Method and related device for assessing bird diversity based on plant functional traits

Abstract

The embodiment of the application provides a bird diversity evaluation method based on plant functional traits and related equipment, and belongs to the technical field of biological diversity monitoring and evaluation; the method comprises the following steps: obtaining plant functional trait data of common plants and bird functional demand data of common birds in a target area; calculating a functional matching degree index indicating the matching degree between the plant functional traits of the common plants and the bird functional demands of the common birds in the target area based on the obtained data; inputting the functional matching degree index of the target area into a trained bird diversity evaluation model for calculation to obtain a bird diversity evaluation result of the target area; based on the matching between the plant functional traits and the bird functional demands, the bird diversity of the region is evaluated, the evaluation result has high interpretability, human factor interference in the evaluation process and negative impact on birds can be reduced, and the evaluation efficiency and accuracy are improved.

Description

Technical Field

[0001] This application relates to the field of biodiversity monitoring and assessment technology, and in particular to a method and related equipment for assessing bird diversity based on plant functional traits. Background Technology

[0002] Bird diversity plays a vital role in maintaining ecological balance within urban ecosystems. It not only participates in material cycling and energy flow but also effectively controls pest populations and facilitates plant seed dispersal. Therefore, accurately assessing bird diversity in urban green spaces is of paramount importance for the construction of urban green infrastructure and the improvement of ecological environment quality. Currently, traditional methods for assessing bird diversity mainly include quadrat and transect methods, both of which rely on manual field observations. These methods are significantly affected by the complexity of the urban environment, the professionalism of the observers, and weather conditions, greatly impacting the accuracy of the observations. Furthermore, the scattered distribution of urban green spaces makes it difficult to achieve comprehensive coverage using these traditional methods, failing to meet the needs for long-term, dynamic monitoring of bird diversity. The tag-recapture method is extremely difficult to implement in urban environments, where bird ranges are severely disturbed by human activity. The capture and tagging process not only easily harms the birds but also consumes enormous human and material resources, making it difficult to promote on a regional scale. In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0003] The main objective of this application is to propose a method and related equipment for assessing bird diversity based on plant functional traits. This method assesses the bird diversity of a region based on the matching between plant functional traits and bird functional needs. While ensuring high interpretability of the assessment results, it can reduce human interference and negative impacts on birds during the assessment process, thereby improving the efficiency and accuracy of the assessment.

[0004] To achieve the above objectives, one aspect of this application proposes a method for assessing bird diversity based on plant functional traits, the method comprising: Acquire plant functional trait data for several common plants within the target area to obtain a plant functional trait database; Obtain functional requirement data of several common bird species within the target area to obtain a bird functional requirement database; The functional matching index of the target area is calculated based on the plant functional trait database and the bird functional requirement database. The functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area. The functional matching index of the target area is input into the trained bird diversity assessment model for calculation to obtain the bird diversity assessment result of the target area.

[0005] In some embodiments, the calculation of the functional matching index of the target region based on the plant functional trait database and the bird functional requirement database includes: Based on the plant functional trait database and the bird functional requirement database, the functional matching degree of a single plant species to a single bird species is calculated to obtain the functional matching degree of each common bird species to several common plants. Based on the functional matching degree of each common bird to several common plants, the functional matching degree index of each common bird to the overall plant community of the target area is obtained. Based on the functional matching index of each common bird species to the overall plant community of the target area, a vector is constructed to obtain the matching index of the target area.

[0006] In some embodiments, the functional matching degree of the single plant species to the single bird species is calculated using the following formula:

[0007] in, For the first Common bird species to the first Functional matching degree of common plants; Let be a similarity function, used to calculate the _th _ The first of the common plants Plant functional trait values With the The first of the common birds Functional requirements for individual birds The degree of matching between them; For the first Plant functional trait values The weighting of plant functional traits indicates their importance in bird habitat selection.

[0008] In some embodiments, the functional matching index of each common bird species to the overall plant community of the target area is calculated using the following formula:

[0009] in, For the first Functional matching index of common bird species to the overall plant community of the target area; For the first The abundance of common plants.

[0010] In some embodiments, the bird diversity assessment model is trained in the following manner: Choose a number of plants and a number of birds; Historical plant functional trait data of several selected plant species within the target area are obtained to form a historical database of plant functional traits; historical bird functional requirement data of several selected bird species within the target area are obtained to form a historical database of bird functional requirements. The historical functional matching index of the target area is calculated based on the historical database of plant functional traits and the historical database of bird functional requirements. The historical functional matching index of the target area is input into the bird diversity assessment pre-model for calculation to obtain the predicted results of bird diversity in the target area; The predicted results of bird diversity in the target area are compared with the actual results. Based on the comparison results, the model parameters of the pre-model for bird diversity assessment are adjusted until the preset requirements are met. The trained bird diversity assessment model is obtained based on the adjustment results.

