A slope landslide geological disaster spot map intelligent identification and prediction system and method

Abstract

The present application provides a kind of slope landslide geological disaster spot chart intelligent identification and prediction system and method, system includes: data unit, for the terrain geology and meteorological environment data of influence slope landslide are collected, obtain original data and real-time data;Characteristic analysis unit extracts the characteristic parameter of influence slope stability, respectively according to preset principle forms spot chart representation, respectively obtains the spot chart feature library of original data and real-time spot chart feature;Identification and prediction unit, the health state of slope is identified and predicted, and is presented in the form of spot chart;The present application is aimed at the complexity of landslide disaster prediction, creates slope landslide geological disaster spot chart intelligent identification and prediction method, through the digital image diagnosis of slope pathological characteristics, the stability state of slope is identified and predicted, provides a kind of intuitive, lively, image prediction and stability diagnosis technique for landslide geological disaster, can be used for long-term prediction and evaluation of geological disasters such as slope.

Description

[Technical Field]

[0001] This invention relates to the field of engineering geology and geotechnical engineering disaster prevention and mitigation technology, and in particular to an intelligent identification and prediction system and method for landslide geological disasters using spot maps. [Background Technology]

[0002] Numerous natural and artificial slopes exist in nature. Slopes are prone to landslides under various natural and human disturbances. Landslides are a type of geological hazard that occurs frequently and is widely distributed in nature. Landslide geological hazards are influenced by many factors, making accurate identification and prediction difficult. For a long time, inaccurate identification and low prediction precision of landslide geological hazards have been a major challenge in landslide hazard prediction and prevention.

[0003] To date, there has been extensive research on landslide disasters, resulting in numerous theories and hypotheses and abundant findings. The entire process of a landslide, from its inception and development to its termination, involves various internal and external factors, complex and variable boundary conditions, and iterative and feedback effects. Therefore, landslide-causing factors have always been a key focus of research in the field of engineering geology. Landslides with different geological conditions and slope structures have varying inducing mechanisms and triggering factors. Landslide development is related to topography, regional tectonic movements, earthquakes, extreme weather, global climate change, and human engineering activities. Using satellite and GIS data to collect topographic, surface, and satellite imagery, a spatial database was established. Geological, slope, aspect, elevation, topographic humidity index, distance from faults, lithology, soil type, and land cover factors related to landslide occurrence were selected. Based on nonlinear system methods such as neural networks, genetic algorithms, and catastrophe theory, the susceptibility and evolution mechanism of landslides were studied. Some researchers have counted 596 landslide susceptibility factors, categorizing them into five types: geological, hydrological, land cover, geomorphological, and others. Some researchers have also used statistical methods to analyze and select seven key factors to create a landslide susceptibility map of Southern California.

[0004] In landslide disaster assessment and prediction, based on time series analysis, various signal decomposition methods are used to decompose the cumulative displacement-time series of landslides. Then, various mathematical methods such as trigonometric functions, differential autoregressive moving average, and vector autoregression analysis, or machine learning models such as backpropagation neural networks, support vector machines, long short-term memory networks, and kernel extreme learning machines are applied to train and predict each displacement component. By superimposing the predicted values ​​of each component, the cumulative displacement is predicted. Many nonlinear prediction models have been proposed to address the combination of determinism and randomness in the evolution of landslide displacement time series, the alternation of gradual and abrupt processes, and the development of ordered and disordered processes. Artificial intelligence algorithms such as Artificial Neural Network (ANN) models and Support Vector Machine (SVM) models are widely used in landslide displacement prediction research.

[0005] However, due to the complexity of the factors influencing landslides, their occurrence is often the result of the coupling of multiple factors. These factors typically exhibit heterogeneity, randomness, uncertainty, dynamics, and nonlinearity, varying with geographical, temporal, and spatial domains, thus presenting significant big data characteristics. Existing quantitative analysis methods, physical simulations, numerical simulations, and nonlinear methods are still insufficient to handle such complex and variable big data problems. Furthermore, current landslide prediction is mainly based on pre-landslide prediction using deformation monitoring, and there are still insurmountable theoretical and technical bottlenecks in medium- and long-term prediction.

[0006] The development of new-generation information technologies such as big data and artificial intelligence has provided technical support for geological disaster prediction in the context of complex large-scale systems.

