A low-maintenance flower bed landscape planning and design method

Abstract

The application discloses a low-maintenance flower field landscape planning and design method, relates to the field of landscape planning and design, and comprises the following steps: determining a potential plant canopy space interference area and determining a suitable matching area between plant species and the environment; based on existing root system growth structure data of candidate plants, analyzing possible growth overlapping areas of each plant root system in underground space, and identifying underground competition sensitive areas of the plant root system; comprehensively considering the canopy space interference area, the suitable matching area between the plant and the environment, and the underground competition sensitive area of the root system, screening plant species combinations suitable for a planning area through spatial multi-factor coupling calculation, and generating a corresponding plant planting layout scheme; and the application realizes scientific optimization of plant layout and species combination, effectively reduces maintenance requirements of the flower field in a later period, and ensures long-term stability and low maintenance of the landscape.

Description

Technical Field

[0001] This invention relates to the field of landscape planning and design, specifically a method for planning and designing low-maintenance flower border landscapes. Background Technology

[0002] Currently, with the continuous expansion of urban greening construction, various landscape flower borders have gradually become an important way to improve the quality of the urban environment. However, traditional flower border planning methods mostly focus only on the visual effect of landscape plants, lacking a systematic analysis of plant growth characteristics and environmental adaptability when designing plant combinations and layouts. This often leads to problems such as poor growth or increased maintenance costs due to space competition between plants after actual planting, making it difficult to meet the long-term, stable, low-maintenance management needs.

[0003] Specifically, existing flower border landscape design techniques lack a holistic consideration and comprehensive assessment of key factors such as the spatial expansion trend of plant canopies, the characteristics of underground root competition, and differences in environmental adaptability. This makes it impossible to accurately and effectively predict and mitigate spatial competition risks during plant growth, severely limiting the long-term landscape effect and low-maintenance performance of flower borders. Therefore, how to scientifically and rationally determine plant layout and combinations based on an in-depth analysis of plant spatial expansion trends, environmental adaptability, and underground root competition has become a crucial technical challenge that urgently needs to be addressed in the field of flower border landscape planning. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a low-maintenance flower border landscape planning and design method.

[0005] To achieve the above objectives, the present invention provides a low-maintenance flower border landscape planning and design method, comprising: Based on the previous crown expansion characteristics of the candidate plants, we analyzed the sensitive locations where the expansion of the plant crowns may cause interference with the growth of neighboring plants, and identified potential areas of spatial interference with the plant crowns. Based on the spatial distribution of soil nutrients and light conditions within the flower border planning area, assess the differences in adaptability of different plants and determine the suitable matching area between plant species and environment; Based on existing root growth structure data of candidate plants, we analyze the possible overlapping areas of root growth in underground space and identify sensitive areas of underground competition among plant roots. Taking into account areas of canopy space interference, suitable matching areas between plants and the environment, and sensitive areas of root system underground competition, the system uses spatial multi-factor coupling calculation to select plant species combinations suitable for the planning area and generate corresponding plant planting layout schemes.

[0006] Compared with the prior art, the beneficial effects of the present invention are: This invention analyzes the expansion trend of plant canopies and identifies potential canopy spatial interference areas, predicting possible spatial interference locations between plants in advance, thereby reducing the risk of canopy conflict during plant growth from the source.

[0007] This invention accurately determines suitable matching areas by assessing the differences in the adaptability of different plants to soil nutrients and light conditions, ensuring efficient coordination between plant species and the environment, thereby reducing the difficulty and cost of subsequent maintenance.

[0008] This invention identifies sensitive areas of underground competition among plant roots, integrates canopy space interference areas and environmental matching areas for spatial multi-factor coupling calculation, effectively selects suitable plant species combinations for the planning area and generates a reasonable layout scheme, thereby achieving the goal of long-term stable low-maintenance flower border landscape. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating the method of the present invention. Detailed Implementation

[0011] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] Please see Figure 1 This embodiment provides a low-maintenance flower border landscape planning and design method, including: S101: Based on the previous crown expansion characteristics of the candidate plants, analyze the sensitive locations that may cause interference to the growth of neighboring plants when the plant crowns expand, and determine the potential spatial interference areas of the plant crowns. It should be understood that the plant crown expansion characteristics specifically refer to the spatial movement and change trend of the crown boundary on a two-dimensional plane over multiple consecutive historical growth periods, including the spatial movement direction, spatial movement distance, and overall movement pattern of the crown boundary feature points. These characteristics are used to predict the future crown expansion range and positional changes of plants, in order to identify locations where the plant crown may spatially overlap or intersect with neighboring plants.

