Adaptive Phase Unwrapping Ground-Based SAR Deformation Monitoring Method and System

Abstract

The present invention relates to the field of geological monitoring technology, and discloses an adaptive phase unwrapping ground-based SAR deformation monitoring method and system. The method includes collecting ground-based SAR echo data, extracting phase gradient characteristics and noise distribution, constructing a model based on compressed sensing theory to solve the phase unwrapping result, establishing a dynamic evolution model of the deformation field that integrates multiple factors, and generating deformation monitoring values through an adaptive weighted fusion algorithm. It also constructs an abnormal deformation detection model to achieve adaptive recalibration of model parameters, and constructs a multi-sensor collaborative calibration network to improve monitoring accuracy. The present invention effectively solves the phase unwrapping problem, comprehensively considers multiple influencing factors, can accurately and in real time monitor surface deformation, promptly detect anomalies and calibrate the model, and integrate multi-sensor data. It has important application value in the fields of geological disaster early warning, engineering structure safety assessment, etc.

Description

Technical Field

[0001] The present invention relates to the technical field of geological monitoring, and in particular to an adaptive phase unwrapping ground-based SAR deformation monitoring method and system. Background Art

[0002] In the field of geological monitoring, accurate and timely monitoring of surface deformation is of vital importance. Whether it is preventing geological disasters, protecting people's lives and property, or ensuring the stable operation of large-scale infrastructure projects, accurate deformation monitoring is an indispensable key link.

[0003] Traditional methods of surface deformation monitoring, such as leveling and total station measurements, can obtain deformation data to a certain extent, but they have many limitations. Leveling relies on fixed measurement points and has a limited measurement range, making it difficult to achieve simultaneous monitoring of large areas. In areas with complex terrain and inaccessible transportation, implementation is difficult and inefficient. Total station measurements are also limited by observation distance and line of sight. In mountainous areas and urban areas with dense high-rise buildings, measurement work often faces numerous obstacles, making it impossible to obtain comprehensive and accurate deformation information.

[0004] Synthetic Aperture Radar (SAR), an active microwave remote sensing technology, uses radar sensors carried by satellites, aircraft, or ground platforms to transmit electromagnetic waves to the Earth's surface and receive reflected signals. Using the principle of synthetic aperture and interferometry (InSAR), it reconstructs high-resolution deformation information of the target area. Unlike traditional optical remote sensing, SAR has the ability to penetrate clouds, rain, fog, and operate at night, enabling all-weather and all-day monitoring of minute surface deformations (millimeter-level). Based on the platform type, SAR is primarily categorized as spaceborne SAR and ground-based SAR. Spaceborne SAR offers wide coverage but limited spatial and temporal resolution, while ground-based SAR, deployed close to the ground, enables high-precision localized monitoring.

[0005] While satellite SAR technology can observe large areas, its relatively low spatial resolution makes it inaccurate for monitoring small local deformations. Furthermore, satellite observation cycles are long, making it difficult to monitor deformation in real time.

[0006] The emergence of ground-based SAR technology has brought new solutions to surface deformation monitoring. It offers high spatial and temporal resolution, enabling continuous observation of the monitored area. However, in practical applications, ground-based SAR also faces a number of challenges. The echo data contains complex information, and phase unwrapping is a key factor limiting monitoring accuracy. The phase unwrapping process is susceptible to noise interference, leading to errors in the unwrapping results and compromising the assessment of actual deformation.

[0007] Furthermore, existing deformation monitoring methods often fail to fully consider the combined influence of multiple factors on deformation, including surface physical parameters, ambient temperature, and external loads. In reality, these factors interact with each other to cause surface deformation. Ignoring any one factor can lead to biased monitoring results, failing to accurately reflect the true extent of deformation.

[0008] At the same time, monitoring data from a single sensor has limitations, making it difficult to fully and accurately describe deformation characteristics. Different sensors have different measurement principles and accuracies, and effectively fusing data from multiple sensors to improve monitoring reliability and accuracy is a pressing issue. Existing methods lack efficient and intelligent detection mechanisms for abnormal deformation detection, making it impossible to promptly identify potential safety hazards and provide early warnings. In summary, developing an adaptive phase unwrapping ground-based SAR deformation monitoring method and system that can overcome these issues is of great practical significance. Summary of the Invention

[0009] The object of the present invention is to provide an adaptive phase unwrapping ground-based SAR deformation monitoring method and system to solve the problems raised in the above background technology.

