Greening plant selection method, system, device and storage medium

Abstract

The application discloses a greening plant selection method, system, device and storage medium, and technical scheme points thereof are as follows: soil analysis data and plant physiological data corresponding to each candidate plant in a sub-region are acquired; a structural equation model is constructed according to a congestion delay index, soil analysis data and plant physiological data of the sub-region, and significant factors of each candidate plant affected by traffic are determined according to the structural equation model; a first fitness of each candidate plant is calculated according to the congestion delay index of the sub-region and the significant factors of each candidate plant in the sub-region; a plant selection model corresponding to each sub-region is constructed based on a genetic algorithm, candidate plants are substituted into the plant selection model of each sub-region, and target plants corresponding to each sub-region are obtained, wherein, an adaptive function of the plant selection model is constructed based on the first fitness, the congestion delay index and the significant factors. The application can select plants with high adaptability and strong carbon fixation capacity based on traffic congestion.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of ecological engineering, and particularly relates to a greening plant selection method, system, device and storage medium. BACKGROUND

[0002] As an important carbon sink carrier, the carbon sequestration potential of urban green land is affected by multiple factors such as plant species, environmental conditions and management methods. For the evaluation of the carbon sequestration capacity of urban greening plants, the existing methods are mostly based on static environment (such as single light intensity, temperature or humidity, etc.), and lack of response mechanism research on urban dynamic microenvironment such as traffic congestion.

[0003] The air pollutants generated by traffic congestion during peak hours significantly affect the photosynthesis efficiency of greening plants. However, the existing methods do not fully consider the influence of automobile exhaust emission during traffic peak on plant photosynthesis. Soil carbon pool components and extracellular enzyme activity detection have been widely used in ecological research, but they have not been integrated into the dynamic management model of urban green land carbon sink, and the dynamic coupling relationship of soil carbon pool and extracellular enzyme activity in the carbon cycle process has not been revealed. SUMMARY

[0004] The purpose of the present application is to provide a greening plant selection method, system, device and storage medium, which can select plants with high adaptability and strong carbon sequestration capacity based on traffic congestion.

[0005] The first aspect of the present application provides a greening plant selection method, comprising:

[0006] dividing the target area into sub-areas of different congestion levels according to the congestion delay index;

[0007] obtaining soil analysis data and plant physiological data corresponding to each candidate plant in the sub-area;

[0008] constructing a structural equation model according to the congestion delay index, soil analysis data and plant physiological data of the sub-area, and determining the significant factors of each candidate plant affected by traffic according to the structural equation model;

[0009] calculating the first fitness of the candidate plants in the sub-area according to the congestion delay index of the sub-area and the significant factors of each candidate plant in the sub-area;

[0010] constructing a plant selection model corresponding to each sub-area based on a genetic algorithm, substituting the candidate plants into the plant selection model of each sub-area, and obtaining the target plants corresponding to each sub-area, wherein the fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index and the significant factors.

[0011] In some embodiments, the constructing the structural equation model according to the congestion delay index of the sub-region, the soil analysis data and the plant physiological data comprises:

[0012] The soil analysis data is processed to obtain soil processing data, and the plant physiological data is processed to obtain plant processing data;

[0013] An initial theoretical model is established according to the congestion delay index, the soil processing data and the plant processing data;

[0014] Parameter estimation is performed on the initial theoretical model, and in a case where a parameter estimation result evaluation index meets a preset index, a structural equation model is obtained.

[0015] In some embodiments, the establishing the initial theoretical model according to the congestion delay index, the soil processing data and the plant physiological data comprises:

[0016] Principal component analysis is performed on extracellular enzyme activity in the soil processing data to obtain key extracellular enzyme activity;

[0017] Principal component analysis is performed on physicochemical properties in the soil processing data to obtain key physicochemical properties;

[0018] Exogenous variables and endogenous variables are determined, a first relationship between the exogenous variables and the endogenous variables is established, and a second relationship between the endogenous variables is established;

[0019] Endogenous latent variables and endogenous manifest variables of the endogenous variables are determined, and a third relationship between the endogenous latent variables and the endogenous manifest variables is established;

[0020] The initial theoretical model is established according to the first relationship, the second relationship and the third relationship.

