CN114548585A - Urban building earthquake damage prediction method based on neural network - Google Patents

Urban building earthquake damage prediction method based on neural network Download PDF

Info

Publication number
CN114548585A
CN114548585A CN202210195922.7A CN202210195922A CN114548585A CN 114548585 A CN114548585 A CN 114548585A CN 202210195922 A CN202210195922 A CN 202210195922A CN 114548585 A CN114548585 A CN 114548585A
Authority
CN
China
Prior art keywords
building
earthquake damage
detected
sample
classification
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
Application number
CN202210195922.7A
Other languages
Chinese (zh)
Inventor
颜学渊
李小林
刘璐
杨国
周福彬
汤昌环
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou University
Fujian Jiuding Construction Engineering Co Ltd
Fujian Minqing Yijian Construction Development Co Ltd
Original Assignee
Fuzhou University
Fujian Jiuding Construction Engineering Co Ltd
Fujian Minqing Yijian Construction Development Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fuzhou University, Fujian Jiuding Construction Engineering Co Ltd, Fujian Minqing Yijian Construction Development Co Ltd filed Critical Fuzhou University
Priority to CN202210195922.7A priority Critical patent/CN114548585A/en
Publication of CN114548585A publication Critical patent/CN114548585A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/08—Construction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y02A30/60—Planning or developing urban green infrastructure

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Primary Health Care (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Educational Administration (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

The invention relates to a city building earthquake damage prediction method based on a neural network, which comprises the following steps: s1, selecting n earthquake damage influence factors; s2, obtaining n classification results of the building to be tested corresponding to the n earthquake damage influence factors through a classification model by taking the n earthquake damage influence factors as classification bases; s3, determining a sample building similar to the building to be detected based on the n classification results of the building to be detected; and S4, predicting the earthquake damage condition of the building to be detected according to the similar earthquake damage condition of the sample building.

