Multi-level constraint InSAR deformation type distinguishing method, system and device and storage medium

Abstract

The invention relates to a multi-level constraint InSAR deformation type distinguishing method, system and device and a storage medium. The method comprises the steps that InSAR annual average deformation phase data and gradient data in a research area range are acquired; a multi-channel input InSAR deformation area detection network is constructed; obtaining a plurality of dichotograms by using the detection network, and determining the boundary of a multi-class InSAR deformation region; spatial overlay analysis of a geographic information system is carried out, and InSAR deformation area types are distinguished step by step; according to the method, the InSAR deformation area type distribution position under the area scale is obtained, InSAR deformation derivative products are obtained, and basic data are provided for geological disaster monitoring and early warning and management decision making.

Description

Technical Field

[0001] The present application relates to the technical field of geological disaster monitoring, and in particular to a multi-level constrained InSAR deformation type differentiation method, system and storage medium. Background Art

[0002] InSAR technology is one of the important earth observation technologies and has been widely used in long-term monitoring of small surface deformation. Obtaining surface deformation information through multi-temporal interferometry and understanding the mechanism and trend of surface deformation are helpful to assess potential risks. At present, the InSAR deformation type differentiation method mainly uses continuous scatterer interferometry to obtain a discrete point set PS composed of high-coherence pixels, calculates deformation, and separates active PS and inactive PS points through clustering methods. Combined with additional data sources such as landslide catalog data, urban vector data, and terrain data in the study area, expert interpretation is used to semi-automatically distinguish landslide active deformation areas, ground subsidence deformation areas, etc. However, the current use of continuous scatterer interferometry technology to distinguish deformation zone types involves a large amount of data and low computational efficiency. This method has certain limitations for monitoring large-scale and wide-area surface deformation.

[0003] In addition, although the current InSAR technology has played an important role in monitoring landslides, urban ground subsidence, mining monitoring and glacier movement, the automation level of InSAR deformation zone classification detection is low in view of the different spatial distribution characteristics of landslides, mining collapses, subsidence and glacier deformation. Summary of the invention

[0004] In order to solve at least one of the above-mentioned technical problems, the present application proposes a multi-level constrained InSAR deformation type differentiation method, system and storage medium.

[0005] According to some embodiments of the present application, a multi-level constrained InSAR deformation type differentiation method is provided, the method comprising:

[0006] Step 1: Acquire the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data;

[0007] Step 2: constructing a multi-channel input InSAR deformation zone detection network; using the detection network to perform feature extraction and prediction segmentation on the first three band channel data of the multi-source fusion data to obtain the first two classification maps;

[0008] Step 3: assigning a projection coordinate system to the first two-classification map and performing raster vectorization processing to obtain a first deformation area vector layer and determine the boundary of the Class I InSAR deformation area;

[0009] Step 4: Using the detection network to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; assigning a projection coordinate system and performing raster vectorization processing on the second binary classification map to obtain a second deformation area vector layer, and determine the boundary of the Class II InSAR deformation area;

[0010] Step 5: Add the sample data of the mining subsidence deformation zone on the slope as a negative sample; repeat step 4 for training and prediction to obtain a third binary classification map; assign a projection coordinate system and perform raster vectorization processing on the third binary classification map to obtain a third deformation zone vector layer, and determine the boundary of the Class III InSAR deformation zone;

[0011] Step 6: Perform a geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, and determine that the vector layer that overlaps with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest is the landslide deformation zone on the slope.

[0012] Step 7: Performing a geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in step 6 and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope;

[0013] Step 8: Perform geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in step 6, the mining subsidence deformation zone boundary on the slope determined in step 7, and the Class I InSAR deformation zone boundary to determine the settlement deformation zone in the plain area.

[0014] In some possible implementations, obtaining the InSAR annual average deformation phase data and slope data within the study area includes:

[0015] The InSAR annual average deformation phase data in the study area were obtained using multi-period InSAR data.

[0016] The corresponding DEM data is obtained by cropping the range of each InSAR annual average deformation phase data, and the slope data is calculated.

[0017] In some possible implementations, the first three band channel data of the four-band channel data are multi-period InSAR annual average deformation phase data, and the fourth band channel data are slope data.

[0018] In some possible implementations, the encoding part of the detection network includes a backbone network mobilenetv2 part structure, a hole convolution ASPP module, a 1X1 convolution module and an upsampling module; the decoding part of the detection network includes a fusion module, a 3X3 convolution module and a 1X1 convolution module.