[0021] In some embodiments, the exogenous variable is the congestion delay index, and the endogenous variables comprise: a first endogenous variable, a second endogenous variable, a third endogenous variable, a fourth endogenous variable and a fifth endogenous variable; wherein the first endogenous variable is a plant carbon fixation amount in the plant physiological data, the second endogenous variable is a photosynthesis key enzyme activity in the plant physiological data, the third endogenous variable is an easily oxidizable organic carbon content in the soil processing data, the fourth endogenous variable is the key extracellular enzyme activity, and the fifth endogenous variable is the key physicochemical property.

[0022] In some embodiments, the calculating the first fitness of the candidate plant in the sub-region according to the congestion delay index of the sub-region and the significant factor of each candidate plant in the sub-region comprises:

[0023] The congestion delay index and the significant factor are subjected to principal component analysis as original variables to obtain a first principal component and a second principal component.

[0024] The traffic delay index and the first weight coefficient of the significance factor are calculated based on the load vector of the first principal component and the load vector of the second principal component.

[0025] The first fitness of candidate plants in the region is obtained by weighting the traffic delay index and its first weight coefficient, and the significance factor and its first weight coefficient.

[0026] In some embodiments, the construction of plant selection models for each sub-region based on a genetic algorithm includes:

[0027] Based on the sub-regions and training plants, establish a population set;

[0028] A fitness function for the plant selection model is constructed based on the congestion delay index, the significance factor, and the first fitness. Constraints are set on the significance factor, and the second fitness of the training plants in the population set is calculated based on the fitness function.

[0029] Based on the second fitness, selection, crossover, and mutation operations are performed iteratively on the training plants. During the iteration process, the second weight coefficient of the fitness function is determined through sensitivity analysis until the iteration termination condition is met, and then the plant selection model is obtained.

[0030] In some embodiments, calculating the second fitness of the training plants within the population set according to the fitness function includes:

[0031] Based on the congestion delay index and the preset maximum congestion delay index, the congestion suppression factor is calculated.

[0032] The actual carbon sink is calculated based on the plant carbon sequestration amount in the congestion suppression factor and the significant factors of the trained plants.

[0033] The regulatory intensity is obtained by calculating the sum of the weights of the significant factors of the trained plant, excluding plant carbon fixation.

[0034] The second fitness of the trained plant is obtained by calculating the sum of the actual carbon sink, the regulatory intensity, and the first fitness.

[0035] A second aspect of the present invention provides a greening plant selection system, comprising:

[0036] The segmentation module is used to divide the target area into sub-areas with different congestion levels based on the congestion delay index;

[0037] The acquisition module is used to acquire soil analysis data and plant physiological data corresponding to each candidate plant in the sub-region;

[0038] The construction module is used to construct a structural equation model based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region, and to determine the significant factors of traffic impact on each candidate plant based on the structural equation model.

[0039] The calculation module is used to calculate the first fitness of the candidate plants in the sub-region based on the congestion delay index of the sub-region and the significance factor of each candidate plant in the sub-region;

[0040] The determination module is used to construct a plant selection model corresponding to each sub-region based on a genetic algorithm, and to substitute the candidate plants into the plant selection model of each sub-region to obtain the target plants corresponding to each sub-region. The fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index and the significance factor.

[0041] A third aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0042] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method described above.

[0043] The technical solution provided by this invention has the following advantages and effects: significant factors that are significantly affected by traffic are screened out by structural equation modeling, and the first fitness of candidate plants is calculated based on these factors as the comprehensive fitness of candidate plants. Then, a plant selection model is constructed based on the selected significant factors and genetic algorithm. The significant factors determined by the structural equation model play a guarantee role in the plant selection model constructed based on genetic algorithm, which can realize pre-validation and hard constraint embedding, select plants with high adaptability and strong carbon sequestration ability, and the structural equation model also enhances the interpretability of the results. Attached Figure Description

[0044] Figure 1 This is a flowchart illustrating the method for selecting green plants provided by the present invention;

[0045] Figure 2 This is a graph showing the measurement data of PPO, CBH, LOC and MOC of Pittosporum tobira and Ligustrum lucidum provided by the present invention;

[0046] Figure 3 The present invention provides GADPH, PGK, Rubisco, and A of Pittosporum tobira and Ligustrum lucidum. max The measured data graph;

[0047] Figure 4 This is a structural block diagram of the greening plant selection system provided by the present invention;

[0048] Figure 5 This is an internal structural diagram of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0049] To facilitate understanding of the present invention, specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings.