Description

Urban building earthquake damage prediction method based on neural network
Technical Field
The invention relates to a neural network-based urban building earthquake damage prediction method, and belongs to the field of earthquake damage prediction.
Background
Urban population, buildings and infrastructure are in intensive development, once earthquake disasters occur in cities, serious consequences can be caused, and earthquake damage prediction of urban group buildings has important significance for reducing earthquake disaster risks. At present, earthquake damage prediction methods for urban group buildings mostly carry out field investigation or statistics on earthquake damage historical data of the group buildings in the past year, and have the defects that: the town building data cannot be updated in time and a large amount of manpower and material resources are needed.
Therefore, an efficient and accurate automatic urban building earthquake damage prediction method is needed.
The invention patent with application number CN201611226153.3, namely a dynamic prediction method of a residential earthquake damage matrix, discloses: firstly, determining earthquake damage factors of western rural residences in a calculation area and the number N of the earthquake damage factors; secondly, determining the ith earthquake damage factor d meeting the jth classification in the rural residential earthquake damage factorsij、ωijAnd the category number T corresponding to the value classification of the ith earthquake damage factor; thirdly, calculating each type of earthquake damage factor; fourthly, calculating a total earthquake damage factor; fifthly, calculating lambda; sixthly, calculating D; seventhly, determining single residences in western rural areas orA village destruction level; eighthly, calculating the damage levels of all western rural single civil houses or villages which need to be calculated, wherein the calculation is already performed without calculation; and ninthly, combining computer software to dynamically give a corresponding earthquake damage matrix. The method is only used for earthquake damage prediction of the residential buildings, cannot be applied to the field of earthquake damage prediction of urban buildings in an expanded mode, and the specific values of the earthquake damage factors and the weighted values in the method still need to be determined manually.
Disclosure of Invention
In order to solve the problems in the prior art, the invention designs a city building earthquake damage prediction method based on a neural network, which utilizes an unmanned aerial vehicle and a classification model to automatically acquire the building information of a building to be detected (the building information is embodied as a classification result in the invention), reduces the building information acquisition cost and can update the building information in time. And based on the classification result, determining similar sample buildings, predicting the earthquake damage conditions of the buildings to be detected according to the earthquake damage conditions of the similar sample buildings, and rapidly and efficiently predicting the earthquake damage conditions of a large number of buildings, so that workers are helped to macroscopically control the earthquake damage conditions of the buildings in a certain area, the consumption of manpower and material resources is low, and the earthquake-proof disaster-reduction planning of the area is facilitated to be worked out.
In order to achieve the purpose, the invention adopts the following technical scheme:
a city building earthquake damage prediction method based on a neural network comprises the following steps:
s1, selecting n earthquake damage influence factors;
s2, obtaining n classification results corresponding to the building to be detected and the n earthquake damage influence factors through a classification model by taking the n earthquake damage influence factors as classification basis;
s3, determining a sample building similar to the building to be detected based on the n classification results of the building to be detected;
and S4, predicting the earthquake damage condition of the building to be detected according to the similar earthquake damage condition of the sample building.
Further, the step S2 is specifically:
acquiring an image to be processed, wherein the image to be processed comprises a building to be detected;
respectively taking n earthquake damage influence factors as classification bases, and constructing and training n classification models; and respectively inputting the images to be processed into n classification models to obtain n classification results of the building to be detected.
Further, the step S3 is specifically:
acquiring a plurality of sample data, wherein each sample data comprises the earthquake damage condition of a sample building and n classification results of the sample building;
respectively calculating the similarity between the building to be detected and the sample building according to the n classification results of the building to be detected and the n classification results of the sample building;
and determining a sample building similar to the building to be detected according to the similarity.
Further, the similarity between the building to be measured and the sample building is calculated and expressed by a formula as follows:
Figure BDA0003525636720000021
in the formula, d (X, Y) is a hamming distance, and X represents a building to be detected; y represents a sample building; x is the number ofiRepresenting a classification result corresponding to the ith earthquake damage influence factor of the building to be detected; y isiRepresenting a classification result corresponding to the ith earthquake damage influence factor of the sample building; w is ai(i ═ 1,2,3, …, n) represents the weight of each impact factor, and represents the importance of each classification result.
Further, the weight of each earthquake damage influence factor is determined by an entropy method.
Further, the step S4 is specifically:
and determining the earthquake damage grade of the building to be detected according to the earthquake damage index of the building to be detected.
And further, correcting the earthquake damage indexes of the similar sample buildings, and taking the corrected earthquake damage indexes as the earthquake damage indexes of the buildings to be detected.
Further, the n earthquake damage influence factors include: site category, construction year, current status quality, height, application and wall material.
Compared with the prior art, the invention has the following characteristics and beneficial effects:
1. the building information of the building to be detected is automatically acquired by the unmanned aerial vehicle and the classification model (the building information is embodied as a classification result in the invention), the building information acquisition cost is reduced, and the building information can be updated in time.
2. The method determines similar sample buildings based on the classification result, predicts the earthquake damage condition of the building to be detected according to the earthquake damage condition of the similar sample buildings, can quickly and efficiently predict the earthquake damage condition of a large number of buildings, thereby helping workers to macroscopically control the building earthquake damage condition of a certain area, having low consumption of manpower and material resources and being beneficial to compiling earthquake-proof disaster-reduction planning of the area.
3. The similarity between the sample building and the building to be measured is calculated by utilizing the classification result and the weighted Hamming distance formula, the common point between the sample building and the building to be measured is fully measured, the existing earthquake damage condition of the sample building is transferred to the building to be measured, the required calculated amount is small, and the prediction precision is high.
4. The method determines the weight of each classification result by using an entropy method, eliminates subjectivity when determining the importance of each earthquake damage influence factor, and enables the obtained similarity to be more objective and more consistent with the actual situation.
5. The method and the device take the corrected earthquake damage index as the earthquake damage index of the building to be detected to judge the earthquake damage grade of the building to be detected, further improve the prediction precision and are further suitable for the condition that the data volume of the sample building is small.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 to 4 are schematic diagrams of images to be processed.