[0019] In some possible implementations, the encoding part of the detection network performs deep semantic feature extraction on the first three band channel data of the multi-source fusion data; the decoding part of the detection network performs 1×1 convolution on the shallow semantic features obtained by the backbone network mobilenetv2, and then fuses them with the deep semantic features obtained by the encoding part, and then outputs abstract semantic features through two 3×3 convolution operations, further predicts and segments the InSAR deformation area, and obtains the first binary classification map.

[0020] In some possible embodiments, the boundaries of the Type I InSAR deformation zones include the landslide deformation zones on the slopes, the mining subsidence deformation zones on the slopes, the settlement deformation zones in the plains, and the glacier deformation zones; the boundaries of the Type II InSAR deformation zones include the landslide deformation zones on the slopes, the mining subsidence deformation zones on the slopes, and the glacier deformation zones; the boundaries of the Type III InSAR deformation zones include the landslide deformation zones on the slopes, and the glacier deformation zones.

[0021] In some possible implementations, the glacier outline vector layer within the study area is obtained using a complete catalog vector layer of global glacier outlines published by GLIMS.

[0022] According to other embodiments of the present application, a multi-level constrained InSAR deformation type differentiation system is provided, the system comprising: a data acquisition module, a data processing module, and a layer analysis module;

[0023] The data acquisition module is used to: obtain the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data;

[0024] The data processing module is used to: construct an InSAR deformation zone detection network with multi-channel input; use the detection network to perform feature extraction and prediction segmentation on the first three band channel data of the multi-source fusion data to obtain a first two-classification map;

[0025] Assigning a projection coordinate system and performing raster vectorization processing on the first two classification maps to obtain a first deformation area vector layer and determine the boundary of the type I InSAR deformation area;

[0026] The detection network is used to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; the second binary classification map is assigned a projection coordinate system and rasterized to obtain a second deformation area vector layer, and the boundary of the Class II InSAR deformation area is determined;

[0027] Adding sample data of mining subsidence deformation zone on the slope as negative samples; repeating training and prediction to obtain a third binary classification map; assigning a projection coordinate system and performing raster vectorization processing on the third binary classification map to obtain a third deformation zone vector layer, and determining the boundary of the Class III InSAR deformation zone;

[0028] The layer analysis module is used to perform geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, and determine that the vector layer overlapping with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest are landslide deformation zones on the slope.

[0029] Performing a geographic information system spatial overlay analysis on the determined landslide deformation zone boundary and glacier deformation zone boundary on the slope and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope;

[0030] The determined landslide deformation zone boundaries and glacier deformation zone boundaries on the slope, the mining subsidence deformation zone boundaries on the slope and the Class I InSAR deformation zone boundaries are subjected to geographic information system spatial overlay analysis to determine the settlement deformation zone in the plain area.

[0031] According to other embodiments of the present application, a multi-level constrained InSAR deformation type distinction device is provided, including a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or at least one program is loaded and executed by the processor to implement the multi-level constrained InSAR deformation type distinction method as described above.

[0032] According to other embodiments of the present application, a storage medium is provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the multi-level constrained InSAR deformation type differentiation method as described above.

[0033] Implementing the embodiments of the present application has the following beneficial effects:

[0034] In view of the problem of low automation level of InSAR deformation zone classification detection, an embodiment of the present invention provides an InSAR deformation type differentiation method. Based on multi-period InSAR annual average deformation phase maps, and targeting the different spatial distribution characteristics of landslides, mining collapses, subsidence, and glacier deformations, a deep learning method is used, combined with multi-level constraints, to gradually differentiate the types of InSAR deformation zones; the distribution positions of InSAR deformation zone types at a regional scale are obtained, and InSAR deformation derivative products are obtained, providing basic data for geological disaster monitoring and early warning, and management decisions. The method provided by the present invention is suitable for deformation monitoring applications in a wide range of research areas, greatly improves the computational efficiency and response speed, and has a high degree of automated classification detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of this specification or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A flowchart showing a method for distinguishing InSAR deformation types with multi-level constraints according to an embodiment of the present application is shown;

[0037] Figure 2 A data processing flow chart of a multi-level constrained InSAR deformation type differentiation method according to an embodiment of the present application is shown;

[0038] Figure 3 A schematic diagram showing sample data of mining subsidence deformation zone on a slope according to an embodiment of the present application;

[0039] Figure 4 A structural block diagram of a multi-level constrained InSAR deformation type differentiation system according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] Combination Figure 1 and Figure 3 The embodiment of the present application provides a multi-level constrained InSAR deformation type differentiation method, including:

[0042] S100: Acquire the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data.