[0007] Therefore, it is necessary to study an intelligent identification and prediction system and method for landslide geological hazards based on spot maps to address the shortcomings of existing technologies and to solve or mitigate one or more of the aforementioned problems. [Summary of the Invention]

[0008] In view of this, the present invention provides an intelligent identification and prediction system and method for landslide geological disasters using spot maps. Addressing the complexity of landslide disaster prediction, the present invention establishes an intelligent identification and prediction method for landslide geological disasters using spot maps. Through digital image diagnosis of slope pathological characteristics, it identifies and predicts the stability state of slopes, providing an intuitive, vivid, and visual prediction and stability diagnosis technology for landslide geological disasters. This technology can be used for long-term prediction and evaluation of geological disasters such as slopes.

[0009] On one hand, the present invention provides an intelligent identification and prediction system for landslide geological hazard spot maps, the system comprising:

[0010] The data unit is used to collect topographic, geological, and meteorological environmental data that affect slope landslides, and to obtain raw and real-time data.

[0011] The feature analysis unit is used to extract feature parameters that affect slope stability from raw data and real-time data, form spot map representations according to preset principles, and obtain the spot map feature library of raw data and real-time spot map features respectively.

[0012] The identification and prediction unit is used to identify and predict the health status of the slope by comparing the feature library of the original data with the real-time feature of the spot map, and to display it in the form of a spot map.

[0013] The data unit is connected to the identification and prediction unit through the feature analysis unit.

[0014] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the sources of the original data acquisition include slope big data acquisition, slope database acquisition, and manual entry, and the sources of the real-time data include real-time monitoring acquisition by monitoring devices and manual entry.

[0015] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the topographic and geological data includes: slope location information, slope geometry, topographic geology, lithology, regional geological structure, and weak interlayers; and the meteorological and environmental data includes meteorological data and data on the impact of human disturbances.

[0016] As described above, and in any possible implementation, a further implementation is provided in which the topographic geological data includes:

[0017] The location information of the slope includes the three-dimensional coordinates, azimuth, and direction angle of the slope's geographical location;

[0018] The slope structure includes the height, slope, inclination, scale of the slope and steps, and retaining walls;

[0019] Topographic geology includes slope type, vegetation cover, slope height / gradient, stratigraphic lithology, loose layer thickness, and dip and dip angle of the basement strata;

[0020] Regional geological structures include fault type, scale, distribution density and distance from slopes, and regional seismic intensity.

[0021] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the human disturbance impact data in the meteorological environment data includes slope toe excavation, surcharge intensity, blasting vibration and external loads, and the external loads include vehicle loads.

[0022] In addition to the aspects and any possible implementations described above, a further implementation is provided in which the feature analysis unit includes an amplifier, a digital strain gauge, a data integration box, and a computer, one end of the amplifier being connected to a data unit and the other end being connected to the data integration box via the digital strain gauge, and the data integration box being connected to the computer.

[0023] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the computer includes a blob image feature processor, a blob image generation processor, and a blob image feature library. One end of the blob image generation processor is connected to a data integration box via the blob image feature processor, and the other end is simultaneously connected to the blob image feature library and the identification and prediction unit; wherein...

[0024] The speckle image feature processor uses images with different current conditions and colors to characterize the feature parameters that affect slope stability;

[0025] The blob plot generator uses key influencing factors of slope sensitivity as feature factors, judges slope stability through preset thresholds, and uses the blob plot method to characterize the feature factors.

[0026] The feature library of blob features constitutes a collection of blob features of slope landslides. Each blob represents a type of catastrophic feature of the slope and has dual attributes of type and size. It is only manifested when the size of the feature value exceeds the threshold; otherwise, it is hidden.

[0027] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the identification and prediction unit includes feature blob map extraction, identification and prediction, and blob map display, wherein;

[0028] Feature spot map extraction involves extracting feature spot maps from the spot map database of the slope to be measured, then storing and processing them.

[0029] The identification and prediction process includes identification and prediction. Identification involves matching explicit and implicit information to identify slope diseases. Prediction involves trend analysis and prediction based on meteorological conditions, earthquake occurrence, and the weathering and strength reduction characteristics of slope rock mass.

[0030] The speckle plot displays the analysis and prediction results and the slope disease identification results in the form of a speckle plot.

[0031] In addition to the aspects and any possible implementations described above, a further implementation is provided, wherein the operation process in the feature blob extraction is specifically as follows: assigning a unique feature code to each feature blob, and the process of multiple blobs forming a code sequence of a certain length according to a certain encoding principle; the code is a binary code, which is "1" when the feature blob is dominant and "0" when it is recessive; the feature factors are encoded to form a binary sequence code.

