CN113378903A - Wide watershed water environment data integration method and system - Google Patents
Wide watershed water environment data integration method and system Download PDFInfo
- Publication number
- CN113378903A CN113378903A CN202110600995.5A CN202110600995A CN113378903A CN 113378903 A CN113378903 A CN 113378903A CN 202110600995 A CN202110600995 A CN 202110600995A CN 113378903 A CN113378903 A CN 113378903A
- Authority
- CN
- China
- Prior art keywords
- water body
- data
- abnormal
- watershed
- branch
- 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.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 240
- 230000010354 integration Effects 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000002159 abnormal effect Effects 0.000 claims abstract description 130
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 238000012216 screening Methods 0.000 claims abstract description 7
- 230000007613 environmental effect Effects 0.000 claims description 61
- 238000010606 normalization Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- 230000005856 abnormality Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000005315 distribution function Methods 0.000 claims description 6
- 238000013139 quantization Methods 0.000 claims description 5
- 230000009191 jumping Effects 0.000 claims description 4
- 238000005520 cutting process Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000005540 biological transmission Effects 0.000 description 5
- 241000192710 Microcystis aeruginosa Species 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 241000195493 Cryptophyta Species 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012851 eutrophication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- PWHULOQIROXLJO-UHFFFAOYSA-N Manganese Chemical compound [Mn] PWHULOQIROXLJO-UHFFFAOYSA-N 0.000 description 1
- 108010049746 Microcystins Proteins 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 229910052748 manganese Inorganic materials 0.000 description 1
- 239000011572 manganese Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 150000003839 salts Chemical class 0.000 description 1
- 239000011573 trace mineral Substances 0.000 description 1
- 235000013619 trace mineral Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wide watershed water environment data integration method and a wide watershed water environment data integration system, which comprise the following steps: step S1, monitoring water body environment data of all branch basins contained in a wide basin in real time, and carrying out homonymy clustering on the branch basins according to the water body environment data to form a basin cluster; step S2, carrying out intra-similarity comparison on all branch domains in the basin cluster to realize the abnormal judgment of the branch domains, and screening the branch domains in abnormal conditions as abnormal branch domains; and step S3, performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed. The method and the device have the advantages that the tributary domains are assigned to the basin clusters by using the same-attribute clustering, the difference of the tributary domains in the clusters is known by comparing the water body environment data of the tributary domains in the same basin cluster, the risk condition of the tributary domains can be rapidly judged, and the detection accuracy is high.
Description
Technical Field
The invention relates to the technical field of environmental monitoring, in particular to a wide watershed water body environmental data integration method and system.
Background
Water is a source of everything, river and lake water are main water sources of domestic water of people and are important components of an ecological system. With the development of modern industry, a large amount of pollutants generated in daily production and life of people are discharged into river and lake water areas, so that the eutrophication of the river and lake water and nutrient salts such as nitrogen, phosphorus and the like in the water areas are caused; the contents of trace elements such as iron, manganese and the like and organic compounds are greatly increased, the water bloom phenomenon caused by the mass propagation of algae is promoted, and the microcystins produced by the water bloom blue algae have great harm to the health of human beings.
Aiming at the harm caused by the water bloom phenomenon, the prevention is superior to the treatment, the real-time monitoring of the water body is the premise of prevention, the eutrophication of the water body is the main reason for generating the water bloom, the water body of the river and lake water is monitored, at present, the method of water quality on-line monitoring is mainly utilized, the water body environment data is collected in real time to analyze and control the water body environment characteristics, but the on-line real-time monitoring can generate water body environment data with huge magnitude order, and the water body environment data with the huge magnitude order is analyzed one by one to show that the abnormal water area needs to consume a large amount of data operation and transmission resources, so that the monitoring efficiency is low finally.
Disclosure of Invention
The invention aims to provide a wide-watershed water environment data integration method and system, and aims to solve the technical problems that in the prior art, real-time monitoring can generate water environment data with huge magnitude order, and abnormal water areas are analyzed one by one according to the water environment data with huge magnitude order, a large amount of data operation and transmission resources are consumed, and finally the monitoring efficiency is low.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a wide watershed water environment data integration method comprises the following steps:
step S1, monitoring water body environment data of all branch basins contained in a wide basin in real time, and carrying out homonymy clustering on the branch basins according to the water body environment data to form a basin cluster;
step S2, carrying out intra-similarity comparison on all branch domains in the basin cluster to realize the abnormal judgment of the branch domains, and screening the branch domains in abnormal conditions as abnormal branch domains;
step S3, performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed, and performing function fitting based on the water body environment key data to realize integration of the discrete wide watershed water body environment data into the environment feature function of the abnormal sub-watershed.
