Arbor community construction method suitable for urban landscaping

Abstract

The invention discloses an arbor community construction method suitable for urban landscaping, and relates to the technical field of urban planning, and the method comprises the steps: deploying an environment sensor in a target urban landscaping region, and collecting the environment data of the target region in real time through a wireless sensor network; based on the environment data, adopting a genetic algorithm to carry out adaptability evaluation on a plurality of candidate tree species, and selecting a tree species combination with the strongest adaptability to carry out preliminary community configuration; and a multi-objective optimization algorithm is adopted to carry out optimization configuration on the number, distribution and ecological functions of tree species in the initial community configuration, the performance of the community under different environmental changes is evaluated, and the overall ecological benefits of the community are maximized. According to the arbor community construction method suitable for urban landscaping provided by the invention, the configuration of the tree species is automatically adjusted based on multi-dimensional evaluation of environmental data, tree species adaptability and community ecological benefits, and the community ecological benefits are maximized.

Description

Technical Field

[0001] The invention relates to the technical field of urban planning, and in particular to a method for constructing an arbor community suitable for urban greening. Background Art

[0002] At present, the construction of urban greening tree communities usually relies on traditional tree species selection methods, which configure and select tree species based on expert experience or single environmental data. These methods focus on the single adaptability of tree species, ignoring the relationship between tree species, the ecological function of tree species, and multi-objective optimization. Traditional tree species configuration methods are often difficult to effectively improve the overall ecological benefits of the community when dealing with complex environmental changes in cities.

[0003] With the advancement of urbanization, the problems faced by greening projects are becoming increasingly complex. Environmental factors have a great impact on tree growth and ecological benefits, while traditional methods are not adaptable enough to environmental changes, resulting in poor results in many urban greening projects. In addition, existing tree species configuration methods fail to fully consider the spatial distribution relationship between tree species and the synergistic effect of ecological functions, and lack effective optimization strategies and algorithm support. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing urban greening tree community construction methods have problems such as incomplete adaptability assessment, neglect of the relationship between tree species, and insufficient support for optimization algorithms. Traditional methods mostly rely on static environmental data for tree species selection, and fail to fully consider the ecological functions, environmental adaptability, and spatial distribution relationships of tree species, resulting in tree species configuration often unable to adapt to complex environmental changes in cities. In addition, there is a lack of efficient optimization algorithms to balance multiple objectives, such as the trade-off between the number of tree species, tree species distribution, and ecological benefits.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for constructing a tree community suitable for urban greening, comprising:

[0007] Environmental sensors are deployed in the target urban greening area, and the environmental data of the target area is collected in real time through a wireless sensor network. Based on the environmental data, a genetic algorithm is used to evaluate the adaptability of multiple candidate tree species, and the most adaptable tree species combination is selected for preliminary community configuration. A multi-objective optimization algorithm is used to optimize the number, distribution and ecological functions of tree species in the preliminary community configuration, evaluate the performance of the community under different environmental changes, and maximize the overall ecological benefits of the community.

[0008] As a preferred solution of the method for constructing a tree community suitable for urban greening described in the present invention, the environmental data includes temperature, humidity, light intensity and air quality.

[0009] As a preferred scheme of the method for constructing a tree community suitable for urban greening described in the present invention, the adaptability evaluation of multiple candidate tree species includes preprocessing the environmental data; initializing a tree species combination population based on the environmental data to generate a combination of multiple candidate tree species; calculating a first adaptability score for each tree species combination; selecting a tree species combination with an adaptability greater than a preset threshold to enter the next generation based on the first adaptability score; generating new tree species combinations through crossover and mutation operations of a genetic algorithm, and optimizing tree species configurations with strong adaptability generation by generation; updating the first adaptability score after each generation of iteration, and finally determining the tree species combination with the strongest adaptability as the initial configuration of the community.

[0010] As a preferred scheme of the method for constructing a tree community suitable for urban greening described in the present invention, the preprocessing includes standardizing temperature, humidity, light intensity and air quality; modeling the standardized environmental data through local weighted regression; calculating the relationship between environmental factors based on the Pearson correlation coefficient, and constructing an interaction matrix.

