A landslide dynamic surface displacement prediction and analysis method and system

By combining satellite remote sensing and ground monitoring sensors for dynamic monitoring and comprehensive timing analysis of landslide areas, the problem of insufficient monitoring of landslide dynamic changes in the existing technology is solved, accurate assessment and timely early warning of landslide trends are achieved, and landslide disaster prevention is improved effect.

CN118887560BActive Publication Date: 2024-12-03CHENGDU TECH UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411375770.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-30
Publication Date
2024-12-03
Estimated Expiration
2044-09-30

AI Technical Summary

Technical Problem

The existing landslide monitoring technology cannot achieve accurate monitoring and early warning of landslide dynamic changes. It relies too much on data at a single time point, lacks systematic evaluation of timing changes, and the early warning model cannot be dynamically adjusted to adapt to complex environmental changes.

Method used

By combining satellite remote sensing and ground monitoring sensors, an image data set and displacement data set are constructed, and time series period labels are attached to calculate the rate of change of image data and displacement data, comprehensive timing analysis is carried out, weights are dynamically adjusted, and the overall trend of landslide areas is predicted. And issue an early warning.

Benefits of technology

It has achieved comprehensive dynamic monitoring of landslide areas, improved the accuracy of landslide trend assessment and timely warning, and enhanced the stability of disaster prevention and risk control.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118887560B_ABST
    Figure CN118887560B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for predicting and analyzing dynamic surface displacement of landslide, which relates to the technical field of surface displacement prediction and analysis; including: constructing a remote sensing image data set; constructing a ground monitoring sensor set; collecting displacement data monitored by the ground monitoring sensor; constructing remote sensing image periodic data and displacement periodic data; calculating the change rate of remote sensing image periodic data of the landslide area at different time points; calculating the change rate of displacement periodic data of the landslide area at different time points; calculating the comprehensive time series analysis results of the landslide area at different time points; calculating the overall trend evaluation value of different landslide areas at different time points; predicting and outputting warnings. The present invention calculates the change rate of image data and displacement data, and performs comprehensive time series analysis, accurately evaluates the landslide trend, divides the risk level according to the set threshold, and issues a warning in time; and enhances the accuracy and stability of the prediction.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of surface displacement prediction and analysis, in particular to a method and system for predicting and analyzing dynamic surface displacement of a landslide. Background Art

[0002] As a common geological disaster, landslides have received widespread attention in recent years. With the global climate change and the intensification of human engineering activities, the frequency and intensity of landslides have gradually increased, posing a serious threat to human life and property safety. For this reason, landslide monitoring and prediction technology has gradually become a research hotspot. Traditional landslide monitoring methods mainly rely on ground observations and historical experience, such as assessing landslide risks by measuring physical phenomena such as surface displacement and crack expansion. However, these methods usually have shortcomings such as limited monitoring range and delayed warning time, and cannot achieve accurate monitoring and early warning of dynamic changes of landslides over a large area and over multiple periods. In recent years, the rapid development of satellite remote sensing technology has provided new technical means for landslide monitoring. Remote sensing images can obtain surface information over a large area and without contact, and combined with ground monitoring data, can provide a more comprehensive perspective for landslide monitoring. However, most of the current related research is limited to static monitoring, lacks comprehensive time series analysis of the dynamic evolution of landslides, and cannot effectively predict the future trend of landslides.

