CN116797030A - Geological monitoring and early warning method, system, computer equipment and storage medium - Google Patents
Geological monitoring and early warning method, system, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116797030A CN116797030A CN202311074844.6A CN202311074844A CN116797030A CN 116797030 A CN116797030 A CN 116797030A CN 202311074844 A CN202311074844 A CN 202311074844A CN 116797030 A CN116797030 A CN 116797030A
- Authority
- CN
- China
- Prior art keywords
- geological
- data
- module
- disaster
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 238000005516 engineering process Methods 0.000 claims abstract description 42
- 239000013598 vector Substances 0.000 claims abstract description 39
- 238000010801 machine learning Methods 0.000 claims abstract description 35
- 230000010354 integration Effects 0.000 claims abstract description 27
- 238000013135 deep learning Methods 0.000 claims abstract description 23
- 238000009826 distribution Methods 0.000 claims abstract description 21
- 238000005305 interferometry Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims description 64
- 238000012502 risk assessment Methods 0.000 claims description 58
- 238000004088 simulation Methods 0.000 claims description 50
- 238000004422 calculation algorithm Methods 0.000 claims description 49
- 230000004044 response Effects 0.000 claims description 49
- 238000010586 diagram Methods 0.000 claims description 30
- 238000000605 extraction Methods 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 230000000694 effects Effects 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 10
- 238000007619 statistical method Methods 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000000547 structure data Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000013461 design Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000011056 performance test Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 239000003673 groundwater Substances 0.000 description 6
- 239000011435 rock Substances 0.000 description 5
- 230000002265 prevention Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002689 soil Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 239000002349 well water Substances 0.000 description 1
- 235000020681 well water Nutrition 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of geological investigation, in particular to a geological monitoring and early warning method, a system, computer equipment and a storage medium, wherein in the actual use process of the geological monitoring and early warning method, the traditional geological disaster prediction method usually only depends on single kind of data, so that the early warning result can have deviation and the actual situation is difficult to comprehensively reflect, and the geological monitoring and early warning method is provided and comprises the following steps: utilizing a data integration technology to fuse and preprocess the multi-source data to generate a comprehensive geological data set; and extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technologies to serve as geological feature vectors. The method has the beneficial effects that more comprehensive geological information can be obtained by integrating multi-source data comprising remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution data, and accuracy of geological disaster prediction is improved.
Description
Technical Field
The invention relates to the technical field of geological investigation, in particular to a geological monitoring and early warning method, a geological monitoring and early warning system, computer equipment and a storage medium.
Background
Geological exploration is a scientific investigation and research method aimed at knowing and evaluating the geological conditions of the earth's surface and subsurface. It relates to the detailed investigation and analysis of geological elements such as geological structure, rock type, stratum distribution, rock-soil properties, mineral resources and the like. The main purpose of geological exploration is to acquire data and information about geological conditions to support planning and decision-making of activities such as various engineering projects, natural resource development, environmental protection, and geological disaster assessment. By geological investigation, the suitability of the land, the distribution of groundwater resources, the potential risk of geological disasters, and the reserves and quality of minerals, etc. can be determined. Geological surveys may include a variety of techniques and methods including field surveys, geomorphic geochemical analyses, geophysical surveys, core sampling, and laboratory testing. These surveys and analysis results are typically consolidated and drawn into geologic maps, geologic profiles, and reports, which are provided to relevant decision makers, engineers, scientists, and researchers for reference and application. Through geological investigation, the evolution history of the earth, the geological process and the distribution condition of natural resources can be deeply known. The method has important significance for reasonably utilizing natural resources, protecting the environment, reducing the risk of geological disasters and promoting sustainable development.
The geological monitoring and early warning method is to identify and early warn potential geological disasters and dangers in advance by monitoring the change of geological processes and phenomena so as to formulate corresponding countermeasures and protection measures. The method comprises ground deformation monitoring, ground water level monitoring, fault monitoring, rock mass stability monitoring, hydrologic monitoring and environment monitoring. Ground deformation monitoring measures the ground deformation by using a GPS and other positioning systems so as to detect the signs of earth crust movement, ground displacement and the like. Groundwater level monitoring evaluates groundwater replenishment conditions and groundwater disaster risk through well water level and groundwater level changes. Fault monitoring focuses on the earthquake activity, stress change and ground cracks of fault zones so as to early warn earthquakes and related geological disasters in advance. The rock mass stability monitoring is used for monitoring deformation, displacement, cracks and other information of rock and soil mass in real time and predicting landslide, rock mass collapse and other geological disasters. Hydrologic monitoring is used for early warning of hydrologic disasters such as flood and debris flow by monitoring rainfall, river water level and flood conditions. Environmental monitoring focuses on the changes of the atmosphere, water and ecological environment, and timely discovers environmental risks and hazards.
In the actual use process of the geological monitoring and early warning method, the traditional geological disaster prediction method often only depends on single kind of data, so that the early warning result may have deviation, and the actual situation is difficult to comprehensively reflect. In the traditional method, a prediction model of the geological disaster often lacks a real-time data feedback and adjustment mechanism, so that a certain defect exists in the aspect of real-time early warning. The early warning of disaster suffered people is usually based on a fixed area, and lack of personalized early warning may lead to low accuracy and effectiveness of early warning information in practical application. Conventional geological disaster early warning generally only provides early warning information, but lacks a decision support and response scheme with strong pertinence, and is unfavorable for actual disaster prevention and reduction work.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a geological monitoring and early warning method, a geological monitoring and early warning system, computer equipment and a storage medium.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the geological monitoring and early warning method comprises the following steps:
utilizing a data integration technology to fuse and preprocess multisource data comprising high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution, so as to generate a comprehensive geological data set;
extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technologies to serve as geological feature vectors;
combining a numerical simulation technology and a geological feature vector, constructing a dynamic prediction model, continuously updating monitoring data, feeding back the monitoring data into the dynamic prediction model, and analyzing the progress and trend of geological disasters in real time to generate a dynamic prediction result of the geological disasters;
based on the dynamic geological disaster prediction result, combining seismic wave propagation simulation and geological structure analysis to perform seismic disaster risk assessment, and simultaneously performing risk classification on the region by using a multi-scale analysis method to generate a geological disaster risk region map;
The social network data is analyzed by machine learning, the crowd possibly threatened by the geological disaster is identified and predicted according to the geological disaster risk area diagram, a threat crowd list is generated, and personalized early warning is realized;
and developing an intelligent decision support system by combining the geological disaster risk area map and the threatening crowd list, and providing a geological disaster response strategy report comprising real-time early warning information, a risk assessment result and a disaster response scheme for a decision maker.