[0013] Specifically, determining potential areas of spatial disturbance in plant canopy space includes: Based on the data on the changes in the crown boundary of the candidate plants during multiple historical growth periods, calculate the spatial movement trend of the plant crown boundary. It should be noted that the crown boundary variation data here specifically refers to the set of location data of crown boundary feature points recorded at the end of each historical growth period of the candidate plants in a two-dimensional coordinate space. To ensure effective comparison of data from different observation periods, a unified local two-dimensional spatial coordinate system needs to be established, with the origin of the spatial coordinates for each plant set at the base point of the plant's rootstock.

[0014] For example, taking lavender as an example, the coordinates of the crown boundary feature points of the plant are recorded at the end of three consecutive historical growth cycles (denoted as cycles t=1, 2, 3), and are denoted as follows: Then the spatial displacement vector of each crown feature point between two adjacent historical observation periods. It can be calculated as: ; It should be noted that after calculating multiple continuous spatial displacement vectors of each crown boundary feature point using the above formula, the average spatial movement trend vector of each crown boundary feature point can be further calculated. The specific calculation method is as follows: In the formula, n is the total number of historical growth periods (for example, if continuous observation is conducted for 3 years, then n=2). The spatial displacement vector of the crown boundary feature point within the t-th historical observation period; The average spatial movement trend vector of the characteristic points at the crown boundary represents the overall trend of plant crown expansion.

[0015] Spatial clustering algorithms were used to cluster the spatial movement trends of the crown boundary, and the clustered areas of crown boundary movement trends were identified as sensitive locations that may cause interference to the growth of neighboring plants. Understandably, the spatial clustering algorithm here is used to identify clusters of feature points with similar and concentrated trends in plant canopy expansion, thereby discovering spatial regions with relatively consistent canopy expansion trends. These regions are sensitive locations that may cause interference to the growth of neighboring plants when the canopy expands in the future.

[0016] The identification of clustered areas of crown boundary movement trends includes: Based on the spatial vector direction of the movement trend of the crown boundary, calculate the spatial similarity of the movement trend of each crown boundary; It should be noted that spatial similarity of movement trends is used to quantitatively describe the degree of similarity between the spatial movement directions of feature points at different crown boundaries.

[0017] For example, for feature points i and j at the crown boundary, their average spatial movement trend vectors are denoted as: The similarity of spatial movement trends between the feature points of the two crown boundaries. It can be obtained through cosine similarity calculation: In the formula, , represents the vector dot product; , representing a vector The modulus length; , representing a vector The length of the module.

[0018] It is understandable that the above calculations yielded... The range of values ​​for is [ 1,1]. Among them, The closer the two feature points are to 1, the more consistent their spatial movement trends are. A value of 1 indicates that the two feature points move in completely opposite directions.

[0019] Using spatial similarity of movement trends as a clustering condition, a spatial clustering network is constructed, and the movement trend clustering area at the crown boundary is determined by dividing the network structure. Specifically, the spatial clustering network is a network structure constructed using crown boundary feature points as network nodes and spatial similarity of movement trends as the network edge connection condition. A network connection is established between two nodes only when the trend similarity between them reaches or exceeds a preset threshold.

[0020] For example, the trend similarity threshold is set to 0.85, that is, when the following conditions are met: A connection is established between node i and node j; otherwise, no connection is established. This results in a complete spatial clustering network.

[0021] It should be understood that after the network is constructed, density clustering methods (such as the DBSCAN algorithm) are used to divide the network into structural regions, thereby identifying multiple clusters of canopy boundary movement trends. These regions represent the locations where the canopy of the candidate plants may expand in the future, and are also sensitive locations that may cause interference with the growth of neighboring plants.