[0003] The existing landslide monitoring technology still has many deficiencies. For example, in dynamic landslide prediction, it relies too much on data from a single time point and lacks a systematic evaluation of the temporal variation patterns of the landslide process, resulting in low accuracy in landslide risk assessment. In addition, most of the existing landslide early warning systems rely on fixed threshold judgments, ignoring the complex environmental changes in the landslide area and unable to dynamically adjust the early warning model. With the deepening of the understanding of landslide hazards, landslide monitoring technology urgently needs to move from static to dynamic, from local to global, and conduct a more comprehensive analysis and prediction of the overall trend of the landslide area. Summary of the invention

[0004] In view of the problems existing in the existing surface displacement prediction and analysis, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to predict and analyze ground surface displacement.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for predicting and analyzing dynamic surface displacement of a landslide, which includes: using satellite remote sensing to collect image data of a landslide area and constructing a remote sensing image data set; deploying ground monitoring sensors in the landslide area and constructing a ground monitoring sensor set; collecting displacement data monitored by the ground monitoring sensors; constructing a time series, and adding time series period labels to the remote sensing image data set and the displacement data set, which are recorded as remote sensing image period data and displacement period data, respectively; based on the remote sensing image period data, calculating the change rate of the remote sensing image period data of the landslide area at different time points; based on the displacement period data, calculating the change rate of the displacement period data of the landslide area at different time points; based on the remote sensing image period data change rate and the displacement period data change rate, calculating the comprehensive time series analysis results of the landslide area at different time points; based on the comprehensive time series analysis results, calculating the overall trend evaluation values ​​of different landslide areas at different time points; predicting and outputting warnings.

[0008] As a preferred solution of the landslide dynamic surface displacement prediction and analysis method described in the present invention, a landslide area database is constructed, denoted as ,in, represents the i-th landslide area, I represents the total number of landslide areas; the landslide area is collected using satellite remote sensing Image data, construct remote sensing image dataset, denoted as ,in, Indicates landslide area remote sensing image data; the landslide area represents an area with potential landslide risk in the geological environment.

[0009] In the landslide area Ground monitoring sensors are deployed in each landslide area, and a ground monitoring sensor is deployed in each landslide area to build a ground monitoring sensor set. ,in, Indicates landslide area The ground monitoring sensor is used to collect displacement data of the ground surface.

[0010] As a preferred solution of the method for predicting and analyzing the dynamic surface displacement of a landslide described in the present invention, the displacement data monitored by the ground monitoring sensor is collected to construct a displacement data set, which is recorded as ,in, Indicates landslide area The displacement data collected by the ground monitoring sensors in the area are used to construct a time series in units of days, which is recorded as ,in, represents the y-th time point, and Y represents the total number of time points.

[0011] Based on the time series, time series period labels are added to the remote sensing image dataset and the displacement dataset, and are respectively recorded as remote sensing image period data. and displacement cycle data , the remote sensing image period data represents the landslide area at time point y Remote sensing image data, the displacement cycle data represents the landslide area at time point y Displacement data collected by ground monitoring sensors.

[0012] As a preferred solution of the method for predicting and analyzing the dynamic surface displacement of a landslide described in the present invention, based on the remote sensing image periodic data , calculate the landslide area at different time points The calculation formula for the change rate of remote sensing image periodic data is as follows:

[0013]

[0014] in, Indicates the landslide area at different time points The change rate of remote sensing image periodic data, Indicates at a point in time Landslide area remote sensing image data.

[0015] Based on the displacement cycle data , calculate the landslide area at different time points The displacement period data change rate is calculated as follows:

[0016]

[0017] in, Indicates the landslide area at different time points The displacement period data change rate, Indicates at a point in time Landslide area The displacement data collected by the ground monitoring sensors, Indicates the preset weight.

[0018] Based on the remote sensing image periodic data change rate and the displacement cycle data change rate , calculate the landslide area at different time points The comprehensive timing analysis results are calculated as follows:

[0019]

[0020] in, Indicates the landslide area at different time points The comprehensive timing analysis results of and Represents the weight of remote sensing image data and displacement data, where and is a dynamic weight.