As a further scheme of the invention, the data integration technology is utilized to fuse and preprocess multi-source data comprising high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution, and the steps for generating the comprehensive geological data set are specifically as follows:
the method comprises the steps that a source collects high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution data to construct an original multi-source data set;
cleaning the original multi-source data set, removing abnormal and repeated values, unifying data formats, and obtaining a cleaned multi-source data set;
integrating the cleaned multi-source data set into a whole by using a KPCA fusion algorithm to serve as fused geological data;
And constructing geological attributes and parameters based on the fused geological data to form a comprehensive geological data set.
As a further scheme of the invention, by utilizing machine learning and deep learning technologies, the key geologic features and geologic hazard hidden danger features are extracted from the comprehensive geologic data set, and the steps for serving as geologic feature vectors specifically include:
utilizing statistical analysis and visualization tool analysis to synthesize a geological data set, and extracting key geological features and geological disaster hidden danger features to be used as a preliminary geological feature analysis result;
selecting key features from the preliminary geologic feature analysis results by using a feature selection algorithm, specifically a random forest, and generating a key geologic feature set;
deep learning, namely a convolutional neural network, is used for processing the key geological feature set, extracting deep geological features and generating a deep geological feature vector;
integrating the depth geological feature vector with the key geological feature set to construct a geological feature vector.
As a further scheme of the invention, the dynamic prediction model is constructed by combining a numerical simulation technology and a geological feature vector, monitoring data are continuously updated and fed back into the dynamic prediction model, the progress and trend of geological disasters are analyzed in real time, and the step of generating a dynamic prediction result of the geological disasters comprises the following steps:
Selecting a prediction algorithm comprising LSTM and GRU according to the geological feature vector, carrying out dynamic prediction on geological disasters, and establishing a preliminary dynamic prediction model;
simulating the possible progress and trend of the geological disaster by using a numerical simulation technology and the preliminary dynamic prediction model to generate a numerical simulation prediction result;
training by using a geological feature vector and the numerical simulation prediction result, and optimizing model parameters by a gradient descent algorithm and a genetic algorithm to obtain an optimized dynamic prediction model;
and providing real-time geological disaster progress and trend analysis by using the optimized dynamic prediction model and combining real-time monitoring data to obtain a geological disaster dynamic prediction result.
As a further scheme of the invention, based on the dynamic prediction result of the geological disaster, the method combines the seismic wave propagation simulation and the geological structure analysis to perform seismic disaster risk assessment, and simultaneously utilizes a multi-scale analysis method to perform risk classification on the region, and the step of generating a geological disaster risk region map comprises the following specific steps:
judging the area and intensity of possible earthquake according to the dynamic prediction result of the geological disaster, and generating prediction earthquake information;
simulating the propagation of the seismic waves in the crust according to the predicted seismic information by using a seismic wave propagation model comprising a fluctuation theory model and a finite difference model, and generating a seismic wave propagation simulation result;
Analyzing the possibly affected geological structure and the possibility of disaster by combining the seismic wave propagation simulation result and geological structure data to generate a geological disaster possibility analysis result;
combining the geological disaster possibility analysis result and a multi-scale analysis algorithm, performing disaster risk assessment, and generating a preliminary disaster risk assessment report;
and dividing risk grades based on the preliminary disaster risk evaluation report, and generating a geological disaster risk area diagram.
As a further scheme of the invention, social network data is analyzed by utilizing machine learning, and the crowd possibly threatened by the geological disaster is identified and predicted according to the geological disaster risk area diagram, a threat crowd list is generated, and the personalized early warning is realized by the steps of:
collecting social network data of an area based on the geological disaster risk area diagram, extracting user region and activity condition information, and integrating a preliminary social network data set;
cleaning and formatting the preliminary social network data set, removing invalid, wrong or repeated information, and obtaining a cleaned social network data set;
identifying crowds possibly threatened by the geological disaster according to the geological disaster risk area map and the cleaned social network data set, and generating a primary threatened crowd list;
And analyzing the preliminary threat crowd list by utilizing machine learning, carrying out risk early warning on the crowd possibly threatened by the geological disaster, and establishing the threat crowd list.
As a further scheme of the invention, by combining the geological disaster risk area map and the threatening crowd list, the intelligent decision support system is developed, and the steps of providing the decision maker with the geological disaster response strategy report comprising real-time early warning information, risk assessment results and disaster response schemes are specifically as follows:
planning and designing the structure and the function of an intelligent decision support system based on the geological disaster risk area diagram and the list of the threatened crowd, and integrating the structure and the function as a primary decision support system design scheme;
integrating the dynamic geological disaster prediction result, the preliminary disaster risk evaluation report and the list of the threatened crowd to generate real-time early warning information;
according to the design scheme of the preliminary decision support system, developing a decision support system, wherein the decision support system comprises the functions of displaying, pushing and managing real-time early warning information and is used as a decision support system with preliminary and complete functions;
according to the real-time early warning information, a disaster risk assessment result and a geological disaster dynamic prediction result, a disaster response scheme is formulated;
And integrating the disaster response scheme and the primarily complete decision support system for system performance test and optimization to obtain a final geological disaster response strategy report and an intelligent decision support system.
The geological monitoring and early warning system is used for executing a geological monitoring and early warning method and consists of a data integration module, a feature extraction module, a dynamic prediction model module, a risk assessment module, a personalized early warning module and a decision support module;
the data integration module integrates the high-resolution remote sensing image, the geological exploration data, the satellite radar interferometry data, the meteorological data and the population distribution data to construct a comprehensive geological data set;
the feature extraction module uses a comprehensive geological data set, performs geological feature extraction through machine learning and deep learning technologies, performs deep analysis on data through statistical analysis and visualization tools, screens out key features through a feature selection algorithm, and performs deep extraction on the key features through convolutional neural networks and other technologies to form geological feature vectors;
the dynamic prediction model module builds a dynamic prediction model for the dynamic prediction model by utilizing a numerical simulation technology based on the geological feature vector, and adopts LSTM and GRU prediction algorithms to carry out preliminary construction of the model, and generates a geological disaster dynamic prediction result after the gradient descent algorithm and the genetic algorithm are optimized;
After a dynamic prediction result of the geological disaster is obtained, the risk assessment module analyzes the seismic area and the intensity, adopts a fluctuation theory model and a finite difference model to simulate the propagation of the seismic waves in the crust, analyzes the possibility of the disaster by combining the simulation result of the propagation of the seismic waves and geological structure data, and utilizes a multi-scale analysis algorithm to complete the assessment of the disaster risk so as to generate a geological disaster risk area diagram;
the personalized early warning module analyzes social network data based on a geological disaster risk area diagram by using a machine learning technology, determines people possibly facing threat, and combines real-time data with the geological disaster risk area diagram to obtain real-time early warning information so as to form a targeted geological disaster response strategy report;
the decision support module develops an intelligent decision support system based on a geological disaster response strategy report, real-time early warning information and a risk assessment result, and performs uninterrupted iteration update and optimization through an intelligent algorithm to provide decision suggestions for a decision maker.
