[go: up one dir, main page]

CN118608707B - Dynamic construction method of three-dimensional hydrogeologic model - Google Patents

Dynamic construction method of three-dimensional hydrogeologic model Download PDF

Info

Publication number
CN118608707B
CN118608707B CN202410656277.3A CN202410656277A CN118608707B CN 118608707 B CN118608707 B CN 118608707B CN 202410656277 A CN202410656277 A CN 202410656277A CN 118608707 B CN118608707 B CN 118608707B
Authority
CN
China
Prior art keywords
current period
pixel
hyperspectral image
pixel point
wavelength
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.)
Active
Application number
CN202410656277.3A
Other languages
Chinese (zh)
Other versions
CN118608707A (en
Inventor
魏善明
朱恒华
刘春华
王玮
谭肖波
徐秋晓
王传琦
毕栋威
周波
魏海红
张宸恺
张之丽
崔亮亮
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.)
Jinan Zhongan Digital Technology Co ltd
Shandong Geological Survey Institute Mineral Exploration Technology Guidance Center Of Shandong Natural Resources Department
Shandong Geological And Mineral Engineering Survey Institute Shandong Provincial Bureau Of Geology And Mineral Exploration And Development Bayi Hydrogeological Engineering Geological Brigade
Original Assignee
Jinan Zhongan Digital Technology Co ltd
Shandong Geological Survey Institute Mineral Exploration Technology Guidance Center Of Shandong Natural Resources Department
Shandong Geological And Mineral Engineering Survey Institute Shandong Provincial Bureau Of Geology And Mineral Exploration And Development Bayi Hydrogeological Engineering Geological Brigade
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 Jinan Zhongan Digital Technology Co ltd, Shandong Geological Survey Institute Mineral Exploration Technology Guidance Center Of Shandong Natural Resources Department, Shandong Geological And Mineral Engineering Survey Institute Shandong Provincial Bureau Of Geology And Mineral Exploration And Development Bayi Hydrogeological Engineering Geological Brigade filed Critical Jinan Zhongan Digital Technology Co ltd
Priority to CN202410656277.3A priority Critical patent/CN118608707B/en
Publication of CN118608707A publication Critical patent/CN118608707A/en
Application granted granted Critical
Publication of CN118608707B publication Critical patent/CN118608707B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Remote Sensing (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Graphics (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention relates to the technical field of image data processing, in particular to a dynamic construction method of a three-dimensional hydrogeologic model, which comprises the steps of obtaining the possibility that each pixel point in a hyperspectral image in the current period is a boundary point of a different region under each wavelength according to the gray level difference of the pixel point under the same wavelength in the eight neighborhood direction from each pixel point and the influence degree of the outside factors such as weather and the like of each pixel point under each wavelength in the hyperspectral image in the current period; according to the probability that each pixel point in the hyperspectral image in the current period is a boundary point of different areas under all different wavelengths, the probability that each pixel point in the hyperspectral image in the current period is a key area point is obtained, a key area is screened out according to the probability that each pixel point in a suspected key area cluster is a key area point, and a three-dimensional hydrogeological model corresponding to the key area is constructed. The method for constructing the three-dimensional hydrogeologic model has the advantages of accuracy and high efficiency.