As a preferable aspect of the present invention, in step S1, the method for forming the watershed clusters specifically includes:
step S101, respectively quantizing all branch areas into a single basin cluster x based on the water environment datay=*ay1,ay2,…,aymB, wherein xySet of water environment data representing the y-th sub-basin, ayzThe method comprises the following steps of representing the z-th class water body environment data of the y-th tributary domain, wherein z belongs to the group of water body environment data, 1, m-, y belongs to the group of water body environment data, 1, n-, m is the total classification number of the water body environment data, and n is the total number of the tributary domains;
step S102, comparing the external similarities of the basin clusters in sequence, and fusing and normalizing the two basin clusters with the maximum external similarity, wherein the external similarity is measured by a levator coefficient:
wherein the content of the first and second substances,is a tributary domain y1And tributary domain y2The coefficient of the bearing capacity of the fruit,is a tributary domain y1And tributary domain y2In thatAndthe value of (a) is selected from,as a weighted variable, k1∈,1,m-,y1,y2E, 1, n-, m is the total classification number of the water body environment data, and n is the total number of the branch drainage basins;
and S103, repeating the step S102 until the total number of the current basin clusters is 10% of the total number of the basin clusters in the step S101, finishing the same-attribute clustering of all the branch basins, and keeping the current basin clusters as final same-attribute clustering results.
As a preferable aspect of the present invention, in the step S2, the specific method for determining the abnormality of the branch flow field includes:
water body environment data x for all sub-watersheds in each watershed clusteryp=*ay1p,ay2p,…,aymp+ respectively carrying out normalization processing to eliminate differences brought by different index dimensions, wherein the normalization formula is as follows:
wherein z belongs to element 1, m-, y belongs to element 1, n2p-,p∈,1,N-,xypA set of water body environment data representing the yth sub-basin in the pth basin cluster, ayzpRepresenting the z-th class water body environment data of the y-th tributary domain in the p-th basin cluster, wherein m is the total class number of the water body environment data, and n2p is the total number of sub-watersheds in the pth watershed cluster, N is the total number of watershed clusters, ayzp ′Representing z-th type water body environment data of the y-th tributary domain in the p-th basin cluster after normalization processing;
quantifying the abnormal distance between every two branch flow domains in the same flow domain cluster, wherein the abnormal distance is measured by Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
wherein, y1,y2∈,1,n2p-,z∈,1,m-,p∈,1,N-,For sub-basin y in the p-th basin cluster1And tributary domain y2M is the total classification number of the water body environment data, n2p is the total number of branch flowfield in the pth flowfield cluster, N is the total number of the flowfield clusters,respectively representing the yth in the p basin cluster after normalization processing1、y2The z-th class water body environment data of each tributary domain;
setting a distance threshold, and judging the abnormal condition of the branch watersheds in the watershed cluster based on the distance threshold.
As a preferred aspect of the present invention, the method for determining a risk status of a sub-basin in the basin cluster based on the distance threshold includes:
if the number of branch areas in each basin cluster p, the distance between which and the branch area y is greater than the distance threshold value, exceeds the total number n of branch areas in the basin cluster p2If p is 80%, the risk condition of the branch basin y is determined to be abnormal, otherwise, the risk condition of the branch basin y is determined to be normal;
and extracting all branch domains with abnormal risk conditions to serve as abnormal branch domains for realizing the integration of the wide-basin water body environment data.
As a preferable scheme of the present invention, in step S3, the specific method for performing fluctuation integration on the water body environment data of the abnormal watershed to form the water body environment critical data includes:
step S301, cutting the real-time water environment data of the abnormal watershed according to a preset time sequence to form a group of water environment continuous data with a time sequence label and including the integral characteristics of the abnormal watershed environment;
step S302, performing fluctuation analysis on a group of the water body environment continuous data to integrate the water body environment continuous data into a group of water body environment key data with time sequence labels and containing abnormal sub-basin environment abnormal characteristics.
As a preferred embodiment of the present invention, the specific method for fluctuation analysis includes:
sequentially calculating the fluctuation degrees of a group of water environment continuous data on adjacent time sequences to form a fluctuation degree data chain, wherein the calculation formula of the fluctuation degrees is as follows:
wherein x ist=*at1,at2,…,atmR is a set of water environment continuous data, xt,xt+1Respectively the water body environment continuous data of the abnormal branch basin under the time sequence of t and t +1, atzThe z-th class water body environment continuous data of the abnormal branch drainage basin of the t-th time sequence are represented, z belongs to the group of 1, m-is the total class number of the water body environment continuous data, and p (x)t,xt+1) Is xtAnd xt+1Is given by the joint probability distribution function of p (x)t) And p (x)t+1) Are each xtAnd xt+1The edge probability distribution function of (1);
calibrating all jump nodes on the fluctuation degree data chain, and selecting water body environment continuous data positioned at two ends of all jump nodes as water body environment key data;
the jumping node refers to a data node with the numerical value difference of adjacent nodes on the fluctuation data chain exceeding a fluctuation threshold value.