[0050] Unless otherwise specified or defined, the terms "first," "second," etc., used in this document are for distinguishing names only and do not represent a specific number or order.

[0051] Unless otherwise stated or defined, the term “and / or” as used herein includes any and all combinations of one or more of the associated listed items.

[0052] It should be noted that in this article, "fixed to" or "connected to" can mean directly fixed to or connected to a component, or indirectly fixed to or connected to a component.

[0053] like Figure 1 As shown, this embodiment provides a method for selecting greening plants, including the following steps S1 to S5:

[0054] Step S1: Divide the target area into sub-areas with different congestion levels based on the congestion delay index.

[0055] In practical applications, the congestion delay index can be obtained in real time by accessing the Gaode Map API. The target area can be a section of highway and its surrounding area. Based on the congestion delay index, the target area is divided into sub-areas with different congestion levels, such as light congestion sub-areas, moderate congestion sub-areas, and heavy congestion sub-areas.

[0056] Step S2: Obtain soil analysis data and plant physiological data corresponding to each candidate plant in the sub-region.

[0057] In practical applications, quadrats were set up in sub-regions with mild, moderate, and severe congestion. In sub-regions with different levels of congestion, healthy plants of candidate plants were selected for plant physiological data collection. In sub-regions with different levels of congestion, topsoil from the 0-20cm layer of healthy plants of candidate plants was selected for soil analysis data collection.

[0058] Specifically, the collected plant physiological data include: maximum net photosynthetic rate and the activities of key photosynthetic enzymes, etc. The carbon fixation of plants is calculated through the maximum net photosynthetic rate. The activities of key photosynthetic enzymes include: glyceraldehyde-3-phosphate dehydrogenase (GAPDH) activity, 3-phosphoglycerate kinase (PGK) activity, and ribulose diphosphate carboxylase / oxygenase (Rubisco) activity. The collected soil analysis data included soil carbon pool components, extracellular enzyme activities, and physicochemical properties. Soil carbon pool components included: inorganic carbon (IC) content, dissolved organic carbon (DOC) content, labile organic carbon (LOC) content, easily oxidizable organic carbon (ROC) content, and mineral-associated organic carbon (MOC) content. Extracellular enzyme activities included: solid-β-glutasidase (β-GC) activity, 1,4-β-D-glutamin cellobilhydrolase (CBH) activity, and solid-polyphenol oxidase (PPO) activity.

[0059] Step S3: Construct a structural equation model based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region, and determine the significant factors affecting each candidate plant by traffic based on the structural equation model.

[0060] Specifically, the construction of a structural equation model based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region includes:

[0061] The soil analysis data is processed to obtain soil treatment data, and the plant physiological data is processed to obtain plant treatment data;

[0062] An initial theoretical model was established based on the congestion delay index, soil treatment data, and plant treatment data.

[0063] The initial theoretical model is subjected to parameter estimation. If the evaluation index of the parameter estimation results meets the preset index, the structural equation model is obtained.

[0064] In practical applications, after data cleaning, normality verification, and dimensional standardization of soil analysis and plant physiological data, soil treatment data corresponding to the soil analysis data and plant treatment data corresponding to the plant physiological data are obtained. Specifically, data exceeding reasonable limits and containing logical contradictions in the soil analysis and plant physiological data are removed to ensure data accuracy; this can be achieved by plotting box plots to eliminate outliers. If missing values ​​exist, multiple imputation is used first, predicting missing values ​​through correlations between variables to preserve data integrity. Then, the Shapiro-Wilk test is used to verify the normality of the data; if the data is severely skewed, logarithmic transformation is performed. Data in the soil analysis and plant physiological data that conform to normality are standardized using Z-scores to unify dimensions for subsequent calculations.

[0065] Specifically, the establishment of the initial theoretical model based on the congestion delay index, soil treatment data, and plant physiological data includes:

[0066] Principal component analysis was performed on the extracellular enzyme activities in the soil treatment data to obtain the key extracellular enzyme activities.