As a further scheme of the invention, the data integration module comprises a high-resolution remote sensing image sub-module, a geological exploration data sub-module, a satellite radar interferometry data sub-module, a meteorological data sub-module and a population distribution data sub-module;
The feature extraction module comprises a machine learning feature extraction sub-module, a deep learning feature extraction sub-module, a statistical analysis sub-module, a visualization tool sub-module and a key feature selection sub-module;
the dynamic prediction model module comprises an LSTM prediction sub-module, a GRU prediction sub-module, a numerical simulation sub-module, a gradient descent optimization sub-module and a genetic algorithm optimization sub-module;
the risk assessment module comprises a seismic area analysis sub-module, a seismic wave propagation simulation sub-module, a geological structure analysis sub-module, a disaster possibility analysis sub-module and a multi-scale risk assessment sub-module;
the personalized early warning module comprises a social network data analysis sub-module, a real-time early warning generation sub-module, a threat crowd determination sub-module, a risk area matching sub-module and a disaster response strategy reporting sub-module;
the decision support module comprises a response strategy analysis sub-module, an intelligent algorithm iteration sub-module, an early warning information integration sub-module, a risk assessment integration sub-module and a decision suggestion generation sub-module.
A computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the geological monitoring and early warning method as described above when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a geological monitoring pre-warning method as described above.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, by integrating the multi-source data comprising the remote sensing image, the geological exploration data, the satellite radar interferometry data, the meteorological data and the population distribution data, more comprehensive geological information can be obtained, and the accuracy of geological disaster prediction is increased. By combining a numerical simulation technology and a dynamic feedback mechanism, the development trend of geological disasters can be analyzed in real time, the prediction result is updated in time, and the timeliness of early warning is improved. People possibly threatened are identified by utilizing artificial intelligence technology and social network data, personalized early warning is realized, and information release is more accurate and effective. The intelligent decision support is provided, so that a decision maker can make corresponding coping strategies according to real-time early warning information, risk assessment results and disaster response schemes, and scientificity and effectiveness of disaster prevention and reduction are improved.
Drawings
FIG. 1 is a schematic diagram of a workflow of a geological monitoring and early warning method according to the present invention;
FIG. 2 is a detailed flowchart of the steps for generating a comprehensive geological data set in the geological monitoring and early warning method provided by the invention;
FIG. 3 is a detailed flowchart of the steps for constructing a geological feature vector in the geological monitoring and early warning method provided by the invention;
FIG. 4 is a detailed flowchart of the steps for generating dynamic prediction results of geological disasters in the geological monitoring and early warning method provided by the invention;
FIG. 5 is a flowchart showing the steps for generating a geological disaster risk area map in the geological monitoring and early warning method according to the present invention;
FIG. 6 is a detailed flowchart of the steps for implementing personalized early warning in the geological monitoring early warning method according to the present invention;
FIG. 7 is a detailed flowchart of the steps for providing a report of a geological disaster response strategy in a geological monitoring and early warning method according to the present invention;
fig. 8 is a block diagram of a geological monitoring and early warning system for executing a geological monitoring and early warning method according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
Referring to fig. 1, the present invention provides a technical solution: the geological monitoring and early warning method comprises the following steps:
Utilizing a data integration technology to fuse and preprocess multisource data comprising high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution, so as to generate a comprehensive geological data set;
extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technologies to serve as geological feature vectors;
combining a numerical simulation technology and a geological feature vector, constructing a dynamic prediction model, continuously updating monitoring data, feeding back the monitoring data into the dynamic prediction model, and analyzing the progress and trend of geological disasters in real time to generate a geological disaster dynamic prediction result;
based on a dynamic geological disaster prediction result, combining seismic wave propagation simulation and geological structure analysis, performing seismic disaster risk assessment, and simultaneously performing risk classification on the region by using a multi-scale analysis method to generate a geological disaster risk region map;
the social network data is analyzed by machine learning, the crowd possibly threatened by the geological disaster is identified and predicted according to the geological disaster risk area diagram, a threat crowd list is generated, and personalized early warning is realized;
and developing an intelligent decision support system by combining the geological disaster risk area diagram and the threatening crowd list, and providing a geological disaster response strategy report comprising real-time early warning information, a risk assessment result and a disaster response scheme for a decision maker.
Firstly, multi-source data are fused and optimized through data integration and preprocessing, and data quality and integrity are improved, so that more accurate geological information is provided. And secondly, the key geological features and the geological disaster hidden danger features are extracted by utilizing machine learning and deep learning technologies, so that the potential risk factors of geological disasters can be accurately identified. In addition, the dynamic prediction model is constructed, the monitoring data is continuously updated, the progress and trend of geological disasters can be analyzed in real time, timely early warning information is provided, and accurate decision support is provided for a decision maker. By combining seismic wave propagation simulation and geologic structure analysis, and performing seismic disaster risk assessment, assessment of seismic disaster risk and demarcation of possible influence range can be provided. The method has the advantages that the social network data are analyzed through machine learning, the threatened crowd is identified and predicted, and in combination with the geological disaster risk area diagram, personalized early warning measures can be formulated, so that disaster response effects are improved. And finally, developing an intelligent decision support system, providing real-time early warning information, risk assessment results and disaster response schemes, and helping a decision maker to make timely and effective decisions.
Referring to fig. 2, the steps of generating a comprehensive geological data set by using a data integration technology to fuse and preprocess multisource data including high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution are specifically as follows:
The method comprises the steps that a source collects high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution data to construct an original multi-source data set;
cleaning an original multi-source data set, removing abnormal values and repeated values, unifying data formats, and obtaining a cleaned multi-source data set;
integrating the cleaned multi-source data set into a whole by using a KPCA fusion algorithm to serve as fused geological data;
and constructing geological attributes and parameters based on the fused geological data to form a comprehensive geological data set.
First, by collecting and cleaning a variety of data sources, the integrity and accuracy of the data may be improved, resulting in more comprehensive and detailed geologic information. And secondly, by fusing different types of geological data, a comprehensive geological data set is generated, so that the dimension and depth of geological information can be enriched, and more attributes and parameters are provided for geological research and prediction. Third, the generation of the comprehensive geological data set supports cross-domain cross analysis, such as correlation research of geological disasters, meteorological factors, population density and the like, and is helpful for more comprehensively understanding the relationship between geological environment and human activities. Finally, the application of the comprehensive geological data set improves the capacity of geological disaster early warning and risk assessment, and improves the accuracy and timeliness of related decisions, thereby reducing the loss and influence caused by geological disasters.
Referring to fig. 3, the steps of extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technology are specifically as follows:
utilizing statistical analysis and visualization tool analysis to synthesize a geological data set, and extracting key geological features and geological disaster hidden danger features to be used as a preliminary geological feature analysis result;
selecting key features from the preliminary geologic feature analysis results by using a feature selection algorithm, specifically a random forest, and generating a key geologic feature set;
deep learning, namely a convolutional neural network, is used for processing the key geological feature set, extracting deep geological features and generating a deep geological feature vector;
integrating the depth geologic feature vector and the key geologic feature set to construct a geologic feature vector.
