Geological disaster intelligent early warning system based on big data analysis

Abstract

The invention discloses a geological disaster intelligent early warning system based on big data analysis, which relates to the technical field of intelligent early warning, comprises a data acquisition module, a data analysis module and a data early warning module, and is characterized in that a radiation radius is set, an influence circumference area is constructed, an erosion critical value is set, a mountain erosion grade is obtained, and a mountain stability model is constructed. And setting a random event, compensating and updating the mountain stability model, and sending an early warning signal according to a comparison result. By integrating various data sources, such as rivers, projects and terrains, more accurate geological disaster early warning can be provided, false alarm and missing alarm phenomena can be effectively reduced, real-time data acquisition and dynamic updating functions are achieved, a mountain stability model can be adjusted according to latest data and conditions, timeliness of early warning information is ensured, and the early warning efficiency is improved. Through construction of the mountain stability model and division of erosion grades, a high-risk area can be effectively identified, a scientific basis is provided for decision makers, and engineering design and transformation are guided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent early warning, and in particular to an intelligent early warning system for geological disasters based on big data analysis. Background Art

[0002] In recent years, with the rapid development of sensor technology, remote sensing technology, artificial intelligence and big data analysis, intelligent early warning technology for geological disasters has also made significant progress. Satellite remote sensing and drone technology have made it possible to monitor geological disasters over a large area. They can quickly obtain information on surface changes and identify potential geological disaster areas. By analyzing historical geological disaster data and combining various factors such as meteorology and topography, data models are established to improve prediction accuracy. In areas where landslides and mudslides occur frequently, sensors are used to monitor rainfall and soil moisture content, etc., to judge the risk of disasters in real time and issue warnings in advance.

[0003] At present, a geological disaster early warning method and a geological disaster early warning system are disclosed in a Chinese invention patent with publication number CN 117854240 B. The method determines the probability of the sliding speed reaching the disaster threshold in the next time window by the sliding speed of the landslide body in the current time window and the sliding speed in the next time window, generates corresponding warning information based on the probability, and warns in the target area in the form of light or sound. However, the relevant technology does not combine the relationship between engineering and mountain hydrology and other factors to build an integrated prediction model, lacks comprehensiveness and comprehensiveness of the prediction, does not effectively compensate for the errors that affect geological disasters, is not conducive to the accuracy of the prediction, and has certain limitations. Summary of the invention

[0004] The technical problem solved by the present invention is that the relevant technology does not combine the relationship between engineering and mountain hydrology and other factors to build an integrated prediction model, lacks the comprehensiveness and comprehensiveness of the prediction, does not effectively compensate for the errors affecting geological disasters, is not conducive to the accuracy of the prediction, and has certain limitations.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a geological disaster intelligent early warning system based on big data analysis, including a data acquisition module, a data analysis module and a data early warning module;

[0006] The data acquisition module obtains a river pipe network map and a project distribution map of the area to be tested, wherein the river pipe network map includes flow direction, flow rate and segment nodes, and the segment nodes are first numbered. The project distribution map includes project types and project locations, and the project distribution map is mapped to the river pipe network map, and the project types and project locations are marked in the river pipe network map, and the project locations are second numbered, and a first distance between the project location and the corresponding river is obtained, a radiation radius is set, and an impact circumference area is constructed;

[0007] The data analysis module obtains an altitude distribution map of the impact circular area, obtains terrain undulations based on the altitude distribution map, analyzes the terrain undulations, obtains a correlation between the project location and the mountain, obtains the water retention rate of the mountain based on the correlation between the project location and the mountain, calculates a third distance between the mountain and the corresponding river, sets an erosion threshold, divides the erosion degree of the mountain based on the erosion threshold, obtains the erosion grade of the mountain, constructs a mountain stability model based on the erosion grade of the mountain and the water retention rate of the mountain, sets random events, calculates the probability of occurrence of the random events, and compensates and updates the mountain stability model based on the probability of occurrence of the random events;

[0008] The data warning module calculates the mountain stability of the current project location according to the updated mountain stability model, sets a stability threshold, compares the mountain stability of the current project location with the stability threshold, and issues a warning signal according to the comparison result.

[0009] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, wherein: the data acquisition module obtains the river network map and engineering distribution map of the area to be tested;

[0010] The river network diagram includes flow direction, flow rate and segment nodes. The sub-river network is divided according to the segment nodes. The segment nodes are represented as demarcation points that decrease with the difference of the first flow gradient. The value of the first flow gradient is obtained through big data analysis. The sub-river network between adjacent segment nodes is regarded as a whole. The segment nodes are first numbered, and the first number is represented by X. i , the sub-river network is represented by X i X i+1 , where i is a natural number, and the project distribution map includes project types and project locations;

[0011] The project distribution map is mapped to the river pipe network map, and the project type and project location are marked in the river pipe network map, and the project location is given a second number, and the second number is represented by Y j , where j is a natural number;

[0012] A first distance between the project location and the corresponding river is obtained, and a first value is set as a radiation radius. The first value is obtained by calculating the radius of the radiation range of historical geological disasters to construct an impact circular area.