[0011] As a preferred embodiment of the method for constructing a tree community suitable for urban greening described in the present invention, the standardized processing is expressed as:

[0012]

[0013] Among them, X i represents the original data of the i-th environmental factor, Represents X i The mean of Represents X i The standard deviation of i represents the standardized environmental data; the local weighted regression is expressed as,

[0014]

[0015] in, represents the predicted environmental parameter value, β represents the parameter set of the regression model, and y j Represents data point x j The corresponding target value, β0, β1 represent the intercept term and slope term respectively, w(x j ) represents the weighting function, calculating the data point x j The influence of the distance from the current point, τ represents the bandwidth parameter of the influence range, x j represents the input value of the jth sample point, xi Indicates the input value of the current target point;

[0016] The constructed interaction matrix is ​​expressed as,

[0017]

[0018] Among them, corr(X′ i ,X′ j ) represents the Pearson correlation coefficient between the i-th environmental factor and the j-th environmental factor, X′ i,k represents the kth data point of the standardized environmental factor i, μX′ i represents the mean of environmental factor i, and n represents the number of data points.

[0019] As a preferred embodiment of the method for constructing a tree community suitable for urban greening according to the present invention, the first adaptability score is expressed as:

[0020]

[0021] Among them, S adapt (T i ) represents the tree species combination T i The first fitness score, w1 and w2 represent the weight coefficients, γ mn Represents the weight coefficient in the interaction matrix.

[0022] As a preferred solution of the method for constructing a tree community suitable for urban greening described in the present invention, the optimization configuration includes defining an objective function based on a preliminary configuration of the community, wherein the objective function includes the contribution of the number of tree species, the distribution of tree species and the ecological functions of tree species to the ecological benefits of the community; setting constraints on the number, distribution and ecological functions of tree species in the community, wherein the constraints include the ecological needs, environmental adaptability and spatial distribution of the tree species; using the NSGA-II algorithm, through non-dominated sorting and crowding sorting, finding the optimal compromise solution among multiple objectives of the number of tree species, the distribution of tree species and the ecological functions of tree species; in the optimization process, calculating a second adaptability score based on the objective function and the constraints; in each iteration generation, adjusting the tree species configuration according to the second adaptability score to maximize the ecological benefits of the community; and finally selecting the tree species configuration with the highest second adaptability score as the optimal configuration of the community.

[0023] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for constructing a tree community suitable for urban greening when executing the computer program.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for constructing a tree community suitable for urban greening.

[0025] Beneficial effects of the present invention: The method for constructing a tree community suitable for urban greening provided by the present invention is based on a multi-dimensional evaluation of environmental data, tree species adaptability, and community ecological benefits, and automatically adjusts the configuration of tree species to maximize the ecological benefits of the community. Through the combination of genetic algorithms and NSGA-II optimization algorithms, the number, distribution, and ecological functions of tree species can be accurately optimized in a complex urban environment, achieving a comprehensive improvement in ecological benefits. In particular, the optimization of the ecological needs, environmental adaptability, and spatial distribution of tree species improves the scientificity and adaptability of greening projects, and helps to achieve more efficient and sustainable urban greening and ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0027] Figure 1 An overall flow chart of a method for constructing a tree community suitable for urban greening provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Example 1

[0031] Reference Figure 1 , which is an embodiment of the present invention, provides a method for constructing a tree community suitable for urban greening, comprising:

[0032] Step S1: Deploy environmental sensors in the green area of ​​the target city and collect environmental data of the target area in real time through a wireless sensor network.

[0033] Step S2: Based on the environmental data, a genetic algorithm is used to evaluate the adaptability of multiple candidate tree species, and the tree species combination with the strongest adaptability is selected for preliminary community configuration.

[0034] Step S3: Use a multi-objective optimization algorithm to optimize the number, distribution and ecological functions of tree species in the initial configuration of the community, evaluate the performance of the community under different environmental changes, and maximize the overall ecological benefits of the community.

[0035] The number of tree species includes the number of each tree species. The distribution of tree species includes the spatial distribution of each tree species in the target area. The ecological function of tree species includes the ecological function of each tree species, such as water retention, air purification, temperature regulation, etc.

[0036] The environmental data includes temperature, humidity, light intensity and air quality.