[0011] In some embodiments, when acquiring the historical plant functional trait data and the historical bird functional requirement data, the acquired data is preprocessed in the following manner: Outliers in the acquired data were identified and processed using box plotting. And / or, fill in the missing data in the acquired data according to the multiple interpolation method; And / or, standardize the data of different dimensions in the acquired data.

[0012] In some embodiments, the method further includes: Adjust the selection criteria for plants and birds; The bird diversity assessment model is trained based on the adjusted plant and bird selection scheme to optimize the bird diversity assessment model.

[0013] To achieve the above objectives, another aspect of this application proposes a bird diversity assessment system based on plant functional traits, the system comprising: The data acquisition module is used to acquire plant functional trait data of several common plants in the target area to obtain a plant functional trait database; and to acquire bird functional requirement data of several common birds in the target area to obtain a bird functional requirement database. The calculation module is used to calculate the functional matching index of the target area based on the plant functional trait database and the bird functional requirement database; the functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area. Evaluation module: The functional matching index of the target area is input into the trained bird diversity evaluation model for calculation to obtain the bird diversity evaluation result of the target area.

[0014] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method, system, electronic device, and storage medium for assessing bird diversity based on plant functional traits. This scheme obtains a plant functional trait database by acquiring plant functional trait data of several common plants within a target area; it also obtains a bird functional requirement database by acquiring bird functional requirement data of several common bird species within the target area; based on the plant functional trait database and the bird functional requirement database, it calculates a functional matching index for the target area; the functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species within the area; the functional matching index of the target area is input into a trained bird diversity assessment model for calculation to obtain the bird diversity assessment result for the target area. In this regard, the method of this application considers the close relationship between plants and birds in urban green spaces, assessing the bird diversity of the area based on the matching between plant functional traits and bird functional requirements. While ensuring high interpretability of the assessment results, it can reduce human interference and negative impacts on birds during the assessment process, improving assessment efficiency and accuracy. Attached Figure Description

[0017] Figure 1 This is a flowchart of a bird diversity assessment method based on plant functional traits provided in an embodiment of this application; Figure 2 This is a schematic diagram comparing the model prediction results and actual results provided in the embodiments of this application; Figure 3This is a flowchart of another bird diversity assessment method based on plant functional traits provided in an embodiment of this application; Figure 4 This is a structural block diagram of a bird diversity assessment system based on plant functional traits provided in an embodiment of this application; Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] 1) Quadrat layout: In ecological surveys, the location, size and number of quadrats are determined in a selected area according to certain principles and methods, so as to reflect the overall vegetation or biological population characteristics through local samples.

[0022] 2) Random Forest Model: An ensemble learning algorithm that improves classification or regression accuracy by constructing multiple decision trees and combining their voting or averaging results.

[0023] 3) Functional Matching Score (FMS) of a single plant species to a single bird species: refers to the degree of adaptation and fit between specific functional traits provided by plants (such as nectar depth and fruit size) and corresponding functional traits of birds (such as beak length and beak width) in ecological interactions.

[0024] 4) Community Functional Matching Index (CFMI): A quantitative indicator that comprehensively measures the degree of ecological adaptation between the various functional traits provided by the plant community (such as the number of flowers and fruits, and canopy structure) and the overall functional needs of the bird community (such as diet composition and habitat preferences).

[0025] 5) Abundance: refers to the abundance of individuals of a species in a community (such as absolute abundance and relative abundance), and is one of the basic parameters used to weight the importance of different species when calculating the functional matching index.

[0026] 6) Shannon-Wiener index: It is a commonly used index in ecology to measure the species diversity of a community, taking into account both species richness (number of species) and evenness (the degree of uniformity in the distribution of the number of individuals of each species).

[0027] Bird diversity plays a vital role in maintaining ecological balance within urban ecosystems. It not only participates in material cycling and energy flow but also effectively controls pest populations and facilitates plant seed dispersal. Therefore, accurately assessing bird diversity in urban green spaces is of paramount importance for the construction of urban green infrastructure and the improvement of ecological environment quality. Currently, traditional methods for assessing bird diversity mainly include quadrat and transect methods, both of which rely on manual field observations. These methods are significantly affected by the complexity of the urban environment, the professionalism of the observers, and weather conditions, greatly impacting the accuracy of the observations. Furthermore, the scattered distribution of urban green spaces makes it difficult to achieve comprehensive coverage using these traditional methods, failing to meet the needs for long-term, dynamic monitoring of bird diversity. The tag-recapture method is extremely difficult to implement in urban environments, where bird ranges are severely disturbed by human activity. The capture and tagging process not only easily harms the birds but also consumes enormous human and material resources, making it difficult to promote on a regional scale. There is a close relationship between plants and birds in urban green spaces. The species composition of plants directly determines the diversity of food available to birds and the types of habitats they can find; plant height, canopy density, and branch angles affect nesting and roosting space for birds; fruit size, nectar quantity, and leaf area directly determine food availability for birds; and the matching degree between flowering / fruiting periods and bird migration and breeding periods determines the timeliness of resources. However, current technologies have not yet established a complete assessment framework "from plant functional traits to bird diversity support capacity," resulting in the inability of plant functional trait research findings to directly serve the formulation of biodiversity management and conservation policies.