[0043] In the embodiment of the present application, the acquisition of the InSAR annual average deformation phase data and slope data within the study area includes:

[0044] The InSAR annual average deformation phase data in the study area were obtained using multi-period InSAR data.

[0045] The corresponding DEM data is obtained by cropping the range of each InSAR annual average deformation phase data, and the slope data is calculated.

[0046] The first three band channel data of the four-band channel data are multi-period InSAR annual average deformation phase data, and the fourth band channel data are slope data.

[0047] S200: constructing an InSAR deformation zone detection network with multi-channel input; using the detection network to perform feature extraction and predictive segmentation on the first three band channel data of the multi-source fusion data to obtain a first two-classification map.

[0048] Combination Figure 2 As shown in Tables 1 and 2, the encoding part of the detection network includes the backbone network mobilenetv2 part structure, the hole convolution ASPP module, the 1X1 convolution module and the upsampling module; the decoding part of the detection network includes the fusion module, the 3X3 convolution module and the 1X1 convolution module. Among them, the 1X1 convolution module is Conv2d 1×1, the 3X3 convolution module is Conv2d 3×3, and the upsampling module is the F.interpolate function.

[0049] The encoding part of the detection network extracts deep semantic features from the first three band channel data of the multi-source fusion data; the decoding part of the detection network performs 1×1 convolution on the shallow semantic features obtained by the backbone network mobilenetv2, and then fuses them with the deep semantic features obtained by the encoding part, and then outputs abstract semantic features through two 3×3 convolution operations, further predicts and segments the InSAR deformation area, and obtains the first two classification maps. In the embodiment of the present application, only part of the structure of the original mobilenetv2 network is used in the process of extracting deep and shallow semantic features, as shown in Table 1.

[0050] Table 1. Some structural parameters of the MobileNetV2 backbone network

[0051]

[0052]

[0053] ASPP is a technology used for image processing, and its full name is Atrous Spatial Pyramid Pooling, which combines dilated convolution and spatial pyramid pooling. The ASPP structural parameters in the embodiment of the present application are shown in Table 2.

[0054] Table 2 Left-side coded ASPP structural parameters

[0055]

[0056] S300: Assigning a projection coordinate system and performing raster vectorization processing on the first binary classification map to obtain a first deformation area vector layer and determine the boundary of the Class I InSAR deformation area.

[0057] In an embodiment of the present application, the boundary of the type I InSAR deformation zone includes a landslide deformation zone on a slope, a mining collapse deformation zone on a slope, a settlement deformation zone in a plain area, and a glacier deformation zone.

[0058] S400: Using the detection network to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; assigning a projection coordinate system and raster vectorization to the second binary classification map to obtain a second deformation zone vector layer, and determine the boundary of the Class II InSAR deformation zone.

[0059] In the embodiment of the present application, the boundary of the Class II InSAR deformation zone includes the landslide deformation zone on the slope, the mining collapse deformation zone on the slope and the glacier deformation zone. The terrain features introduced by this step remove the settlement deformation zone in the plain area.

[0060] S500: Add the sample data of the mining subsidence deformation zone on the slope as a negative sample; repeat S400 for training and prediction to obtain a third two-classification map; assign the projection coordinate system and raster vectorization to the third two-classification map to obtain a third deformation zone vector layer, and determine the Class III InSAR deformation zone boundary. In the embodiment of the present application, this step uses the same network as S400 for training and prediction. This step enhances the knowledge of negative samples, optimizes the sampling ratio of positive and negative samples, removes the mining subsidence deformation zone on the slope, and the Class III InSAR deformation zone boundary includes the landslide deformation zone and the glacier deformation zone on the slope. Figure 3 Sample data of a mining collapse deformation zone on a slope according to an embodiment of the present application is shown. The data is a deformation phase map caused by mining collapse obtained after processing InSAR data, which serves as a negative sample.

[0061] S600: Perform a geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, and determine that the vector layer that overlaps with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest is the landslide deformation zone on the slope. In the embodiment of the present application, the glacier contour vector layer within the study area is obtained using the complete catalog vector layer of global glacier contours published by GLIMS.

[0062] S700: Performing a geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in S600 and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope.

[0063] S800: Performing a geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in S600, and the mining subsidence deformation zone boundary on the slope determined in S700 and the Class I InSAR deformation zone boundary to determine the settlement deformation zone in the plain area.

[0064] In the embodiment of the present application, the InSAR deformation types can be quickly distinguished through the above multi-level step constraints.

[0065] The method embodiments provided in the embodiments of the present application can be executed in electronic devices such as mobile terminals, computer terminals, servers or similar computing devices.