[0022] Based on the degree of overlap between the sensitive location and the initial canopy width of the surrounding plants, potential areas of spatial disturbance to the plant canopy width are identified; It should be noted that the actual identification of potential interference areas should also take into account the overlap of the canopy space layout of the candidate plant and the adjacent plants when they were initially planted, so as to ensure the accuracy of the judgment of potential interference areas.

[0023] Specifically, for each identified sensitive location area, the overlap area of ​​the canopy between the candidate plant and the neighboring plants under the initial planting layout is calculated, thereby determining the area where there is a potential risk of canopy interference.

[0024] For example, let the initial crown area of ​​the candidate plant be A, the initial crown area of ​​the adjacent plant be B, and the initial crown overlap area between the two be C. Then, the initial crown overlap ratio R can be defined as: ; It is understandable that the overlap ratio R calculated using the above formula ranges from [0,1]. The closer R is to 1, the higher the initial overlap of the plant canopies, and the greater the likelihood of future spatial interference; conversely, the closer R is to 0, the less overlap there is initially, and the very low likelihood of future spatial interference.

[0025] Specifically, in actual landscape planning, an overlap ratio threshold is usually set, for example, 0.3 as the threshold. Then, when the overlap ratio meets the following conditions: When the corresponding overlapping area is located within the sensitive location area, the area is identified as a potential area of ​​interference with plant canopy space.

[0026] S102: Based on the spatial distribution of soil nutrients and light conditions within the flower border planning area, assess the differences in adaptability of different plants and determine the suitable matching area between plant species and environment; It should be noted that the assessment of plant adaptability differences mentioned here refers to the quantitative analysis of the suitability differences of different plants under different environmental conditions based on the growth characteristics of the candidate plants and the spatial distribution data of specific soil nutrients and light conditions in the flower border planning area, so as to obtain the matching relationship between different plant species and environmental space, and thus further determine the suitable planting area.

[0027] Specifically, determining the suitable matching area between plant species and the environment includes: Acquire spatial distribution data of soil nutrients and light within the flower border planning area, and construct a plant environmental suitability evaluation model based on the growth characteristics of the candidate plants; It should be understood that the plant environmental suitability evaluation model is a model based on the relationship between the historical growth data of the candidate plant and environmental factors, used to describe the suitability of the plant's growth performance under specific environmental conditions.

[0028] The construction of the plant environmental suitability evaluation model includes: Data on nutrient absorption efficiency and light utilization efficiency of different plants during their historical growth cycles were collected, and the above data were spatially matched and fused to form a training dataset for plant environmental adaptability. It should be noted that nutrient absorption efficiency here refers to the efficiency of plants in absorbing key nutrient elements (such as nitrogen, phosphorus, and potassium) from the soil within a specific time period; light utilization efficiency refers to the efficiency of plants in using light energy for biomass accumulation through photosynthesis.

[0029] For example, taking lavender as an example, during three consecutive growth cycles (represented by cycles t=1,2,3), nutrient absorption efficiency data and light utilization efficiency data of the plant are recorded under different soil nutrient and light conditions in the planned area. Based on the collected spatial coordinates, a spatial data recording format is formed: In the formula, Let represent the nutrient absorption efficiency of lavender at location coordinates (x, y) during the t-th growth cycle; Let represent the light utilization efficiency of lavender at location coordinates (x, y) during the t-th growth cycle.

[0030] Furthermore, spatial data fusion methods are used to interpolate and spatially match the collected data to obtain a complete training dataset for plant environmental adaptability, which can then be used for subsequent model training.

[0031] A pre-built neural network model was trained using a plant environmental adaptability training dataset, and the model outputs an evaluation value of the spatial growth suitability of plants under different nutrient and light conditions. It should be understood that the neural network model can adopt a multilayer perceptron (MLP) structure, including an input layer, a hidden layer, and an output layer.

[0032] Specifically, the input layer includes soil nutrient characteristic parameters and light intensity characteristic parameters; the output layer is the plant growth suitability evaluation value. The number of hidden layers and neurons can be adjusted according to specific training needs.

[0033] For example, the input variables of a neural network model are represented as follows: In the formula, N, P, and K represent the nitrogen, phosphorus, and potassium contents in the soil at the corresponding location of the plant, respectively; L is the light intensity data at that location.