As a preferable scheme of the present invention, in step S3, the specific method for implementing function fitting based on the water body environment critical data to integrate the discrete wide watershed water body environment data into the environmental characteristic function of the abnormal watershed includes:
drawing an integral characteristic curved surface representing the integral environmental characteristics of the abnormal branch watershed on the group of the water body environment continuous data in a multi-dimensional coordinate system;
drawing an abnormal characteristic curved surface representing the environmental abnormal characteristics of the abnormal branch watershed on the group of water body environmental key data in a multi-dimensional coordinate system;
fitting the integral characteristic curved surface and the abnormal characteristic curved surface to form an environmental characteristic curved surface which represents the environmental integral characteristic of the abnormal branch drainage basin and the environmental abnormal characteristic;
and performing function quantization on the environmental characteristic curved surface into an environmental characteristic function so as to integrate the scattered wide watershed water body environmental data into an environmental characteristic function of an abnormal watershed.
As a preferable scheme of the invention, the dimension of the multidimensional coordinate system is determined by the category number of the water body environment continuous data.
As a preferred aspect of the present invention, the present invention provides an integration system according to the wide watershed water environment data integration method, including:
the data acquisition unit is arranged at the branch drainage basin and used for monitoring the water body environment data of the branch drainage basin in real time;
the abnormal discrimination unit is used for carrying out intra-similarity comparison on all branch domains in the basin cluster to realize abnormal discrimination on the branch domains and screening the branch domains in abnormal conditions as abnormal branch domains;
and the data integration unit is used for performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed, and performing function fitting on the basis of the water body environment key data to realize integration of the discrete wide watershed water body environment data into the environment feature function of the abnormal sub-watershed.
As a preferred scheme of the invention, the data acquisition unit, the abnormality judgment unit and the data integration unit are in communication connection to realize data exchange.
Compared with the prior art, the invention has the following beneficial effects:
the method belongs the branch flow field to the flow field cluster by using the same-attribute clustering, knows the difference of the branch flow fields in the cluster by comparing the water body environment data of the branch flow fields in the same flow field cluster, can quickly judge the risk condition of the branch flow fields, has high detection accuracy, performs function quantization environment characteristic function on the water body environment data with discrete branch flow fields, integrates the wide-flow-field water body environment data into the environment characteristic function representing the abnormal flow field, masters the characteristics of the wide-flow-field water body environment to a great extent, reduces the operation and transmission of the water body environment with large magnitude order, and improves the water body monitoring efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
Fig. 1 is a flowchart of a wide watershed water environment data integration method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a wide-flow-field structure according to an embodiment of the present invention;
fig. 3 is a schematic view of a watershed cluster structure provided in an embodiment of the present invention;
FIG. 4 is a schematic diagram of a fluctuation data chain according to an embodiment of the present invention;
fig. 5 is a block diagram of an integrated system according to an embodiment of the present invention.
The reference numerals in the drawings denote the following, respectively:
1-a data acquisition unit; 2-an abnormality determination unit; 3-a data integration unit; 4-water environment continuous data; 5-a fluctuation degree data chain; 6-water body environment key data.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1 to 5, the wide watershed water body is divided into a plurality of sub watersheds for monitoring when monitoring the water body environment due to large area, and the core of the wide watershed water body environment monitoring is to acquire a watershed with an environmental risk, so the wide watershed water body environment monitoring focuses on environmental data with the environmental risk, but conventional environmental data without the risk, and the environmental data with the environmental risk needs to be integrated in the process of processing the wide watershed water body environment data to master the environmental characteristics of the risk watershed and reduce the occupation of operation space, transmission space and storage space by the conventional environmental data without the risk, so the invention provides an integration method of the wide watershed water body environment data.
A wide watershed water environment data integration method comprises the following steps:
step S1, monitoring water body environment data of all branch basins contained in the wide watershed in real time, and carrying out homonymy clustering on the branch basins according to the water body environment data to form a watershed cluster;
in step S1, the method for forming a basin cluster specifically includes:
step S101, respectively quantizing all branch areas into a single basin cluster x based on water environment datay=*ay1,ay2,…,aymB, wherein xySet of water environment data representing the y-th sub-basin, ayzThe method comprises the following steps of representing the z-th class water body environment data of the y-th tributary domain, wherein z belongs to the group of water body environment data, 1, m-, y belongs to the group of water body environment data, 1, n-, m is the total classification number of the water body environment data, and n is the total number of the tributary domains;
step S102, comparing the external similarities of the basin clusters in sequence, fusing and normalizing the two basin clusters with the maximum external similarity, and measuring the external similarity by using a levator coefficient:
wherein the content of the first and second substances,is a tributary domain y1And tributary domain y2The coefficient of the bearing capacity of the fruit,is a tributary domain y1And tributary domain y2In thatAndthe value of (a) is selected from,as a weighted variable, k1∈,1,m-,y1,y2E, 1, n-, m is the total classification number of the water body environment data, and n is the total number of the branch drainage basins;
and S103, repeating the step S102 until the total number of the current basin clusters is 10% of the total number of the basin clusters in the step S101, finishing the same-attribute clustering of all the branch basins, and keeping the current basin clusters as final same-attribute clustering results.