[0010] To achieve the above-mentioned object, the present invention provides the following technical solution: an adaptive phase unwrapping ground-based SAR deformation monitoring method, the method comprising:

[0011] Collect ground-based SAR echo data, including interferometric phase, polarization scattering matrix and time series observation information;

[0012] extracting phase gradient characteristics and noise distribution from the echo data;

[0013] A phase unwrapping optimization model is constructed based on compressed sensing theory, and the global phase unwrapping result is solved by a sparse constrained iterative algorithm.

[0014] Establishing a dynamic evolution model of the deformation field, wherein the dynamic evolution model of the deformation field integrates surface physical parameters, ambient temperature field and external load action data;

[0015] According to the phase unwrapping result and the deformation field dynamic evolution model, a deformation monitoring value is generated through an adaptive weighted fusion algorithm.

[0016] Preferably, the phase gradient characteristics include a local phase difference matrix, a frequency domain coherence spectrum and a polarization phase consistency characteristic.

[0017] Preferably, the sparse constrained iterative algorithm includes:

[0018] Constructing a phase residual objective function, wherein the function includes an L1 norm sparsity term and a total variation regularization term;

[0019] The alternating direction multiplier method is used to decompose the objective function and generate iterative update rules;

[0020] The convergence is accelerated by an adaptive step-size adjustment strategy, and a residual feedback mechanism is introduced to dynamically correct the iterative path.

[0021] Preferably, the deformation field dynamic evolution model includes:

[0022] The surface medium is discretized based on the finite element method, and the partial differential equations of node displacement and strain tensor are established;

[0023] Integrate temperature gradient field data and modify deformation field boundary conditions through thermal-mechanical coupling analysis;

[0024] Combined with the Kalman filter algorithm, the deformation field is predicted and updated in real time.

[0025] Preferably, the adaptive weighted fusion algorithm includes:

[0026] Calculate the frequency band weight coefficient based on the signal-to-noise ratio and spatial resolution of the phase unwrapping result;

[0027] Construct a multi-scale fusion pyramid and perform weighted superposition of deformation fields at various scales;

[0028] The rasterization artifacts of the fusion result are eliminated by edge-preserving filtering.

[0029] Preferably, the method further comprises:

[0030] An abnormal deformation detection model is constructed based on a generative adversarial network, which uses historical deformation data as real samples and real-time monitoring data as generated samples;

[0031] When the probability of abnormality output by the discriminator exceeds a threshold, the adaptive recalibration of the deformation field model parameters is triggered.

[0032] Preferably, the adaptive recalibration comprises:

[0033] Define the credibility intervals and physical constraints of deformation field parameters;

[0034] The Bayesian optimization algorithm is used to search for the optimal parameter combination, and the parameter posterior distribution is verified by Markov chain Monte Carlo sampling.

[0035] Preferably, the method further comprises:

[0036] Constructing a multi-sensor collaborative calibration network that integrates GNSS displacement data, inclinometer measurement data, and SAR deformation monitoring values;

[0037] The spatiotemporal correlation between sensors is modeled through graph convolutional neural networks to generate joint calibration corrections.

[0038] Preferably, the present invention further includes an adaptive phase unwrapping ground-based SAR deformation monitoring system, the system comprising:

[0039] Data acquisition module: used to collect echo data of ground-based SAR;

[0040] Phase filtering module: extracting phase gradient characteristics and noise distribution from the echo data;

[0041] Disentanglement optimization module: Based on the compressed sensing theory, a phase disentanglement optimization model is constructed, and the global phase disentanglement result is solved through the sparse constrained iterative algorithm;

[0042] Deformation modeling module: establishes a dynamic evolution model of the deformation field, integrating surface physical parameters and ambient temperature field data;

[0043] Fusion output module: Based on the phase unwrapping results and the deformation field model, the deformation monitoring value is generated through an adaptive weighted fusion algorithm.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] During data processing and phase unwrapping, ground-based SAR echo data is collected and phase gradient characteristics and noise distribution are extracted. This process fully exploits the effective information in the data, providing a foundation for subsequent precise unwrapping and analysis. A phase unwrapping optimization model is constructed based on compressed sensing theory, and a sparse constrained iterative algorithm is used to solve the global phase unwrapping result. This algorithm constructs a phase residual objective function consisting of an L1 norm sparse term and a total variation regularization term, decomposes it using the alternating direction multiplier method, and generates an iterative update rule. It also employs an adaptive step size adjustment strategy to accelerate convergence and introduces a residual feedback mechanism to dynamically correct the iterative path. These operations not only effectively suppress noise interference on phase unwrapping and improve unwrapping accuracy, but also offer greater stability and accuracy when processing complex data compared to traditional unwrapping methods. They can more accurately restore true phase information, providing a reliable basis for subsequent deformation analysis.