[0034] The output variable is the suitability evaluation value S, which is limited to the range of [0,1]. It represents the degree of plant growth suitability in the corresponding spatial location. A value close to 1 indicates that the environment is highly suitable for plant growth, and a value close to 0 indicates that the environment is less suitable for plant growth.

[0035] It should be noted that the neural network model is trained using conventional supervised learning methods (such as backpropagation algorithm), and the model weight parameters are optimized using known plant growth efficiency data in the training dataset, ultimately resulting in a stable model that can be used for spatial suitability evaluation.

[0036] Based on the spatial suitability evaluation output of the neural network model, a plant environmental suitability evaluation model is generated. Specifically, once the neural network model is trained, by inputting environmental parameter data of the spatial location to be evaluated, the neural network can output the corresponding plant environmental suitability evaluation value, thereby completing the evaluation of the spatial distribution of plant growth suitability in the entire planning area and generating a complete plant environmental suitability evaluation model.

[0037] Based on the output results of the plant environmental suitability evaluation model, the differences in plant growth capacity in different environmental spatial regions are analyzed to obtain the spatial distribution of plant suitability gaps. It should be noted that the plant suitability gap here refers to the difference in suitability evaluation values ​​between different plants under the same spatial environmental conditions. This gap is used to determine the relative superiority or inferiority of the growth suitability of different plants under the same spatial conditions.

[0038] Specifically, for any spatial location (x, y), let the suitability evaluation values ​​of plant A and plant B be respectively... The fitness gap between the two plants It can be calculated as: The plant suitability gap at each spatial location within the entire planning area is calculated based on the above formula, thus forming a spatial distribution map of the plant suitability gap.

[0039] By using a spatial gap minimization strategy, suitable matching areas between plant species and the environment can be determined from the spatial distribution of plant suitability gaps. Understandably, the spatial gap minimization strategy here is to select plant types with high suitability evaluation values ​​and small gaps in each spatial location in order to achieve the best match between plants and the environment.

[0040] For example, for any spatial location (x, y), the plant species with the highest suitability evaluation value is selected, and a plant suitability gap threshold is set (e.g., When the fitness difference between any two plants... Less than or equal to this threshold, that is: If the value is 0, it means that the location is suitable for planting both types of plants; otherwise, it is only suitable for planting the type of plant with the higher suitability rating.

[0041] By employing the aforementioned strategy of minimizing spatial gaps, suitable matching areas between various plant species and their environment are determined, thus providing a foundation for subsequent optimization of plant layout and combinations.

[0042] S103: Based on the existing root growth structure data of the candidate plants, analyze the possible overlapping areas of root growth in the underground space and identify the sensitive areas of underground competition of plant roots. It should be noted that the sensitive area for underground competition of plant roots here refers to the area where the roots of different plants may intersect and be densely packed in the underground space. Identifying the sensitive area for underground competition of roots can effectively avoid problems of nutrient and water competition caused by root competition during future planting, thereby achieving the goal of low maintenance in flower border planning.

[0043] Specifically, the identification of underground competition-sensitive areas of plant roots includes: Collect three-dimensional spatial growth structure data of the root system of the candidate plants, and use spatial geometric calculation methods to determine the spatial distribution density of the root nodes of each plant. It should be understood that three-dimensional spatial structure data of plant roots typically includes the three-dimensional spatial coordinates (x, y, z) of root nodes. Based on these spatial coordinate data, the distribution density of each root node in the underground space can be further calculated to analyze the density of root distribution.

[0044] For example, taking the root structure data of plant i as an example, the three-dimensional coordinates of the plant root nodes are recorded as follows: In the formula, Let be the coordinates of the kth root node of plant i; Let i be the total number of root nodes of plant i.

[0045] Specifically, the spatial distribution density can be calculated using a spatial voxel partitioning method based on the root node coordinates. The specific method is as follows: A regular three-dimensional grid is established in the underground space. The size of the grid cell can be set according to the accuracy of the actual root system data (e.g., a cubic grid with a length, width, and height of 5cm). Then, by counting the number of root nodes falling into each grid cell, the distribution density value of the nodes in each grid cell can be obtained.