Description

Dynamic construction method of three-dimensional hydrogeologic model
Technical Field
The application relates to the technical field of image data processing, in particular to a dynamic construction method of a three-dimensional hydrogeologic model.
Background
The dynamic construction of the three-dimensional hydrogeologic model is affected by seasonal changes, the dynamic effects of the influences caused by human activities and the like, so that the constructed three-dimensional hydrogeologic model can describe and simulate the complexity and the dynamic property of a groundwater system more accurately, real-time monitoring and prediction are required to be carried out on the groundwater system, the model can better reflect the conditions of groundwater flow, water level distribution, water quality change and the like, and the method has important significance for emergency and emergency measure establishment. For the whole research area, according to the characteristics of groundwater level change sensitivity, hydrogeological condition complexity and the like, the degree of obvious change of different areas in a short period is different, so that the key areas with different degrees exist in the whole research area. However, when a three-dimensional hydrogeologic model is constructed, real-time related data is generally acquired for the whole research area, so that the data information amount is overlarge, more time and resources are needed for processing and analyzing, and the model cannot be updated in time, so that the real-time performance and accuracy of the model are affected. Because the traditional K-means clustering algorithm cannot comprehensively consider the data characteristic change (such as the data characteristic change caused by the influence of weather, environment and the like) when measuring the distance between different sample points, the distance measurement between the different sample points is inaccurate, and the accuracy of constructing the three-dimensional hydrogeological model is further influenced.
Disclosure of Invention
The invention provides a dynamic construction method of a three-dimensional hydrogeologic model, which aims to solve the problem that the accuracy of constructing the three-dimensional hydrogeologic model is affected due to inaccurate measurement of the distance between different sample points caused by the fact that the change of data characteristics cannot be comprehensively considered when the distance between different sample points is measured by the traditional K-means clustering algorithm.
The invention relates to a dynamic construction method of a three-dimensional hydrogeologic model, which adopts the following technical scheme:
one embodiment of the invention provides a dynamic construction method of a three-dimensional hydrogeologic model, which comprises the following steps:
Acquiring a plurality of hyperspectral images of the same research area in different periods, wherein each pixel point in the hyperspectral images corresponds to a plurality of gray values under different wavelengths, and the different periods comprise a current period and a reference history period;
according to the difference between gray values of each pixel point in the hyperspectral image of the current period and the reference history period under the same wavelength, obtaining the degree of influence of external factors such as weather and the like on each pixel point in the hyperspectral image of the current period under each wavelength;
According to the gray level difference of each pixel point in the same wavelength along the eight neighborhood direction in the hyperspectral image of the current period and the degree of influence of weather and other external factors on each pixel point at each wavelength, the possibility that each pixel point in the hyperspectral image of the current period is a junction point of different areas at each wavelength is obtained;
According to the possibility that each pixel point in the hyperspectral image in the current period is a junction point of different areas under all different wavelengths, the possibility that each pixel point in the hyperspectral image in the current period is a key area point is obtained;
taking the difference of the possibility that any two pixel points in the hyperspectral image in the current period are taken as key region points as the clustering distance of any two pixel points, and carrying out clustering operation on the hyperspectral image in the current period to obtain a plurality of suspected key region clusters;
And screening out the critical area according to the possibility that the pixel points in the suspected critical area cluster are critical area points, and constructing a three-dimensional hydrogeologic model corresponding to the critical area.
Preferably, the obtaining the degree of influence of external factors such as weather on each pixel point in the hyperspectral image in the current period according to the difference between gray values of each pixel point in the hyperspectral image in the current period and the reference history period at the same wavelength includes the following specific steps:
According to the gray value of each pixel point in the hyperspectral image of the current period and the reference history period under the same wavelength, obtaining the gray difference of each pixel point in the hyperspectral image of the current period under each wavelength;
And obtaining the degree of influence of external factors such as weather and the like on each pixel point in the hyperspectral image in the current period according to the difference between the gray differences of all the pixel points in the hyperspectral image in the current period at each wavelength.
Preferably, the gray level difference of each pixel point in the hyperspectral image in the current period under each wavelength is obtained according to the gray level value of each pixel point in the hyperspectral image in the current period and the reference history period under the same wavelength, and the specific steps include:
and recording the absolute value of the difference value of the gray value of the mth pixel point in the hyperspectral image of the current period and the reference history period at the ith wavelength as the gray difference of the mth pixel point in the hyperspectral image of the current period at the ith wavelength.
Preferably, the degree of influence of weather and other external factors on each pixel point in the hyperspectral image in the current period is obtained according to the difference between gray differences of all pixel points in the hyperspectral image in the current period at each wavelength, and the specific formula is as follows:
Wherein Q i,m represents the degree of influence of external factors such as weather on the mth pixel point in the hyperspectral image in the current period under the ith wavelength, and delta Q i,m represents the gray level difference of the mth pixel point in the hyperspectral image in the current period under the ith wavelength; the method comprises the steps of representing the average value of gray differences of all pixel points in a hyperspectral image in the current period at the ith wavelength, wherein norm () is a normalization function, M represents the number of pixel points in the hyperspectral image in the current period, and I is an absolute value function.
Preferably, according to the gray scale difference of each pixel point at the same wavelength along the eight neighborhood direction in the hyperspectral image of the current period and the degree of influence of weather and other external factors on each pixel point at each wavelength, the method obtains the possibility that each pixel point in the hyperspectral image of the current period is a boundary point of different regions at each wavelength, and comprises the following specific steps:
Constructing a local neighborhood of each pixel point in the hyperspectral image in the current period;
According to the gray level difference of each pixel point in the same wavelength along the eight neighborhood direction from each pixel point in the local neighborhood of each pixel point in the hyperspectral image in the current period and the degree of influence of weather and other external factors on each pixel point in each wavelength, the possibility that each pixel point in the hyperspectral image in the current period is a boundary point of different areas in each wavelength is obtained.