[0067] Principal component analysis was performed on the carbon pool components in the soil treatment data to obtain the key carbon pool components;

[0068] Principal component analysis was performed on the physicochemical properties of the soil treatment data to obtain the key physicochemical properties;

[0069] Identify exogenous and endogenous variables, establish the first relationship between exogenous and endogenous variables, and establish the second relationship between endogenous variables;

[0070] Identify the endogenous latent variables and endogenous manifest variables of the endogenous variables, and establish a third relationship between the endogenous latent variables and endogenous manifest variables;

[0071] An initial theoretical model is established based on the first, second, and third relationships.

[0072] In practical applications, principal component analysis is performed on extracellular enzyme activity, carbon pool composition, and physicochemical properties to reduce variable dimensionality, achieve data dimensionality reduction, and solve the problem of collinearity. The identified exogenous variable is the congestion delay index, and the identified endogenous variables include: a first endogenous variable, a second endogenous variable, a third endogenous variable, a fourth endogenous variable, and a fifth endogenous variable; wherein, the first endogenous variable is the plant carbon fixation amount in the plant physiological data, the second endogenous variable is the activity of key photosynthetic enzymes in the plant physiological data, the third endogenous variable is the key carbon pool composition in the soil treatment data, the fourth endogenous variable is the key extracellular enzyme activity, and the fifth endogenous variable is the key physicochemical properties.

[0073] Specifically, in this application, the activities of key photosynthetic enzymes, key carbon pool components, key extracellular enzyme activities, and key physicochemical properties are considered as endogenous latent variables; GADPH activity, PGK activity, and Rubisco activity are considered as endogenous manifest variables of key photosynthetic enzyme activities; PPO activity and CBH activity are considered as endogenous manifest variables of key extracellular enzyme activities; ROC, LOC, and MOC are considered as endogenous manifest variables of key carbon pool components; and organic matter content is considered as an endogenous manifest variable of key physicochemical properties.

[0074] Specifically, an initial theoretical model is established based on the first, second, and third relationships. Then, the robust maximum likelihood method is used to estimate the parameters of the initial theoretical model. A model fit evaluation system is constructed using the root mean square error of approximation (RMSEA), the comparative fit index (CFI), and the standardized root mean square residual (SRMR). The preset indices are: RMSEA ≤ 0.08, CFI ≥ 0.95, and SRMR ≤ 0.08. If the parameter estimation results meet the preset indices, the resulting equation model is obtained. Based on the path coefficients of the structural equation, variables significantly affected by traffic are identified and used as significant factors.

[0075] Step S4: Calculate the first fitness of the candidate plants in the sub-region based on the congestion delay index of the sub-region and the significance factor of each candidate plant in the sub-region.

[0076] Specifically, the step of calculating the first fitness of candidate plants in a region based on the congestion delay index of the sub-region and the significance factors of each candidate plant in that region includes:

[0077] Principal component analysis was performed using the congestion delay index and significant factors as the original variables to obtain the first principal component and the second principal component.

[0078] The traffic delay index and the first weight coefficient of the significance factor are calculated based on the load vector of the first principal component and the load vector of the second principal component.

[0079] The first fitness of candidate plants in the region is obtained by weighting the traffic delay index and its first weight coefficient, and the significance factor and its first weight coefficient.

[0080] In practical applications, after performing principal component analysis on the original variables, the comprehensive coefficient of each original variable is calculated. The formula for calculating the comprehensive coefficient is as follows:

[0081] γ=(Z1·V PC1 +Z2·V PC2 ) / V

[0082] Where Z1 represents the loading vector of the original variable in the first principal component, V PC1 V represents the variance contribution rate of the first principal component, Z2 represents the loading vector of the original variables in the second principal component, and V PC2 Let X represent the variance contribution rate of the second principal component, and V represent the cumulative variance contribution rate of the first and second principal components. After calculating the comprehensive coefficient of the traffic delay index and the significance factor according to the comprehensive coefficient calculation formula, the comprehensive coefficient is normalized to obtain the first weight coefficient of the traffic delay index and the significance factor. Assuming the cumulative variance contribution rate of the first and second principal components is 90%, the loading vector of the first principal component is X = -0.3, Y1 = 0.85, Y2 = 0.82, and the loading vector of the second principal component is Y3 = 0.78, where X represents the traffic delay index and Y1-Y3 represent the significance factor. The comprehensive coefficient of X is calculated by combining the loading vectors of the first and second principal components, resulting in a comprehensive coefficient of (-0.3 × 6) / 2. The comprehensive coefficient of Y1 is (0.85×60%+0×30%) / 90%=0.57, the comprehensive coefficient of Y2 is (0.82×60%+0×30%) / 90%=0.55, and the comprehensive coefficient of Y3 is (0×60%+0.78×30%) / 90%=0.26. After normalizing the comprehensive coefficients of the significant factors of the congestion delay index, the corresponding first weight coefficients are obtained.

[0083] In practical applications, principal component analysis (PCA) can be used to extract the main effect patterns, eliminate secondary interferences, objectively quantify the true co-occurrence of congestion delay index and significant factors, avoid subjective bias, and accurately capture the synergistic effects between variables.

[0084] Step S5: Construct a plant selection model for each sub-region based on a genetic algorithm, and substitute the candidate plants into the plant selection model for each sub-region to obtain the target plants for each sub-region. The fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index, and the significance factor.

[0085] Specifically, the construction of plant selection models for each sub-region based on genetic algorithms includes:

[0086] Based on the sub-regions and training plants, establish a population set;

[0087] A fitness function for the plant selection model is constructed based on the congestion delay index, the significance factor, and the first fitness. Constraints are set on the significance factor, and the second fitness of the training plants in the population set is calculated based on the fitness function.

[0088] Based on the second fitness, selection, crossover, and mutation operations are performed iteratively on the training plants. During the iteration process, the second weight coefficient of the fitness function is determined through sensitivity analysis until the iteration termination condition is met, and then the plant selection model is obtained.

[0089] In practical applications, when designing the encoding, each chromosome represents a training plant. The number of training plants can be set to M, and i = 1. The training plants are labeled with i as the number. The gene sequence contains the significant factors corresponding to the training species, which reduces the redundant genes that may be included in random encoding and improves the convergence efficiency of the algorithm. The number of significant factors can be set to N, and j = 1. The significant factors are labeled with j as the number. The significant factors of the corresponding training plants are obtained in the sub-regions of each traffic congestion level, and the first fitness of each training plant in the sub-region is calculated to obtain the population set of the sub-region.

[0090] Specifically, calculating the second fitness of the training plants within the population set based on the fitness function includes:

[0091] Based on the congestion delay index and the preset maximum congestion delay index, the congestion suppression factor is calculated.

[0092] The actual carbon sink is calculated based on the plant carbon sequestration amount in the congestion suppression factor and the significant factors of the trained plants.

[0093] The regulatory intensity is obtained by calculating the sum of the weights of the significant factors of the trained plant, excluding plant carbon fixation.

[0094] The second fitness of the trained plant is obtained by calculating the sum of the actual carbon sink, the regulatory intensity, and the first fitness.

[0095] In practical applications, the formula for calculating the fitness function is:

[0096]

[0097] Wherein, Y1 represents plant carbon sequestration, X represents the congestion delay index, and X max w represents the maximum congestion delay index. j Y represents the second weighting coefficient of the j-th significant factor. j This represents the j-th significant factor. The congestion inhibition factor (1-X / X) was used to evaluate plant carbon sequestration. maxThis approach aims to suppress the physiological limitations of environmental stress on plant carbon sequestration, making the fitness function more closely reflect urban realities. The constraints include hard screening conditions such as setting the activity of key photosynthetic enzymes to be greater than or equal to a threshold and soil physicochemical properties pH ∈ [5.5, 7.5]. F1 represents the first fitness, and F2 represents the second fitness. The core objective of the fitness function is to maximize plant carbon sequestration while suppressing the negative impact of traffic congestion. The fitness function can calculate the second fitness of each training plant in the population set. During iteration, a hybrid strategy of elite retention and roulette wheel selection is used. The top 10% of training plants with the highest second fitness are retained for the next generation, and the remainder are selected probabilistically. Then, single-point crossover (80% probability) is performed, such as exchanging a significant factor between two training plants, like photosynthetic enzyme activity or soil indicators, simulating gene recombination. Mutation is then performed: randomly perturbing a significant factor (1%-5% probability), such as adjusting ROC content and key physicochemical properties, to introduce diversity. The initial weights of the second weight coefficient can be referenced from the path coefficients of the structural equation model, and the second weight coefficient is determined through sensitivity analysis. For the iteration termination condition, a maximum number of iterations (e.g., 200) or a threshold can be set where the second fitness changes less than a certain threshold for several consecutive generations (e.g., 10 generations). This threshold can be set to 1%.

