CN118247108A - Regional earthquake security assessment method and system based on database technology - Google Patents
Regional earthquake security assessment method and system based on database technology Download PDFInfo
- Publication number
- CN118247108A CN118247108A CN202410678411.XA CN202410678411A CN118247108A CN 118247108 A CN118247108 A CN 118247108A CN 202410678411 A CN202410678411 A CN 202410678411A CN 118247108 A CN118247108 A CN 118247108A
- Authority
- CN
- China
- Prior art keywords
- earthquake
- seismic
- data
- target area
- building
- 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
- 238000005516 engineering process Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims description 49
- 238000011156 evaluation Methods 0.000 claims abstract description 87
- 238000010276 construction Methods 0.000 claims abstract description 32
- 238000013058 risk prediction model Methods 0.000 claims abstract description 24
- 230000009471 action Effects 0.000 claims abstract description 23
- 230000000694 effects Effects 0.000 claims description 24
- 230000009467 reduction Effects 0.000 claims description 20
- 238000013461 design Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000012876 topography Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 8
- 230000010354 integration Effects 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 8
- 230000008485 antagonism Effects 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000032683 aging Effects 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 4
- 230000008901 benefit Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 238000011158 quantitative evaluation Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 11
- 238000013439 planning Methods 0.000 description 10
- 238000007619 statistical method Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 6
- 230000004044 response Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000002265 prevention Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 239000004566 building material Substances 0.000 description 2
- 238000013524 data verification Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000009440 infrastructure construction Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012502 risk assessment Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 208000009119 Giant Axonal Neuropathy Diseases 0.000 description 1
- 208000025174 PANDAS Diseases 0.000 description 1
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 1
- 240000000220 Panda oleosa Species 0.000 description 1
- 235000016496 Panda oleosa Nutrition 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000003042 antagnostic effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 239000004567 concrete Substances 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008846 dynamic interplay Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 201000003382 giant axonal neuropathy 1 Diseases 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000011150 reinforced concrete Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Geophysics And Detection Of Objects (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a regional earthquake safety evaluation method and a regional earthquake safety evaluation system based on a database technology, wherein earthquake history data, geological exploration data, topographic and geomorphic information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information are collected as data required for earthquake safety evaluation and are stored into a central database after being preprocessed; extracting data required by seismic safety evaluation corresponding to a target area from a central database by utilizing database query; establishing a seismic risk prediction model based on the data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area within a preset time period; evaluating the vulnerability level of a target area under the action of an earthquake by combining the structure type, the construction year and the earthquake fortification level information of a building in the target area; and calculating the risk level of the earthquake in the target area based on the occurrence frequency of the earthquake and the vulnerability level, and realizing quantitative evaluation of the earthquake risk in the target area.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a regional earthquake security assessment method and system based on a database technology.
Background
Traditional seismic safety evaluation methods are mostly dependent on manual field investigation, manual statistical analysis of historical seismic data and simple mathematical model prediction, and are time-consuming and labor-consuming, and accuracy and efficiency are often difficult to meet the requirements of modern disaster prevention and reduction. Particularly, in the area development planning under complex geological conditions, a systematic and fine earthquake safety assessment tool is lacking, so that the fields of urban planning, infrastructure construction and the like face a great risk.
Under the background, the rapid development of database technology and information technology brings revolutionary changes to the field of seismic safety evaluation. By constructing the regional earthquake evaluation system based on the database technology, the effective integration and management of massive earthquake data, geological data, building information and other multi-source data can be realized. But the system can not comprehensively evaluate key factors, and provides scientific decision support for urban planning, land utilization, building design and emergency response.
Disclosure of Invention
The embodiment of the invention provides a regional earthquake safety assessment method and a regional earthquake safety assessment system based on a database technology, which can at least solve the problem that the prior art cannot comprehensively assess key factors and provide scientific decision support for urban planning, land utilization, building design and emergency response.
In a first aspect, an embodiment of the present invention provides a regional earthquake security assessment method based on a database technology, including:
Collecting seismic history data, geological exploration data, topographic and geomorphic information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by seismic safety evaluation, and storing the data in a central database after preprocessing;
Extracting data required by seismic safety evaluation corresponding to a target area from a central database by utilizing database query;
establishing a seismic risk prediction model based on the data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area within a preset time period;
Evaluating the vulnerability level of a target area under the action of an earthquake by combining the structure type, the construction year and the earthquake fortification level information of a building in the target area;
and calculating the seismic risk level of the target area based on the seismic occurrence frequency and the vulnerability level.
Optionally, the step of extracting data required for seismic security assessment corresponding to the target area from the central database using database query includes:
The central database automatically captures earthquake news and disaster reports on the Internet by utilizing a crawler technology to supplement real-time information so as to provide data required by inquiring earthquake safety evaluation corresponding to a target area;
The central database also comprises detailed design drawings and construction records of the building in the target area so as to ensure the accuracy of the structural type, the construction year and the earthquake fortification level information of the building.
Optionally, the step of establishing a seismic risk prediction model based on the data required by the seismic safety evaluation to evaluate the occurrence frequency of the earthquake in the target area within a preset time period includes:
Cleaning data required by seismic safety evaluation extracted from a central database aiming at a target area, removing abnormal values and filling missing values so as to ensure data quality;
Based on the data required by the pre-processed seismic safety evaluation, a mixed model framework is adopted to construct a seismic risk prediction model, wherein the seismic risk prediction model combines a seismology theory and a deep learning model, the data required by the seismic safety evaluation of a target area is used as a training set, model super parameters are adjusted through cross verification, and the prediction performance of the seismic risk prediction model is optimized.