The branch domains with the same environmental attributes are divided into the same basin cluster by using a hierarchical clustering method, so that the same basin cluster is subjected to unified analysis of water body environmental data, discrete branch domains can be integrated into the basin cluster, and the first integration of wide basin water body environmental data is realized.
Step S2, carrying out intra-similarity comparison on all branch domains in the flow domain cluster to realize the abnormal judgment of the branch domains, and screening the branch domains in abnormal conditions as abnormal branch domains;
in step S2, the specific method for determining the abnormality of the branch flow field includes:
water body environment data x for all sub-watersheds in each watershed clusteryp=*ay1p,ay2p,…,aymp+ respectively carrying out normalization treatment to eliminate the difference caused by different index dimensions, wherein the normalization formula is as follows:
wherein z belongs to element 1, m-, y belongs to element 1, n2p-,p∈,1,N-,xypA set of water body environment data representing the yth sub-basin in the pth basin cluster, ayzpRepresenting the z-th class water body environment data of the y-th tributary domain in the p-th basin cluster, wherein m is the total class number of the water body environment data, and n2p is the total number of sub-watersheds in the pth watershed cluster, N is the total number of watershed clusters, ayzp ′Representing z-th type water body environment data of the y-th tributary domain in the p-th basin cluster after normalization processing;
quantifying the abnormal distance between every two branch flow domains in the same flow domain cluster, wherein the abnormal distance is measured by using Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
wherein, y1,y2∈,1,n2p-,z∈,1,m-,p∈,1,N-,For sub-basin y in the p-th basin cluster1And tributary domain y2M is the total classification number of the water body environment data, n2p is the total number of branch flowfield in the pth flowfield cluster, N is the total number of the flowfield clusters,respectively representing the yth in the p basin cluster after normalization processing1、y2The z-th class water body environment data of each tributary domain;
and setting a distance threshold, and judging the abnormal condition of the branch drainage basin in the drainage basin cluster based on the distance threshold.
The method for judging the risk condition of the branch drainage basin in the drainage basin cluster based on the distance threshold comprises the following steps:
if the number of branch areas in each basin cluster p, the distance between which and the branch area y is greater than the distance threshold value, exceeds the total number n of branch areas in the basin cluster p2If p is 80%, the risk condition of the branch basin y is determined to be abnormal, otherwise, the risk condition of the branch basin y is determined to be normal;
and extracting all branch domains with abnormal risk conditions to serve as abnormal branch domains for realizing the integration of the wide-basin water body environment data.
And judging abnormal sub-watersheds in the same watershed cluster, and integrating all water body environment data contained in the watershed cluster into the water body environment data of the abnormal sub-watersheds to realize the second integration of the wide watershed water body environment.
As shown in fig. 2 and 3, the number of the watershed clusters is 3, the watershed cluster 1 includes branch watersheds 1-6, the watershed cluster 2 includes branch watersheds 7-11, the watershed cluster 3 includes branch watersheds 12-14, the water body environment attributes of the branch watersheds 1-6 in the watershed cluster 1 are similar, the water body environment attributes of the branch watersheds 7-11 in the watershed cluster 2 are similar, and the water body environment attributes of the branch watersheds 1-6 and 7-11 between the watershed clusters 1 and 2 have a large difference, so that the internal similarity comparison of the water body environment data of the branch watersheds 1-6 in the watershed cluster 1 can be performed, and the ecological risks of the branch watersheds can be judged.
And S3, performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed, and performing function fitting based on the water body environment key data to realize integration of the discrete wide watershed water body environment data into the environment feature function of the abnormal sub-watershed.
As shown in fig. 4, in step S3, the specific method for forming the critical data of the water body environment by performing fluctuation integration on the water body environment data of the abnormal watershed includes:
s301, cutting the real-time water environment data of the abnormal branch drainage basin according to a preset time sequence to form a group of water environment continuous data with a time sequence label and including the integral characteristics of the abnormal branch drainage basin environment;
step S302, performing fluctuation analysis on a group of water body environment continuous data to integrate the group of water body environment continuous data into a group of water body environment key data with time sequence labels and containing abnormal sub-basin environment abnormal characteristics.