[0037] The adaptability evaluation of multiple candidate tree species includes preprocessing the environmental data; initializing a tree species combination population based on the environmental data to generate a combination of multiple candidate tree species; calculating a first adaptability score for each tree species combination; selecting a tree species combination with an adaptability greater than a preset threshold to enter the next generation based on the first adaptability score; generating new tree species combinations through crossover and mutation operations of a genetic algorithm, and optimizing tree species configurations with strong adaptability generation by generation; updating the first adaptability score after each generation iteration, and finally determining the tree species combination with the strongest adaptability as the initial configuration of the community.

[0038] The preprocessing includes standardizing the temperature, humidity, light intensity and air quality; modeling the standardized environmental data through local weighted regression; calculating the relationship between environmental factors based on the Pearson correlation coefficient and constructing an interaction matrix.

[0039] The standardization process is expressed as,

[0040]

[0041] Among them, X i represents the original data of the i-th environmental factor, Represents X i The mean of Represents X i The standard deviation of i Represents the standardized environmental data.

[0042] The local weighted regression is expressed as,

[0043]

[0044] in, represents the predicted environmental parameter value, β represents the parameter set of the regression model, and y j Represents data point x j The corresponding target value, β0, β1 represent the intercept term and slope term respectively, w(x j ) represents the weighting function, calculating the data point x j The influence of the distance from the current point, τ represents the bandwidth parameter of the influence range, x j represents the input value of the jth sample point, x i Indicates the input value of the current target point.

[0045] The constructed interaction matrix is ​​expressed as,

[0046]

[0047] Among them, corr(X′ i ,X′ j ) represents the Pearson correlation coefficient between the i-th environmental factor and the j-th environmental factor, X′ i,k represents the kth data point of the standardized environmental factor i, μX′ i represents the mean of environmental factor i, and n represents the number of data points.

[0048] The first adaptability score is expressed as,

[0049]

[0050] Among them, S adapt (T i ) represents the tree species combination T i The first fitness score, w1 and w2 represent the weight coefficients, γ mn Represents the weight coefficient in the interaction matrix.

[0051] It should be noted that, in this embodiment, the environmental data is first standardized to ensure that different types of environmental data can be directly compared and effectively integrated. By calculating the mean and standard deviation of each environmental factor, the original data is converted into standardized data. The purpose of standardization is to eliminate the differences in dimensions and ranges of different environmental factors. After this processing, all environmental data are converted into a unified scale, eliminating the impact caused by different units, making the subsequent adaptability score calculation more accurate.

[0052] The standardization process is to subtract the mean of each environmental factor from each environmental data point and divide it by the standard deviation of the environmental factor. In this way, the mean value of each environmental factor becomes 0 and the standard deviation becomes 1, which ensures that all environmental data are in the same dimension and the impact of different environmental factors can be treated fairly. The results of the standardization process provide a basis for subsequent steps, making the comparison between different environmental factors meaningful.

[0053] Next, the environmental data is modeled using Local Weighted Regression (LWR). In this process, the distance between each target data point and all other data points is first calculated. Data points with smaller distances have a greater influence on the target point. Therefore, a distance-dependent weight is assigned to each data point through a Gaussian weighting function. Data points that are closer to the target point have larger weight values, while data points that are farther away have smaller weights. The weights are calculated using a Gaussian function, where the bandwidth parameter controls the range of influence, and the larger the bandwidth, the wider the range of influence. The calculation of weights ensures that closer data points play a more important role in the model.

[0054] Then, based on these weighted weights, the environmental data are fitted through regression analysis. In the regression process, the goal is to find a best-fit curve and find the optimal regression coefficient by minimizing the error. Specifically, the regression model attempts to achieve the best mapping between environmental data and fitness values ​​by minimizing the weighted error. The results of the regression analysis will give the fitness values ​​of each tree species combination in a specific environment, which reflect the growth potential of the tree species in that environment.

[0055] Further, in order to consider the mutual relationship between different environmental factors, the present invention calculates the Pearson correlation coefficient between environmental factors. Through this process, we can measure the linear correlation between two environmental factors. The value range of the Pearson correlation coefficient is from -1 to 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents nothing to do. By calculating the correlation coefficient between each pair of environmental factors, we obtain a complete interaction matrix, which represents the degree of mutual influence between environmental factors. Each element in the interaction matrix reflects the relationship between different environmental factors, which has an important influence on the final adaptability score calculation.