Optionally, the step of constructing the seismic risk prediction model by using the mixed model framework includes:
Adopting a deep learning architecture and generating uncertainty of an antagonism network for simulating earthquake activities so as to integrate the advantages of the model through a weighted fusion integration method;
The deep learning framework structure can be expressed as follows:
；
Wherein, Representing time step/>Hidden state of/>Is the data required by seismic safety evaluation,/>And/>Respectively nonlinear activation functions,/>And/>Is a model parameter;
Constructing a condition-based countermeasure network to simulate uncertainty in seismic activity, the condition-based countermeasure network including a generator Sum discriminator/>The expression for the conditional antagonism network is:
；
In the context of a seismic prediction scenario, For generating new samples of seismic data,/>For determining whether the input data is real seismic data or new samples of seismic data, wherein/>The input noise is sampled from a gaussian distribution and used as a seed for generating new samples of seismic data.
Optionally, the method further comprises:
the weighted average expression of the weighted fusion integration method is as follows:
；
Wherein, Is the final prediction output,/>Represents the/>Prediction function of individual model,/>Is the weight assigned to the model;
Second, design The following are provided:
；
Wherein, And/>Is a constant for adjusting the magnitude of the overall weight; /(I)And/>Is an index that is adjusted according to the importance of the feature.
Optionally, the step of evaluating the vulnerability level of the target area under the action of earthquake by combining the structure type, the construction year and the earthquake fortification level information of the building in the target area comprises the following steps:
calculating earthquake resistance index of building according to building structure type Wherein/>，/>Representing field correction factor,/>A measurement representing the average value of shear wave velocity at the first 30 meters depth;
introduction of building age reduction factors based on year of construction Wherein/>Is an aging rate constant,/>Adjusting the earthquake resistance of the building according to the age of the building;
determining earthquake resistance evaluation index based on preset earthquake fortification level information The calculation formula isWherein/>Is the structural durability coefficient,/>For damage tolerance coefficient,/>Is the vulnerability index under the action of earthquake;
And determining the vulnerability grade of the target area under the action of earthquake based on the earthquake resistance index, the building age reduction factor and the earthquake resistance performance evaluation index.
Optionally, the step of determining the vulnerability level of the target area under the action of the earthquake based on the earthquake resistance index, the building age reduction factor and the earthquake resistance evaluation index includes:
according to the earthquake resistance index of each building Age reduction factor/>Earthquake resistance evaluation index/>Calculating comprehensive vulnerability score/>, of each buildingThe expression is as follows:
；
Wherein, Representing all buildings/>, of the areaFor normalization processing; /(I)，/>，/>Is the weight of each factor,/>Representing age reduction factor,/>Representing an earthquake resistance evaluation index;
Score comprehensive vulnerability Comparing with a preset standard threshold value set, classifying the building into a plurality of vulnerability grades, and setting the following grading rules:
-low vulnerability: ；
medium vulnerability: ；
high vulnerability: ；
extremely high vulnerability: ；
Wherein, ,/>,/>The thresholds for low, medium, and high vulnerability, respectively.
In a second aspect, an embodiment of the present invention provides a regional earthquake security assessment system based on a database technology, including:
The collecting module is used for collecting earthquake history data, geological exploration data, topography information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by earthquake safety evaluation, and storing the data into the central database after preprocessing;
The query module is used for utilizing the database to query and extracting data required by seismic safety evaluation corresponding to the target area from the central database;
The first evaluation module is used for establishing a seismic risk prediction model based on data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area in a preset time period;
The second evaluation module is used for evaluating the vulnerability level of the target area under the action of earthquake by combining the structure type, the construction year and the earthquake fortification level information of the building in the target area;
And the calculation module is used for calculating the earthquake risk level of the target area based on the earthquake occurrence frequency and the vulnerability level.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to run the computer program to perform the regional seismic assessment method based on the database technology according to the first aspect.
In a fourth aspect, an embodiment of the present invention provides a readable storage medium, where a computer program is stored, where the computer program includes program code for controlling a process to execute a process, where the process includes the regional seismic evaluation method based on database technology according to the first aspect.
The embodiment of the invention uses the collected earthquake history data, geological exploration data, topography and topography information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by earthquake safety evaluation, and stores the data into a central database after preprocessing; extracting data required by seismic safety evaluation corresponding to a target area from a central database by utilizing database query; establishing a seismic risk prediction model based on the data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area within a preset time period; evaluating the vulnerability level of a target area under the action of an earthquake by combining the structure type, the construction year and the earthquake fortification level information of a building in the target area; based on the earthquake occurrence frequency and the vulnerability level, calculating to obtain the earthquake risk level of the target area, realizing quantitative evaluation of the earthquake risk of the target area, combining the earthquake occurrence frequency with the vulnerability level of the building, and determining the whole earthquake risk level of the target area through cross analysis.
The beneficial effects of the embodiments of the present invention may refer to technical effects corresponding to technical features in the specific implementation manner, and are not described herein.
Drawings
FIG. 1 is a schematic diagram of a regional earthquake safety evaluation method based on a database technology according to an embodiment of the present invention;
Fig. 2 is a schematic illustration of a middle flow of another regional earthquake safety assessment method based on a database technology according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
In the current society, with the acceleration of the urban process and the frequent occurrence of global earthquake activities, the ability to ensure the safety of urban construction and major engineering projects, especially against earthquake disasters, has become a vital task. Traditional seismic safety evaluation methods are mostly dependent on manual field investigation, manual statistical analysis of historical seismic data and simple mathematical model prediction, and are time-consuming and labor-consuming, and accuracy and efficiency are often difficult to meet the requirements of modern disaster prevention and reduction. Particularly, in the area development planning under complex geological conditions, a systematic and fine earthquake safety assessment tool is lacking, so that the fields of urban planning, infrastructure construction and the like face a great risk.
In this context, the rapid development of database technology and information technology has brought revolutionary changes to the field of seismic security assessment. By constructing the regional earthquake evaluation system based on the database technology, the effective integration and management of massive earthquake data, geological data, building information and other multi-source data can be realized. The system can update global and local earthquake monitoring data in real time, comprehensively evaluate key factors such as earthquake activity rules, geological structure stability, soil liquefaction potential, building earthquake resistance and the like by applying a high-level data analysis algorithm, and provide scientific decision support for urban planning, land utilization, building design and emergency response.
The embodiment provides a specific implementation method of a regional earthquake safety evaluation system based on a database technology, as shown in the problem 1, the method comprises the following steps:
Step 1: collecting and integrating data, namely collecting seismic history data, geological exploration data, topography and topography information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by seismic safety evaluation, and storing the data into a central database after preprocessing;
in the embodiment of the invention, the data source collection refers to that the system firstly collects the historical seismic data (including earthquake time, earthquake level, intensity and the like), geological exploration data (such as soil type, fault distribution), topography and relief information (altitude, gradient), geological structure information (stratum structure, fault activity), geophysical exploration information (gravity and magnetic force abnormality), site vibration parameters (such as peak acceleration PGA) and detailed attribute information (such as structure type, construction age, floor height and earthquake resistance level) of a building from authoritative channels such as a national seismic bureau, a geological survey institution, a topography and relief research department, a building management department and the like.
The data preprocessing refers to that collected data is subjected to cleaning, format unification, outlier rejection and other processes, so that the data quality is ensured, and then the collected data is stored in a central database. The database adopts high-efficiency data model design, and is convenient for quick retrieval and analysis.
Through the step, a comprehensive and accurate earthquake safety base database of the target area is established, a solid base is laid for subsequent analysis, and the reliability and accuracy of an evaluation result are ensured.
Step 2: data analysis and processing, namely, utilizing database query to extract data required by seismic safety evaluation corresponding to a target area from a central database;
According to the embodiment of the invention, according to the geographic coordinate range of a specific target area, the SQL query language or other database query tools are utilized to accurately extract the seismic history record, the geological information and the building attribute data related to the specific target area from the central database, so that quantitative evaluation of the seismic risk of the target area is realized, scientific risk early warning information is provided for local government and construction units, and reasonable land utilization planning and anti-seismic fortification strategies are facilitated to be formulated.
Step 3: the earthquake risk evaluation is carried out, and an earthquake risk prediction model is established based on data required by the earthquake safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area in a preset time period;
The embodiment of the invention establishes a seismic risk prediction model based on the extracted data by adopting a statistical method or a machine learning algorithm (such as logistic regression and a neural network), and the model predicts the probability of occurrence of the earthquake and the possible maximum earthquake level of the target area in a preset time period (such as 10 years and 50 years) in the future by taking the factors such as the earthquake activity period, the geological condition and the like into consideration.
Step 4: analyzing the vulnerability of a building and an infrastructure, and evaluating the vulnerability level of a target area under the action of an earthquake by combining the structural type, the construction year and the earthquake fortification level information of the building in the target area;
Wherein, vulnerability index calculation: for each building in the target area, according to the structural type (such as a frame and brick and concrete), the construction year and the earthquake fortification level (such as design intensity), the earthquake resistance index, the age reduction factor and the earthquake resistance evaluation index are calculated, as described above.
Vulnerability classification: in combination with the indexes, the earthquake vulnerability grades of the buildings are divided by adopting a multi-criterion evaluation method (such as analytic hierarchy process and fuzzy comprehensive evaluation), such as low, medium, high and extremely high, so as to clearly indicate earthquake-resistant weak points of different buildings in the area, provide basis for preferential reinforcement and reconstruction, and reduce casualties and property loss possibly caused by earthquake disasters.
Step 5: and (3) comprehensive risk assessment, namely calculating the risk level of the earthquake in the target area based on the occurrence frequency of the earthquake and the vulnerability level.
In the embodiment of the invention, the risk matrix construction is to combine the occurrence frequency of the earthquake with the vulnerability grade of the building to construct an earthquake risk grade matrix. And determining the overall earthquake risk level of the target area through cross analysis.
The risk classification is to divide the target area into low risk, medium risk, high risk and extremely high level according to the risk matrix result, and each level corresponds to different countermeasures and resource allocation suggestions.
And the finally formed earthquake risk map of the target area provides visual guidance for government decision-making, community planning and emergency response plan making, and promotes reasonable allocation of resources and effective prevention and control of earthquake disasters.
Further, in still another embodiment of the present invention, the step of extracting data required for seismic security assessment corresponding to the target area from the central database by using database query includes:
The central database automatically captures earthquake news and disaster reports on the Internet by utilizing a crawler technology to supplement real-time information so as to provide data required by inquiring earthquake safety evaluation corresponding to a target area;
In this step, the system periodically and automatically accesses authoritative seismic information websites, news portals and social platforms, screens and captures up-to-date seismic news, disaster reports and real-time monitoring data for keywords (such as "earthquake", "geological disaster", "rescue action", etc.). The information crawled includes, but is not limited to, earthquake occurrence time, location, magnitude, impact range, and preliminary damage assessment reports. After cleaning, de-duplication and standardization treatment, the real-time data are synchronized to a central database in real time, so that an evaluation system can timely reflect earthquake activity dynamics, and in addition, a special real-time information table can be set up in the central database for storing data captured from the Internet. The table is intelligently associated with other tables such as historical seismic data, geological exploration data and the like to form a rich data resource pool. By adopting a data fusion algorithm, the newly added real-time data can be ensured to be seamlessly fused into the existing data system, and the comprehensiveness and timeliness of the data are improved.
The central database also comprises detailed design drawings and construction records of the building in the target area so as to ensure the accuracy of the structural type, the construction year and the earthquake fortification level information of the building.
The central database specifically designs a building information subsystem that stores not only basic building information (e.g., address, structure type, year of construction) collected from official channels, but also incorporates detailed design drawings and construction records of the building in the target area. The design drawing comprises a building plan, a structural design drawing and the like, and the construction record covers key information such as building materials, construction technology, earthquake-proof fortification level and the like. These data are automatically entered into the database through cooperation with the building units, design institutions, and digital scanning and OCR techniques, ensuring accuracy of the data.
In addition, data verification and updating can be performed in practical application so as to implement a regular data verification process, and consistency of the building actual state and database records is compared by using an automatic script, wherein the consistency comprises on-site investigation and drawing rechecking, and matching checking of construction records and completion acceptance reports. For the discovered inconsistent or missing information, the verification is immediately performed and the database is updated, so that the freshness and reliability of the data are maintained.
Through the embodiment, the system remarkably improves the instantaneity and accuracy of seismic safety evaluation. The automatic grabbing and fusion of the internet data enable the system to respond to the earthquake event rapidly, and provide data support for instant evaluation and emergency response. Meanwhile, by integrating detailed design drawings and construction records, the accuracy of building earthquake resistance evaluation is ensured, and a solid data base is provided for formulating targeted disaster prevention and reduction measures. The series of measures promote the scientificalness and refinement level of the earthquake risk management together, and provide powerful technical support for guaranteeing the life and property safety of people.
Further, in still another embodiment of the present invention, the step of establishing a seismic risk prediction model based on the data required for seismic safety evaluation to evaluate the frequency of occurrence of the earthquake in the target area within a preset time period includes:
Cleaning data required by seismic safety evaluation extracted from a central database aiming at a target area, removing abnormal values and filling missing values so as to ensure data quality;
In an embodiment of the invention, deep feature engineering processing is performed on the seismic safety evaluation data of the target area extracted from the central database, including but not limited to feature selection, feature conversion and feature construction. The goal of this stage is to mine out key factors that affect the risk of earthquakes and ensure the quality and consistency of the data. Preprocessing may involve normalization, etc. to eliminate dimensional effects and improve model convergence, in particular, extracting data sets of seismic histories, geologic features, topography, etc. associated with a target region from a central database. The method comprises the steps of removing repeated records, filling missing values (using interpolation or an estimation method based on data distribution) by using a data cleaning tool and algorithm (such as Pandas library of Python), identifying and eliminating abnormal values (using a Z-score or IQR method), ensuring the accuracy and the integrity of data, and extracting meaningful characteristics such as historical seismic activity frequency, fault distance, geological stability index, topography influence factor and the like from the preprocessed data based on a seismology theory. And a feature selection method (such as recursive feature elimination and correlation coefficient analysis) is adopted to simplify the feature set, reduce redundancy and improve model efficiency.
Based on the data required by the pre-processed seismic safety evaluation, a mixed model framework is adopted to construct a seismic risk prediction model, wherein the seismic risk prediction model combines a seismology theory and a deep learning model, the data required by the seismic safety evaluation of a target area is used as a training set, model super parameters are adjusted through cross verification, and the prediction performance of the seismic risk prediction model is optimized.
The step of constructing the earthquake hazard prediction model by adopting the mixed model frame comprises the following steps:
Adopting a deep learning architecture and generating uncertainty of an antagonism network for simulating earthquake activities so as to integrate the advantages of the model through a weighted fusion integration method;
The deep learning framework structure can be expressed as follows:
；
Wherein, Representing time step/>Hidden state of/>Is the data required by seismic safety evaluation,/>And/>Respectively nonlinear activation functions,/>And/>Is a model parameter;
Constructing a condition-based countermeasure network to simulate uncertainty in seismic activity, the condition-based countermeasure network including a generator Sum discriminator/>The expression for the conditional antagonism network is:
；
In the context of a seismic prediction scenario, For generating new samples of seismic data,/>For determining whether the input data is real seismic data or new samples of seismic data, wherein/>The input noise is sampled from a gaussian distribution and used as a seed for generating new samples of seismic data.
In the seismic prediction scenario that generates the reactance network (GANs), the two core components are the "Generator" (G) and the "arbiter" (Discriminator, D). They cooperate to enhance the performance of the model through an antagonistic learning process, particularly in terms of generating realistic and diverse patterns of seismic activity. The two component functions are explained in detail below:
Generators (G)
Meaning of representative: generator G is a deep learning model whose goal is to create new samples as close as possible to the real seismic data. In the context of seismic prediction, G is designed to generate a series of possible seismic activity patterns that reflect the spatio-temporal characteristics of the occurrence of the earthquake, such as the frequency, intensity distribution, etc., of the earthquake. The generated data may be time series data of the earthquake, a seismic waveform, or some statistical feature of the seismic activity.