[0032] In accordance with the aspects described above and any possible implementation, a method for intelligent identification and prediction of landslide geological hazards using spot maps is further provided. This method is implemented through the aforementioned intelligent identification and prediction system for landslide geological hazards using spot maps. The method digitizes the diagnostic results of slope diseases into CT images, visually displaying the location, extent, and occurrence time of slope diseases. By observing the evolution of the feature spot maps over time, the evolution process of slope diseases can be observed, and the occurrence time and scale of slope diseases can be predicted, providing timely early warnings and alarms.

[0033] Compared with the prior art, the present invention can achieve the following technical effects:

[0034] This technology enables the CT-like imaging of slope disease diagnosis. The location, extent, and occurrence time of slope diseases are displayed intuitively, vividly, and visually through spot maps, eliminating the need for quantitative calculations and analytical analysis. The collected slope data is multi-dimensional, including engineering geological and geotechnical engineering survey data, as well as resource and environmental satellite and seismic network data. Real-time and dynamic data are directly collected through the monitoring system. Alternatively, existing survey reports containing engineering data, historical meteorological and seismic data, and statistical prediction data can be manually input. The data is versatile, allowing for statistical analysis and processing of meteorological, slope morphology, structure, stratigraphy, and geological structure data. By observing the evolution of the characteristic spot maps over time, the progression of slope diseases can be observed, and the timing and scale of slope disease occurrence can be predicted, providing timely early warnings and alerts, and offering effective opportunities and basis for slope prevention and control.

[0035] Of course, any product implementing this invention does not necessarily need to achieve all of the technical effects described above at the same time. [Attached Image Description]

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a system configuration diagram of the intelligent identification and prediction system for landslide geological hazards provided in one embodiment of the present invention;

[0038] Figure 2 This is the basic structure of slope data provided in one embodiment of the present invention;

[0039] Figure 3 This is a diagram illustrating a dot pattern generation mechanism provided in one embodiment of the present invention;

[0040] Figure 4 This is a diagram illustrating the code operation mechanism of a dot map according to an embodiment of the present invention;

[0041] Figure 5 This is a slope health status spot identification, prediction and image display diagram provided by an embodiment of the present invention.

Detailed Implementation Methods

[0042] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0043] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0044] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0045] This invention provides an intelligent identification and prediction system for landslide geological hazard spot maps, the system comprising:

[0046] The data unit is used to collect topographic, geological, and meteorological environmental data that affect slope landslides, and to obtain raw and real-time data.

[0047] The feature analysis unit is used to extract feature parameters that affect slope stability from raw data and real-time data, form spot map representations according to preset principles, and obtain the spot map feature library of raw data and real-time spot map features respectively.

[0048] The identification and prediction unit is used to identify and predict the health status of the slope by comparing the feature library of the original data with the real-time feature of the spot map, and to display it in the form of a spot map.

[0049] The data unit is connected to the identification and prediction unit through the feature analysis unit.

[0050] The sources of the raw data include slope big data acquisition, slope database acquisition, and manual entry, while the sources of the real-time data include real-time monitoring acquisition by monitoring devices and manual entry.

[0051] The topographic and geological data include: slope location information, slope geometry, topography and geology, lithology, regional geological structure and weak interlayers; the meteorological and environmental data include meteorological data and data on the impact of human disturbance.

[0052] In the aforementioned topographic and geological data:

[0053] The location information of the slope includes the three-dimensional coordinates, azimuth, and direction angle of the slope's geographical location;

[0054] The slope structure includes the height, slope, inclination, scale of the slope and steps, and retaining walls;

[0055] Topographic geology includes slope type, vegetation cover, slope height / gradient, stratigraphic lithology, loose layer thickness, and dip and dip angle of the basement strata;

[0056] Regional geological structures include fault type, scale, distribution density and distance from slopes, and regional seismic intensity.

[0057] The meteorological environmental data includes data on human disturbance effects such as slope toe excavation, surcharge intensity, blasting vibration, and external loads, including vehicle loads.

[0058] The feature analysis unit includes an amplifier, a digital strain gauge, a data integration box, and a computer. One end of the amplifier is connected to the data unit, and the other end is connected to the data integration box via the digital strain gauge. The data integration box is connected to the computer.

[0059] The computer contains a blob image feature processor, a blob image generation processor, and a blob image feature library. One end of the blob image generation processor is connected to the data integration box via the blob image feature processor, and the other end is connected to both the blob image feature library and the identification and prediction unit.