[0028] In view of this, this application provides a method, system, electronic device, and storage medium for assessing bird diversity based on plant functional traits. This scheme obtains a plant functional trait database by acquiring plant functional trait data of several common plants within a target area; it also obtains a bird functional requirement database by acquiring bird functional requirement data of several common bird species within the target area; based on the plant functional trait database and the bird functional requirement database, it calculates a functional matching index for the target area; the functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species within the area; the functional matching index of the target area is input into a trained bird diversity assessment model for calculation to obtain the bird diversity assessment result for the target area. This method considers the close relationship between plants and birds in urban green spaces, assessing bird diversity in the area based on the matching between plant functional traits and bird functional requirements. While ensuring high interpretability of the assessment results, it reduces human interference and negative impacts on birds during the assessment process, improving assessment efficiency and accuracy.

[0029] The bird diversity assessment method based on plant functional traits provided in this application relates to the field of biodiversity monitoring and assessment. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a tablet, laptop, desktop computer, etc., but is not limited thereto; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application implementing the bird diversity assessment method based on plant functional traits, etc., but is not limited to the above forms.

[0030] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0031] Figure 1 This is an optional flowchart of a bird diversity assessment method based on plant functional traits provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S103.

[0032] Step S101: Obtain plant functional trait data of several common plants in the target area to obtain a plant functional trait database; obtain bird functional requirement data of several common birds in the target area to obtain a bird functional requirement database.

[0033] Acquire plant functional trait data of common plants and bird functional requirements data of common birds in the target area, and construct corresponding databases as the data basis for subsequent calculations.

[0034] Step S102: Based on the plant functional trait database and the bird functional requirements database, the functional matching index of the target area is calculated; the functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area.

[0035] Considering the matching between plant functional traits and bird functional needs, the functional matching index of the target area is calculated as data input for subsequent evaluation models.

[0036] Step S103: Input the functional matching index of the target area into the trained bird diversity assessment model for calculation to obtain the bird diversity assessment result of the target area.

[0037] Finally, the calculated regional functional matching index is input into the trained evaluation model to calculate the corresponding bird diversity evaluation results.

[0038] In some embodiments, obtaining plant functional trait data and bird functional requirement data requires identifying a green area; the area is identified through quadrat layout, specifically including: Layout principles: Based on the vertical structure and distribution characteristics of urban green space vegetation, a layered layout strategy of "trees as the base and shrubs and grasses nested within" is adopted to ensure coverage of different vegetation types, dominant species, and microhabitats, comprehensively reflecting the overall characteristics of the green space plant community. Priority is given to laying quadrats in areas with frequent bird activity, such as tree forest edges, dense shrub areas, and areas rich in herbaceous plants, while taking into account both uniformity and representativeness.

[0039] Layout method: A combination of systematic sampling and random sampling was used. Sampling points were laid out in a 1km × 1km grid. If there were ≥3 vegetation types (forest, shrubland, grassland) within a grid, an additional quadrat was placed within each vegetation type. Quadrat area and number: Tree quadrats are uniformly 20m × 20m in size, and the number is determined based on the tree coverage area (3-5 quadrats for <5 hectares, 5-15 quadrats for 5-20 hectares, and 2-3 additional quadrats for every 5 hectares above 20 hectares, with a total of ≥10 quadrats); each tree quadrat is paired with 5 5m × 5m shrub quadrats (1 at each corner and one in the center), and 1-2 quadrats are set up per 500m² in pure shrub areas; 3-5 1m × 1m herbaceous quadrats are randomly placed within each tree / shrub quadrat (≥5 within tree quadrats and ≥3 within shrub quadrats). The spacing between all quadrats is ≥50 meters to avoid mutual interference.

[0040] Quadrat marking and recording: The four corner coordinates of each quadrat were accurately located using GPS and marked with poles. At the same time, basic information such as the terrain (e.g., flat land, slope, depression), surrounding environment (e.g., nearby roads, buildings, water bodies, etc.), and intensity of human interference at the location of the quadrat were recorded to provide background information for subsequent data interpretation and analysis.