Working principle: the generator typically receives as input a random noise vector z (typically from a simple probability distribution, such as a gaussian distribution) and then converts this noise to seemingly real seismic data samples through a series of transformations (implemented by a multi-layer neural network). As training proceeds, G learns how to better utilize z to generate data, making it more and more difficult for these generated data to be distinguished from real data.
Distinguishing device (D)
Meaning of representative: the arbiter D is also a deep learning model, but its task is to determine whether a given seismic data sample is authentic (from the actual observation dataset) or counterfeit (produced by the generator G), as opposed to the generator. In the context of seismic prediction, D needs to learn and identify complex patterns and rules in the seismic data in order to accurately distinguish true seismic records from synthetic data.
Working principle: d accepts as input a seismic data sample and outputs a probability value between 0 and 1 representing the probability that the sample is considered authentic. In the early stage of training, D relatively easily distinguishes real samples from generated samples, but as the quality of data generated by G is improved, challenges facing D are increased, and own discriminant criteria need to be continuously optimized, which promotes D to deeply learn complex details of seismic activities.
During the countermeasure training process, G and D are played against each other, G generating more realistic, indistinguishable patterns of seismic activity to fool D, while D attempts to more accurately identify which are realistic seismic data and which are generated by G. The dynamic interaction mechanism improves the performance of both parties, and finally G can generate a highly realistic seismic data sample, and the existence of D promotes G to better capture the uncertainty characteristic of seismic activity, so that the overall prediction capability and robustness of the model are enhanced.
In the training cycle, the specific update procedure is as follows:
For generator G:
the input noise (z) is typically sampled from a uniform or gaussian distribution as a seed for generating new samples. Its dimensions determine the potential size of the space in which the data is generated.
Loss function, namely, binary cross entropy loss is generally adopted, and the probability that the sample generated by G is misjudged as true by D is measured. The aim is to maximize this probability, i.e. to let G spoof D better.
For the discriminator D
True data-samples from actual seismic recordings.
Data is generated, namely, seismic activity simulation data generated by G according to the noise vector.
The loss function includes two parts, one is the loss of the probability that the real data is judged to be true and the other is the loss of the probability that the generated data is judged to be false. The objective is to minimize the loss of true data that is misclassified and to maximize the loss of correctly identified generated data.
Alternate training, in each iteration, the parameters of the arbiter D are updated first, and then the parameters of the generator G are updated based on the updated D. Thus, the performance of both parties can be gradually improved.
Gradient penalty-gradient penalty (e.g., gradient penalty GP for wasperstein distance, or more commonly R1 regularization) may be added in practice to stabilize training, preventing pattern collapse.
Learning rate decays, i.e., gradually decreasing the learning rate as training progresses helps the model converge to a better solution.
And (3) early-stopping strategy, namely observing performance indexes on the verification set, stopping training when no significant improvement exists, and avoiding over-fitting.
Through the steps, the generation countermeasure network can gradually optimize the fidelity of the generated seismic activity mode, and the performance of the model in the aspect facing the uncertainty of the seismic prediction is improved.
Further, to make it a more complex and varied specific scenario, a specific expression of w i may be designed to reflect the characteristics of the seismic data. In the field of seismic prediction, the contributions of different features (e.g., magnitude, source depth, historical seismic activity frequency, etc.) to the prediction result may be different. Therefore, the embodiment of the invention can dynamically adjust the weighted average expression of the weighted fusion integration method of each feature according to the relevance, importance and reliability of the feature as follows:
；
Wherein, Is the final prediction output,/>Represents the/>Prediction function of individual model,/>Is the weight assigned to the model;
Second, design The following are provided:
；
Wherein, And/>Is a constant for adjusting the magnitude of the overall weight; /(I)And/>Is an index that is adjusted according to the importance of the feature. If a feature is more important, the corresponding/>The value is larger. These parameters may be learned by optimization algorithms (e.g., gradient descent) during training of the predictive model or may be preset based on statistical analysis of historical data.
Specifically, in actual operation, whether parameters are learned by an optimization algorithm or set based on statistical analysis of historical data, certain methodologies need to be followed. The following are specific examples of two approaches:
by optimizing algorithm learning parameters, it is assumed that a machine learning model (such as a neural network or a support vector machine) is used to predict the risk of earthquakes, and the model directly or indirectly includes the weight parameters 、/>、/>And/>In this scenario, it is a common practice to use a gradient descent method to optimize these parameters. The following is a brief example flow based on gradient descent:
1. Model definition: a model is constructed, the output of which is related to the prediction of the risk of earthquakes, wherein the computational logic of w i is embedded, either directly or through an activation function. For example, if a neural network is used, a weight matrix may be designed at a layer of the network, the elements of the matrix being composed of 、/>、/>And/>And (5) combining and calculating to obtain the product.
2. Loss function definition: a suitable loss function, such as Mean Square Error (MSE) or cross entropy loss, is selected to measure the difference between the model predictions and the actual seismic data.
3. Gradient calculation: model parameters (include、/>、/>And/>) The calculation is performed with respect to the gradient of the loss function. This step is typically done automatically by a back propagation algorithm.
4. Parameter updating: the parameters are updated at a learning rate η according to the gradient descent law. For example, for parametersUpdate formula to/>And similarly, other parameters are updated correspondingly.
5. Iterative optimization: repeating steps 3-4 until the loss of the model is no longer significantly reduced or reaches a predetermined number of iterations.