[0056] Finally, the first adaptability score of the tree species combination is calculated by comprehensively considering the local weighted regression results and the relationship between environmental factors. The adaptability score consists of two parts: one is the environmental data prediction result provided by the regression model, and the other is the weighted value of the relationship between environmental factors provided by the interaction matrix. The calculation formula of the adaptability score combines the weighted contribution of the regression results and the interaction matrix to obtain a comprehensive adaptability value. This adaptability score reflects the adaptability of the tree species combination in a specific environment, taking into account the individual effects of environmental factors and the interactions between them, thus providing a more comprehensive and accurate basis for the optimization of tree species combinations.

[0057] Through the above process, the calculated adaptability score can not only reflect the adaptability of the tree species combination in a specific environment, but also effectively reveal the synergy between different environmental factors. This method of comprehensively considering the complex relationships between environmental data overcomes the shortcomings of traditional methods and can more accurately evaluate the ecological benefits of tree species configuration. In traditional methods, the relationship between environmental factors is usually ignored or simplified to linear weighting. The present invention, through the introduction of local weighted regression and interaction matrix, can more carefully capture the nonlinear relationship and interaction between environmental factors, thereby greatly improving the accuracy and scientificity of adaptability scores.

[0058] The optimization configuration includes defining an objective function based on a preliminary configuration of the community, wherein the objective function includes the contribution of the number of tree species, the distribution of tree species, and the ecological functions of tree species to the ecological benefits of the community; setting constraints on the number, distribution, and ecological functions of tree species in the community, wherein the constraints include the ecological needs, environmental adaptability, and spatial distribution of the tree species; using the NSGA-II algorithm to find the optimal compromise solution among multiple objectives of the number of tree species, the distribution of tree species, and the ecological functions of tree species through non-dominated sorting and crowding sorting; in the optimization process, calculating a second fitness score based on the objective function and the constraints; in each iteration, adjusting the tree species configuration according to the second fitness score to maximize the ecological benefits of the community; and finally selecting the tree species configuration with the highest second fitness score as the optimal configuration of the community.

[0059] The community configuration optimization process in this embodiment adopts the multi-objective optimization algorithm NSGA-II to achieve the optimal compromise between the number of tree species, tree species distribution and tree species ecological functions. First, when optimizing the configuration, define the objective function, which comprehensively considers the contribution of the number of tree species, tree species distribution and tree species ecological functions to the ecological benefits of the community. Specifically, the objective function includes the following parts: first, the optimization of the number of tree species, which aims to ensure the appropriate proportion of each tree species in the community and avoid excessive reproduction or too few tree species; second, the optimization of tree species distribution, which ensures the rationality of tree species distribution in the community, so that each tree species can obtain sufficient resources and compete effectively in different spatial locations; third, the optimization of tree species ecological functions refers to the quantification of the ecological benefits of different tree species, including contributions to ecological service functions such as air quality, temperature regulation, and water regulation. These goals will be incorporated into the objective function through weighted synthesis.

[0060] The optimization of the objective function is not only to maximize the benefits of a single goal, but to find an optimal compromise solution between these goals through comprehensive consideration of multiple goals. In actual operation, the number, distribution and ecological functions of tree species will be affected by constraints. These constraints include the ecological needs of tree species (such as the adaptability of environmental factors such as moisture, temperature, soil type to tree species), the environmental adaptability of tree species (the growth ability of tree species to specific environmental conditions), and the spatial distribution of tree species in the community (that is, different tree species should be distributed in suitable locations). In this embodiment, by setting these constraints, it is ensured that the tree species configuration of each generation in the optimization process conforms to the laws of ecology to avoid ecological imbalance.

[0061] The NSGA-II algorithm uses non-dominated sorting and crowding sorting techniques in the optimization process to find the optimal solution through multiple generations of iteration. In the evolution of each generation, all individuals in the current population are first non-dominated sorted, that is, the individuals in the population are sorted according to the dominance relationship of the objective function value, and those individuals that perform better on all objectives are preferentially selected as parents. Subsequently, individuals are further screened through crowding sorting to ensure that the diversity of the population is maintained in each generation. The purpose of crowding sorting is to achieve a balance between multiple objectives, avoid concentrating on the local optimal solution of a certain objective, and ensure that the algorithm can explore a wider solution space, thereby obtaining a more diverse and representative optimal solution.