[0046] The established dynamic evolution model of the deformation field integrates surface physical parameters, ambient temperature fields, and external load data. By discretizing the surface medium using the finite element method, partial differential equations for node displacements and strain tensors are established. Thermal-mechanical coupling analysis combined with temperature gradient field data is used to modify the deformation field boundary conditions. The Kalman filter algorithm is then used to predict and update the deformation field in real time. This enables the model to comprehensively and accurately reflect the dynamic evolution of surface deformation, fully accounting for the impact of various practical factors on deformation. Compared to traditional models, the prediction results are closer to reality, enabling the early detection of potential deformation trends and providing a more reliable basis for disaster warning and engineering safety assessments.

[0047] To generate deformation monitoring values, an adaptive weighted fusion algorithm is used. Frequency band weight coefficients are calculated based on the signal-to-noise ratio and spatial resolution of the phase unwrapping results. A multi-scale fusion pyramid is constructed to perform weighted superposition of the deformation field at each scale. Edge-preserving filtering is then used to eliminate rasterization artifacts in the fusion results. This fusion method fully leverages the advantages of data from different frequency bands, improving the accuracy and resolution of monitoring results while effectively eliminating artifacts generated during the fusion process. This makes monitoring results clearer and more reliable, facilitating intuitive analysis and judgment of deformation conditions.

[0048] A model for detecting abnormal deformations is constructed based on a generative adversarial network, using historical deformation data as real samples and real-time monitoring data as generated samples. When the discriminator outputs an abnormal probability exceeding a threshold, it triggers adaptive recalibration of the deformation field model parameters. By defining credibility intervals and physical constraints for the deformation field parameters, a Bayesian optimization algorithm is used to search for the optimal parameter combination, and the posterior distribution of the parameters is verified through Markov Chain Monte Carlo sampling. This mechanism enables real-time and intelligent detection of abnormal deformations, promptly identifying potential safety hazards. Adaptive recalibration ensures the accuracy and reliability of the model, significantly improving the early warning capabilities of the monitoring system.

[0049] The constructed multi-sensor collaborative calibration network integrates GNSS displacement data, inclinometer measurements, and SAR deformation monitoring values. Using a graph convolutional neural network to model the spatiotemporal correlations between sensors, it generates joint calibration corrections. This network effectively integrates multi-sensor data, leveraging the strengths of different sensors to complement and verify each other, improving the reliability and accuracy of monitoring data and providing strong support for a more comprehensive and accurate understanding of surface deformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a working principle diagram of the adaptive phase unwrapping ground-based SAR deformation monitoring method according to the present invention;

[0051] Figure 2 This is the workflow diagram of the sparse constrained iterative algorithm;

[0052] Figure 3 Flowchart for abnormal deformation detection and recalibration triggering;

[0053] Figure 4 The diagram shows the architecture of the adaptive phase unwrapping ground-based SAR deformation monitoring system. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0055] See also Figure 1-Figure 4 The present invention provides a technical solution: an adaptive phase unwrapping ground-based SAR deformation monitoring method, the method comprising:

[0056] Specialized ground-based SAR equipment is used to observe the monitoring area and acquire echo data. This data includes interferometric phase, polarization scattering matrix, and time series observation information. The interferometric phase reflects the phase differences at different locations in the monitoring area and is an important basis for subsequent deformation analysis. The polarization scattering matrix contains information on the polarization characteristics of the ground objects, which helps to more comprehensively understand the characteristics of the ground objects in the monitoring area. The time series observation information records observation data at different time points and can be used to analyze the trend of deformation changes over time. During the actual acquisition process, the parameters of the ground-based SAR equipment, such as the transmission frequency, bandwidth, and observation angle, are reasonably set according to the scope of the monitoring area, the complexity of the terrain, and the monitoring accuracy requirements to ensure the acquisition of high-quality echo data.