[0098] After reaching the iteration termination condition, a plant selection model based on a genetic algorithm is obtained. This model can select appropriate greening plants according to the congestion level of a sub-region. For example, in sub-regions with mild, moderate, and severe congestion, Pittosporum tobira and Ligustrum lucidum are selected as candidate plants. Significant factors corresponding to candidate plants in sub-regions with different congestion levels are obtained, such as net photosynthetic rate, GAPDH activity, PGK activity, Rubisco activity, PPO activity, CBH activity, LOC, and MOC. Figure 2 and Figure 3 As shown, the carbon sequestration capacity of candidate plants was calculated based on net photosynthetic rate. Then, the first fitness of candidate plants in each sub-region was calculated based on the congestion delay index and the significance factor of the candidate plants. Each candidate plant was then substituted into the corresponding plant selection model to obtain the target plant for each sub-region. For example, in heavily congested urban environments, Pittosporum tobira exhibits stronger adaptability. Pittosporum tobira has a high photosynthetic rate and a higher content of stable components in its rhizosphere soil carbon pool, making it an excellent plant for improving urban carbon sequestration efficiency.

[0099] The greening plant selection method of the present invention uses structural equation modeling to screen out significant factors that are significantly affected by traffic, and uses these factors to calculate the first fitness of candidate plants as the comprehensive fitness of candidate plants. Then, a plant selection model is constructed based on the selected significant factors and genetic algorithm. The significant factors determined by the structural equation model play a guarantee role for the plant selection model constructed based on genetic algorithm, which can realize pre-validation and hard constraint embedding. Furthermore, the structural equation model enhances the interpretability of the results.

[0100] like Figure 4 As shown, this embodiment of the invention also provides a greening plant selection system, including:

[0101] The segmentation module 10 is used to divide the target area into sub-areas with different congestion levels based on the congestion delay index;

[0102] The acquisition module 20 is used to acquire soil analysis data and plant physiological data corresponding to each candidate plant in the sub-region;

[0103] The construction module 30 is used to construct a structural equation model based on the congestion delay index, soil analysis data and plant physiological data of the sub-region, and to determine the significant factors of traffic impact on each candidate plant based on the structural equation model.

[0104] The calculation module 40 is used to calculate the first fitness of the candidate plants in the region based on the congestion delay index of the sub-region and the significance factor of each candidate plant in the region;

[0105] The determination module 50 is used to construct a plant selection model corresponding to each sub-region based on a genetic algorithm, and to substitute the candidate plants into the plant selection model of each sub-region to obtain the target plants corresponding to each sub-region. The fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index and the significance factor.

[0106] Each module of the aforementioned greening plant selection system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules and units can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0107] like Figure 5 As shown, an embodiment of the present invention discloses a computer device, including a memory and a processor, wherein the memory stores a computer program;

[0108] The computer device can be a server, and its internal structure diagram can be as follows: Figure 5As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system, computer programs, and the database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements the greening plant selection method described in the above embodiments.

[0109] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0110] This invention also discloses a computer-readable storage medium storing a computer program that causes a computer to execute the greening plant selection method described in the above embodiments.

[0111] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for selecting greening plants, characterized in that, include: The target area is divided into sub-areas with different congestion levels based on the congestion delay index; Obtain soil analysis data and plant physiological data corresponding to each candidate plant in the sub-region; Structural equation modeling was constructed based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region. Based on the structural equation modeling, the significant factors affecting traffic for each candidate plant were determined. The first fitness of the candidate plants in the sub-region is calculated based on the congestion delay index of the sub-region and the significance factor of each candidate plant in the sub-region. A plant selection model for each sub-region is constructed based on a genetic algorithm. The candidate plants are substituted into the plant selection model for each sub-region to obtain the target plants for each sub-region. The fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index, and the significance factor.

2. The method for selecting greening plants as described in claim 1, characterized in that, The construction of a structural equation model based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region includes: The soil analysis data is processed to obtain soil treatment data, and the plant physiological data is processed to obtain plant treatment data; An initial theoretical model was established based on the congestion delay index, soil treatment data, and plant treatment data. The initial theoretical model is subjected to parameter estimation. If the evaluation index of the parameter estimation results meets the preset index, the structural equation model is obtained.

