CN118052377A - Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat - Google Patents
Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat Download PDFInfo
- Publication number
- CN118052377A CN118052377A CN202410453370.4A CN202410453370A CN118052377A CN 118052377 A CN118052377 A CN 118052377A CN 202410453370 A CN202410453370 A CN 202410453370A CN 118052377 A CN118052377 A CN 118052377A
- Authority
- CN
- China
- Prior art keywords
- water
- ecological
- score
- inversion
- ecology
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 235
- 238000011156 evaluation Methods 0.000 title claims abstract description 65
- 238000012544 monitoring process Methods 0.000 claims abstract description 133
- 238000000034 method Methods 0.000 claims abstract description 40
- 230000011218 segmentation Effects 0.000 claims abstract description 16
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 abstract description 5
- 238000012937 correction Methods 0.000 description 7
- 230000001360 synchronised effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 101100295091 Arabidopsis thaliana NUDT14 gene Proteins 0.000 description 1
- 241000192710 Microcystis aeruginosa Species 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a water ecological comprehensive evaluation method and system based on automatic inversion of water habitat, and relates to the technical field of data processing, wherein the method comprises the following steps: acquiring water environment data of an ecological monitoring point position; according to a pre-constructed deep network semantic segmentation model, identifying the water environment data of the ecological monitoring points to obtain probability values of the types represented by each pixel point in the water environment data of the ecological monitoring points; according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point, calculating the water environment score of each ecological monitoring point; and calculating the water ecology comprehensive score of each ecological monitoring point according to the water environment score, the water environment score and the water organism diversity score of each ecological monitoring point. The application realizes the comprehensive evaluation of the water ecology by an automatic and objective water environment evaluation method, and improves the accuracy, reliability and efficiency of the comprehensive evaluation of the water ecology.
Description
Technical Field
The application relates to the technical field of data processing, in particular to a water ecological comprehensive evaluation method and system based on automatic inversion of water habitat.
Background
The comprehensive evaluation of the water ecology relates to comprehensive scoring of three aspects of water environment, aquatic environment and aquatic organism diversity of a monitoring point. The evaluation of the water environment quality is based on the calculation of the corresponding score by combining the monitoring data with the evaluation standard. The aquatic organism evaluation is also a score calculated based on the number of species monitored in combination with a formula. The evaluation of the aquatic environment relates to monitoring point position shoreline, water body vegetation coverage and the like, and indexes of the aquatic environment such as the point position shoreline, the water body vegetation coverage and the like are mainly identified by manually utilizing remote sensing data and monitoring data of site points, and based on the result of manual identification, an expert performs scoring to obtain the final score of the aquatic environment element. The combined score of the final monitored point is obtained by summing the weights of the three element scores.
In the comprehensive evaluation of water ecology, the aspects of water environment, aquatic organism diversity and the like are calculated based on real monitoring data according to a standard and normative formula, so that the obtained result is fair and objective. Many works for evaluating the aquatic environment are realized by manual experience operation, including satellite data selection, remote sensing data preprocessing, model threshold selection and the like, and the influence of many factors leads to identification results, which definitely increase the uncertainty and subjectivity of the evaluation of the aquatic environment, so that the scientific evaluation of the aquatic environment cannot be supported. Because of inversion of aquatic environments, more work is involved including downloading of data, preprocessing of data, and inversion of data. The data inversion is especially high in labor cost, so that the development of comprehensive water ecology evaluation is not facilitated.
Therefore, the technical problems to be solved are: how to establish an automatic and objective water ecological assessment method to realize comprehensive water ecological assessment, avoid the inaccuracy of comprehensive water ecological assessment caused by the uncertainty and subjectivity of the water ecological assessment, and improve the accuracy, reliability and efficiency of comprehensive water ecological assessment.
Disclosure of Invention
The application aims to provide a comprehensive water ecological assessment method and system based on automatic inversion of water ecological environment, which realize comprehensive water ecological assessment by an automatic and objective water ecological assessment method, avoid the inaccuracy of comprehensive water ecological assessment caused by the uncertainty and subjectivity of water ecological assessment, and improve the accuracy, reliability and efficiency of comprehensive water ecological assessment.
