A geological disaster early warning method, device and medium based on convolutional neural network

Through the method based on convolutional neural network, real-time and historical data of geological disasters are used to predict, the problem of insufficient geological disaster prediction and early warning information in the existing technology is solved, efficient and timely warning of geological disasters is achieved, and the response to geological disasters is improved. Disaster decision support capability.

CN118570988BActive Publication Date: 2024-11-01SANYA UNIVERSITY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411013500.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-01
Estimated Expiration
2044-07-26

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively predict and warn of random, vague and variable geological disasters, especially in complex geographical environments, resulting in insufficient prediction and early warning information for geological disasters, and it is impossible to respond to the harm caused by geological disasters in a timely and effective manner. .

Method used

Using a method based on convolutional neural network, by obtaining real-time and historical monitoring data of geological disasters, training convolutional neural network models, computing the prediction results of geological disasters, and formulating response mechanisms and early warning information based on the prediction results, including disaster types and risks. Level, impact area and action recommendations.

Benefits of technology

It has achieved efficient and timely early warning of geological disasters with randomness, ambiguity and variability, provided more accurate and reliable geological disaster prediction and early warning information, and improved the decision-making support capabilities in geological disaster response.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118570988B_ABST
    Figure CN118570988B_ABST
Patent Text Reader

Abstract

The present invention discloses a geological disaster early warning method, device and medium based on convolutional neural network, which relates to the field of geological engineering technology. The method comprises: step S1: based on the classification of geological disasters, obtaining the monitoring data of the corresponding evaluation index, the monitoring data comprises: real-time monitoring data and historical monitoring data; step S2: using the evaluation index of the historical monitoring data of geological disasters as the training data set of the convolutional neural network model, and inputting the convolutional neural network model; step S3: training the convolutional neural network model through the machine learning algorithm, inputting the real-time monitoring data into the trained convolutional neural network model to obtain the prediction result of the geological disaster; step S4: responding to and warning the geological disaster based on the prediction result. The present invention solves the problem of using neural network technology to make early warnings for geological disasters with randomness, fuzziness and variability, thereby providing efficient and timely information for early warning of geological disasters.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of geological engineering technology, and in particular to a convolutional neural network-based geological disaster early warning method, device and medium. Background Art

[0002] Geological disasters will inevitably have a serious adverse impact on life safety, economic development and ecological environment protection. With the development of economic activities, such as the construction of water conservancy facilities and urbanization, the human changes to the geological environment have been accelerated, and some economic activities may even induce geological problems.

[0003] In the prior art, the prediction of geological disaster risks is usually made by analyzing spatial probabilities or certain important factors, such as the probability factor of the distance of the disaster and the probability factor of the time of the disaster. The prediction methods used include geomorphic analogy, geometric method, and empirical analysis method. These geological disaster judgment factors and analysis methods are still insufficient for sudden geological problems, as well as the negative impact of these problems on economic development and the huge harm to people's lives. In addition, the influencing factors and analysis methods of geological disasters are accompanied by the characteristics of geological disasters themselves, that is, diversity and uncertainty; moreover, they are often interspersed with the influence of many complex geographical environments. Therefore, the management and evaluation of data related to geological disasters becomes more complicated.

[0004] In the context of the full development of artificial intelligence technology, the use of neural network technology for large-scale information processing and distributed storage, combined with the self-learning and real-time processing characteristics of neural networks, can produce very good results in the prediction of geological disasters. In particular, for some geological disasters with randomness, fuzziness, and variability, the use of neural network technology is more practical and progressive. Summary of the invention

[0005] In order to solve the technical problem of how to use neural network technology to warn of geological disasters with randomness, fuzziness and variability, the embodiment of the present invention provides a method, device and medium for warning geological disasters based on convolutional neural network. The technical solution is as follows:

[0006] In a first aspect, a convolutional neural network-based geological disaster early warning method is provided, the method comprising: step S1: based on the classification of geological disasters, obtaining monitoring data of corresponding evaluation indicators, the monitoring data comprising: real-time monitoring data and historical monitoring data; step S2: using the evaluation indicators of historical monitoring data at different time points of geological disasters as a training data set of a convolutional neural network model, and inputting the convolutional neural network model; step S3: training the convolutional neural network model through a machine learning algorithm, and inputting the real-time monitoring data into the trained convolutional neural network model to obtain a prediction result of the geological disaster; step S4: responding to and warning of the geological disaster based on the prediction result.