[0041] In some embodiments, the above-mentioned plant functional trait database is constructed by including common plant species and their functional traits in the target area, wherein: Species composition and distribution: Within each quadrat, detailed information such as plant species name, number of individuals, diameter at breast height (DBH), and basal diameter were recorded. For herbaceous plants, their canopy coverage was recorded. All quadrat data were compiled to construct a catalog of urban green space plant species, calculate the relative abundance and importance of each species, and clarify the distribution pattern and dominant position of species in green spaces.

[0042] Determination of core functional traits: including but not limited to the following traits: Specific leaf area (SLA), calculated by collecting mature leaf samples, measuring the area with a leaf area meter, drying and weighing, and calculating SLA (leaf area / dry weight); Leaf dry matter content (LDMC), determined by the ratio of fresh weight to dried weight of leaves; Plant height (H), measured using a laser rangefinder combined with a UAV lidar system; Wood density (WD), calculated by measuring the volume and dry weight of standard wood segments; Seed quality (SM), measured using an electronic balance to determine the average weight of 1000 seeds; Nectar volume (NV), measured by extracting nectar from flowers using a micro-syringe; Fruit type (FT), recorded according to classification as fleshy fruit, dry fruit, stone fruit, etc.; First flowering date (FFD), recorded annually using a phenological monitoring system. Leaf area index (LAI) was measured in the field using a vegetation canopy analyzer; canopy density (CD) was calculated using drone aerial images combined with image processing technology to determine the vegetation coverage ratio; branch angle (BA) was measured at the junction of the plant trunk and primary branch using a protractor, accurate to 1°, and the angle between the branch and the trunk was recorded; bark roughness (BarkR) was assessed using a qualitative grading method.

[0043] Data quality control methods: (1) Take the mean of three repeated measurements; (2) Use the 3σ method + Grubbs test (α=0.05) to remove outliers; (3) Use random forest to recover missing values ​​(missForest R package, mtry=3).

[0044] In some embodiments, the aforementioned bird functional requirements database is constructed by including common bird species in the target area and their functional requirements, specifically including: Multi-dimensional demand data extraction: Data on bird diet (herbivorous, carnivorous, omnivorous, etc.), feeding frequency, and food preferences were extracted from global open databases; information on nest site preferences (canopy, tree hole, shrubland, etc.), breeding season duration, and migration type was obtained from the BirdLife database (BirdLife International); features such as body mass, feeding layer (ground, middle layer, canopy layer), and flocking behavior were extracted from the HBW database (HBW Alive), covering a total of 15 core functional dimensions (specifically: diet type, foraging height, nest site type, nest substrate, body size, activity rhythm, breeding season, migration status, burrow / nest requirement, nectar dependence, fruit dependence, insect dependence, ground foraging requirement, canopy foraging requirement, disturbance resistance index, and roosting height); considering branch utilization preference data, the bird's habitat selection tendency for branches at different angles was clarified.

[0045] In some embodiments, the process of calculating the functional matching index of the target area based on a plant functional trait database and a bird functional requirement database includes, but is not limited to, steps S201 to S203: Step S201: Calculate the functional matching degree of a single plant species to a single bird species based on the plant functional trait database and the bird functional requirement database, and obtain the functional matching degree of each common bird species to several common plants.

[0046] First, starting from the smallest level, we calculate the functional matching degree of a single common bird species with several single common plants in the target area; specifically, we consider how well the functional traits of the plants match the functional needs of the birds.

[0047] Step S202: Calculate the functional matching degree of each common bird species with respect to several common plants to obtain the functional matching degree index of each common bird species to the overall plant community of the target area.

[0048] After calculating the functional matching degree of a single common bird species with each single common plant species, the next step is to consider the functional matching degree of a single common bird species with the overall plant community of the target area from the perspective of the overall plant community.

[0049] Step S203: Construct a vector based on the functional matching index of the overall plant community in the target area for each common bird species to obtain the matching index of the target area.

[0050] Finally, by summarizing and constructing vectors for the functional matching of various common bird species with the overall plant community of the target area, the matching degree index of the target area is obtained.

[0051] In some embodiments, the functional matching degree of a single plant species to a single bird species is calculated using the following formula, as shown in equation (1):

[0052] in, For the first Common bird species to the first Functional matching degree of common plants; Let be a similarity function, used to calculate the _th _ ... The first of the common plants Plant functional trait values With the The first of the common birds Functional requirements for individual birds The degree of matching between them; For the first Plant functional trait values The weighting of plant functional traits indicates their importance in bird habitat selection.

[0053] To calculate the functional similarity between a single plant species and a single bird species, the results need to be normalized to the [0, 1] interval. Different calculation methods can be used to calculate similarity for different types of functional traits. For continuous traits (such as height and canopy density), similarity can be calculated using a Gaussian kernel function or a linear decay function. For example, if birds prefer a height of 10m, a 15m tree might have a similarity of 0.8, while a 5m tree might have a similarity of 0.5.