[0062] In the iterative process of each generation, the second adaptability score is calculated based on the value of the aforementioned objective function and the constraints to measure the adaptability of the current tree species configuration. Specifically, the second adaptability score comprehensively considers the number, distribution and ecological function of tree species in the current environment, and adjusts the tree species configuration strategy based on the optimization results of the objective function. In this process, the tree species configuration with a higher adaptability score indicates that it has stronger adaptability and ecological benefits under the current environmental conditions, and is therefore more likely to be selected into the next generation. In this way, the community configuration will be gradually optimized in order to maximize the overall ecological benefits of the community.

[0063] Finally, after several generations of optimization iterations, this embodiment will select the tree species configuration with the highest second adaptability score as the optimal configuration. This configuration achieves the best compromise between multiple objectives, can maximize the overall ecological benefits of the community, and ensure the balance between the number, distribution and ecological functions of tree species. At this point, the optimal configuration not only meets the ecological needs and environmental adaptability of tree species, but also can make full use of the spatial resources of urban greening areas, maximize the ecological value of each tree species, and ultimately form a tree community configuration with good ecological benefits.

[0064] In summary, this embodiment can effectively find the optimal tree species configuration by optimizing among multiple objectives such as the number, distribution and ecological function of tree species through the NSGA-II algorithm. Through non-dominated sorting and crowding sorting, this embodiment ensures population diversity and avoids the emergence of local optimal solutions. At the same time, the calculation mechanism of the second adaptive score ensures that the tree species configuration of each generation continues to tend toward the optimal solution, and finally obtains the community configuration with the greatest ecological benefit. This process not only solves the limitations of single-objective optimization in traditional methods, but also realizes the optimal community configuration under complex environmental conditions by integrating multi-dimensional ecological benefit indicators.

[0065] In an optional embodiment of the present invention, the objective function includes an objective function of the number of tree species, an objective function of the spatial distribution of tree species, and an objective function of the ecological function of tree species.

[0066] The objective function of tree species quantity reflects the contribution of tree species configuration within the community to the ecological benefits of the community. Reasonable tree species quantity distribution helps to improve the biodiversity, stress resistance and resource utilization efficiency of the community, which is defined as:

[0067]

[0068] Among them, y k represents the number of the kth tree species, β k represents the ecological contribution of the kth tree species, ν k represents the optimal number of the k-th tree species, represents the variance of the number of k-th tree species.

[0069] It should be noted that the ecological contribution is quantified by the contribution of each tree species to the ecological benefits of the community, such as carbon absorption capacity, air purification and other functions. The specific formula is:

[0070]

[0071] Among them, f ki is the contribution of tree species k in the i-th aspect, N is the total number of functions, ν k represents the optimal quantity, obtained through actual data, literature research or expert evaluation, Represents the quantity variance, determined based on historical data or growth characteristics, β k It represents the ecological contribution, which is quantified by the contribution of each tree species to the ecological benefits of the community, such as carbon absorption capacity, air purification and other functions. The specific formula is:

[0072]

[0073] Among them, f ki is the contribution of tree species k in the i-th aspect, and N is the total number of functions.

[0074] The spatial distribution of tree species affects the overall ecological benefits of the community. Reasonable distribution helps to reduce competition between tree species and optimize resource utilization. The objective function is defined as:

[0075]

[0076] Among them, z k is the spatial distribution of the kth tree species, δ kl is the spatial correlation between the kth and lth tree species, d kl is the distance between the kth and lth tree species. kl is the spatial interaction distance between the kth and lth tree species.

[0077] It should be noted that spatial correlation is quantified based on the symbiotic or competitive relationship between tree species and is expressed as:

[0078]

[0079] The spatial distance is the shortest distance between tree species k and l, usually the straight-line distance of the overlapping area of ​​their growth space.

[0080] The interaction distance is determined based on the growth space requirements of the tree species and is usually obtained through experimental data or ecological studies.