3. The method for selecting greening plants as described in claim 2, characterized in that, The initial theoretical model established based on the congestion delay index, soil treatment data, and plant physiological data includes: Principal component analysis was performed on the extracellular enzyme activities in the soil treatment data to obtain the key extracellular enzyme activities. Principal component analysis was performed on the carbon pool components in the soil treatment data to obtain the key carbon pool components; Principal component analysis was performed on the physicochemical properties of the soil treatment data to obtain the key physicochemical properties; Identify exogenous and endogenous variables, establish the first relationship between exogenous and endogenous variables, and establish the second relationship between endogenous variables; Identify the endogenous latent variables and endogenous manifest variables of the endogenous variables, and establish a third relationship between the endogenous latent variables and endogenous manifest variables; An initial theoretical model is established based on the first, second, and third relationships.

4. The method for selecting greening plants as described in claim 3, characterized in that, The exogenous variable is the congestion delay index, and the endogenous variables include: a first endogenous variable, a second endogenous variable, a third endogenous variable, a fourth endogenous variable, and a fifth endogenous variable; wherein, the first endogenous variable is the plant carbon sequestration in the plant physiological data, the second endogenous variable is the activity of key photosynthetic enzymes in the plant physiological data, the third endogenous variable is the key carbon pool components in the soil treatment data, the fourth endogenous variable is the activity of key extracellular enzymes, and the fifth endogenous variable is the key physicochemical properties.

5. The method for selecting greening plants as described in claim 1, characterized in that, The calculation of the first fitness of candidate plants in a region based on the congestion delay index of the sub-region and the significance factors of each candidate plant in that region includes: Principal component analysis was performed using the congestion delay index and significant factors as the original variables to obtain the first principal component and the second principal component. The traffic delay index and the first weight coefficient of the significance factor are calculated based on the load vector of the first principal component and the load vector of the second principal component. The first fitness of candidate plants in the region is obtained by weighting the traffic delay index and its first weight coefficient, and the significance factor and its first weight coefficient.

6. The method for selecting greening plants as described in claim 1, characterized in that, The method for constructing plant selection models for each sub-region based on genetic algorithms includes: Based on the sub-regions and training plants, establish a population set; A fitness function for the plant selection model is constructed based on the congestion delay index, the significance factor, and the first fitness. Constraints are set on the significance factor, and the second fitness of the training plants in the population set is calculated based on the fitness function. Based on the second fitness, selection, crossover, and mutation operations are performed iteratively on the training plants. During the iteration process, the second weight coefficient of the fitness function is determined through sensitivity analysis until the iteration termination condition is met, and then the plant selection model is obtained.

7. The method for selecting greening plants as described in claim 6, characterized in that, The step of calculating the second fitness of the training plants within the population set according to the fitness function includes: Based on the congestion delay index and the preset maximum congestion delay index, the congestion suppression factor is calculated. The actual carbon sink is calculated based on the plant carbon sequestration amount in the congestion suppression factor and the significant factors of the trained plants. The regulatory intensity is obtained by calculating the sum of the weights of the significant factors of the trained plant, excluding plant carbon fixation. The second fitness of the trained plant is obtained by calculating the sum of the actual carbon sink, the regulatory intensity, and the first fitness.

8. A greening plant selection system, characterized in that, include: The segmentation module is used to divide the target area into sub-areas with different congestion levels based on the congestion delay index; The acquisition module is used to acquire soil analysis data of the sub-region and plant physiological data of candidate plants in the region; A construction module is used to construct a structural equation model based on the congestion delay index, soil analysis data, and plant physiological data of the sub-region, and to determine the significant factors affected by traffic based on the structural equation model. The calculation module is used to calculate the first fitness of the candidate plants in the sub-region based on the congestion delay index of the sub-region and the significance factor of each candidate plant in the sub-region; The determination module is used to construct a plant selection model corresponding to each sub-region based on a genetic algorithm, and to substitute the candidate plants into the plant selection model of each sub-region to obtain the target plants corresponding to each sub-region. The fitness function of the plant selection model is constructed based on the first fitness, the congestion delay index and the significance factor.

9. A computer device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images