CN113505948A - Future ecological security pattern prediction and optimization method based on Bayesian network - Google Patents
Future ecological security pattern prediction and optimization method based on Bayesian network Download PDFInfo
- Publication number
- CN113505948A CN113505948A CN202111065542.3A CN202111065542A CN113505948A CN 113505948 A CN113505948 A CN 113505948A CN 202111065542 A CN202111065542 A CN 202111065542A CN 113505948 A CN113505948 A CN 113505948A
- Authority
- CN
- China
- Prior art keywords
- ecological
- land
- bayesian network
- pattern
- model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000005457 optimization Methods 0.000 title claims abstract description 28
- 238000011161 development Methods 0.000 claims abstract description 24
- 230000001413 cellular effect Effects 0.000 claims abstract description 18
- 238000011160 research Methods 0.000 claims abstract description 17
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 230000007246 mechanism Effects 0.000 claims abstract description 9
- 238000009826 distribution Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 239000002689 soil Substances 0.000 claims description 11
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 7
- 229910052799 carbon Inorganic materials 0.000 claims description 7
- 230000009919 sequestration Effects 0.000 claims description 7
- 238000010206 sensitivity analysis Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 description 12
- 241000282414 Homo sapiens Species 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010276 construction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002609 medium Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013316 zoning Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention discloses a Bayesian network-based future ecological security pattern prediction and optimization method, wherein the prediction method comprises the following steps: s1, establishing a geographic information basic database of a research area; s2, setting an ecosystem service, and constructing a Bayesian network model for predicting an ecological security pattern; s3, forecasting various land requirements under the natural development scene by using a Markov model; s4, measuring land use development potential by using a mixed cellular CA model; s5, land use pattern prediction is carried out on the basis of a land type competition and quantitative conversion mechanism of the mixed cellular CA model; and S6, inputting the land utilization data into an ecological safety pattern prediction model to predict future ecological safety patterns. The method solves the problem of factor uncertainty in the prediction of the ecological safety pattern, and improves the reliability of research results.
Description
Technical Field
The invention relates to the technical field of ecological prediction, in particular to a future ecological security pattern prediction and optimization method based on a Bayesian network.
Background
Ecological safety is based on human being, and can protect resources necessary for human production and life in social development and maintain the safe state of harmonious and stable development of human society. The ecological safety pattern is an important means and a basic guarantee for regulating and managing ecological safety, and reasonable and effective spatial connection and configuration optimization are carried out on the key ecological elements through predicting existing or potential points, lines, surfaces and the like which have important significance for maintaining the ecological process and ecological safety of the area, so that the basic spatial pattern which can guide reasonable expansion of a city, guarantee the structure and functions of natural resources of the area, realize high harmony of human beings and ecological environment and improve the overall ecological safety level of the area is constructed. The prediction and optimization of the ecological safety pattern provide an effective way for solving the problems existing in the current regional ecological safety construction and realizing the ecological protection and restoration of the homeland space, and currently become the key points of the academic world and the attention of the decision-making departments of the government of China.
The prediction method of the ecological safety pattern has no unified standard at present, different scholars propose different ecological safety pattern prediction methods based on different subject backgrounds, and the prediction methods are mainly divided into a multi-element comprehensive overlapping construction method, a cellular automaton model and a source ground-resistance surface-corridor combined mode. The comprehensive multi-element superposition construction method is based on each individual ecological element, weights are set for the ecological safety pattern layers of the single elements according to importance levels, and the ecological safety patterns of the research area are constructed by superposition. The cellular automata model is constructed by the joint analysis of spatial data and a spatial model to generate a dynamic security pattern. The source ground-resistance surface-corridor combined mode is used for constructing an ecological safety pattern by predicting the ecological source ground of an area, setting a resistance surface, predicting an ecological corridor and other key steps. Although the method achieves certain achievements in predicting and optimizing the ecological security pattern, the construction of the ecological security pattern is mostly carried out by adopting a static visual angle and based on the current ecological red line, a natural protection area and the like, and whether the currently evaluated ecosystem service is related to the development of ten years or more in the future or not is difficult to judge. And uncertainty of dynamic changes of various biological environment factors and social environment factors along with time is not considered in the prediction of the ecological safety pattern, so that the accuracy and reliability of results are difficult to ensure. In addition, the previous optimization aiming at the ecological safety pattern is only optimized aiming at a land utilization factor, the influence of the space configuration on the ecological process by considering factors such as land, soil, air temperature, rainfall, vegetation coverage and the like is neglected, and the problem is to be solved in the research.