[0021] As a preferred solution of the landslide dynamic surface displacement prediction and analysis method of the present invention, the dynamic weight adjustment process includes:

[0022] According to historical data analysis and The initial value of

[0023] For each time point , calculate the weight adjustment factor:

[0024]

[0025]

[0026] in, and Respectively represent remote sensing data and displacement data at time points The adjustment factor, For at time point , quality indicators of remote sensing image data, Indicates at a point in time Quality indicators of displacement data collected by ground monitoring sensors, For at time point , the correlation between remote sensing image data and the current assessment time point, For at time point ,The correlation degree between the displacement data collected by the ground monitoring sensor and the current evaluation time point; For at time point The error index of prediction based on historical remote sensing image data, For at time point Error indicators predicted based on historical ground monitoring sensor displacement data; based on the calculated weight adjustment factors, update the values ​​of α and β:

[0027]

[0028]

[0029] in, is the learning rate, and Indicates time The weight value when ; and Represents the updated weight value.

[0030] As a preferred solution of the method for predicting and analyzing the dynamic surface displacement of a landslide according to the present invention, based on the landslide area at different time points Comprehensive timing analysis results of , calculate the overall trend assessment value of different landslide areas at different time points, the calculation formula is as follows:

[0031]

[0032] in, Represents the overall trend assessment value of different landslide areas at different time points.

[0033] Preset trend thresholds ,like The landslide area is predicted If the surface displacement trend is low, no warning will be issued; , then the landslide area is predicted If the surface displacement trend is moderate, a Level 2 warning will be issued; , then the landslide area is predicted The surface displacement trend is high, and a level one warning is issued.

[0034] In a second aspect, an embodiment of the present invention provides a landslide dynamic surface displacement prediction and analysis system, which includes: a landslide area database construction and monitoring deployment module, which uses satellite remote sensing to collect image data of the landslide area and constructs a remote sensing image data set; deploys ground monitoring sensors in the landslide area to construct a ground monitoring sensor set; a data acquisition and time series labeling module, which collects displacement data monitored by the ground monitoring sensors; constructs a time series, and adds time series period labels to the remote sensing image data set and the displacement data set, which are recorded as remote sensing image period data and displacement period data, respectively; a time series data change rate and comprehensive analysis module, which calculates the remote sensing image period data change rate of the landslide area at different time points based on the remote sensing image period data; calculates the displacement period data change rate of the landslide area at different time points based on the displacement period data; calculates the comprehensive time series analysis results of the landslide area at different time points based on the remote sensing image period data change rate and the displacement period data change rate; a trend evaluation and warning triggering module, which calculates the overall trend evaluation value of different landslide areas at different time points based on the comprehensive time series analysis results; predicts and outputs warnings.

[0035] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of a method for predicting and analyzing dynamic surface displacement of a landslide as described in the first aspect of the present invention are implemented.

[0036] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of a method for predicting and analyzing dynamic surface displacement of a landslide as described in the first aspect of the present invention are implemented.

[0037] The beneficial effects of the present invention are as follows: by combining satellite remote sensing and ground monitoring sensors, image data and surface displacement data of the landslide area are collected, and time series labels are added to these data to achieve all-round and dynamic monitoring of the landslide area; by calculating the change rates of image data and displacement data, and performing comprehensive time series analysis based on these change rates, the method can accurately evaluate the landslide trend, and classify the risk level according to the set threshold value, and issue early warnings; the fusion analysis of multi-source data makes up for the shortcomings of a single data source, enhances the accuracy and stability of the prediction, ensures the early prevention and risk control of landslide disasters, and has extremely high practical value and innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 It is a schematic diagram of the steps of a method for predicting and analyzing dynamic surface displacement of landslides according to the present invention;

[0040] Figure 2 The present invention is a structural schematic diagram of a landslide dynamic surface displacement prediction and analysis system. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] Example 1

[0045] See also Figure 1 In this embodiment, a method for predicting and analyzing dynamic surface displacement of a landslide is provided, and the method comprises the following steps:

[0046] S1: Use satellite remote sensing to collect image data of the landslide area and construct a remote sensing image dataset; deploy ground monitoring sensors in the landslide area and construct a ground monitoring sensor set.