Firstly, key features can be efficiently extracted from complex geological data through automatic feature extraction, so that labor and time cost are saved. And secondly, the deep learning method can extract deep geological features, capture potential modes and association relations in data, and improve the identification and prediction accuracy of geological disasters. In addition, the geological features extracted by machine learning and deep learning can be used for constructing a more accurate and reliable geological disaster prediction model and a risk assessment model, so that scientific basis of a decision maker is provided, and loss and influence caused by geological disasters are reduced.
Referring to fig. 4, in combination with a numerical simulation technique and a geological feature vector, a dynamic prediction model is constructed, continuously updated monitoring data is fed back into the dynamic prediction model, and the progress and trend of geological disasters are analyzed in real time, so that a dynamic prediction result of the geological disasters is generated specifically by the following steps:
selecting a prediction algorithm comprising LSTM and GRU according to the geological feature vector, carrying out dynamic prediction of geological disasters, and establishing a preliminary dynamic prediction model;
simulating possible progress and trend of geological disasters by using a numerical simulation technology and a preliminary dynamic prediction model to generate a numerical simulation prediction result;
training by using a geological feature vector and a numerical simulation prediction result, and optimizing model parameters by using a gradient descent algorithm and a genetic algorithm to obtain an optimized dynamic prediction model;
and providing real-time geological disaster progress and trend analysis by using the optimized dynamic prediction model and combining real-time monitoring data to obtain a geological disaster dynamic prediction result.
Firstly, the real-time dynamic prediction can analyze the progress and trend of geological disasters in time, provide early warning and prediction information and help take timely countermeasures. Secondly, through numerical simulation auxiliary prediction, the possible progress and trend of geological disasters can be simulated, and more comprehensive and accurate prediction results are provided. Meanwhile, the performance of the prediction model can be further improved by optimizing model parameters, so that the prediction model is more suitable for actual conditions and changes of monitoring data. Finally, the real-time monitoring data is combined for analysis, so that real-time geological disaster situation assessment can be provided, accurate information is provided for a decision maker, and decision making and measures against the geological disasters are facilitated.
Referring to fig. 5, based on a dynamic prediction result of a geological disaster, combining with a seismic wave propagation simulation and a geological structure analysis, performing seismic disaster risk assessment, and simultaneously performing risk classification on an area by using a multi-scale analysis method, the steps of generating a geological disaster risk area map are specifically as follows:
judging the area and intensity of the possible earthquake according to the dynamic prediction result of the geological disaster, and generating predicted earthquake information;
simulating the propagation of the seismic waves in the crust according to the predicted seismic information by using a seismic wave propagation model comprising a fluctuation theory model and a finite difference model, and generating a seismic wave propagation simulation result;
combining the seismic wave propagation simulation result and the geological structure data, analyzing the possibly affected geological structure and the possibility of disaster occurrence, and generating a geological disaster possibility analysis result;
combining a geological disaster possibility analysis result and a multi-scale analysis algorithm, performing disaster risk assessment, and generating a preliminary disaster risk assessment report;
and dividing risk grades based on the preliminary disaster risk evaluation report, and generating a geological disaster risk area diagram.
Firstly, by predicting the seismic information and simulating the seismic wave propagation, accurate seismic wave characteristics and the distribution situation of a seismic influence area can be provided, and important data and basis are provided for seismic disaster risk assessment. Secondly, in combination with geologic structure analysis, the impact of the earthquake on the geologic structure can be evaluated, revealing the type and extent of geologic hazards that may occur. In addition, by using the multi-scale risk assessment method, risk grades of different areas and places in the area can be divided, and fine guidance is provided for disaster prevention and emergency management. By comprehensively applying the methods, the risk degree of the earthquake disaster can be effectively estimated, and the decision support capability of disaster prevention, disaster reduction and emergency response is improved.
Referring to fig. 6, social network data is analyzed by machine learning, and according to a geological disaster risk area diagram, a crowd possibly threatened by the geological disaster is identified and predicted, a threat crowd list is generated, and the steps for realizing personalized early warning are specifically as follows:
collecting social network data of an area based on a geological disaster risk area diagram, extracting user region and activity condition information, and integrating a preliminary social network data set;
cleaning and formatting the preliminary social network data set, removing invalid, wrong or repeated information, and obtaining a cleaned social network data set;
identifying crowds possibly threatened by the geological disasters according to the geological disaster risk area map and the cleaned social network data set, and generating a primary threatened crowd list;
and analyzing the primary threat crowd list by utilizing machine learning, carrying out risk early warning on the crowd possibly threatened by the geological disaster, and establishing the threat crowd list.
By utilizing machine learning to analyze social network data and combining with a geological disaster risk area diagram, the crowd possibly threatened by the geological disaster is identified and predicted, a threat crowd list is generated, personalized early warning is realized, and a plurality of beneficial effects can be brought. First, the method can more fully understand the geographic position and activity condition of people based on social network data, so that people possibly threatened can be accurately identified. And secondly, through analysis and prediction capabilities of machine learning, efficient processing and crowd identification of large-scale data can be realized, and the accuracy and timeliness of early warning are improved. In addition, through personalized early warning, early warning information and countermeasures can be provided for the threatened crowd in a targeted manner, and the efficiency and the effect of emergency response are improved.
Referring to fig. 7, in combination with a geological disaster risk area diagram and a list of threatened people, the steps of developing an intelligent decision support system and providing a decision maker with a geological disaster response strategy report including real-time early warning information, a risk assessment result and a disaster response scheme are specifically as follows:
planning and designing the structure and the function of an intelligent decision support system based on the geological disaster risk area diagram and the list of the threatened crowd, and integrating the structure and the function as a primary decision support system design scheme;
integrating the dynamic geological disaster prediction result, the preliminary disaster risk evaluation report and the list of the threatened crowd to generate real-time early warning information;
according to the design scheme of the preliminary decision support system, developing the decision support system, wherein the decision support system comprises the functions of displaying, pushing and managing real-time early warning information and is used as a decision support system with preliminary and complete functions;
according to the real-time early warning information, a disaster risk assessment result and a geological disaster dynamic prediction result, a disaster response scheme is formulated;
and integrating the disaster response scheme and the initially complete decision support system in function, and performing system performance test and optimization to obtain a final geological disaster response strategy report and an intelligent decision support system.
Firstly, the system integrates geological disaster risk information and crowd data, provides accurate geological disaster early warning and risk assessment results, and provides a comprehensive information basis for a decision maker. And secondly, through a real-time early warning function, a decision maker can timely know disaster risks and the conditions of the threatened crowd so as to quickly make coping decisions and improve the timeliness and accuracy of emergency response. In addition, the system also supports the formulation of disaster response schemes, provides personalized countermeasure measures, helps decision makers to effectively organize resources and rescue actions, and realizes efficient disaster countermeasure.