[0066] The above embodiments have introduced in detail the InSAR deformation type differentiation method with multi-level constraints. The implementation of the embodiments of the present application has the following beneficial effects:

[0067] Based on the multi-period InSAR annual average deformation phase map, the deep learning method is used to gradually distinguish the types of InSAR deformation zones based on the different spatial distribution characteristics of landslides, mining collapses, subsidence, and glacier deformations, combined with multi-level constraints; the distribution positions of InSAR deformation zone types at the regional scale are obtained, and InSAR deformation derivative products are obtained to provide basic data for geological disaster monitoring and early warning, and management decision-making. The method provided by the present invention is suitable for deformation monitoring applications in a wide range of research areas, greatly improves the computational efficiency and response speed, and has a high degree of automated classification and detection.

[0068] The present application also provides a multi-level constrained InSAR deformation type differentiation system 10. For details, please refer to Figure 4 , the system 10 includes: a data acquisition module 100, a data processing module 200, and a layer analysis module 300;

[0069] The data acquisition module 100 is used to: obtain the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data;

[0070] The data processing module 200 is used to: construct an InSAR deformation zone detection network with multi-channel input; use the detection network to perform feature extraction and prediction segmentation on the first three band channel data of the multi-source fusion data to obtain a first two-classification map;

[0071] Assigning a projection coordinate system and performing raster vectorization processing on the first two classification maps to obtain a first deformation area vector layer and determine the boundary of the type I InSAR deformation area;

[0072] The detection network is used to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; the second binary classification map is assigned a projection coordinate system and rasterized to obtain a second deformation area vector layer, and the boundary of the Class II InSAR deformation area is determined;

[0073] Adding sample data of mining subsidence deformation zone on the slope as negative samples; repeating training and prediction to obtain a third binary classification map; assigning a projection coordinate system and performing raster vectorization processing on the third binary classification map to obtain a third deformation zone vector layer, and determining the boundary of the Class III InSAR deformation zone;

[0074] The layer analysis module 300 is used to perform geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, and determine that the vector layer overlapping with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest are landslide deformation zones on the slope.

[0075] Performing a geographic information system spatial overlay analysis on the determined landslide deformation zone boundary and glacier deformation zone boundary on the slope and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope;

[0076] The determined landslide deformation zone boundaries and glacier deformation zone boundaries on the slope, the mining subsidence deformation zone boundaries on the slope and the Class I InSAR deformation zone boundaries are subjected to geographic information system spatial overlay analysis to determine the settlement deformation zone in the plain area.

[0077] In the embodiment of the present application, the data acquisition module 100, the data processing module 200, and the layer analysis module 300 can also be used for more specific processing operations corresponding to the steps of the above method.

[0078] The embodiment of the present application also provides a multi-level constrained InSAR deformation type differentiation device, including a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or at least one program is loaded and executed by the processor to implement the multi-level constrained InSAR deformation type differentiation method as described above. Among them, the memory can be used to store software programs and modules, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory. In addition, the memory may include a high-speed random access memory and may also include a non-volatile memory. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory. Optionally, the device may also include one or more CPUs or multiple GPUs, one or more power supplies, one or more wired or wireless network interfaces, one or more input and output interfaces 940, and / or, one or more operating systems, and the like.

[0079] An embodiment of the present application also provides a storage medium, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the multi-level constrained InSAR deformation type differentiation method as described above.

[0080] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A multi-level constrained InSAR deformation type differentiation method, characterized in that: The method comprises: Step 1: Acquire the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data; Step 2: constructing a multi-channel input InSAR deformation zone detection network; using the detection network to perform feature extraction and prediction segmentation on the first three band channel data of the multi-source fusion data to obtain the first two classification maps; Step 3: assigning a projection coordinate system to the first two-classification map and performing raster vectorization processing to obtain a first deformation area vector layer and determine the boundary of the Class I InSAR deformation area; Step 4: Using the detection network to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; assigning a projection coordinate system and performing raster vectorization processing on the second binary classification map to obtain a second deformation area vector layer, and determine the boundary of the Class II InSAR deformation area; Step 5: Add the sample data of the mining subsidence deformation zone on the slope as a negative sample; repeat step 4 for training and prediction to obtain a third binary classification map; assign a projection coordinate system and perform raster vectorization processing on the third binary classification map to obtain a third deformation zone vector layer, and determine the boundary of the Class III InSAR deformation zone; Step 6: Performing a geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, determining that the vector layer that overlaps with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest is the landslide deformation zone on the slope; Step 7: Performing a geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in step 6 and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope; Step 8: Perform geographic information system spatial overlay analysis on the landslide deformation zone boundary and the glacier deformation zone boundary on the slope determined in step 6, the mining subsidence deformation zone boundary on the slope determined in step 7, and the Class I InSAR deformation zone boundary to determine the settlement deformation zone in the plain area.

