Pattern Analysis and Evolution Prediction of Shanghai Pudong International Airport Based on PSI Long Time Series Observations

Being built on the reclamation area, Shanghai Pudong International Airport (SPIA) has been undergoing uneven subsidence since the beginning of its operation in 1999. In order to explore the evolution characteristics of ground deformation in the SPIA reclamation area and further provide assurance for the airport’s safe operation, 141 Sentinel-1A images from October 2016 to September 2021 were selected to acquire time-series ground deformation observations by the StaMPS PSI processing procedure. We subsequently built a ground deformation prediction model using the Long Short Term Memory (LSTM) neural network for the short-term prediction of the SPIA deformation severity area. On this basis, the spatial-temporal evolution trends of SPIA ground deformation in the reclamation area were revealed concerning the influence and mode of action of geological conditions and environmental factors. Finally, we proposed targeted recommendations and strategies for the comprehensive ground deformation prevention and control needs of SPIA. The results indicated that the SPIA exhibits overall subsidence in the eastern part, with the maximum deformation rate reaching −57.29 mm/a. Meanwhile, the central and western part has a local uplift with the maximum deformation rate reaching 32.76 mm/a. The proposed LSTM ground deformation prediction model demonstrated excellent robustness in the region of uneven deformation, and the prediction results were in high agreement with the StaMPS PSI monitoring results. The time-series observations and prediction results are expected to provide references for the expansion project of SPIA and help the research of ground deformation and prevention in related fields.

Plasticity solutions for ground deformation prediction of shallow tunnels in undrained clay

Elastic-plastic contraction solutions of a cavity within an infinite soil mass are widely used to estimate ground response curves of deep tunnels. The pressure-convergence response of soil around shallow tunnels, however, tends to vary with tunnel embedment ratio. To account for the embedment ratio effect, this paper presents a general solution procedure for undrained contraction analysis of a thick-wall cylinder or spherical shell of isotropically hardening soils, by which a set of analytical and semi-analytical large strain solutions for several Cam-Clay soil models is derived. Results obtained with the new solutions show that the cavity contraction response highly depends on the soil stress history (overconsolidation ratio) and the radial thickness of the surrounding soil. A limit ratio of the outer to the inner radii exists, beyond which the thickness ratio effect becomes negligible. The limit ratio for a spherical shell is smaller than that for a hollow cylinder, and it decreases with the overconsolidation ratio of soil. Based on the analogy between cavity contraction and tunnel convergence, theoretical methods for predicting ground response curves of shallow plane-strain tunnels in clays are proposed and validated by comparing with relevant experimental and numerical simulation results. The solutions can also provide valuable benchmark methods for verifying various numerical programmes.

Surface Deformation Law of Cixian Section of the South-to-North Water Transfer Project

The disturbance of ground deformation caused by pipe jacking construction has become one of the important factors affecting the safety of the surrounding buildings and environmental changes. The construction of the sewage pipe network, which is in the Cixian section of the South-to-North Water Diversion Middle Route, is taking as an example. Theoretical prediction and field tests are conducted to research the ground settlement deformation caused by the disturbance of pipe jacking construction. Research indicates that the surface settlement near Hexie Avenue in Ci County meets the engineering safety requirements when the volume loss rate of the local layer is controlled within 6.9%. And the maximum surface settlement within the construction range of the Ci County section of the South-to-North Water Diversion Project was within 2.5-4 mm, which did not break the safety threshold. Suggested values for the formation loss rate and settlement trough width coefficient index are proposed for similar working conditions, which are 3.31% and 0.525 respectively. Relevant research results provide a reference for the study of ground deformation prediction under similar working conditions.