Preferably, the constructing a local neighborhood of each pixel in the hyperspectral image in the current period includes the following specific steps:
In the hyperspectral image in the current period, each pixel point is taken as a circle center, the radius r is taken as a circle, and the circle is recorded as a local neighborhood of each pixel point, wherein r is a preset radius.
Preferably, in the local neighborhood of each pixel point in the hyperspectral image in the current period, the gray scale difference of the pixel point in the same wavelength along the eight neighborhood direction from each pixel point and the degree of influence of weather and other external factors on each pixel point in each wavelength are obtained, so as to obtain the possibility that each pixel point in the hyperspectral image in the current period is a boundary point of different regions in each wavelength, and the specific formula is as follows:
Wherein W i,j represents the possibility that the jth pixel point in the hyperspectral image of the current period is a junction point of different areas at the ith wavelength, Q i,m represents the degree of influence of external factors such as weather and the like on the mth pixel point in the hyperspectral image of the current period, deltaq i,j,l,b represents the gray scale difference of the jth pixel point in the eighth neighborhood direction from the jth pixel point in the hyperspectral image of the current period at the ith wavelength, deltaq i,j,l,max represents the maximum value in the gray scale difference of all the pixel points in the ith wavelength in the eighth neighborhood direction from the jth pixel point in the local neighborhood of the jth pixel point in the hyperspectral image of the current period from the jth pixel point in the eighth neighborhood direction; Standard deviations of all Δq i,j,l,max-Δqi,j,l,b when b falls within interval [1, b i,j,l ]; all when l is within interval [1,8] Standard deviation of (2).
Preferably, the probability that each pixel point in the hyperspectral image according to the current period is a junction point of different areas under all different wavelengths, the probability that each pixel point in the hyperspectral image in the current period is a key region point is obtained, and the specific formula is as follows:
Wherein E j represents the possibility that the jth pixel point in the hyperspectral image in the current period is a key area point, I represents the number of wavelengths corresponding to the jth pixel point in the hyperspectral image in the current period, and W i,j represents the possibility that the jth pixel point in the hyperspectral image in the current period is a junction point of different areas under the ith wavelength.
Preferably, the specific obtaining step of the clustering distance of any two pixel points is as follows:
And recording the absolute value of the difference value of the possibility that any two pixel points in the hyperspectral image in the current period are key region points as the clustering distance of the any two pixel points.
Preferably, the screening the critical area according to the possibility that the pixel point in the suspected critical area cluster is a critical area point includes the following specific steps:
calculating the average value of the possibility that all the pixel points in each suspected critical area cluster are critical area points, and marking the suspected critical area cluster corresponding to the average value of the possibility that all the maximum pixel points are critical area points as a critical area.
The technical scheme has the advantages that according to the gray level difference of the pixels in the same wavelength along the eight neighborhood direction from each pixel in the hyperspectral image in the current period and the degree of influence of weather and other external factors on each pixel in each wavelength, the possibility that each pixel in the hyperspectral image in the current period is a junction point of different areas in each wavelength is obtained, the degree of influence of weather and other external factors on each pixel in the hyperspectral image in the current period is comprehensively analyzed, the change of data characteristics caused by the influence of weather, environment and the like is considered, the accuracy of critical area screening is improved, and the accuracy of constructing a three-dimensional hydrogeological model is further improved. According to the probability that each pixel point in the hyperspectral image in the current period is a boundary point of different areas under all different wavelengths, the probability that each pixel point in the hyperspectral image in the current period is a key area point is obtained, the difference of the probability that any two pixel points in the hyperspectral image in the current period are the clustering distance of any two pixel points is used as the clustering distance of any two pixel points, clustering operation is carried out on the hyperspectral image in the current period to obtain a plurality of suspected key area clusters, the key areas are screened out according to the probability that the pixel points in the suspected key area clusters are the key area points, and a three-dimensional hydrogeological model corresponding to the key areas is constructed. By screening out the critical areas and collecting key information aiming at the critical areas, the acquisition of information of non-critical areas is reduced, and then the data volume for dynamically constructing the three-dimensional hydrogeologic model is reduced, so that the dynamic construction of the three-dimensional hydrogeologic model is more efficient and adaptive.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of a method for dynamically constructing a three-dimensional hydrogeologic model according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purposes, the following detailed description refers to the specific implementation, structure, characteristics and effects of a dynamic construction method of a three-dimensional hydrogeologic model according to the present invention, with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the dynamic construction method of the three-dimensional hydrogeologic model provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for dynamically constructing a three-dimensional hydrogeologic model according to an embodiment of the present invention is shown, where the method includes the following steps:
Step S001, acquiring a plurality of hyperspectral images of the same research area in different periods, wherein each pixel point in the hyperspectral images corresponds to a plurality of gray values under different wavelengths, and the different periods comprise a current period and a reference history period.
And acquiring a plurality of hyperspectral images of the same research area in different periods, wherein each pixel point in the hyperspectral image corresponds to reflection intensity of a plurality of different wavelengths, and the reflection intensity is called a gray value in the embodiment, namely, each pixel point corresponds to the gray value of a plurality of different wavelengths.
In this embodiment, a reference history period is selected to be one week before, which is described as an example.
The research area is the area where the three-dimensional hydrogeologic model needs to be built, and a plurality of hyperspectral images of the same research area in different periods are obtained through satellite remote sensing.
It should be noted that each pixel in the hyperspectral image may represent a reflection intensity or reflectivity, and each pixel in the hyperspectral image actually corresponds to a small area of the earth's surface, and there is a corresponding radiation intensity value in each band in the area, where the values reflect the spectral characteristics of the earth's surface in different bands. These reflection intensity values are typically represented in digital form, which may be floating point numbers between 0 and 1, or integers between 0 and 255 (gray values), hereinafter collectively referred to as gray values, in which the reflection intensity is embodied.