[0060] The speckle image feature processor uses images with different current conditions and colors to characterize the feature parameters that affect slope stability;

[0061] The blob plot generator uses key influencing factors of slope sensitivity as feature factors, judges slope stability through preset thresholds, and uses the blob plot method to characterize the feature factors.

[0062] The feature library of blob features constitutes a collection of blob features of slope landslides. Each blob represents a type of catastrophic feature of the slope and has dual attributes of type and size. It is only manifested when the size of the feature value exceeds the threshold; otherwise, it is hidden.

[0063] The identification and prediction unit includes feature blob image extraction, identification and prediction, and blob image display, wherein;

[0064] Feature spot map extraction involves extracting feature spot maps from the spot map database of the slope to be measured, then storing and processing them.

[0065] The identification and prediction process includes identification and prediction. Identification involves matching explicit and implicit information to identify slope diseases. Prediction involves trend analysis and prediction based on meteorological conditions, earthquake occurrence, and the weathering and strength reduction characteristics of slope rock mass.

[0066] The speckle plot displays the analysis and prediction results and the slope disease identification results in the form of a speckle plot.

[0067] The specific operation process in the feature blob extraction is as follows: assigning a unique feature code to each feature blob, and forming a code sequence of a certain length by multiple blobs according to a certain encoding principle; the code is a binary code, which is "1" when the feature blob is dominant and "0" when it is recessive; the feature factors are encoded to form a binary sequence code.

[0068] This invention also provides a method for intelligent identification and prediction of landslide geological hazards using spot maps. The method is implemented through the aforementioned intelligent identification and prediction system for landslide geological hazards using spot maps. The method digitizes the diagnostic results of slope diseases into CT images, visually displaying the location, extent, and occurrence time of slope diseases. By observing the evolution of the feature spot maps over time, the evolution process of slope diseases can be observed, and the occurrence time and scale of slope diseases can be predicted, providing timely early warning and alarm.

[0069] Example 1:

[0070] This invention diagnoses the health status of slopes through spot diagram analysis of slope stability. It identifies and evaluates slope stability based on regional environmental data without requiring quantitative calculations or analysis. Furthermore, slope diagnosis enables the prediction and prevention of landslides. This invention overcomes the limitations of traditional landslide prediction methods in handling quantitative issues. The system comprises a data unit, a feature analysis unit, and a judgment and prediction unit.

[0071] The data unit is a system for collecting topographic, geological, and meteorological environmental data that affect slope landslides. This unit collects slope data and provides raw data for slope stability identification and prediction.

[0072] The slope data refers to information on the location of the slope, its geometric structure, topography, geology, lithology, regional geological structure, weak interlayers, and data on meteorological and human disturbances. The slope data covers data from the sky, air, ground, and people in the area where the slope is located, including real-time monitoring data from meteorological satellites, resource and environmental satellites, and seismic networks, as well as geological surveys, explorations, and human activities related to the slope. It has the characteristics of big data, such as large data volume, many types, heterogeneity, rapid changes, uncertainty, nonlinearity, and low value density.

[0073] The location of the slope is mainly obtained from the satellite positioning system. The parameters include the three-dimensional coordinates, azimuth and direction angle of the slope's geographical location, which are provided by the satellite positioning system or other conventional topographic surveying techniques.

[0074] The slope structure mainly includes the height, slope, inclination, scale of the slope and steps, and slope retaining.

[0075] The topographic and geological data mainly comes from the topographic and geological survey data of the slope site, including slope type, vegetation coverage, slope height / gradient, stratigraphic lithology, loose layer thickness, and dip and dip angle of the basement strata.

[0076] The regional geological structure data mainly includes fault type, scale, distribution density and distance from slopes, and regional seismic intensity;

[0077] The human activity data mainly includes external loads such as slope toe excavation, surcharge intensity, blasting vibration, and vehicle load.

[0078] The feature analysis unit consists of an amplifier, a digital strain gauge, a data integration box, and a computer, all integrated into the host unit. The computer can be a microcontroller. The information in the data unit is large-scale slope data, which can be acquired in real time through a slope database and monitoring system, or entered manually. When the monitoring signal is an electrical parameter, it must be amplified by the amplifier and then enter the data integration box through the digital strain gauge. The slope statistical data is directly input from the system database into the data integration box for data analysis and integration, and then uploaded to the identification and prediction unit.