In order to achieve the above purpose, the application provides a comprehensive water ecology evaluation method based on automatic inversion of water habitat, which comprises the following steps: acquiring water environment data of an ecological monitoring point position; according to a pre-constructed deep network semantic segmentation model, identifying the water environment data of the ecological monitoring points to obtain probability values of the types represented by each pixel point in the water environment data of the ecological monitoring points; according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point, calculating the water environment score of each ecological monitoring point; and calculating the water ecology comprehensive score of each ecological monitoring point according to the water environment score, the water environment score and the water organism diversity score of each ecological monitoring point.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, which is described above, comprises the following steps of: acquiring longitude and latitude coordinates of all ecological monitoring points; acquiring satellite remote sensing data in a geographical area and a monitoring period range according to longitude and latitude coordinates of the ecological monitoring point; and preprocessing all satellite remote sensing data to obtain water environment data of all ecological monitoring points.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, as described above, wherein the probability value of the type represented by each pixel point in the water ecological data of the ecological monitoring point is obtained as follows:
,
wherein, Represents the/>The/>, of the individual ecological monitoring pointsProbability values of the types represented by the individual pixels; /(I)Representing inversion element/>Type number of/>Represents the/>The/>, of the individual ecological monitoring pointsInversion element of individual pixel points/>Probability values of (a) are provided.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, as described above, wherein the method for calculating the water ecological score of each ecological monitoring point location according to the probability value of the type represented by each pixel point in the water ecological data of the ecological monitoring point location comprises the following steps: obtaining the inversion type of each pixel point according to the probability value of the type represented by each pixel point; and calculating the water environment score of each ecological monitoring point according to the inversion type of each pixel point.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, which is described above, wherein the method for calculating the water ecological score of each ecological monitoring point location according to the inversion type of each pixel point comprises the following steps: classifying inversion types according to the attribute of the inversion types; classifying according to inversion types of pixel points of the ecological monitoring points to obtain area occupation ratios of inversion types of different types; and calculating the water environment score of the ecological monitoring point according to the area occupation ratios of different inversion types.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, which is described above, wherein the calculation formula of the water ecological score of the ecological monitoring point is as follows:
;
wherein, Water environmental scores representing ecological monitoring points; /(I)For inversion type calculated by entropy weight methodWeights of (2); /(I)For ecology monitoring point location/>Inversion type/>Is a ratio of the area of (2); /(I)Representing inversion element/>Is a number of types of (a).
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, which is described above, comprises the following steps of: acquiring water environment scoring weights, water environment scoring weights and aquatic organism diversity scoring weights; and calculating the comprehensive water ecology score of each ecological monitoring point according to the water environment score weight, the water environment score weight and the aquatic organism diversity score weight, and the water environment score, the water environment score and the aquatic organism diversity score of each ecological monitoring point.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion, which is described above, wherein the calculation formula of the water ecological comprehensive score of the ecological monitoring point is as follows:
;
wherein, Water ecology comprehensive scores representing ecology monitoring points; /(I)Respectively scoring weights of water environment and aquatic environment and diversity of aquatic organisms; /(I)Water environment score, and aquatic organism diversity score, respectively.
The water ecological comprehensive evaluation method based on the water ecological automatic inversion is characterized in that the types of the inversion types are divided into a positive type set and a negative type set according to the attribute of the inversion types.
As a second aspect of the present application, the present application provides a water ecological comprehensive evaluation system based on automatic inversion of water habitat, the system comprising: the data acquisition module is used for acquiring water environment data of the ecological monitoring point positions; the probability value acquisition module is used for identifying the water environment data of the ecological monitoring points according to a pre-constructed deep network semantic segmentation model to obtain a probability value of the type represented by each pixel point in the water environment data of the ecological monitoring points; the data processor is used for calculating the water environment score of each ecological monitoring point according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point; the data processor is also used for calculating the water ecology comprehensive score of each ecology monitoring point according to the water environment score, the water environment score and the aquatic organism diversity score of each ecology monitoring point.
The beneficial effects achieved by the application are as follows:
(1) According to the application, the objective comprehensive evaluation of the water environment can be realized based on the model of the AI machine vision (deep network semantic segmentation model), the subjectivity of manual operation is eliminated, the water environment evaluation result is more reasonable, the inaccuracy of the comprehensive evaluation of the water ecology caused by the uncertainty and subjectivity of the water environment evaluation is avoided, and the accuracy and reliability of the comprehensive evaluation of the water ecology are improved.
(2) The application can realize rapid and automatic evaluation of the aquatic environment, improves the working efficiency of the aquatic environment evaluation, and further improves the comprehensive evaluation efficiency of the aquatic ecology.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings to those skilled in the art.
FIG. 1 is a flow chart of a comprehensive water ecology evaluation method based on automatic inversion of water habitats according to an embodiment of the application.
FIG. 2 is a frame diagram of a comprehensive water ecology evaluation method based on automatic inversion of water habitats according to an embodiment of the application.
FIG. 3 is a schematic structural diagram of an integrated water ecological assessment system based on automatic inversion of water habitats according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Example 1
As shown in fig. 1 and 2, the application provides a water ecological comprehensive evaluation method based on automatic inversion of water habitat, which comprises the following steps:
And S1, acquiring water environment data of the ecological monitoring point positions.
Step S1 comprises the steps of:
step S110, longitude and latitude coordinates of all ecological monitoring points are obtained.
Specifically, position information of each ecological monitoring point is obtained based on a Geographic Information System (GIS), and the position information comprises longitude and latitude coordinates.
And step S120, acquiring satellite remote sensing data in a geographic area and a monitoring period range according to longitude and latitude coordinates of the ecological monitoring point.
Based on the longitude and latitude coordinates of each ecological monitoring point, the geographic area where the longitude and latitude coordinates are located is obtained, and the satellite remote sensing data of the same satellite in the preset monitoring date or the adjacent date range of the monitoring date (the adjacent date range is for example, within 1 day, within 2 days, within 3 days and the like before and after the monitoring date) is downloaded in the satellite remote sensing database.
And step S130, preprocessing all satellite remote sensing data to obtain water environment data of all ecological monitoring points.
Specifically, the satellite description information is combined to uniformly preprocess all satellite remote sensing data.
The preprocessing of the satellite remote sensing data is an important step, and helps to ensure the quality and accuracy of the data, so that the subsequent data analysis and application are convenient. The following steps are combined with satellite description information to uniformly realize preprocessing of all satellite remote sensing data:
In step S131, all the satellite remote sensing data are received and converted into a universal format.
In step S132, satellite description information is acquired.
Specifically, metadata of the satellite is parsed, and detailed information about the satellite, sensors, imaging conditions (e.g., time, angle, cloud coverage, etc.) is obtained. This information is critical for the subsequent preprocessing steps.
Specifically, the satellite description information includes, for example: satellite images use specific map projection systems, the date of their capture, geographic coverage describing the satellite images, radiation correction coefficients (for converting the image data to radiance or reflectivity), and/or image quality information (including noise levels, blur, etc. parameters affecting image quality), etc.
And step S133, performing radiometric calibration, atmospheric correction, geometric correction, image clipping and splicing and/or data quality evaluation on the images in the satellite remote sensing data according to the satellite description information.
Radiation calibration: according to the information in the metadata, DN (digital number) values of the remote sensing images are converted into radiance or reflectivity.
Atmospheric correction: and the influence of the atmosphere on the remote sensing image, such as aerosol, scattering and the like, is eliminated. This can be achieved by using an atmospheric correction model (e.g., 6S, MODTRAN, etc.).
Geometric correction: and carrying out geometric correction on the remote sensing image according to the geographic coordinate information in the metadata, and ensuring that the ground feature position on the image is consistent with the actual geographic position.
Cutting and splicing images: and cutting the remote sensing image according to the required research area, and splicing a plurality of images into a complete area.
Data quality assessment: based on the preprocessed remote sensing image, the quality of the data, such as noise, cloud coverage, etc., is evaluated. For poor quality data, further processing or culling is required.
And S2, identifying the water environment data of the ecological monitoring points according to a pre-constructed deep network semantic segmentation model, and obtaining the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring points.
According to the pre-constructed deep network semantic segmentation model, the automatic identification of the water environment data of the ecological monitoring point positions is realized, and the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point positions is obtained, so that the objective comprehensive evaluation of the water environment can be realized based on the AI machine vision model (the pre-constructed deep network semantic segmentation model), the subjectivity of manual operation is eliminated, and the water environment evaluation result is ensured to be more reasonable.
The pre-constructed deep network semantic segmentation model is Deeplab V. It should be explained that: the deep network semantic segmentation model Deeplab V is an image semantic segmentation model based on deep learning, and is mainly used for classifying and labeling images at pixel level. The model is improved on the basis of Deeplab V and V2, and the main innovation points comprise Multi-grid introduction, ASPP structure improvement and CRFs post-treatment removal. Deeplab V3 after extracting the feature map through a backhaul network, performing a hole convolution operation (also called expansion convolution) on the feature map to improve the receptive field, and better capturing the context information. In addition, deeplab V also adopts a pyramid pooling module to fuse the context information of different areas so as to better process targets with different scales. The pre-constructed deep network semantic segmentation model adopts the existing method, and is not described in detail herein.