[0057] The collected echo data is processed to extract phase gradient characteristics and noise distribution. Phase gradient characteristics reflect phase changes and are important for subsequent phase unwrapping. Obtaining noise distribution helps suppress noise in subsequent processing and improve monitoring accuracy. During the extraction process, specialized data processing algorithms, such as those based on signal processing theory, are used to analyze and calculate the echo data to obtain accurate phase gradient characteristics and noise distribution information.

[0058] Based on compressed sensing theory, a phase unwrapping optimization model was constructed. This model exploits the sparsity of the signal and uses a sparse constrained iterative algorithm to solve for global phase unwrapping. When constructing the model, the characteristics of the monitoring data and actual requirements were fully considered, and the model parameters were appropriately set. The sparse constrained iterative algorithm improves computational efficiency while maintaining unwrapping accuracy. During the solution process, continuous iterative optimization is performed to gradually obtain accurate global phase unwrapping results.

[0059] A dynamic deformation field evolution model was established, integrating data on surface physical parameters, ambient temperature fields, and external loads. Surface physical parameters, such as soil type and geological structure, affect surface deformation. Changes in ambient temperature fields cause thermal expansion and contraction of surface materials, in turn influencing deformation. External loads, such as building weight and traffic loads, are also significant contributors to surface deformation. By integrating these data, a more accurate description of the dynamic evolution of the deformation field can be achieved. When developing the model, relevant physical theories and mathematical methods were applied to incorporate these factors, and appropriate parameter settings and model calibration were performed.

[0060] The phase unwrapping results are combined with the deformation field dynamic evolution model to generate deformation monitoring values using an adaptive weighted fusion algorithm. This algorithm automatically adjusts weights based on the characteristics and reliability of different data, leveraging the strengths of both to achieve more accurate deformation monitoring values. In practical applications, the algorithm parameters should be appropriately adjusted based on the specific conditions and needs of the monitoring area to achieve optimal monitoring results.

[0061] The present invention will be further described below in conjunction with Examples 1 to 6: Example 1

[0062] When processing echo data to extract phase gradient features, we focus on the local phase difference matrix, frequency domain coherence map and polarization phase consistency features. The local phase difference matrix is used to describe the phase difference between adjacent pixels. By calculating the phase difference between adjacent pixels, the phase change trend can be clearly displayed. Assume that the phases of adjacent pixels are and , then the elements in the local phase difference matrix can be expressed as The frequency domain coherence spectrum is obtained by performing frequency domain analysis on the echo data, which reflects the correlation between different frequency components. When calculating the frequency domain coherence spectrum, the echo data is first Fourier transformed to obtain frequency domain data, and then the coherence coefficients between different frequency components are calculated. The polarization phase consistency feature is extracted based on the polarization scattering matrix, which measures the degree of phase consistency between different polarization channels. For the polarization scattering matrix , a specific algorithm is used to calculate the phase of different polarization channels, thereby obtaining polarization phase consistency features. These phase gradient features reflect the characteristics of the echo data from different angles, providing rich information for subsequent phase unwrapping and deformation analysis.

[0063] In practice, the parameters and algorithms for calculating these features should be appropriately selected based on the type of surface feature in the monitoring area and the monitoring objective. For example, when monitoring densely built-up areas, the calculation window of the local phase difference matrix can be appropriately reduced to more accurately capture phase changes at building boundaries. When monitoring large natural areas, the calculation of the frequency domain coherence spectrum and polarization phase consistency features can utilize a wider frequency range and more polarization channels to obtain more comprehensive surface feature information. At the same time, the extracted phase gradient features can be denoised in combination with noise distribution information to improve their accuracy and reliability. Filtering algorithms, such as median filtering and Gaussian filtering, can be used to smooth the local phase difference matrix and remove abnormal phase differences caused by noise. For the frequency domain coherence spectrum and polarization phase consistency features, thresholds can be set to remove frequency components and polarization channels with significant noise interference. Example 2

[0064] When using the sparse constrained iterative algorithm to solve the global phase unwrapping result, the phase residual objective function is first constructed. This function contains the L1 norm sparsity term and the total variation regularization term. Assume that the phase to be unwrapped is , the observed phase is , then the phase residual objective function It can be expressed as:

[0065] ,

[0066] in, and is the weight coefficient, which is used to balance the importance of different items; Indicates phase The L1 norm sparse term can promote the sparseness of the phase gradient, which is beneficial to remove noise and retain the edge information of the phase; is the total variation regularization term, which is used to maintain the smoothness of the phase and avoid excessive fluctuations in the unwrapping results; is the fitting term of the observed data, ensuring that the unwrapping result is as close as possible to the observed data.