Statistical analysis based on historical data presets:
If statistical analysis based on historical data is selected to set these parameters, this can be done by:
1. data collection and pretreatment: a large amount of seismic event data, including magnitude, depth of source, etc., is collected and subjected to the necessary data cleansing and preprocessing.
2. Feature importance assessment: the importance of each feature (e.g., magnitude, depth of source) to the seismic risk prediction is assessed using statistical methods (e.g., correlation analysis, mutual information, chi-square test) or machine learning feature selection methods (e.g., feature importance of random forests, sparsity of LASSO regression).
3. Parameter estimation: setting based on feature importance resultsAnd/>Is a value of (2). For example, if the magnitude is found by analysis to be highly correlated with the risk of earthquakes, one can give/>Higher values. And meanwhile, according to expert knowledge or data distribution, determining the initial values of alpha and gamma, and ensuring the rationality of the weight factors.
4. And (3) verification and adjustment: and verifying the performance of the model on historical data by using a cross verification method and the like, and fine-tuning parameters according to verification results until the performance of the model reaches a satisfactory level.
By the two methods, parameters can be effectively determined whether by an automatic learning process or manual setting based on statistical analysis、/>、/>And/>And further improves the accuracy and reliability of the earthquake risk prediction model.
In the embodiment of the invention, by giving more relevant characteristics higher weight, the influence of irrelevant or noise characteristics can be reduced, thereby improving the accuracy and reliability of the prediction model; with the deep research of seismology, new findings can be rapidly reflected in weight distribution, so that a model evolves with the progress of scientific cognition; under limited computing resources, high weights focused on key features can help converge to an effective model faster, saving time and computing costs; weight distribution reveals which factors are most critical in seismic prediction, which is critical to understanding and communicating with the predicted results, particularly in risk assessment and emergency response planning.
In still another embodiment of the present invention, the step of evaluating the vulnerability level of the target area under the action of earthquake by combining the structural type, construction year and earthquake fortification level information of the building in the target area includes:
calculating earthquake resistance index of building according to building structure type Wherein/>，/>Representing field correction factor,/>A measurement representing the average value of shear wave velocity at the first 30 meters depth;
introduction of building age reduction factors based on year of construction Wherein/>Is an aging rate constant,/>Adjusting the earthquake resistance of the building according to the age of the building;
determining earthquake resistance evaluation index based on preset earthquake fortification level information The calculation formula isWherein/>Is the structural durability coefficient,/>For damage tolerance coefficient,/>Is the vulnerability index under the action of earthquake;
And determining the vulnerability grade of the target area under the action of earthquake based on the earthquake resistance index, the building age reduction factor and the earthquake resistance performance evaluation index.
Further, the step of determining the vulnerability level of the target area under the action of earthquake based on the earthquake resistance index, the building age reduction factor and the earthquake resistance evaluation index comprises the following steps:
according to the earthquake resistance index of each building Age reduction factor/>Earthquake resistance evaluation index/>Calculating comprehensive vulnerability score/>, of each buildingThe expression is as follows:
；/>
Wherein, Representing all buildings/>, of the areaFor normalization processing; /(I)，/>，/>Is the weight of each factor,/>Representing age reduction factor,/>Representing an earthquake resistance evaluation index;
Score comprehensive vulnerability Comparing with a preset standard threshold value set, classifying the building into a plurality of vulnerability grades, and setting the following grading rules:
-low vulnerability: ；
medium vulnerability: ；
high vulnerability: ；
extremely high vulnerability: ；
Wherein, ,/>,/>The thresholds for low, medium, and high vulnerability, respectively.
Assuming that we are evaluating the earthquake resistance of buildings located within a particular target area, the following is an example of how to operate specifically according to the above method:
1. Calculating a shock resistance index Vs30:
Field correction coefficient Kz: according to geological exploration data, determining that the target area belongs to a soft soil field, and consulting relevant specifications to obtain kz=1.2.
Shear wave velocity average value Sds: the shear wave velocity average value of the first 30 meters depth is measured to be 300 meters/second through geological radar detection.
Calculating Vs30: substitution into the formula yields vs30=kz×sds=1.2×300=360 m/s. This indicates that the earthquake resistance of the field in this area is better.
2. Building age reduction factor Af:
aging rate constant λ: depending on the building materials and maintenance conditions, λ=0.005 year-1 is assumed.
Building age t: a building was built in 1990, currently 2023, then t=2023-1990=33.
Af is calculated: substituting the formula yields af=e- λt=e-0.005×33≡0.84. This means that the earthquake resistance of the building is reduced by aging.
3. Shock resistance evaluation index QBR
Structural durability coefficient Rd: according to the structural design file of the building, the building is of a reinforced concrete structure, and rd=0.9.
Damage tolerance coefficient Cd: referring to the building specification, the damage tolerance of the building is higher, and cd=0.8 is set.
Vulnerability index Ie under seismic action: ie=0.7 based on statistical analysis of the effect of historical earthquakes on this type of building.
Calculating QBR: substitution into the formula yields qbr=rd×cd×ie=0.9×0.8×0.7=0.504. The building is indicated to have moderate earthquake resistance evaluation index.
4. Determining vulnerability level
Comprehensive evaluation: in combination with Vs 30=360 m/s representing better site conditions, af=0.84 shows that the building is compromised by age, while qbr=0.504 indicates that the building itself has moderate earthquake resistance.