[0007] Optionally, the evaluation indicators include: hazard indicators, damage indicators, disaster prevention and mitigation capability indicators and multi-disaster correlation impact indicators; wherein the multi-disaster correlation impact indicators include: causal relationship impact indicators or offsetting relationship impact indicators.

[0008] Optionally, step S1: based on the classification of geological disasters, obtaining monitoring data of corresponding evaluation indicators, including: using remote sensing images to obtain geological feature video image frames of the target area to obtain real-time geological data; and preprocessing the collected real-time geological data.

[0009] Optionally, step S2: using the evaluation index of the historical monitoring data of geological disasters at different time points as a training data set of the convolutional neural network model and inputting it into the convolutional neural network model, including:

[0010] Step S21: Obtain the data matrix C of the historical monitoring data i×j ,

[0011] ;

[0012] Step S22: Based on the selected data matrix C of the historical monitoring data i×j , calculate the corresponding evaluation index P according to the following formula i :

[0013] (1)

[0014] Where i represents the type of geological disaster, i={earthquake=1, fault dislocation=2, volcanic eruption=3, landslide=4, debris flow=5, ground collapse=6, river and lake bank collapse=7, coastal erosion=8, harbor siltation=9, tidal sand dam=10, expansive soil expansion=11, ground collapse=12, frozen soil thawing=13, desertification=14, river water leakage=15, ...M}, M represents the total number of geological disaster types, represents the geological disaster monitoring index, j = {rainfall = 1, mountain displacement = 2, terrain slope = 3, valley length = 4, soil moisture = 5, stratum structure = 6, vegetation coverage = 7, vegetation type = 8, population density = 9, land use change = 10, engineering construction = 11, ... N}, N represents the total number of geological disaster monitoring indicators, P ij represents the probability of the jth geological disaster monitoring indicator of the i-th geological disaster type, w ij Represents the weight of the jth geological hazard monitoring indicator of the i-th geological hazard type.

[0015] Optionally, step S3: training the convolutional neural network model by a machine learning algorithm comprises:

[0016] Step S31: inputting the data of the training data set into the convolutional neural network model to generate a sample feature vector;

[0017] The convolutional neural network model includes: an input layer, an output layer and a hidden layer, wherein the number of neurons δ is set based on the hidden layer and calculated according to the following formula:

[0018] (2)

[0019] Among them, X represents the total number of neurons in the input layer, and Y represents the total number of neurons in the output layer. Represents a constant preset for the convolutional neural network model;

[0020] Based on the design between the input layer, the output layer and the hidden layer, the number of neurons in the input layer and the output layer is determined respectively, wherein the number of neurons between the input layer, the output layer and the hidden layer is , all follow the formula:

[0021] (3)

[0022] Among them, x represents the neuron node vector;

[0023] Step S32: Optimizing the convolutional neural network model by using the calculated value of the optimization function, wherein the optimization function is calculated by the following formula:

[0024] (4)

[0025] in, represents the i-th sample feature vector, i={1, 2, 3...N}, N represents the total number of geological disaster monitoring indicators, represents the corrected value of the sample eigenvector, represents the point-wise product operation, Represents the preset correction value of the corresponding geological disaster.

[0026] Optionally, step S4: based on the prediction results, respond and warn of geological disasters, including: step S41: set up a response mechanism based on the classification of geological disasters, and formulate corresponding event priorities and time response targets; step S42: based on the event priority and the time response target, set warning information including: disaster type, risk level, affected area and action recommendations.

[0027] Optionally, using remote sensing images to obtain geological feature video image frames of the target area includes: using multiple image sensors to collect geological feature video image frames of the target area based on a time series.

[0028] In the second aspect, a convolutional neural network-based geological disaster early warning device is provided, including: a data acquisition module, which is used to obtain monitoring data of corresponding evaluation indicators based on the classification of geological disasters, and the monitoring data includes: real-time monitoring data and historical monitoring data; a training set construction module, which is used to use the evaluation indicators of historical monitoring data of geological disasters at different time points as a training data set of a convolutional neural network model, and input the convolutional neural network model; a convolutional neural network model module, which is used to train the convolutional neural network model through a machine learning algorithm, and input the real-time monitoring data into the trained convolutional neural network model to obtain the prediction results of geological disasters; an early warning processing module, which is used to respond to and warn of geological disasters based on the prediction results.

