CN-121981573-A - Intelligent regulation and control method and system for plateau forestation habitat

CN121981573ACN 121981573 ACN121981573 ACN 121981573ACN-121981573-A

Abstract

The invention provides an intelligent regulation and control method and system for a plateau forestation habitat, and belongs to the technical field of ecological intelligent regulation and control. The method comprises the steps of S1, obtaining multi-source data to construct a habitat database, quantifying target species habitat demand parameters, S2, calculating comprehensive ecological function values and species suitability indexes to identify habitat demand conflict areas, S3, designing a regulation and control scheme and pre-evaluating benefits, S4, taking multi-species overall benefit maximization and equilibrium optimization as targets, outputting an optimal scheme through a multi-target optimization algorithm, S5, obtaining feedback data through a monitoring network after implementation, comparing actual and expected benefits, and linking and correcting model parameters when deviation exceeds a threshold value to form closed-loop optimization. By adopting the intelligent control method and system for the plateau forestation habitat, dynamic accurate diagnosis and simulation optimization decision of the habitat quality are realized, a real-time feedback self-adaptive management mechanism is constructed, and diversity of the plateau beasts and birds is improved.

Inventors

SHI QI
YU QIANG
WANG YU
YANG XINYU
LIU YILIN
MA JINLING
SUN ZHE
ZHOU WANGJIAN

Assignees

北京林业大学

Dates

Publication Date: 20260505
Application Date: 20260122

Claims (10)

1. The intelligent regulation and control method for the plateau forestation habitat is characterized by comprising the following steps of: s1, acquiring multi-source data of a target area, constructing a habitat database, and interpreting and quantifying habitat demand parameters of at least two target species based on animal ecological knowledge; s2, taking a habitat database and habitat demand parameters as inputs, calculating comprehensive ecological function values of an evaluation unit, calculating potential suitability indexes of all species, and identifying a multi-species habitat demand conflict area; Step S3, designing a plurality of regulation schemes based on the multi-species habitat demand conflict area and the potential suitability index, pre-evaluating expected regulation benefits of each regulation scheme on each species, and calculating an overall synergistic benefit index; s4, optimizing each regulation scheme by utilizing a multi-objective optimization algorithm with the aim of maximizing the overall expected benefits of multiple species and optimizing the benefits among species on the basis of the expected comprehensive regulation benefits and the overall synergistic benefits indexes of each regulation scheme, and outputting an optimal habitat regulation optimization scheme; And S5, implementing an optimal habitat regulation optimization scheme, acquiring actual habitat state data through a monitoring network, calculating actual comprehensive regulation benefits, comparing the actual comprehensive regulation benefits with the expected comprehensive regulation benefits obtained in the step S3, feeding back the actual habitat state data to the step S2 and the step S3 when the deviation exceeds a threshold value, and recalculating and updating the model.
2. The intelligent control method for the highland forestation habitat of claim 1, wherein the step S1 specifically comprises: s11, collecting remote sensing data, topographic data, meteorological data, soil data and target species activity monitoring data of a target area; step S12, carrying out space-time matching and fusion on the multi-source data to construct a habitat database; step S13, interpreting and quantifying habitat requirement parameters of each species for concealment, food resources, water sources, propagation conditions and interference distance for at least two target species.
3. The intelligent control method for the highland forestation habitat of claim 1, wherein the step S2 specifically comprises: S21, dividing a research area into standard evaluation units; Step S22, calculating the comprehensive ecological function value of each evaluation unit by using an ecological function quantization model based on the constructed habitat database And each sub-function value, the calculation formula is: ; ; ; ; ; Wherein, the 、、、 The weight coefficients of four functions of water conservation, food supply, shelter hiding and breeding and young child breeding are respectively provided, Is a function value for conservation of the water source, The food is supplied with a functional value, In order to conceal the value of the shelter function, In order to reproduce the functional value of the young, Is the first The vegetation coverage of the individual evaluation units, Is the first The leaf area index of each evaluation unit, Is the first The annual precipitation of the individual evaluation units, Is the first The soil saturation water conductivity of each evaluation unit, 、、 As the weight coefficient of the light-emitting diode, Is the first Normalized vegetation index of the individual evaluation units, Is the first The herbaceous biomass of the individual evaluation units, Is the first The edible plant richness of each evaluation unit, 、、 As the weight coefficient of the light-emitting diode, Is the first The vegetation density of the individual evaluation units, Is the first The vegetation height of the individual evaluation units, Is the first The surface roughness of the individual evaluation units, 、、 As the weight coefficient of the light-emitting diode, Is the first The topography concealment of the individual evaluation units, Is the first The inverse of the distance of the individual evaluation units from the interference source, Is the first The microclimate suitability of each unit was evaluated, 、、 Is a weight coefficient; Step S23, based on the habitat demand parameters interpreted in the step S1, respectively constructing a species-specific habitat suitability model for each target species, and calculating potential suitability indexes of each species in each evaluation unit, wherein the specific process is as follows: Step S231, for target species Selecting a set of key environment variables thereof Wherein each variable corresponds to a type of habitat demand parameter in step S1, 、、 Respectively represent 1 st, 2 nd to 2 nd Specific values or types of the individual critical environmental variables; Step S232, calculating and evaluating unit Potential suitability index of (2) : ; Wherein, the In order to be an intercept term, Is the first Individual environment variables Is used for the response coefficient of (a), To be an evaluation unit Middle (f) The value of the individual environmental variable(s), As a total number of environmental variables, A base number that is a natural logarithm; step S233, adopting a maximum likelihood estimation method to respond to the coefficient based on the activity monitoring data of the target species Performing calibration; Step S234, calculating all evaluation units Normalizing the values to obtain potential suitability index distribution of the species in the whole research area; And step S24, identifying a multi-species habitat demand conflict area by comparing and analyzing suitability indexes of each species.
4. The intelligent control method for the highland forestation habitat of claim 3, wherein in the step S24, the identification of the multi-species habitat demand conflict area is realized by the following method: step S241, for each evaluation unit Calculating potential suitability indices of species A and species B And ; Step S242, defining conflict index : ; Wherein, the And Habitat demand weights for species a and species B, respectively; step S243, setting conflict threshold When (when) When the evaluation unit is used, the evaluation unit is marked as a life requirement conflict area; And S244, performing spatial cluster analysis on all the identified habitat demand conflict areas to form a connected habitat demand conflict area.
5. The intelligent control method for the highland forestation habitat of claim 4, wherein the step S3 specifically comprises: S31, designing a plurality of regulation schemes with different spatial configurations and vegetation structural parameters by taking the identified habitat demand conflict area as a regulation target area; S32, inputting parameters of each regulation scheme into a habitat regulation benefit evaluation model, and pre-simulating expected habitat quality values of each target species after implementation of each regulation scheme based on potential suitability indexes and habitat demand parameters Expected comprehensive regulation and control benefits Wherein a habitat quality value is expected The calculation formula of (2) is as follows: ; Wherein, the Is the third step after the implementation of the regulation scheme The first evaluation unit The ecological function value of the item is calculated, Is the first The weight coefficient of the term ecological function to the target species, A total number of ecological functions; expected comprehensive regulation and control benefits The calculation formula of (2) is as follows: ; Wherein, the Is the third step after the implementation of the regulation scheme The expected habitat quality values of the individual evaluation units, In order to evaluate the total number of units, Is the average habitat quality value before regulation; And step S33, calculating the overall synergistic benefit index of the regulation scheme based on the expected comprehensive regulation benefit, wherein the overall synergistic benefit index comprises overall benefit and benefit balance.
6. The intelligent control method for the highland forestation habitat of claim 5, wherein in step S33, the overall benefit is The calculation formula of (2) is as follows: ; Wherein, the Is the first The expected comprehensive regulatory benefits of the individual species, Is the total number of species; the calculation process of the benefit balance degree is as follows: step S331, calculating the ecological niche weights of the species The calculation formula is as follows: ; Wherein, the Is of a species Is used to determine the endangered class coefficients of (1), Is of a species Is used for the ecological function coefficient of the (a), Is of a species Is used to determine the protection priority coefficient of (1), A temporary index variable for traversing all species; Step S332, calculating the weighted benefit mean value : ; Step S333, calculating the weighted balance degree : ; Step S334, the calculated weighted balance degree Multi-objective optimization decision for step S4.
7. The intelligent control method for the highland forestation habitat of claim 6, wherein the step S4 specifically comprises: s41, establishing a multi-objective optimization model based on expected comprehensive regulation and control benefits and overall synergistic benefit indexes of each regulation and control scheme; step S42, defining an optimization objective function and constraint conditions of the multi-objective optimization model, wherein the optimization objective function is as follows: optimization objective 1 maximizing overall benefit ; Optimization objective 2 maximizing benefit balance ; The constraint conditions are as follows: wherein In order to regulate the overall cost of the solution, Is a pre-calculated upper limit; Step S43, defining specific parameters of a multi-objective optimization algorithm, wherein the specific parameters comprise population scale, maximum iteration times, crossover probability and variation probability; S44, adopting a second generation non-dominant sorting genetic algorithm to carry out optimization solution; and S45, selecting the pareto optimal solution set from the final population.
8. The intelligent control method for the plateau afforestation habitat of claim 7, wherein in step S45, an entropy weight TOPSIS method is adopted to select an optimal solution from pareto fronts, and the method specifically comprises the following steps: step S451, constructing a decision matrix of the pareto solution set, wherein the decision matrix comprises two indexes of overall benefit and benefit balance; Step S452, determining objective weights of two indexes by adopting an entropy weight method; Step S453, based on the species requirement parameters interpreted in step S1, introducing the species requirement satisfaction as a third decision index, wherein the calculation formula is as follows: ; Wherein, the To be an evaluation unit For species Is used as a potential suitability index for the test specimen, To be an evaluation unit Is a part of the area of (2); step S454, normalizing the decision matrix; Step S455, determining a positive ideal solution and a negative ideal solution; step 456, calculating Euclidean distance between each solution and positive and negative ideal solutions; And step 457, calculating the relative closeness of each solution, and selecting the solution with the maximum closeness as an optimal regulation scheme.
9. The intelligent control method for the highland forestation habitat of claim 8, wherein the step S5 specifically comprises: step S51, implementing the habitat regulation engineering according to the output optimal habitat regulation optimization scheme; step S52, acquiring implemented actual habitat state data through an air-to-ground integrated monitoring network; step S53, processing the actual habitat state data, and fusing and updating the processed data with a habitat database; Step S54, re-executing the calculation process of step S2 and step S3 based on the updated data to obtain the actual ecological function value Index of suitability for actual species And actual comprehensive regulation and control benefits Wherein the actual comprehensive regulation and control benefits The calculation formula of (2) is as follows: ; Wherein, the To actually monitor the first The habitat quality values of the individual evaluation units; Step S55, benefit comparison and deviation analysis, specifically includes: calculating actual comprehensive regulation and control benefits Comprehensive regulation and control benefits with expectations Relative error of (2) : ; When (when) When the regulation effect is expected, maintaining the current model parameters; When (when) Entering a parameter correction flow; Wherein the method comprises the steps of Is a threshold value; s56, model parameter linkage correction; and step S57, applying the corrected model parameters to the next round of habitat evaluation and regulation decision.
10. An intelligent regulation and control system for a plateau forestation habitat, which is characterized by comprising: the data acquisition and database construction module is used for acquiring multi-source data of the target area and constructing a habitat database; the habitat demand parameter quantification module is used for interpreting and quantifying habitat demand parameters of at least two target species based on animal ecology knowledge; The habitat assessment and conflict identification module is used for calculating the comprehensive ecological function value of the assessment unit and the potential suitability index of each species and identifying a multi-species habitat demand conflict area; The regulation scheme design and pre-evaluation module is used for designing a plurality of regulation schemes according to the multi-species habitat demand conflict area and the potential suitability index, pre-evaluating expected regulation benefits of the schemes and calculating an overall synergistic benefit index; the multi-objective optimization decision module is used for optimizing each regulation and control scheme by utilizing a multi-objective optimization algorithm and outputting an optimal habitat regulation and control optimization scheme by taking the maximization of the overall expected benefits of multiple species and the optimization of the benefits among the species as targets; The monitoring and closed-loop optimization module is used for implementing an optimal scheme, acquiring actual habitat state data through a monitoring network, calculating actual comprehensive regulation and control benefits and comparing the actual comprehensive regulation and control benefits with expected benefits, and feeding the actual data back to the habitat evaluation and conflict identification module and the regulation and control scheme design and pre-evaluation module to recalculate and update model parameters when the deviation exceeds a threshold value.

