CN114154680A - Urban ground collapse prediction method and device and electronic equipment - Google Patents

Urban ground collapse prediction method and device and electronic equipment Download PDF

Info

Publication number
CN114154680A
CN114154680A CN202111292044.2A CN202111292044A CN114154680A CN 114154680 A CN114154680 A CN 114154680A CN 202111292044 A CN202111292044 A CN 202111292044A CN 114154680 A CN114154680 A CN 114154680A
Authority
CN
China
Prior art keywords
collapse
data
sub
ground
prediction
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
CN202111292044.2A
Other languages
Chinese (zh)
Inventor
宋维静
蔡茜
王力哲
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.)
China University of Geosciences
Original Assignee
China University of Geosciences
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 China University of Geosciences filed Critical China University of Geosciences
Priority to CN202111292044.2A priority Critical patent/CN114154680A/en
Publication of CN114154680A publication Critical patent/CN114154680A/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
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • General Health & Medical Sciences (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Fuzzy Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Computer Security & Cryptography (AREA)
  • Educational Administration (AREA)
  • Primary Health Care (AREA)
  • Remote Sensing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a method, a device and electronic equipment for predicting urban ground collapse, wherein the method comprises the following steps: acquiring collapse element data of a plurality of collapse sub-areas in a designated area, wherein the collapse element data comprises geological terrain data and human activity data, and determining a data set for model training according to the collapse element data; constructing a full convolution neural network, and training the full convolution neural network by adopting the data set to obtain a ground collapse prediction model; acquiring collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the probability of collapse of the sub-region to be predicted. The technical scheme of the invention can improve the prediction effect of urban ground collapse.

Description

Urban ground collapse prediction method and device and electronic equipment
Technical Field
The invention relates to the technical field of geological disaster prediction, in particular to a method and a device for predicting urban ground subsidence and electronic equipment.
Background
The ground subsidence is a dynamic geological phenomenon that surface rocks and soil bodies are subsided downwards under the action of natural or artificial factors and form a subsidence pit on the ground, the subsidence of the ground can cause the falling of pedestrians or vehicles, and the prediction of the urban ground subsidence is very important for protecting the life and property safety of people.
At present, the existing urban ground collapse prediction method is to obtain geological data of the ground and predict the probability of urban ground collapse according to the geological data, but the method only considers the influence of natural geological factors on urban ground collapse, and the factors influencing urban ground collapse are not considered comprehensively enough, so that the prediction effect is poor.
Disclosure of Invention
The invention solves the problem of how to improve the prediction effect of urban ground collapse.
In order to solve the above problems, the invention provides a method and a device for predicting urban ground collapse, and an electronic device.
In a first aspect, the present invention provides a method for predicting urban ground collapse, including:
acquiring collapse element data of a plurality of collapse sub-areas in a designated area, wherein the collapse element data comprises geological terrain data and human activity data, and determining a data set for model training according to the collapse element data;
constructing a full convolution neural network, and training the full convolution neural network by adopting the data set to obtain a ground collapse prediction model;
acquiring collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the probability of collapse of the sub-region to be predicted.
Optionally, the geological-terrain data comprises at least one of terrain data, soil-quality classification data, and normalized vegetation index, and the human-activity data comprises at least one of land-utilization classification data, subway data, building-height data, and impervious-surface data.
Optionally, before acquiring collapsed factor data of a plurality of collapsed sub-regions in the designated region, the method further includes:
acquiring ground collapse historical data of the designated area, wherein the ground collapse historical data comprises at least one of ground collapse event records, high-resolution remote sensing data, street view data and map historical image data;
and identifying and marking the geographical position and the collapse range of the collapse sub-area in the designated area according to the ground collapse historical data, and determining the collapse sub-area.
Optionally, the determining a data set for model training from the collapsed factor data comprises:
performing mesh division on the designated area to obtain a plurality of grid units, and enabling the grid units in which the collapse sub-areas are located to be collapse grid units;
for any collapsed grid cell, combining the collapsed factor data of the collapsed grid cell and the collapsed factor data of the adjacent grid cell into a collapsed data matrix, the collapsed data matrices corresponding to all the collapsed grid cells forming the data set.
Optionally, the training the full convolutional neural network with the data set comprises:
dividing the data set into a training set and a test set;
training the full convolution neural network by adopting the training set, testing the precision of the full convolution neural network by adopting the testing set, and iteratively training the full convolution neural network until the precision of the full convolution neural network reaches a preset threshold value to obtain the ground collapse prediction model.
Optionally, after outputting the probability of collapse of the sub-region to be predicted, the method further includes:
and performing two-classification processing on the probability by adopting a support vector machine classifier, and determining the ground collapse easiness of the sub-region to be predicted.
Optionally, the method further comprises:
determining the ground collapse vulnerability of each grid cell in the designated area;
and constructing a ground collapse easiness map of the designated area according to the ground collapse easiness of each grid unit.
In a second aspect, the present invention provides an urban ground collapse prediction device, including:
the system comprises an acquisition module, a model training module and a data analysis module, wherein the acquisition module is used for acquiring collapse element data of a plurality of collapse sub-areas in a specified area, the collapse element data comprises geological terrain data and human activity data, and a data set used for model training is determined according to the collapse element data;
the training module is used for constructing a full convolution neural network, training the full convolution neural network by adopting the data set and obtaining a ground collapse prediction model;
and the prediction module is used for acquiring the collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the collapse probability of the sub-region to be predicted.
In a third aspect, the present invention provides an electronic device comprising a memory and a processor;
the memory for storing a computer program;
the processor, when executing the computer program, is configured to implement the urban ground collapse prediction method as described above.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for urban ground collapse prediction as described above.
The urban ground collapse prediction method, the urban ground collapse prediction device and the storage medium have the advantages that: the geological topography data and the human activity data of a plurality of subsidence sub-areas in the designated area are obtained, a data set for model training is generated according to the geological topography data and the human activity data, and the full convolution neural network constructed by adopting the data set for training not only considers the geological topography data, but also considers the influence of human activity on the ground subsidence, fully considers various factors influencing the ground subsidence, and can improve the prediction accuracy of the ground subsidence prediction model obtained by training. By adopting the full convolution neural network, the spatial information in collapse element data of the collapse sub-region can be prevented from being lost, and the prediction effect of the ground collapse is improved. After collapse factor data of the sub-region to be predicted are processed, the collapse factor data are input into a trained ground collapse prediction model, and the probability of collapse of the sub-region to be predicted can be accurately output. According to the technical scheme, various factors influencing ground collapse are fully considered, the full-convolution neural network is trained, collapse easiness is predicted, and the prediction effect of ground collapse is improved.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting urban ground collapse according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a training process of a ground collapse prediction model according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an urban ground collapse prediction device according to another embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
As shown in fig. 1, a method for predicting urban ground collapse according to an embodiment of the present invention includes:
step S110, collapse element data of a plurality of collapse sub-areas in a designated area are obtained, the collapse element data comprise geological terrain data and human activity data, and a data set used for model training is determined according to the collapse element data.
Optionally, the geological-terrain data comprises at least one of terrain data, soil-quality classification data, and normalized vegetation index, and the human-activity data comprises at least one of land-utilization classification data, subway data, building-height data, and impervious-surface data.
Specifically, the collapse element data of the collapse sub-region can be labeled to obtain the collapse element data with the collapse label. The topographic data may include DEM (Digital Elevation Model) data, and the geological topographic data and human activity data may be obtained from remote sensing data, geological data websites and the like, where human activity in a urbanization process is an important influence factor affecting urban ground collapse, and due to loss of image boundary information, illumination change, natural vibration, a camera itself and other reasons, the image may have noise, that is, certain noise may exist in the extracted DEM data and normalized vegetation index data, and the extracted data may be subjected to information filtering by using a wavelet transform method, and the geological topographic data and human activity data are shown in table 1.
TABLE 1 geological topography data and human Activity data description
Figure DEST_PATH_IMAGE001
And step S120, constructing a full convolution neural network, and training the full convolution neural network by adopting the data set to obtain a ground collapse prediction model.
Specifically, the full convolution Neural network fcn (full volumetric Neural networks) is used for ground collapse prediction, and compared with the Convolutional network cnn (full volumetric Neural networks), due to the use of global pooling, partial spatial information is lost, so that the classification effect is poor. As shown in fig. 2, after data is input into the full convolution neural network, a feature map is obtained through feature extraction, and then a collapse susceptibility prediction result of a corresponding sub-region is obtained through classification.
Step S130, acquiring collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the collapse probability of the sub-region to be predicted.
In the embodiment, geological topography data and human activity data of a plurality of subsidence sub-areas in the designated area are obtained, a data set for model training is generated according to the geological topography data and the human activity data, and the full convolution neural network constructed by training is trained by adopting the data set, so that not only is the geological topography data considered, but also the influence of human activity on ground subsidence is considered, various factors influencing ground subsidence are fully considered, and the prediction accuracy of the ground subsidence prediction model obtained by training can be improved. By adopting the full convolution neural network, the spatial information in collapse element data of the collapse sub-region can be prevented from being lost, and the prediction effect of the ground collapse is improved. After collapse factor data of the sub-region to be predicted are processed, the collapse factor data are input into a trained ground collapse prediction model, and the probability of collapse of the sub-region to be predicted can be accurately output. According to the technical scheme, various factors influencing ground collapse are fully considered, the full-convolution neural network is trained, collapse easiness is predicted, and the prediction effect of the ground collapse is improved, namely the prediction accuracy is improved.
Optionally, before acquiring collapsed factor data of a plurality of collapsed sub-regions in the designated region, the method further includes:
acquiring ground collapse historical data of the designated area, wherein the ground collapse historical data comprises at least one of ground collapse event records, high-resolution remote sensing data, street view data and map historical image data;
and identifying and marking the geographical position and the collapse range of the collapse sub-area in the designated area according to the ground collapse historical data, and determining the collapse sub-area.
Specifically, as the ground collapse event records are less, the geographical position and the collapse range of the collapse in the designated area can be identified and labeled by combining high-resolution remote sensing data, street view data and map historical image data, for example, the collapse range can be labeled by the arcGIS, the collapse range is framed and marked with the central longitude and latitude, a shpfile file is generated, and the collapse sub-area is determined in the designated area, so that the accuracy of sample labeling is improved.
Optionally, the determining a data set for model training from the collapsed factor data comprises:
performing mesh division on the designated area to obtain a plurality of grid units, and enabling the grid units in which the collapse sub-areas are located to be collapse grid units;
for any collapsed grid cell, combining the collapsed factor data of the collapsed grid cell and the collapsed factor data of the adjacent grid cell into a collapsed data matrix, the collapsed data matrices corresponding to all the collapsed grid cells forming the data set.
Specifically, a plurality of grid units with the same size can be obtained by meshing the remote sensing image of the designated area, each grid unit corresponds to one sub-area, and the size of the area corresponding to each grid unit is positively correlated with the resolution of the remote sensing image. And enabling the grid unit in which the collapse sub-area is located to be a collapse grid unit, combining collapse element data of the collapse grid unit and collapse element data of grid units adjacent to the collapse grid unit into a collapse data matrix of 3 x n, wherein n is the number of data items in the collapse element data.
In the optional embodiment, the collapse element data of the collapse grid unit and the collapse element data of the adjacent grid unit are combined into the collapse data matrix, the collapse data matrix is adopted to train the full convolution neural network, not only the collapse element data in the single grid unit but also the spatial information elements of quality inspection of the adjacent grid unit are considered, various elements influencing ground collapse are fully considered, and the accuracy of ground collapse prediction is improved.
Optionally, the performing collapse prediction according to the collapse factor data and the ground collapse prediction model comprises: combining collapse factor data of the sub-region to be predicted and collapse factor data of grid units adjacent to the sub-region to be predicted into a collapse data matrix, inputting the collapse data matrix into a ground collapse prediction model, and outputting the collapse probability of the sub-region to be predicted.
Optionally, the training the full convolutional neural network with the data set comprises:
dividing the data set into a training set and a test set;
training the full convolution neural network by adopting the training set, testing the precision of the full convolution neural network by adopting the testing set, and iteratively training the full convolution neural network until the precision of the full convolution neural network reaches a preset threshold value to obtain the ground collapse prediction model.
Specifically, 80% of collapse data matrixes in the data set can be used as a training set, 20% of collapse data matrixes in the data set can be used as a test set, and a trained full-convolution neural network, namely a ground collapse prediction model, can be obtained through adaptive iterative training.
Optionally, the ground collapse prediction model further includes a support vector machine classifier, and after outputting the probability that the sub-region to be predicted collapses, the method further includes:
and performing two-classification processing on the probability by adopting a support vector machine classifier, and determining the ground collapse easiness of the sub-region to be predicted.
Specifically, the strong classification performance of the support vector machine classifier is used, the processing of the collapse prediction result can be used as a two-classification event, the probability value obtained by prediction is subjected to two-classification processing, and the sub-region to be predicted is divided into a ground collapse prone region or a ground collapse non-prone region through comparison with a preset threshold value.
In the optional embodiment, the probability value obtained by predicting the full convolution neural network is subjected to two classification processes, the ground collapse easiness of the sub-region to be predicted is determined, and the intuitiveness of the prediction result can be improved.
Optionally, the method further comprises:
determining the ground collapse vulnerability of each grid cell in the designated area;
and constructing a ground collapse easiness map of the designated area according to the ground collapse easiness of each grid unit.
Specifically, the ground collapse easiness of each sub-area in the designated area is determined, and the ground collapse easiness of all the sub-areas forms a ground collapse easiness map of the designated area, so that the map is convenient to observe, and the intuitiveness of the display of the prediction result is improved.
As shown in fig. 3, another embodiment of the present invention provides an urban ground collapse prediction apparatus, including:
the system comprises an acquisition module, a model training module and a data analysis module, wherein the acquisition module is used for acquiring collapse element data of a plurality of collapse sub-areas in a specified area, the collapse element data comprises geological terrain data and human activity data, and a data set used for model training is determined according to the collapse element data;
the training module is used for constructing a full convolution neural network, training the full convolution neural network by adopting the data set and obtaining a ground collapse prediction model;
and the prediction module is used for acquiring the collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the collapse probability of the sub-region to be predicted.
Another embodiment of the present invention provides an electronic device including a memory and a processor; the memory for storing a computer program; the processor, when executing the computer program, is configured to implement the urban ground collapse prediction method as described above. The electronic device may include a computer, a server, and the like.
Yet another embodiment of the present invention provides a computer readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the urban ground collapse prediction method as described above.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like. In this application, the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention. In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
Although the present disclosure has been described above, the scope of the present disclosure is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present disclosure, and these changes and modifications are intended to be within the scope of the present disclosure.