As a specific embodiment of the invention, for the water habitat inversion elementIn other words, according to a pre-constructed deep network semantic segmentation model, probability values/>, which can represent each type of each pixel point in the remote sensing picture of the aquatic environment around the ecological monitoring point s, of each type are obtained;
Wherein,Representing the number of pixels,/>And the number of the ecological monitoring points is represented.
,
Wherein,Represents the/>The/>, of the individual ecological monitoring pointsProbability values of the types represented by the individual pixels; /(I)Representing inversion element/>Type number of/>Represents the/>The/>, of the individual ecological monitoring pointsInversion element of individual pixel points/>Probability values (i.e., model recognition probabilities) of (a) a model.
And S3, calculating the water environment score of each ecological monitoring point according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point.
Step S3 includes the steps of:
step S310, according to the probability value of the type represented by each pixel point, the inversion type of each pixel point is obtained.
Step S310 includes the steps of:
And step S311, determining types according to the maximum value of probability values of pixel points around the ecological monitoring point position, and then assigning different types as 1, 2, 3, … … and f.
In step S312, all pixels are divided into f classes by using spatial clustering, and the inversion type of the pixels in each cluster is defined as the type with the largest number of pixels in the type.
Specifically, in an actual water environment, the types around the ecological monitoring points are continuous, the types are not directly determined according to the maximum probability value of the pixel points, but are determined according to the maximum probability value of the pixel points around the ecological monitoring points, and then different types are assigned to be 1, 2,3, … … and f. All pixels are then classified into f-class using spatial clustering. The inversion type of the pixels in each cluster is defined as the type with the largest number of pixels in the type.
It should be explained that spatial clustering refers to grouping objects in space into multiple classes or clusters, such that there is a higher spatial similarity between objects in the same cluster, and a lower spatial similarity between objects in different clusters.
Step S320, calculating the water environment score of each ecological monitoring point according to the inversion type of each pixel point.
Step S320 includes the steps of:
Step S321, classifying inversion types according to the attribute of the inversion types.
Specifically, the inversion types are classified into two types according to their attributes, one being a positive type set a (e.g., aquatic plants in aquatic vegetation types) and the other being a negative type set N (e.g., water bloom in aquatic vegetation types).
And S322, classifying according to inversion types of pixel points of the ecological monitoring points, and acquiring area occupation ratios of inversion types of different types.
Specifically, the area occupation ratios of inversion types of all the ecological monitoring points are obtained as follows:
;
wherein, Inversion type/>, representing ecological monitoring point position sIs a ratio of the area of (2); /(I)Representing the number of pixels around the ecological monitoring point s; /(I)Representing that the type of pixel points around the ecological monitoring point position s is/>The number of pixels of (a); /(I)The number of types of inversion elements F is represented.
And step S323, calculating the water environment score of the ecological monitoring point according to the area occupation ratios of different inversion types.
Specifically, the weight of each inversion type of the ecological monitoring point position is calculated by using an entropy weight method, and the final water environment score of the ecological monitoring point position s is calculated:
;
Wherein,Water environmental scores representing ecological monitoring points; /(I)For inversion type calculated by entropy weight methodWeights of (2); /(I)For ecology monitoring point location/>Inversion type/>Is a ratio of the area of the lens.
It should be explained that the entropy weight method is an objective assignment method. The entropy weight method calculates the entropy weight of each index by utilizing information entropy according to the variation degree of each index, and corrects the weight of each index by the entropy weight, so that objective index weight is obtained. Generally, the smaller the information entropy of a certain index, the greater the degree of variation of the index, the greater the amount of information provided, and the greater the effect that can be played in the overall evaluation, and the greater the weight thereof. Conversely, if the information entropy of a certain index is larger, the degree of variation of the index value is smaller, the amount of information provided is smaller, the effect on the overall evaluation is smaller, and the weight is smaller.
And S4, calculating the comprehensive water ecology score of each ecological monitoring point according to the water environment score, the water environment score and the aquatic organism diversity score of each ecological monitoring point.
Step S4 includes the steps of:
step S410, obtaining water environment scoring weights, water environment scoring weights and aquatic organism diversity scoring weights.
As a specific embodiment of the present invention, a method for obtaining a water environment scoring weight, an aquatic environment scoring weight, and an aquatic organism diversity scoring weight includes:
In step S411, an importance degree matrix of the expert on the water environment, the water environment and the aquatic organisms is obtained.
It will be appreciated that the comprehensive evaluation of water ecology involves comprehensive evaluation of three aspects of water environment, water environment and aquatic organisms, the three of which have different effects on water ecology. The purpose of the evaluation is to provide a decision for the manager, which may not be achieved simply from the standpoint of data, so that a plurality of water ecology experts are required to judge the weights of the three.
Step S412, based on the importance degree matrix of the expert on the water environment, the water environment and the aquatic organisms, obtaining the water environment scoring weight, the water environment scoring weight and the aquatic organism diversity scoring weight by using an AHP analytic hierarchy process.
The AHP analytic hierarchy process is one combined qualitative and quantitative hierarchical decision making process. Based on the deep research of the essence, influence factors, internal relations and the like of the decision-making problem, the decision-making thinking process is mathematically realized by using less quantitative information, so that a simple decision-making method is provided for complex decision-making problems with multiple targets, multiple criteria or no structural characteristics. The AHP analytic hierarchy process is an existing analytic method, and the water environment scoring weight, the water environment scoring weight and the aquatic organism diversity scoring weight obtained by using the AHP analytic hierarchy process are obtained by adopting an existing technical method, which is not described herein.
Step S420, calculating the comprehensive water ecology score of each ecological monitoring point according to the water environment score weight, the water environment score weight and the aquatic organism diversity score weight, and the water environment score, the water environment score and the aquatic organism diversity score of each ecological monitoring point.
Specifically, the calculation formula of the water ecology comprehensive score of the ecological monitoring point position is as follows:
;
wherein, Water ecology comprehensive scores representing ecology monitoring points; /(I)Respectively scoring weights of water environment and aquatic environment and diversity of aquatic organisms; /(I)Water environment score, and aquatic organism diversity score, respectively.
As a specific embodiment of the invention, the water environment scoring and the aquatic organism diversity scoring adopt scoring modes in the prior art, and are not repeated here.
As an embodiment of the invention, the comparison result is shown in Table 1 by using the data of 10 water ecology monitoring points in a certain river basin.
Table 1:
note that: wherein the manual time only comprises the time for identifying the preprocessed satellite remote sensing data. The system comprises the total time of automatic downloading of data, preprocessing of the data, inversion of the data and the like.
As can be seen from the comparison result of the data of the 10 water ecology monitoring points in the drainage basin in table 1, the evaluation efficiency of the invention is greatly improved, and the evaluation result of the 10 water ecology monitoring points by combining the invention is more objective than the result obtained based on the current evaluation method through comprehensive evaluation of relevant experts, and the difference between the water ecology monitoring points is more reasonable.
Example two
As shown in fig. 3, the present application provides a water ecology comprehensive evaluation system 100 based on automatic inversion of water environments, the system comprising:
The data acquisition module 10 is used for acquiring water environment data of the ecological monitoring points;
The probability value obtaining module 20 is configured to identify the water environment data of the ecological monitoring points according to a deep network semantic segmentation model that is constructed in advance, and obtain a probability value of a type represented by each pixel point in the water environment data of the ecological monitoring points;
A data processor 30 for calculating an water environmental score of each ecology monitoring point according to the probability value of the type represented by each pixel point in the water environmental data of the ecology monitoring point;
The data processor 30 is further configured to calculate an aquatic ecology composite score for each ecology monitoring point based on the water environment score, and the aquatic organism diversity score for each ecology monitoring point.
The application also provides a computer storage medium which stores computer instructions, and the computer instructions are used for executing the address mapping method of the high-capacity solid state disk when being called. The computer storage medium contains one or more program instructions for execution by the processor of a method for comprehensive evaluation of water ecology based on automatic inversion of water habitats.
The disclosed embodiments of the present invention provide a computer readable storage medium having stored therein computer program instructions that, when run on a computer, cause the computer to perform the above-described water ecological comprehensive evaluation method based on automatic inversion of water habitat.
The embodiment of the invention provides a processor for processing the water ecological comprehensive evaluation method based on the automatic inversion of the water habitat.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The Processor may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field programmable gate array (Field Programmable GATE ARRAY, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be Read-Only Memory (ROM), programmable ROM (PROM), erasable Programmable ROM (z230078 f8xm2016. Eprom), electrically Erasable Programmable ROM (ELECTRICALLY EPROM EEPROM), or flash Memory. The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, ddr SDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (Direct Rambus RAM, DRRAM).
The beneficial effects achieved by the application are as follows:
(1) According to the application, the objective comprehensive evaluation of the water environment can be realized based on the model of the AI machine vision (deep network semantic segmentation model), the subjectivity of manual operation is eliminated, the water environment evaluation result is more reasonable, the inaccuracy of the comprehensive evaluation of the water ecology caused by the uncertainty and subjectivity of the water environment evaluation is avoided, and the accuracy and reliability of the comprehensive evaluation of the water ecology are improved.
(2) The application can realize rapid and automatic evaluation of the aquatic environment, improves the working efficiency of the aquatic environment evaluation, and further improves the comprehensive evaluation efficiency of the aquatic ecology.
In the description of the present application, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present application, the word "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the application. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present application may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the application with unnecessary detail. Thus, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The foregoing description is only illustrative of the invention and is not to be construed as limiting the invention. Various modifications and variations of the present invention will be apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present invention are intended to be included within the scope of the claims of the present invention.
Claims (10)
1. The comprehensive water ecology evaluation method based on the automatic inversion of the water habitat is characterized by comprising the following steps of:
acquiring water environment data of an ecological monitoring point position;
According to a pre-constructed deep network semantic segmentation model, identifying the water environment data of the ecological monitoring points to obtain probability values of the types represented by each pixel point in the water environment data of the ecological monitoring points;
according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point, calculating the water environment score of each ecological monitoring point;
And calculating the water ecology comprehensive score of each ecological monitoring point according to the water environment score, the water environment score and the water organism diversity score of each ecological monitoring point.
2. The method for comprehensively evaluating water ecology based on automatic inversion of water habitats according to claim 1, wherein the method for acquiring water ecology data of ecological monitoring points comprises the following steps:
acquiring longitude and latitude coordinates of all ecological monitoring points;
acquiring satellite remote sensing data in a geographical area and a monitoring period range according to longitude and latitude coordinates of the ecological monitoring point;
And preprocessing all satellite remote sensing data to obtain water environment data of all ecological monitoring points.
3. The comprehensive water ecology evaluation method based on automatic inversion of water ecology according to claim 1, wherein the probability value of the type represented by each pixel point in the water ecology data of the obtained ecological monitoring point is:
,
wherein, Represents the/>The/>, of the individual ecological monitoring pointsProbability values of the types represented by the individual pixels; /(I)Representing inversion element/>Type number of/>Represents the/>The/>, of the individual ecological monitoring pointsInversion element of individual pixel points/>Probability values of (a) are provided.
4. The comprehensive water ecological assessment method based on automatic inversion of water ecological environment according to claim 1, wherein the method for calculating the water ecological score of each ecological monitoring point location according to the probability value of the type represented by each pixel point in the water ecological environment data of the ecological monitoring point location comprises:
obtaining the inversion type of each pixel point according to the probability value of the type represented by each pixel point;
And calculating the water environment score of each ecological monitoring point according to the inversion type of each pixel point.
5. The method for comprehensively evaluating water ecology based on automatic inversion of water ecology of claim 4 wherein the method for calculating water ecology score of each ecological monitoring point based on inversion type of each pixel point comprises:
classifying inversion types according to the attribute of the inversion types;
Classifying according to inversion types of pixel points of the ecological monitoring points to obtain area occupation ratios of inversion types of different types;
And calculating the water environment score of the ecological monitoring point according to the area occupation ratios of different inversion types.
6. The comprehensive water ecological assessment method based on automatic inversion of water ecological environment according to claim 5, wherein the calculation formula of the water ecological score of the ecological monitoring point is:
;
wherein, Water environmental scores representing ecological monitoring points; /(I)Inversion type/>, calculated by entropy weight methodWeights of (2); /(I)For ecology monitoring point location/>Inversion type/>Is a ratio of the area of (2); /(I)Representing inversion element/>Is a number of types of (a).
7. The method for comprehensive water ecology assessment based on automatic inversion of water habitats of claim 1 wherein the method for calculating comprehensive water ecology score for ecology monitoring points comprises:
Acquiring water environment scoring weights, water environment scoring weights and aquatic organism diversity scoring weights;
And calculating the comprehensive water ecology score of each ecological monitoring point according to the water environment score weight, the water environment score weight and the aquatic organism diversity score weight, and the water environment score, the water environment score and the aquatic organism diversity score of each ecological monitoring point.