Referring to fig. 8, the geological monitoring and early warning system is used for executing a geological monitoring and early warning method, and the geological monitoring and early warning system is composed of a data integration module, a feature extraction module, a dynamic prediction model module, a risk assessment module, a personalized early warning module and a decision support module;
the data integration module integrates the high-resolution remote sensing image, the geological exploration data, the satellite radar interferometry data, the meteorological data and the population distribution data to construct a comprehensive geological data set;
the feature extraction module uses a comprehensive geological data set, performs geological feature extraction through machine learning and deep learning technologies, performs deep analysis on data through statistical analysis and visualization tools, screens out key features through a feature selection algorithm, and performs deep extraction on the key features through convolutional neural networks and other technologies to form geological feature vectors;
The dynamic prediction model module builds a dynamic prediction model for the dynamic prediction model by utilizing a numerical simulation technology based on the geological feature vector, adopts LSTM and GRU prediction algorithms to carry out preliminary construction of the model, and generates a geological disaster dynamic prediction result after the gradient descent algorithm and the genetic algorithm are optimized;
after a dynamic prediction result of the geological disaster is obtained, the risk assessment module analyzes the seismic area and the intensity, adopts a fluctuation theory model and a finite difference model to simulate the propagation of the seismic waves in the crust, analyzes the possibility of the disaster by combining the simulation result of the propagation of the seismic waves and geological structure data, and utilizes a multi-scale analysis algorithm to complete the assessment of the disaster risk so as to generate a geological disaster risk area diagram;
the personalized early warning module analyzes social network data based on the geological disaster risk area map by using a machine learning technology, determines the crowd possibly facing threat, combines the real-time data with the geological disaster risk area map, obtains real-time early warning information, and forms a targeted geological disaster response strategy report;
the decision support module develops an intelligent decision support system based on a geological disaster response strategy report, real-time early warning information and a risk assessment result, and performs uninterrupted iteration update and optimization through an intelligent algorithm to provide decision suggestions for a decision maker.
First, the data integration module integrates a variety of high quality data sources into a comprehensive geological data set, providing comprehensive geological information. And secondly, the feature extraction module analyzes and extracts key features from the comprehensive geological data through a machine learning and deep learning technology, so that the characterization capability and the prediction accuracy of the data are improved. And then, the dynamic prediction model module constructs a dynamic prediction model based on the extracted features, and predicts by using an advanced prediction algorithm to realize dynamic prediction and monitoring of the geological disaster. In addition, the risk assessment module combines seismic wave propagation simulation and geological structure data to carry out disaster risk assessment, generates a geological disaster risk area diagram, and provides fine analysis and early warning of geological disaster risks. Further, the personalized early warning module utilizes the social network data and the real-time data to identify the possibly threatened crowd, provides personalized geological disaster early warning information and enhances the protection and rescue measures of the crowd. And finally, the decision support module develops an intelligent decision support system by integrating early warning information, risk assessment results and geological disaster response strategy reports, provides accurate information for a decision maker, and supports decision making and optimization of disaster response decisions.
Referring to fig. 8, the data integration module includes a high-resolution remote sensing image sub-module, a geological exploration data sub-module, a satellite radar interferometry data sub-module, a meteorological data sub-module, and a population distribution data sub-module;
the feature extraction module comprises a machine learning feature extraction sub-module, a deep learning feature extraction sub-module, a statistical analysis sub-module, a visualization tool sub-module and a key feature selection sub-module;
the dynamic prediction model module comprises an LSTM prediction sub-module, a GRU prediction sub-module, a numerical simulation sub-module, a gradient descent optimization sub-module and a genetic algorithm optimization sub-module;
the risk assessment module comprises a seismic area analysis sub-module, a seismic wave propagation simulation sub-module, a geological structure analysis sub-module, a disaster possibility analysis sub-module and a multi-scale risk assessment sub-module;
the personalized early warning module comprises a social network data analysis sub-module, a real-time early warning generation sub-module, a threat population determination sub-module, a risk area matching sub-module and a disaster response strategy reporting sub-module;
the decision support module comprises a response strategy analysis sub-module, an intelligent algorithm iteration sub-module, an early warning information integration sub-module, a risk assessment integration sub-module and a decision suggestion generation sub-module.
First, the data integration module can integrate various high-quality geological data sources comprehensively to provide a comprehensive geological information basis. And secondly, the feature extraction module extracts key features by utilizing technologies such as machine learning, deep learning and the like, and improves the data characterization capability and the prediction accuracy. The dynamic prediction model module builds a dynamic prediction model based on the extracted features, so that geological disasters can be accurately predicted and monitored. Meanwhile, the risk assessment module provides comprehensive disaster risk assessment, and helps a decision maker to know potential risks and take corresponding measures. The personalized early warning module determines the possibly threatened crowd by analyzing the social network and the real-time data and generates personalized geological disaster early warning information. And finally, integrating early warning information and a risk assessment result by the decision support module, providing scientific decision suggestions for a decision maker, and improving the accuracy of the decision and the response efficiency.
A computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the geological monitoring and early warning method as described above when the computer program is executed.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a geological monitoring pre-warning method as described above.
Working principle:
data integration: first, multi-source data including high resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data, and demographic data are collected. And then cleaning the data, removing the abnormal and repeated values, and unifying the data formats to obtain the cleaned multi-source data set. Next, the cleaned multisource dataset is fused into a comprehensive geological dataset for subsequent analysis and prediction using data integration techniques (e.g., KPCA fusion algorithms).
Feature extraction: and extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technologies. First, the integrated geological dataset is analyzed by statistical analysis and visualization tools to extract preliminary geological features. Then, a feature selection algorithm (such as a random forest) is used to select key features from the preliminary geologic features. Then, the key features are extracted deeply by a deep learning technology (such as a convolutional neural network) to generate deep geological feature vectors. And finally, integrating the depth geological feature vector with the key geological feature set to construct a geological feature vector.
Dynamic prediction model: and combining a numerical simulation technology and a geological feature vector to construct a dynamic prediction model. And selecting a proper prediction algorithm, such as a long-short-term memory network (LSTM) or a gating and circulating unit (GRU), according to the geological feature vector, and establishing a preliminary dynamic prediction model. And simulating the possible progress and trend of the geological disaster by using a numerical simulation technology and a preliminary dynamic prediction model, and generating a numerical simulation prediction result. And then, optimizing model parameters such as a gradient descent algorithm, a genetic algorithm and the like to obtain an optimized dynamic prediction model. And (3) utilizing the optimized dynamic prediction model, combining real-time monitoring data, and analyzing the progress and trend of the geological disaster in real time to generate a dynamic prediction result of the geological disaster.