The specific method for fluctuation analysis comprises the following steps:
sequentially calculating the fluctuation degree of a group of water environment continuous data on adjacent time sequences to form a fluctuation degree data chain, wherein the calculation formula of the fluctuation degree is as follows:
wherein x ist=*at1,at2,…,atmR is a set of water environment continuous data, xt,xt+1Respectively the water body environment continuous data of the abnormal branch basin under the time sequence of t and t +1, atzThe z-th class water body environment continuous data of the abnormal branch drainage basin of the t-th time sequence are represented, z belongs to the group of 1, m-is the total class number of the water body environment continuous data, and p (x)t,xt+1) Is xtAnd xt+1Is given by the joint probability distribution function of p (x)t) And p (x)t+1) Are each xtAnd xt+1The edge probability distribution function of (1);
calibrating all jump nodes on the fluctuation degree data chain, and selecting water body environment continuous data positioned at two ends of all jump nodes as water body environment key data;
the jumping node refers to a data node with the numerical value difference of adjacent nodes on the fluctuation data chain exceeding a fluctuation threshold value.
The fluctuation degree is characterized by the fluctuation degree between the continuous water environment data of adjacent time sequences, the fluctuation degree is lower when the numerical value is higher, namely the continuous water environment data of the adjacent time sequences are reduced to be represented by the continuous water environment data of any one time sequence in the adjacent time sequences, therefore, the fluctuation degree between the continuous water environment data of the adjacent time sequences forms a fluctuation degree node data chain, the continuous water environment data of the adjacent time sequences corresponding to all data nodes on a gentle curve in the fluctuation degree node data chain have consistent fluctuation degree, the continuous water environment data of a certain time sequence corresponding to all data nodes on the gentle curve can be randomly selected for characterization to finish variable data dimension reduction, the continuous water environment data of the adjacent time sequences corresponding to jumping nodes on the fluctuation degree node data chain have inconsistent fluctuation degree, namely the continuous water environment data of the adjacent time sequences are changed violently, the method embodies that the drastic change of the water body environment is represented as the occurrence of environmental risk, so that the continuous water body environment data of adjacent time sequences are reserved as the key water body environment data and can be used for analyzing and obtaining the abnormal characteristics of the water body environment.
Step S3, the concrete method for integrating the discrete wide watershed water environment data into the environmental characteristic function of the abnormal watershed based on the water environment key data by performing function fitting comprises the following steps:
drawing an integral characteristic curved surface representing the integral characteristics of the environment of the abnormal branch watershed on a multi-dimensional coordinate system by using a group of water environment continuous data;
drawing an abnormal characteristic curved surface representing the environmental abnormal characteristics of the abnormal branch watershed on a group of water body environmental key data in a multi-dimensional coordinate system;
fitting the integral characteristic curved surface and the abnormal characteristic curved surface to form an environmental characteristic curved surface which represents the environmental integral characteristic of the abnormal branch drainage basin and the environmental abnormal characteristic;
and performing function quantization on the environmental characteristic curved surface into an environmental characteristic function so as to integrate the discrete wide watershed water body environmental data into an environmental characteristic function of the abnormal watershed.
The integral characteristic curved surface is a quantitative representation of the integral characteristic of the water body environment, the abnormal characteristic curved surface is a quantitative representation of the abnormal characteristic of the water body environment, the abnormal characteristic curved surface only comprises data of a plurality of water body environment key data, but the environmental characteristic curved surface is only fit according to the data of the plurality of water body environment key data, and the fitting precision is poor; the integral characteristic curved surface has enough data for fitting the environmental characteristic curved surface for representing the integral characteristic of the water body environment, but the details of the abnormal characteristic are difficult to display, so the integral characteristic curved surface and the abnormal characteristic curved surface are combined to obtain enough data and obtain abnormal characteristic data at the same time, and the integral characteristic curved surface can be used for fitting the environmental characteristic curved surface which can represent the integral water body environmental characteristic of the abnormal branch basin and can highlight the key water body environmental characteristic.
The method comprises the steps of quantizing an environmental characteristic curved surface into an environmental characteristic function, integrating discrete tributary domain water body environmental data into the environmental characteristic function, realizing the third integration of wide-basin water body environmental data, finally realizing the integration of the wide-basin water body environmental data into the environmental characteristic function of an abnormal tributary domain, effectively reducing the storage order of magnitude of the water body environmental data, only needing to store the environmental characteristic function, and when a professional analyst needs to analyze the water body environment, only needing to draw the environmental characteristic function to obtain the environmental overall characteristic and the abnormal characteristic of the abnormal tributary domain in the whole wide-basin.
The dimension of the multidimensional coordinate system is determined by the category number of the water body environment continuous data.