Disclosure of Invention
The invention aims to overcome one or more defects in the prior art and provide a future ecological security pattern prediction and optimization method based on a Bayesian network.
The purpose of the invention is realized by the following technical scheme: the future ecological security pattern prediction and optimization method based on the Bayesian network comprises the following steps:
s1, establishing a geographic information basic database of a research area;
s2, setting an ecosystem service, and constructing a Bayesian network model for predicting an ecological security pattern;
s3, forecasting various land requirements under the natural development scene by using a Markov model;
s4, measuring land use development potential by using a mixed cellular CA model;
s5, land use pattern prediction is carried out on the basis of a land type competition and quantitative conversion mechanism of the mixed cellular CA model;
and S6, predicting the future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction.
Preferably, the geographic information base database includes land use data, nighttime light image data, ground meteorological data, soil data, terrain data, traffic data, river data, normalized vegetation index data, net primary productivity data, and national administrative maps.
Preferably, the ecosystem services include carbon sequestration, water conservation, food supply, habitat quality and water and soil conservation.
Preferably, constructing a bayesian network model for ecological security pattern prediction comprises:
s21, discretizing the selected grid image layer of the node variable by adopting a natural breakpoint method based on ArcGIS software;
s22, extracting the value of the discretized raster image layer to a single raster data layer to obtain sample point data;
s23, dividing the sample point data into a training set and a test set;
and S24, constructing a Bayesian network model, and training the Bayesian network model by using a training set.
Preferably, the formula of the markov model is as follows:
wherein,represents the land typet+1The state vector of the time of day,represents the land typetThe state vector of the time of day,representing land classes for state transition probability matricesiTransfer to land speciesjAnd is a probability of,。
Preferably, the S6 includes:
s61, identifying key factors influencing the ecosystem service by using sensitivity analysis;
s62, identifying the maximum probability state of the key factor according to the probability distribution of the network nodes in the Bayesian network model and the conditional probability table;
s63, obtaining a spatial distribution pattern of the ecosystem service under a future scene according to superposition of the maximum probability state of the key factors;
and S64, identifying a future ecological safety pattern according to the spatial distribution pattern of the ecosystem service under the future scene.
The optimization method of the future ecological security pattern based on the Bayesian network comprises the following steps:
K1. establishing a geographic information basic database of a research area;
K2. setting an ecosystem service, and constructing a Bayesian network model for predicting an ecological security pattern;
K3. forecasting various land requirements under a natural development scene by using a Markov model;
K4. using a mixed cellular CA model to measure the land development potential;
K5. land use pattern prediction is carried out on the basis of land use type competition and quantitative conversion mechanisms of the mixed cellular CA model;
K6. predicting a future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction;
K7. partitioning future ecological security patterns, defining an area with the highest ecological system service level as an ecological protection priority area, and defining an area with the lowest ecological system service level as an ecological optimization area;
K8. and protecting an ecological system of the ecological priority area, and performing ecological restoration on the ecological optimization area.