[0054] For categorical / ranked traits (e.g., fruit type, bark roughness): use an exact matching function (1 for a match, 0 for a non-match) or a predefined matching matrix (e.g., a match of 1 between berry plants and fruit-eating birds, and a match of 0.2 between berry plants and insectivorous birds).

[0055] In some embodiments, the functional matching index of each common bird species to the overall plant community of the target area is calculated by the following formula, as shown in Equation (2):

[0056] in, For the first Functional matching index of common bird species to the overall plant community of the target area; For the first The abundance of common plants.

[0057] This index reflects common bird species. The level of comprehensive functional resources available in the target area; The higher the elevation, the more likely the target area is to attract and support birds. Survival.

[0058] Furthermore, the matching degree index of the target area can be represented as a vector of land function matching degree indices for several common bird species, i.e. These common birds can serve as representatives of functional groups of birds.

[0059] In some embodiments, the bird diversity assessment model is trained in the following manner: Step S301: Select several kinds of plants and several kinds of birds.

[0060] Several plants and birds were selected as representatives.

[0061] Step S302: Obtain historical plant functional trait data of several selected plant species in the target area to obtain a historical database of plant functional traits; obtain historical bird functional requirement data of several selected bird species in the target area to obtain a historical database of bird functional requirements.

[0062] Obtain the corresponding data as the basis for model training.

[0063] Step S303: Calculate the historical functional matching index of the target area based on the historical database of plant functional traits and the historical database of bird functional requirements.

[0064] Calculate the relevant data as input for model training.

[0065] Step S304: Input the historical functional matching index of the target area into the bird diversity assessment pre-model for calculation to obtain the predicted results of bird diversity in the target area.

[0066] The relevant data is input into the model to obtain the training prediction results.

[0067] Step S305: Compare the predicted results of bird diversity in the target area with the actual results, adjust the model parameters of the pre-model for bird diversity assessment based on the comparison results until the preset requirements are met, and obtain the trained bird diversity assessment model based on the adjustment results.

[0068] Finally, based on the difference between the predicted and actual results, the model is adjusted to obtain a well-trained bird diversity assessment model.

[0069] Optionally, the output of the bird diversity assessment model includes, but is not limited to, predicted bird diversity indices, such as species richness (S) and the Shannon-Wiener index (S). ) etc.; such as Figure 2 The diagram shown compares the predicted species richness and Shannon index with the actual values. Figure 2 (1) Comparison of predicted and actual results for species richness. Figure 2 (2) indicates the comparison between the predicted and actual results of the Shannon index.

[0070] Optionally, the bird diversity assessment model provided in this application can be based on models such as random forest models or gradient boosting machines, which can better handle complex nonlinear relationships between variables.

[0071] Optionally, auxiliary variables can be introduced during training; optional auxiliary variables include green space area, surrounding environmental disturbance index, etc.; specific auxiliary data can be obtained in the following ways: (1) Geographical environment data: Using Geographic Information System (GIS) technology, data such as the geographical location, area, and topography (elevation, slope, aspect) of urban green spaces are obtained. The topographic relief of green spaces is analyzed using digital elevation models (DEM), and the land use types (such as residential areas, commercial areas, industrial areas, nature reserves, etc.) around the green spaces are analyzed in combination with remote sensing images to clarify the potential impact of geographical environmental factors on bird diversity in urban green spaces. (2) Climate data: Collect climate data of the city over many years, including temperature, precipitation, sunshine, wind speed, etc.

[0072] (3) Human interference data: Information on human interference in urban green spaces, such as the number of tourists, types of tour activities, and green space maintenance measures (pruning, fertilization, pest and disease control), is obtained through field surveys, questionnaires and statistical data from urban management departments.

[0073] In some embodiments, when acquiring historical plant functional trait data and historical bird functional requirement data, the acquired data are preprocessed in the following manner: Outliers in the acquired data were identified and processed using box plots. And / or, fill in missing data in the acquired data using multiple interpolation methods; And / or, standardize data of different dimensions in the acquired data.

[0074] By preprocessing the acquired data, the quality of the input data to the model can be effectively improved.

[0075] In some embodiments, the method further includes: Adjust the selection schemes for plants and birds; based on the adjusted selection schemes, train the bird diversity assessment model to optimize it.

[0076] By proposing different training data input schemes and training models based on them, it is possible to select models with better performance and achieve scientific and precise ecological optimization design.

[0077] In summary, the embodiments of this method have at least the following beneficial effects: (1) Reduce human interference: This invention does not require direct contact with birds, avoiding the disturbance to birds caused by capture, tagging and other operations, minimizing the interference with the natural behavior and ecological environment of urban birds, protecting the living and breeding space of birds in urban green spaces, and conforming to the concept of urban ecological protection.