[0079] The feature analysis involves identifying key factors that significantly impact slope stability from landslide-affecting factors through research on slope stability and statistical analysis of literature. Feature parameters influencing slope stability are extracted from slope data, and a speckle map feature is generated according to certain principles. This unit consists of speckle map features, speckle map generation, and a speckle map feature library.

[0080] The spot map representation uses images of different current conditions and colors to characterize the characteristic parameters affecting slope stability. In the slope structure data, slope height, slope, dip, slope size, and slope retaining status are represented by the ratio of unit slope height to slope, the ratio of the weight of the easily sliding layer of the slope to the equivalent weight of the slope retaining, and the ratio of the dip angle of the strata to the dip angle of the slope. Characteristic parameters such as strata geology, soil and rock properties, overburden, weathering characteristics, hydrological characteristics, main physical and mechanical properties of soil and rock, regional faults, weak interlayers, seismic intensity, and recent tectonic movements, as well as meteorological factors such as rainfall, snow, and freeze-thaw cycles, and external characteristic factors such as blasting vibration, excavation, and dynamic / static loads, are all extracted and represented by characteristic parameters through statistical analysis of literature and historical landslide big data. The feature of the spot map depends on the threshold of this factor as a stability influence.

[0081] The spot map generation uses key influencing factors of slope sensitivity as characteristic factors. When the value of a characteristic factor parameter reaches or exceeds a threshold, it causes slope instability; when it is below the threshold, it affects slope stability but does not cause damage, and no spot map is generated. Using the spot map method, each characteristic factor corresponds to a specific situation. The threshold is used as the critical size of the spot map. Each characteristic factor is represented by a spot map. Different characteristic factors are presented as spot maps in the slope. The characteristic spot map reflects the location and range of slope instability in a visual, vivid, and graphic way, in the form of a CT image. The risk level of the slope is reflected by the type, size, and range of the spot map. The spot map is presented on the three-dimensional slope body and can also be mapped onto the slope surface, horizontal projection map, and cross-section and longitudinal section.

[0082] The so-called spot map feature library is a collection of spot maps that constitute slope landslide features. Each spot map represents a type of catastrophic feature of the slope and has dual attributes of type and size. It is only manifested when the feature value exceeds the threshold; otherwise, it is hidden. Catastrophic features are the "lesions" of individual slopes. The type, size, and range of different "lesions" together characterize the health status of the slope and are the basic basis for diagnosing slope diseases.

[0083] The feature spot map is a graphical representation of the slope feature factors after they reach or exceed the feature factor threshold. It has the dual attributes of specific shape and size and is the basic unit of the spot map feature library. The health status of the slope is reflected by at least one feature spot map, and in most cases, it is a spot area formed by multiple types of feature spot maps according to certain principles.

[0084] The identification and prediction unit includes feature patch map extraction, identification and prediction, and patch map display. This unit extracts feature patch maps of the slope from the patch map database of the slope to be measured, compares the feature patch maps of the slope with the patch maps in the standard feature library, identifies and predicts the health status of the slope, and displays the results in the form of a patch map.

[0085] The feature spot map extraction is the process of extracting feature spot maps from the spot map database of the slope to be measured. After the spot maps are extracted, they are stored and processed.

[0086] The operation is to assign a unique feature code to each feature blob, and multiple blobs are combined into a code sequence of a certain length according to certain encoding principles. The code is a binary code, which is "1" when the feature blob is dominant and "0" when it is recessive. The feature factors are encoded in the order of slope location, geometric structure, topography and geology, lithology, regional geological structure, weak interlayers, meteorological and human disturbance influences to form a (0,1) binary sequence code.

[0087] The identification and prediction unit consists of a computer, a printer, and an external display terminal. The computer analyzes, stores, and outputs the slope data through a program, and identifies and predicts the slope in real time.

[0088] The identification process involves extracting feature blob images and searching for matches against a standard blob image feature library. If a feature blob image matches a standard blob image, it is determined to be a dominant feature; otherwise, it is considered a recessive feature. By searching the blob images of all factors, blob images of all dominant features are obtained, thereby completing the process of identifying slope diseases.

[0089] The prediction is based on the monitoring data of satellites such as resource meteorology and seismic networks to conduct trend analysis on meteorological conditions such as rain and snow in the slope area, earthquake occurrence, and characteristics such as slope rock weathering and strength attenuation. By inputting trend data, the health status of the slope under future conditions is evaluated and predicted, and the prediction is displayed in the form of a spot map through calculation and the location, scale and time of occurrence are given early warning.

[0090] The spot map display involves displaying the extracted spot map in the three-dimensional space of the slope, and it can also be displayed on the plane, slope surface, longitudinal section and cross section.

[0091] The intelligent identification and prediction technology for landslide geological hazards using spot maps involves the acquisition, transmission, and analysis of data from the data unit, feature analysis unit, and judgment and prediction unit. Data is input to the system host via interfaces and cables. The host consists of an amplifier, a digital strain gauge, and a computer. A CR-655 interface cable connects the amplifier and the digital strain gauge. Data is transmitted between the digital strain gauge and the data integration box via an RS-232C interface cable. Data is transmitted between the data integration box and the data analysis unit via a CR-553B interface cable. Electrical signals acquired by the data unit are amplified by the amplifier, converted into binary data by the strain gauge, calibrated, and then input into the computer. Non-electrical signal data is directly input into the data integration box without conversion, and then input to the computer via interfaces and cables. Display devices include various terminals, including computers and displays.

[0092] Example 2:

[0093] like Figure 1 As shown, the present invention relates to an intelligent identification and prediction technology for landslide geological hazards using spot maps. This technology is implemented through a system and its corresponding methods. The system includes a slope data unit, a feature analysis unit, and an identification and prediction unit.

[0094] The data unit includes the geographical location of the slope, which is automatically imported from a satellite positioning system or manually entered to obtain the geographical coordinates and orientation of the slope. Regional meteorological data is mainly provided by meteorological satellites, including meteorological factors such as temperature, humidity, rainfall, rainfall intensity, snow depth, and freeze-thaw depth in the area where the slope is located. Slope characteristics include slope type, slope height, slope angle, slope length, attitude, vegetation type, and vegetation coverage. Stratigraphic geology mainly includes the overburden, weathered layer, basement layer, special soils and rocks, groundwater, weak strata, and rock mass structure. Data includes rock strata attitude; regional tectonics such as faults and their distance from the slope, recent tectonic movements, seismic intensity, and acceleration; engineering activities such as slope toe excavation, loading, blasting vibration, vehicle transportation, and slope retaining; slope geological data provided by engineering geological surveys, geotechnical engineering investigations, and seismic network data; real-time meteorological and seismic data can be provided for this technology through resource, environmental, and meteorological satellites and seismic networks; data in the data unit includes real-time monitoring data and existing survey data, with the survey data stored in the slope database for use by the feature analysis unit.

[0095] In this embodiment, the slope data is connected to the feature analysis unit via an interface and cables.

[0096] The feature analysis unit includes an amplifier to amplify the measured electrical signal and connects to the digital strain gauge via a CR-655 interface cable. The data is input to the data integration module via an RS-232C interface cable. The digital signal in the data is directly uploaded to the digital integration module via the RS-232C interface and cable, and then input to the computer. The amplifier, digital strain gauge, and computer in the data analysis unit are integrated in the host computer.

[0097] The data integration box integrates the data input from the feature data analysis unit and inputs it to the identification and prediction unit via the CR-553B interface cable.

[0098] The identification and prediction unit performs speckle extraction, identification, and prediction, and displays the results in the form of speckles. The identification and prediction unit includes a computer and other terminals for data storage, display, analysis, printing, and transmission.

[0099] like Figure 2 As shown in the figure, the basic composition diagram of slope data in the embodiment of the present invention extracts feature data from data such as slope location, geometric structure, topography and geology, lithology, geological structure, vegetation, meteorology and human activities, and generates a basic slope database. The feature analysis unit integrates, filters and statistically analyzes the data to form data types, feature data and corresponding feature factor thresholds.

[0100] like Figure 3As shown, in the embodiment of the present invention, the process of generating the blob map involves the system sequentially extracting feature data from the slope data unit. In the feature analysis unit, the data undergoes preprocessing such as integration, filtering, noise reduction, and deformation. Feature factors are extracted, and the factor parameters are compared and judged against their thresholds. If the threshold is exceeded, the feature factor is assigned a graphic and size according to the encoding principle. If the threshold condition is not met, the next feature factor is extracted from the database. This process is repeated until all types and their feature factors are extracted and assigned graphics and sizes, at which point the blob map generation process ends. The blob map data constitutes a slope blob map library. The current state of the blob map for each feature factor is unique.