Progressive failure mechanism in granular materials subjected to an alternant active and passive trapdoor

Underground structures/machines may undergo upward and downward movements due to construction activities or environmental changes. The ground state could be significantly disturbed by previous construction and subsequent structural movements. In this study, alternant active and passive trapdoor tests simulating the ground disturbance were conducted to explore the progressive failure of the overlying soil using a self-developed particle image velocimetry system. The evolution of load, characteristic of soil movement, propagation of shear bands, evolution of failure zones, and volumetric change behavior were obtained and interpreted to better understand the progressive failure of soil. Four typical progressive failure modes (e.g., local punching shear failure and tensile failure) corresponding to different disturbance paths were identified and compared with the classical active or passive arching mechanisms. The results showed that the degradation of the arching effect will occur, whether in subsequent active or passive state. Prediction of the load on the structure based on classical arching mechanism could significantly deviate real load. Meanwhile, a much larger surface settlement and settlement range were observed compared to that of classical active state with the same ground loss value. Further, the effect of the previous ground disturbance on the progressive failure mechanisms was interpreted by the dilative and contractive behavior of the overlying soil. This study provides a profound basis for estimation of the life-cycle load on underground structures and prediction of ground deformation in view of the ground elevation or erosion collapse caused by subsequent engineering activities and changes in the surrounding environmental condition.

Study on influence characteristics of shield tunnel depth and spacing on settlement in clay strata

The surrounding ground disturbance and surface settlement induced by shield construction are the key problems of tunnelling control and necessary to be studied. Taking the shield tunnel project of Beijing Subway Line 14 as the research background, this paper studies the influence of tunnel spacing and depth on surface settlement distribution by numerical simulation method, and analyzes the relationship between the two factors and maximum settlement. The results indicate that the increase of tunnel depth or tunnel spacing leads to the decrease of the maximum settlement and the settlement reduction rate increases. With the increase of tunnel depth, the settlement trough presents approximately symmetrical distribution, and the symmetry axis is inclined to the first tunnel. With the increase of tunnel spacing, the superposition effect of twin tunnel excavation decreases, and the settlement trough transits from U-shaped to W-shaped with the maximum settlement decreasing relatively from single peak to double peaks. Also, the tunnel depth or spacing is highly correlated with the maximum settlement in a certain range, and the tunnel depth has a stronger linear correlation than the tunnel spacing. The research results provide certain theoretical guidance and references for the prediction of ground deformation and settlement control of shield construction.

Numerical simulation with hardening soil model parameters of marine clay obtained from conventional tests

Over the last decades, numerical modelling has gained practical importance in geotechnical engineering as a valuable tool for predicting geotechnical problems. An accurate prediction of ground deformation is achieved if models that account for the pre-failure behaviour of soil are used. In this paper, laboratory results of the consolidated drain (CD) triaxial compression tests and one-dimensional consolidation tests of marine clay were used to determine the hardening soil model (HSM) parameter for use in Plaxis 3D analyses. The parameters investigated for the HSM were stiffness, strength and advanced parameters. The stiffness parameters were secant stiffness in CD triaxial compression test (E_{50}^{text{ref}}), tangent stiffness for primary oedometer loading test (E_{text{oed}}^{text{ref}} ), unloading/reloading stiffness (E_{text{ur}}^{text{ref}}) and power for the stress-level dependency of stiffness (m). The strength parameters were effective cohesion (c_{text{ref}}^{text{'}}), effective angle of internal friction (phi^{text{'}}) and angle of dilatancy (psi^{text{'}}). The advanced parameters were Poisson’s ratio for unloading–reloading (ν) and K0-value for normal consolidation left( {K_{circ}^{text{nc}} } right). Furthermore, Plaxis 3D was used to simulate the laboratory results to verify the effectiveness of this study. The results revealed that the stiffness parameters E_{50}^{text{ref}} , E_{text{oed}}^{text{ref}} , E_{text{ur}}^{text{ref}} and m are equal to 3.4 MPa, 3.6 MPa, 12 MPa and 0.7, respectively, and that the strength parameters c_{text{ref}}^{text{'}}, phi^{text{'}}, psi^{text{'}} and K_{circ}^{text{nc}} are equal to 33 kPa, 17.51°, 1.6° and 0.7, respectively. A final comparison of the laboratory results with the numerical results revealed that they were in accordance, which proved the efficacy of the study.