[0081] The ecological function of a tree species reflects its actual contribution to the environment and ecosystem. Optimizing the ecological function of a tree species can maximize the overall ecological benefits of the community. The objective function is defined as:

[0082]

[0083] Among them, w k is the number of the kth tree species, f k is the ecological function index of the kth tree species, is the optimal number of the kth tree species.

[0084] It should be noted that the ecological function index includes the carbon absorption capacity, air purification, precipitation interception and other functions of tree species. Each ecological function can be obtained through experimental data or literature, expressed as:

[0085] f k =f k1 +f k2 +…+f km

[0086] Among them, f ki Represents the ecological function of tree species k in the i-th aspect (such as carbon absorption, air purification, etc.).

[0087] The optimal number is also determined by ecological requirements and community configuration criteria.

[0088] Constraints ensure that the tree species configuration during the optimization process meets environmental requirements and actual operational capabilities, including: tree species quantity constraints, spatial distribution constraints and ecological adaptability constraints:

[0089] The tree species quantity constraint is expressed as:

[0090]

[0091] in, and is the minimum and maximum suitable number of tree species k.

[0092] The spatial distribution constraint is expressed as:

[0093]

[0094] Among them, C is the restriction of spatial distribution, which ensures a reasonable distance between tree species and avoids excessive density.

[0095] The ecological adaptability constraint is expressed as:

[0096]

[0097] Among them, EA k is the environmental adaptability index of tree species k, ensuring the ecological adaptability of the selected tree species in the target area.

[0098] The NSGA-II algorithm solution process includes:

[0099] Generate an initial population P0, each individual represents a tree species configuration, including:

[0100] Number of tree species y1,y2,…,y p

[0101] Spatial distribution of tree species z1,z2,…,z p

[0102] Ecological functions of tree species f1, f2, …, f p

[0103] A non-dominated sort is performed on each generation of the population, and the crowding degree of each individual is calculated. Non-dominated sorting ensures that non-dominated solutions are selected, and crowding degree calculation is used to maintain the diversity of solutions.

[0104] A new generation of population is generated through crossover (such as single-point crossover) and mutation (such as site mutation) operations to ensure the diversity of the population and the continuous evolution of the optimal solution.

[0105] In each generation, based on the objective function and constraints, the second fitness score is calculated to guide the optimization of the community configuration. Finally, the tree species configuration with the highest second fitness score is selected as the optimal solution for the community.

[0106] Example 2

[0107] An embodiment of the present invention is different from the previous embodiment in that:

[0108] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0109] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0110] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0111] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0112] Example 3

[0113] One embodiment of the present invention provides a method for constructing a tree community suitable for urban greening. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through comparative experiments.

[0114] The green area selected for the experiment is located in the central urban area of ​​a certain city, with a specific coverage area of ​​20 hectares. The area was originally a mixed development zone in the urban area, mainly including some urban roads, parking lots and buildings, and the green coverage is insufficient. Therefore, the goal of this experiment is to improve the ecological benefits of the region through reasonable tree species configuration. In order to ensure the accuracy of the data and the scientific nature of the experiment, multiple environmental sensors are deployed in the experimental area, including temperature and humidity sensors, light intensity sensors and air quality sensors, to collect environmental data of the area in real time. The data collected by the sensors covers key environmental factors such as temperature, humidity, light intensity and air quality in the area.

[0115] In the first stage of the experiment of the method of the present invention, the collected environmental data is first standardized. By standardizing the values ​​of environmental factors such as temperature, humidity, light intensity and air quality, it is ensured that different environmental data have the same dimension. After standardization, the experiment uses local weighted regression (LWR) to model the standardized environmental data and generate predicted values ​​for each environmental factor. This process ensures that the influence of each data point can better reflect the influence of current environmental conditions when adjusting the tree species configuration according to environmental changes in a weighted manner. The weighted value between each generation of data points is determined by its distance from the current point, thereby ensuring that points with closer distances have a greater impact on the results, and that data points with stronger adaptability have a more prominent impact on subsequent tree species configurations.

[0116] In order to further improve the evaluation of tree species adaptability, the experiment calculated the correlation between various environmental factors and constructed an interaction matrix using the Pearson correlation coefficient. These data provide a theoretical basis for the selection and optimization of subsequent tree species combinations. By calculating the interaction matrix, the experiment determined the correlation between various environmental factors and further refined the adaptability score of tree species configuration.