[0078] (2) The assessment results are more objective and stable: plant functional traits are relatively stable in the urban environment and are less affected by short-term human activities and environmental fluctuations. The assessment of bird diversity based on plant functional traits avoids the subjectivity of human observation and the randomness of the urban environment. The assessment results are more objective, stable and reliable, and can truly reflect the long-term trend of bird diversity in urban green spaces, providing a reliable data basis for urban ecological protection. (3) The assessment efficiency is significantly improved: By collecting plant functional trait data in batches and combining them with an efficient assessment model, the assessment of bird diversity in large areas of urban green space can be completed quickly. Compared with traditional methods, it saves a lot of manpower, material resources and time costs, can adapt to the characteristics of rapid changes in the urban ecological environment, and meet the needs of urban ecological protection and management for rapid acquisition of bird diversity information. (4) High accuracy of assessment: By using advanced data analysis methods and machine learning algorithms, we can deeply explore the complex relationship between the functional traits of plants and bird diversity in urban green spaces, comprehensively consider the comprehensive impact of various factors in the urban environment, such as the urban heat island effect and the intensity of human disturbance, on plants and birds, construct a high-precision assessment model, improve the accuracy of bird diversity assessment, provide accurate scientific basis for urban ecological protection decision-making, and help the precise governance of urban ecological environment. (5) Possess dynamic assessment capabilities: Through regular verification and updating of the model, it can capture the dynamic changes in bird diversity in urban green spaces in a timely manner, adapt to the impact of changes in green space area, vegetation type, ecological function and other factors on bird diversity during urban development; provide strong support for the dynamic adjustment of urban ecological protection measures, realize the sustainable management of urban ecosystems, and promote the coordinated development of urban ecological environment and biodiversity.

[0079] (6) High interpretability of assessment results: Traditional assessment indicators (such as green space area) can only answer "where there are many birds", but cannot explain "why there are many birds here"; the method of this invention directly links the actual needs of birds through the functional traits of plants, such as crown size reflecting habitat space and fruit abundance reflecting food supply. The assessment results can clearly indicate whether the high bird diversity of a certain green space is due to abundant food or complex habitat structure, and the underlying ecological reasons can be understood.

[0080] like Figure 3 As shown, Figure 3 A flowchart illustrating another method for assessing bird diversity based on plant functional traits provided in this application; wherein the method includes the following steps: 1. Selection of sample plots and layout of quadrats Based on the "Classification Standard for Urban Green Space", representative urban green spaces were selected as research plots, including any one or more of the following categories: park green space, protective green space, ancillary green space, plaza land, and regional green space. Record basic information such as the geographical location, area, and boundaries of the sample plot; Several survey quadrats were set up within the sample plots to ensure coverage of different vegetation types, dominant species and microhabitats, so as to fully reflect the overall characteristics of the green space plant community. Priority should be given to setting up quadrats in areas where birds frequently visit, such as the edges of arbor forests, dense shrublands, and areas rich in herbaceous plants; The specific area and number of quadrats are as follows: tree quadrats are uniformly 20m×20m, and the number is determined according to the tree coverage area (3-5 quadrats for <5 hectares, 5-15 quadrats for 5-20 hectares, and 2-3 additional quadrats for every 5 hectares above 20 hectares, with a total of ≥10 quadrats); each tree quadrat is equipped with 5 5m×5m shrub quadrats (1 at each of the four corners and the center), and 1-2 quadrats are set up for every 500㎡ in pure shrub areas; 3-5 1m×1m herbaceous quadrats are randomly placed in each tree / shrub quadrat (≥5 in tree quadrats and ≥3 in shrub quadrats); the spacing between all quadrats is ≥50 meters to avoid mutual interference.

[0081] 2. Investigation and determination of plant functional traits Plant functional trait data were systematically collected within each plot: (1) Structural and functional traits: including tree height, diameter at breast height, crown width, canopy closure, shrub height and cover, herb height and cover, bark roughness and vegetation vertical structure complexity index. (2) Leaf economic traits: including specific leaf area, leaf dry matter content, leaf nitrogen content, leaf phosphorus content, and leaf thickness; (3) Reproductive functional traits: including the duration of flowering and fruiting period, fruit abundance, size, color and type, seed size and quality; (4) Phenological functional traits: including evergreen / decaying, leaf unfolding period, leaf fall period, and duration of green period.

[0082] (5) Community structure index: count the number and quantity of tree, shrub and herb species in the quadrat, and calculate the proportion of each life form.

[0083] The aforementioned trait data can be obtained through a combination of field measurements, laboratory analysis, and literature database searches.