[0047] Specifically, a landslide area database is constructed, denoted as ,in, represents the i-th landslide area, I represents the total number of landslide areas; the landslide area is collected using satellite remote sensing Image data, construct remote sensing image dataset, denoted as ,in, Indicates landslide area remote sensing image data; the landslide area represents an area with potential landslide risk in the geological environment.

[0048] Furthermore, in the landslide area Ground monitoring sensors are deployed in each landslide area, and a ground monitoring sensor is deployed in each landslide area to build a ground monitoring sensor set. ,in, Indicates landslide area The ground monitoring sensor is used to collect displacement data of the ground surface.

[0049] S2: Collect displacement data monitored by ground monitoring sensors; construct a time series, and add time series period labels to the remote sensing image dataset and the displacement dataset, which are recorded as remote sensing image period data and displacement period data, respectively.

[0050] Specifically, the displacement data monitored by the ground monitoring sensor is collected to construct a displacement data set, which is recorded as ,in, Indicates landslide area The displacement data collected by the ground monitoring sensors in the area are used to construct a time series in units of days, which is recorded as ,in, represents the y-th time point, and Y represents the total number of time points.

[0051] Furthermore, based on the time series, time series period labels are added to the remote sensing image dataset and the displacement dataset, and are recorded as remote sensing image period data and displacement data, respectively. and displacement cycle data , the remote sensing image period data represents the landslide area at time point y Remote sensing image data, the displacement cycle data represents the landslide area at time point y Displacement data collected by ground monitoring sensors.

[0052] S3: Based on the remote sensing image periodic data, calculate the change rate of the remote sensing image periodic data of the landslide area at different time points; based on the displacement periodic data, calculate the change rate of the displacement periodic data of the landslide area at different time points; based on the change rate of the remote sensing image periodic data and the change rate of the displacement periodic data, calculate the comprehensive time series analysis results of the landslide area at different time points.

[0053] Specifically, based on the remote sensing image periodic data , calculate the landslide area at different time points The calculation formula for the change rate of remote sensing image periodic data is as follows:

[0054]

[0055] in, Indicates the landslide area at different time points The change rate of remote sensing image periodic data, Indicates at a point in time Landslide area remote sensing image data.

[0056] In the present invention, the formula analyzes the change trend by calculating the difference of remote sensing image data at consecutive time points in the landslide area. Specifically, it calculates the change of image data at each time point relative to the previous time point, and then sums up these changes. This differential analysis can reveal the change of remote sensing image data over time, thereby reflecting the change pattern of the landslide area.

[0057] Further, based on the displacement cycle data , calculate the landslide area at different time points The displacement period data change rate is calculated as follows:

[0058]

[0059] in, Indicates the landslide area at different time points The displacement period data change rate, Indicates at a point in time Landslide area The displacement data collected by the ground monitoring sensors, Indicates the preset weight.

[0060] In the present invention, It's time point The weight of , different weights can be assigned to different time points according to the time distance, and the data closer to the current time has a greater weight; Represents the cumulative change of displacement data; this formula reflects the cumulative deviation of displacement data and is suitable for analyzing the evolution of gradual surface displacement.

[0061] Furthermore, based on the remote sensing image periodic data change rate and the displacement cycle data change rate , calculate the landslide area at different time points The comprehensive timing analysis results are calculated as follows:

[0062]

[0063] in, Indicates the landslide area at different time points The comprehensive timing analysis results of and Represents the weight of remote sensing image data and displacement data, where and is a dynamic weight.

[0064] Furthermore, and The dynamic weight adjustment mechanism is as follows:

[0065] According to historical data analysis and The initial value of

[0066] Quantified according to the following indicators and The degree of adjustment required: data quality indicator DQ, time correlation indicator TC, prediction error indicator PE, the specific operations are as follows:

[0067] For each time point , calculate the weight adjustment factor:

[0068]

[0069]

[0070] in, and Respectively represent remote sensing data and displacement data at time points The adjustment factor, For at time point , quality indicators of remote sensing image data, Indicates at a point in time Quality indicators of displacement data collected by ground monitoring sensors, For at time point , the correlation between remote sensing image data and the current assessment time point, For at time point ,The correlation degree between the displacement data collected by the ground monitoring sensor and the current evaluation time point; For at time point The error index of prediction based on historical remote sensing image data, For at time point Error metrics for predictions based on historical ground monitoring sensor displacement data.