[0117] After the environmental data processing, the experiment entered the genetic algorithm stage. In this stage, the candidate tree species were selected after a detailed adaptability evaluation, and five tree species were selected: camphor, ginkgo, ash, osmanthus and sycamore. The performance of each tree species in environmental adaptability and ecological function was evaluated in detail, and the tree species combination was optimized based on the adaptability score. The initial population of the genetic algorithm consists of multiple tree species combinations, and the adaptability scores of these combinations are calculated based on the aforementioned local weighted regression and interaction matrix.

[0118] After multiple generations of iterative optimization, the combination and number of tree species gradually tended to the optimal configuration. In the end, the optimized tree species configuration was: 130 camphor trees, 80 ginkgo trees, 100 fraxinus trees, 60 osmanthus trees, and 50 sycamore trees. The optimized tree species distribution ensures the reasonable spatial distribution of each tree, avoids excessive competition between tree species, and fully considers the ecological function and adaptability of each tree species under specific environmental conditions. Camphor trees, as the dominant tree species in the community, mainly play an air purification and beautification effect; ginkgo trees are highly drought-resistant and adaptable to urban environments; fraxinus trees and osmanthus trees provide good landscape effects and enhance the aesthetics of urban greening; sycamore trees play a significant role in regulating air humidity.

[0119] The traditional method does not use a comprehensive adaptability assessment in tree species selection, but rather selects based on past experience and common greening tree species. Commonly used tree species include camphor, ginkgo, ash, and sycamore. Most of these tree species are already widely used under similar environmental conditions, and landscape designers usually choose the most familiar tree species based on experience. This selection does not fully consider the impact of specific environmental changes on the growth of tree species, nor does it deeply explore the adaptability of each tree species under specific environmental conditions.

[0120] The traditional method of tree species distribution adopts a regular uniform spacing distribution pattern. Garden designers divide the tree species distribution in proportion according to the overall area of ​​the greening area, without carefully considering the spatial requirements and ecological functions of specific tree species. Cinnamomum camphora is selected as the main tree species, occupying about 30% of the space in the area; Ginkgo biloba, ash and sycamore occupy 20%, 25% and 25% respectively. The spatial distribution between tree species is allocated entirely according to conventional standards and area ratios, without fully considering the ecological functions and mutual influence of different tree species.

[0121] The method of the present invention solves the problems of insufficient environmental adaptability, inaccurate tree species configuration and lack of optimization mechanism in traditional methods by introducing real-time environmental data collection and tree species configuration method based on multi-objective optimization algorithm. Compared with traditional methods, the present invention can dynamically evaluate and adjust tree species configuration, ensure that tree species can grow optimally under different environmental conditions, and significantly improve the ecological benefits of urban greening communities.

[0122] Traditional methods rely on historical climate data and experience to select tree species, and tree species configuration usually adopts a static and simple proportional allocation method, ignoring the long-term impact of environmental changes on tree species growth, and failing to consider the ecological interaction between tree species, resulting in poor community adaptability and low ecological benefits. However, the present invention deploys environmental sensors to collect environmental data such as temperature, humidity, light intensity, and air quality in real time, and combines genetic algorithms and multi-objective optimization algorithms to not only update environmental data in real time, but also dynamically optimize the selection, distribution, and ecological function configuration of tree species, thereby ensuring the maximization of community adaptability and ecological benefits.

[0123] Through experimental comparison, the effect of the method of the present invention and the traditional method in practical application is significantly different. In a 20-hectare urban greening area, the traditional method selected 4 common tree species and distributed them at uniform spacing. However, in later monitoring, it was found that the growth of the community was greatly affected by environmental changes, and some tree species failed to adapt to local environmental conditions, resulting in the death or poor growth of some tree species. The present invention optimizes and adjusts the number, distribution and ecological functions of tree species through real-time monitoring and combined with a multi-objective optimization algorithm, which not only improves the survival rate of tree species, but also significantly enhances the ecological functions of the community, such as air purification, temperature regulation and biodiversity support. Finally, the ecological benefits of the optimized configuration community of the present invention increased by more than 25% within 5 years, significantly improving the comprehensive benefits of the greening area compared to traditional methods.