[0067] Next, the alternating direction multiplier method is used to decompose the objective function and generate an iterative update rule. By decomposing the objective function into multiple sub-problems, solving each sub-problem separately, and then updating the variables alternately, the optimal solution is gradually approached. During the iteration process, an adaptive step adjustment strategy is used to accelerate convergence. The step size is dynamically adjusted according to the result of each iteration. For example, if the current iteration result changes greatly, the step size is appropriately increased to speed up the convergence speed; if the change is small, the step size is reduced to improve the convergence accuracy. At the same time, a residual feedback mechanism is introduced to dynamically correct the iteration path. According to the phase residual after each iteration, the direction of the next iteration is adjusted to make the iterative process more stable and accurate. In practical applications, it is necessary to reasonably select the weight coefficient according to the characteristics of the monitoring data and the limitations of computing resources. and . You can test different value combinations through experiments, observe the quality of the unwrapping results, and select the optimal parameters. In addition, you also need to pay attention to the setting of the iteration termination condition to avoid excessive iterations that lead to waste of computing resources. Generally, the termination condition can be determined based on the change in the phase residual or the number of iterations. For example, when the phase residual is less than a preset threshold, or the number of iterations reaches a certain upper limit, the iteration is stopped. Example 3

[0068] When establishing the dynamic evolution model of the deformation field, the surface medium is discretized based on the finite element method. The surface medium is divided into multiple finite element units, each of which consists of nodes. The partial differential equations of the node displacement and strain tensor are established to describe the deformation behavior of the surface medium under stress. Let the node displacement be , the strain tensor is , according to the theory of elasticity, the relationship between them can be expressed by the partial differential equation: ,in is the stress tensor, and the strain tensor Through the constitutive relationship Get in touch, is the elastic matrix, which depends on the material properties of the surface medium. The temperature gradient field data is integrated and the deformation field boundary conditions are corrected through thermal-mechanical coupling analysis.

[0069] Temperature changes can cause thermal expansion or contraction of the surface medium, thereby generating additional stress and strain. Assume that the temperature change is , the thermal expansion coefficient is , then the thermal strain ,in is a unit tensor. Thermal strain is incorporated into the strain tensor to modify the boundary conditions of the deformation field. The Kalman filter algorithm is combined to predict and update the deformation field in real time. The Kalman filter algorithm can use the state equation and observation equation of the system to optimally estimate and predict the state of the deformation field. Let the state vector of the deformation field be , the observation vector is , the state equation is , the observation equation is ,in is the state transition matrix, is the observation matrix, and These are process noise and observation noise. Through the prediction and update steps of the Kalman filter algorithm, the estimated value of the deformation field is continuously adjusted to make it closer to the actual deformation. In practical applications, it is necessary to accurately obtain the material parameters of the surface medium, such as the elastic modulus, Poisson's ratio, and thermal expansion coefficient. These parameters can be obtained through field tests, geological surveys, and other methods. At the same time, to ensure the accuracy of the temperature gradient field data, multiple temperature sensors can be deployed in the monitoring area to collect temperature data in real time and perform data fusion and processing. In addition, it is necessary to reasonably set the parameters of the Kalman filter algorithm, such as the process noise covariance matrix and the observation noise covariance matrix, to improve the accuracy of prediction and update. Example 4

[0070] When using the adaptive weighted fusion algorithm to generate deformation monitoring values, the frequency band weight coefficient is calculated based on the signal-to-noise ratio and spatial resolution of the phase unwrapping result. The signal-to-noise ratio of the phase unwrapping result of each frequency band is , the spatial resolution is , then the frequency band weight coefficient It can be calculated by the following formula:

[0071] ,

[0072] in is the total number of frequency bands. In this way, frequency bands with high signal-to-noise ratio and high spatial resolution will be given greater weights and play a more important role in the fusion process.