As shown in fig. 5, based on the wide watershed water environment data integration method, the invention provides an integration system, which is characterized by comprising:
the data acquisition unit 1 is used for monitoring the water body environment data of the branch flow field in real time at the branch flow field;
the anomaly judgment unit 2 is used for carrying out intra-similarity comparison on all branch domains in the flow domain cluster to realize anomaly judgment on the branch domains and screening the branch domains in abnormal conditions as abnormal branch domains;
and the data integration unit 3 is used for performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing abnormal features of the abnormal sub-watershed, and performing function fitting based on the water body environment key data to realize integration of the discrete wide watershed water body environment data into an environment feature function of the abnormal sub-watershed.
The data acquisition unit, the abnormality judgment unit and the data integration unit are in communication connection to realize data exchange.
The method belongs the branch flow field to the flow field cluster by using the same-attribute clustering, knows the difference of the branch flow fields in the cluster by comparing the water body environment data of the branch flow fields in the same flow field cluster, can quickly judge the risk condition of the branch flow fields, has high detection accuracy, performs function quantization environment characteristic function on the water body environment data with discrete branch flow fields, integrates the wide-flow-field water body environment data into the environment characteristic function representing the abnormal flow field, masters the characteristics of the wide-flow-field water body environment to a great extent, reduces the operation and transmission of the water body environment with large magnitude order, and improves the water body monitoring efficiency.
According to the method, the branch basins in the same basin cluster are used as a reference, and the ecological risk condition of the branch basins is judged through mutual comparison, so that the risk occurrence of the branch basins can be recognized early, and the safety and stability of the water body in the wide basin can be guaranteed.
The method introduces the concept of river basin cluster unified monitoring into the branch river basin ecological risk monitoring, and combines similar branch river basins together to form each river basin cluster, thereby being beneficial to the long-term supervision of the branch river basins.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A wide watershed water environment data integration method is characterized by comprising the following steps:
step S1, monitoring water body environment data of all branch basins contained in a wide basin in real time, and carrying out homonymy clustering on the branch basins according to the water body environment data to form a basin cluster;
step S2, carrying out intra-similarity comparison on all branch domains in the basin cluster to realize the abnormal judgment of the branch domains, and screening the branch domains in abnormal conditions as abnormal branch domains;
step S3, performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed, and performing function fitting based on the water body environment key data to realize integration of the discrete wide watershed water body environment data into the environment feature function of the abnormal sub-watershed.
2. The wide watershed water environment data integration method according to claim 1, wherein the wide watershed water environment data integration method comprises the following steps: in step S1, the method for forming the watershed clusters includes:
step S101, respectively quantizing all branch areas into a single basin cluster x based on the water environment datay={ay1,ay2,…,aymIn which xySet of water environment data representing the y-th sub-basin, ayzAnd the class z water body environment data representing the y tributary domain, wherein z belongs to [1, m ]],y∈[1,n]M is the total classification number of the water body environment data, and n is the total number of the branch drainage basins;
step S102, comparing the external similarities of the basin clusters in sequence, and fusing and normalizing the two basin clusters with the maximum external similarity, wherein the external similarity is measured by a levator coefficient:
wherein the content of the first and second substances,is a tributary domain y1And tributary domain y2The coefficient of the bearing capacity of the fruit,is a tributary domain y1And tributary domain y2In thatAndthe value of (a) is selected from,as a weighted variable, k1∈[1,m],y1,y2∈[1,n]M is the total classification number of the water body environment data, and n is the total number of the branch drainage basins;
and S103, repeating the step S102 until the total number of the current basin clusters is 10% of the total number of the basin clusters in the step S101, finishing the same-attribute clustering of all the branch basins, and keeping the current basin clusters as final same-attribute clustering results.
3. The wide watershed water environment data integration method according to claim 2, wherein the wide watershed water environment data integration method comprises the following steps: in step S2, the specific method for determining an abnormality in a branch flow field includes:
water body environment data x for all sub-watersheds in each watershed clusteryp={ay1p,ay2p,…,aympRespectively carrying out normalization processing to eliminate differences brought by different index dimensions, wherein the normalization formula is as follows:
wherein z ∈ [1, m ]],y∈[1,n2p],p∈[1,N],xypA set of water body environment data representing the yth sub-basin in the pth basin cluster, ayzpRepresenting the z-th class water body environment data of the y-th tributary domain in the p-th basin cluster, wherein m is the total class number of the water body environment data, and n2p is the total number of sub-watersheds in the pth watershed cluster, N is the total number of watershed clusters, ayzp' indicating z-th class water body environment data of the y-th tributary domain in the p-th basin cluster after normalization processing;
quantifying the abnormal distance between every two branch flow domains in the same flow domain cluster, wherein the abnormal distance is measured by Euclidean distance, and the calculation formula of the Euclidean distance is as follows:
wherein, y1,y2∈[1,n2p],z∈[1,m],p∈[1,N],For sub-basin y in the p-th basin cluster1And tributary domain y2M is the total classification number of the water body environment data, n2p is the total number of branch flowfield in the pth flowfield cluster, N is the total number of the flowfield clusters,respectively representing the yth in the p basin cluster after normalization processing1、y2The z-th class water body environment data of each tributary domain;
setting a distance threshold, and judging the abnormal condition of the branch watersheds in the watershed cluster based on the distance threshold.