[0029] In a third aspect, an electronic device is provided, comprising: a processor; a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the above-mentioned convolutional neural network-based geological disaster early warning method are implemented.

[0030] In a fourth aspect, a computer-readable storage medium is provided, in which program code is stored. The program code is loaded and executed by a processor to implement the steps of the above-mentioned convolutional neural network-based geological disaster early warning method.

[0031] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least: solving the problem of using neural network technology to issue early warnings for geological disasters with randomness, fuzziness, and variability, thereby providing efficient and timely information for early warnings of geological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 It is a flow chart of a geological disaster early warning method based on a convolutional neural network provided by an embodiment of the present invention;

[0034] Figure 2 It is a schematic block diagram of a geological disaster early warning device based on a convolutional neural network provided by an embodiment of the present invention;

[0035] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0037] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two. In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the distinction between them is not emphasized, the meanings to be expressed are consistent. In the embodiments of the present invention, sometimes subscripts such as W 1 It may be written in non-subscript form such as W1. When the difference is not emphasized, the meaning is the same.

[0038] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0039] In order to solve the existing technical problem of how to use neural network technology to warn of geological disasters with randomness, fuzziness and variability, the present invention proposes a geological disaster warning method based on convolutional neural network to obtain efficient and timely information for geological disaster warning. In addition, the present invention also adopts a geological disaster warning device based on convolutional neural network, and a computer-readable storage medium to implement the steps of the geological disaster warning method based on convolutional neural network.

[0040] Specifically, the embodiment of the present invention provides a geological disaster early warning method based on convolutional neural network. Figure 1 The flowchart of the early warning method 100 of geological disasters based on convolutional neural network is shown, and the processing flow of the method may include the following steps:

[0041] Step S1: Acquire monitoring data of corresponding evaluation indicators, that is, based on the classification of geological disasters, acquire monitoring data of corresponding evaluation indicators, the monitoring data includes: real-time monitoring data and historical monitoring data.

[0042] In some exemplary embodiments of the present invention, the evaluation index includes: a hazard index, a damage index, a disaster prevention and mitigation capability index and a multi-disaster correlation impact index; wherein the multi-disaster correlation impact index includes: a causal relationship impact index or an offset relationship impact index. The prediction of geological disasters needs to consider hazard indexes, damage indexes, disaster prevention and mitigation capability indexes and multi-disaster correlation impact indexes, etc., so as to conduct a comprehensive analysis. For example, the hazard index and / or damage index can be predicted based on the population density, infrastructure density and cultivated land area ratio in the predetermined area; the disaster prevention and mitigation capability index and / or damage index can be predicted based on the distribution of population attributes, the firmness of infrastructure and the slope of cultivated land area in the predetermined area; the disaster prevention and mitigation capability index can be predicted based on the medical level, per capita income and transportation facilities in the research unit. For another example, the causal relationship impact index can be rainfall in extreme meteorological disasters and mudslides, mountain torrents, waterlogging in geological disasters. Because mudslides, mountain torrents and waterlogging are often geological disasters induced by extreme precipitation, and the occurrence of geological disasters may further aggravate the severity of mudslides, mountain torrents and waterlogging. Another example: high temperatures in extreme meteorological disasters can increase the risk of drought and forest fire risk levels; the above situation belongs to the causal relationship between multiple disasters. On the contrary, multi-disaster correlation impact indicators refer to disasters that have a mutually offsetting relationship among disasters, for example: extreme precipitation in meteorological disasters can alleviate drought and reduce forest fire risk levels.

[0043] In some other exemplary embodiments of the present invention, step S1: based on the classification of geological disasters, obtaining monitoring data of corresponding evaluation indicators, including: using remote sensing images to obtain geological feature video image frames of the target area to obtain real-time geological data; preprocessing the collected real-time geological data.

[0044] In some other exemplary embodiments of the present invention, obtaining geological feature video image frames of a target area using remote sensing images includes: using multiple image sensors to collect geological feature video image frames of the target area based on a time series.