[0071] Based on the calculated weight adjustment factors, update the values ​​of α and β:

[0072]

[0073]

[0074] in, is the learning rate, which controls the speed of weight adjustment and is usually set to a small value such as 0.1; and Indicates time The weight value when ; and Represents the updated weight value.

[0075] To ensure that the weights are always within a valid range, the following constraints are applied:

[0076]

[0077]

[0078] Optionally, in order to avoid drastic fluctuations in weights, a moving average smoothing process may be introduced.

[0079] Integrate the dynamically adjusted smoothing weights into the original comprehensive timing analysis result calculation formula to obtain a new comprehensive timing analysis result. , and evaluate the effectiveness of the dynamic weight adjustment mechanism at regular intervals (such as monthly or quarterly):

[0080]

[0081] in, is the actual observed surface displacement.

[0082] If the average performance of M consecutive cycles is lower than the preset threshold , then consider resetting the weights.

[0083] In the present invention, the formula converts the remote sensing image period data change rate into and the displacement cycle data change rate Fusion is performed by weighted averaging; and It is the weight of dynamic remote sensing image data and displacement data, indicating the contribution of remote sensing image data and displacement data to the comprehensive analysis results. It can comprehensively consider the impact of remote sensing data and displacement data on changes in landslide areas, thereby providing a more comprehensive dynamic assessment of landslides.

[0084] S4: Based on the comprehensive time series analysis results, calculate the overall trend assessment values ​​of different landslide areas at different time points; predict and output warnings.

[0085] Specifically, based on the landslide area at different time points Comprehensive timing analysis results of , calculate the overall trend assessment value of different landslide areas at different time points, the calculation formula is as follows:

[0086]

[0087] in, Represents the overall trend assessment value of different landslide areas at different time points.

[0088] Furthermore, a preset trend threshold ,like The landslide area is predicted If the surface displacement trend is low, no warning will be issued; , then the landslide area is predicted If the surface displacement trend is moderate, a Level 2 warning will be issued; , then the landslide area is predicted The surface displacement trend is high, and a level one warning is issued.

[0089] In the present invention, the formula for the overall trend evaluation value is to calculate the comprehensive time series analysis results of all landslide areas By averaging the comprehensive analysis results of each landslide area, an overall trend assessment of all landslide areas can be obtained; by summarizing the comprehensive analysis results of each landslide area, a macro-assessment of the overall landslide activity is provided, and the dynamic characteristics of different landslide areas can be compared to identify areas with significant changes or potential dangers.

[0090] Example 2

[0091] See also Figure 2 In this embodiment, a landslide dynamic surface displacement prediction and analysis system is provided, which includes: a landslide area database construction and monitoring deployment module, which uses satellite remote sensing to collect image data of the landslide area and construct a remote sensing image data set; deploys ground monitoring sensors in the landslide area to construct a ground monitoring sensor set; a data acquisition and time series labeling module, which collects displacement data monitored by the ground monitoring sensors; constructs a time series, and adds time series period labels to the remote sensing image data set and the displacement data set, which are recorded as remote sensing image period data and displacement period data respectively; a time series data change rate and comprehensive analysis module, which calculates the remote sensing image period data change rate of the landslide area at different time points based on the remote sensing image period data; calculates the displacement period data change rate of the landslide area at different time points based on the displacement period data; calculates the comprehensive time series analysis results of the landslide area at different time points based on the remote sensing image period data change rate and the displacement period data change rate; a trend evaluation and warning triggering module, which calculates the overall trend evaluation value of different landslide areas at different time points based on the comprehensive time series analysis results; and predicts and outputs warnings.