The invention has the beneficial effects that:
(1) the ecological safety pattern prediction and optimization method provided by the invention solves the problem of factor uncertainty in ecological safety pattern prediction on one hand, and improves the reliability of research results; on the other hand, by identifying the state with the maximum probability of the key factors influencing the ecological security pattern, the spatial configuration of the factors when the ecological system service is in different states can be known, reference is provided for optimizing the ecological security pattern, and the purpose of optimizing the ecological security pattern by comprehensively considering the state combination of all the influencing factors is achieved;
(2) according to the invention, an open decision support tool is constructed by coupling a land utilization model and a Bayesian network, so that the structure is flexible and the universality is strong;
(3) according to the ecological safety pattern prediction method, the Bayesian network model is used for predicting the ecological safety pattern, so that the ecological safety pattern under the conditions of insufficiency, incompleteness and uncertainty can be inferred, the uncertainty of environmental factor change can be expressed through the conditional probability table, the causal relationship among all the influence factors can be effectively expressed, and the reliability and the accuracy of research results are improved;
(4) the invention integrates various ecosystem services into one Bayesian network, not only can detect the influence of factor change on different ecosystem service changes, but also can judge the interaction among the ecosystem services in the network and the spatial distribution of various ecosystem service state combinations, and is the basis for identifying important ecological land and constructing ecological safety patterns;
(5) the method constructs a future land utilization scene from the perspective of the composite functional body, and supposes that each land utilization unit is a mixed structure containing multiple land utilization types, so that a simulation result is more in line with the actual land utilization condition;
(6) the invention comprehensively considers the influence of the combination change of the influence factor states on the ecosystem service, and further provides an effective ecosystem service optimization scheme by referring to the optimal factor combination condition, thereby providing a new visual angle for making ecological protection and restoration measures for governments and related departments.
Drawings
FIG. 1 is a flow chart of a Bayesian network-based future ecological security pattern prediction method;
FIG. 2 is a schematic diagram of a Bayesian concept network;
FIG. 3 is a schematic diagram of a Bayesian network model;
FIG. 4 is a schematic diagram of a Bayesian network model modeling process;
FIG. 5 is a schematic diagram of an area of interest for ecological security pattern prediction and ecological security pattern optimization in a future scenario;
fig. 6 is a flowchart of a future ecological security pattern optimization method based on a bayesian network.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood 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 obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
Referring to fig. 1 to 6, the present embodiment takes the south-chuan economic area of sichuan province as an example, and provides a future ecological security pattern prediction and optimization method based on bayesian network:
as shown in fig. 1, a method for predicting and optimizing future ecological security patterns based on a bayesian network includes:
s1, establishing a geographic information basic database of a research area.
Generally, the process of establishing the geographic information basic database of the research area is as follows: the method comprises the steps of obtaining land utilization data, night light image data, ground meteorological data (air temperature, precipitation, evapotranspiration, solar radiation and the like), soil data, terrain data, traffic data, river data, normalized vegetation index data (NDVI), net primary productivity data (NPP) and national administrative zoning maps (city level and county level), and establishing a geographic information basic database of a research area based on the data.
And S2, setting an ecosystem service and constructing a Bayesian network model for predicting the ecological security pattern.
The ecosystem clothes link the natural ecosystem process with human welfare and are effective indexes for quantitatively evaluating ecological safety and sustainability. According to regional resource environmental conditions and social economic activities, carbon sequestration, water conservation, grain supply, habitat quality and water and soil conservation are selected as main ecological system services of the region.
Specifically, the method for constructing the Bayesian network model for predicting the ecological security pattern comprises the following steps:
and S21, carrying out discretization processing on the selected grid image layer of the node variable by adopting a natural discontinuous point method based on ArcGIS software.
And S22, extracting the value of the discretized raster image layer to a single raster data layer to obtain sample point data.
And S23, dividing the sample point data into a training set and a test set.
And S24, constructing a Bayesian network model, and training the Bayesian network model by using a training set.
For example, randomly dividing the sample points into 80% training set and 20% testing set, wherein 80% of the training set is used for model training, obtaining probability distribution and conditional probability table (as shown in fig. 3) for establishing all network nodes in the bayesian network model (as shown in fig. 2), and the specific modeling process is shown in fig. 4.
The Bayesian network model predicts future ecological safety patterns based on prior knowledge and observation data, and expresses uncertainty of land utilization and environmental change under different scenes through a conditional probability table, so that reliability of research results is improved; meanwhile, the condition of the selected ecosystem service in the research area can be comprehensively analyzed, and important ecological land is identified according to the interaction relationship among the ecosystem services and the influence of factor change on different ecosystem services, so that the prediction of the ecological safety pattern is realized.