[0045] Step S2: Obtain the training data set of the convolutional neural network model, that is, use the evaluation indicators of the historical monitoring data of geological disasters at different time points as the training data set of the convolutional neural network model and input it into the convolutional neural network model. It should be noted that various geological changes occur frequently in reality, so the historical monitoring data at different time points are often massive data. The use of the convolutional neural network model can greatly improve the efficiency of evaluation and prediction.

[0046] In some exemplary embodiments of the present invention, the evaluation index of the historical monitoring data of geological disasters at different time points is used as a training data set of the convolutional neural network model and input into the convolutional neural network model, including:

[0047] Step S21: Obtain the data matrix C of historical monitoring data i×j ,

[0048] ;

[0049] Step S22: Based on the selected data matrix C of historical monitoring data i×j , calculate the corresponding evaluation index P according to the following formula i :

[0050] (1)

[0051] Where i represents the type of geological disaster, i={earthquake=1, fault dislocation=2, volcanic eruption=3, landslide=4, debris flow=5, ground collapse=6, river and lake bank collapse=7, coastal erosion=8, harbor siltation=9, tidal sand dam=10, expansive soil expansion=11, ground collapse=12, frozen soil thawing=13, desertification=14, river water leakage=15, ...M}, M represents the total number of geological disaster types, represents the geological disaster monitoring index, j = {rainfall = 1, mountain displacement = 2, terrain slope = 3, valley length = 4, soil moisture = 5, stratum structure = 6, vegetation coverage = 7, vegetation type = 8, population density = 9, land use change = 10, engineering construction = 11, ... N}, N represents the total number of geological disaster monitoring indicators, P ij represents the probability of the jth geological disaster monitoring indicator of the i-th geological disaster type, w ij Represents the weight of the jth geological hazard monitoring indicator of the i-th geological hazard type.

[0052] Step S3: Calculate the prediction results of corresponding geological disasters for the trained convolutional neural network model, that is, train the convolutional neural network model through a machine learning algorithm, and input the real-time monitoring data into the trained convolutional neural network model to obtain the prediction results of geological disasters.

[0053] In some exemplary embodiments of the present invention, step S3: training the convolutional neural network model by a machine learning algorithm comprises:

[0054] Step S31: input the data of the training data set into the convolutional neural network model to generate a sample feature vector;

[0055] The convolutional neural network model includes: input layer, output layer and hidden layer, where the number of neurons δ is set based on the hidden layer and calculated according to the following formula:

[0056] (2)

[0057] Among them, δ represents the total number of neurons in the hidden layer, X represents the total number of neurons in the input layer, and Y represents the total number of neurons in the output layer. Represents the constants preset by the convolutional neural network model;

[0058] Based on the design between the input layer, output layer and hidden layer, the number of neurons in the input layer and output layer is determined respectively. The neurons between the input layer, output layer and hidden layer all follow the formula:

[0059] (3)

[0060] Among them, x represents the neuron node vector;

[0061] Step S32: Optimize the convolutional neural network model by using the calculated value of the optimization function. The optimization function formula is calculated as:

[0062] (4)

[0063] in, represents the i-th sample feature vector, i={1, 2, 3...N}, N represents the total number of geological disaster monitoring indicators, represents the corrected value of the sample eigenvector, represents the point-wise product operation, Represents the preset correction value of the corresponding geological disaster.

[0064] Step S4: respond to and warn of geological disasters, that is, respond to and warn of geological disasters based on the prediction results.

[0065] In some exemplary embodiments of the present invention, step S4: responding and warning of geological disasters based on prediction results, including: step S41: setting up a response mechanism based on the classification of geological disasters, and formulating corresponding event priorities and time response targets; step S42: based on event priorities and time response targets, setting warning information including: disaster type, risk level, affected area and action recommendations.

[0066] The above-mentioned embodiments disclosed in the present invention are merely exemplary implementations: they solve the problem of using neural network technology to issue early warnings for geological disasters that are random, fuzzy, and variable, thereby providing efficient and timely information for early warnings of geological disasters.

[0067] Figure 2 2 is a schematic block diagram of a geological disaster early warning device 200 based on a convolutional neural network according to an exemplary embodiment. The geological disaster early warning device 200 based on a convolutional neural network includes: a data acquisition module 202, a training set construction module 204, a convolutional neural network model module 206 and an early warning processing module 208, wherein:

[0068] The data acquisition module 202 is used to acquire monitoring data of corresponding evaluation indicators based on the classification of geological disasters, and the monitoring data includes: real-time monitoring data and historical monitoring data;

[0069] The training set construction module 204 is used to use the evaluation indicators of the historical monitoring data of geological disasters at different time points as the training data set of the convolutional neural network model and input it into the convolutional neural network model;

[0070] The convolutional neural network model module 206 is used to train the convolutional neural network model through a machine learning algorithm, and input the real-time monitoring data into the trained convolutional neural network model to obtain the prediction results of geological disasters;

[0071] The early warning processing module 208 is used to respond to and warn of geological disasters based on the prediction results.

[0072] In some exemplary embodiments of the present invention, the evaluation indicators of the data acquisition module 202 may include: hazard indicators, damage indicators, disaster prevention and mitigation capability indicators and multi-disaster correlation impact indicators; wherein the multi-disaster correlation impact indicators include: causal relationship impact indicators or offsetting relationship impact indicators.

[0073] In some other exemplary embodiments of the present invention, the data acquisition module 202 obtains monitoring data of corresponding evaluation indicators based on the classification of geological disasters, which may include: using remote sensing images to obtain geological feature video image frames of the target area to obtain real-time geological data; and preprocessing the collected real-time geological data.

[0074] In some other exemplary embodiments of the present invention, the data acquisition module 202 may use remote sensing images to acquire geological feature video image frames of the target area, which may include: using multiple image sensors to collect geological feature video image frames of the target area based on a time series.

[0075] In some exemplary embodiments of the present invention, the training set construction module 204 can use the evaluation indicators of the historical monitoring data of geological disasters at different time points as the training data set of the convolutional neural network model, and input the convolutional neural network model, which may include:

[0076] Get the data matrix C of historical monitoring data i×j ,

[0077] ;

[0078] Based on the data matrix C of the selected historical monitoring data i×j , calculate the corresponding evaluation index P according to the following formula i :

[0079]

[0080] Where i represents the type of geological disaster, i={earthquake=1, fault dislocation=2, volcanic eruption=3, landslide=4, debris flow=5, ground collapse=6, river and lake bank collapse=7, coastal erosion=8, harbor siltation=9, tidal sand dam=10, expansive soil expansion=11, ground collapse=12, frozen soil thawing=13, desertification=14, river water leakage=15, ...M}, M represents the total number of geological disaster types, represents the geological disaster monitoring index, j = {rainfall = 1, mountain displacement = 2, terrain slope = 3, valley length = 4, soil moisture = 5, stratum structure = 6, vegetation coverage = 7, vegetation type = 8, population density = 9, land use change = 10, engineering construction = 11, ... N}, N represents the total number of geological disaster monitoring indicators, P ij represents the probability of the jth geological disaster monitoring indicator of the i-th geological disaster type, w ij Represents the weight of the jth geological hazard monitoring indicator of the i-th geological hazard type.

[0081] In some exemplary embodiments of the present invention, the convolutional neural network model module 206 may train the convolutional neural network model through a machine learning algorithm, including:

[0082] Input the data of the training data set into the convolutional neural network model to generate a sample feature vector;

[0083] The convolutional neural network model includes: input layer, output layer and hidden layer, where the number of neurons δ is set based on the hidden layer design and calculated according to the following formula:

[0084]

[0085] Among them, X represents the total number of neurons in the input layer, and Y represents the total number of neurons in the output layer. Represents the constants preset by the convolutional neural network model;

[0086] Based on the design between the input layer, output layer and hidden layer, the number of neurons in the input layer and output layer is determined respectively. , all follow the formula:

[0087]

[0088] Among them, x represents the neuron node vector;

[0089] The convolutional neural network model is optimized by optimizing the calculated value of the function. The optimization function formula is calculated as follows:

[0090]

[0091] in, represents the i-th sample feature vector, i={1, 2, 3...N}, N represents the total number of geological disaster monitoring indicators, represents the corrected value of the sample eigenvector, represents the point-wise product operation, Represents the preset correction value of the corresponding geological disaster.

[0092] In some exemplary embodiments of the present invention, the early warning processing module 208 can respond to and warn of geological disasters based on the prediction results, which may include: Step S41: Setting up a response mechanism based on the classification of geological disasters, and formulating corresponding event priorities and time response targets; Step S42: Based on event priorities and time response targets, setting early warning information including: disaster type, risk level, affected area and action recommendations.

[0093] In an exemplary embodiment, the present invention further provides an electronic device, the electronic device comprising:

[0094] processor;

[0095] A memory having computer-readable instructions stored thereon, which, when loaded and executed by a processor, implement the steps of the above-mentioned convolutional neural network-based geological disaster early warning method.

[0096] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3As shown, the electronic device 300 may include a processor 3001 and a memory 3002. Optionally, the electronic device 300 may also include a transceiver 3003. The processor 3001, the memory 3002 and the transceiver 3003 may be connected, for example, via a communication bus. The memory 3002 stores computer-readable instructions, and when the computer-readable instructions are executed by the processor 3001, the steps of the above-mentioned geological disaster early warning method based on the convolutional neural network are implemented.

[0097] In a specific implementation, as an embodiment, the processor 3001 may include one or more CPUs, such as Figure 3 CPU0 and CPU1 are shown in FIG.

[0098] In a specific implementation, as an embodiment, the electronic device 300 may also include multiple processors, such as Figure 3 3001 and processor 3004 are shown in FIG. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0099] The memory 3002 is used to store the software program for executing the solution of the present invention, and the execution is controlled by the processor 3001. The specific implementation method can refer to the above method embodiment, which will not be repeated here.

[0100] The transceiver 3003 is used to communicate with a network device or a terminal device.

[0101] Optionally, the transceiver 3003 may include a receiver and a transmitter, wherein the receiver is used to implement a receiving function, and the transmitter is used to implement a sending function.

[0102] Optionally, the transceiver 3003 may be integrated with the processor 3001 , or may exist independently and be coupled to the processor 3001 via an interface circuit of the electronic device 300 , which is not specifically limited in the embodiment of the present invention.

[0103] It should be noted that Figure 3 The structure of the electronic device 300 shown in the figure does not constitute a limitation on the electronic device. The actual electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. In addition, the technical effects of the electronic device 300 can refer to the technical effects of the above-mentioned method embodiment, which will not be repeated here.

[0104] In an exemplary embodiment, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is loaded and executed by a processor to implement the steps of the above-mentioned convolutional neural network-based geological disaster early warning method. For example, the computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.

[0105] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0106] In the specification, references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments", etc. indicate that the embodiments may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the relevant art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0107] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0108] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0109] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0110] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0111] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0113] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0114] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0115] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A geological disaster early warning method based on convolutional neural network, It is characterized in that The method comprises: Step S1: Based on the classification of geological disasters, obtain monitoring data of corresponding evaluation indicators, wherein the monitoring data includes: real-time monitoring data and historical monitoring data; The evaluation indicators include: risk index, damage index, disaster prevention and mitigation capacity index and multi-disaster correlation impact index; the multi-disaster correlation impact index includes: causal relationship impact index or offset relationship impact index; The monitoring data of the corresponding evaluation indicators are obtained based on the classification of geological disasters, including: Using remote sensing images to obtain video image frames of geological features of the target area to obtain real-time geological data; pre-processing the collected real-time geological data; The method of obtaining a geological feature video image frame of a target area using remote sensing images includes: Using multiple image sensors to collect time-series video image frames of geological features of a target area; Step S2: using the evaluation index of the historical monitoring data of geological disasters at different time points as a training data set of the convolutional neural network model, and inputting it into the convolutional neural network model; Among them, step S2 uses the evaluation indicators of historical monitoring data of geological disasters at different time points as the training data set of the convolutional neural network model and inputs the convolutional neural network model, including: Step S21: Obtain the data matrix C of the historical monitoring data i×j , ; Step S22: Based on the selected data matrix C of the historical monitoring data i×j , calculate the corresponding evaluation index P according to the following formula i : (1) Where i represents the type of geological disaster, i={earthquake=1, fault dislocation=2, volcanic eruption=3, landslide=4, debris flow=5, ground collapse=6, river and lake bank collapse=7, coastal erosion=8, harbor siltation=9, tidal sand dam=10, swelling and shrinkage of expansive soil=11, ground collapse=12, frozen soil thawing=13, desertification=14, river water leakage=15, …M}, M represents the total number of geological disaster types, j represents the geological disaster monitoring index, j={precipitation=1, mountain displacement=2, terrain slope=3, valley length=4, soil moisture=5, stratum structure=6, vegetation coverage=7, vegetation type=8, population density=9, land use change=10, engineering construction=11, …N}, N represents the total number of geological disaster monitoring indicators, P ij represents the probability of the jth geological disaster monitoring indicator of the i-th geological disaster type, w ij The weight of the jth geological hazard monitoring indicator representing the i-th geological hazard type; Step S3: training the convolutional neural network model through a machine learning algorithm, and inputting the real-time monitoring data into the trained convolutional neural network model to obtain the prediction results of geological disasters; The convolutional neural network model is trained by a machine learning algorithm, including: Step S31: inputting the data of the training data set into the convolutional neural network model to generate a sample feature vector; The convolutional neural network model includes: an input layer, an output layer and a hidden layer, wherein the number of neurons δ is set based on the hidden layer and calculated according to the following formula: (2) Among them, X represents the total number of neurons in the input layer, and Y represents the total number of neurons in the output layer. Represents a constant preset for the convolutional neural network model; Based on the design between the input layer, the output layer and the hidden layer, the number of neurons in the input layer and the output layer is determined respectively, wherein the number of neurons between the input layer, the output layer and the hidden layer is , all follow the formula: (3) Among them, x represents the neuron node vector; Step S32: Optimizing the convolutional neural network model by using the calculated value of the optimization function, wherein the optimization function formula is: (4) in, represents the i-th sample feature vector, i={1, 2, 3...N}, N represents the total number of geological disaster monitoring indicators, represents the corrected value of the sample eigenvector, represents the point-wise product operation, Represents the preset correction value of the corresponding geological hazard; Step S4: Based on the prediction results, respond to and warn of geological disasters.

2. The early warning method for geological disasters based on convolutional neural network according to claim 1, It is characterized in that Step S4: Based on the prediction results, respond to and warn of geological disasters, including: Step S41: Setting a response mechanism based on the classification of geological disasters and formulating corresponding event priorities and time response targets; Step S42: Based on the event priority and the time response target, set warning information, including: disaster type, risk level, affected area and action recommendations.

3. A geological disaster early warning device based on convolutional neural network, used to implement the method described in any one of claims 1 to 2, It is characterized in that include: A data acquisition module is used to acquire monitoring data of corresponding evaluation indicators based on the classification of geological disasters, wherein the monitoring data includes: real-time monitoring data and historical monitoring data; A training set construction module is used to use the evaluation indicators of historical monitoring data of geological disasters at different time points as training data sets of the convolutional neural network model and input them into the convolutional neural network model; Among them, the training set construction module is used to: Step S21: Obtain the data matrix C of the historical monitoring data i×j , ; Step S22: Based on the selected data matrix C of the historical monitoring data i×j , calculate the corresponding evaluation index P according to the following formula i : (1) Where i represents the type of geological disaster, i={earthquake=1, fault dislocation=2, volcanic eruption=3, landslide=4, debris flow=5, ground collapse=6, river and lake bank collapse=7, coastal erosion=8, harbor siltation=9, tidal sand dam=10, swelling and shrinkage of expansive soil=11, ground collapse=12, frozen soil thawing=13, desertification=14, river water leakage=15, …M}, M represents the total number of geological disaster types, j represents the geological disaster monitoring index, j={precipitation=1, mountain displacement=2, terrain slope=3, valley length=4, soil moisture=5, stratum structure=6, vegetation coverage=7, vegetation type=8, population density=9, land use change=10, engineering construction=11, …N}, N represents the total number of geological disaster monitoring indicators, P ij represents the probability of the jth geological disaster monitoring indicator of the i-th geological disaster type, w ij The weight of the jth geological hazard monitoring indicator representing the i-th geological hazard type; A convolutional neural network model module, used to train the convolutional neural network model through a machine learning algorithm, and input the real-time monitoring data into the trained convolutional neural network model to obtain the prediction results of geological disasters; The early warning processing module is used to respond to and warn of geological disasters based on the prediction results.

4. An electronic device, It is characterized in that The electronic device comprises: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the early warning method for geological disasters based on a convolutional neural network as described in any one of claims 1 to 2 is implemented.

5. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores program code, and the program code is loaded by a processor and executes the early warning method for geological disasters based on convolutional neural network as described in any one of claims 1 to 2.