Risk assessment: and carrying out seismic disaster risk assessment based on a dynamic prediction result of the geological disasters by combining seismic wave propagation simulation and geological structure analysis. Firstly, according to a dynamic prediction result of geological disasters, determining the area and intensity of possible earthquake, and generating prediction earthquake information. Then, the propagation of the seismic wave in the crust is simulated by using a seismic wave propagation simulation model (such as a wave theory model and a finite difference model), and a seismic wave propagation simulation result is generated. And analyzing the possibly affected geological structure and the possibility of disaster by combining the seismic wave propagation simulation result and the geological structure data to generate a geological disaster possibility analysis result. And then, carrying out risk classification on the region by using a multi-scale analysis method, and generating a geological disaster risk region map.
Personalized early warning: and analyzing social network data by using machine learning, and identifying and predicting the crowd possibly threatened by the geological disaster according to the geological disaster risk area map. And collecting social network data of the area according to the geological disaster risk area diagram, extracting information such as user regions, activity conditions and the like, and constructing a preliminary social network data set. And cleaning and formatting the preliminary social network data set, removing invalid, wrong or repeated information, and obtaining the cleaned social network data set. And then, identifying the crowd possibly threatened by the geological disaster according to the geological disaster risk area map and the cleaned social network data set, and generating a primary threatened crowd list. And finally, analyzing the list of the primarily threatened crowd by using a machine learning algorithm, and performing risk early warning to form personalized early warning.
Decision support system: and developing an intelligent decision support system by combining the geological disaster risk area diagram and the list of the threatened crowd. And (3) according to the geological disaster risk area map, the real-time early warning information and the disaster risk assessment result, a disaster response scheme is formulated. Integrating the contents of a disaster response scheme, real-time early warning information, a risk assessment result and the like, developing an intelligent decision support system, and providing a decision maker with a geological disaster response strategy report of the real-time early warning information, the risk assessment result and the disaster response scheme.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. The geological monitoring and early warning method is characterized by comprising the following steps of:
utilizing a data integration technology to fuse and preprocess multisource data comprising high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution, so as to generate a comprehensive geological data set;
extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set by using machine learning and deep learning technologies to serve as geological feature vectors;
combining a numerical simulation technology and a geological feature vector, constructing a dynamic prediction model, continuously updating monitoring data, feeding back the monitoring data into the dynamic prediction model, and analyzing the progress and trend of geological disasters in real time to generate a dynamic prediction result of the geological disasters;
Based on the dynamic geological disaster prediction result, combining seismic wave propagation simulation and geological structure analysis to perform seismic disaster risk assessment, and simultaneously performing risk classification on the region by using a multi-scale analysis method to generate a geological disaster risk region map;
the social network data is analyzed by machine learning, the crowd possibly threatened by the geological disaster is identified and predicted according to the geological disaster risk area diagram, a threat crowd list is generated, and personalized early warning is realized;
and developing an intelligent decision support system by combining the geological disaster risk area map and the threatening crowd list, and providing a geological disaster response strategy report comprising real-time early warning information, a risk assessment result and a disaster response scheme for a decision maker.
2. The geological monitoring and early warning method according to claim 1, wherein the step of generating the comprehensive geological data set by utilizing the data integration technology to fuse and preprocess the multi-source data including high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution comprises the following steps:
the method comprises the steps that a source collects high-resolution remote sensing images, geological exploration data, satellite radar interferometry data, meteorological data and population distribution data to construct an original multi-source data set;
Cleaning the original multi-source data set, removing abnormal and repeated values, unifying data formats, and obtaining a cleaned multi-source data set;
integrating the cleaned multi-source data set into a whole by using a KPCA fusion algorithm to serve as fused geological data;
and constructing geological attributes and parameters based on the fused geological data to form a comprehensive geological data set.
3. The geological monitoring and early warning method according to claim 1, wherein the step of extracting key geological features and geological disaster hidden danger features from the comprehensive geological data set as geological feature vectors using machine learning and deep learning techniques comprises the following steps:
utilizing statistical analysis and visualization tool analysis to synthesize a geological data set, and extracting key geological features and geological disaster hidden danger features to be used as a preliminary geological feature analysis result;
selecting key features from the preliminary geologic feature analysis results by using a feature selection algorithm, specifically a random forest, and generating a key geologic feature set;
deep learning, namely a convolutional neural network, is used for processing the key geological feature set, extracting deep geological features and generating a deep geological feature vector;
integrating the depth geological feature vector with the key geological feature set to construct a geological feature vector.
4. The geological monitoring and early warning method according to claim 1, wherein the step of constructing the dynamic prediction model by combining a numerical simulation technology and a geological feature vector, continuously updating monitoring data and feeding the monitoring data back into the dynamic prediction model, and analyzing the progress and trend of geological disasters in real time to generate a dynamic prediction result of the geological disasters is specifically as follows:
selecting a prediction algorithm comprising LSTM and GRU according to the geological feature vector, carrying out dynamic prediction on geological disasters, and establishing a preliminary dynamic prediction model;
simulating the possible progress and trend of the geological disaster by using a numerical simulation technology and the preliminary dynamic prediction model to generate a numerical simulation prediction result;
training by using a geological feature vector and the numerical simulation prediction result, and optimizing model parameters by a gradient descent algorithm and a genetic algorithm to obtain an optimized dynamic prediction model;
and providing real-time geological disaster progress and trend analysis by using the optimized dynamic prediction model and combining real-time monitoring data to obtain a geological disaster dynamic prediction result.
5. The geological monitoring and early warning method according to claim 1, wherein the step of performing seismic disaster risk assessment by combining seismic wave propagation simulation and geological structure analysis based on the dynamic prediction result of geological disasters and performing risk classification on areas by using a multi-scale analysis method at the same time comprises the following steps of:
Judging the area and intensity of possible earthquake according to the dynamic prediction result of the geological disaster, and generating prediction earthquake information;
simulating the propagation of the seismic waves in the crust according to the predicted seismic information by using a seismic wave propagation model comprising a fluctuation theory model and a finite difference model, and generating a seismic wave propagation simulation result;
analyzing the possibly affected geological structure and the possibility of disaster by combining the seismic wave propagation simulation result and geological structure data to generate a geological disaster possibility analysis result;
combining the geological disaster possibility analysis result and a multi-scale analysis algorithm, performing disaster risk assessment, and generating a preliminary disaster risk assessment report;
and dividing risk grades based on the preliminary disaster risk evaluation report, and generating a geological disaster risk area diagram.
6. The geological monitoring and early warning method according to claim 1, wherein the steps of analyzing social network data by machine learning, identifying and predicting a crowd possibly threatened by geological disasters according to the geological disaster risk area map, generating a threatening crowd list, and realizing personalized early warning are specifically as follows:
collecting social network data of an area based on the geological disaster risk area diagram, extracting user region and activity condition information, and integrating a preliminary social network data set;
Cleaning and formatting the preliminary social network data set, removing invalid, wrong or repeated information, and obtaining a cleaned social network data set;
identifying crowds possibly threatened by the geological disaster according to the geological disaster risk area map and the cleaned social network data set, and generating a primary threatened crowd list;
and analyzing the preliminary threat crowd list by utilizing machine learning, carrying out risk early warning on the crowd possibly threatened by the geological disaster, and establishing the threat crowd list.