In order to evaluate the prediction capability of the Bayesian network model on the ecological security pattern, parent nodes in 20% test sets which are randomly divided are input, corresponding child nodes are predicted, and the prediction accuracy of the Bayesian network model is evaluated by using a confusion matrix. After the accuracy inspection meets the requirements, the ecological system service under the future situation can be predicted, and the ecological safety pattern of the research area is further identified. The evaluation results show that the overall accuracy of carbon sequestration, grain supply, water conservation, habitat quality and water and soil conservation is 77.48%, 75.48%, 76.50%, 84.04% and 75.69% respectively, which indicates that the model accuracy meets the prediction requirements of ecological safety patterns under different situations.
And S3, forecasting various land requirements under the natural development situation by utilizing the Markov model.
The Markov (Markov) model is based on the condition of no-after-effect assumption, and the region unit state at the time t +1 only depends on the region unit state at the time t, and the scheme of the embodiment utilizes the Markov model to acquire the region unit requirements under different scenes. The calculation formula of the Markov model is as follows:
wherein,represents the land typet+1The state vector of the time of day,represents the land typetThe state vector of the time of day,representing land classes for state transition probability matricesiTransfer to land speciesjAnd is a probability of,。
And S4, measuring the land development potential by using a mixed cell CA model.
And S5, carrying out land use pattern prediction based on a land use type competition and quantitative conversion mechanism of the mixed cellular CA model. Namely, land use patterns under natural development scenes are predicted by using land type competition and quantitative conversion mechanisms of the mixed cellular CA model based on various land use requirements and land use development potentials.
Specifically, the land use development potential is measured by using a random forest algorithm, a mapping relation between the land use development and the driving factors with high contribution is mined, so that a historical rule that various different driving force factors influence each land use change is obtained, and a calculation formula is shown in a formula (2).
In the formula,Ais the selected drive factor;Sis a division of a data setA boundary point;is thatiTraining sample independent variable data for the epoch;is dependent variable data of the training sample in the i period;are respectively a data setThe sample mean of (1).
The land type competition and quantitative conversion mechanism adjusts the change direction of each land type through a driving coefficient on one hand, and comprehensively considers the influence of the sub-cellular scale, the neighborhood scale and the region scale on the other hand, constructs a roulette rule to simulate the increase of each region unit in each iteration and the reduction of other land utilization. And performing RGB (red, green and blue) synthetic display on different wave bands by using ArcGIS software in a land utilization pattern. The core idea of the mixed cellular CA model is that the land utilization unit is considered to be a mixed unit consisting of a plurality of land utilization types, and land utilization competition and transformation on the sub-cellular scale are considered so as to simulate structural change inside the land utilization unit. The embodiment utilizes the mixed cellular CA model to measure the land use development potential, and compared with the traditional CA model, the land use situation and the multifunctional concept of land use can be reflected more truly. Moreover, for the land types with small demand change, the mixed cellular CA model can simulate the slight change of the land types, and the accuracy and the reliability of the simulation result are improved.
In this embodiment, multiple ecosystem services are integrated into one bayesian network, so that not only the influence of factor change on different ecosystem service changes is detected, but also the interaction between ecosystem services in the network and the spatial distribution of multiple ecosystem service state combinations can be judged.
And S6, predicting the future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction.
The S6 includes:
and S61, identifying key factors influencing the ecosystem service by using sensitivity analysis.
The sensitivity analysis can identify key factors (VB > 0.1) influencing the ecosystem service by analyzing the sensitivity of each variable in the model to the change of the target variable, and the analysis result is shown in Table 1.
And S62, identifying the maximum probability state of the key factor according to the probability distribution of the network nodes in the Bayesian network model and the conditional probability table.
The maximum probability states of the key factors affecting the ecosystem services are shown in table 2.
And S63, obtaining the spatial distribution pattern of the ecosystem service under the future situation according to the superposition of the maximum probability state of the key factors.
And S64, identifying a future ecological safety pattern according to the spatial distribution pattern of the ecosystem service under the future scene.