4. The wide watershed water environment data integration method according to claim 3, wherein the wide watershed water environment data integration method comprises the following steps: the method for determining the risk condition of the branch drainage basin in the drainage basin cluster based on the distance threshold value comprises the following steps:
if the number of branch areas in each basin cluster p, the distance between which and the branch area y is greater than the distance threshold value, exceeds the total number n of branch areas in the basin cluster p2If p is 80%, the risk condition of the branch basin y is determined to be abnormal, otherwise, the risk condition of the branch basin y is determined to be normal;
and extracting all branch domains with abnormal risk conditions to serve as abnormal branch domains for realizing the integration of the wide-basin water body environment data.
5. The wide watershed water environment data integration method according to claim 4, wherein the wide watershed water environment data integration method comprises the following steps: in step S3, the specific method for forming the critical data of the water environment by performing fluctuation integration on the water environment data of the abnormal watershed includes:
step S301, cutting the real-time water environment data of the abnormal watershed according to a preset time sequence to form a group of water environment continuous data with a time sequence label and including the integral characteristics of the abnormal watershed environment;
step S302, performing fluctuation analysis on a group of the water body environment continuous data to integrate the water body environment continuous data into a group of water body environment key data with time sequence labels and containing abnormal sub-basin environment abnormal characteristics.
6. The wide watershed water environment data integration method according to claim 5, wherein the wide watershed water environment data integration method comprises the following steps: the specific method for fluctuation analysis comprises the following steps:
sequentially calculating the fluctuation degrees of a group of water environment continuous data on adjacent time sequences to form a fluctuation degree data chain, wherein the calculation formula of the fluctuation degrees is as follows:
wherein x ist={at1,at2,…,atmR is a group of water environment continuous data, xt,xt+1Respectively the water body environment continuous data of the abnormal branch basin under the time sequence of t and t +1, atzAnd z-th class water body environment continuous data of abnormal branch basin representing t-th time sequence, wherein z belongs to [1, m ]]M is the total classification number of the water body environment continuous data, p (x)t,xt+1) Is xtAnd xt+1Is given by the joint probability distribution function of p (x)t) And p (x)t+1) Are each xtAnd xt+1The edge probability distribution function of (1);
calibrating all jump nodes on the fluctuation degree data chain, and selecting water body environment continuous data positioned at two ends of all jump nodes as water body environment key data;
the jumping node refers to a data node with the numerical value difference of adjacent nodes on the fluctuation data chain exceeding a fluctuation threshold value.
7. The wide watershed water body environment data integration method according to claim 6, wherein in the step S3, performing function fitting based on the water body environment key data to realize a specific method for integrating the discrete wide watershed water body environment data into the environment feature function of the abnormal watershed comprises:
drawing an integral characteristic curved surface representing the integral environmental characteristics of the abnormal branch watershed on the group of the water body environment continuous data in a multi-dimensional coordinate system;
drawing an abnormal characteristic curved surface representing the environmental abnormal characteristics of the abnormal branch watershed on the group of water body environmental key data in a multi-dimensional coordinate system;
fitting the integral characteristic curved surface and the abnormal characteristic curved surface to form an environmental characteristic curved surface which represents the environmental integral characteristic of the abnormal branch drainage basin and the environmental abnormal characteristic;
and performing function quantization on the environmental characteristic curved surface into an environmental characteristic function so as to integrate the scattered wide watershed water body environmental data into an environmental characteristic function of an abnormal watershed.
8. The wide-watershed water body environment data integration method according to claim 7, wherein the dimension of the multidimensional coordinate system is determined by the category number of the water body environment continuous data.
9. An integration system of the wide watershed water environment data integration method according to any one of claims 1 to 8, characterized by comprising:
the data acquisition unit (1) is arranged at the branch drainage basin and used for monitoring the water body environment data of the branch drainage basin in real time;
the abnormity discrimination unit (2) is used for carrying out intra-similarity comparison on all branch domains in the basin cluster to realize abnormity discrimination on the branch domains, and screening the branch domains in abnormal conditions as abnormal branch domains;
and the data integration unit (3) is used for performing fluctuation integration on the water body environment data of the abnormal sub-watershed to form water body environment key data containing the abnormal features of the abnormal sub-watershed, and performing function fitting on the basis of the water body environment key data to realize integration of the discrete wide watershed water body environment data into the environment feature function of the abnormal sub-watershed.