[0084] 3. Data collection for bird diversity survey Bird diversity was surveyed using a combination of transect and point methods. Bird observations were conducted concurrently with the vegetation survey, choosing clear, low-wind mornings (6:00-10:00) and evenings (16:00-18:00). The species names, numbers, behavioral types, and habitat use levels of birds observed within the sample plots were recorded. Surveys were conducted 2-3 times per month, covering the breeding season (March-July) and wintering season (November-February of the following year). Bird diversity indices were calculated, including species richness index, Shannon-Wiener diversity index, Simpson dominance index, and abundance index. Species richness (S) is the total number of bird species recorded.

[0085] The Shannon-Wiener diversity index can be calculated using the following formula (3): ,in For the first The proportion of individuals of a particular bird species to the total number of individuals.

[0086] The Simpson dominance index is calculated as shown in equation (4): ; The bird abundance index is the total number of bird individuals surveyed.

[0087] At the same time, birds are divided into different functional groups. Based on diet, they are divided into insectivorous birds, fruit-eating birds, grain-eating birds, omnivorous birds, and birds of prey. Based on nesting habits, they are divided into tree-nesting birds, bush-nesting birds, ground-nesting birds, and building-nesting birds. Based on migratory behavior, they are divided into resident birds, summer migratory birds, and winter migratory birds.

[0088] 4. Data quality control The collected raw data underwent preprocessing: (a) outlier detection and processing, using box plots to identify and process outliers; (b) missing value imputation, using multiple imputation to fill in missing data for a small number of data points; (c) data standardization, using Z-score standardization for trait indices of different dimensions; and (d) multicollinearity diagnosis, calculating the variance inflation factor (VIF) and removing highly collinear variables with a VIF greater than 10. Principal component analysis (PCA) and correlation analysis were used to screen key functional trait indices that were significantly correlated with bird diversity from the measured plant functional trait indices, which were then used as input variables for model construction.

[0089] 5. Prediction Model Construction and Training Using bird diversity indicators as the dependent variable and key plant functional traits as independent variables, a random forest algorithm was used as the base model. Hyperparameter optimization, including the number of decision trees, maximum depth, and minimum number of split samples, was performed using grid search to determine the optimal parameter combination. Ten-fold cross-validation was used to evaluate model performance, with root mean square error (RMSE) and coefficient of determination (R²) as evaluation metrics. Importance scores for each plant functional trait variable were calculated to identify the key traits that contribute most to bird diversity prediction. The final prediction model was determined when the model's R² reached a preset threshold (e.g., ≥0.75).

[0090] 6. Bird diversity prediction and output The functional trait data of the plants in the urban green space to be evaluated are input into the trained prediction model, and the model outputs the predicted value of bird diversity for that green space. Based on the prediction results, an assessment report on bird diversity in urban green spaces can be generated, providing a scientific basis for urban green space planning and management.

[0091] In summary, the embodiments of this method have at least the following beneficial effects: (1) Reduce survey costs and improve assessment efficiency: Traditional methods require professionals to repeatedly observe bird activity in different seasons, which is time-consuming and labor-intensive. The method in this embodiment assesses bird diversity potential by measuring relatively fixed plant traits. Assessors only need basic plant identification skills and can complete data collection with a single plant survey. The assessment work significantly reduces manpower, time and financial costs, making rapid assessment of large-scale urban green spaces possible.

[0092] (2) Support for long-term dynamic monitoring and trend analysis: The method in this embodiment can establish long-term monitoring plots, enabling continuous tracking and assessment of bird diversity through periodic (e.g., annual) collection of plant trait data. Compared to traditional bird surveys that require frequent operations, the method in this embodiment significantly reduces the cost and workload of long-term monitoring, making it possible to establish a large-scale, long-term bird diversity monitoring network. Through the accumulation of data over many years, the interannual variation trends of bird diversity in urban green spaces can be analyzed, the effectiveness of urban greening policies and management measures can be evaluated, key drivers of biodiversity change can be identified, and a scientific basis for adaptive management can be provided. This dynamic monitoring capability is crucial for understanding the evolution of urban ecosystems and formulating effective biodiversity conservation strategies.

[0093] (3) The assessment results have clear ecological explanatory power: The method in this embodiment directly relates the actual needs of birds through plant functional traits, such as crown size reflecting habitat space and fruit abundance reflecting food supply. The assessment results can clearly indicate whether the high bird diversity of a certain green space is due to abundant food or complex habitat structure, and can help understand the underlying ecological reasons.

[0094] (4) The assessment results can guide specific green space management measures: The method in this embodiment provides a scientific decision support tool for urban green space planning and management. By quantifying the relationship between plant functional traits and bird diversity, the impact of different vegetation configuration schemes on biodiversity can be clarified, and plant species and configuration patterns that are conducive to bird diversity can be actively selected in green space design. For example, increasing the proportion of fruiting plants, increasing canopy complexity, and extending the flowering and fruiting period can all effectively improve bird diversity. Management departments can use this method to assess the ecological quality of existing green spaces, identify key areas for biodiversity conservation, and optimize resource allocation.

[0095] Please see Figure 4 This application also provides a bird diversity assessment system based on plant functional traits, which can implement the above-mentioned method. The system includes: The data acquisition module is used to acquire plant functional trait data of several common plants in the target area to obtain a plant functional trait database; and to acquire bird functional requirement data of several common birds in the target area to obtain a bird functional requirement database. The calculation module is used to calculate the functional matching index of the target area based on the plant functional trait database and the bird functional requirement database. The functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area. Evaluation module: The functional matching index of the target area is input into the trained bird diversity assessment model for calculation, and the bird diversity assessment results of the target area are obtained.

[0096] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0097] Please see Figure 5 This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can include any smart terminal such as a tablet computer or an in-vehicle computer.

[0098] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0099] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0100] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0101] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0102] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of this application, and do not constitute a limitation on the technical solutions provided in this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in this application are also applicable to similar technical problems.

[0103] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0106] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0107] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0109] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0110] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for assessing bird diversity based on plant functional traits, characterized in that, The method includes the following steps: Obtain plant functional trait data for several common plants in the target area to create a plant functional trait database; Obtain functional requirement data of several common bird species within the target area to obtain a bird functional requirement database; The functional matching index of the target area is calculated based on the plant functional trait database and the bird functional requirement database. The functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area. The functional matching index of the target area is input into the trained bird diversity assessment model for calculation to obtain the bird diversity assessment result of the target area.

2. The method according to claim 1, characterized in that, The functional matching index of the target region is calculated based on the plant functional trait database and the bird functional requirement database, including: Based on the plant functional trait database and the bird functional requirement database, the functional matching degree of a single plant species to a single bird species is calculated to obtain the functional matching degree of each common bird species to several common plants. Based on the functional matching degree of each common bird to several common plants, the functional matching degree index of each common bird to the overall plant community of the target area is obtained. Based on the functional matching index of each common bird species to the overall plant community of the target area, a vector is constructed to obtain the matching index of the target area.

3. The method according to claim 2, characterized in that, The functional compatibility of a single plant species with a single bird species is calculated using the following formula: in, For the first Common bird species to the first Functional matching degree of common plants; Let be a similarity function, used to calculate the _th _ ... The first of the common plants Plant functional trait values With the The first of the common birds Functional requirements for individual birds The degree of matching between them; For the first Plant functional trait values The weighting of plant functional traits indicates their importance in bird habitat selection.

4. The method according to claim 3, characterized in that, The functional matching index of each common bird species to the overall plant community of the target area is calculated using the following formula: in, For the first Functional matching index of common bird species to the overall plant community of the target area; For the first The abundance of common plants.

5. The method according to claim 1, characterized in that, The bird diversity assessment model was trained in the following manner: Choose a number of plants and a number of birds; Historical plant functional trait data of several selected plant species within the target area are obtained to form a historical database of plant functional traits; historical bird functional requirement data of several selected bird species within the target area are obtained to form a historical database of bird functional requirements. The historical functional matching index of the target area is calculated based on the historical database of plant functional traits and the historical database of bird functional requirements. The historical functional matching index of the target area is input into the bird diversity assessment pre-model for calculation to obtain the predicted results of bird diversity in the target area; The predicted results of bird diversity in the target area are compared with the actual results. Based on the comparison results, the model parameters of the pre-model for bird diversity assessment are adjusted until the preset requirements are met. The trained bird diversity assessment model is obtained based on the adjustment results.

6. The method according to claim 5, characterized in that, When acquiring the historical plant functional trait data and the historical bird functional requirement data, the acquired data are preprocessed in the following manner: Outliers in the acquired data were identified and processed using box plotting. And / or, fill in the missing data in the acquired data according to the multiple interpolation method; And / or, standardize the data of different dimensions in the acquired data.

7. The method according to claim 5, characterized in that, The method further includes: Adjust the selection criteria for plants and birds; The bird diversity assessment model is trained based on the adjusted plant and bird selection scheme to optimize the bird diversity assessment model.

8. A bird diversity assessment system based on plant functional traits, characterized in that, The system includes: The data acquisition module is used to acquire plant functional trait data of several common plants in the target area to obtain a plant functional trait database; and to acquire bird functional requirement data of several common birds in the target area to obtain a bird functional requirement database. The calculation module is used to calculate the functional matching index of the target area based on the plant functional trait database and the bird functional requirement database; the functional matching index indicates the degree of matching between the plant functional traits of common plant species and the bird functional requirements of common bird species in the area. Evaluation module: The functional matching index of the target area is input into the trained bird diversity evaluation model for calculation to obtain the bird diversity evaluation result of the target area.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

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

Images