[0092] This embodiment also provides a computer device, which is applicable to a method for predicting and analyzing dynamic surface displacement of landslides, and includes a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a method for predicting and analyzing dynamic surface displacement of landslides as proposed in the above embodiment.

[0093] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0094] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a method for predicting and analyzing the dynamic surface displacement of a landslide as proposed in the above embodiment is implemented.

[0095] In summary, the present invention collects image data and surface displacement data of the landslide area by combining satellite remote sensing and ground monitoring sensors, and adds time series labels to these data, thereby realizing all-round and dynamic monitoring of the landslide area; by calculating the change rates of image data and displacement data, and performing comprehensive time series analysis based on these change rates, the method can accurately evaluate the landslide trend, and classify the risk level according to the set threshold value, and issue early warning; the fusion analysis of multi-source data makes up for the shortcomings of a single data source, enhances the accuracy and stability of the prediction, ensures the early prevention and risk control of landslide disasters, and has extremely high practical value and innovation.

[0096] Example 3

[0097] Referring to Table 1, which is the third embodiment of the present invention, this embodiment provides a method for predicting and analyzing dynamic surface displacement of landslides. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0098] In a high-risk landslide zone in a certain mountainous area, researchers selected six typical landslide-prone areas for a 180-day dynamic surface displacement monitoring and predictive analysis. These areas are located in different geological environments, including ridges, foothills and river valleys, with different geological characteristics and landslide risks.

[0099] First, the research team used high-resolution optical satellites and SAR satellites to collect remote sensing images of the six selected landslide areas for 180 consecutive days and built a complete remote sensing image data set. At the same time, high-precision GNSS receivers were installed at key locations in each landslide area as ground monitoring sensors to collect surface displacement data in real time. These sensors use RTK technology and can provide millimeter-level displacement accuracy.

[0100] To ensure the accuracy and reliability of the data, the research team used multi-source data fusion technology. Remote sensing image data was processed through multi-temporal image comparison and InSAR technology to extract surface deformation information. The data from ground monitoring sensors was optimized through real-time kinematic post-processing technology to eliminate errors such as atmospheric delay.

[0101] During the data collection process, the researchers noticed that the rate of surface deformation in some areas increased significantly during the rainy season.

[0102] In order to better capture this seasonal change, the team optimized the time series construction and adopted the adaptive time window technology, shortening the sampling interval during the period of faster deformation rate and appropriately extending the sampling interval during the relatively stable period. This method not only ensures the intensive collection of data in the key period, but also avoids data redundancy.

[0103] When calculating the rate of change of periodic data of remote sensing images, the research team introduced a multi-scale analysis method, which not only considered the changes in adjacent time points, but also introduced long-term trend analysis. By taking a weighted average of the change rates at different time scales, a more robust estimate of the change rate was obtained. This method effectively reduced the impact of short-term noise and improved the reliability of the changing trend.

[0104] For the calculation of the rate of change of displacement periodic data, the researchers innovatively adopted an adaptive weight method, dynamically adjusting the weights of different time points according to the change pattern of historical data. During periods of accelerated displacement, the weights of previous data with a higher proportion will be automatically increased to more keenly capture potential landslide risks.

[0105] In the calculation of the comprehensive time series analysis results, the research team introduced a nonlinear fusion model. They found that the reliability of remote sensing image data and displacement data varies in different situations. Therefore, a dynamic weight allocation mechanism based on data quality was designed. When the remote sensing image is greatly affected by clouds and fog, the system will automatically reduce its weight; when the ground sensor data fluctuates abnormally, the system will also adjust its weight accordingly. This method greatly improves the stability and reliability of the comprehensive analysis results.

[0106] Finally, when calculating the overall trend assessment value, the researchers took into account the nonlinear characteristics of landslide occurrence and introduced an exponential growth model, which accelerated the growth rate of the assessment value when approaching a critical state. This method can identify potential landslide risks more promptly and provide a more reliable decision-making basis for the early warning system.