Ground movements modeling applying adjusted influence function

Mathematical modeling of surface deformations caused by underground mining operation is commonly carried out with use of empirical, numerical or stochastic models. One of the most frequently applied model for prediction of ground deformation in many countries is Knothe model. The model developed by Knothe belongs to the stochastic methods and is based on the influence function. In China a prediction method named Probability Integration Method (PIF) was established by Liu Baochen and Liao Guohua based on the stochastic medium theory. Modified version of that model allows to predict ground movements caused by mining operation in extremely complex technical and geological conditions. That model is commonly applied for coal, metal ore and salt deposits. The article presents several modifications of the mathematical model used in China and Poland. This model is very widespread in the world, therefore the generalizations proposed in the article can be implemented for the purposes of prediction surface deformations for various types of deposits in many countries. The presented generalizations were then tested on specific examples of coal mining, copper ore mining and rock salt deposit. The obtained results indicate high efficiency of methods based on the influence function in complex geological and mining conditions.

Maximum shear modulus evaluation based on continuous wavelet transform of bender element test

Maximum shear modulus (Gmax) is a crucial parameter in the prediction of ground deformation and performance of seismic design. Practically, the Gmax parameter could be obtained from specific laboratory test or seismic field test. Bender element (BE) test is nondestructive laboratory test, which is simple yet reliable method in determining Gmax of soil. This study focuses on application; processes and analysis of Gmax values obtained from BE laboratory test using continuous wavelet transform (CWT) method. The Gmax values were validated with results from field seismic dilatometer test (sDMT) conducted at the same site of soil sampling for BE laboratory test. BE laboratory tests were conducted on undisturbed Auckland residual clay at various effective confining pressures (ECP) under fully saturated condition. The Gmax values analysis between CWT and field sDMT data were based on the overburden pressures values that matches with ECP applied in the BE laboratory test. In summary, the comparison between CWT analysis of laboratory and field sDMT data indicated good consistency of Gmax values. Thus, confirmed the reliability of CWT method in estimating Gmax parameter from BE laboratory test.

Ground Deformation Analysis Using InSAR and Backpropagation Prediction with Influencing Factors in Erhai Region, China

The long continuity of Interferometric Synthetic Aperture Radar (InSAR) can provide high space and resolution data for ground deformation investigations. The ground deformation in this paper appeared in the city’s development, although it is close to the Erhai region, which is different from a water-deficient city. Therefore, the analysis and prediction of ground deformation using a new method is required. In this study, Sentinel-1 Synthetic Aperture Radar (SAR) images from 2015 to 2018 were used to study the characteristics of ground deformation in the Erhai region using the Small Baseline Subset Interferometric SAR (SBAS-InSAR) technique. The results were cross-validated using ascending and descending direction images to ensure the accuracy. In addition, the results showed that there was little ground deformation in the northern part of the Erhai region, while there was obvious ground deformation in the southern part. Four influencing factors—including the building area, water level, cumulative precipitation, and cumulative temperature of the southern Erhai region—were used together to predict the cumulative ground deformation using back-propagation (BP). The R of all the involved data was 0.966, and the root mean square errors (RMSEs) between the simulated values using BP and the true measured values were 3.063, 1.003, and 1.119, respectively. The results showed that BP has great potential in predicting the change tendency of ground deformation with high precision. The main reason for ground deformation is the continuous increase of building area; the water level followed. The cumulative precipitation and cumulative temperature are the reasons for the seasonal ground deformation. Some countermeasures and suggestions are given to face the challenge of serious ground deformation.

Prediction of Ground Deformation during Pipe-Jacking Considering Multiple Factors

Pipe-jacking is a construction method widely used in pipeline constructions. Prediction of ground deformation induced by pipe-jacking, is important for safety and scheduling purposes. This paper presents an approach to predict ground deformation during pipe-jacking considering following factors: (i) bulkhead additive thrust; (ii) friction on jacking machine; (iii) grouting pressure; and (iv) ground loss. Mindlin’s solution was used to calculate the ground deformation induced by bulkhead additive thrust and friction on the jacking machine. The shearing disturbance coefficient was adopted to evaluate the mitigation effect of shearing behavior on ground deformation. Verruijt’s solution was used to simulate the effect of grouting pressure. Sagaseta’s method was adopted to consider the ground loss induced by over-excavation. Subsequently, a three-dimensional analytical solution for ground deformation induced by pipe-jacking was obtained. A case study based on a pipe-jacking project undertaken in Jiangsu, China was analyzed to validate the proposed approach. The results indicated that the proposed approach was robust and could be implemented for future pipe-jacking projects.