When the hydrogeologic condition of the current research area is analyzed, the hyperspectral image has the characteristics of high spatial resolution, multispectral information and the like, so that different ground object types such as water bodies, soil, vegetation and the like can be identified, a richer data basis is provided for hydrogeologic analysis, the surface environment can be better understood, and hidden geology and hydrographic features can be found. Therefore, the embodiment provides a basis for the subsequent analysis of determining the critical area of the current research area by acquiring the hyperspectral image of the current research area.
Step S002, according to the difference between gray values of each pixel point in the hyperspectral image of the current period and the reference history period under the same wavelength, obtaining the degree of influence of external factors such as weather and the like on each pixel point in the hyperspectral image of the current period under each wavelength.
It should be noted that, in the current research area, the hydrogeologic features are represented by hyperspectral images, but the geological stability, soil hydrographic conditions and other conditions of different areas in the whole research area are different, so that under the influence of rainfall or human activities and the like, the degrees of the change of the hydrogeologic features of different areas are different, and the degrees of the difference of the hyperspectral images acquired in the current research area in different periods are different. For example, the geological structure in a part of the current research area is stable, the underground rock stratum is firm and has low water permeability, so that the underground water level changes slowly, or the soil type and the water content are proper, and the water infiltration and the storage are facilitated. In the above case, therefore, even if there is rainfall or the influence of human activity, the change of the region whose hydrogeologic characteristics are less excellent than those described above (the above characteristics are just examples thereof, and there are other factors contributing to the maintenance of the hydrogeologic characteristics) is relatively slow. Aiming at hyperspectral images acquired in different periods, the possibility that each pixel point is a key area is determined based on the analysis hydrologic characteristic performance of each pixel point under different wavelengths, and then the measurement mode of the distance between sample points when different pixel points are clustered is determined.
The hyperspectral images in different periods of the research area are affected by factors such as rainfall or human activities, the hyperspectral images in different areas of the research area are changed, the change amplitude is affected by factors such as the geological stability of the area and the soil hydrologic condition, so that the change amplitude of the hyperspectral images in the same wavelength in different periods is compared, the degree of the influence of external factors such as weather on the research area in different wavelengths can be reflected, and the manifestation degree of the research area in different wavelengths is determined.
Firstly, the definition of a key area in a research area is described, the difference of the hydrogeologic features of different areas in different periods is different because the whole range of the research area is large, and the area with quick change of the hydrogeologic features is called as the key area because data updating and measurement are needed to be carried out on the area in time.
And recording the absolute value of the difference value of the gray value of the mth pixel point in the hyperspectral image of the current period and the reference history period at the ith wavelength as the gray difference of the mth pixel point in the hyperspectral image of the current period at the ith wavelength.
The calculation method for the degree of influence of weather and other external factors on the mth pixel point in the hyperspectral image in the current period under the ith wavelength is as follows:
Wherein Q i,m represents the degree of influence of external factors such as weather on the mth pixel point in the hyperspectral image in the current period under the ith wavelength, and delta Q i,m represents the gray level difference of the mth pixel point in the hyperspectral image in the current period under the ith wavelength; the method comprises the steps of representing the average value of gray differences of all pixel points in a hyperspectral image in the current period at the ith wavelength, wherein norm () is a normalization function, M represents the number of pixel points in the hyperspectral image in the current period, and I is an absolute value function.
It should be noted that Δq i,m represents the gray level difference of the mth pixel point in the hyperspectral image of the current period at the ith wavelength, and the larger the gray level difference is, the more obvious the difference of the hydrogeologic features of the pixel point in the hyperspectral image of the current period at the current wavelength is, namely the degree of influence of external factors such as weather is, butOnly represented by the average value, there may be too large or too small gray differences corresponding to some pixels, so that the corresponding gray differencesThe larger the image is, but this only can illustrate that some areas in the current research area are greatly influenced by factors such as weather, and the image is mapped to the whole research area to show the false image as if the current research area is greatly influenced by external factors such as weather, so the embodiment passesThe smaller the value is, the closer the gray level difference corresponding to each pixel point in the current research area is to the average value, namely the influence of factors such as weather and the like on each area in the current research area is more balanced (the influence degree of the whole research area is large, and the influence degree of weather factors on the corresponding current whole research area is more true and accurate). Therefore, it isTaking this as a reference valueThe smaller the value of the adjustment coefficient, the greater the degree of adjustment of the reference value.
So far, the degree that each pixel point in the hyperspectral image in the current period is influenced by external factors such as weather and the like at each wavelength is obtained.
Step S003, according to the gray level difference of the pixel points in the same wavelength along the eight neighborhood direction from each pixel point in the hyperspectral image of the current period and the degree of influence of weather and other external factors on each pixel point at each wavelength, the possibility that each pixel point in the hyperspectral image of the current period is a boundary point of different regions at each wavelength is obtained.
The degree of influence of external factors such as weather at different periods of each wavelength is analyzed, and is determined based on the whole research area corresponding to each wavelength, and the degree of influence of each pixel point at each wavelength can be analyzed and judged to determine the possibility that each pixel point at each wavelength is a boundary point of different areas (different geological stability and soil hydrologic condition areas).
It should be further noted that, in the whole research area, the geological stability and the soil hydrologic condition of different areas are different, for the pixel points in the same area (the same or similar geological stability and soil hydrologic condition area), the corresponding gray level difference is similar to other pixel points in the neighborhood at the same wavelength in different periods, and the gray level difference corresponding to other pixel points in the neighborhood at the boundary of the different areas may be obviously different, and these places may be key nodes in the hydrogeology process, and have important geological, hydrologic and ecological significance. Analysis of this characteristic can better find the criticality of each pixel based on the hydrogeologic feature information presented throughout the investigation region at the current wavelength.