Vulnerability classification: the partition criteria are assumed as follows:
High: vs30<300m/s and QBR <0.4
In (a): vs30<400m/s of 300.ltoreq.Vs and QBR < 0.4.ltoreq.QBR <0.6
Low: vs30 is more than or equal to 400m/s and QBR is more than or equal to 0.6
According to the above conditions, the building site conditions are good, but the building can be rated as "medium vulnerability" due to the compromise of the earthquake resistance caused by the age of the building and the medium evaluation index of the earthquake resistance. The embodiment of the invention shows how the theoretical formula is applied to the earthquake resistance evaluation of the actual building through specific numerical calculation, so as to determine the vulnerability grade of the actual building under the action of earthquake.
In still another embodiment of the present invention, a regional earthquake security assessment system based on database technology, as shown in fig. 2, includes:
The collecting module 01 is used for collecting earthquake history data, geological exploration data, topography information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by earthquake safety evaluation, and storing the data into the central database after preprocessing;
the query module 02 is used for utilizing database query to extract data required by seismic safety evaluation corresponding to the target area from the central database;
The first evaluation module 03 is configured to establish a seismic risk prediction model based on data required by the seismic safety evaluation, so as to evaluate the occurrence frequency of the earthquake in the target area within a preset time period;
The second evaluation module 04 is used for evaluating the vulnerability level of the target area under the action of earthquake by combining the structure type, the construction year and the earthquake fortification level information of the building in the target area;
The calculating module 05 is configured to calculate, based on the frequency of occurrence of the earthquake and the vulnerability level, a risk level of the earthquake in the target area.
The embodiment of the invention also provides electronic equipment, which comprises:
A processor;
A memory for storing processor-executable instructions;
wherein the processor is configured to invoke the instructions stored in the memory to perform the method described previously.
In yet another aspect of embodiments of the present invention, a computer-readable storage medium is provided, having stored thereon computer program instructions which, when executed by a processor, implement the method as described above.
The present invention may be a method, apparatus, system, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for performing various aspects of the present invention.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (10)
1. The regional earthquake evaluation method based on the database technology is characterized by comprising the following steps of:
Collecting seismic history data, geological exploration data, topographic and geomorphic information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by seismic safety evaluation, and storing the data in a central database after preprocessing;
Extracting data required by seismic safety evaluation corresponding to a target area from a central database by utilizing database query;
establishing a seismic risk prediction model based on the data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area within a preset time period;
Evaluating the vulnerability level of a target area under the action of an earthquake by combining the structure type, the construction year and the earthquake fortification level information of a building in the target area;
and calculating the seismic risk level of the target area based on the seismic occurrence frequency and the vulnerability level.
2. The regional seismic safety assessment method based on database technology according to claim 1, wherein the step of extracting data required for seismic safety assessment corresponding to the target region from the central database by using database query comprises:
The central database automatically captures earthquake news and disaster reports on the Internet by utilizing a crawler technology to supplement real-time information so as to provide data required by inquiring earthquake safety evaluation corresponding to a target area;
The central database also comprises detailed design drawings and construction records of the building in the target area so as to ensure the accuracy of the structural type, the construction year and the earthquake fortification level information of the building.
3. The regional earthquake safety assessment method based on the database technology according to claim 1, wherein the step of establishing an earthquake risk prediction model based on data required for the earthquake safety assessment to assess the occurrence frequency of the earthquake in the target region within a preset time period comprises the steps of:
Cleaning data required by seismic safety evaluation extracted from a central database aiming at a target area, removing abnormal values and filling missing values so as to ensure data quality;
Based on the data required by the pre-processed seismic safety evaluation, a mixed model framework is adopted to construct a seismic risk prediction model, wherein the seismic risk prediction model combines a seismology theory and a deep learning model, the data required by the seismic safety evaluation of a target area is used as a training set, model super parameters are adjusted through cross verification, and the prediction performance of the seismic risk prediction model is optimized.
4. The regional seismic survey method based on database technology of claim 3, wherein the step of constructing the seismic risk prediction model using a hybrid model framework comprises:
Adopting a deep learning architecture and generating uncertainty of an antagonism network for simulating earthquake activities so as to integrate the advantages of the model through a weighted fusion integration method;
The deep learning framework structure can be expressed as follows:
；
Wherein, Representing time step/>Hidden state of/>Is the data required by seismic safety evaluation,/>And/>Respectively nonlinear activation functions,/>And/>Is a model parameter;
Constructing a condition-based countermeasure network to simulate uncertainty in seismic activity, the condition-based countermeasure network including a generator Sum discriminator/>The expression for the conditional antagonism network is:
；
In the context of a seismic prediction scenario, For generating new samples of seismic data,/>For determining whether the input data is real seismic data or new samples of seismic data, wherein/>The input noise is sampled from a gaussian distribution and used as a seed for generating new samples of seismic data.
5. The regional seismic survey method based on database technology of claim 4, further comprising:
the weighted average expression of the weighted fusion integration method is as follows:
；
Wherein, Is the final prediction output,/>Represents the/>Prediction function of individual model,/>Is the weight assigned to the model;
Second, design The following are provided:
；
Wherein, And/>Is a constant for adjusting the magnitude of the overall weight; /(I)And/>Is an index that is adjusted according to the importance of the feature.
6. The regional earthquake safety assessment method based on the database technology as set forth in claim 1, wherein the step of assessing the vulnerability level of the target region under the action of an earthquake by combining the structural type, construction year and earthquake fortification level information of the building in the target region comprises:
calculating earthquake resistance index of building according to building structure type Wherein/>，/>Representing field correction factor,/>A measurement representing the average value of shear wave velocity at the first 30 meters depth;
introduction of building age reduction factors based on year of construction Wherein/>Is an aging rate constant,/>Adjusting the earthquake resistance of the building according to the age of the building;
determining earthquake resistance evaluation index based on preset earthquake fortification level information The calculation formula isWherein/>Is the structural durability coefficient,/>For damage tolerance coefficient,/>Is the vulnerability index under the action of earthquake;
And determining the vulnerability grade of the target area under the action of earthquake based on the earthquake resistance index, the building age reduction factor and the earthquake resistance performance evaluation index.