[0101] like Figure 4 As shown, in this embodiment of the invention, the code operation mechanism of the blob image is as follows: In this embodiment, the system sequentially extracts blob images from the slope blob image library, judges their type and source, determines the feature factors, and judges the blob images. If a feature factor is present, code "1" is generated; if not, code "0" is generated. The search proceeds sequentially from type-feature factor-blob image until the blob image of all factors of the last type is obtained, thus forming a code sequence composed of (0, 1). Each code sequence corresponds to a specific type of slope disease. The code sequence is the internal operation code of the system and is a supplement to the blob image. Through the code sequence, textual and graphic diagnostic results of the blob image and the health status of the slope can be obtained.

[0102] In this embodiment, a typical implementation case involves a slope located in North China. At a certain time in summer, the region experienced an unusually heavy rainfall, causing a landslide. This slope is a natural slope, and the rainfall reached a threshold. The meteorological sub-code for the slope area is 001000, indicating that the rainfall in the slope area reached the threshold, which was a triggering factor for the landslide. At that time, the temperature, humidity, rainfall intensity, snow depth, and freeze-thaw depth were not the main factors influencing the landslide. The geological code is 10101001, indicating that the overlying strata are easily landslideable, the weathering layer is acceptable, the basement layer and the overlying strata dip in the same direction and are smooth-slip strata, there are no special soils or rocks, groundwater seeps out during rainfall, accelerating slope instability, there are no weak strata, the rock mass structure is relatively intact, and the rock strata attitude is consistent with the slope attitude. It is conducive to slope instability; the regional tectonic code is 0000, indicating that the fault is far from the slope, there is no seismic activity during rainfall, the regional seismic intensity is low, and the vibration acceleration is small; the human engineering activity code is 10000, indicating that the slope toe has been excavated, but there is no surcharge, no blasting vibration, no vehicle transportation or other external loads, and there is no retaining wall or other slope support after the slope toe is excavated; in sequence, the codes of each type of characteristic factor are arranged in a certain order to form the code of the slope accident. According to this code, the cause of the slope disease can be directly found and the spatial location of instability can be displayed as needed.

[0103] This invention realizes the CT imaging approach to slope disease diagnosis. The slope data is displayed intuitively, vividly, and visually through a speckle map, showing the location, extent, and timing of slope diseases without the need for quantitative calculations and analytical analysis. The collected slope data is multi-dimensional, including engineering geological and geotechnical engineering survey data, as well as resource and environmental satellite and seismic network data, which are directly collected in real-time and dynamically through a monitoring system. Alternatively, it can include engineering data from existing survey reports, historical meteorological and seismic data, and statistical prediction data, which can be manually input. The data is versatile, allowing for statistical analysis and processing of meteorological, slope morphology, structure, stratigraphy, and geological structure data. By observing the evolution of the characteristic speckle map over time, the progression of slope diseases can be observed, and the timing and scale of slope disease occurrence can be predicted, providing timely early warnings and alerts, and offering effective opportunities and basis for slope prevention and control.

[0104] Practice has shown that applying this technology to the identification and prediction of landslides, ground subsidence and debris flow disasters solves the problems of handling complex, random, uncertain and heterogeneous aspects involved in quantitative calculation and analytical analysis. It reveals and displays the location, scale and time of slope disease occurrence in a visual, vivid and graphic way in the form of spot maps, with high visibility.

[0105] This invention diagnoses the health status of slopes through spot diagram analysis of slope stability. It identifies and evaluates slope stability based on regional environmental data without requiring quantitative calculations or analysis. Furthermore, slope diagnosis enables the prediction and prevention of landslides. This invention overcomes the limitations of traditional landslide prediction methods in handling quantitative issues. It can be applied to the stability identification and prediction of various natural and artificial slopes.

[0106] The above provides a detailed description of the intelligent identification and prediction system and method for landslide geological hazards based on the embodiments of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and its core ideas; furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

[0107] Certain terms are used in the specification and claims to refer to specific components. Those skilled in the art will understand that hardware manufacturers may use different names to refer to the same component. This specification and claims do not distinguish components based on differences in name, but rather on differences in function. The terms "comprising" and "including" used throughout the specification and claims are open-ended and should be interpreted as "comprising / including but not limited to". "Approximately" means that within an acceptable margin of error, those skilled in the art can solve the technical problem and substantially achieve the technical effect within a certain margin of error. The following descriptions in the specification are preferred embodiments for carrying out this application; however, these descriptions are for the purpose of illustrating the general principles of this application and are not intended to limit the scope of this application. The scope of protection of this application shall be determined by the appended claims.

[0108] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system that includes said element.