7. The geological monitoring and early warning method according to claim 1, wherein the step of developing an intelligent decision support system by combining the geological disaster risk area map and the threatening crowd list to provide a geological disaster response strategy report including real-time early warning information, risk assessment results and disaster response schemes for a decision maker comprises the following steps:
planning and designing the structure and the function of an intelligent decision support system based on the geological disaster risk area diagram and the list of the threatened crowd, and integrating the structure and the function as a primary decision support system design scheme;
integrating the dynamic geological disaster prediction result, the preliminary disaster risk evaluation report and the list of the threatened crowd to generate real-time early warning information;
According to the design scheme of the preliminary decision support system, developing a decision support system, wherein the decision support system comprises the functions of displaying, pushing and managing real-time early warning information and is used as a decision support system with preliminary and complete functions;
according to the real-time early warning information, a disaster risk assessment result and a geological disaster dynamic prediction result, a disaster response scheme is formulated;
and integrating the disaster response scheme and the primarily complete decision support system for system performance test and optimization to obtain a final geological disaster response strategy report and an intelligent decision support system.
8. The geological monitoring and early warning system is characterized in that the geological monitoring and early warning system is used for executing the geological monitoring and early warning method according to any one of claims 1-7, and the geological monitoring and early warning system consists of a data integration module, a feature extraction module, a dynamic prediction model module, a risk assessment module, a personalized early warning module and a decision support module;
the data integration module integrates the high-resolution remote sensing image, the geological exploration data, the satellite radar interferometry data, the meteorological data and the population distribution data to construct a comprehensive geological data set;
the feature extraction module uses a comprehensive geological data set, performs geological feature extraction through machine learning and deep learning technologies, performs deep analysis on data through statistical analysis and visualization tools, screens out key features through a feature selection algorithm, and performs deep extraction on the key features through convolutional neural networks and other technologies to form geological feature vectors;
The dynamic prediction model module builds a dynamic prediction model for the dynamic prediction model by utilizing a numerical simulation technology based on the geological feature vector, and adopts LSTM and GRU prediction algorithms to carry out preliminary construction of the model, and generates a geological disaster dynamic prediction result after the gradient descent algorithm and the genetic algorithm are optimized;
after a dynamic prediction result of the geological disaster is obtained, the risk assessment module analyzes the seismic area and the intensity, adopts a fluctuation theory model and a finite difference model to simulate the propagation of the seismic waves in the crust, analyzes the possibility of the disaster by combining the simulation result of the propagation of the seismic waves and geological structure data, and utilizes a multi-scale analysis algorithm to complete the assessment of the disaster risk so as to generate a geological disaster risk area diagram;
the personalized early warning module analyzes social network data based on a geological disaster risk area diagram by using a machine learning technology, determines people possibly facing threat, and combines real-time data with the geological disaster risk area diagram to obtain real-time early warning information so as to form a targeted geological disaster response strategy report;
the decision support module develops an intelligent decision support system based on a geological disaster response strategy report, real-time early warning information and a risk assessment result, and performs uninterrupted iteration update and optimization through an intelligent algorithm to provide decision suggestions for a decision maker;
The data integration module comprises a high-resolution remote sensing image sub-module, a geological exploration data sub-module, a satellite radar interferometry data sub-module, a meteorological data sub-module and a population distribution data sub-module;
the feature extraction module comprises a machine learning feature extraction sub-module, a deep learning feature extraction sub-module, a statistical analysis sub-module, a visualization tool sub-module and a key feature selection sub-module;
the dynamic prediction model module comprises an LSTM prediction sub-module, a GRU prediction sub-module, a numerical simulation sub-module, a gradient descent optimization sub-module and a genetic algorithm optimization sub-module;
the risk assessment module comprises a seismic area analysis sub-module, a seismic wave propagation simulation sub-module, a geological structure analysis sub-module, a disaster possibility analysis sub-module and a multi-scale risk assessment sub-module;
the personalized early warning module comprises a social network data analysis sub-module, a real-time early warning generation sub-module, a threat crowd determination sub-module, a risk area matching sub-module and a disaster response strategy reporting sub-module;
the decision support module comprises a response strategy analysis sub-module, an intelligent algorithm iteration sub-module, an early warning information integration sub-module, a risk assessment integration sub-module and a decision suggestion generation sub-module.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the geological monitoring pre-warning method of any one of claims 1 to 7.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the geological monitoring pre-warning method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311074844.6A CN116797030A (en) | 2023-08-25 | 2023-08-25 | Geological monitoring and early warning method, system, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311074844.6A CN116797030A (en) | 2023-08-25 | 2023-08-25 | Geological monitoring and early warning method, system, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116797030A true CN116797030A (en) | 2023-09-22 |
Family
ID=88050039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311074844.6A Pending CN116797030A (en) | 2023-08-25 | 2023-08-25 | Geological monitoring and early warning method, system, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116797030A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117172561A (en) * | 2023-11-03 | 2023-12-05 | 广东新禾道信息科技有限公司 | Geological disaster risk hidden danger prediction method and system based on intelligent model algorithm |
| CN117292262A (en) * | 2023-10-11 | 2023-12-26 | 中国公路工程咨询集团有限公司 | Geological mapping identification method and system based on unmanned aerial vehicle remote sensing image |
| CN117808272A (en) * | 2024-02-29 | 2024-04-02 | 南京迅集科技有限公司 | Industrial system productivity optimization and scheduling method and system based on machine learning |