In the hyperspectral image in the current period, each pixel point is taken as a circle center, the radius r is taken as a circle, and the circle is recorded as a local neighborhood of each pixel point, wherein r is a preset radius, and r=13, and the description is given by taking this as an example.
The calculation method for the possibility that the jth pixel point in the hyperspectral image in the current period is a junction point of different areas under the ith wavelength is as follows:
Wherein W i,j represents the possibility that the jth pixel point in the hyperspectral image of the current period is a junction point of different areas at the ith wavelength, Q i,m represents the degree of influence of external factors such as weather and the like on the mth pixel point in the hyperspectral image of the current period, deltaq i,j,l,b represents the gray scale difference of the jth pixel point in the eighth neighborhood direction from the jth pixel point in the hyperspectral image of the current period at the ith wavelength, deltaq i,j,l,max represents the maximum value in the gray scale difference of all the pixel points in the ith wavelength in the eighth neighborhood direction from the jth pixel point in the local neighborhood of the jth pixel point in the hyperspectral image of the current period from the jth pixel point in the eighth neighborhood direction; Standard deviations of all Δq i,j,l,max-Δqi,j,l,b when b falls within interval [1, b i,j,l ]; all when l is within interval [1,8] Standard deviation of (2).
When there is no pixel point in one of the eight neighborhood directions of the pixel point, the direction is not analyzed in the above formula.
The eight neighborhood direction is a known technique, and the specific method is not described here.
The different areas represent areas with different geological stability and soil hydrologic conditions.
The Q i is taken as a weight, and the greater the Q i is, the greater the degree of influence of external factors such as weather in a research area corresponding to the current pixel point under the wavelength is, so that the overall key of the wavelength where the current pixel point is located is laid, and the greater the Q i is, the greater the influence degree of the current pixel point on the boundary point of different areas is.
It should be noted that, in the local neighborhood of the jth pixel point in the hyperspectral image in the current period, Δq i,j,l,max is used to represent the maximum value of the gray differences of all the pixel points in the ith wavelength in the eighth neighborhood direction from the jth pixel point; By comparing the adjacent degree of the gray level difference of other pixel points and the gray level difference of the maximum pixel point in the same direction, The local neighborhood of the pixel point is determined, the consistency of the change of the hydrogeologic features in the eight neighborhood directions of the pixel point is indicated, the larger the value is, the larger the difference exists between the change of the hydrogeologic features in all directions, and the greater the possibility that the jth pixel point in the hyperspectral image in the current period is a junction point of different areas under the ith wavelength is.
Thus, the possibility that each pixel point in the hyperspectral image in the current period is a junction point of different areas under each wavelength is obtained.
Step S004, according to the possibility that each pixel point in the hyperspectral image in the current period is a junction point of different areas under all different wavelengths, the possibility that each pixel point in the hyperspectral image in the current period is a key area point is obtained.
The process analysis determines the possibility of boundary points of different areas (different geological stability and soil hydrologic condition areas) of each pixel point under different wavelengths, and sums the possibility of the boundary points to comprehensively determine the possibility of each pixel point being a key area point under different wavelengths.
The calculation method for the possibility that the jth pixel point in the hyperspectral image in the current period is a key area point is as follows:
Wherein E j represents the possibility that the jth pixel point in the hyperspectral image in the current period is a key area point, I represents the number of wavelengths corresponding to the jth pixel point in the hyperspectral image in the current period, and W i,j represents the possibility that the jth pixel point in the hyperspectral image in the current period is a junction point of different areas under the ith wavelength.
The possibility that the jth pixel point in the hyperspectral image in the current period is a key area point is comprehensively determined through accumulation of the possibility that the jth pixel point in the hyperspectral image in the current period is a junction point of different areas under different wavelengths.
Thus, the possibility that each pixel point in the hyperspectral image in the current period is a key area point is obtained.
Step S005, clustering the hyperspectral image in the current period by taking the difference of the possibility that any two pixel points in the hyperspectral image in the current period are key area points as the clustering distance of any two pixel points to obtain a plurality of suspected key area clusters, screening out the key areas according to the possibility that the pixel points in the suspected key area clusters are the key area points, and constructing a three-dimensional hydrogeological model corresponding to the key areas.
And taking each pixel point in the hyperspectral image in the current period as a sample point in clustering, and utilizing a distance measurement mode in a K-means clustering algorithm, wherein the distance measurement mode for different sample points is the absolute value of the difference value of the possibility that any two pixel points in the hyperspectral image corresponding to the current period are key region points.
The preset clustering number is 8 by taking this as an example for description by the distance measurement mode between different sample points, so that the absolute value of the difference value of the possibility that any two pixel points in the hyperspectral image in the current period are key region points is the clustering distance of any two pixel points, and the hyperspectral image in the current period is clustered by adopting a K-means clustering algorithm to obtain a plurality of suspected key region clusters.
Calculating the average value of the possibility that all the pixel points in each suspected critical area cluster are critical area points, and marking the suspected critical area cluster corresponding to the average value of the possibility that all the maximum pixel points are critical area points as a critical area.
And dynamically constructing a three-dimensional hydrogeological model by adopting a numerical simulation method based on the data of the groundwater level, the hydrogeological condition and the topography fluctuation of the key region.
The method is characterized in that for key information acquisition areas of key areas, information updating of the key areas can be set to be carried out once every two days, other areas can be set to be carried out once a week, a three-dimensional hydrogeologic model is dynamically constructed through multi-source data such as geology, hydrology and topography, a numerical simulation method is adopted, and future water resource changes and groundwater dynamics are predicted through simulating groundwater flow, hydrologic process and the like.
The K-means clustering algorithm and the numerical simulation method are known techniques, and specific methods are not described herein.
This embodiment is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.