Analytical prediction for ground movements and liner internal forces induced by shallow tunnels considering non-uniform convergence pattern and ground-liner interaction mechanism

Current studies for tunneling-induced ground movements provide little information on the complex interaction between the tunnel liner and the surrounding soils. In particular, little attention is paid to the internal force analyses for segment liners based on the non-uniform convergence deformation pattern. This paper presents a closed-form analytical solution for the prediction of ground deformation and liner internal forces induced by shallow tunnels in clays. The non-uniform convergence deformation pattern is incorporated as the boundary condition of displacements between the ground and the liner. We investigated the difference between uniform radial and non-uniform convergence deformation patterns on the surface settlements and lateral deformation of soils. In general, good alignment was obtained between the predicted ground deformation caused by the non-uniform convergence model and field observations for tunnels in clays. In addition, the influences of sensitive parameters on the ground movements induced by tunneling were evaluated based on the non-uniform convergence pattern, including the soil and liner properties, the geometric properties of tunnel, the tunnel depth, the excavation gap and other main parameters. Furthermore, these solutions offer a more comprehensive framework for understanding the ground-liner interaction mechanism and the circumferential distribution of internal forces for segment liners. Parametric analyses were used to measure the influences of the lateral earth pressure coefficient on the axial forces and bending moments of tunnel liners. Results are provided on a theoretical basis to estimate the interaction behavior between the tunnel liner and the surrounding soils correctly.

The Research of Ground Deformation Prediction Neural Network Model on City Underground Construction

This paper sees the underground construction shield tunnel and foundation trench as study object. It has analyzed disturbance mechanism and ground deformation mechanism, which were caused by shield tunnel and building pit construction. Through the system analysis of ground deformation influence factor, it has confirmed main influence factors, like geological environment condition of overall consideration, physical parameter and construction technology. And it has established ground deformation prediction model based on neural network. Then it has made sensitivity analysis of affecting ground deformation factor by neural network hierarchical analytical approach.

Improving the prediction of excavation-induced ground movements

Activities associated with deep excavations cause ground movements. It is important to predict the deformation of the ground and adjacent structures during an excavation with reasonable accuracy. In contrast to the detailed methodology for limit equilibrium checks in TR26, there is not much guidance on how to overcome the challenges for predicting ground deformations accurately. This paper looks into the key difficulties of predicting excavation-induced ground movements, and attempts to improve the prediction incrementally by making some suggestions on the design and checking process. Specifically, three suggestions will be made in the paper. These are selecting soil stiffness based on expected strain levels in the soil, applying empirical checks on numerical predictions and adopting a progressive modification approach to observational method for excavation analysis and ground deformation prediction.

Wavenet ability assessment in comparison to ANN for predicting the maximum surface settlement caused by tunneling

An alternative method of maximum ground surface settlement prediction, which is based on integration between wavelet theory and Artificial Neural Network (ANN), or wavelet network (wavenet), is presented. In order to minimize the risk of tunneling, a tunnel engineer needs to be able to make reliable prediction of ground deformations induced by tunneling. Any prediction from numerical analysis was highly dependent on the model adopted for modeling the soil behavior. However, setting up a realistic model that would be able to calculate tunneling-induced settlement profiles is rather difficult. Most of the researches show that the capability (i.e. pattern recognition and memorization) of an ANN is suitable for inherent uncertainties and imperfections found in geotechnical engineering problems considering its successful application without any restriction. Wavenet is a single hidden layer feedforward neural network, which uses wavelets as its activation functions. In this study different wavelets are applied as activation functions to predict the maximum surface settlement due to tunneling. Wavenet parameters such as dilation and translation are fixed and only the weights of the network are optimized during its learning process, which is performed by a back-propagation algorithm. The efficacy of this type of network in function learning and estimation is demonstrated through measurements extracted from EPB shield tunneling. The simulation results indicate decrease in estimation error values that depicts its ability to enhance the function approximation capability and consequently exhibits excellent learning ability compared to the conventional back-propagation neural network with sigmoid or other activation functions.