| CN117874499A (en) * | 2024-03-13 | 2024-04-12 | 天津市地质研究和海洋地质中心 | Geological disaster early warning method and system based on dynamic data monitoring |
| CN117953664A (en) * | 2024-03-27 | 2024-04-30 | 中铁水利水电规划设计集团有限公司 | Geological disaster prediction method and system based on artificial intelligence |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524321A (en) * | 2020-04-21 | 2020-08-11 | 中国科学院、水利部成都山地灾害与环境研究所 | Geological disaster early warning method |
| CN111538076A (en) * | 2020-05-13 | 2020-08-14 | 浙江大学 | Earthquake magnitude rapid estimation method based on deep learning feature fusion |
| CN111862536A (en) * | 2020-06-26 | 2020-10-30 | 武汉北斗星度科技有限公司 | Automatic monitoring and early warning system for geological disasters |
| CN112735094A (en) * | 2020-12-17 | 2021-04-30 | 中国地质环境监测院 | Geological disaster prediction method and device based on machine learning and electronic equipment |
| US20210373199A1 (en) * | 2020-06-01 | 2021-12-02 | City University Of Hong Kong | Seismic hazard determination method and system |
| CN116182952A (en) * | 2023-03-06 | 2023-05-30 | 江苏融智绘地理信息科技有限公司 | Intelligent acquisition method for geological disaster investigation information |
| CN116386281A (en) * | 2023-03-22 | 2023-07-04 | 云南省地质环境监测院(云南省环境地质研究院) | Landslide hazard hidden danger remote sensing early warning system and method |
| CN116466399A (en) * | 2023-04-14 | 2023-07-21 | 之江实验室 | Prediction method and device, readable storage medium and electronic equipment |
| CN116580532A (en) * | 2023-04-20 | 2023-08-11 | 西藏大学 | Geological disaster early warning system based on radar remote sensing technology |
-
2023
- 2023-08-25 CN CN202311074844.6A patent/CN116797030A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111524321A (en) * | 2020-04-21 | 2020-08-11 | 中国科学院、水利部成都山地灾害与环境研究所 | Geological disaster early warning method |
| CN111538076A (en) * | 2020-05-13 | 2020-08-14 | 浙江大学 | Earthquake magnitude rapid estimation method based on deep learning feature fusion |
| US20210373199A1 (en) * | 2020-06-01 | 2021-12-02 | City University Of Hong Kong | Seismic hazard determination method and system |
| CN111862536A (en) * | 2020-06-26 | 2020-10-30 | 武汉北斗星度科技有限公司 | Automatic monitoring and early warning system for geological disasters |
| CN112735094A (en) * | 2020-12-17 | 2021-04-30 | 中国地质环境监测院 | Geological disaster prediction method and device based on machine learning and electronic equipment |
| CN116182952A (en) * | 2023-03-06 | 2023-05-30 | 江苏融智绘地理信息科技有限公司 | Intelligent acquisition method for geological disaster investigation information |
| CN116386281A (en) * | 2023-03-22 | 2023-07-04 | 云南省地质环境监测院(云南省环境地质研究院) | Landslide hazard hidden danger remote sensing early warning system and method |
| CN116466399A (en) * | 2023-04-14 | 2023-07-21 | 之江实验室 | Prediction method and device, readable storage medium and electronic equipment |
| CN116580532A (en) * | 2023-04-20 | 2023-08-11 | 西藏大学 | Geological disaster early warning system based on radar remote sensing technology |
Non-Patent Citations (1)
| Title |
|---|
| 刘立;李长安;高俊华;余德清;夏乐;: "基于北斗与InSAR的地质灾害监测关键问题探讨", 地质科技情报, no. 06 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292262A (en) * | 2023-10-11 | 2023-12-26 | 中国公路工程咨询集团有限公司 | Geological mapping identification method and system based on unmanned aerial vehicle remote sensing image |
| CN117292262B (en) * | 2023-10-11 | 2024-02-23 | 中国公路工程咨询集团有限公司 | Geological mapping identification method and system based on unmanned aerial vehicle remote sensing image |
| CN117172561A (en) * | 2023-11-03 | 2023-12-05 | 广东新禾道信息科技有限公司 | Geological disaster risk hidden danger prediction method and system based on intelligent model algorithm |
| CN117172561B (en) * | 2023-11-03 | 2024-01-02 | 广东新禾道信息科技有限公司 | Geological disaster risk hidden danger prediction method and system based on intelligent model algorithm |
| CN117808272A (en) * | 2024-02-29 | 2024-04-02 | 南京迅集科技有限公司 | Industrial system productivity optimization and scheduling method and system based on machine learning |
| CN117808272B (en) * | 2024-02-29 | 2024-05-10 | 南京迅集科技有限公司 | Industrial system productivity optimization and scheduling method and system based on machine learning |
| CN117874499A (en) * | 2024-03-13 | 2024-04-12 | 天津市地质研究和海洋地质中心 | Geological disaster early warning method and system based on dynamic data monitoring |
| CN117874499B (en) * | 2024-03-13 | 2024-05-31 | 天津市地质研究和海洋地质中心 | Geological disaster early warning method and system based on dynamic data monitoring |
| CN117953664A (en) * | 2024-03-27 | 2024-04-30 | 中铁水利水电规划设计集团有限公司 | Geological disaster prediction method and system based on artificial intelligence |
| CN117953664B (en) * | 2024-03-27 | 2024-06-18 | 中铁水利水电规划设计集团有限公司 | Geological disaster prediction method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116797030A (en) | Geological monitoring and early warning method, system, computer equipment and storage medium | |
| Corominas et al. | Recommendations for the quantitative analysis of landslide risk | |
| Wan | A spatial decision support system for extracting the core factors and thresholds for landslide susceptibility map | |
| CN111191880B (en) | Slope full life cycle safety management method based on digital mapping | |
| KR100982448B1 (en) | Ground subsidence prediction system and predicting method using the same | |
| Wang et al. | Rainfall‐induced landslide hazard assessment using artificial neural networks | |
| CN113283802A (en) | Landslide risk assessment method for complex and difficult mountain area | |
| CN116975576B (en) | Mountain road geological disaster risk evaluation method based on key information statistics | |
| Weatherill et al. | Framework for seismic hazard analysis of spatially distributed systems | |
| Niu et al. | Susceptibility assessment of landslides triggered by the Lushan earthquake, April 20, 2013, China | |
| Suh et al. | Subsidence hazard assessment at the Samcheok coalfield, South Korea: a case study using GIS | |
| De Risi et al. | Seismic risk at urban scale: the role of site response analysis | |
| CN114036841A (en) | Landslide incidence prediction method and system based on semi-supervised support vector machine model | |
| Delavar et al. | Earthquake vulnerability assessment for hospital buildings using a GIS-based group multi criteria decision making approach: a case study of Tehran, Iran | |
| Maurizio et al. | A multi temporal kernel density estimation approach for new triggered landslides forecasting and susceptibility assessment | |
| Di Meo et al. | Real time damage scenario and seismic risk assessment of Italian roadway network | |
| Seddiki et al. | Using GIS Combined with AHP for Mapping landslide Susceptibility in Mila, in Algeria | |
| Jin et al. | Earthquake Risk Assessment Approach Using Multiple Spatial Parameters for Shelter Demands. | |
| Zhang et al. | Assessment of Geological Hazards in Ningde Based on Hybrid Intelligent Algorithm. | |
| Li et al. | Risk-based tsunami early warning using random forest | |
| Barnhart et al. | Evaluation of debris-flow building damage forecasts | |
| Bullock et al. | Regional estimation of liquefaction-induced ground deformations using a data-informed probabilistic approach | |
| Tordesillas et al. | Augmented intelligence forecasting and what-if-scenario analytics with quantified uncertainty for big real-time slope monitoring data | |
| CN116797755B (en) | Modeling method for multi-time-space three-dimensional geological structure of mixed rock zone | |
| Khakimova et al. | THE ROLE OF DIGITALIZATION IN MONITORING HAZARDOUS GEOLOGICAL PROCESSES |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |