CN115240076A - Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition - Google Patents
Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition Download PDFInfo
- Publication number
- CN115240076A CN115240076A CN202210218939.XA CN202210218939A CN115240076A CN 115240076 A CN115240076 A CN 115240076A CN 202210218939 A CN202210218939 A CN 202210218939A CN 115240076 A CN115240076 A CN 115240076A
- Authority
- CN
- China
- Prior art keywords
- elevation
- remote sensing
- satellite remote
- data
- sensing image
- 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
- 238000012502 risk assessment Methods 0.000 title claims abstract description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000009825 accumulation Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000013136 deep learning model Methods 0.000 claims abstract description 8
- 238000013075 data extraction Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011160 research Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 6
- 206010013647 Drowning Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000009193 crawling Effects 0.000 description 2
- 230000009849 deactivation Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000556 factor analysis Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
Abstract
The invention provides an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification, which is characterized by comprising the following steps: urban ponding point acquisition module: acquiring urban ponding point data through a social media platform, acquiring longitude and latitude information of the ponding point by utilizing ArcGIS software, and acquiring corresponding satellite remote sensing images and elevation data from a world network and a geospatial data cloud platform respectively according to the longitude and latitude information; the satellite remote sensing image feature extraction module: inputting the satellite remote sensing image into a deep learning model, identifying the target class in the satellite remote sensing image, and taking the sum of the pixel points of each identified target as a characteristic value of urban inland inundation influence factors; elevation data extraction module: downloading through a geographic space data cloud platform to obtain elevation tif data with a water accumulation point as a center, and extracting elevation values and relative elevation values of the water accumulation point, wherein the elevation values comprise six characteristics of water bodies, courses, greenbelts, elevations and the like; the prediction analysis module based on the XGboost model comprises: integrating the obtained characteristic values and the obtained elevation values into a data set, training the XGboost model, and analyzing influence factors of urban waterlogging risks through each index weight.
Description
Technical Field
The invention relates to an urban waterlogging disaster influence factor analysis technology, in particular to a method for urban waterlogging disaster risk research and influence factor identification and analysis.
Background
Urban inland inundation disasters have great influence on cities, and bring immeasurable loss to the cities: waterlogging and ponding in urban areas, paralysis of traffic, threat of house property, pollution of water resources, rapid spread of diseases, damage of building facilities and even possible casualties; torrential flood occurs in remote urban areas, and drainage is not smooth; besides waterlogging and ponding in urban areas, peripheral farmlands and villages can be flooded, crops are seriously reduced in production, life and property safety of cultivated livestock and people are threatened, and serious economic loss is caused.
A method for researching risk of inland inundation disasters in urban scales generally adopts historical disaster situation data, scenario analysis, remote sensing and GIS, an index system and the like to research the risk. The evaluation process based on the historical disaster data is simple, but the dependency on the historical data is strong, so that new disaster data needs to be continuously introduced to ensure the reliability of the research result. The risk evaluation method based on the scenario analysis improves the spatial accuracy of the risk evaluation result, but has higher requirements on the time scale, the accuracy and the simulation modeling of data. The risk evaluation method based on the combination of the remote sensing technology and the GIS also has the problems of larger research scale, low drawing precision and the like. The evaluation method based on the index system is a method commonly adopted in urban flood risk evaluation, and a regional risk evaluation model is constructed by utilizing a flood disaster risk index.
Disclosure of Invention
The invention provides an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification, which is used for solving the incomplete condition of an urban waterlogging disaster risk research method.
An urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification comprises the following steps:
urban water accumulation point acquisition module: acquiring urban ponding point data through a social media platform, acquiring longitude and latitude information of the ponding point by utilizing ArcGIS software, and acquiring corresponding satellite remote sensing images and elevation data from a world network and a geospatial data cloud platform respectively according to the longitude and latitude information;
the satellite remote sensing image feature extraction module: inputting the satellite remote sensing image into a deep learning model, identifying the target class in the satellite remote sensing image, and taking the sum of the pixel points of each identified target as a characteristic value of urban inland inundation influence factors;
elevation data extraction module: downloading through a geographic space data cloud platform to obtain elevation tif data with a water accumulation point as a center, and extracting an elevation value and a relative elevation value of the water accumulation point;
the prediction analysis module based on the XGboost model comprises: and integrating the acquired characteristic values and the elevation values into a data set, training the XGboost model, and analyzing influence factors of urban waterlogging risks through each index weight.
As an embodiment of the present invention, the urban water spot collection module includes:
a water accumulation point acquisition unit: the method comprises the steps of crawling a webpage containing a keyword 'drowning/flooding' or 'waterlogging/ponding' in a news report of 2017-2018, carrying out data cleaning and deleting repeated information irrelevant to the flood disaster on the obtained text, and then preprocessing the text by Chinese word segmentation and word removal deactivation to obtain 7 thousands of pieces of information. In order to geographically locate urban inland inundation sites from text contents, a nationwide community directory of part of China's cities is downloaded, including community names, geographic locations and other information from famous residential websites https:// www. Terms about community, road, and direction are extracted from the posts. Community directories of partial cities in china are then used to match these terms so that the geographical location of the reported water spot can be determined. Guiding the geographic positions into ArcGIS software to obtain corresponding longitude and latitude coordinates, so as to conveniently obtain satellite images of the water accumulation points;
the satellite remote sensing image acquisition unit: by using geocoding and reverse geocoding of a national geographic information public service platform sky map, a satellite remote sensing image with the resolution of 1024 multiplied by 1024 is intercepted on the sky map by taking a water accumulation point coordinate as a central area.
As an embodiment of the present invention, the satellite remote sensing image feature extraction module includes:
labeling data units: labeling target classes such as water bodies, roads and greenbelts in the satellite remote sensing images by using a labelme tool, and labeling 200 satellite remote sensing images and 4 target classes in total by using the labeled data as a training set of a deep learning model;
deep learning training unit: in a Pythrch framework, a semantic segmentation U-net model is trained by using a training set, verification and optimization are carried out through a test set, and finally the average pixel precision (MPA) reaches about 81.89%.
As an embodiment of the present invention, it is an elevation data extraction module that includes:
elevation value extraction unit: extracting elevation data of a central point of an elevation tif file matrix through a program to obtain an elevation value of a water accumulation point;
relative elevation value extraction unit: because of the difference of the overall elevations among different cities, in order to make the study of the elevation data among the cities meaningful, the average elevation of the elevation of four vertexes subtracted from the elevation of the center point of the elevation tif image is used as the relative elevation of the sample point.
As an embodiment of the present invention, the XGBoost model-based prediction analysis module includes:
the XGboost algorithm unit: providing a foundation for constructing a training model through an XGboost algorithm of a preset machine learning system, verifying and optimizing the XGboost model by using a test set, evaluating the performance of the XGboost model, and finally obtaining the weight of urban inland inundation risk factors;
a model optimization unit: and determining the optimal parameters of the model by using a grid parameter adjusting method, finally verifying the model by using a test set, and finally verifying that the average value of the AUC reaches about 0.88 through 5-fold cross verification.
The beneficial effects of the invention are as follows: and (3) carrying out urban waterlogging disaster risk research by applying satellite remote sensing data and deep learning. An algorithm model based on deep learning is constructed, features of elements such as water bodies, roads and greenbelts in the satellite remote sensing image are extracted, and finally main image factors of urban waterlogging disaster risks are analyzed through the XGboost model, so that more research methods for urban waterlogging risk factors are provided, and the research efficiency is improved.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart of an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification according to an embodiment of the present invention;
fig. 2 is an effect diagram of satellite remote sensing image feature extraction in an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification in the embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it should be understood that they are presented herein only to illustrate and explain the present invention and not to limit the present invention.
The embodiment of the invention provides an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification, and the overall framework is shown in figure 1:
according to the method, reports about urban inland inundation in 2017-2018 are collected through a social media platform, and satellite remote sensing images and elevations corresponding to the ponding points are obtained after the ponding points are located. And then, a training data set is made to train a semantic segmentation model and perform performance evaluation on the model, the trained weights are used for predicting the obtained satellite remote sensing images of the positive sample and the negative sample, and each predicted image can obtain a corresponding label image (as shown in figure 2). And accumulating the number of each type of pixel points on the label graph through a program to obtain the sum of the number of each type of pixel points, namely the area of each type. And secondly, integrating the area of each category in each picture, the elevation value and the relative elevation value of the corresponding picture and the mark (1 or 0) of the corresponding positive and negative sample, and storing the integrated values in a Comma Separated Value (CSV) file format to form a final data table. Finally, the data sheet is sent into an extreme gradient promotion model to analyze urban inland inundation disaster factors and evaluate the performance of the model
The embodiment of the invention provides an urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification, which comprises the following steps:
urban water accumulation point acquisition module: acquiring urban ponding point data through a social media platform, acquiring longitude and latitude information of the ponding point by utilizing ArcGIS software, and acquiring corresponding satellite remote sensing images and elevation data from a world network and a geospatial data cloud platform respectively according to the longitude and latitude information;
the satellite remote sensing image feature extraction module: inputting the satellite remote sensing image into a deep learning model, identifying the target class in the satellite remote sensing image, and taking the sum of the pixel points of each identified target as a characteristic value of urban inland inundation influence factors;
elevation data extraction module: downloading through a geographic space data cloud platform to obtain elevation tif data with a water accumulation point as a center, and extracting an elevation value and a relative elevation value of the water accumulation point;
the prediction analysis module based on the XGboost model comprises: and integrating the acquired characteristic values and the elevation values into a data set, training the XGboost model, and analyzing influence factors of urban waterlogging risks through each index weight.
The working principle of the technical scheme is as follows: dividing the obtained urban inland inundation satellite image map into a training set and a testing set, and constructing a training sample library; training sample data of the training sample library through a U-Net network under a Pythrch frame to generate a semantic segmentation model; and integrating the result obtained after the semantic segmentation model is trained with the elevation data of the submerged point, importing the result into the XGboost model, and obtaining the main influence factor information of the urban inland inundation disaster.
The beneficial effects of the above technical scheme are: and carrying out flood disaster influence factor analysis by applying satellite image data related to urban inland inundation disasters and deep learning. And (3) constructing an algorithm model based on deep learning, and extracting features of elements such as water bodies, roads and the like in the satellite images to finally obtain main influence factors of urban inland inundation. The method greatly improves the overall recognition rate (81.89% in practical implementation) for recognizing the targets such as water bodies, roads, greenbelts and the like in the satellite images, and has more accurate recognition capability compared with the prior art. The method shows that the satellite image picture can be better identified by the deep learning model used by the method, the targets such as water bodies, roads and the like in the satellite image picture can be effectively and automatically extracted, and the main influence factors of urban flood disasters can be accurately analyzed.
In one embodiment, the municipal ponding point collection module comprises:
a water accumulation point acquisition unit: through crawling the information of keywords 'drowning/flooding' or 'waterlogging/ponding' contained in the news reports of 2017-2018, data cleaning and deletion of repeated information irrelevant to flood disasters are carried out on the obtained text, then preprocessing is carried out on the text through Chinese word segmentation and word removal deactivation, 7 thousands of pieces of information are obtained, and 6407 ponding points are obtained. In order to geographically locate urban inland inundation sites from text contents, a nationwide community directory of part of cities in China is downloaded, and information including community names, geographic positions and the like is obtained from well-known residential websites https:// www. Terms about community, road, and direction are extracted from the posts. Community directories of partial cities in china are then used to match these terms so that the geographic location of the water spot for these reports can be determined. Guiding the geographic positions into ArcGIS software to obtain corresponding longitude and latitude coordinates, so as to conveniently obtain satellite images of the water accumulation points;
the satellite remote sensing image acquisition unit: by applying geographic coding and reverse geographic coding of a national geographic information public service platform sky map, a satellite remote sensing image with the resolution of 1024 x 1024 is intercepted on the sky map by taking a ponding point coordinate as a central area.
In one embodiment, the satellite remote sensing image feature extraction module comprises:
labeling data units: target classes such as water bodies, roads and greenbelts in the satellite remote sensing images are marked by using a labelme tool, corresponding label names are filled after each class is marked, a json file is generated after each picture is marked and stored, and label information is contained in the json file. Finally, converting the json file into a data set serving as a training set of the deep learning model, and marking 200 satellite remote sensing images including water bodies, roads, greenbelts and other 4 target classes;
deep learning training unit: in a Pythroch frame, a semantic segmentation U-net model is trained by using a training set, verification and optimization are carried out through a test set, and finally the average pixel precision (MPA) reaches about 81.89%.
In one embodiment, the elevation data extraction module comprises:
elevation value extraction unit: extracting elevation data of a central point of an elevation tif file matrix through a program to obtain an elevation value of a water accumulation point;
relative elevation value extraction unit: because of the difference of the overall elevations among different cities, in order to make the study of the elevation data among the cities meaningful, the average elevation of the elevation of four vertexes subtracted from the elevation of the center point of the elevation tif image is used as the relative elevation of the sample point.
In one embodiment, the XGBoost model-based predictive analysis module comprises:
XGboost arithmetic unit: providing a foundation for constructing a training model through an XGboost algorithm of a preset machine learning system, verifying and optimizing the XGboost model by using a test set, evaluating the performance of the XGboost model, and finally obtaining the weight of urban inland inundation risk factors;
a model optimization unit: and determining the optimal parameters of the model by using a grid parameter adjusting method, finally verifying the model by using a test set, and finally verifying that the average value of the AUC reaches about 0.88 through 5-fold cross verification.
Claims (5)
1. An urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification is characterized by comprising the following steps:
urban ponding point acquisition module: acquiring urban ponding point data through a social media platform, acquiring longitude and latitude information of the ponding point by utilizing ArcGIS software, and acquiring corresponding satellite remote sensing images and elevation data from a world network and a geospatial data cloud platform respectively according to the longitude and latitude information;
the satellite remote sensing image feature extraction module: inputting the satellite remote sensing image into a deep learning model, identifying the target class in the satellite remote sensing image, and taking the sum of the pixel numbers of each identified target as a characteristic value of an urban waterlogging influence factor;
elevation data extraction module: downloading through a geographic space data cloud platform to obtain elevation tif data with a water accumulation point as a center, and extracting an elevation value and a relative elevation value of the water accumulation point;
the prediction analysis module based on the XGboost model comprises: and integrating the acquired characteristic values and the elevation values into a data set, training the XGboost model, and analyzing influence factors of urban waterlogging risks through each index weight.
2. The urban waterlogging risk assessment algorithm based on satellite remote sensing image target identification as claimed in claim 1, wherein the urban waterlogging point collection module comprises:
ponding point acquisition unit: collecting information related to urban inland inundation in 2017-2018 through news reports, deleting repeated data, and acquiring longitude and latitude information of a water accumulation point by using ArcGIS software;
the satellite remote sensing image acquisition unit: by using geocoding and reverse geocoding of a national geographic information public service platform sky map, a satellite remote sensing image with the resolution of 1024 multiplied by 1024 is intercepted on the sky map by taking a water accumulation point coordinate as a central area.
3. The urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition as claimed in claim 1, wherein the satellite remote sensing image feature extraction module comprises:
labeling data unit: labeling target classes such as water bodies, roads, greenbelts and the like in the satellite remote sensing images by using a labelme tool, and taking the labeled data as a training set of a deep learning model;
deep learning training unit: based on a Pythrch deep learning framework, a semantic segmentation U-net model is trained by using a training set, and verification and optimization are performed through a test set.
4. The urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition as claimed in claim 1, wherein the elevation data extraction module comprises:
elevation value extraction unit: extracting elevation data of a central point of an elevation tif file matrix through a program to obtain an elevation value of a water accumulation point;
relative elevation value extraction unit: because of the difference of the overall elevations among different cities, in order to make the study of the elevation data among the cities meaningful, the average elevation of the elevation of four vertexes subtracted from the elevation of the center point of the elevation tif image is used as the relative elevation of the sample point.
5. The urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition as claimed in claim 1, wherein the prediction analysis module based on the XGBoost model comprises:
XGboost arithmetic unit: providing a foundation for constructing a training model through a preset XGboost algorithm of a machine learning system;
a model optimization unit: and determining the optimal parameters of the model by using a grid parameter adjusting method, and finally verifying the model by using a test set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218939.XA CN115240076A (en) | 2022-03-08 | 2022-03-08 | Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210218939.XA CN115240076A (en) | 2022-03-08 | 2022-03-08 | Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115240076A true CN115240076A (en) | 2022-10-25 |
Family
ID=83668174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210218939.XA Pending CN115240076A (en) | 2022-03-08 | 2022-03-08 | Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240076A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116484688A (en) * | 2023-04-26 | 2023-07-25 | 中国水利水电科学研究院 | Urban inland inundation numerical value experiment method |
| CN117010208A (en) * | 2023-08-17 | 2023-11-07 | 江苏长三角智慧水务研究院有限公司 | Method, device, equipment and storage medium for determining waterlogging prevention and treatment scheme |
| CN117893906A (en) * | 2024-01-18 | 2024-04-16 | 中国科学院西北生态环境资源研究院 | System and method for realizing automatic production and preparation of key elements of geology |
-
2022
- 2022-03-08 CN CN202210218939.XA patent/CN115240076A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116484688A (en) * | 2023-04-26 | 2023-07-25 | 中国水利水电科学研究院 | Urban inland inundation numerical value experiment method |
| CN116484688B (en) * | 2023-04-26 | 2023-10-13 | 中国水利水电科学研究院 | Urban inland inundation numerical value experiment method |
| US12056427B1 (en) | 2023-04-26 | 2024-08-06 | China Institute Of Water Resources And Hydropower Research | Numerical experimental method for urban waterlogging |
| CN117010208A (en) * | 2023-08-17 | 2023-11-07 | 江苏长三角智慧水务研究院有限公司 | Method, device, equipment and storage medium for determining waterlogging prevention and treatment scheme |
| CN117893906A (en) * | 2024-01-18 | 2024-04-16 | 中国科学院西北生态环境资源研究院 | System and method for realizing automatic production and preparation of key elements of geology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115240076A (en) | Urban waterlogging risk assessment algorithm based on satellite remote sensing image target recognition | |
| CN111932036B (en) | Fine spatio-temporal scale dynamic population prediction method and system based on position big data | |
| CN110346517B (en) | Smart city industrial atmosphere pollution visual early warning method and system | |
| CN112949413A (en) | City landscape element classification and locality measurement method based on street view picture | |
| KR100982447B1 (en) | Landslide occurrence prediction system and predicting method using the same | |
| CN113505842B (en) | Automatic urban building extraction method suitable for large-scale regional remote sensing image | |
| CN117010726B (en) | Intelligent early warning method and system for urban flood control | |
| CN111709646B (en) | Air pollution exposure risk evaluation method and system | |
| CN113505521B (en) | Urban waterlogging rapid forecasting method based on neural network-numerical simulation | |
| CN112070056A (en) | Sensitive land use identification method based on object-oriented and deep learning | |
| CN116343103B (en) | Natural resource supervision method based on three-dimensional GIS scene and video fusion | |
| CN118070619B (en) | Urban waterlogging model sensitive parameter identification optimization method by utilizing machine learning | |
| Zhang et al. | Using street view images to identify road noise barriers with ensemble classification model and geospatial analysis | |
| CN106651004A (en) | Flood forecasting method based on rainfall flood space-time database | |
| CN115471980B (en) | Mud-rock flow disaster early warning method | |
| CN114898089B (en) | Functional area extraction and classification method fusing high-resolution images and POI data | |
| CN113408918B (en) | Multi-temporal remote sensing analysis-based rural garbage downscaling space-time distribution inversion method | |
| CN117649048A (en) | Monitoring method and device for river and lake ecological space key supervision objects | |
| CN116307857A (en) | Built-up area environment evaluation method based on remote sensing image scene understanding | |
| CN115879594A (en) | Urban settlement population distribution trend prediction method based on geographic detector | |
| CN114154680A (en) | Urban ground collapse prediction method and device and electronic equipment | |
| CN117893015B (en) | Risk crowd analysis method and system for dam break accident of tailing pond | |
| CN113610346A (en) | Village development potential evaluation and village classification method and device based on multi-source data | |
| CN117746271B (en) | Intelligent recognition method for high-consequence area of gas transmission pipeline based on unmanned aerial vehicle image | |
| Li et al. | Study on road damage assessment based on RS and GIS |
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 |