[0124] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for constructing a tree community suitable for urban greening, characterized in that: include: Deploy environmental sensors in the green areas of the target city and collect environmental data of the target area in real time through wireless sensor networks; Based on the environmental data, a genetic algorithm is used to evaluate the adaptability of multiple candidate tree species, and the tree species combination with the strongest adaptability is selected for preliminary community configuration; A multi-objective optimization algorithm is used to optimize the number, distribution and ecological functions of tree species in the initial configuration of the community, evaluate the performance of the community under different environmental changes, and maximize the overall ecological benefits of the community.

2. The method for constructing a tree community suitable for urban greening according to claim 1, characterized in that: The environmental data includes temperature, humidity, light intensity and air quality.

3. The method for constructing a tree community suitable for urban greening as claimed in claim 2, characterized in that: The adaptability assessment of the plurality of candidate tree species includes preprocessing the environmental data; Initialize a tree species combination population based on the environmental data to generate a combination of multiple candidate tree species; Calculate the first fitness score for each tree species combination; According to the first fitness score, a tree species combination with fitness greater than a preset threshold is selected to enter the next generation; Generate new tree species combinations through crossover and mutation operations of genetic algorithms, and optimize the tree species configuration with strong adaptability generation by generation; After each generation of iteration, the first fitness score is updated, and the tree species combination with the strongest adaptability is finally determined as the preliminary configuration of the community.

4. The method for constructing a tree community suitable for urban greening as claimed in claim 3, characterized in that: The pretreatment includes standardizing the temperature, humidity, light intensity and air quality; The standardized environmental data were modeled by locally weighted regression; The interrelationships among environmental factors were calculated based on Pearson's correlation coefficient, and an interaction matrix was constructed.

5. The method for constructing a tree community suitable for urban greening as claimed in claim 4, characterized in that: The standardization process is expressed as, Among them, X i represents the original data of the i-th environmental factor, Represents X i The mean of Represents X i The standard deviation of i Indicates the standardized environmental data; The local weighted regression is expressed as, in, represents the predicted environmental parameter value, β represents the parameter set of the regression model, and y j Represents data point x j The corresponding target value, β0, β1 represent the intercept term and slope term respectively, w(x j ) represents the weighting function, calculating the data point x j The influence of the distance from the current point, τ represents the bandwidth parameter of the influence range, x j represents the input value of the jth sample point, x i Indicates the input value of the current target point.

6. The method for constructing a tree community suitable for urban greening according to claim 5, characterized in that: The constructed interaction matrix is ​​expressed as, Among them, corr(X′ i ,X′ j ) represents the Pearson correlation coefficient between the i-th environmental factor and the j-th environmental factor, X′ i,k represents the kth data point of the standardized environmental factor i, μX′ i represents the mean of environmental factor i, and n represents the number of data points.

7. The method for constructing a tree community suitable for urban greening according to claim 6, characterized in that: The first adaptability score is expressed as, Among them, S adapt (T i ) represents the tree species combination T i The first fitness score, w1 and w2 represent the weight coefficients, γ mn Represents the weight coefficient in the interaction matrix.

8. The method for constructing a tree community suitable for urban greening according to claim 7, characterized in that: The optimization configuration includes defining an objective function based on the preliminary configuration of the community, wherein the objective function includes the number of tree species, the distribution of tree species and the contribution of the ecological functions of tree species to the ecological benefits of the community; Setting constraints on the number, distribution and ecological functions of tree species in the community, including the ecological requirements, environmental adaptability and spatial distribution of the tree species; Using the NSGA-II algorithm, the optimal compromise solution is found among multiple objectives including the number of tree species, tree species distribution and tree species ecological function through non-dominated sorting and crowding sorting. During the optimization process, based on the objective function and the constraints, a second fitness score is calculated; In each generation iteration, the tree species configuration is adjusted according to the second fitness score to maximize the ecological benefit of the community; Finally, the tree species configuration with the second highest adaptability score was selected as the optimal configuration of the community.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for constructing a tree community suitable for urban greening according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a tree community suitable for urban greening as described in any one of claims 1 to 8 are implemented.

Images