Description

Intelligent regulation and control method and system for plateau forestation habitat Technical Field The invention relates to the technical field of ecological intelligent regulation and control, in particular to an intelligent regulation and control method and system for a plateau forestation habitat. Background The high-primitive ecological system has complex terrain and harsh climate, and the biodiversity protection and ecological restoration tasks are difficult. The traditional habitat restoration engineering mainly aims at improving vegetation coverage, and the adopted forestation and vegetation management method focuses on plant species selection and survival rate, and lacks systematic consideration on specific habitat requirements of various wild organisms such as animals, birds and the like in the area. Key habitat elements such as hidden places, food resources, propagation conditions, migration galleries and the like on which animals depend for survival are often ignored in the existing planning design, so that ecological restoration engineering can not effectively promote animal population restoration and diversity maintenance while improving vegetation coverage, and even specific species can be blocked due to the simplification of habitat structures. The prior art has obvious defects in the aspect of fine regulation and control of the supporting habitat. On the one hand, the habitat monitoring is mostly dependent on a single data source or periodic manual investigation, so that the fusion analysis and dynamic evaluation of the multidimensional environmental factors and animal activity space-time data are difficult to realize, and the judgment of the habitat quality is delayed and one-sided. On the other hand, due to the lack of a quantitative prediction model for linking the habitat structural parameters with the effect of the regulation and control measures, the management decision is mostly based on experience, the habitat improvement benefits of different regulation and control schemes cannot be simulated, compared and optimized before implementation, and the dynamic adjustment and continuous improvement according to the monitoring result after implementation cannot be realized, so that the management process is intelligent and has poor adaptability. Therefore, when the existing method is used for meeting complex demands such as coexistence of multiple species in a plateau, rapid change of habitat and the like, challenges such as inaccurate habitat evaluation, lack of predictability of regulation and control decisions, difficulty in continuous optimization of management process and the like are generally faced. A new approach is needed to solve the above problems. Disclosure of Invention The invention aims to provide an intelligent regulation and control method and system for a highland forestation habitat, which are used for solving the problems of rough management, decision-making dependence on experience and difficulty in collaborative improvement of the quality of multi-species habitats in the existing high-primordial ecological restoration engineering. According to the method, dynamic diagnosis of the habitat quality, simulation previewing and multi-objective collaborative optimization of a regulation scheme are realized by fusing multisource monitoring data and species ecological requirements, and based on implementation of a feedback self-adaptive correction model, habitat management is changed from passive management with forest as a center to active optimization of habitat with the aim of improving diversity of high-altitude animals and birds. In order to achieve the purpose, the invention provides an intelligent control method for a plateau forestation habitat, which comprises the following steps: s1, acquiring multi-source data of a target area, constructing a habitat database, and interpreting and quantifying habitat demand parameters of at least two target species based on animal ecological knowledge; s2, taking a habitat database and habitat demand parameters as inputs, calculating comprehensive ecological function values of an evaluation unit, calculating potential suitability indexes of all species, and identifying a multi-species habitat demand conflict area; Step S3, designing a plurality of regulation schemes based on the multi-species habitat demand conflict area and the potential suitability index, pre-evaluating expected regulation benefits of each regulation scheme on each species, and calculating an overall synergistic benefit index; s4, optimizing each regulation scheme by utilizing a multi-objective optimization algorithm with the aim of maximizing the overall expected benefits of multiple species and optimizing the benefits among species on the basis of the expected comprehensive regulation benefits and the overall synergistic benefits indexes of each regulation scheme, and outputting an optimal habitat regulation optimization scheme; And S5, implementing an optimal