7. The regional earthquake safety assessment method based on the database technology as set forth in claim 6, wherein the step of determining the vulnerability level of the target region under the action of earthquake based on the earthquake resistance index, the building age reduction factor, and the earthquake resistance performance assessment index comprises:
according to the earthquake resistance index of each building Age reduction factor/>Earthquake resistance evaluation index/>Calculating comprehensive vulnerability score/>, of each buildingThe expression is as follows:
；
Wherein, Representing all buildings/>, of the areaFor normalization processing; /(I)，/>，/>Is the weight of each factor,/>Representing age reduction factor,/>Representing an earthquake resistance evaluation index;
Score comprehensive vulnerability Comparing with a preset standard threshold value set, classifying the building into a plurality of vulnerability grades, and setting the following grading rules:
-low vulnerability: ；
medium vulnerability: ；
high vulnerability: ；
extremely high vulnerability: ；
Wherein, ,/>,/>The thresholds for low, medium, and high vulnerability, respectively.
8. A regional seismic survey system based on database technology, comprising:
The collecting module is used for collecting earthquake history data, geological exploration data, topography information, geological structure information, geophysical exploration information, site vibration parameter information and building attribute information as data required by earthquake safety evaluation, and storing the data into the central database after preprocessing;
The query module is used for utilizing the database to query and extracting data required by seismic safety evaluation corresponding to the target area from the central database;
The first evaluation module is used for establishing a seismic risk prediction model based on data required by the seismic safety evaluation so as to evaluate the occurrence frequency of the earthquake in the target area in a preset time period;
The second evaluation module is used for evaluating the vulnerability level of the target area under the action of earthquake by combining the structure type, the construction year and the earthquake fortification level information of the building in the target area;
And the calculation module is used for calculating the earthquake risk level of the target area based on the earthquake occurrence frequency and the vulnerability level.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the database technology based regional seismic profiling method of claim 8.
10. A readable storage medium, characterized in that the readable storage medium has stored therein a computer program comprising program code for controlling a process to execute a process comprising the regional seismic profiling method based on database technology according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410678411.XA CN118247108A (en) | 2024-05-29 | 2024-05-29 | Regional earthquake security assessment method and system based on database technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410678411.XA CN118247108A (en) | 2024-05-29 | 2024-05-29 | Regional earthquake security assessment method and system based on database technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118247108A true CN118247108A (en) | 2024-06-25 |
Family
ID=91559342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410678411.XA Pending CN118247108A (en) | 2024-05-29 | 2024-05-29 | Regional earthquake security assessment method and system based on database technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118247108A (en) |
-
2024
- 2024-05-29 CN CN202410678411.XA patent/CN118247108A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3889652A1 (en) | Performance-level seismic motion hazard analysis method based on three-layer dataset neural network | |
| CN113379105B (en) | Site earthquake liquefaction disaster rapid evaluation method based on artificial intelligence | |
| CN113807570B (en) | XGBoost-based reservoir dam risk level assessment method and system | |
| CN111967712B (en) | Traffic risk prediction method based on complex network theory | |
| CN116975576B (en) | Mountain road geological disaster risk evaluation method based on key information statistics | |
| CN116797030A (en) | Geological monitoring and early warning method, system, computer equipment and storage medium | |
| CN114580706A (en) | Power financial service wind control method and system based on GRU-LSTM neural network | |
| CN110889440A (en) | Rockburst grade prediction method and system based on principal component analysis and BP neural network | |
| CN115879654B (en) | Underground roadway stability prediction and reliability evaluation method | |
| CN113009553A (en) | Interpretable seismic motion parameter probability density distribution prediction method based on NGboost and SHAP values | |
| CN111814699A (en) | Deep learning earthquake prediction method for SWARM electromagnetic satellite data | |
| CN111914943B (en) | Information vector machine method and device for comprehensively judging stability of dumping type karst dangerous rock | |
| CN111709072B (en) | Underground vibration amplitude parameter prediction method | |
| CN117726181A (en) | Collaborative fusion and hierarchical prediction method for typical disaster risk heterogeneous information of coal mine | |
| CN116992522A (en) | Deep foundation pit support structure deformation prediction method, device, equipment and storage medium | |
| Wang et al. | Cumulative absolute velocity prediction for earthquake early warning with deep learning | |
| CN117540303A (en) | Landslide susceptibility assessment method and system based on cross semi-supervised machine learning algorithm | |
| CN111026790A (en) | Structure safety assessment and forecasting method based on data mining | |
| CN118247108A (en) | Regional earthquake security assessment method and system based on database technology | |
| Zhang et al. | A real‐time seismic damage prediction framework based on machine learning for earthquake early warning | |
| Xiao et al. | New Risk Control Technology for Port Channel Construction Operations Based on BIM | |
| Manral et al. | Prediction of earthquake using machine learning algorithms | |
| Ruggieri et al. | Using transfer learning technique to define seismic vulnerability of existing buildings through mechanical models | |
| Sun | A data-driven building seismic response prediction framework: From simulation and recordings to statistical learning | |
| Mahsuli | Resilience of civil infrastructure by optimal risk mitigation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication |