An artificial intelligence-based geological disaster monitoring and early warning method and system

Abstract

The present invention discloses a method and system for geological disaster monitoring and early warning based on artificial intelligence, which relates to the technical field of geological data processing. It includes establishing a matching relationship between geological disasters and geological features, so as to accurately adapt all relevant geological features corresponding to each geological disaster, providing a reliable basis for subsequent monitoring and early warning of geological disasters. Set the geological feature early warning values of each type of geological disaster under each geological disaster hidden danger point, integrate multiple geological disasters with cross or intersection relationships to form the location conditions of multiple geological disaster hidden danger points, and evaluate the risk levels of geological disaster hidden danger points to ensure the timeliness of geological disaster early warning. Adjust the geological feature early warning values of geological disasters according to the geological disaster impact chain, consider the mutual influence between geological disasters, and set the early warning value lead of the affected geological disasters to adjust the early warning values accordingly. It improves the accuracy of geological disaster monitoring, the advance and timeliness of early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of geological data processing, and particularly to a geological disaster monitoring and early warning method and system based on artificial intelligence. Background Art

[0002] With the intensification of global climate change and human activities, geological disasters occur frequently, posing a serious threat to the safety of people's lives and property. There are many limitations in traditional geological disaster monitoring means, such as limited monitoring scope and insufficient early warning accuracy. The rapid development of artificial intelligence technology provides a new solution for geological disaster monitoring and early warning. By integrating advanced technologies such as big data, Internet of Things, and cloud computing, artificial intelligence can monitor and analyze a large amount of environmental monitoring data in real time, such as rainfall, soil humidity, and seismic waveforms.

[0003] In the prior art, the geological disaster situation is often monitored according to the threshold of geological features, which is often fixed and does not consider the mutual influence between different geological disasters, resulting in poor accuracy of geological disaster monitoring, low advance and timeliness of early warning, and inability to effectively ensure the safety protection of geological disasters.

[0004] Therefore, how to improve the accuracy of geological disaster monitoring, the advance and timeliness of early warning is a technical problem to be solved at present. Summary of the Invention

[0005] The object of the present invention is to solve the problems in the prior art that the threshold of geological features is fixed and the mutual influence between different geological disasters is not considered, resulting in poor accuracy of geological disaster monitoring, low advance and timeliness of early warning, and a geological disaster monitoring and early warning method based on artificial intelligence is proposed, which includes:

[0006] Collect geological information in the target area, extract geological features of all categories of geological information, and match the geological feature categories with geological disaster categories to establish a matching relationship between geological disasters and geological features;

[0007] Construct a map of the target area, mark geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological features, and determine geological disaster hidden danger points of different risk levels;

[0008] Set the geological feature early warning value of each type of geological disaster under each geological disaster hidden danger point, and construct a geological disaster impact chain for each geological disaster hidden danger point;

[0009] Adjust the geological feature early warning value of geological disasters according to the geological disaster impact chain, so as to realize the monitoring and early warning of geological disasters.

[0010] In some embodiments of the present application, the geological feature categories are matched with the geological disaster categories to establish a matching relationship between geological disasters and geological features, including,

[0011] Obtain the cause information of each geological disaster category, decompose the cause information into multiple conditions, connect the multiple conditions to form the process of the geological disaster, with the conditions as the nodes in the process, confirm the geological feature categories under each node, and thus determine a type of geological feature;

[0012] Record the geological features other than a type of geological feature as other geological features, calculate the linear correlation degree between a type of geological feature and other geological features, and screen out the second type of geological features;

[0013] Calculate the non - linear correlation degree according to a type of geological feature, the function of the preset radial basis function kernel, and other geological features, and screen out the second type of geological features;

[0014] Match each geological disaster category with its corresponding first - type geological features and second - type geological features, thereby establishing a matching relationship between geological disasters and geological features.

[0015] In some embodiments of the present application, geological disasters are marked one by one on the map of the target area through the matching relationship between geological disasters and geological features, including,

[0016] Collect the historical occurrence records of geological disasters, mark them on the map of the target area according to the historical occurrence records of geological disasters, perform the matching of the first - type geological features and the second - type geological features on the map of the target area through the matching relationship between geological disasters and geological features, and calculate the geological feature matching degree;

[0017] Perform an overlay analysis of the historical occurrence records of geological disasters and the geological feature matching degree on the map of the target area to determine the geological disaster category and the specific location of the geological disaster.

[0018] In some embodiments of the present application, geological disaster potential points with different risk levels are determined, including,

[0019] Form geological disaster areas based on the specific locations of geological disasters, evaluate the influence range and hazard degree of each geological disaster area, record the relationship that there is an intersection between geological disaster areas or an intersection between the influence ranges of geological disaster areas as an intersection relationship, calculate the intersection degree between different geological disasters in the intersection relationship, and each intersection relationship corresponds to a geological disaster potential point;

[0020] Calculate the risk index of the geological disaster potential point according to the hazard degree of each geological disaster area and the intersection degree between different geological disasters in the intersection relationship, thereby determining the risk level of the geological disaster potential point;

[0021] ;

[0022] Wherein, is the risk index of the th geological hazard hidden danger point, is the number of geological disasters under the th geological hazard hidden danger point, is the risk weight of the th geological disaster, is the hazard degree of the th geological disaster under the th geological hazard hidden danger point, , are respectively the weights of the influence degrees of the intersection degree and the geological disaster with the greatest influence, is the maximum value in, is a preset constant.

[0023] In some embodiments of the present application, the geological feature warning values of each type of geological disaster under each geological hazard hidden danger point are set, including,

[0024] Collect the historical value ranges of each type of geological feature in the historical occurrence records of geological disasters, intercept the historical value ranges of each type of geological feature at the time of geological disaster occurrence, determine the average historical value ranges of each type of geological feature, and determine the first warning value of each type of geological feature according to the average historical value ranges;

[0025] Calculate the average value and standard deviation of the geological features according to the historical value ranges of each type of geological feature at the time of geological disaster occurrence, map a multiple through the risk level of the geological hazard hidden danger point, and determine the second warning value of each type of geological feature by combining the average value, standard deviation and multiple of the geological features;

[0026] Set the geological feature warning values of each type of geological disaster according to the first warning value and the second warning value of each type of geological feature.

[0027] In some embodiments of the present application, for each geological hazard hidden danger point, a geological disaster impact chain is constructed, including,

[0028] Analyze the causal relationships between multiple geological disasters under each geological hazard hidden danger point, use each geological disaster as an event node in the geological disaster impact chain, connect the event nodes with line segments according to the causal relationships, and assign different lengths to the line segments according to the influence degrees between the event nodes, so as to construct the geological disaster impact chain.

[0029] In some embodiments of the present application, before adjusting the geological feature warning value of the geological disaster according to the geological disaster impact chain, the method further includes,

[0030] Define the state spaces of the non-occurrence state and the occurrence state of each geological disaster according to geological characteristics, and calculate the state transition probability of the evolution of the non-occurrence state of the geological disaster to the occurrence state at the current time according to a preset period;

[0031] Based on the state transition probability, determine whether there is an impending geological disaster. If there is an impending geological disaster, adjust the geological characteristic warning value of the geological disaster according to the geological disaster impact chain;

[0032] Otherwise, do not adjust the geological characteristic warning value of the geological disaster.

[0033] In some embodiments of the present application, adjusting the geological characteristic warning value of the geological disaster according to the geological disaster impact chain includes,

[0034] Determine the geological disasters affected by the impending geological disaster and the degree of influence in the geological disaster impact chain, and determine the advance amount of the geological characteristic warning value of the geological disaster affected by the impending geological disaster;

[0035] ;

[0036] Among them, is the advance amount of the geological characteristic warning value of the th impending geological disaster on the th geological disaster it affects, is the state transition probability of the th geological disaster affected, is the initial advance amount of the geological characteristic warning value of the th geological disaster affected by the th impending geological disaster, is the influence adjustment conversion coefficient of the th geological disaster affected by the th impending geological disaster, is the degree of influence of the th impending geological disaster on the

[0037] Adjust the geological characteristic warning value through the advance amount of the geological characteristic warning value, so as to conduct timely monitoring and early warning of geological disasters.

[0038] Correspondingly, the present application also provides an artificial intelligence-based geological disaster monitoring and early warning system, including,

[0039] A matching module, configured to collect geological information in the target area, extract geological characteristics of all categories of geological information, and match the geological characteristic categories with geological disaster categories to establish a matching relationship between geological disasters and geological characteristics;

[0040] A risk module, which is used to construct a map of the target area, mark geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological features, and determine the hidden danger points of geological disasters with different risk levels;

[0041] A construction module, which is used to set the geological feature warning values of each type of geological disaster under each hidden danger point of geological disasters, and construct a geological disaster impact chain for each hidden danger point of geological disasters;

[0042] A monitoring module, which is used to adjust the geological feature warning values of geological disasters according to the geological disaster impact chain, so as to realize the monitoring and early warning of geological disasters.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0044] 1. Establish a matching relationship between geological disasters and geological features, so as to accurately adapt all relevant geological features corresponding to each geological disaster, providing a reliable basis for the subsequent monitoring and early warning of geological disasters. Determine the hidden danger points of geological disasters with different risk levels, set the geological feature warning values of each type of geological disaster under each hidden danger point of geological disasters, integrate multiple geological disasters with cross or intersection relationships, form the location conditions of multiple hidden danger points of geological disasters, and evaluate the risk levels of the hidden danger points of geological disasters, which is convenient for setting the warning values of subsequent geological features and ensures the timeliness of geological disaster early warning.

[0045] 2. Construct a geological disaster impact chain, adjust the geological feature warning values of geological disasters according to the geological disaster impact chain, consider the mutual influence between geological disasters, set the advance amount of the warning value of the affected geological disaster, and adjust the warning value accordingly. Improve the accuracy of geological disaster monitoring, the advance and timeliness of early warning, ensure that geological disasters can be monitored in a timely, effective and accurate manner, and facilitate the early setting of safety measures. Description of the Drawings

[0046] Figure 1 It is a schematic flow chart of a method for monitoring and early warning of geological disasters based on artificial intelligence proposed by the present invention;

[0047] Figure 2 It is a schematic structural diagram of a system for monitoring and early warning of geological disasters based on artificial intelligence proposed by the present invention. Detailed Embodiments

[0048] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0049] Refer to Figure 1, A geological disaster monitoring and early warning method based on artificial intelligence, comprising the following steps:

[0050] Step S101, collect geological information within the target area, extract geological features of all categories of geological information, and match the geological feature categories with geological disaster categories to establish a matching relationship between geological disasters and geological features.

[0051] In this embodiment, it is necessary to collect geological information within the target area from multiple channels, including geological exploration reports, remote sensing image data, historical geological disaster records, meteorological data, etc. These data are the basis for subsequent analysis. Using GIS (Geographic Information System) technology, remote sensing technology, and geological knowledge, feature recognition is performed on the sorted geological information to extract geological features such as stratigraphic lithology, geological structure, topography, and hydrogeological conditions. General classification of features: The extracted geological features are classified according to their properties, such as physical features, chemical features, mechanical features, etc., and then classified into more detailed categories for subsequent matching with geological disaster categories.

[0052] In some embodiments of the present application, when matching the geological feature categories with geological disaster categories to establish a matching relationship between geological disasters and geological features, it includes,

[0053] Obtain the cause information of each geological disaster category, decompose the cause information into multiple conditions, connect the multiple conditions to form the process of the geological disaster, the conditions are used as nodes in the process, confirm the geological feature categories under each node, and thus determine a type of geological feature;

[0054] Record the geological features other than a type of geological feature as other geological features, calculate the linear correlation degree between a type of geological feature and other geological features, and screen out the second type of geological features;

[0055] Calculate the non - linear correlation degree according to a type of geological feature, the function of the preset radial basis function kernel, and other geological features, and screen out the second type of geological features;

[0056] Match each geological disaster category with its corresponding first - type geological features and second - type geological features to establish a matching relationship between geological disasters and geological features.