Claims (10)

1. A method for predicting urban ground collapse is characterized by comprising the following steps:
acquiring collapse element data of a plurality of collapse sub-areas in a designated area, wherein the collapse element data comprises geological terrain data and human activity data, the human activity data comprises at least one of land utilization classification data, subway data, building height data and impervious surface data, and a data set for model training is determined according to the collapse element data;
constructing a full convolution neural network, and training the full convolution neural network by adopting the data set to obtain a ground collapse prediction model;
acquiring collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the probability of collapse of the sub-region to be predicted.
2. The urban ground collapse prediction method according to claim 1, wherein the geological topography data comprises at least one of topographic data, soil texture classification data and normalized vegetation index.
3. The urban ground collapse prediction method according to claim 1, wherein before acquiring collapse factor data of a plurality of collapsed sub-regions in a specified region, further comprising:
acquiring ground collapse historical data of the designated area, wherein the ground collapse historical data comprises at least one of ground collapse event records, high-resolution remote sensing data, street view data and map historical image data;
and identifying and marking the geographical position and the collapse range of the collapse sub-area in the designated area according to the ground collapse historical data, and determining the collapse sub-area.
4. The urban ground collapse prediction method according to claim 1, wherein said determining a data set for model training from the collapse factor data comprises:
performing mesh division on the designated area to obtain a plurality of grid units, and enabling the grid units in which the collapse sub-areas are located to be collapse grid units;
for any collapsed grid cell, combining the collapsed factor data of the collapsed grid cell and the collapsed factor data of the adjacent grid cell into a collapsed data matrix, the collapsed data matrices corresponding to all the collapsed grid cells forming the data set.
5. The method of urban ground collapse prediction according to claim 4, wherein said training said full convolution neural network with said data set comprises:
dividing the data set into a training set and a test set;
training the full convolution neural network by adopting the training set, testing the precision of the full convolution neural network by adopting the testing set, and iteratively training the full convolution neural network until the precision of the full convolution neural network reaches a preset threshold value to obtain the ground collapse prediction model.
6. The urban ground collapse prediction method according to any one of claims 1 to 5, wherein after outputting the probability of collapse of the sub-region to be predicted, the method further comprises:
and performing two-classification processing on the probability by adopting a support vector machine classifier, and determining the ground collapse easiness of the sub-region to be predicted.
7. The urban ground collapse prediction method according to claim 6, further comprising:
determining the ground collapse vulnerability of each grid cell in the designated area;
and constructing a ground collapse easiness map of the designated area according to the ground collapse easiness of each grid unit.
8. An urban ground collapse prediction device, comprising:
the system comprises an acquisition module, a model training module and a control module, wherein the acquisition module is used for acquiring collapse element data of a plurality of collapse sub-areas in a designated area, the collapse element data comprises geological terrain data and human activity data, the human activity data comprises at least one of land utilization classification data, subway data, building height data and impervious surface data, and a data set for model training is determined according to the collapse element data;
the training module is used for constructing a full convolution neural network, training the full convolution neural network by adopting the data set and obtaining a ground collapse prediction model;
and the prediction module is used for acquiring the collapse factor data of the sub-region to be predicted in the designated region, performing collapse prediction according to the collapse factor data and the ground collapse prediction model, and outputting the collapse probability of the sub-region to be predicted.
9. An electronic device comprising a memory and a processor;
the memory for storing a computer program;
the processor, when executing the computer program, for implementing the urban ground collapse prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the urban ground collapse prediction method according to any one of claims 1 to 7.
CN202111292044.2A 2021-11-03 2021-11-03 Urban ground collapse prediction method and device and electronic equipment Pending CN114154680A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111292044.2A CN114154680A (en) 2021-11-03 2021-11-03 Urban ground collapse prediction method and device and electronic equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111292044.2A CN114154680A (en) 2021-11-03 2021-11-03 Urban ground collapse prediction method and device and electronic equipment