[0109] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0110] The foregoing description illustrates and describes several preferred embodiments of this application. However, as previously stated, it should be understood that this application is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the application concept described herein through the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of this application should be within the protection scope of the appended claims.

Claims

1. A smart identification and prediction system for landslide geological hazards using spot maps, characterized in that, The intelligent identification and prediction system for slope landslide geological hazards using spot maps includes: The data unit is used to collect topographic, geological, and meteorological environmental data that affect slope landslides, and to obtain raw and real-time data. The feature analysis unit is used to extract feature parameters that affect slope stability from raw data and real-time data, form spot map representations according to preset principles, and obtain the spot map feature library of raw data and real-time spot map features respectively. The identification and prediction unit is used to identify and predict the health status of the slope by comparing the feature library of the original data with the real-time feature of the spot map, and to display it in the form of a spot map. The data unit is connected to the identification and prediction unit through the feature analysis unit.

2. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 1, characterized in that, The sources of the raw data include slope big data acquisition, slope database acquisition, and manual entry, while the sources of the real-time data include real-time monitoring acquisition by monitoring devices and manual entry.

3. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 1, characterized in that, The topographic and geological data include: slope location information, slope geometry, topography and geology, lithology, regional geological structure and weak interlayers; the meteorological and environmental data include meteorological data and data on the impact of human disturbance.

4. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 3, characterized in that, In the aforementioned topographic and geological data: The location information of the slope includes the three-dimensional coordinates, azimuth, and direction angle of the slope's geographical location; The slope structure includes the height, slope, inclination, scale of the slope and steps, and retaining walls; Topographic geology includes slope type, vegetation cover, slope height / gradient, stratigraphic lithology, loose layer thickness, and dip and dip angle of the basement strata; Regional geological structures include fault type, scale, distribution density and distance from slopes, and regional seismic intensity.

5. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 3, characterized in that, The meteorological environmental data includes data on human disturbance effects such as slope toe excavation, surcharge intensity, blasting vibration, and external loads, including vehicle loads.

6. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 1, characterized in that, The feature analysis unit includes an amplifier, a digital strain gauge, a data integration box, and a computer. One end of the amplifier is connected to the data unit, and the other end is connected to the data integration box via the digital strain gauge. The data integration box is connected to the computer.

7. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 6, characterized in that, The computer contains a blob image feature processor, a blob image generation processor, and a blob image feature library. One end of the blob image generation processor is connected to the data integration box via the blob image feature processor, and the other end is connected to both the blob image feature library and the identification and prediction unit. The speckle image feature processor uses images with different current conditions and colors to characterize the feature parameters that affect slope stability; The blob plot generator uses key influencing factors of slope sensitivity as feature factors, judges slope stability through preset thresholds, and uses the blob plot method to characterize the feature factors. The feature library of blob features constitutes a collection of blob features of slope landslides. Each blob represents a type of catastrophic feature of the slope and has dual attributes of type and size. It is only manifested when the size of the feature value exceeds the threshold; otherwise, it is hidden.

8. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 1, characterized in that, The identification and prediction unit includes feature blob image extraction, identification and prediction, and blob image display, wherein; Feature spot map extraction involves extracting feature spot maps from the spot map database of the slope to be measured, then storing and processing them. The identification and prediction process includes identification and prediction. Identification involves matching explicit and implicit information to identify slope diseases. Prediction involves trend analysis and prediction based on meteorological conditions, earthquake occurrence, and the weathering and strength reduction characteristics of slope rock mass. The speckle plot displays the analysis and prediction results and the slope disease identification results in the form of a speckle plot.

9. The intelligent identification and prediction system for landslide geological hazards based on spot maps according to claim 8, characterized in that, The specific operation process in the feature blob extraction is as follows: assigning a unique feature code to each feature blob, and forming a code sequence of a certain length by multiple blobs according to a certain encoding principle; the code is a binary code, which is "1" when the feature blob is dominant and "0" when it is recessive; The feature factors are encoded to form a binary sequence code.

10. A method for intelligent identification and prediction of landslide geological hazards using spot maps, characterized in that, The method is implemented by the intelligent identification and prediction system for slope landslide geological disasters using spot maps as described in any one of claims 1-9. The intelligent identification and prediction method for slope landslide geological disasters uses CT imaging to visualize the diagnosis results of slope diseases, displaying the location, extent, and occurrence time of slope diseases. By observing the evolution of the feature spot map over time, the evolution process of slope diseases can be observed, and the occurrence time and scale of slope diseases can be predicted, providing timely early warning and alarm.

Images