[0057] In this embodiment, the genetic mechanisms of each type of geological disaster are studied in depth, including the physical, chemical, and mechanical processes of their occurrence. Geological features directly related to the causes of geological disasters are identified, such as topography, stratum lithology, geological structure, hydrogeological conditions, etc., so as to extract a type of geological features. According to the results of the analysis of the genetic mechanism, a dynamic process is constructed. Each node on the process represents a key geological feature or condition, and the nodes are connected in the logical order of the occurrence of geological disasters to form a complete process. For example, for landslide disasters, a type of geological features may include steep terrain, loose rock and soil layers, abundant groundwater, etc. Taking the landslide disaster as an example, the dynamic process may include: increase in terrain slope → loosening of rock and soil layers → infiltration of groundwater → occurrence of landslide.

[0058] It can be understood that the secondary geological features are geological features with a relatively high degree of relevance to the primary geological features and can also indirectly reflect the situation of geological disasters. Statistical methods (such as Pearson correlation coefficient) are used to calculate the linear correlation between the primary geological features and other features. In addition to linear correlation, non-linear correlation also needs to be considered. Non-linear correlation indicates that there is a more complex relationship between two variables, and this relationship cannot be described by a straight line. The kernel function is a technique used in support vector machines to handle non-linear data. It can map the original data to a high-dimensional space, so that the data that is linearly inseparable in the low-dimensional space becomes linearly separable in this high-dimensional space. Radial basis function (RBF) kernel: Also known as the Gaussian kernel, it is one of the most commonly used kernel functions in SVMs and can handle complex non-linear relationships, thereby calculating non-linear correlation.

[0059] Step S102, construct a map of the target area, and mark each geological disaster on the map of the target area through the matching relationship between geological disasters and geological features to determine the potential geological disaster points of different risk levels.

[0060] In this embodiment, the GIS technology is used to construct a digital map of the target area, including topographic maps, geological maps, etc. According to the matching relationship between geological disasters and geological features, each geological disaster is marked on the map, indicating information such as the type of disaster, location, scale, etc. Geological disasters that are close in location or affect each other are integrated into a potential geological disaster point (area), and the risk level is comprehensively described by the cross situation and hazard degree of geological disasters.

[0061] In some embodiments of the present application, each geological disaster is marked on the map of the target area through the matching relationship between geological disasters and geological features, including

[0062] Collect historical occurrence records of geological disasters, mark them on the map of the target area according to the historical occurrence records of geological disasters, match the first-class geological features and the second-class geological features on the map of the target area through the matching relationship between geological disasters and geological features, and calculate the geological feature matching degree;

[0063] Conduct an overlay analysis of the historical occurrence records of geological disasters and the geological feature matching degree on the map of the target area to determine the geological disaster category and the specific location of the geological disaster.

[0064] In this embodiment, collect historical geological disaster records, including information such as disaster types (such as landslides, earthquakes, debris flows, etc.), occurrence time, location, scale, influence range, loss situation, etc. Conduct the matching of the first-class geological features and the second-class geological features, and calculate the geological feature matching degree (calculate the matching degree through the category matching situation of the first-class geological features and the second-class geological features on the map). According to the geological disaster type and occurrence mechanism, determine which geological features are key and need to be used for matching. For example, for landslide disasters, it may be necessary to pay attention to terrain slope, rock and soil type, groundwater conditions, etc.; for earthquake disasters, it may mainly focus on crustal movement, fault distribution, etc. Overlay and analyze the geological disaster records and the geological feature matching results to find the areas where historical geological disasters are prone to occur and match the geological features, and determine the areas where geological disasters may occur.

[0065] In some embodiments of the present application, determine geological disaster hidden danger points of different risk levels, including,

[0066] Form geological disaster areas according to the specific locations of geological disasters, evaluate the influence range and hazard degree of each geological disaster area, record the relationship where there is an intersection between geological disaster areas or an intersection between the influence ranges of geological disaster areas as an intersection relationship, calculate the intersection degree between different geological disasters in the intersection relationship, and each intersection relationship corresponds to a geological disaster hidden danger point;

[0067] Calculate the risk index of the geological disaster hidden danger point according to the hazard degree of each geological disaster area and the intersection degree between different geological disasters in the intersection relationship, so as to determine the risk level of the geological disaster hidden danger point;

[0068] ;

[0069] Among them, is the risk index of the th geological disaster hidden danger point, is the number of geological disasters under the th geological disaster hidden danger point, is the risk weight of the th geological disaster, is the Under the hazard degree of each geological disaster, , are the respective weights of the intersection degree and the influence degree of the geological disaster with the greatest influence, is the maximum value in is a preset constant.

[0070] In this embodiment, according to the locations of geological disasters, each geological disaster area is delimited. According to factors such as the type, scale, historical occurrence frequency, potential losses, etc. of geological disasters, the hazard degree of each area is evaluated, and technical means such as Geographic Information System (GIS) are used to evaluate the possible influence range of each geological disaster area. The intersection relationship indicates that the locations of two geological disasters are relatively close or there is mutual influence. The intersection degree is the degree of intersection of geological disaster areas or the degree of intersection of influence ranges (the intersection area of the areas), and a comprehensive value is determined by synthesizing all intersection degrees, which is the intersection degree. The essence of a geological disaster hidden danger point is an area where there are multiple different geological disasters with an intersection relationship.

[0071] It can be understood that represents the correction of the sum of the hazard degrees of multiple geological disasters by combining the intersection degree and the geological disaster with the greatest influence, is to balance the magnitude of the correction function, and different risk index intervals of geological disaster hidden danger points correspond to different risk levels of geological disaster hidden danger points.

[0072] Step S103, set the geological feature warning value of each type of geological disaster under each geological disaster hidden danger point, and construct a geological disaster influence chain for each geological disaster hidden danger point.

[0073] In this embodiment, the warning value is the threshold of geological features. When the value of the geological feature is close to this threshold, it does not mean that the geological disaster has occurred, but that the geological disaster is about to occur and is in a dangerous state.

[0074] In some embodiments of the present application, setting the geological feature warning value of each type of geological disaster under each geological disaster hidden danger point includes,

[0075] Collect the historical numerical range of each type of geological feature in the historical occurrence records of geological disasters, intercept the historical numerical range of each type of geological feature when the geological disaster occurs, determine the average historical numerical range of each type of geological feature, and determine the first warning value of each type of geological feature according to the average historical numerical range;

[0076] Calculate the average value and standard deviation of geological features based on the historical value ranges of each type of geological feature during the occurrence of geological disasters. Map a multiple through the risk level of geological disaster hidden danger points, and combine the average value, standard deviation, and multiple of geological features to determine the second warning value for each type of geological feature;

[0077] Set the geological feature warning value for each type of geological disaster according to the first warning value and the second warning value of each type of geological feature.

[0078] In this embodiment, based on the historical value ranges of each type of geological feature during the occurrence of geological disasters, determine an average historical value range, and thereby determine the first warning value of geological features. Different risk levels map to different multiples. According to the mean and standard deviation of geological feature values, initially set a warning threshold. For example, the mean plus a certain multiple of the standard deviation (such as 1.5 times or 2 times) can be used as the warning threshold. Set the geological feature warning value (weighted average) for each type of geological disaster according to the first warning value and the second warning value of each type of geological feature.

[0079] In some embodiments of the present application, a geological disaster impact chain is constructed for each geological disaster hidden danger point, including,

[0080] Analyze the causal relationships between multiple geological disasters under each geological disaster hidden danger point. Treat each geological disaster as an event node in the geological disaster impact chain, connect the event nodes with line segments according to the causal relationships, and assign different lengths to the line segments according to the influence degree between the event nodes, thereby constructing the geological disaster impact chain.

[0081] In this embodiment, analyze the relationships between different types of geological disasters under the same geological disaster hidden danger point, and identify possible geological disaster chains. For example, a landslide may trigger a debris flow, and an earthquake may trigger a landslide, a collapse, etc. Identify all possible geological disaster types involved under each geological disaster hidden danger point, such as landslides, debris flows, earthquakes, collapses, etc. Treat each disaster type as an independent event node and record it in detail. Describe the characteristics of each event node, including its occurrence conditions, triggering factors, historical occurrence frequencies, influence ranges, etc. This information will help analyze the causal relationships and influence degrees between nodes in the follow-up. Through historical data, expert experience, and on-site investigations, analyze the causal relationships between each event node. Determine which disasters may trigger other disasters, as well as their triggering mechanisms and sequences. According to the causal relationship analysis, connect the event nodes with causal relationships with line segments. The direction of the line segment represents the direction of influence, that is, from one disaster node to the next disaster node that it may trigger. Quantify the influence degree between each event node, and according to the quantification result of the influence degree, assign different lengths to the line segments connecting the event nodes. The greater the influence degree, the longer the line segment length, to visually display the relative influence intensity between different disasters.

[0082] In some embodiments of the present application, before adjusting the geological feature warning value of a geological disaster according to the geological disaster impact chain, the method further includes:

[0083] Defining two state spaces of the non-occurrence state and the occurrence state for each geological disaster according to geological features, and calculating the state transition probability of the non-occurrence state of the geological disaster evolving to the occurrence state at the current time according to a preset period;

[0084] Judging whether there is an impending geological disaster based on the state transition probability. If there is an impending geological disaster, adjusting the geological feature warning value of the geological disaster according to the geological disaster impact chain;

[0085] Otherwise, do not adjust the geological feature warning value of the geological disaster.

[0086] In this embodiment, a state is defined for each geological disaster, including two states of "not occurred" and "occurred", which constitute a state space, where each state represents a specific situation of a geological disaster. Calculate the probability of each geological disaster transferring from the "not occurred" state to the "occurred" state. These probabilities constitute a transition probability matrix, and each element in the matrix represents the probability of transferring from one state to another state. The probability of each geological disaster transferring to the occurrence state in the current state can be calculated through the steady-state distribution or time evolution formula of the Markov chain. Judging whether there is an impending geological disaster based on the state transition probability. When there is an impending geological disaster, it indicates that the geological disaster may occur soon. At this time, adjust the warning values of other geological disasters affected by this geological disaster so as to monitor the geological disaster situation in a timely manner.

[0087] Step S104, adjusting the geological feature warning value of the geological disaster according to the geological disaster impact chain to realize the monitoring and warning of the geological disaster.

[0088] In this embodiment, the lead of the geological feature warning value here is the comprehensive lead of the geological feature warning value of this type of geological disaster, and the comprehensive lead is specifically allocated according to the matching relationship between the geological feature and the geological disaster.

[0089] In some embodiments of the present application, adjusting the geological feature warning value of the geological disaster according to the geological disaster impact chain includes:

[0090] Determining the geological disasters affected by the impending geological disaster and the degree of influence in the geological disaster impact chain, and determining the lead of the geological feature warning value of the geological disaster affected by the impending geological disaster;

[0091] ;

[0092] Wherein, For the th upcoming geological disaster, the lead of the early warning value of the geological characteristics of the th geological disaster affected by it, For the state transition probability of the th geological disaster affected by it, For the initial lead of the early warning value of the geological characteristics of the th geological disaster affected by the th upcoming geological disaster, For the influence adjustment conversion coefficient of the th geological disaster affected by the th upcoming geological disaster, For the influence degree of the th geological disaster affected by the

[0093] Adjust the early warning value of geological characteristics through the lead of the early warning value of geological characteristics, so as to monitor and give early warning of geological disasters in a timely manner.

[0094] In this embodiment, "early warning threshold lead time" emphasizes the advance of the early warning value in time. Indicates the correction of the initial lead by the influence degree.

[0095] Correspondingly, the present application also provides an artificial intelligence-based geological disaster monitoring and early warning system, as Figure 2 shown, including,

[0096] A matching module, used to collect geological information in the target area, extract geological characteristics of all categories of geological information, and match the geological characteristic categories with the geological disaster categories to establish a matching relationship between geological disasters and geological characteristics;

[0097] A risk module, used to construct a map of the target area, mark geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological characteristics, and determine hidden danger points of geological disasters with different risk levels;

[0098] A construction module, used to set the early warning value of the geological characteristics of each type of geological disaster under each geological disaster hidden danger point, and construct a geological disaster influence chain for each geological disaster hidden danger point;

[0099] A monitoring module, used to adjust the early warning value of the geological characteristics of geological disasters according to the geological disaster influence chain, so as to realize the monitoring and early warning of geological disasters.