[0107] The following are some key data from the six landslide areas during the 180-day monitoring period (sampling was done every 30 days):

[0108] Table 1

[0109]

[0110] Through the analysis of the above monitoring data, it can be seen that, taking the ridge area A as an example, its remote sensing image change rate gradually increased from 0.15% at 30 days to 1.05% at 180 days, an increase of 7 times, and the displacement change rate increased from 0.8 mm / day to 6.5 mm / day, an increase of 8.125 times. This acceleration trend fully reflects the advantage of the method of the present invention in capturing the dynamic evolution of landslides; and by comparing the remote sensing image change rate and the displacement change rate, it can be seen that the two show a good correlation, but not completely consistent.

[0111] In addition, data shows that all areas have experienced a process from no warning to level 2 warning, and then to level 1 warning. This progressive warning mechanism reduces the false alarm rate and ensures the timeliness of risk identification.

[0112] It can be seen that the present invention can not only identify potential risks at an early stage, but also provide detailed risk level classification, providing strong support for disaster prevention and mitigation decision-making.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A landslide dynamic surface displacement prediction and analysis method, Features: include: S1: Use satellite remote sensing to collect image data of the landslide area and construct a remote sensing image dataset; deploy ground monitoring sensors in the landslide area and construct a ground monitoring sensor set; S2: Collect displacement data monitored by ground monitoring sensors; construct time series, and add time series period labels to the remote sensing image dataset and displacement dataset, which are recorded as remote sensing image period data and displacement period data respectively; S3: Based on the remote sensing image periodic data, calculate the change rate of the remote sensing image periodic data of the landslide area at different time points; based on the displacement periodic data, calculate the change rate of the displacement periodic data of the landslide area at different time points; based on the change rate of the remote sensing image periodic data and the change rate of the displacement periodic data, calculate the comprehensive time series analysis results of the landslide area at different time points; S4: Based on the comprehensive time series analysis results, calculate the overall trend assessment values ​​of different landslide areas at different time points; Predict and output warnings; The S3 includes: Based on the remote sensing image periodic data , calculate the landslide area at different time points The calculation formula for the change rate of remote sensing image periodic data is as follows: ; in, Indicates the landslide area at different time points The change rate of remote sensing image periodic data, Indicates at a point in time Landslide area Remote sensing image data, represents the i-th landslide area, Indicates landslide area Remote sensing image data, represents the yth time point, Y represents the total number of time points, Indicates at a point in time Landslide area Remote sensing image data; Based on the displacement cycle data , calculate the landslide area at different time points The displacement period data change rate is calculated as follows: ; in, Indicates the landslide area at different time points The displacement period data change rate, Indicates at a point in time Landslide area The displacement data collected by the ground monitoring sensors, represents the preset weight, Indicates landslide area The displacement data collected by the ground monitoring sensors in represents the yth time point, Y represents the total number of time points, Indicates at a point in time Landslide area Displacement data collected by ground monitoring sensors; Based on the remote sensing image periodic data change rate and the displacement cycle data change rate , calculate the landslide area at different time points The comprehensive timing analysis results are calculated as follows: ; in, Indicates the landslide area at different time points The comprehensive timing analysis results of and Represents the weight of remote sensing image data and displacement data, where and is the dynamic weight; The dynamic weight adjustment process includes the following: According to historical data analysis and The initial value of For each time point , calculate the weight adjustment factor: ; ; in, and Respectively represent remote sensing data and displacement data at time points The adjustment factor, For at time point , quality indicators of remote sensing image data, Indicates at a point in time Quality indicators of displacement data collected by ground monitoring sensors, For at time point , the correlation between remote sensing image data and the current assessment time point, For at time point ,The correlation degree between the displacement data collected by the ground monitoring sensor and the current evaluation time point; For at time point The error index of prediction based on historical remote sensing image data, For at time point Error indicators for prediction based on historical ground monitoring sensor displacement data; Based on the calculated weight adjustment factors, update the values ​​of α and β: ; ; in, is the learning rate, and Indicates time The weight value when ; and Represents the updated weight value; The S4 includes: Based on the landslide area at different time points Comprehensive timing analysis results of , calculate the overall trend assessment value of different landslide areas at different time points, the calculation formula is as follows: ; in, represents the overall trend assessment value of different landslide areas at different time points, and I represents the total number of landslide areas; Preset trend thresholds ,like The landslide area is predicted If the surface displacement trend is low, no warning will be issued; , then the landslide area is predicted If the surface displacement trend is moderate, a Level 2 warning will be issued; , then the landslide area is predicted The surface displacement trend is high, and a level one warning is issued.