Detailed Description
The present invention will be described in more detail with reference to examples.
Example one
As shown in fig. 1, a city building earthquake damage prediction method based on a neural network includes the following steps:
shooting a building to be detected by using an unmanned aerial vehicle to obtain an image to be processed (as shown in figures 2 to 4);
and selecting n earthquake damage influence factors according to the earthquake damage history of the urban building. In this embodiment, the earthquake damage influence factor is selected: site category, construction year, current situation quality, height, application and wall material.
And correspondingly constructing n classification models according to the selected n earthquake damage influence factors, wherein each classification model structure in the embodiment adopts a neural network YOLOv-3. And respectively training the n classification models by taking the n earthquake damage influence factors as classification bases. And finally, respectively inputting the images to be processed into the n trained classification models to obtain n classification results. In this embodiment, the factors of the impact of earthquake damage and the corresponding classification results are shown in the following table:
Figure BDA0003525636720000041
Figure BDA0003525636720000051
the earthquake damage conditions of a plurality of sample buildings under various earthquake intensity levels (in the embodiment, earthquake damage indexes under various earthquake intensity levels) and n classification results of the sample buildings are obtained as a sample data set.
And respectively calculating the similarity between the building to be measured and each sample building by using a weighted Hamming distance formula. The weighted hamming distance formula is as follows:
Figure BDA0003525636720000052
in the formula, d (X, Y) represents a Hamming distance value, and X represents a building to be measured; y represents a sample building; x is the number ofiI-th earthquake damage influence factor correspondence representing building to be testedThe classification result of (2); y isiA classification result representing an ith influence factor of the sample building; w is ai(i ═ 1,2,3, …, n) represents the weight of each impact factor.
The minimum hamming distance, the higher the similarity. And determining the sample building with the minimum Hamming distance value as a sample building similar to the building to be detected. And according to the consistency of the earthquake damage conditions of the building and the earthquake damage, the earthquake damage index of the building to be tested under each earthquake intensity is the earthquake damage index of the sample building under each earthquake intensity.
And determining the earthquake damage grade of the building to be detected according to the earthquake damage index of the building to be detected.
The beneficial effect of this embodiment lies in:
1. the building information of the building to be detected is automatically acquired by the unmanned aerial vehicle and the classification model (the building information is embodied as a classification result in the invention), the building information acquisition cost is reduced, and the building information can be updated in time.
2. Based on the classification result, the similar sample buildings are determined, the earthquake damage condition of the building to be detected is predicted according to the earthquake damage condition of the similar sample buildings, and the earthquake damage condition of a large number of buildings can be predicted quickly and efficiently, so that workers are helped to macroscopically control the earthquake damage condition of the building in a certain area, the consumption of manpower and material resources is low, and the earthquake-proof disaster-reduction planning of the area is facilitated to be worked out.
3. The similarity between the sample building and the building to be measured is calculated by utilizing the classification result and the weighted Hamming distance formula, common points between the sample building and the building to be measured are fully measured, the existing earthquake damage condition of the sample building is transferred to the building to be measured, the required calculation amount is small, and the prediction precision is high.
Example two
In the present embodiment, the weight of each classification result is determined by the entropy method
The sample dataset contains 5 sample buildings. Constructing judgment matrixes of 6 earthquake damage influence factors, and carrying out linear scale transformation standardization processing on the judgment matrixes to obtain a standardized matrix Y (Y ═ Yij)5*6
Wherein the content of the first and second substances,
Figure BDA0003525636720000061
xijrepresenting a classification result corresponding to the jth earthquake damage influence factor of the ith sample building; max xijRepresenting the maximum value of the i x j classification results;
normalizing the normalized matrix to obtain
Figure BDA0003525636720000062
Calculating the entropy of the jth earthquake damage influence factor
Figure BDA0003525636720000063
k＝(ln5)-1
Weighting each earthquake damage influence factor by using an entropy method to obtain a weight vector beta of the earthquake damage influence factorj
Figure BDA0003525636720000071
hj＝1-ej 1≤j≤6
The respective factors of the seismic influence are weighted as follows
βj＝(0.07，0.03，0.06，0.06，0.5，0.8)
The method has the advantages that the weight of each classification result is determined by using an entropy method, subjectivity in determining the importance of each earthquake damage influence factor is eliminated, and the obtained similarity is more objective and more consistent with the actual situation.
EXAMPLE III
The earthquake damage indexes of the similar sample buildings under various earthquake intensity degrees are the earthquake damage indexes of the building to be tested under the various earthquake intensity degrees. The earthquake damage indexes suitable for buildings with different structural types are different, for example, the earthquake damage index of reinforced concrete is elongation, and the earthquake damage index of a brick-concrete structure is the degree of resisting earthquake action of the brick-concrete structure. In this embodiment, if the structure type of the building to be tested is reinforced concrete, the earthquake damage index is taken as the structure elongation rate μ. And (3) the structural elongation mu of the similar sample building under a certain earthquake intensity is 1.5, and the earthquake damage grade is obtained to be slight damage according to the corresponding relation between the earthquake damage index and the earthquake damage grade, so that the earthquake damage prediction of the building to be detected is completed. The correspondence between the earthquake damage index and the earthquake damage level under a certain earthquake intensity is shown in the following table.
Figure BDA0003525636720000072
The results of the earthquake damage prediction of all buildings in a certain area by using the prediction method of the invention are shown in the table below, and the results comprise the percentage of buildings with different earthquake damage grades to all buildings in the area under different earthquake intensity.
6 degree 7 degree 8 degree 9 degree
Is substantially intact 90.16％ 73.88％ 12.72％ 8.15％
Slight damage 4.81％ 9.65％ 35.74％ 11.49％
Moderate destruction 0.97％ 10.07％ 25.95％ 22.49％
Severe damage 1.37％ 1.71％ 15.40％ 31.56％
Destroy it 2.69％ 4.68％ 10.19％ 26.30％
Example four
And correcting the earthquake damage index of the similar sample building according to the correction coefficient of the earthquake damage influence factor. In this embodiment, the building height correction coefficient is multiplied by the earthquake damage index of the similar sample building to obtain the corrected earthquake damage index. And taking the corrected earthquake damage index as the earthquake damage index of the building to be detected.
The method has the advantages that the earthquake damage grade of the building to be detected is judged by taking the corrected earthquake damage index as the earthquake damage index of the building to be detected, prediction precision is further improved, and the method is further suitable for the condition that the data volume of the sample building is small.
It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Claims (8)

1. A city building earthquake damage prediction method based on a neural network is characterized by comprising the following steps:
s1, selecting n earthquake damage influence factors;
s2, obtaining n classification results of the building to be tested corresponding to the n earthquake damage influence factors through a classification model by taking the n earthquake damage influence factors as classification bases;
s3, determining a sample building similar to the building to be detected based on the n classification results of the building to be detected;
and S4, predicting the earthquake damage condition of the building to be detected according to the similar earthquake damage condition of the sample building.
2. The urban building earthquake damage prediction method based on the neural network as claimed in claim 1, wherein the step S2 specifically comprises:
acquiring an image to be processed, wherein the image to be processed comprises a building to be detected;
respectively taking n earthquake damage influence factors as classification bases, and constructing and training n classification models; and respectively inputting the images to be processed into n classification models to obtain n classification results of the building to be detected.
3. The urban building earthquake damage prediction method based on the neural network as claimed in claim 1, wherein the step S3 specifically comprises:
acquiring a plurality of sample data, wherein each sample data comprises the earthquake damage condition of a sample building and n classification results of the sample building;
respectively calculating the similarity between the building to be detected and the sample building according to the n classification results of the building to be detected and the n classification results of the sample building;
and determining a sample building similar to the building to be detected according to the similarity.
4. The urban building earthquake damage prediction method based on the neural network as claimed in claim 3, wherein the similarity between the building to be tested and the sample building is calculated and expressed by a formula:
Figure FDA0003525636710000011
in the formula, d (X, Y) is a Hamming distance, and X represents a building to be detected; y represents a sample building; x is the number ofiRepresenting a classification result corresponding to the ith earthquake damage influence factor of the building to be detected; y isiRepresenting a classification result corresponding to the ith earthquake damage influence factor of the sample building; w is ai(i ═ 1,2,3, …, n) represents the weight of each impact factor, and represents the importance of each classification result.
5. The method as claimed in claim 4, wherein the weight of each earthquake damage influencing factor is determined by entropy method.
6. The urban building earthquake damage prediction method based on the neural network as claimed in claim 1, wherein the step S4 specifically comprises:
and determining the earthquake damage grade of the building to be detected according to the earthquake damage index of the building to be detected.
7. The urban building earthquake damage prediction method based on the neural network as claimed in claim 6, further comprising: and correcting the similar earthquake damage index of the sample building, and taking the corrected earthquake damage index as the earthquake damage index of the building to be detected.
8. The urban building earthquake damage prediction method based on the neural network as claimed in claim 1, wherein the n earthquake damage influence factors comprise: site category, construction year, current status quality, height, application and wall material.
CN202210195922.7A 2022-03-01 2022-03-01 Urban building earthquake damage prediction method based on neural network Pending CN114548585A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210195922.7A CN114548585A (en) 2022-03-01 2022-03-01 Urban building earthquake damage prediction method based on neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210195922.7A CN114548585A (en) 2022-03-01 2022-03-01 Urban building earthquake damage prediction method based on neural network

