CN111260264B - Resource type city ecological safety early warning method and device - Google Patents
Resource type city ecological safety early warning method and device Download PDFInfo
- Publication number
- CN111260264B CN111260264B CN202010370172.3A CN202010370172A CN111260264B CN 111260264 B CN111260264 B CN 111260264B CN 202010370172 A CN202010370172 A CN 202010370172A CN 111260264 B CN111260264 B CN 111260264B
- Authority
- CN
- China
- Prior art keywords
- coefficient
- bayesian network
- ecological safety
- early warning
- resource type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000007613 environmental effect Effects 0.000 claims abstract description 11
- 230000003631 expected effect Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000005325 percolation Methods 0.000 claims 1
- 238000011160 research Methods 0.000 abstract description 9
- 230000036039 immunity Effects 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 125000002015 acyclic group Chemical group 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000035515 penetration Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000003517 fume Substances 0.000 description 1
- 230000001900 immune effect Effects 0.000 description 1
- 239000010842 industrial wastewater Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 239000002910 solid waste Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a resource type urban ecological safety early warning method and a resource type urban ecological safety early warning device, which decompose ecological safety comprehensive consideration of a research area into 3 levels of ecological environment state, ecological safety threat and ecological risk immunity function based on a state-stress-immunity, state-danger-immunity, SDI model. The Bayesian network root node is a resource type urban ecological safety early warning C; determining intermediate nodes C of a Bayesian networkjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecological Risk immunocompetence C3. The method solves the problems that the existing resource type city ecological safety early warning method is generally based on expert scoring, has larger main influence and is comparatively analyzed.
Description
Technical Field
The invention relates to the field of neural networks, in particular to a resource type urban ecological safety early warning method and device.
Background
Resource type cities make historical contributions in the development process of promoting national economy, but exploitation and utilization of resources have great negative effects on the environment, serious threats to ecological safety of the resource type cities, and constraints and limitations on long-term development of the resource type cities, which is a common test faced by many resource type cities in China. The ecological safety problem not only can produce violent influence to the inside of the region, but also can bring negative influence to the social harmony of the surrounding region, and influence the harmony and stability of the country. Therefore, the research on the early warning and response mechanism of the resource type city has important significance for improving the ecological safety condition of the resource type city and promoting the sustainable development of the resource type city.
Scholars at home and abroad make abundant researches on regional ecological safety by using methods such as an ecological footprint method, an ecological L-V model, fuzzy comprehensive evaluation and the like. In the domestic aspect, Zhoushan and the like apply a variable weight model to research ecological safety early warning of Zhoushan islands, and the result shows that the ecological safety of the region is in a 'middle police' state. Mashiwu et al establishes a land ecological safety early warning index system based on a pressure-state-response (P-S-R) framework and studies the land ecological safety early warning in the three gorges reservoir area. Xumei and the like carry out dynamic early warning on the travel ecological safety of Zhang Jiajie city based on an improved Topsis gray GM (1, 1) model, and the travel ecological safety closeness of Zhang Jiajie city is further improved. In 1990, British scholars Sleeser adopts an ECCO model to predict an elastic relation between population and resource environment bearing capacity under different development strategies, and finally determines that the long-term development is an optimal development scheme. In 2001, Tilman et al performed early warning studies on global environmental changes caused by agriculture, indicating that rapid growth in population is a potential risk for ecosystems.
People have more researches on the evolution trend of ecological safety, but the researched model and method only have more evolution on the trend and have less analysis on the reason for the evolution. Therefore, aiming at the analysis capability of the Bayesian network model in advance and after, the Bayesian network is established by analyzing the characteristics of fundamentally different absorption connectivity structures in the seepage theory around the critical probability and the path coefficient, the ecological safety evolution trend is predicted, and the reason causing the evolution trend is analyzed, so that the improvement scheme measures are provided, and the evolution trend is accelerated or inhibited.
The Bayesian network, also called belief network, is an extension of Bayes method, and is one of the most effective theoretical models in uncertain knowledge expression and reasoning field at present. Since its introduction by Pearl in 1988, it has become a hot spot of research in recent years. A bayesian network is a Directed Acyclic Graph (DAG) consisting of nodes representing variables and Directed edges connecting these nodes. The nodes represent random variables, the directed edges among the nodes represent the mutual correlation system (the father node points to the son node), the relation strength is expressed by conditional probability, and the prior probability is used for expressing information without the father node. The node variables may be abstractions of any problem, such as: test values, observations, opinion polls, etc. The method is applicable to expressing and analyzing uncertain and probabilistic events, and to making decisions that are conditionally dependent on a variety of control factors, and can make inferences from incomplete, inaccurate, or uncertain knowledge or information.
The existing resource type city ecological safety early warning method is generally based on expert scoring, has a large main effect and is relatively analyzed.
Disclosure of Invention
The invention aims to: the method and the device for early warning of the ecological safety of the resource type city are provided, and the problems that the existing method for early warning of the ecological safety of the resource type city is generally based on expert scoring, has large main influence and is relatively simple to analyze are solved.
The technical scheme adopted by the invention is as follows:
a resource type city ecological safety early warning method comprises the following steps:
s1, determining that the root node of the Bayesian network is a resource type city ecological safety early warning C; determining intermediate nodes C of a Bayesian networkjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecologyRisk immunocompetence C3(ii) a Intermediate node CjComprising at least one leaf node Cji;
S2, analysis CjiTo CjThe drift diameter coefficient and the decision coefficient;
s3, establishing a Bayesian network model according to the path coefficient and the decision coefficient obtained in the step S2;
and S4, judging whether the Bayesian network model established in the step S3 achieves the expected effect, performing safety early warning according to the obtained Bayesian network model, and otherwise, re-analyzing and determining the coefficient after adjusting the data seepage force of each node.
The state-stress-immunity, state-danger-immunity, SDI model decomposes ecological safety comprehensive consideration of a research area into 3 levels of ecological environment state, ecological safety stress and ecological risk immunity. The Bayesian network root node is a resource type urban ecological safety early warning C; determining intermediate nodes C of a Bayesian networkjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecological Risk immunocompetence C3。
Further, step S2 analyzes CjiTo CjBefore the path coefficient and the decision coefficient are determined, the data of each node is preprocessed.
Further, the method for preprocessing the data of each node comprises the following steps:
cleaning data, filling null values and standardizing data from 0 to 1;
initializing parameters and preprocessing data, and first performing penetration thresholdSet to 0.5.
Suppose the data to be filled is xiFour values adjacent to each other on the left and right are xi-2,xi-1,xi+1,xi+2(ii) a Null padding is then padded using the following formula:
whereinIs a natural constant, is a constant in mathematics, is an infinite acyclic decimal number, and is an transcendental number, and the value of the constant is about 2.71828.
Further, the analysis of the path coefficient in step S2 includes the following steps:
s201, establishing a normal equation set;
s202, calculating a drift diameter coefficient according to a normal equation set;
s203, drawing a drift diameter map according to the drift diameter coefficient obtained in the step S202, and calculating an indirect drift diameter coefficient according to the drift diameter map;
s204, judging C according to the drift diameter coefficient and the indirect drift diameter coefficientjiTo CjThe influence of (c).
Further, the analysis of the decision coefficient in step S3 includes the following steps:
S207, according toThe value of (b) is used to complete the decision coefficient analysis ifIf the main relevant traits are included in the path analysis, the analysis result can express the relationship among the traits, and the step S3 is entered, otherwise, the data of each node is perfected again and the step S201 is entered.
Further, the method for establishing the bayesian network model in step S3 includes the following steps:
s301, analyzing the decision coefficient and then selecting CjiTo CjC80% before the comprehensive influencejiAdding a Bayesian network as a leaf node;
s302, judgment CjiTo CjPositive or negative influence according to CjiTo CjPositive and negative determination of influence CjiA priori probability of (a);
s303, selecting an index which can seep to a target layer from indexes which are not added into the Bayesian network, and adding the index into the Bayesian network;
and S304, converting the decision coefficient into a conditional probability to obtain the Bayesian network model.
Further, the method for determining whether the bayesian network model established in step S3 achieves the expected effect in step S4 includes the following steps:
s401, obtaining posterior probabilities of all indexes of a target layer by using the Bayesian network model established in the step S3, and sequentially obtaining conditional probabilities of a criterion layer and a target layer resource type city ecological safety early warning by using the Bayesian network model;
s402, judging whether the expected effect is achieved according to the posterior probability of each index and the conditional probability of the target layer resource type city ecological safety early warning.
A device for resource type city ecological safety early warning comprises:
a memory for storing executable instructions;
and the processor is used for executing the executable instructions stored in the memory and realizing the resource type city ecological safety early warning method.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. according to the resource type urban ecological safety early warning method and device, no expert scoring is performed, the influence of artificial subjective factors is reduced, and the stability of a model is improved;
2. according to the method and the device for the resource type urban ecological safety early warning, after the drift diameter coefficient analysis, whether important data are missed or not can be checked, and the important data can be searched, so that the information collection during the analysis is complete;
3. the resource type city ecological safety early warning method and device can remove unimportant data, reduce the data volume and simplify the Bayesian network structure;
4. according to the method and the device for resource type urban ecological safety early warning, after a Bayesian network is established, the method and the device can be used for scoring and risk assessment, and can also be used for estimating the influence of each criterion layer according to a target layer;
5. the invention relates to a method and a device for resource type urban ecological safety early warning, which can estimate the action of a target layer based on posterior probability from a criterion and provide some scheme measures;
6. according to the resource type city ecological safety early warning method and device, the mutual relation among data is described by using a graphic method, so that the semantics are clear, the understanding is easy, and the analysis is easy;
7. according to the method and the device for early warning of the ecological safety of the resource type city, the strength of the dependency relationship is expressed by the probability distribution table, and the prior information is organically combined with the sample knowledge, so that the integration of the prior knowledge and the data is promoted, and the method and the device are particularly effective when sample data is sparse or the data is difficult to obtain;
8. the invention relates to a method and a device for early warning ecological safety of a resource type city, wherein the design method reflects a probability relation model among data in the whole database, and an accurate model can be established even if a certain data variable is lacked
9. The invention relates to a method and a device for early warning of resource type city ecological safety, wherein a Bayesian network is established based on a seepage theory, and when some information elements which are not added into the Bayesian network exist but the probability is larger than a critical value, the Bayesian network is added, so that the accuracy of a Bayesian network model can be enhanced, the information elements playing an important role at the moment can be prevented from being ignored, and when the probability of the information elements is smaller than the critical value, the Bayesian model is not included, and the Bayesian model can be simplified, so that the simple analysis can be facilitated.
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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts, wherein:
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a diagrammatic illustration of a drift diameter diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to fig. 1 and 2, the described embodiments should not be construed as limiting the present invention, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to be limiting of the invention.
Example 1
A resource type city ecological safety early warning method comprises the following steps:
s1, determining that the root node of the Bayesian network is a resource type city ecological safety early warning C; determining intermediate nodes C of a Bayesian networkjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecological Risk immunocompetence C3(ii) a Intermediate node CjComprising at least one leaf node Cji;
S2, analysis CjiTo CjThe drift diameter coefficient and the decision coefficient;
s3, establishing a Bayesian network model according to the path coefficient and the decision coefficient obtained in the step S2;
and S4, judging whether the Bayesian network model established in the step S3 achieves the expected effect, performing safety early warning according to the obtained Bayesian network model, and otherwise, re-analyzing and determining the coefficient after adjusting the data seepage force of each node.
The state-stress-immunity, state-danger-immunity, SDI model decomposes ecological safety comprehensive consideration of a research area into 3 levels of ecological environment state, ecological safety stress and ecological risk immunity. The Bayesian network root node is a resource type urban ecological safety early warning C; determining intermediate nodes C of a Bayesian networkjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecological Risk immunocompetence C3。
Example 2
This example is further based on example 1, analysis C of step S2jiTo CjBefore the path coefficient and the decision coefficient are determined, the data of each node is preprocessed.
Further, the method for preprocessing the data of each node comprises the following steps:
cleaning data, filling null values and standardizing data from 0 to 1;
initializing parameters and preprocessing data, and first performing penetration thresholdSet to 0.5.
Suppose the data to be filled is xiFour values adjacent to each other on the left and right are xi-2,xi-1,xi+1,xi+2(ii) a Null padding is then padded using the following formula:
Example 3
In this embodiment, based on embodiment 1, the analysis of the path coefficient in step S2 includes the following steps:
s201, establishing a normal equation set;
s202, calculating a drift diameter coefficient according to a normal equation set;
s203, drawing a drift diameter map according to the drift diameter coefficient obtained in the step S202, and calculating an indirect drift diameter coefficient according to the drift diameter map;
s204, judging C according to the drift diameter coefficient and the indirect drift diameter coefficientjiTo CjThe influence of (c).
Further, the analysis of the decision coefficient in step S3 includes the following steps:
S207, according toThe value of (b) is used to complete the decision coefficient analysis ifIf the main relevant traits are included in the path analysis, the analysis result can express the relationship among the traits, and the step S3 is entered, otherwise, the data of each node is perfected again and the step S201 is entered.
Further, the method for establishing the bayesian network model in step S3 includes the following steps:
s301, analyzing the decision coefficient and then selecting CjiTo CjC80% before the comprehensive influencejiAdding a Bayesian network as a leaf node;
s302, judgment CjiTo CjPositive or negative influence according to CjiTo CjPositive and negative determination of influence CjiA priori probability of (a);
s303, selecting an index which can seep to a target layer from indexes which are not added into the Bayesian network, and adding the index into the Bayesian network;
and S304, converting the decision coefficient into a conditional probability to obtain the Bayesian network model.
Further, the method for determining whether the bayesian network model established in step S3 achieves the expected effect in step S4 includes the following steps:
s401, obtaining posterior probabilities of all indexes of a target layer by using the Bayesian network model established in the step S3, and sequentially obtaining conditional probabilities of a criterion layer and a target layer resource type city ecological safety early warning by using the Bayesian network model;
s402, judging whether the expected effect is achieved according to the posterior probability of each index and the conditional probability of the target layer resource type city ecological safety early warning.
Example 5
A device for resource type city ecological safety early warning comprises:
a memory for storing executable instructions;
and the processor is used for executing the executable instructions stored in the memory and realizing the resource type city ecological safety early warning method.
Example 6
The embodiment is an example adopting the scheme:
and the SDI model is adopted to decompose the ecological safety comprehensive consideration of the research area into 3 layers of ecological environment state, ecological safety stress and ecological risk immunity function. The Bayesian network root node is a resource type urban ecological safety early warning C; intermediate node CjThe method comprises the following steps: environmental state C1Ecological safety stress C2And ecological Risk immunocompetence C3(ii) a Intermediate node CjComprising at least one leaf node Cji;
Influencing intermediate node C1(ambient state) leaf node has C1i(1≤i≤n1) Wherein n is1The number of factors influencing the environmental state. E.g. C11Shows the average water resource amount per person of the first influencing factor C12Expressing the second influencing factor of the per capita area, …, C1n1Denotes the n-th1And (c) an influencing factor.
Intermediate node C2(ecological Security duress) leaf node has C2i(1≤i≤n2) Wherein n is2The number of factors influencing ecological safety stress. E.g. C21Indicating the first influencing factor, the emission of industrial fumes C22…, C representing the second influencing factor of industrial wastewater discharge2n2Denotes the n-th2And (c) an influencing factor.
Intermediate node C3(ecological Risk immunological competence) of the leaf node having C3i(1≤i≤n3) Wherein n is3The number of factors influencing ecological risk immunity. C31Indicates the first influencing factor of the comprehensive utilization rate of the industrial solid waste, C32The centralized treatment rate of the municipal domestic sewage, … and C, representing the second influencing factor3n3Denotes the n-th3And (c) an influencing factor. The method comprises the following specific steps:
s01, preparation of data:
s01.1, preprocessing of data, filling of null value and 0-1 standardization of data, and supposing that data X to be fillediFour values adjacent to each other on the left and right are Xi-2,Xi-1,Xi+1,Xi+2(ii) a Null padding is then padded using the following formula:
where e is a natural constant, a constant in mathematics, an infinite acyclic decimal number, and an transcendental number, and has a value of about 2.71828.
S01.2, initializing parameters and preprocessing data, and firstly, carrying out penetration thresholdSet to 0.5.
S02, analyzing the drift diameter coefficient:
to be provided withTo C1The analysis of the drift diameter coefficient of (a) is taken as an example,to C2,To C3,To CjThe analysis of the drift diameter coefficient is similar. The method comprises the following specific steps:
s02.1, establishing a normal equation set:
suppose the first intermediate node environmental state C after processing1Corresponding leaf node C11,C12,……,C1n1The normalized data isCorresponds to C1Data of (a) is y1Then the normal equation is:
s02.1.1, calculating a single correlation coefficient:
In the formula:is composed ofAndthe sum of the products of (a) and (b),is composed ofAndthe sum of the products of (a) and (b),is composed ofThe sum of the squares of (a) and (b),is composed ofThe sum of the squares of (a) and (b),is composed ofThe sum of squares of.
S02.1.2 normal equations are set up:
s02.2, calculating a drift diameter coefficient: solving the above equation system yields:
s02.3, drawing a drift diameter map:
only one sketch is drawn due to the excessive number of elements, as in fig. 2;
s02.3, calculating an indirect drift diameter coefficient:
s02.3.1 Water resource per capita C11To ambient state C1Calculating the coefficients of all indirect drift diameters;
s02.3.1.1 Water resource per capita C11Through the per capita cultivated land area C12To the environmental state C1The indirect drift diameter coefficient is as follows:;
s02.3.1.2 Water average Water resource amount C11By passingFor yield C1The indirect path diameter coefficient of (2):;
s02.3.2 calculation of CijCalculation of respective indirect path coefficients
S02.4, judging the influence of the drift diameter coefficient:
and (4) making the direct drift diameter coefficient and the indirect drift diameter coefficient into a drift diameter coefficient analysis list.
And C1Can be decomposed into the independent variable pair C1The direct path coefficient and the indirect path coefficient of (a), namely:;
S02.4.1、C1ito C1Judging the influence:
according toThe influence is judged according to the magnitude of the influence. Due to C1iThere is a correlation between r1The order of the magnitude of the influence does not truly reflect the influence of the independent variable.
S02.4.2, judging from the direct path coefficient:
according toThe single correlation coefficient and the direct path coefficient may be in different orders. Thus C in the single correlation coefficient and direct path coefficient1iTo C1The order of magnitude of the influence does not completely reflect the influence of the independent variable.
S02.4.3, comprehensive judgment:
we can get the followingAndcarry out comprehensive judgment, C1iTo C1The comprehensive influence is as follows:
s02.5, determining coefficient analysis:
s02.5.1 calculating the decision coefficient:
s02.5.1.1, calculating a single independent variable C1iTo C1Coefficient of determination of
Single independent variable C1iTo C1To determine the coefficientsThe calculation formula and the calculation method are as follows:;
s02.5.1.2 calculating two independent variables C1j、C1iTo C1The determination coefficient of (2):
two independent variable pairs C1To determine the coefficientsThe calculation formula and the calculation method are as follows:;
s02.5.2, determining coefficient analysis:
s02.5.2.1 evaluation of the results of the diameter analysis:
if it is notIt is shown that the analysis of the drift diameter already includes the main relevant traits, and the analysis result can express the relationship between the traits. If it is notThe difference from 1 is large, which indicates that the main relevant characters are lost in the path analysis. Therefore, it is necessary to search again for the relevant traits, i.e., the index layer elements, refine the data, and return to S1 after refining the data.
S03, the rest CjiTo CjComprehensive influence(j =1,2,3 …) can be calculated similarly, and CjInfluence on C(j =1,2,3 …) may also be calculated similarly.
S04, establishing a Bayesian network model:
s04.1, analyzing the decision coefficient, and then selecting CjiTo CjC80% before the comprehensive influencejiAnd adding them into the Bayesian network as leaf nodes;
s04.2, according to actual conditions, CjiTo CjThe combined influence may be positive or negative;
hypothesis CjiThe maximum value of the previously occurring data isMinimum value of,CjiIs the current data of;
s04.3, selecting an index capable of seeping to a target layer from the indexes which are not added into the Bayesian network:
if it is notThen, the index CjiCan seep to the standard layer CjThen all the indexes C capable of seeping into the criterion layer are calculatedjiIs/are as followsSize of (1), before takingAnd (rounding) the energy can seep to the target layer resource type city ecological safety early warning. They are then added to the bayesian network.
S04.4, converting the decision coefficient into a conditional probability:
and obtaining the Bayesian network model.
S05, use of a Bayesian network model:
s05.1, decision making analysis after events:
s05.1.1, inputting the data of the target layer and converting the data into corresponding probability:
where x is the current data, xmax,xminThe current data is maximum and minimum;
s05.1.2, obtaining the probability corresponding to the criterion through Bayes network, thereby obtaining the posterior probability of each index of the target layer, analyzing the posterior probability of each index, and proposing scheme measures based on the posterior probability.
S05.2 was used to predict:
s05.1.1, judging whether the indexes capable of seeping to the target layer are all in the Bayesian network or not, and if not, adding the indexes into the Bayesian network.
S05.1.2, the conditional probability of the criterion layer and the conditional probability of the target layer resource type city ecological safety early warning are obtained in sequence by utilizing the Bayesian network model.
S06, judging whether the expected effect is achieved, if not, increasing the seepage force, namely reducing the size of the seepage threshold; if the desired effect is achieved, the algorithm ends.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A resource type city ecological safety early warning method is characterized in that: the method comprises the following steps: s1, determining that the root node of the Bayesian network is a resource type city ecological safety early warning C; determining intermediate nodes Cj of the bayesian network, comprising: environmental status C1, ecological safety stress C2, and ecological risk immunocompetence C3; the intermediate node Cj comprises at least one leaf node Cji;
s2, analyzing the path coefficient and the decision coefficient of the Cji to the Cj;
s3, establishing a Bayesian network model according to the path coefficient and the decision coefficient obtained in the step S2;
the method for establishing the Bayesian network model comprises the following steps of:
s301, analyzing the decision coefficient, and then selecting Cji of which 80% of the Cji has the comprehensive influence on the Cj and adding the Cji into a Bayesian network as a leaf node;
s302, judging whether the Cji has influence on the Cj or not, and determining the prior probability of the Cji according to the positive and negative of the Cji on the Cj;
s303, selecting an index which can seep to a target layer from indexes which are not added into the Bayesian network, and adding the index into the Bayesian network;
s304, converting the decision coefficient into a conditional probability to obtain a Bayesian network model;
s4, judging whether the Bayesian network model established in the step S3 achieves the expected effect, if so, carrying out safety early warning according to the obtained Bayesian network model, otherwise, re-analyzing and determining the coefficient after adjusting the data seepage force of each node;
the method for establishing whether the Bayesian network model achieves the expected effect comprises the following steps: s401, obtaining posterior probabilities of all indexes of a target layer by using the Bayesian network model established in the step S3, and sequentially obtaining conditional probabilities of a criterion layer and a target layer resource type city ecological safety early warning by using the Bayesian network model;
s402, judging whether the expected effect is achieved according to the posterior probability of each index and the conditional probability of the target layer resource type city ecological safety early warning.
2. The resource-based urban ecological safety precaution method according to claim 1, characterized in that: step S2 preprocesses the data of each node before analyzing the path coefficient and the decision coefficient of Cj for Cj.
3. The resource-based urban ecological safety precaution method according to claim 2, characterized in that: the method for preprocessing the data of each node comprises the following steps: cleaning data, filling null values and standardizing data from 0 to 1;
parameters and data after preprocessing were initialized, and the percolation threshold was first set to 0.5.
4. The resource-based urban ecological safety precaution method according to claim 1, characterized in that: the analysis of the path coefficient in step S2 includes the steps of: s201, establishing a normal equation set;
s202, calculating a drift diameter coefficient according to a normal equation set;
s203, drawing a drift diameter map according to the drift diameter coefficient obtained in the step S202, and calculating an indirect drift diameter coefficient according to the drift diameter map;
and S204, judging the influence of the Cji on the Cj according to the drift diameter coefficient and the indirect drift diameter coefficient.
5. The method of claim 4, wherein the method comprises the following steps: the analysis of the decision coefficient in step S3 includes the steps of: s205, calculating a decision coefficient of a single independent variable Cji to Cj;
s206, calculating decision coefficients of two independent variables Cji1 and Cji2 on Cj;
s207, determining coefficient analysis is completed according to the values, if so, the main relevant characters are included in the path analysis, the analysis result can express the relation among the characters, and the step S3 is entered, otherwise, the step S201 is entered after the data of each node is perfected again.
6. The utility model provides a device of ecological safety precaution in resource type city which characterized in that: the method comprises the following steps: a memory for storing executable instructions;
a processor for executing the executable instructions stored in the memory to implement the method of resource-based urban ecological security warning as claimed in claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010370172.3A CN111260264B (en) | 2020-05-06 | 2020-05-06 | Resource type city ecological safety early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010370172.3A CN111260264B (en) | 2020-05-06 | 2020-05-06 | Resource type city ecological safety early warning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111260264A CN111260264A (en) | 2020-06-09 |
CN111260264B true CN111260264B (en) | 2020-10-30 |
Family
ID=70955203
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010370172.3A Active CN111260264B (en) | 2020-05-06 | 2020-05-06 | Resource type city ecological safety early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111260264B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101145397B1 (en) * | 2011-06-09 | 2012-05-15 | 목포대학교산학협력단 | Red tide blooms prediction method using fuzzy reasoning and naive bayes classifier |
CN104361418A (en) * | 2014-12-05 | 2015-02-18 | 北京师范大学 | Watershed water ecological security monitoring pre-warning platform and watershed water ecological security monitoring pre-warning method |
CN105184427A (en) * | 2015-10-23 | 2015-12-23 | 石河子大学 | Method and device for early warning of farmland ecological environment |
CN105224772A (en) * | 2015-11-04 | 2016-01-06 | 松辽流域水资源保护局松辽流域水环境监测中心 | A kind of Nenjiang representative region Ecology methods of risk assessment based on system dynamics decision model |
CN105243503A (en) * | 2015-10-19 | 2016-01-13 | 上海海洋大学 | Coastal zone ecological safety assessment method based on space variables and logistic regression |
CN105303007A (en) * | 2015-12-04 | 2016-02-03 | 松辽流域水资源保护局松辽流域水环境监测中心 | Method for building Nierji reservoir water ecological risk early warning model through fusion technology |
CN105956390A (en) * | 2016-04-27 | 2016-09-21 | 重庆交通大学 | Ecological safety early-warning and evaluating visualization system and method |
CN106650182A (en) * | 2015-10-27 | 2017-05-10 | 武汉大学 | Index selection based drainage area ecological safety evaluation method |
CN106845511A (en) * | 2016-11-16 | 2017-06-13 | 吉林大学 | A kind of network space-time monitoring method based on group management loading |
CN107194610A (en) * | 2017-06-16 | 2017-09-22 | 北京师范大学 | Urban ecological safety evaluation method based on configuration process functional mode |
CN107271405A (en) * | 2017-06-30 | 2017-10-20 | 中国水利水电科学研究院 | A kind of water quality parameter retrieving concentration method and apparatus of multi-model collaboration |
CN107480889A (en) * | 2017-07-10 | 2017-12-15 | 辽宁省环境科学研究院 | A kind of Wetland Ecology Safety warning grade assessment method |
CN108364432A (en) * | 2018-02-22 | 2018-08-03 | 海南师范大学 | A kind of littoral zone early warning system |
CN108470221A (en) * | 2018-02-07 | 2018-08-31 | 中国水利水电科学研究院 | The prediction technique and device of Watershed Runoff |
CN108876167A (en) * | 2018-06-27 | 2018-11-23 | 南京林业大学 | A kind of seashore wetland ecological security assessment method based on DPSIR model |
CN109858692A (en) * | 2019-01-25 | 2019-06-07 | 广西财经学院 | A kind of Land ecological warning grade assessment method |
CN110175371A (en) * | 2019-05-08 | 2019-08-27 | 汪少华 | A kind of greening residue theoretical amount statistical calculation method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10353973B2 (en) * | 2016-08-19 | 2019-07-16 | Flipboard, Inc. | Domain ranking for digital magazines |
CN107885909A (en) * | 2017-10-18 | 2018-04-06 | 中国水利水电科学研究院 | A kind of weight of water quality remote sensing multi-model collaboration inverting assembles optimization method and device |
CN107909247A (en) * | 2017-10-26 | 2018-04-13 | 东南大学 | A kind of city macroscopic view Road Traffic Safety Factors analysis method based on spatial level Bayesian model |
CN110610293A (en) * | 2019-08-13 | 2019-12-24 | 中国人民解放军国防科技大学 | Marine environment risk assessment method based on improved Bayesian network |
-
2020
- 2020-05-06 CN CN202010370172.3A patent/CN111260264B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101145397B1 (en) * | 2011-06-09 | 2012-05-15 | 목포대학교산학협력단 | Red tide blooms prediction method using fuzzy reasoning and naive bayes classifier |
CN104361418A (en) * | 2014-12-05 | 2015-02-18 | 北京师范大学 | Watershed water ecological security monitoring pre-warning platform and watershed water ecological security monitoring pre-warning method |
CN105243503A (en) * | 2015-10-19 | 2016-01-13 | 上海海洋大学 | Coastal zone ecological safety assessment method based on space variables and logistic regression |
CN105184427A (en) * | 2015-10-23 | 2015-12-23 | 石河子大学 | Method and device for early warning of farmland ecological environment |
CN106650182A (en) * | 2015-10-27 | 2017-05-10 | 武汉大学 | Index selection based drainage area ecological safety evaluation method |
CN105224772A (en) * | 2015-11-04 | 2016-01-06 | 松辽流域水资源保护局松辽流域水环境监测中心 | A kind of Nenjiang representative region Ecology methods of risk assessment based on system dynamics decision model |
CN105303007A (en) * | 2015-12-04 | 2016-02-03 | 松辽流域水资源保护局松辽流域水环境监测中心 | Method for building Nierji reservoir water ecological risk early warning model through fusion technology |
CN105956390A (en) * | 2016-04-27 | 2016-09-21 | 重庆交通大学 | Ecological safety early-warning and evaluating visualization system and method |
CN106845511A (en) * | 2016-11-16 | 2017-06-13 | 吉林大学 | A kind of network space-time monitoring method based on group management loading |
CN107194610A (en) * | 2017-06-16 | 2017-09-22 | 北京师范大学 | Urban ecological safety evaluation method based on configuration process functional mode |
CN107271405A (en) * | 2017-06-30 | 2017-10-20 | 中国水利水电科学研究院 | A kind of water quality parameter retrieving concentration method and apparatus of multi-model collaboration |
CN107480889A (en) * | 2017-07-10 | 2017-12-15 | 辽宁省环境科学研究院 | A kind of Wetland Ecology Safety warning grade assessment method |
CN108470221A (en) * | 2018-02-07 | 2018-08-31 | 中国水利水电科学研究院 | The prediction technique and device of Watershed Runoff |
CN108364432A (en) * | 2018-02-22 | 2018-08-03 | 海南师范大学 | A kind of littoral zone early warning system |
CN108876167A (en) * | 2018-06-27 | 2018-11-23 | 南京林业大学 | A kind of seashore wetland ecological security assessment method based on DPSIR model |
CN109858692A (en) * | 2019-01-25 | 2019-06-07 | 广西财经学院 | A kind of Land ecological warning grade assessment method |
CN110175371A (en) * | 2019-05-08 | 2019-08-27 | 汪少华 | A kind of greening residue theoretical amount statistical calculation method |
Non-Patent Citations (3)
Title |
---|
"应用贝叶斯网络对冀北山区森林健康预警";卞西陈;《中国优秀硕士学位论文全文数据库 农业科技辑》;20120915(第09期);第D049-14页 * |
"海岛城市化过程中的生态安全动态评价与驱动力分析———以平潭岛为例";高升 等;《生态学报》;20180104;第38卷(第7期);第2503-2511页 * |
Long-lead Term Precipitation Forecasting by Hierarchical Clustering-based Bayesian Structural Vector Autoregression;Kaixun Hua 等;《2016 IEEE 13th International Conference on Networking, Sensing, and Control》;20160430;第1-6页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111260264A (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liang et al. | A novel wind speed prediction strategy based on Bi-LSTM, MOOFADA and transfer learning for centralized control centers | |
CN101354757B (en) | Method for predicting dynamic risk and vulnerability under fine dimension | |
Yue-Ju et al. | Soil quality assessment using weighted fuzzy association rules | |
Liao et al. | A neighbor decay cellular automata approach for simulating urban expansion based on particle swarm intelligence | |
Jalalkamali | Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters | |
Zhang et al. | The uncertainty of probabilistic rough sets in multi-granulation spaces | |
CN107133686A (en) | City-level PM2.5 concentration prediction methods based on Spatio-Temporal Data Model for Spatial | |
CN114445634A (en) | Sea wave height prediction method and system based on deep learning model | |
Lin et al. | Air quality forecasting based on cloud model granulation | |
Touqeer et al. | Multi-attribute decision making using grey relational projection method based on interval type-2 trapezoidal fuzzy numbers | |
CN115221793A (en) | Tunnel surrounding rock deformation prediction method and device | |
Maleki et al. | Z-numbers based novel method for assessing groundwater specific vulnerability | |
Li et al. | Expert knowledge-driven Bayesian network modeling for marine disaster assessment under the small sample condition | |
CN111260264B (en) | Resource type city ecological safety early warning method and device | |
Yang et al. | Dynamic three-way multi-criteria decision making with basic uncertain linguistic information: A case study in product ranking | |
CN110109904B (en) | Environment-friendly big data oriented water quality soft measurement method | |
CN117236687A (en) | Port water pollution risk assessment method based on Bayesian network and risk matrix | |
Hart et al. | Accuracy and power analysis of social networks built from count data | |
CN114595764A (en) | Method and system for acquiring influence degree of urban factors on inland inundation disaster loss | |
Luo et al. | Analysis and research on sustainable development factors of the sports industry based on chaos theory | |
Mishra et al. | Hydro-geochemical attributes based classifiers for groundwater analysis | |
CN108364136B (en) | Water resource shortage risk analysis method and system based on evidence reasoning | |
Jain et al. | Water scarcity prediction for global region using machine learning | |
Liu et al. | A prediction method of urban water pollution based on improved BP neural network | |
Vagin et al. | Modelling human reasoning in intelligent decision support systems |
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 |