[0073] Construct a multi-scale fusion pyramid and perform weighted superposition of deformation fields at each scale. First, perform multi-scale decomposition of deformation field data of different frequency bands to obtain image pyramids of different resolutions. At each scale level, perform weighted superposition of deformation field data of each frequency band according to the calculated frequency band weight coefficient. For example, at a certain scale level, the fused deformation field It can be expressed as

[0074] ,

[0075] in It is The frequency band in Deformation field data at multiple scales is collected. Edge-preserving filtering is used to eliminate rasterization artifacts in the fusion results. Edge-preserving filtering algorithms smooth the fusion results and remove rasterization artifacts while preserving edge information in the deformation field. Algorithms such as bilateral filtering and guided filtering can be used. Appropriate filtering parameters, such as filter radius and standard deviation, should be selected based on the characteristics and requirements of the fusion results. In practical applications, accurate assessment of the signal-to-noise ratio and spatial resolution is essential. The signal-to-noise ratio can be calculated as the ratio of signal power to noise power, taking into account the characteristics of the echo data and the distribution of noise. Spatial resolution depends on the parameters of the ground-based SAR equipment and the data processing method. It can be determined through observation and analysis of known standard targets. Furthermore, when constructing a multi-scale fusion pyramid, the decomposition scale and fusion method must be appropriately selected to ensure that the fusion results reflect the overall trend of the deformation field while preserving detailed information. Furthermore, when performing edge-preserving filtering, care must be taken to avoid excessive filtering that may cause loss of edge information, which could affect the accuracy of deformation monitoring. Example 5

[0076] An abnormal deformation detection model is constructed based on the generative adversarial network, with historical deformation data as real samples and real-time monitoring data as generated samples. and the discriminator Composition. Generator The role of is to generate simulated deformation data based on random noise, making it as close as possible to the real historical deformation data; the discriminator It is responsible for judging whether the input data is real historical deformation data or simulated data generated by the generator. During the training process, the generator and the discriminator compete with each other and continuously optimize their parameters. Let the random noise be , the simulated deformation data generated by the generator is , the real historical deformation data is , then the discriminator The objective function can be expressed as:

[0077] ,

[0078] in is the distribution of real historical deformation data, is the distribution of random noise. When the probability of the discriminator outputting anomalies exceeds the threshold, the adaptive recalibration of the deformation field model parameters is triggered.

[0079] During the adaptive recalibration process, the credibility intervals and physical constraints for the deformation field parameters are first defined. For example, for the elastic modulus of the surface medium, a reasonable range of values is determined based on geological data and experience, serving as the credibility interval. Physical constraints are also set based on physical principles, such as the elastic modulus cannot be negative. A Bayesian optimization algorithm is then used to search for the optimal parameter combination. The Bayesian optimization algorithm constructs a surrogate model of the objective function and uses probability distributions to estimate the optimal parameter locations. During the search process, the surrogate model is continuously updated based on new sampling points, gradually approaching the optimal solution. Finally, the posterior distribution of the parameters is verified using Markov Chain Monte Carlo sampling. Markov Chain Monte Carlo sampling samples from the posterior distribution of the parameters, generating a series of parameter samples that conform to the posterior distribution. Analysis of these samples verifies whether the optimal parameter combination obtained by the Bayesian optimization algorithm is reasonable and consistent with the actual situation. In practical applications, the quality and representativeness of historical deformation data must be ensured. Historical deformation data should cover a variety of geological conditions, environmental factors, and time periods, so that the generator can learn realistic deformation patterns. When setting the discriminator threshold, it's important to consider both monitoring sensitivity and false alarm rate. If the threshold is set too high, some abnormal deformations may be missed; if the threshold is set too low, a high number of false alarms may be generated. Furthermore, during adaptive recalibration, it's important to fully utilize existing monitoring data and prior knowledge to improve recalibration efficiency and accuracy. Example 6

[0080] A multi-sensor collaborative calibration network is constructed, which integrates GNSS displacement data, inclinometer measurement data and SAR deformation monitoring values. GNSS displacement data can provide high-precision absolute displacement information, inclinometer measurement data can reflect the tilt change of the surface, and SAR deformation monitoring values have the characteristics of large area and high resolution. Combining these three types of data can more comprehensively monitor surface deformation. The spatiotemporal correlation between sensors is modeled through graph convolutional neural networks to generate joint calibration corrections. Graph convolutional neural networks can process data with graph structures, treating sensors as nodes in the graph and the spatiotemporal relationships between sensors as edges. Assume the number of sensors is , the node feature matrix is ,in is the dimension of node features, and the adjacency matrix is , represents the connection relationship between sensors. The graph convolutional neural network learns the spatiotemporal correlation between sensors by performing convolution operations on the node feature matrix and the adjacency matrix. Its convolution operation can be expressed as:

[0081] ,

[0082] in It is The node feature matrix of the layer, It is The weight matrix of the layer, is the activation function, , is the identity matrix, yes Through the learning of graph convolutional neural networks, a spatiotemporal correlation model between sensors is obtained, and then a joint calibration correction is generated based on GNSS displacement data, inclinometer measurement data, and SAR deformation monitoring values.