[0100] Compared with the prior art, the beneficial effects of the present invention are:

[0101] 1. Establish the matching relationship between geological disasters and geological features, so as to accurately adapt all relevant geological features corresponding to each geological disaster, providing a reliable basis for the subsequent monitoring and early warning of geological disasters. Determine the hidden danger points of geological disasters with different risk levels, set the geological feature early warning values for each type of geological disaster under each geological disaster hidden danger point, integrate multiple geological disasters with cross or intersection relationships, form the location conditions of multiple geological disaster hidden danger points, and evaluate the risk levels of geological disaster hidden danger points, which is convenient for setting the early warning values of subsequent geological features and ensuring the timeliness of geological disaster early warning.

[0102] 2. Construct the geological disaster impact chain, adjust the geological feature early warning values of geological disasters according to the geological disaster impact chain, consider the mutual influence between geological disasters, set the lead of the early warning value of the affected geological disaster, and adjust the early warning value accordingly. It improves the accuracy of geological disaster monitoring, the lead and timeliness of early warning, ensures that geological disasters can be monitored in a timely, effective and accurate manner, and is convenient for setting safety measures in advance.

[0103] Through the description of the above implementation manners, those skilled in the art can clearly understand that the present invention can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various implementation scenarios of the present invention.

[0104] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the drawings are not necessarily essential for implementing the present invention.

[0105] Those skilled in the art can understand that the modules in the system in the implementation scenario can be distributed in the system of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more systems different from the present implementation scenario. The modules in the above implementation scenario can be combined into one module, or further split into multiple sub-modules.

[0106] The above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution of the present invention and its inventive concept, makes equivalent substitutions or changes, and should be covered by the protection scope of the present invention.

Claims

1. A geological disaster monitoring and early warning method based on artificial intelligence, characterized in that, including collecting geological information within the target area, extracting geological features of all categories of geological information, matching the geological feature categories with geological disaster categories, and establishing a matching relationship between geological disasters and geological features; constructing a map of the target area, marking geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological features, and determining potential geological disaster points with different risk levels; setting geological feature warning values for each type of geological disaster under each potential geological disaster point, and constructing a geological disaster impact chain for each potential geological disaster point; adjusting the geological feature warning values of geological disasters according to the geological disaster impact chain, so as to realize the monitoring and early warning of geological disasters; wherein adjusting the geological feature warning values of geological disasters according to the geological disaster impact chain includes determining the geological disasters affected by the upcoming geological disaster and the degree of influence in the geological disaster impact chain, and determining the advance amount of the geological feature warning value of the geological disaster affected by the upcoming geological disaster; Among them, is the advance amount of the geological feature warning value of the j2th geological disaster affected by the j1th upcoming geological disaster, is the state transition probability of the j2th geological disaster affected, is the initial advance amount of the geological feature warning value of the j2th geological disaster affected by the j1th upcoming geological disaster, is the influence adjustment conversion coefficient of the j1th upcoming geological disaster on the j2th geological disaster it affects, is the influence degree of the j1th upcoming geological disaster on the j2th geological disaster it affects; adjusting the geological feature warning value through the advance amount of the geological feature warning value, so as to conduct timely monitoring and early warning of geological disasters.

2. The method for geological disaster monitoring and early warning based on artificial intelligence according to claim 1, wherein, and matching the geological feature categories with geological disaster categories to establish a matching relationship between geological disasters and geological features including obtaining the cause information of each geological disaster category, decomposing the cause information into multiple conditions, connecting the multiple conditions to form the process of the geological disaster, using the conditions as nodes in the process, and confirming the geological feature categories under each node, so as to determine a type of geological feature; recording the geological features other than a type of geological feature as other geological features, calculating the linear correlation degree between a type of geological feature and other geological features, and screening out the second type of geological features; calculating the non-linear correlation degree according to a type of geological feature, the function of the preset radial basis function kernel and other geological features, and screening out the second type of geological features; matching and corresponding each geological disaster category with its corresponding first type of geological feature and second type of geological feature, so as to establish a matching relationship between geological disasters and geological features.

3. The method for geological disaster monitoring and early warning based on artificial intelligence according to claim 2, wherein marking geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological features, including collecting the historical occurrence records of geological disasters, marking them on the map of the target area according to the historical occurrence records of geological disasters, matching the first type of geological feature and the second type of geological feature on the map of the target area through the matching relationship between geological disasters and geological features, and calculating the geological feature matching degree; conducting an overlay analysis of the historical occurrence records of geological disasters and the geological feature matching degree on the map of the target area to determine the geological disaster category and the specific location of the geological disaster.