2. The method for predicting and analyzing dynamic surface displacement of landslide according to claim 1, It is characterized in that The operation process of S1 includes: Construct a landslide area database, denoted as ,in, represents the i-th landslide area, I represents the total number of landslide areas; the landslide area is collected using satellite remote sensing Image data, construct remote sensing image dataset, denoted as ,in, Indicates landslide area remote sensing image data; the landslide area indicates an area with potential landslide risk in the geological environment; In the landslide area Ground monitoring sensors are deployed in each landslide area, and a ground monitoring sensor is deployed in each landslide area to build a ground monitoring sensor set. ,in, Indicates landslide area The ground monitoring sensor is used to collect displacement data of the ground surface.

3. The method for predicting and analyzing the dynamic surface displacement of a landslide according to claim 2, It is characterized in that The operation process of S2 includes: Collect the displacement data monitored by the ground monitoring sensor and construct a displacement data set, which is recorded as ,in, Indicates landslide area The displacement data collected by the ground monitoring sensors in the area are used to construct a time series in units of days, which is recorded as ,in, represents the yth time point, and Y represents the total number of time points; Based on the time series, time series period labels are added to the remote sensing image dataset and the displacement dataset, and are respectively recorded as remote sensing image period data. and displacement cycle data , the remote sensing image period data Indicates at a point in time Landslide area Remote sensing image data, the displacement cycle data Indicates at a point in time Landslide area Displacement data collected by ground monitoring sensors.

4. A landslide dynamic surface displacement prediction and analysis system, based on a landslide dynamic surface displacement prediction and analysis method according to any one of claims 1 to 3, Features: Also includes, The landslide area database construction and monitoring deployment module uses satellite remote sensing to collect image data of the landslide area and build a remote sensing image data set; ground monitoring sensors are deployed in the landslide area to build a ground monitoring sensor set; The data acquisition and time series labeling module collects the displacement data monitored by the ground monitoring sensors; constructs the time series, and adds time series period labels to the remote sensing image data set and the displacement data set, recording them as remote sensing image period data and displacement period data respectively; The time series data change rate and comprehensive analysis module calculates the change rate of remote sensing image periodic data at different time points in the landslide area based on remote sensing image periodic data; calculates the change rate of displacement periodic data at different time points in the landslide area based on displacement periodic data; calculates the comprehensive time series analysis results of the landslide area at different time points based on the change rate of remote sensing image periodic data and the change rate of displacement periodic data; The trend assessment and early warning trigger module calculates the overall trend assessment values ​​of different landslide areas at different time points based on the comprehensive time series analysis results; Predict and output warnings.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, Features: When the processor executes the computer program, the steps of a method for predicting and analyzing dynamic surface displacement of a landslide according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the steps of a method for predicting and analyzing dynamic surface displacement of a landslide according to any one of claims 1 to 3 are implemented.

Citation Information

Patent Citations

  • Method for detecting landslide displacement field by using optical satellite stereoscopic image

    CN114820552A

  • Urban geological safety geological disaster multistage early warning method

    CN118351671A

  • Tailing pond risk monitoring and early-warning system based on internet of things

    WO2023061039A1