[0046] The spatial hotspot detection method was used to detect the spatial distribution density of root nodes to obtain the hotspot areas of plant root density. It should be noted that the root density hotspots here refer to areas in underground space with relatively high node distribution density and strong spatial aggregation. These areas may become the basis for sensitive areas of root competition in the future.

[0047] The process of obtaining the hotspot region of plant root density includes: The root node coordinate data is mapped to the grid cells of the underground space, and the spatial aggregation intensity of the nodes in each grid cell is calculated. Specifically, the spatial clustering intensity mentioned above can be calculated by evaluating the relative relationship between node density and its neighborhood density.

[0048] For example, a spatial clustering intensity index for a certain grid cell is defined. for: In the formula, This represents the node density within the grid cell, which is the number of nodes in the cell divided by the cell volume. This is the average node density of the neighborhood of this cell (e.g., the 3×3×3 neighboring cells centered on this cell).

[0049] Understandable, The larger the value, the higher the root node density of the unit is relative to its neighborhood density, that is, the stronger the spatial aggregation of the root system of the unit.

[0050] Local spatial autocorrelation analysis was used to identify root density hotspots with high aggregation intensity and that meet the preset statistical characteristics. It should be noted that the classical method can be used for local spatial autocorrelation analysis. The method, specifically the calculation formula, is as follows: In the formula, Let be the local spatial autocorrelation value of element i; The spatial cohesion intensity value of element j ; This represents the elements of the spatial weight matrix (adjacent elements are 1, and non-adjacent elements are 0). S is the average aggregation intensity of all elements; S is the standard deviation of the aggregation intensity of all elements; n is the total number of elements.

[0051] Preferably, when the unit's The value is greater than the preset statistical threshold (e.g.: If the confidence level is 99%, then the unit can be determined to belong to the root density hotspot region.

[0052] After identifying the root density hotspots of each plant through the above process, the spatial overlap between the hotspots is further analyzed.

[0053] Based on the spatial overlap of root density hotspots of different plants, the underground competition sensitive areas of plant roots can be identified; Specifically, the method for identifying sensitive areas of root competition in the underground region is as follows: First, the spatial distribution of root density hotspots for different plants is obtained; then, spatial overlap analysis is used to identify spatial units with significant overlap between hotspots of different plants, and the degree of overlap can be expressed by an overlap index. Quantitative expression: In the formula, Let be the total volume of the hotspot regions for plant i and plant j, respectively; This represents the total volume of the overlapping portion of the two hotspot regions.

[0054] For example, if the overlap index threshold is set to 0.3, then when the overlap index meets the following conditions... At that time, the corresponding spatial area was identified as a sensitive area for underground competition of the root system.

[0055] S104: Taking into account the canopy space interference area, the suitable matching area between plants and the environment, and the sensitive area of ​​root underground competition, the combination of plant species suitable for the planning area is selected through spatial multi-factor coupling calculation, and the corresponding plant planting layout scheme is generated. It should be noted that by comprehensively considering the spatial distribution characteristics of the above-mentioned canopy space interference area, the suitable matching area between plants and the environment, and the sensitive area of ​​root underground competition, spatial multi-factor coupling calculations are performed to select a suitable combination of plant species and planting layout scheme, thereby effectively reducing the workload of subsequent maintenance.

[0056] Specifically, the selection of suitable plant species combinations for the planned area includes: Based on the spatial distribution of canopy spatial disturbance areas, plant-environment suitable matching areas, and root system underground competition sensitive areas, a multi-dimensional set of spatial constraints is constructed. It should be understood that the set of multidimensional spatial constraints here is established by integrating the spatial information of the above three types of spatial regions to constrain the selection of plant combinations.

[0057] Specifically, the set of multidimensional space constraints is represented as: In the formula, This indicates the spatial constraints corresponding to the area of ​​spatial interference in the canopy, specifically including the overlapping areas of plant canopy expansion trends; This indicates the spatial constraints corresponding to the suitable matching area between plants and the environment, including the suitable areas for different plant species to soil nutrients and light conditions; This indicates the spatial constraints corresponding to the sensitive areas of underground competition among root systems, including areas where different plant root systems overlap in the underground space.