4. The method for monitoring and warning of geological disasters based on artificial intelligence according to claim 3, characterized in that, determining potential geological disaster points with different risk levels, including forming geological disaster areas according to the specific locations of geological disasters, evaluating the influence scope and hazard degree of each geological disaster area, recording the relationship that there is an intersection between geological disaster areas or an intersection between the influence scopes of geological disaster areas as an intersection relationship, calculating the intersection degree between different geological disasters in the intersection relationship, and each intersection relationship corresponds to a potential geological disaster point; Calculate the risk index of geological hazard potential points based on the hazard degree of each geological hazard area and the intersection degree between different geological hazards in the intersection relationship, so as to determine the risk level of geological hazard potential points; Among them, is the risk index of the i1-th geological disaster hidden danger point, n is the number of geological disasters under the i1-th geological disaster hidden danger point, is the risk weight of the i2-th geological disaster, W is the intersection degree, is the hazard degree of the i2-th geological disaster under the i1-th geological disaster hidden danger point, and β1 and β2 are the respective weights of the intersection degree and the influence degree of the geological disaster with the greatest impact, is the maximum value in, and k1 is a preset constant.

5. The geological disaster monitoring and early warning method based on artificial intelligence according to claim 1, characterized in that Set the geological feature warning values for each type of geological hazard under each geological hazard potential point, including Collect the historical value ranges of each type of geological feature in the historical occurrence records of geological disasters, intercept the historical value ranges of each type of geological feature at the time of geological disaster occurrence, determine the average historical value range of each type of geological feature, and determine the first warning value of each type of geological feature according to the average historical value range; Calculate the average value and standard deviation of geological features according to the historical value ranges of each type of geological feature at the time of geological disaster occurrence, map out a multiple through the risk level of the geological hazard potential point, and determine the second warning value of each type of geological feature by combining the average value, standard deviation and multiple of geological features; Set the geological feature warning values for each type of geological hazard according to the first warning value and the second warning value of each type of geological feature.

6. The method for geological disaster monitoring and early warning based on artificial intelligence according to claim 1, characterized in that, Construct a geological disaster impact chain for each geological hazard potential point, including Analyze the causal relationship between multiple geological hazards under each geological hazard potential point, take each geological hazard as an event node in the geological disaster impact chain, connect the event nodes with line segments according to the causal relationship, and assign different lengths to the line segments according to the influence degree between the event nodes, so as to construct the geological disaster impact chain.

7. The method for monitoring and early warning of geological disasters based on artificial intelligence according to claim 6, characterized in that, Before adjusting the geological feature warning values of geological disasters according to the geological disaster impact chain, the method further includes Define two state spaces of the non-occurrence state and the occurrence state of each geological disaster according to geological features, and calculate the state transition probability of the non-occurrence state of the geological disaster evolving into the occurrence state at the current time according to a preset cycle; Judge whether there is an impending geological disaster based on the state transition probability. If there is an impending geological disaster, adjust the geological feature warning values of the geological disaster according to the geological disaster impact chain; Otherwise, do not adjust the geological feature warning values of geological disasters.

8. An artificial intelligence-based geological disaster monitoring and early warning system for implementing the artificial intelligence-based geological disaster monitoring and early warning method according to any one of claims 1-7, characterized in that, The system includes A matching module for collecting geological information in the target area, extracting geological features of all categories of geological information, and matching the geological feature categories with the geological disaster categories to establish a matching relationship between geological disasters and geological features; A risk module for constructing a map of the target area, marking geological disasters one by one on the map of the target area through the matching relationship between geological disasters and geological features, and determining geological hazard potential points of different risk levels; A construction module for setting the geological feature warning values for each type of geological hazard under each geological hazard potential point and constructing a geological disaster impact chain for each geological hazard potential point; A monitoring module for adjusting the geological feature warning values of geological disasters according to the geological disaster impact chain, so as to realize the monitoring and early warning of geological disasters.

Images