2. The method according to claim 1, characterized in that The acquisition of InSAR annual average deformation phase data and slope data within the study area includes: The InSAR annual average deformation phase data in the study area were obtained using multi-period InSAR data. The corresponding DEM data is obtained by cropping the range of each InSAR annual average deformation phase data, and the slope data is calculated.

3. The method according to claim 1, characterized in that The first three band channel data of the four-band channel data are multi-period InSAR annual average deformation phase data, and the fourth band channel data are slope data.

4. The method according to claim 1, characterized in that: in, The encoding part of the detection network includes a backbone network mobi lenetv2 partial structure, a hole convolution ASPP module, a 1X1 convolution module and an upsampling module; the decoding part of the detection network includes a fusion module, a 3X3 convolution module and a 1X1 convolution module.

5. The method according to claim 4, characterized in that The encoding part of the detection network extracts deep semantic features from the first three band channel data of the multi-source fusion data; the decoding part of the detection network performs 1×1 convolution on the shallow semantic features obtained by the backbone network mobi lenetv2, and then fuses them with the deep semantic features obtained by the encoding part, and then outputs abstract semantic features through two 3×3 convolution operations, further predicts and segments the InSAR deformation area, and obtains the first two classification maps.

6. The method according to claim 1, characterized in that The boundaries of the Type I InSAR deformation zones include the landslide deformation zone on the slope, the mining collapse deformation zone on the slope, the settlement deformation zone in the plain area and the glacier deformation zone; the boundaries of the Type II InSAR deformation zones include the landslide deformation zone on the slope, the mining collapse deformation zone on the slope and the glacier deformation zone; the boundaries of the Type III InSAR deformation zones include the landslide deformation zone on the slope and the glacier deformation zone.

7. The method according to claim 1, characterized in that The glacier outline vector layer within the study area is obtained using the complete catalog vector layer of global glacier outlines released by GLIMS.

8. A multi-level constrained InSAR deformation type differentiation system, characterized in that: The system includes: a data acquisition module, a data processing module, and a layer analysis module; The data acquisition module is used to: obtain the InSAR annual average deformation phase data and slope data within the study area; perform band synthesis on the InSAR annual average deformation phase data and slope data to generate multi-source fusion data; wherein the multi-source fusion data is four-band channel data; The data processing module is used to: construct an InSAR deformation zone detection network with multi-channel input; use the detection network to perform feature extraction and prediction segmentation on the first three band channel data of the multi-source fusion data to obtain a first two-classification map; Assigning a projection coordinate system and performing raster vectorization processing on the first two classification maps to obtain a first deformation area vector layer and determine the boundary of the type I InSAR deformation area; The detection network is used to train and predict the four band channel data of the multi-source fusion data to obtain a second binary classification map; the second binary classification map is assigned a projection coordinate system and rasterized to obtain a second deformation area vector layer, and the boundary of the Class II InSAR deformation area is determined; Adding sample data of mining subsidence deformation zone on the slope as negative samples; repeating training and prediction to obtain a third binary classification map; assigning a projection coordinate system and performing raster vectorization processing on the third binary classification map to obtain a third deformation zone vector layer, and determining the boundary of the Class III InSAR deformation zone; The layer analysis module is used to perform geographic information system spatial overlay analysis on the boundary of the Class III InSAR deformation zone and the glacier contour vector layer within the study area, and determine that the vector layer overlapping with the glacier contour vector layer within the study area is the glacier deformation zone, and the rest are landslide deformation zones on the slope. Performing a geographic information system spatial overlay analysis on the determined landslide deformation zone boundary and glacier deformation zone boundary on the slope and the Class II InSAR deformation zone boundary to determine the mining subsidence deformation zone on the slope; The determined landslide deformation zone boundaries and glacier deformation zone boundaries on the slope, the mining subsidence deformation zone boundaries on the slope and the Class I InSAR deformation zone boundaries are subjected to geographic information system spatial overlay analysis to determine the settlement deformation zone in the plain area.

9. A multi-level constrained InSAR deformation type differentiation device, characterized in that: The invention comprises a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or at least one program is loaded and executed by the processor to implement the multi-level constrained InSAR deformation type differentiation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by the processor to implement the multi-level constrained InSAR deformation type differentiation method as described in any one of claims 1 to 7.

Images