When all the ecosystem services are in the same level, the capacity of providing multiple ecosystem services in an area with a relationship of low balance and high cooperation among the ecosystem services can be embodied, and the method has important significance for maintaining regional ecological safety and sustainable development and constructing a regional ecological safety pattern. Therefore, in the embodiment, it is defined that 'i = { carbon sequestration = Highest, grain supply = Highest, water and soil conservation = Highest, habitat quality = Highest, water conservation = Highest }, ii = { carbon sequestration = Medium, grain supply = Medium, water and soil conservation = Medium, habitat quality = Medium, water conservation = Medium }, iv = { carbon sequestration = Low, water and soil conservation = Low, habitat quality = Low }' and the ecosystem service corresponding to the four subsets is analyzed, the state of the Highest probability of the ecological factors corresponding to the subsets i, ii, iii, iv is subjected to stacking analysis, the spatial distribution of the subsets i, ii, iii, iv is identified as a safety region 5, as shown in fig. 5. The results show that in the natural development scenario, the area ratio of the subsets i, ii, iii, iv is 2.76%, wherein the subsets i, ii are mainly distributed in south yibin, south luzhou and east, and the subsets iii, iv are mainly distributed in south yibin and north east luzhou.
As shown in fig. 6, the method for optimizing future ecological security pattern based on bayesian network includes:
K1. and establishing a geographic information basic database of the research area.
K2. And setting an ecosystem service, and constructing a Bayesian network model for predicting the ecological security pattern.
K3. And forecasting various land requirements under the natural development scene by using the Markov model.
K4. The mixed cell CA model was used to measure the development potential.
K5. Land use pattern prediction is carried out on the basis of land use type competition and quantitative conversion mechanisms of the mixed cellular CA model.
K6. And predicting the future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction.
K7. And partitioning the future ecological security pattern, defining the area with the highest ecological system service level as an ecological protection priority area, and defining the area with the lowest ecological system service level as an ecological optimization area.
K8. And protecting an ecological system of the ecological priority area, and performing ecological restoration on the ecological optimization area.
The subsets I and IV are used as areas with the highest and lowest service levels of the ecosystem and are important areas for optimizing the ecological safety pattern. Based on the partition management principle, the subset I and the subset IV are respectively defined as an ecological protection priority area and an ecological optimization area, and the role positioning of the subset I and the subset IV is a core protection area and a key restoration area supplied by the services of an ecological system. The ecological protection priority area should pay attention to the maintenance of the ecological environment and implement strict ecological system protection. And the management of the ecological optimization area tries to start from optimizing the spatial configuration of the key factors, make and implement the state of the relevant measure optimization factors, and make the spatial combination of the key factors tend to the optimal configuration, thereby realizing the ecological restoration of the ecological optimization area.
The factors that have the greatest impact on ecosystem service were found from sensitivity analysis to be NPP, grade, forest land area ratio, and evapotranspiration. And then, according to the conditional probability table and the probability distribution of the nodes, the combination characteristics and the spatial distribution of the key factor probability maximum state in the distribution regions of the subset I and the subset IV are determined. The result shows that the subset I is mainly distributed in areas with high NPP, high gradient, high forest land area occupation and low evapotranspiration, and the subset IV is characterized by low NPP, low gradient, low forest land area occupation and high evapotranspiration, so that the division of the north area of Jiang 'an county, the middle area of Jiang' an county, the Hejiang county and the Luzhou junction area of the Yibin city is finally determined as a key optimization area. The border areas of the ancient Chinese iris county, the northeast of the XuYong county, the southeast of Hejiang county, the tribute county of Yibin city and the Xingsheng county in Luzhou city are defined as key protection areas, as shown in FIG. 5. For the subset I area, the interference of human beings on vegetation, landforms and water resources is strictly controlled, and for the subset IV area, regional ecological protection and restoration are realized by intervening NPP, forest land area ratio and evapotranspiration index optimization factor combination, such as increasing regional vegetation coverage, reducing regional population density, implementing bioengineering measures and the like.
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. The future ecological security pattern prediction method based on the Bayesian network is characterized by comprising the following steps:
s1, establishing a geographic information basic database of a research area;
s2, setting an ecosystem service, and constructing a Bayesian network model for predicting an ecological security pattern;
s3, forecasting various land requirements under the natural development scene by using a Markov model;
s4, measuring land use development potential by using a mixed cellular CA model;
s5, land use pattern prediction is carried out on the basis of a land type competition and quantitative conversion mechanism of the mixed cellular CA model;
and S6, predicting the future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction.
2. The Bayesian network-based future ecological safety pattern prediction method of claim 1, wherein the geographic information base database includes land utilization data, nighttime light image data, ground meteorological data, soil data, terrain data, traffic data, river data, normalized vegetation index data, net primary productivity data, and national administrative maps.
3. The Bayesian network-based future ecological safety pattern prediction method of claim 1, wherein the ecosystem services include carbon sequestration, water conservation, food supply, habitat quality, and water and soil conservation.
4. The Bayesian network based future ecological security pattern prediction method of claim 1, wherein constructing a Bayesian network model for ecological security pattern prediction comprises:
s21, discretizing the selected grid image layer of the node variable by adopting a natural breakpoint method based on ArcGIS software;
s22, extracting the value of the discretized raster image layer to a single raster data layer to obtain sample point data;
s23, dividing the sample point data into a training set and a test set;
and S24, constructing a Bayesian network model, and training the Bayesian network model by using a training set.
5. The Bayesian network-based future ecological security pattern prediction method of claim 1, wherein the Markov model has a calculation formula of:
6. The Bayesian network-based future ecological security pattern prediction method as recited in claim 1, wherein the S6 comprises:
s61, identifying key factors influencing the ecosystem service by using sensitivity analysis;
s62, identifying the maximum probability state of the key factor according to the probability distribution of the network nodes in the Bayesian network model and the conditional probability table;
s63, obtaining a spatial distribution pattern of the ecosystem service under a future scene according to superposition of the maximum probability state of the key factors;
and S64, identifying a future ecological safety pattern according to the spatial distribution pattern of the ecosystem service under the future scene.
7. The optimization method of the future ecological security pattern based on the Bayesian network is characterized by comprising the following steps:
K1. establishing a geographic information basic database of a research area;
K2. setting an ecosystem service, and constructing a Bayesian network model for predicting an ecological security pattern;
K3. forecasting various land requirements under a natural development scene by using a Markov model;
K4. using a mixed cellular CA model to measure the land development potential;
K5. land use pattern prediction is carried out on the basis of land use type competition and quantitative conversion mechanisms of the mixed cellular CA model;
K6. predicting a future ecological safety pattern based on the Bayesian network and the land utilization pattern obtained by prediction;
K7. partitioning future ecological security patterns, defining an area with the highest ecological system service level as an ecological protection priority area, and defining an area with the lowest ecological system service level as an ecological optimization area;
K8. and protecting an ecological system of the ecological priority area, and performing ecological restoration on the ecological optimization area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111065542.3A CN113505948B (en) | 2021-09-13 | 2021-09-13 | Future ecological security pattern prediction and optimization method based on Bayesian network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111065542.3A CN113505948B (en) | 2021-09-13 | 2021-09-13 | Future ecological security pattern prediction and optimization method based on Bayesian network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113505948A true CN113505948A (en) | 2021-10-15 |
CN113505948B CN113505948B (en) | 2021-11-19 |
Family
ID=78016734
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111065542.3A Active CN113505948B (en) | 2021-09-13 | 2021-09-13 | Future ecological security pattern prediction and optimization method based on Bayesian network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113505948B (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354757A (en) * | 2008-09-08 | 2009-01-28 | 中国科学院地理科学与资源研究所 | Method for predicting dynamic risk and vulnerability under fine dimension |
CN102323993A (en) * | 2011-09-21 | 2012-01-18 | 北京林业大学 | Method for predicting dynamic changes of shelterbelt system pattern |
CN103576164A (en) * | 2012-07-20 | 2014-02-12 | 上海莱凯数码科技有限公司 | High-resolution remote sensing image fusion method based on linear Bayesian estimation |
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 |
CN105608474A (en) * | 2015-12-30 | 2016-05-25 | 二十一世纪空间技术应用股份有限公司 | High-resolution-image-based regional adaptive cultivated land extraction method |
CN106933945A (en) * | 2017-01-20 | 2017-07-07 | 上海同济城市规划设计研究院 | Urban ecological security spatial framework model building method |
CN107767954A (en) * | 2017-10-16 | 2018-03-06 | 中国科学院地理科学与资源研究所 | A kind of Environmental Health Risk Monitoring early warning system and method based on space Bayesian network |
CN108280588A (en) * | 2018-02-08 | 2018-07-13 | 广州地理研究所 | A kind of Ecological safety pattern's construction method based on machine learning |
CN108563733A (en) * | 2018-04-09 | 2018-09-21 | 中国科学院寒区旱区环境与工程研究所 | A kind of land use data assimilation method based on Bayesian inference |
CN108920674A (en) * | 2018-07-09 | 2018-11-30 | 广州地理研究所 | A kind of Ecological safety pattern's construction method |
CN109614734A (en) * | 2018-12-21 | 2019-04-12 | 内江师范学院 | A kind of airport asphalt concrete pavement limited deformation meta-model and comparative analysis method |
CN110415346A (en) * | 2019-07-10 | 2019-11-05 | 华中师范大学 | The method for carrying out soil erosion simulation using the three-dimensional cellular automaton of object-oriented |
CN110991497A (en) * | 2019-11-15 | 2020-04-10 | 同济大学 | Urban land use change cellular automata simulation method based on BSVC (binary coded VC) method |
CN112329973A (en) * | 2020-08-20 | 2021-02-05 | 国网湖北省电力有限公司襄阳供电公司 | Space-time load prediction method based on graph neural network and regional gridding |
-
2021
- 2021-09-13 CN CN202111065542.3A patent/CN113505948B/en active Active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101354757A (en) * | 2008-09-08 | 2009-01-28 | 中国科学院地理科学与资源研究所 | Method for predicting dynamic risk and vulnerability under fine dimension |
CN102323993A (en) * | 2011-09-21 | 2012-01-18 | 北京林业大学 | Method for predicting dynamic changes of shelterbelt system pattern |
CN103576164A (en) * | 2012-07-20 | 2014-02-12 | 上海莱凯数码科技有限公司 | High-resolution remote sensing image fusion method based on linear Bayesian estimation |
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 |
CN105608474A (en) * | 2015-12-30 | 2016-05-25 | 二十一世纪空间技术应用股份有限公司 | High-resolution-image-based regional adaptive cultivated land extraction method |
CN106933945A (en) * | 2017-01-20 | 2017-07-07 | 上海同济城市规划设计研究院 | Urban ecological security spatial framework model building method |
CN107767954A (en) * | 2017-10-16 | 2018-03-06 | 中国科学院地理科学与资源研究所 | A kind of Environmental Health Risk Monitoring early warning system and method based on space Bayesian network |
CN108280588A (en) * | 2018-02-08 | 2018-07-13 | 广州地理研究所 | A kind of Ecological safety pattern's construction method based on machine learning |
CN108563733A (en) * | 2018-04-09 | 2018-09-21 | 中国科学院寒区旱区环境与工程研究所 | A kind of land use data assimilation method based on Bayesian inference |
CN108920674A (en) * | 2018-07-09 | 2018-11-30 | 广州地理研究所 | A kind of Ecological safety pattern's construction method |
CN109614734A (en) * | 2018-12-21 | 2019-04-12 | 内江师范学院 | A kind of airport asphalt concrete pavement limited deformation meta-model and comparative analysis method |