Publications (1)

Publication Number Publication Date
CN114154680A true CN114154680A (en) 2022-03-08

Family

ID=80458694

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111292044.2A Pending CN114154680A (en) 2021-11-03 2021-11-03 Urban ground collapse prediction method and device and electronic equipment

Country Status (1)

Country Link
CN (1) CN114154680A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081706A (en) * 2022-06-16 2022-09-20 中国安能集团第三工程局有限公司 Loess collapse prediction method and device based on bidirectional LSTM network

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115081706A (en) * 2022-06-16 2022-09-20 中国安能集团第三工程局有限公司 Loess collapse prediction method and device based on bidirectional LSTM network

Similar Documents

Publication Publication Date Title
CN105893972B (en) Automatic monitoring method for illegal building based on image and implementation system thereof
Pham et al. Urban growth and change analysis using remote sensing and spatial metrics from 1975 to 2003 for Hanoi, Vietnam
JP2019533180A (en) Change detection based map interface update system
Abd et al. Maximum likelihood for land-use/land-cover mapping and change detection using Landsat satellite images: A case study “South of Johor”
CN110956412B (en) Flood dynamic assessment method, device, medium and equipment based on real-scene model
CN112669323B (en) Image processing method and related equipment
CN116343103B (en) Natural resource supervision method based on three-dimensional GIS scene and video fusion
Byrne et al. Estimating badger social-group abundance in the Republic of Ireland using cross-validated species distribution modelling
Ehrlich et al. Quantifying the building stock from optical high-resolution satellite imagery for assessing disaster risk
CN116051777B (en) Super high-rise building extraction method, apparatus and readable storage medium
CN113254559A (en) Equipment site selection method based on geographic information system
CN112861732A (en) Method, system and device for monitoring land in ecological environment fragile area
CN114154680A (en) Urban ground collapse prediction method and device and electronic equipment
CN114220017A (en) Remote sensing data scale self-adaptive adjusting method and device, storage medium and equipment
Gillespie et al. Predictive modelling for archaeological sites: Ashokan edicts from the Indian subcontinent
CN113688172A (en) Landslide susceptibility evaluation model training method, landslide susceptibility evaluation device and medium
CN112990024A (en) Method for monitoring urban raise dust
CN112184900B (en) Method, device and storage medium for determining elevation data
CN110132966B (en) Method and system for evaluating risk of spatial position of soil pollution source
Märker et al. Explorative spatial analysis of Neandertal sites using terrain analysis and stochastic environmental modelling
CN111652932A (en) Vector verification method, device and equipment for remote sensing image geographical positioning
CN116189000B (en) Land parcel analysis method and apparatus
CN117195016B (en) Sewage treatment mode determining method and device, computer equipment and storage medium
Rienow et al. The future of central european cities–Optimization of a cellular automaton for the spatially explicit prediction of urban sprawl
CN112883840B (en) Power transmission line extraction method based on key point detection

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