10. An integration system according to claim 2, wherein the data acquisition unit (1), the abnormality determination unit (2) and the data integration unit (3) are communicatively connected to each other for data interaction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110600995.5A CN113378903B (en) | 2021-05-31 | 2021-05-31 | Wide-river-basin water body environment data integration method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110600995.5A CN113378903B (en) | 2021-05-31 | 2021-05-31 | Wide-river-basin water body environment data integration method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113378903A true CN113378903A (en) | 2021-09-10 |
CN113378903B CN113378903B (en) | 2024-05-10 |
Family
ID=77575164
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110600995.5A Active CN113378903B (en) | 2021-05-31 | 2021-05-31 | Wide-river-basin water body environment data integration method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113378903B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794584A (en) * | 2015-04-30 | 2015-07-22 | 中国科学院南京地理与湖泊研究所 | Lake-type watershed water ecological function primary and secondary zoning method |
CN105868533A (en) * | 2016-03-23 | 2016-08-17 | 四川理工学院 | River basin water environment integrated perception and application method based on Internet of Things and 3S technology |
CN110728320A (en) * | 2019-10-11 | 2020-01-24 | 福建工程学院 | Water quality monitoring and early warning method and system based on combination of self-coding and clustering |
US20200118060A1 (en) * | 2018-10-12 | 2020-04-16 | International Business Machines Corporation | Intelligent classification for product pedigree identification |
CN111709586A (en) * | 2020-06-19 | 2020-09-25 | 大连理工大学 | Water level typing design and control method for flood diversion in reservoir basin |
-
2021
- 2021-05-31 CN CN202110600995.5A patent/CN113378903B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104794584A (en) * | 2015-04-30 | 2015-07-22 | 中国科学院南京地理与湖泊研究所 | Lake-type watershed water ecological function primary and secondary zoning method |
CN105868533A (en) * | 2016-03-23 | 2016-08-17 | 四川理工学院 | River basin water environment integrated perception and application method based on Internet of Things and 3S technology |
US20200118060A1 (en) * | 2018-10-12 | 2020-04-16 | International Business Machines Corporation | Intelligent classification for product pedigree identification |
CN110728320A (en) * | 2019-10-11 | 2020-01-24 | 福建工程学院 | Water quality monitoring and early warning method and system based on combination of self-coding and clustering |
CN111709586A (en) * | 2020-06-19 | 2020-09-25 | 大连理工大学 | Water level typing design and control method for flood diversion in reservoir basin |
Also Published As
Publication number | Publication date |
---|---|
CN113378903B (en) | 2024-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021174751A1 (en) | Method, apparatus and device for locating pollution source on basis of big data, and storage medium | |
Amini et al. | On density-based data streams clustering algorithms: A survey | |
CN105163326B (en) | A kind of cell clustering method and system based on wireless network traffic feature | |
CN1561503A (en) | Classification of objects through model ensembles | |
CN108665119B (en) | Water supply pipe network abnormal working condition early warning method | |
CN104809255A (en) | Load shape acquisition method and system | |
CN110969346A (en) | Drainage basin water ecological function regional treatment demand evaluation method based on index screening | |
CN109947815B (en) | Power theft identification method based on outlier algorithm | |
CN111339499B (en) | Sewage treatment plant running state evaluation method based on time trajectory similarity | |
CN112906738B (en) | Water quality detection and treatment method | |
CN113670616B (en) | Bearing performance degradation state detection method and system | |
CN114720764B (en) | Harmonic analysis method and system based on real-time monitoring data of electric meter | |
CN111797887A (en) | Anti-electricity-stealing early warning method and system based on density screening and K-means clustering | |
CN111626360A (en) | Method, device, equipment and storage medium for detecting fault type of boiler | |
CN108053646B (en) | Traffic characteristic obtaining method, traffic characteristic prediction method and traffic characteristic prediction system based on time sensitive characteristics | |
Zhu et al. | Fuzzy c-means clustering identification method of urban road traffic state | |
CN117493813A (en) | Urban carbon strength analysis method and related equipment | |
CN117609818A (en) | Power grid association relation discovery method based on clustering and information entropy | |
CN113378903A (en) | Wide watershed water environment data integration method and system | |
Zhang et al. | A new outlier detection algorithm based on fast density peak clustering outlier factor. | |
Li et al. | Spatiotemporal classification analysis of long-term environmental monitoring data in the northern part of Lake Taihu, China by using a self-organizing map | |
CN113496440B (en) | User abnormal electricity consumption detection method and system | |
Shahoud et al. | Descriptive statistics time-based meta features (DSTMF) constructing a better set of meta features for model selection in energy time series forecasting | |
Khetarpal et al. | Power quality disturbance classification taking into consideration the loss of data during pre-processing of disturbance signal | |
CN114969143A (en) | Inter-city atmospheric pollutant space-time correlation characteristic analysis method based on data mining |
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 |