CN110415346A (en) * | 2019-07-10 | 2019-11-05 | 华中师范大学 | The method for carrying out soil erosion simulation using the three-dimensional cellular automaton of object-oriented |
CN110991497A (en) * | 2019-11-15 | 2020-04-10 | 同济大学 | Urban land use change cellular automata simulation method based on BSVC (binary coded VC) method |
CN112329973A (en) * | 2020-08-20 | 2021-02-05 | 国网湖北省电力有限公司襄阳供电公司 | Space-time load prediction method based on graph neural network and regional gridding |
Non-Patent Citations (8)
Title |
---|
HAMAD R 等: "Predicting Land Use/Land Cover Changes Using a CA-Markov Model under Two Different Scenarios", 《SUSTAINABILITY》 * |
PENG LI等: "Linking the random forests model and GIS to assess geo-hazards risk:a case study in Shifang County", 《IEEE ACCESS》 * |
周爽 等: "成都市景观格局与生态***服务的关联效应", 《山地学报》 * |
彭建 等: "区域生态安全格局构建研究进展与展望", 《地理研究》 * |
李亚丽 等: "城市元胞自动机模型的构建及其应用研究进展", 《科技导报》 * |
杨国清 等: "基于CA-Markov模型的土地利用格局变化研究", 《武汉大学学报》 * |
杨慧: "基于贝叶斯滤波的随机CA城市扩张模型研究", 《万方学术期刊数据库》 * |
陈田田 等: "基于生态***服务权衡的生态安全多情景决策", 《中国环境科学》 * |
Also Published As
Publication number | Publication date |
---|---|
CN113505948B (en) | 2021-11-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhang et al. | Land use/cover predictions incorporating ecological security for the Yangtze River Delta region, China | |
Liao et al. | Urban sprawl scenario simulations based on cellular automata and ordered weighted averaging ecological constraints | |
Zhang et al. | Simulation and analysis of urban growth scenarios for the Greater Shanghai Area, China | |
Ford et al. | A multi-scale urban integrated assessment framework for climate change studies: A flooding application | |
CN110458048A (en) | Take population distribution Spatio-temporal Evolution and the cognition of town pattern feature into account | |
CN112163367B (en) | Firefly algorithm and cellular automaton fused city expansion simulation prediction method | |
CN113505510B (en) | Ecological safety pattern recognition method fusing landscape index and random walk model | |
Liang et al. | Impacts of land management practice strategy on regional ecosystems: Enlightenment from ecological redline adjustment in Jiangsu, China | |
CN110096563A (en) | A kind of ecological network construction method based on ecology service logic coding | |
CN110543671A (en) | city safety livability modeling method based on artificial society | |
Wang et al. | Modeling urban growth by coupling localized spatio-temporal association analysis and binary logistic regression | |
Yang et al. | A multitarget land use change simulation model based on cellular automata and its application | |
Li et al. | Research on land‐use evolution and ecosystem services value response in mountainous counties based on the SD‐PLUS model | |
Nejadi et al. | Modeling Plausible Impacts of land use change on wildlife habitats, Application and validation: Lisar protected area, Iran | |
Cao et al. | A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization | |
Yu et al. | Evaluation and prediction of land use change impacts on ecosystem service values in Nanjing City from 1995 to 2030 | |
Guo et al. | Simulating urban growth by coupling macro-processes and micro-dynamics: a case study on Wuhan, China | |
Tian et al. | Suburban sprawl measurement and landscape analysis of cropland and ecological land: A case study of Jiangsu Province, China | |
Yang et al. | Spatiotemporal characteristics of human activity on coastal landscape of Laizhou Bay | |
Xi et al. | A Bayesian model for estimating the effects of human disturbance on wildlife habitats based on nighttime light data and INLA-SPDE | |
Zhang et al. | Estimating the outdoor environment of workers’ villages in East China using machine learning | |
Talebi et al. | Forest road planning to improve tourism accessibility: a comparison of different methods applied in a real case study | |
CN113505948B (en) | Future ecological security pattern prediction and optimization method based on Bayesian network | |
Stewart et al. | A Voronoi diagram based population model for social species of wildlife | |
Huang et al. | Integrating “quality-risk-demand” framework and circuit theory to identify spatial range and priority area of ecological security pattern in a rapidly urbanizing landscape |
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 |