8. The water ecological comprehensive evaluation method based on the water ecological automatic inversion according to claim 7, wherein the calculation formula of the water ecological comprehensive score of the ecological monitoring point is:
;
wherein, Water ecology comprehensive scores representing ecology monitoring points; /(I)Respectively scoring weights of water environment and aquatic environment and diversity of aquatic organisms; /(I)Water environment score, and aquatic organism diversity score, respectively.
9. The method for comprehensive evaluation of water ecology based on automatic inversion of water habitats according to claim 5, wherein the types of inversion types are classified into a positive type set and a negative type set according to the attribute of the inversion type.
10. An aquatic ecology comprehensive evaluation system based on automatic inversion of aquatic environment, which is characterized by comprising:
The data acquisition module is used for acquiring water environment data of the ecological monitoring point positions;
the probability value acquisition module is used for identifying the water environment data of the ecological monitoring points according to a pre-constructed deep network semantic segmentation model to obtain a probability value of the type represented by each pixel point in the water environment data of the ecological monitoring points;
the data processor is used for calculating the water environment score of each ecological monitoring point according to the probability value of the type represented by each pixel point in the water environment data of the ecological monitoring point;
the data processor is also used for calculating the water ecology comprehensive score of each ecology monitoring point according to the water environment score, the water environment score and the aquatic organism diversity score of each ecology monitoring point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410453370.4A CN118052377A (en) | 2024-04-16 | 2024-04-16 | Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410453370.4A CN118052377A (en) | 2024-04-16 | 2024-04-16 | Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat |
Publications (1)
Publication Number | Publication Date |
---|---|
CN118052377A true CN118052377A (en) | 2024-05-17 |
Family
ID=91050418
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410453370.4A Pending CN118052377A (en) | 2024-04-16 | 2024-04-16 | Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118052377A (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110059758A (en) * | 2019-04-24 | 2019-07-26 | 海南长光卫星信息技术有限公司 | A kind of remote sensing image culture pond detection method based on semantic segmentation |
CN110414488A (en) * | 2019-08-20 | 2019-11-05 | 河海大学 | Cyanobacteria bloom monitoring with remote sensing based on planktonic algae index and deep learning |
WO2020188364A1 (en) * | 2019-03-20 | 2020-09-24 | Suryanarayana Raju Sagi | Machine vision system and methods for inspecting aquatic species |
US20200375155A1 (en) * | 2019-04-11 | 2020-12-03 | Zhejiang University | Feedback feeding system for pond recirculation with fusion of machine vision and infrared detection |
CN112488020A (en) * | 2020-12-10 | 2021-03-12 | 西安交通大学 | Water environment pollution condition detection and evaluation device based on unmanned aerial vehicle aerial photography data |
CN112712087A (en) * | 2020-12-29 | 2021-04-27 | 哈尔滨工业大学 | Remote sensing image ground object semantic segmentation method based on deep convolutional neural network |
WO2021238030A1 (en) * | 2020-05-26 | 2021-12-02 | 浙江大学 | Water level monitoring method for performing scale recognition on the basis of partitioning by clustering |
CN115862010A (en) * | 2022-09-09 | 2023-03-28 | 滁州学院 | High-resolution remote sensing image water body extraction method based on semantic segmentation model |
CN116482313A (en) * | 2023-04-20 | 2023-07-25 | 成都南易生态环境科技有限公司 | Water ecology monitoring and comprehensive evaluation method based on environment DNA technology |
CN116721385A (en) * | 2023-06-16 | 2023-09-08 | 西北大学 | Machine learning-based RGB camera data cyanobacteria bloom monitoring method |
CN117495851A (en) * | 2023-12-29 | 2024-02-02 | 陕西中医药大学 | Image contour processing-based water environment microorganism detection method |
US20240062539A1 (en) * | 2022-08-19 | 2024-02-22 | X Development Llc | Aquatic biomass estimation |
-
2024
- 2024-04-16 CN CN202410453370.4A patent/CN118052377A/en active Pending
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020188364A1 (en) * | 2019-03-20 | 2020-09-24 | Suryanarayana Raju Sagi | Machine vision system and methods for inspecting aquatic species |
US20200375155A1 (en) * | 2019-04-11 | 2020-12-03 | Zhejiang University | Feedback feeding system for pond recirculation with fusion of machine vision and infrared detection |
CN110059758A (en) * | 2019-04-24 | 2019-07-26 | 海南长光卫星信息技术有限公司 | A kind of remote sensing image culture pond detection method based on semantic segmentation |
CN110414488A (en) * | 2019-08-20 | 2019-11-05 | 河海大学 | Cyanobacteria bloom monitoring with remote sensing based on planktonic algae index and deep learning |
WO2021238030A1 (en) * | 2020-05-26 | 2021-12-02 | 浙江大学 | Water level monitoring method for performing scale recognition on the basis of partitioning by clustering |
CN112488020A (en) * | 2020-12-10 | 2021-03-12 | 西安交通大学 | Water environment pollution condition detection and evaluation device based on unmanned aerial vehicle aerial photography data |
CN112712087A (en) * | 2020-12-29 | 2021-04-27 | 哈尔滨工业大学 | Remote sensing image ground object semantic segmentation method based on deep convolutional neural network |
US20240062539A1 (en) * | 2022-08-19 | 2024-02-22 | X Development Llc | Aquatic biomass estimation |
CN115862010A (en) * | 2022-09-09 | 2023-03-28 | 滁州学院 | High-resolution remote sensing image water body extraction method based on semantic segmentation model |
CN116482313A (en) * | 2023-04-20 | 2023-07-25 | 成都南易生态环境科技有限公司 | Water ecology monitoring and comprehensive evaluation method based on environment DNA technology |
CN116721385A (en) * | 2023-06-16 | 2023-09-08 | 西北大学 | Machine learning-based RGB camera data cyanobacteria bloom monitoring method |
CN117495851A (en) * | 2023-12-29 | 2024-02-02 | 陕西中医药大学 | Image contour processing-based water environment microorganism detection method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20170184393A1 (en) | Method for identifying air pollution sources based on aerosol retrieval and glowworm swarm algorithm | |
CN115223063B (en) | Deep learning-based unmanned aerial vehicle remote sensing wheat new variety lodging area extraction method and system | |
CN113033453B (en) | Method and system suitable for remote sensing identification of crop types in landscape crushing area | |
CN113887515A (en) | Remote sensing landslide identification method and system based on convolutional neural network | |
CN111898503A (en) | Crop identification method and system based on cloud coverage remote sensing image and deep learning | |
CN112419202B (en) | Automatic wild animal image recognition system based on big data and deep learning | |
CN107967454B (en) | Double-path convolution neural network remote sensing classification method considering spatial neighborhood relationship | |
CN115457408A (en) | Land monitoring method and device, electronic equipment and medium | |
CN116343103A (en) | Natural resource supervision method based on three-dimensional GIS scene and video fusion | |
CN112967286B (en) | Method and device for detecting newly added construction land | |
CN112836590B (en) | Flood disaster monitoring method and device, electronic equipment and storage medium | |
Qu et al. | Mapping large area tea plantations using progressive random forest and Google Earth Engine | |
Ge et al. | Improving spatial and temporal variation of ammonia emissions for the Netherlands using livestock housing information and a Sentinel-2-derived crop map | |
CN117392382A (en) | Single tree fruit tree segmentation method and system based on multi-scale dense instance detection | |
CN118052377A (en) | Water ecological comprehensive evaluation method and system based on automatic inversion of water habitat | |
CN115713691A (en) | Pixel-level electric power popularity estimation method and device based on noctilucent remote sensing | |
CN115546658A (en) | Night cloud detection method combining data set quality improvement and CNN improvement | |
Gruszczyński et al. | Correction of low vegetation impact on UAV-derived point cloud heights with U-Net networks | |
CN115828181A (en) | Potato disease category identification method based on deep learning algorithm | |
Li et al. | Object based building extraction by QuickBird image for population estimation: A case study of the City of Waterloo | |
CN117251520B (en) | Method and device for identifying biodiversity key region and electronic equipment | |
CN116933664B (en) | Earth surface temperature data reconstruction model construction method and earth surface temperature data reconstruction method | |
CN117670527B (en) | Method and system for determining peasant household loan credit limit based on land parcel data | |
CN117874526A (en) | FY4A/4B cloud coverage inversion method and system based on LSTM neural network | |
CN117456287B (en) | Method for observing population number of wild animals by using remote sensing image |
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 |