[0083] In practical applications, it is crucial to ensure the accuracy and synchronization of data from each sensor. GNSS equipment and inclinometers should be regularly calibrated and maintained to ensure the accuracy of measurement data. Furthermore, the observation times of SAR monitoring and other sensors should be synchronized as closely as possible to avoid data fusion errors caused by time differences. Furthermore, when constructing graph convolutional neural networks, the network structure and parameters, such as the number of layers, node feature dimensions, and weight matrix initialization, must be appropriately configured. Experiments can be conducted to test different network structures and parameter combinations and select the optimal model to improve the accuracy of the joint calibration corrections, thereby enhancing overall deformation monitoring accuracy.

[0084] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0085] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An adaptive phase unwrapping ground-based SAR deformation monitoring method, characterized in that: include: Collect ground-based SAR echo data, including interferometric phase, polarization scattering matrix and time series observation information; extracting phase gradient characteristics and noise distribution from the echo data; A phase unwrapping optimization model is constructed based on compressed sensing theory, and the global phase unwrapping result is solved by a sparse constrained iterative algorithm. Establishing a dynamic evolution model of the deformation field, wherein the dynamic evolution model of the deformation field integrates surface physical parameters, ambient temperature field and external load action data; The phase unwrapping results are combined with the dynamic evolution model of the deformation field, and the deformation monitoring value is generated using the adaptive weighted fusion algorithm; the adaptive weighted fusion algorithm automatically adjusts the weight according to the characteristics and reliability of different data, fully combining the advantages of both to obtain more accurate deformation monitoring values.

2. The adaptive phase unwrapping ground-based SAR deformation monitoring method according to claim 1, characterized in that: The phase gradient features include a local phase difference matrix, a frequency domain coherence spectrum and a polarization phase consistency feature.

3. The adaptive phase unwrapping ground-based SAR deformation monitoring method according to claim 1, characterized in that: The sparse constrained iterative algorithm includes: Constructing a phase residual objective function, wherein the function includes an L1 norm sparsity term and a total variation regularization term; The alternating direction multiplier method is used to decompose the objective function and generate iterative update rules; The convergence is accelerated by an adaptive step-size adjustment strategy, and a residual feedback mechanism is introduced to dynamically correct the iterative path.

4. The adaptive phase unwrapping ground-based SAR deformation monitoring method according to claim 3, characterized in that: The deformation field dynamic evolution model includes: The surface medium is discretized based on the finite element method, and the partial differential equations of node displacement and strain tensor are established; Integrate temperature gradient field data and modify deformation field boundary conditions through thermal-mechanical coupling analysis; Combined with the Kalman filter algorithm, the deformation field is predicted and updated in real time.

5. The adaptive phase unwrapping ground-based SAR deformation monitoring method according to claim 1, characterized in that: The method further comprises: Constructing a multi-sensor collaborative calibration network that integrates GNSS displacement data, inclinometer measurement data, and SAR deformation monitoring values; The spatiotemporal correlation between sensors is modeled through graph convolutional neural networks to generate joint calibration corrections.

6. An adaptive phase unwrapping ground-based SAR deformation monitoring system, characterized by: include: Data acquisition module: used to collect echo data of ground-based SAR; Phase filtering module: extracting phase gradient characteristics and noise distribution from the echo data; Disentanglement optimization module: Based on the compressed sensing theory, a phase disentanglement optimization model is constructed, and the global phase disentanglement result is solved through the sparse constrained iterative algorithm; Deformation modeling module: establishes a dynamic evolution model of the deformation field, integrating surface physical parameters and ambient temperature field data; Fusion output module: combines the phase unwrapping results with the deformation field dynamic evolution model and generates deformation monitoring values using an adaptive weighted fusion algorithm; The adaptive weighted fusion algorithm automatically adjusts the weights according to the characteristics and reliability of different data, fully combining the advantages of both to obtain more accurate deformation monitoring values.

Images