Publications (1)

Publication Number Publication Date
CN114548585A true CN114548585A (en) 2022-05-27

Family

ID=81662240

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210195922.7A Pending CN114548585A (en) 2022-03-01 2022-03-01 Urban building earthquake damage prediction method based on neural network

Country Status (1)

Country Link
CN (1) CN114548585A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117972437A (en) * 2024-03-29 2024-05-03 四川省建筑设计研究院有限公司 Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117972437A (en) * 2024-03-29 2024-05-03 四川省建筑设计研究院有限公司 Regional building earthquake damage prediction method and system aiming at complex terrain geological conditions

Similar Documents

Publication Publication Date Title
CN108876027B (en) GIS-based rural residential point centralized residential area site selection and optimization method
CN112200358B (en) Landslide level prediction method, landslide level prediction device, landslide level prediction equipment and storage medium
US10984518B2 (en) Methods and systems for assessing the quality of geospatial data
CN109933901B (en) MCR city expansion simulation method for optimizing service value of ecosystem
CN115017591A (en) Building structure group earthquake-resistant performance evaluation method
US20230140289A1 (en) Traffic accident prediction systems and methods
CN115564114A (en) Short-term prediction method and system for airspace carbon emission based on graph neural network
CN112131731A (en) Urban growth cellular simulation method based on spatial feature vector filtering
CN115271373A (en) Method and system for defining elastic development boundary of urban group
CN112329262A (en) Residential building gas carbon emission prediction method
CN113095127A (en) Building post-earthquake positioning and damage state evaluation method based on satellite images
CN114548585A (en) Urban building earthquake damage prediction method based on neural network
CN111178756B (en) Multiple linear regression fire risk assessment method based on environmental big data
CN115829163B (en) Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river
CN112200355A (en) Landslide prediction method, device, equipment and storage medium
JP7224133B2 (en) Infrastructure equipment inspection support system, infrastructure equipment inspection support method and program
CN115859765B (en) Urban expansion prediction method, device, equipment and storage medium
CN115936264A (en) Single-day engineering quantity calculation method, staged engineering quantity prediction method and prediction device
CN115829209A (en) Environment-friendly intelligent warehouse environment-friendly quality analysis method and device based on carbon path
CN115587694A (en) Data processing method, device and equipment for house rent batch evaluation
CN115907532A (en) Vehicle repair enterprise layout analysis and evaluation method and system
CN115271221A (en) City expansion prediction method, device, medium and equipment
CN106384205B (en) Modeling method and device for collecting operation input duration
CN114863272A (en) Method and system for determining influence strength of urban vegetation on urban comprehensive vitality
CN113689048A (en) Method, system and computer-readable storage medium for predicting refined spatial distribution of future population

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