[0013] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the logic of mapping the engineering distribution map to the river network map includes:

[0014] Obtain a river network map, calculate the proportion of the area to be tested in the river network map, record it as a first ratio, obtain a project distribution map, calculate the proportion of the area to be tested in the project distribution map, record it as a second ratio, calculate the ratio of the first ratio to the second ratio, record it as a third ratio, amplify the project distribution map according to the third ratio to obtain a first image, overlap and move the first image with the river network map until the area to be tested in the first image overlaps with the area to be tested in the river network map, stop moving the first image, map the project type and project location in the first image to the river network map, and mark them in the corresponding sub-river network, establish a first mapping relationship between the project location and the corresponding sub-river network, and the expression of the first mapping relationship is:

[0015] Y j →X i X i+1 .

[0016] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the calculation logic of the first distance includes:

[0017] Obtain the project location, match the corresponding sub-river network according to the first mapping relationship, set the midpoint of the sub-river network as the reference point, the project location is represented by the location of the geometric center of the project, and the distance between the project location and the reference point is calculated by the distance formula, which is recorded as the first distance.

[0018] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the data analysis module obtains an altitude distribution map of the affected circular area, and obtains the terrain undulation condition according to the altitude distribution map, wherein the terrain undulation condition includes peaks, flatness and gullies, and the analysis logic of the terrain undulation condition includes:

[0019] Acquire contour lines in an altitude distribution map, extract a first feature value of the contour line through machine vision, the first feature value of the contour line is expressed as a shape feature value of the contour line, retrieve a standard contour shape database, the standard contour shape database contains terrain undulation conditions and corresponding contour distribution maps, obtain any contour line graph, record it as a reference, extract a second feature value of the reference through machine vision, the second feature value of the reference is expressed as a shape feature value of the reference, calculate the similarity of the first feature value and the second feature value through a pre-similarity formula, traverse the similarity, sort the similarity in descending order, select the reference corresponding to the similarity with the largest value, set its corresponding terrain state as the current terrain undulation condition, the terrain undulation condition includes peaks, flatness and gullies, and use different color blocks to paint different terrain undulation conditions in the affected circular area, which are respectively recorded as the first key color block, the second key color block and the third key color block;

[0020] When the contour lines are dense and in the shape of closed circles, the terrain undulation is set to a peak; when the contour lines are widely spaced and parallel, the terrain undulation is set to flat; the large interval between contour lines is indicated as being greater than or equal to a second value, and the second value is obtained through expert experience; when the contour lines are in a "V" shape, the terrain undulation is set to a gully; the density of the contour lines is directly proportional to the color value of the first key color block, the interval distance of the contour lines is inversely proportional to the color value of the second key color block, the "V"-shaped depth of the contour lines is directly proportional to the color value of the third color block, and the color value of the first key color block is greater than or equal to the color value of the second key color block, and the color value of the second key color block is greater than or equal to the color value of the third key color block.

[0021] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the data analysis module analyzes the terrain undulation to obtain the correlation between the project location and the mountain, the correlation includes that the project location is not adjacent to the mountain, the project location is located on the sunny slope of the mountain, and the project location is located on the shady slope of the mountain. The analysis logic of the correlation between the project location and the mountain includes:

[0022] Obtain the project location and the corresponding first key color block, second key color block and third key color block, obtain the color values ​​of the first key color block, second key color block and third key color block, construct a fan map of the project location, the fan map takes the project location as the vertex, takes the minimum length covering three color blocks as the radius, takes the direction of the fan as the positive direction, takes the third value as the search length, sets the color tolerance, starts from the vertex and searches for the color value in the positive direction, calculates the difference between the color values ​​of adjacent searches, and records it as the first difference, the color tolerance is expressed as the maximum difference of the color value change when the terrain is not undulating, and the color critical difference represents the color difference of a standard high mountain;

[0023] When the first difference is less than or equal to the third value, the association relationship between the project location and the mountain is that the project location is not adjacent to the mountain; when the first difference is greater than the third value and the positive direction is south, the association relationship between the project location and the mountain is that the project location is located on the sunny slope of the mountain; when the first difference is greater than the third value and the positive direction is north, the association relationship between the project location and the mountain is that the project location is located on the shady slope of the mountain.

[0024] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the water retention rate of the mountain is obtained according to the correlation between the project location and the mountain, and the water retention rate includes the water retention rate of the sunny slope and the water retention rate of the shady slope. The logic for obtaining the water retention rate includes:

[0025] Collect the soil moisture content of the sunny slope and the soil moisture content of the shady slope of the mountain, obtain the average daily rainfall in the area to be tested, calculate the ratio of the average daily rainfall to the soil moisture content of the sunny slope, record it as the moisture retention rate of the sunny slope, calculate the ratio of the first loss difference to the average daily rainfall, record it as the moisture retention rate of the sunny slope, calculate the ratio of the average daily rainfall to the soil moisture content of the shady slope, record it as the moisture retention rate of the shady slope;

[0026] When the association relationship is that the project location is located on the sunny slope of the mountain or the project location is located on the shady slope of the mountain, the color values ​​are sorted in descending order, and the position corresponding to the color value with the largest value is selected and set as the peak point. The peak point is used as the mountain reference point, and the distance between the mountain reference point and the corresponding river is calculated by the distance formula, which is recorded as the third distance. The fourth value and the fifth value are set as the erosion critical value, wherein the fourth value is less than the fifth value. The erosion critical value is expressed as the distance corresponding to the degree of erosion of the mountain by the river. The erosion degree of the mountain is obtained through expert experience, and the erosion level of the mountain is obtained by dividing the erosion degree according to the erosion critical value. The division logic of the erosion level includes:

[0027] When the third distance is less than or equal to the fourth value, the erosion level is set to the first erosion level; when the third distance is greater than the fourth value and less than or equal to the fifth value, the erosion level is set to the second erosion level; when the third distance is greater than the fifth value, the erosion level is set to the third erosion level;

[0028] A mountain stability model is constructed according to the erosion grade of the mountain and the water retention rate of the mountain. The construction logic of the mountain stability model includes:

[0029] The historical landslide values ​​were obtained, and the total number of historical landslides was counted. The historical landslide values ​​were scored by experts according to the severity of the landslides. The corresponding historical mountain erosion grade and historical mountain water retention rate were calculated. The historical landslide values ​​were used as dependent variables, and the historical mountain erosion grade and historical mountain water retention rate were used as independent variables. Multiple regression analysis was performed to obtain a mountain stability model. The expression of the mountain stability model is:

[0030]

[0031] Among them, L is the historical landslide value, n is the number of independent variables, m is k is the kth independent variable, C k is the coefficient of the kth independent variable.

[0032] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the data analysis module sets random events, which include heavy rain, blizzard and typhoon, and calculates the probability of occurrence of random events. The calculation logic of the probability of occurrence includes:

[0033] The number of days of the random event is obtained, recorded as the first day, the ratio of the first day to the number of days in a year is calculated, and the ratio of the first day to the number of days in a year is set as the first occurrence probability, the weather corresponding to the historical landslide value is obtained, and the weather corresponding to the historical landslide value is compared with the random event, the number of occurrences of the random event is counted, and the ratio of the number of occurrences of the random event to the total number of historical landslides is calculated, and the second occurrence probability is calculated. According to the conditional probability formula, the comprehensive probability is calculated, and the calculation expression of the comprehensive probability is:

[0034]

[0035] Among them, P(A|B) is the comprehensive probability, P(AB) is the overlapping probability of the first occurrence probability and the second occurrence probability, and P(B) is the second occurrence probability;

[0036] The mountain stability model is compensated and updated. The calculation expression of the updated mountain stability model is:

[0037]

[0038] Among them, L' is the updated mountain stability model, and ε is a random correction value distributed between 0 and 0.2.

[0039] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, the data early warning module obtains the current project location, calculates the corresponding current mountain erosion level and the current mountain moisture retention rate, calculates the mountain stability of the current project location according to the updated mountain stability model, sets the sixth value and the seventh value as stability thresholds, wherein the sixth value is less than the seventh value, compares the mountain stability of the current project location with the stability threshold, and issues an early warning signal according to the comparison result.

[0040] As a preferred solution of the intelligent early warning system for geological disasters based on big data analysis described in the present invention, when the mountain stability is less than the sixth value, a first early warning signal is issued, when the mountain stability is greater than or equal to the sixth value and less than the seventh value, a second early warning signal is issued, when the mountain stability is greater than or equal to the seventh value, a third early warning signal is issued, and the mountain stability of the current project location and the second number of the current project location are displayed on the OLED display screen.

[0041] The beneficial effects of the present invention are as follows: by integrating multiple data sources, such as rivers, projects and terrain, it is possible to provide more accurate geological disaster warnings, effectively reduce false alarms and missed alarms, and possess real-time data collection and dynamic update functions, so that the mountain stability model can be adjusted according to the latest data and conditions to ensure the timeliness of the warning information. By constructing the mountain stability model and dividing the erosion levels, it is possible to effectively identify high-risk areas, provide a scientific basis for decision makers, and guide engineering design and renovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 A basic flow chart of a geological disaster intelligent early warning system based on big data analysis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] 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 drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0044] Example, see Figure 1 , which is an embodiment of the present invention, provides a geological disaster intelligent early warning system based on big data analysis, including a data acquisition module, a data analysis module and a data early warning module;

[0045] The data acquisition module obtains a river pipe network map and a project distribution map of the area to be tested, wherein the river pipe network map includes flow direction, flow rate and segment nodes, and the segment nodes are first numbered. The project distribution map includes project types and project locations, and the project distribution map is mapped to the river pipe network map, and the project types and project locations are marked in the river pipe network map, and the project locations are second numbered, and a first distance between the project location and the corresponding river is obtained, a radiation radius is set, and an impact circumference area is constructed;

[0046] The data analysis module obtains an altitude distribution map of the impact circular area, obtains terrain undulations based on the altitude distribution map, analyzes the terrain undulations, obtains a correlation between the project location and the mountain, obtains the water retention rate of the mountain based on the correlation between the project location and the mountain, calculates a third distance between the mountain and the corresponding river, sets an erosion threshold, divides the erosion degree of the mountain based on the erosion threshold, obtains the erosion grade of the mountain, constructs a mountain stability model based on the erosion grade of the mountain and the water retention rate of the mountain, sets random events, calculates the probability of occurrence of the random events, and compensates and updates the mountain stability model based on the probability of occurrence of the random events;

[0047] The data warning module calculates the mountain stability of the current project location according to the updated mountain stability model, sets a stability threshold, compares the mountain stability of the current project location with the stability threshold, and issues a warning signal according to the comparison result.