[0058] Based on the set of multidimensional spatial constraints, spatial conflict analysis is performed on the selected plant combinations to quantify the degree of spatial conflict of each plant combination. Specifically, spatial conflict analysis is quantified by defining a spatial conflict index SC. For example, the formula for calculating the spatial conflict index for plant combination i is as follows: In the formula, This represents the degree of conflict of plant combination i within the canopy space disturbance area; The conflict index represents the degree of adaptation of plant combination i within the suitable matching area between plants and environment; The root conflict index of plant combination i in the root-scarce competition sensitive area; the weight coefficient. satisfy Preferably, by way of example, take .

[0059] For example, for the plant combination "lavender-coreleaf", the spatial conflict indices of the three regions mentioned above are calculated respectively, and the spatial conflict index SC is calculated in combination with the weighting coefficients. In actual calculation, the index value is between 0 and 1, where the closer the value is to 0, the lower the degree of spatial conflict.

[0060] By ranking the degree of spatial conflict, the plant species combination with the lowest degree of spatial conflict is selected to obtain the plant species combination suitable for the planning area; It should be noted that the combinations ranked according to the spatial conflict index are selected as suitable combinations of plant species.

[0061] For example, by calculating the spatial conflict index of several plant combinations, such as "lavender-phlox", "coreopsis-phlox", and "lavender-coreopsis", the spatial conflict index is obtained respectively. If the spatial conflict index of the "lavender-phlox" combination is the lowest, then this combination is preferred as the plant species combination that is ultimately suitable for the planning area.

[0062] Specifically, generating the corresponding plant planting layout scheme includes: Calculate the initial spatial layout of the overall plant combination based on the initial spatial position of the plant species combination in the suitable matching area; It is understandable that the initial spatial layout is the preliminary arrangement of plant combinations within a spatial area. Specifically, based on suitable matching areas, the selected plant combinations are spatially initialized according to their initial suitable area positions to obtain the initial spatial layout scheme for each plant.

[0063] For example, taking the plant combination "lavender-phlox" as an example, based on the aforementioned suitable matching area spatial distribution, lavender is initially arranged in an area with strong sunlight and good soil drainage, and phlox is initially arranged in an area with ample underground space and good adaptability, thereby determining the initial spatial layout.

[0064] A spatial layout optimization algorithm is used to optimize and iterate the initial state of the spatial layout, taking the canopy space interference area and the root system underground competition sensitive area as spatial constraints, and generate the corresponding plant planting layout scheme. Specifically, the spatial layout optimization algorithm preferably employs a genetic algorithm (GA), which obtains a plant planting layout scheme through iterative optimization. The objective function is to minimize the spatial conflict index of the layout scheme. The genetic algorithm process is disclosed as follows: First, the initial layout state is used as the initial population, and the position coordinates of each plant layout are represented by an encoding method. Then, define the fitness function F, for example, by using the reciprocal of the aforementioned spatial conflict index SC as the fitness function: In the formula, For example: (), used to prevent the denominator from being zero; Furthermore, the genetic algorithm iteratively updates the population layout through selection, crossover, and mutation operations, selecting individuals with larger fitness function values ​​as the next generation population, and repeating the iteration until convergence; Finally, when the population converges (for example, the change in the optimal fitness function value is less than 0.01% over 10 consecutive iterations, or the maximum number of iterations is reached), the iteration is terminated, and the final plant planting layout scheme is determined.

[0065] For example, through the above optimization, it was finally determined that "lavender" is located in the center of the planning area with good light, and "phlox" is arranged in the outer space. The root systems of the two plants intersect and the degree of canopy interference is low, thus obtaining the optimal low-maintenance plant layout scheme, ensuring the coordination and maintainability of future plant growth, and achieving the low-maintenance design goal.

[0066] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A low-maintenance flower border landscape planning and design method, characterized in that, include: Based on the previous crown expansion characteristics of the candidate plants, we analyzed the sensitive locations where the expansion of the plant crowns may cause interference with the growth of neighboring plants, and identified potential areas of spatial interference with the plant crowns. Based on the spatial distribution of soil nutrients and light conditions within the flower border planning area, assess the differences in adaptability of different plants and determine the suitable matching area between plant species and environment; Based on existing root growth structure data of candidate plants, we analyze the possible overlapping areas of root growth in underground space and identify sensitive areas of underground competition among plant roots. Taking into account areas of canopy space interference, suitable matching areas between plants and the environment, and sensitive areas of root system underground competition, the system uses spatial multi-factor coupling calculation to select plant species combinations suitable for the planning area and generate corresponding plant planting layout schemes.

2. The method according to claim 1, characterized in that, The process of identifying potential areas of spatial disturbance in plant canopy space includes: Based on the data on the changes in the crown boundary of the candidate plants during multiple historical growth periods, calculate the spatial movement trend of the plant crown boundary. Spatial clustering algorithms were used to cluster the spatial movement trends of the crown boundary, and the clustered areas of crown boundary movement trends were identified as sensitive locations that may cause interference to the growth of neighboring plants. Based on the degree of overlap between the sensitive location and the initial canopy width of the surrounding plants, potential areas of spatial disturbance to the plant canopy width are identified.

3. The method according to claim 2, characterized in that, The identified areas of clustered movement trends at the crown boundary include: Based on the spatial vector direction of the movement trend of the crown boundary, calculate the spatial similarity of the movement trend of each crown boundary; Using spatial similarity of movement trends as a clustering condition, a spatial clustering network is constructed, and the movement trend clustering area at the crown boundary is determined by dividing the network structure.

4. The method according to claim 1, characterized in that, The determination of suitable matching areas between plant species and the environment includes: Acquire spatial distribution data of soil nutrients and light within the flower border planning area, and construct a plant environmental suitability evaluation model based on the growth characteristics of the candidate plants; Based on the output results of the plant environmental suitability evaluation model, the differences in plant growth capacity in different environmental spatial regions are analyzed to obtain the spatial distribution of plant suitability gaps. By using a spatial gap minimization strategy, suitable matching areas between plant species and the environment can be determined from the spatial distribution of plant suitability gaps.

5. The method according to claim 4, characterized in that, The construction of the plant environmental suitability evaluation model includes: Data on nutrient absorption efficiency and light utilization efficiency of different plants during their historical growth cycles were collected, and the above data were spatially matched and fused to form a training dataset for plant environmental adaptability. A pre-built neural network model was trained using a plant environmental adaptability training dataset, and the model outputs an evaluation value of the spatial growth suitability of plants under different nutrient and light conditions. Based on the spatial suitability evaluation output of the neural network model, a plant environmental suitability evaluation model is generated.

6. The method according to claim 1, characterized in that, The identification of underground competitive sensitive areas of plant roots includes: Collect three-dimensional spatial growth structure data of the root system of the candidate plants, and use spatial geometric calculation methods to determine the spatial distribution density of the root nodes of each plant. The spatial hotspot detection method was used to detect the spatial distribution density of root nodes to obtain the hotspot areas of plant root density. Based on the spatial overlap of root density hotspots of different plants, sensitive areas of underground competition for plant roots can be identified.

7. The method according to claim 6, characterized in that, The process of obtaining the hotspot region of plant root density includes: The root node coordinate data is mapped to the grid cells of the underground space, and the spatial aggregation intensity of the nodes in each grid cell is calculated. Local spatial autocorrelation analysis was used to identify root density hotspots with high aggregation intensity and that meet the preset statistical characteristics.

8. The method according to claim 1, characterized in that, The selection of suitable plant species combinations for the planning area includes: Based on the spatial distribution of canopy spatial disturbance areas, plant-environment suitable matching areas, and root system underground competition sensitive areas, a multi-dimensional set of spatial constraints is constructed. Based on the set of multidimensional spatial constraints, spatial conflict analysis is performed on the selected plant combinations to quantify the degree of spatial conflict of each plant combination. By ranking the degree of spatial conflict, the plant species combination with the lowest degree of spatial conflict is selected to obtain the plant species combination suitable for the planning area.

9. The method according to claim 1, characterized in that, The generation of the corresponding plant planting layout scheme includes: Calculate the initial spatial layout of the overall plant combination based on the initial spatial position of the plant species combination in the suitable matching area; A spatial layout optimization algorithm is adopted, taking the canopy space interference area and the root system underground competition sensitive area as spatial constraints, to optimize and iterate the initial state of the spatial layout and generate the corresponding plant planting layout scheme.

Images