Claims (5)

1.一种三维水文地质模型的动态构建方法，其特征在于，该方法包括以下步骤：1. A method for dynamically constructing a three-dimensional hydrogeological model, characterized in that the method comprises the following steps: 获取同一研究区域若干个不同时期的高光谱影像；其中，高光谱影像中的每个像素点对应若干个不同的波长下的灰度值，不同时期包含当前时期和一个参考历史时期；Obtain hyperspectral images of the same study area at several different periods; each pixel in the hyperspectral image corresponds to grayscale values at several different wavelengths, and different periods include the current period and a reference historical period; 根据当前时期和参考历史时期的高光谱影像中每个像素点在同一波长下的灰度值之间的差异，得到当前时期的高光谱影像中每个像素点在每个波长下受天气等外界因素影响的程度；According to the difference between the grayscale values of each pixel in the hyperspectral images of the current period and the reference historical period at the same wavelength, the degree to which each pixel in the hyperspectral images of the current period is affected by external factors such as weather at each wavelength is obtained; 根据当前时期的高光谱影像中，从每个像素点开始沿着八邻域方向上像素点在同一波长下的灰度差异以及每个像素点在每个波长下受天气等外界因素影响的程度，得到当前时期的高光谱影像中每个像素点在每个波长下为不同区域交界点的可能性；According to the grayscale difference of each pixel point along the eight neighborhood directions at the same wavelength in the hyperspectral image of the current period and the degree to which each pixel point is affected by external factors such as weather at each wavelength, the possibility of each pixel point in the hyperspectral image of the current period being the boundary point of different regions at each wavelength is obtained; 根据当前时期的高光谱影像中每个像素点在所有不同波长下为不同区域交界点的可能性，得到当前时期的高光谱影像中每个像素点为关键区域点的可能性；According to the possibility that each pixel point in the hyperspectral image of the current period is the boundary point of different regions at all different wavelengths, the possibility that each pixel point in the hyperspectral image of the current period is the key region point is obtained; 以当前时期的高光谱影像中任意两个像素点为关键区域点的可能性的差异为任意两个像素点的聚类距离，对当前时期的高光谱影像进行聚类操作，得到若干个疑似关键性区域簇；The difference in the possibility that any two pixels in the hyperspectral image of the current period are key area points is taken as the clustering distance of any two pixels, and the hyperspectral image of the current period is clustered to obtain several suspected key area clusters; 根据疑似关键性区域簇中像素点为关键区域点的可能性，筛选出关键性区域；构建关键性区域对应的三维水文地质模型；According to the possibility that the pixel points in the suspected key area cluster are key area points, the key areas are screened out; and a three-dimensional hydrogeological model corresponding to the key areas is constructed; 所述根据当前时期和参考历史时期的高光谱影像中每个像素点在同一波长下的灰度值之间的差异，得到当前时期的高光谱影像中每个像素点在每个波长下受天气等外界因素影响的程度，包括的具体步骤如下：The method of obtaining the degree to which each pixel in the hyperspectral image of the current period is affected by external factors such as weather at each wavelength based on the difference between the grayscale values of each pixel in the hyperspectral image of the current period and the reference historical period at the same wavelength includes the following specific steps: 根据当前时期和参考历史时期的高光谱影像中每个像素点在同一波长下的灰度值，得到当前时期的高光谱影像中每个像素点在每个波长下的灰度差；According to the gray value of each pixel point at the same wavelength in the hyperspectral image of the current period and the reference historical period, the gray difference of each pixel point at each wavelength in the hyperspectral image of the current period is obtained; 根据当前时期的高光谱影像中所有像素点在每个波长下的灰度差之间的差异，得到当前时期的高光谱影像中每个像素点在每个波长下受天气等外界因素影响的程度，包括的具体公式如下：According to the difference between the grayscale differences of all pixels in the hyperspectral image of the current period at each wavelength, the degree to which each pixel in the hyperspectral image of the current period is affected by external factors such as weather at each wavelength is obtained, including the specific formula as follows: ； ; 式中，表示当前时期的高光谱影像中第个像素点在第个波长下受天气等外界因素影响的程度；表示当前时期的高光谱影像中第个像素点在第个波长下的灰度差；表示当前时期的高光谱影像中所有像素点在第个波长下的灰度差的均值；为归一化函数；表示当前时期的高光谱影像中的像素点数量；为绝对值函数；In the formula, Indicates the number of hyperspectral images in the current period. The pixel at The degree to which the wavelength is affected by external factors such as weather; Indicates the number of hyperspectral images in the current period. The pixel at Grayscale difference under wavelength; Indicates that all pixels in the hyperspectral image of the current period are The mean value of grayscale difference under wavelengths; is the normalization function; Indicates the number of pixels in the hyperspectral image of the current period; is the absolute value function; 所述根据当前时期的高光谱影像中，从每个像素点开始沿着八邻域方向上像素点在同一波长下的灰度差异以及每个像素点在每个波长下受天气等外界因素影响的程度，得到当前时期的高光谱影像中每个像素点在每个波长下为不同区域交界点的可能性，包括的具体步骤如下：The method of obtaining the possibility that each pixel in the hyperspectral image of the current period is a boundary point of different regions at each wavelength based on the grayscale difference of each pixel along the eight neighborhood directions at the same wavelength and the degree to which each pixel is affected by external factors such as weather at each wavelength in the hyperspectral image of the current period, includes the following specific steps: 在当前时期的高光谱影像中，构建每个像素点的局部邻域；In the hyperspectral image of the current period, the local neighborhood of each pixel is constructed; 根据当前时期的高光谱影像中每个像素点的局部邻域内，从每个像素点开始沿着八邻域方向上像素点在同一波长下的灰度差异以及每个像素点在每个波长下受天气等外界因素影响的程度，得到当前时期的高光谱影像中每个像素点在每个波长下为不同区域交界点的可能性，包括的具体公式如下：According to the grayscale difference of each pixel point at the same wavelength in the local neighborhood of each pixel point in the hyperspectral image of the current period, along the eight neighborhood directions starting from each pixel point, and the degree to which each pixel point is affected by external factors such as weather at each wavelength, the possibility of each pixel point in the hyperspectral image of the current period being the boundary point of different regions at each wavelength is obtained, including the specific formula as follows: ； ; 式中，表示当前时期的高光谱影像中第个像素点在第个波长下为不同区域交界点的可能性；表示当前时期的高光谱影像中，从第个像素点开始沿着八邻域方向中的第方向上第个像素点在第个波长下的灰度差；表示当前时期的高光谱影像中第个像素点的局部邻域内，从第个像素点开始沿着八邻域方向中的第方向上所有像素点在第个波长下的灰度差中的最大值；表示当前时期的高光谱影像中的第个像素点的局部邻域内，从第个像素点开始沿着八邻域方向中的第方向上的所有像素点在第个波长下的数量；为属于区间内时所有的标准差；为属于区间内时所有的标准差；In the formula, Indicates the number of hyperspectral images in the current period. The pixel at The possibility of being the boundary point of different regions at different wavelengths; Indicates the hyperspectral image of the current period, from The pixel point starts along the first direction of the eight-neighborhood Direction The pixel at Grayscale difference under wavelength; Indicates the number of hyperspectral images in the current period. In the local neighborhood of pixels, from the The pixel point starts along the first direction of the eight-neighborhood All pixels in the direction The maximum value of the grayscale difference under wavelengths; Indicates the first In the local neighborhood of pixels, from the The pixel point starts along the first direction of the eight-neighborhood All pixels in the direction The number of wavelengths; for Belong to the interval All internal time The standard deviation of for Belong to the interval All internal time The standard deviation of 所述根据疑似关键性区域簇中像素点为关键区域点的可能性，筛选出关键性区域，包括的具体步骤如下：The method of screening out key areas according to the possibility that the pixel points in the suspected key area cluster are key area points includes the following specific steps: 计算每个疑似关键性区域簇中所有像素点为关键区域点的可能性的均值，将最大的所有像素点为关键区域点的可能性的均值对应的疑似关键性区域簇，记为关键性区域。The mean of the likelihood that all pixels in each suspected critical region cluster are critical region points is calculated, and the suspected critical region cluster corresponding to the largest mean of the likelihood that all pixels are critical region points is recorded as the critical region. 2.根据权利要求1所述一种三维水文地质模型的动态构建方法，其特征在于，所述根据当前时期和参考历史时期的高光谱影像中每个像素点在同一波长下的灰度值，得到当前时期的高光谱影像中每个像素点在每个波长下的灰度差，包括的具体步骤如下：2. According to the method for dynamically constructing a three-dimensional hydrogeological model of claim 1, it is characterized in that the grayscale difference of each pixel in the hyperspectral image of the current period at each wavelength is obtained according to the grayscale value of each pixel in the hyperspectral image of the current period and the reference historical period at the same wavelength, and the specific steps include the following: 将当前时期和参考历史时期的高光谱影像中第个像素点在第个波长下的灰度值的差值绝对值，记为当前时期的高光谱影像中第个像素点在第个波长下的灰度差。The hyperspectral images of the current period and the reference historical period are The pixel at The absolute value of the difference in grayscale values at wavelengths is recorded as the first The pixel at The grayscale difference at different wavelengths. 3.根据权利要求1所述一种三维水文地质模型的动态构建方法，其特征在于，所述在当前时期的高光谱影像中，构建每个像素点的局部邻域，包括的具体步骤如下：3. A method for dynamically constructing a three-dimensional hydrogeological model according to claim 1, characterized in that the local neighborhood of each pixel point is constructed in the hyperspectral image of the current period, including the following specific steps: 在当前时期的高光谱影像中，将以每个像素点为圆心，半径为r为圆，记为每个像素点的局部邻域；其中r为预设的半径。In the hyperspectral image of the current period, a circle with each pixel as the center and a radius of r is recorded as the local neighborhood of each pixel; r is the preset radius. 4.根据权利要求1所述一种三维水文地质模型的动态构建方法，其特征在于，所述根据当前时期的高光谱影像中每个像素点在所有不同波长下为不同区域交界点的可能性，得到当前时期的高光谱影像中每个像素点为关键区域点的可能性，包括的具体公式如下：4. According to the method for dynamically constructing a three-dimensional hydrogeological model in claim 1, it is characterized in that the possibility of each pixel point in the hyperspectral image of the current period being a boundary point of different regions at all different wavelengths is obtained, and the specific formula included is as follows: ； ; 式中，表示当前时期的高光谱影像中第个像素点为关键区域点的可能性；表示当前时期的高光谱影像中第个像素点对应的波长数量；表示当前时期的高光谱影像中第个像素点在第个波长下为不同区域交界点的可能性。In the formula, Indicates the number of hyperspectral images in the current period. The possibility that a pixel point is a key area point; Indicates the number of hyperspectral images in the current period. The number of wavelengths corresponding to each pixel; Indicates the number of hyperspectral images in the current period. The pixel at The possibility of the intersection of different regions at different wavelengths. 5.根据权利要求1所述一种三维水文地质模型的动态构建方法，其特征在于，所述任意两个像素点的聚类距离的具体获取步骤如下：5. According to the method for dynamically constructing a three-dimensional hydrogeological model of claim 1, it is characterized in that the specific steps of obtaining the cluster distance between any two pixel points are as follows: 将当前时期的高光谱影像中任意两个像素点为关键区域点的可能性的差值绝对值，记为所述任意两个像素点的聚类距离。The absolute value of the difference between the possibilities of any two pixels in the hyperspectral image of the current period being key area points is recorded as the clustering distance of the any two pixels.
CN202410656277.3A 2024-05-24 2024-05-24 Dynamic construction method of three-dimensional hydrogeologic model Active CN118608707B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410656277.3A CN118608707B (en) 2024-05-24 2024-05-24 Dynamic construction method of three-dimensional hydrogeologic model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410656277.3A CN118608707B (en) 2024-05-24 2024-05-24 Dynamic construction method of three-dimensional hydrogeologic model

Publications (2)

Publication Number Publication Date
CN118608707A CN118608707A (en) 2024-09-06
CN118608707B true CN118608707B (en) 2025-03-14

Family

ID=92562261

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410656277.3A Active CN118608707B (en) 2024-05-24 2024-05-24 Dynamic construction method of three-dimensional hydrogeologic model

Country Status (1)

Country Link
CN (1) CN118608707B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116403154A (en) * 2023-03-06 2023-07-07 广州市林业和园林科学研究院 Intelligent monitoring method for combined three-dimensional greening abnormality of landscape architecture
CN117132594A (en) * 2023-10-25 2023-11-28 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) Intelligent detection method for underground water microplastic based on hyperspectral image

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9147265B2 (en) * 2012-06-04 2015-09-29 Raytheon Company System and method for rapid cluster analysis of hyperspectral images

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116403154A (en) * 2023-03-06 2023-07-07 广州市林业和园林科学研究院 Intelligent monitoring method for combined three-dimensional greening abnormality of landscape architecture
CN117132594A (en) * 2023-10-25 2023-11-28 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) Intelligent detection method for underground water microplastic based on hyperspectral image

Also Published As

Publication number Publication date
CN118608707A (en) 2024-09-06

Similar Documents

Publication Publication Date Title
Li et al. Urban flood susceptibility mapping based on social media data in Chengdu city, China
Lemercier et al. Extrapolation at regional scale of local soil knowledge using boosted classification trees: A two-step approach
CN112200358B (en) Landslide level prediction method, landslide level prediction device, landslide level prediction equipment and storage medium
CN111832518B (en) Space-time fusion-based TSA remote sensing image land utilization method
CN112200362B (en) Landslide prediction method, landslide prediction device, landslide prediction equipment and storage medium
Feng et al. An integrated method of selecting environmental covariates for predictive soil depth mapping
CN109063657B (en) Aboveground biomass estimation and scaling method for homogeneous regional spectral units
CN114819737B (en) Method, system and storage medium for estimating carbon reserves of highway road vegetation
Pippuri et al. Classification of forest land attributes using multi-source remotely sensed data
CN117709583B (en) Data-driven dynamic landslide susceptibility evaluation and disaster factor change inference method
Ørka et al. A framework for a forest ecological base map–an example from Norway
CN112200355B (en) Landslide prediction method, landslide prediction device, landslide prediction equipment and storage medium
Liu et al. Fusing landsat-8, sentinel-1, and sentinel-2 data for river water mapping using multidimensional weighted fusion method
CN119250547B (en) Intelligent monitoring and early warning method and system for cofferdam construction process
AU2021101780A4 (en) Aboveground Biomass Estimation and Scale Conversion for Mean Regional Spectral Units
CN119740124A (en) Comprehensive assessment method of road collapse risk based on multi-source data fusion
CN118608707B (en) Dynamic construction method of three-dimensional hydrogeologic model
Amirgaliyev et al. Remote sensing and machine learning algorithms to predict soil salinity in southern Kazakhstan
Shimoni et al. An urban expansion model for African cities using fused multi temporal optical and SAR data
CN120125067B (en) Ecological protection red line foundation investigation method based on homeland space planning
Gui et al. Reconstructing Reservoir Water Level-Area-Storage Volume Curve Using Multi-source Satellite Imagery and Intelligent Classification Algorithms
CN120087851B (en) A probabilistic assessment method for flash flood and debris flow susceptibility based on cascade learning model
CN119269418B (en) Regional soil moisture monitoring method for airborne spectrum reconstruction optical satellite remote sensing
CN119903116A (en) Snow depth inversion method and system based on SAR image based on underlying surface information fusion
CN120673547A (en) A Beidou-based intelligent geological disaster monitoring and early warning method and system

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
GR01 Patent grant
GR01 Patent grant