[0048] By integrating multiple data sources, such as rivers, projects and terrain, the present invention can provide more accurate geological disaster warnings, effectively reduce false alarms and missed alarms, and has real-time data collection and dynamic update functions, so that the mountain stability model can be adjusted according to the latest data and conditions to ensure the timeliness of the warning information. Through the construction of the mountain stability model and the classification of erosion levels, high-risk areas can be effectively identified, providing a scientific basis for decision makers and guiding engineering design and transformation.

[0049] The data acquisition module obtains the river network map and engineering distribution map of the area to be tested;

[0050] The river network diagram includes flow direction, flow rate and segment nodes. The sub-river network is divided according to the segment nodes. The segment nodes are represented as demarcation points that decrease with the difference of the first flow gradient. The value of the first flow gradient is obtained through big data analysis. The sub-river network between adjacent segment nodes is regarded as a whole. The segment nodes are first numbered. The first number is represented as Xi. The sub-river network is represented as XiXi+1, where i is a natural number. The project distribution map includes project types and project locations.

[0051] Mapping the project distribution map to the river pipe network map, marking the project types and project locations in the river pipe network map, and assigning a second number to the project locations, wherein the second number is represented by Yj, where j is a natural number;

[0052] A first distance between the project location and the corresponding river is obtained, and a first value is set as a radiation radius. The first value is obtained by calculating the radius of the radiation range of historical geological disasters to construct an impact circular area.

[0053] In specific implementation, by combining the river network map with the project distribution map, comprehensive monitoring of the area to be tested can be achieved, providing basic data for subsequent analysis. The river segmentation method based on the first flow gradient enables the system to more accurately reflect the dynamic changes of the river, making it easier to understand the impact of water flow on geological disasters. By calculating the distance between the project location and the river and combining historical disaster data, the risk of the project to potential geological disasters can be accurately assessed, providing an important basis for decision-making, affecting the structure of the circumferential area, helping to identify areas that may be affected within a certain radius, and facilitating the adoption of corresponding prevention and response measures.

[0054] The logic of mapping the engineering distribution map to the river network map includes:

[0055] Obtain a river network map, calculate the proportion of the area to be tested in the river network map, record it as a first ratio, obtain a project distribution map, calculate the proportion of the area to be tested in the project distribution map, record it as a second ratio, calculate the ratio of the first ratio to the second ratio, record it as a third ratio, amplify the project distribution map according to the third ratio to obtain a first image, overlap and move the first image with the river network map until the area to be tested in the first image overlaps with the area to be tested in the river network map, stop moving the first image, map the project type and project location in the first image to the river network map, and mark them in the corresponding sub-river network, establish a first mapping relationship between the project location and the corresponding sub-river network, and the expression of the first mapping relationship is:

[0056] Y j →X i X i+1 .

[0057] The calculation logic of the first distance includes:

[0058] Obtain the project location, match the corresponding sub-river network according to the first mapping relationship, set the midpoint of the sub-river network as the reference point, the project location is represented by the location of the geometric center of the project, and the distance between the project location and the reference point is calculated by the distance formula, which is recorded as the first distance.

[0059] In the specific implementation, by accurately mapping the project distribution map with the river network map, the spatial correlation between the two is ensured, providing an effective basis for subsequent geological analysis. The mapping process enables different types of data (such as project location and river information) to be intuitively displayed in the same layer, which is convenient for users to understand and analyze. By marking the type and location of the project, potential geological risks can be identified more accurately. Especially in the assessment of the impact of hydrological changes on the project, the third ratio is used to magnify the image, so that the system can dynamically adjust the proportion of the image according to the actual proportion, ensuring the accuracy of the mapping, and realizing the effective integration of project distribution and hydrological information, providing data support for the formulation of comprehensive geological disaster management and response strategies.

[0060] The data analysis module obtains an altitude distribution map of the impact circumference area, and obtains terrain undulation conditions according to the altitude distribution map, wherein the terrain undulation conditions include peaks, flatness, and gullies, and the analysis logic of the terrain undulation conditions includes:

[0061] Acquire contour lines in an altitude distribution map, extract a first feature value of the contour line through machine vision, the first feature value of the contour line is expressed as a shape feature value of the contour line, retrieve a standard contour shape database, the standard contour shape database contains terrain undulation conditions and corresponding contour distribution maps, obtain any contour line graph, record it as a reference, extract a second feature value of the reference through machine vision, the second feature value of the reference is expressed as a shape feature value of the reference, calculate the similarity of the first feature value and the second feature value through a pre-similarity formula, traverse the similarity, sort the similarity in descending order, select the reference corresponding to the similarity with the largest value, set its corresponding terrain state as the current terrain undulation condition, the terrain undulation condition includes peaks, flatness and gullies, and use different color blocks to paint different terrain undulation conditions in the affected circular area, which are respectively recorded as the first key color block, the second key color block and the third key color block;

[0062] When the contour lines are dense and in the shape of closed circles, the terrain undulation is set to a peak; when the contour lines are widely spaced and parallel, the terrain undulation is set to flat; the large interval between contour lines is indicated as being greater than or equal to a second value, and the second value is obtained through expert experience; when the contour lines are in a "V" shape, the terrain undulation is set to a gully; the density of the contour lines is directly proportional to the color value of the first key color block, the interval distance of the contour lines is inversely proportional to the color value of the second key color block, the "V"-shaped depth of the contour lines is directly proportional to the color value of the third color block, and the color value of the first key color block is greater than or equal to the color value of the second key color block, and the color value of the second key color block is greater than or equal to the color value of the third key color block.

[0063] In the specific implementation, contour line features are extracted by machine vision and compared with the standard database, which can accurately identify different terrain undulations and improve the accuracy of terrain analysis. The similarity calculation is used to compare the contour line shapes to judge the terrain state more scientifically and avoid errors caused by subjective judgment. Different color blocks represent different terrain states, making the terrain features more intuitive on the map and easy to quickly identify and understand. According to the characteristics and density changes of the contour lines, the undulation of the terrain can be dynamically reflected to adapt to the analysis needs under different terrain conditions. The combination of geographic information science, machine vision and big data analysis provides new ideas and methods for future geographic information system (GIS) applications.

[0064] The data analysis module analyzes the terrain undulation to obtain the correlation between the project location and the mountain, wherein the correlation includes that the project location is not adjacent to the mountain, the project location is located on the sunny slope of the mountain, and the project location is located on the shady slope of the mountain. The analysis logic of the correlation between the project location and the mountain includes:

[0065] Obtain the project location and the corresponding first key color block, second key color block and third key color block, obtain the color values ​​of the first key color block, second key color block and third key color block, construct a fan map of the project location, the fan map takes the project location as the vertex, takes the minimum length covering three color blocks as the radius, takes the direction of the fan as the positive direction, takes the third value as the search length, sets the color tolerance, starts from the vertex and searches for the color value in the positive direction, calculates the difference between the color values ​​of adjacent searches, and records it as the first difference, the color tolerance is expressed as the maximum difference of the color value change when the terrain is not undulating, and the color critical difference represents the color difference of a standard high mountain;

[0066] When the first difference is less than or equal to the third value, the association relationship between the project location and the mountain is that the project location is not adjacent to the mountain; when the first difference is greater than the third value and the positive direction is south, the association relationship between the project location and the mountain is that the project location is located on the sunny slope of the mountain; when the first difference is greater than the third value and the positive direction is north, the association relationship between the project location and the mountain is that the project location is located on the shady slope of the mountain.

[0067] In specific implementation, the relationship between the project location and the mountain can be more accurately identified through the difference in color values, ensuring the scientific nature of the analysis results. The construction of the fan map makes the analysis process more intuitive, which helps decision makers quickly understand the relationship between the project location and the surrounding terrain. According to the changes in color difference and orientation, different terrain conditions can be flexibly judged, which improves the adaptability of the analysis. The objective color value difference is used for judgment, which reduces the errors that may be caused by human subjective judgment and improves the reliability of data analysis. By clarifying the relationship between the project location and the mountain, data support is provided for project planning, environmental impact assessment and potential risk analysis, ensuring the safety and feasibility of the project.

[0068] The water retention rate of the mountain is obtained according to the correlation between the project location and the mountain. The water retention rate includes the water retention rate of the sunny slope and the water retention rate of the shady slope. The logic for obtaining the water retention rate includes:

[0069] Collect the soil moisture content of the sunny slope and the soil moisture content of the shady slope of the mountain, obtain the average daily rainfall in the area to be tested, calculate the ratio of the average daily rainfall to the soil moisture content of the sunny slope, record it as the moisture retention rate of the sunny slope, calculate the ratio of the first loss difference to the average daily rainfall, record it as the moisture retention rate of the sunny slope, calculate the ratio of the average daily rainfall to the soil moisture content of the shady slope, record it as the moisture retention rate of the shady slope;

[0070] When the association relationship is that the project location is located on the sunny slope of the mountain or the project location is located on the shady slope of the mountain, the color values ​​are sorted in descending order, and the position corresponding to the color value with the largest value is selected and set as the peak point. The peak point is used as the mountain reference point, and the distance between the mountain reference point and the corresponding river is calculated by the distance formula, which is recorded as the third distance. The fourth value and the fifth value are set as the erosion critical value, wherein the fourth value is less than the fifth value. The erosion critical value is expressed as the distance corresponding to the degree of erosion of the mountain by the river. The erosion degree of the mountain is obtained through expert experience, and the erosion level of the mountain is obtained by dividing the erosion degree according to the erosion critical value. The division logic of the erosion level includes:

[0071] When the third distance is less than or equal to the fourth value, the erosion level is set to the first erosion level; when the third distance is greater than the fourth value and less than or equal to the fifth value, the erosion level is set to the second erosion level; when the third distance is greater than the fifth value, the erosion level is set to the third erosion level;

[0072] A mountain stability model is constructed according to the erosion grade of the mountain and the water retention rate of the mountain. The construction logic of the mountain stability model includes:

[0073] The historical landslide values ​​were obtained, and the total number of historical landslides was counted. The historical landslide values ​​were scored by experts according to the severity of the landslides. The corresponding historical mountain erosion grade and historical mountain water retention rate were calculated. The historical landslide values ​​were used as dependent variables, and the historical mountain erosion grade and historical mountain water retention rate were used as independent variables. Multiple regression analysis was performed to obtain a mountain stability model. The expression of the mountain stability model is:

[0074]

[0075] Among them, L is the historical landslide value, n is the number of independent variables, m is k is the kth independent variable, C k is the coefficient of the kth independent variable.

[0076] In specific implementation, by analyzing the soil moisture content of the sunny and shady slopes, the water retention capacity of the mountain can be more accurately evaluated, which is helpful for soil and water conservation and ecological environment protection. The erosion critical value is set according to the distance and expert experience. Combined with the influence of the river, the erosion condition of the mountain is scientifically evaluated for targeted governance. Through multivariate regression analysis, a stability model is constructed to effectively predict the possibility of mountain collapse and help formulate corresponding prevention and control measures. The setting of color values ​​and peak points makes the complex analysis process more intuitive, which helps relevant personnel quickly understand and apply the analysis results.

[0077] The data analysis module sets random events, which include heavy rain, blizzard and typhoon, and calculates the probability of occurrence of random events. The calculation logic of the probability of occurrence includes:

[0078] The number of days of the random event is obtained, recorded as the first day, the ratio of the first day to the number of days in a year is calculated, and the ratio of the first day to the number of days in a year is set as the first occurrence probability, the weather corresponding to the historical landslide value is obtained, and the weather corresponding to the historical landslide value is compared with the random event, the number of occurrences of the random event is counted, and the ratio of the number of occurrences of the random event to the total number of historical landslides is calculated, and the second occurrence probability is calculated. According to the conditional probability formula, the comprehensive probability is calculated, and the calculation expression of the comprehensive probability is:

[0079]

[0080] Among them, P(A|B) is the comprehensive probability, P(AB) is the overlapping probability of the first occurrence probability and the second occurrence probability, and P(B) is the second occurrence probability;

[0081] The mountain stability model is compensated and updated. The calculation expression of the updated mountain stability model is:

[0082]

[0083] Among them, L' is the updated mountain stability model, and ε is a random correction value distributed between 0 and 0.2.

[0084] In the specific implementation, by quantifying the probability of occurrence of random events such as heavy rainfall, blizzards and typhoons, the potential impact of these natural events on mountain stability is scientifically assessed, so that corresponding prevention and response measures can be made. The introduction of comparative analysis of historical collapse data and weather events makes the probability calculation more accurate and reliable, and enhances the predictive ability of the model. Through the dynamic update of the mountain stability model, the latest impact of random events is reflected in a timely manner, so as to maintain the accuracy and effectiveness of the model under different climatic conditions. Through the simple form of probability calculation and model update expression, non-professionals can also understand the analysis logic of mountain stability, which is conducive to promotion and application.

[0085] The data warning module obtains the current project location, calculates the corresponding current mountain erosion level and the current mountain moisture retention rate, calculates the mountain stability of the current project location according to the updated mountain stability model, sets the sixth value and the seventh value as stability thresholds, wherein the sixth value is less than the seventh value, compares the mountain stability of the current project location with the stability threshold, and issues a warning signal based on the comparison result.

[0086] When the mountain stability is less than the sixth value, a first warning signal is issued; when the mountain stability is greater than or equal to the sixth value and less than the seventh value, a second warning signal is issued; when the mountain stability is greater than or equal to the seventh value, a third warning signal is issued, and the mountain stability of the current project location and the second number of the current project location are displayed on the OLED display.

[0087] In specific implementation, through a multi-level early warning mechanism, early warnings can be issued in a timely manner at different stability stages to ensure that relevant personnel can quickly take corresponding measures, support dynamic monitoring of mountain stability, and be able to update and feedback based on real-time data to improve management effectiveness. The timely issuance of early warning signals can effectively prevent geological disasters such as landslides, improve the safety of engineering operations, and reduce casualties and property losses.

[0088] By integrating multiple data sources, such as rivers, projects and terrain, the present invention can provide more accurate geological disaster warnings, effectively reduce false alarms and missed alarms, and has real-time data collection and dynamic update functions, so that the mountain stability model can be adjusted according to the latest data and conditions to ensure the timeliness of the warning information. Through the construction of the mountain stability model and the classification of erosion levels, high-risk areas can be effectively identified, providing a scientific basis for decision makers and guiding engineering design and transformation.

[0089] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0090] 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. An intelligent early warning system for geological disasters based on big data analysis, characterized in that: Including data collection module, data analysis module and data early warning module; The data acquisition module obtains a river pipe network map and a project distribution map of the area to be tested, wherein the river pipe network map includes flow direction, flow rate and segment nodes, and the segment nodes are first numbered. The project distribution map includes project types and project locations, and the project distribution map is mapped to the river pipe network map, and the project types and project locations are marked in the river pipe network map, and the project locations are second numbered, and a first distance between the project location and the corresponding river is obtained, a radiation radius is set, and an impact circumference area is constructed; The data analysis module obtains an altitude distribution map of the impact circular area, obtains terrain undulations based on the altitude distribution map, analyzes the terrain undulations, obtains a correlation between the project location and the mountain, obtains the water retention rate of the mountain based on the correlation between the project location and the mountain, calculates a third distance between the mountain and the corresponding river, sets an erosion threshold, divides the erosion degree of the mountain based on the erosion threshold, obtains the erosion grade of the mountain, constructs a mountain stability model based on the erosion grade of the mountain and the water retention rate of the mountain, sets random events, calculates the probability of occurrence of the random events, and compensates and updates the mountain stability model based on the probability of occurrence of the random events; The data warning module calculates the mountain stability of the current project location according to the updated mountain stability model, sets a stability threshold, compares the mountain stability of the current project location with the stability threshold, and issues a warning signal according to the comparison result.

2. The intelligent early warning system for geological disasters based on big data analysis as claimed in claim 1, characterized in that: The data acquisition module obtains the river network map and engineering distribution map of the area to be tested; The river network diagram includes flow direction, flow rate and segment nodes. The sub-river network is divided according to the segment nodes. The segment nodes are represented as demarcation points that decrease with the difference of the first flow gradient. The value of the first flow gradient is obtained through big data analysis. The sub-river network between adjacent segment nodes is regarded as a whole. The segment nodes are first numbered, and the first number is represented by X. i , the sub-river network is represented by X i X i+1 , where i is a natural number, and the project distribution map includes project types and project locations; The project distribution map is mapped to the river pipe network map, and the project type and project location are marked in the river pipe network map, and the project location is given a second number, and the second number is represented by Y j , where j is a natural number; A first distance between the project location and the corresponding river is obtained, and a first value is set as a radiation radius. The first value is obtained by calculating the radius of the radiation range of historical geological disasters to construct an impact circular area.

3. The intelligent early warning system for geological disasters based on big data analysis as claimed in claim 2, characterized in that: The logic of mapping the engineering distribution map to the river network map includes: Obtain a river network map, calculate the proportion of the area to be tested in the river network map, record it as a first ratio, obtain a project distribution map, calculate the proportion of the area to be tested in the project distribution map, record it as a second ratio, calculate the ratio of the first ratio to the second ratio, record it as a third ratio, amplify the project distribution map according to the third ratio to obtain a first image, overlap and move the first image with the river network map until the area to be tested in the first image overlaps with the area to be tested in the river network map, stop moving the first image, map the project type and project location in the first image to the river network map, and mark them in the corresponding sub-river network, establish a first mapping relationship between the project location and the corresponding sub-river network, and the expression of the first mapping relationship is: AND j →X i X i+1 。 4. The intelligent early warning system for geological disasters based on big data analysis as claimed in claim 2, characterized in that: The calculation logic of the first distance includes: Obtain the project location, match the corresponding sub-river network according to the first mapping relationship, set the midpoint of the sub-river network as the reference point, the project location is represented by the location of the geometric center of the project, and the distance between the project location and the reference point is calculated by the distance formula, which is recorded as the first distance.

5. The intelligent early warning system for geological disasters based on big data analysis according to claim 1, characterized in that: The data analysis module obtains an altitude distribution map of the impact circumference area, and obtains terrain undulation conditions according to the altitude distribution map, wherein the terrain undulation conditions include peaks, flatness, and gullies, and the analysis logic of the terrain undulation conditions includes: Acquire contour lines in an altitude distribution map, extract a first feature value of the contour line through machine vision, the first feature value of the contour line is expressed as a shape feature value of the contour line, retrieve a standard contour shape database, the standard contour shape database contains terrain undulation conditions and corresponding contour distribution maps, obtain any contour line graph, record it as a reference, extract a second feature value of the reference through machine vision, the second feature value of the reference is expressed as a shape feature value of the reference, calculate the similarity of the first feature value and the second feature value through a pre-similarity formula, traverse the similarity, sort the similarity in descending order, select the reference corresponding to the similarity with the largest value, set its corresponding terrain state as the current terrain undulation condition, the terrain undulation condition includes peaks, flatness and gullies, and use different color blocks to paint different terrain undulation conditions in the affected circular area, which are respectively recorded as the first key color block, the second key color block and the third key color block; When the contour lines are dense and in the shape of closed circles, the terrain undulation is set to a peak; when the contour lines are widely spaced and parallel, the terrain undulation is set to a flat state; the large interval between contour lines is indicated as being greater than or equal to a second value, and the second value is obtained through expert experience; when the contour lines are in a "V" shape, the terrain undulation is set to a gully; the density of the contour lines is directly proportional to the color value of the first key color block, the interval distance of the contour lines is inversely proportional to the color value of the second key color block, the "V"-shaped depth of the contour lines is directly proportional to the color value of the third color block, and the color value of the first key color block is greater than or equal to the color value of the second key color block, and the color value of the second key color block is greater than or equal to the color value of the third key color block.

6. The intelligent early warning system for geological disasters based on big data analysis as claimed in claim 5, characterized in that: The data analysis module analyzes the terrain undulations to obtain the correlation between the project location and the mountain, wherein the correlation includes that the project location is not adjacent to the mountain, the project location is located on the sunny slope of the mountain, and the project location is located on the shady slope of the mountain. The analysis logic of the correlation between the project location and the mountain includes: Obtain the project location and the corresponding first key color block, second key color block and third key color block, obtain the color values ​​of the first key color block, second key color block and third key color block, construct a fan map of the project location, the fan map takes the project location as the vertex, takes the minimum length covering three color blocks as the radius, takes the direction of the fan as the positive direction, takes the third value as the search length, sets the color tolerance, starts from the vertex and searches for the color value in the positive direction, calculates the difference between the color values ​​of adjacent searches, and records it as the first difference, the color tolerance is expressed as the maximum difference of the color value change when the terrain is not undulating, and the color critical difference represents the color difference of a standard high mountain; When the first difference is less than or equal to the third value, the association relationship between the project location and the mountain is that the project location is not adjacent to the mountain; when the first difference is greater than the third value and the positive direction is south, the association relationship between the project location and the mountain is that the project location is located on the sunny slope of the mountain; when the first difference is greater than the third value and the positive direction is north, the association relationship between the project location and the mountain is that the project location is located on the shady slope of the mountain.

7. The intelligent early warning system for geological disasters based on big data analysis according to claim 6, characterized in that: The water retention rate of the mountain is obtained according to the correlation between the project location and the mountain. The water retention rate includes the water retention rate of the sunny slope and the water retention rate of the shady slope. The logic for obtaining the water retention rate includes: Collect the soil moisture content of the sunny slope and the soil moisture content of the shady slope of the mountain, obtain the average daily rainfall in the area to be tested, calculate the ratio of the average daily rainfall to the soil moisture content of the sunny slope, record it as the moisture retention rate of the sunny slope, calculate the ratio of the first loss difference to the average daily rainfall, record it as the moisture retention rate of the sunny slope, calculate the ratio of the average daily rainfall to the soil moisture content of the shady slope, record it as the moisture retention rate of the shady slope; When the association relationship is that the project location is located on the sunny slope of the mountain or the project location is located on the shady slope of the mountain, the color values ​​are sorted in descending order, and the position corresponding to the color value with the largest value is selected and set as the peak point. The peak point is used as the mountain reference point, and the distance between the mountain reference point and the corresponding river is calculated by the distance formula, which is recorded as the third distance. The fourth value and the fifth value are set as the erosion critical value, wherein the fourth value is less than the fifth value. The erosion critical value is expressed as the distance corresponding to the degree of erosion of the mountain by the river. The erosion degree of the mountain is obtained through expert experience, and the erosion level of the mountain is obtained by dividing the erosion degree according to the erosion critical value. The division logic of the erosion level includes: When the third distance is less than or equal to the fourth value, the erosion level is set to the first erosion level; when the third distance is greater than the fourth value and less than or equal to the fifth value, the erosion level is set to the second erosion level; when the third distance is greater than the fifth value, the erosion level is set to the third erosion level; A mountain stability model is constructed according to the erosion grade of the mountain and the water retention rate of the mountain. The construction logic of the mountain stability model includes: The historical landslide values ​​were obtained, and the total number of historical landslides was counted. The historical landslide values ​​were scored by experts according to the severity of the landslides. The corresponding historical mountain erosion grade and historical mountain water retention rate were calculated. The historical landslide values ​​were used as dependent variables, and the historical mountain erosion grade and historical mountain water retention rate were used as independent variables. Multiple regression analysis was performed to obtain a mountain stability model. The expression of the mountain stability model is: Among them, L is the historical landslide value, n is the number of independent variables, m is k is the kth independent variable, C k is the coefficient of the kth independent variable.

8. The intelligent early warning system for geological disasters based on big data analysis according to claim 1, characterized in that: The data analysis module sets random events, which include heavy rain, blizzard and typhoon, and calculates the probability of occurrence of random events. The calculation logic of the probability of occurrence includes: The number of days of the random event is obtained, recorded as the first day, the ratio of the first day to the number of days in a year is calculated, and the ratio of the first day to the number of days in a year is set as the first occurrence probability, the weather corresponding to the historical landslide value is obtained, and the weather corresponding to the historical landslide value is compared with the random event, the number of occurrences of the random event is counted, and the ratio of the number of occurrences of the random event to the total number of historical landslides is calculated, and the second occurrence probability is calculated. According to the conditional probability formula, the comprehensive probability is calculated, and the calculation expression of the comprehensive probability is: Among them, P(A|B) is the comprehensive probability, P(AB) is the overlapping probability of the first occurrence probability and the second occurrence probability, and P(B) is the second occurrence probability; The mountain stability model is compensated and updated. The calculation expression of the updated mountain stability model is: Among them, L' is the updated mountain stability model, and ε is a random correction value distributed between 0 and 0.

2.

9. The intelligent early warning system for geological disasters based on big data analysis according to claim 1, characterized in that: The data warning module obtains the current project location, calculates the corresponding current mountain erosion level and the current mountain moisture retention rate, calculates the mountain stability of the current project location according to the updated mountain stability model, sets the sixth value and the seventh value as stability thresholds, wherein the sixth value is less than the seventh value, compares the mountain stability of the current project location with the stability threshold, and issues a warning signal based on the comparison result.

10. The intelligent early warning system for geological disasters based on big data analysis according to claim 9, characterized in that: When the mountain stability is less than the sixth value, a first warning signal is issued; when the mountain stability is greater than or equal to the sixth value and less than the seventh value, a second warning signal is issued; when the mountain stability is greater than or equal to the seventh value, a third warning signal is issued, and the mountain stability of the current project location and the second number of the current project location are displayed on the OLED display.

Images