Landscape garden planting planning management system based on terrain environment analysis

Abstract

The invention discloses a landscape garden planting planning management system based on terrain environment analysis, and mainly relates to the technical field of garden planting planning. Comprising a data acquisition and processing module used for collecting and preprocessing environmental data of terrain, climate and soil of a target garden area; the data feature extraction module is used for extracting key features and forming multi-dimensional environment feature vectors; the environment area division module is used for performing clustering analysis on the garden area through a self-adaptive clustering algorithm to form different environment areas; and the plant demand module is used for constructing a plant demand map. The method has the beneficial effects that comprehensive and accurate information support can be provided for garden design, so that the efficiency and the quality of garden planning are improved.

Description

Technical Field

[0001] The invention relates to the technical field of garden planting planning, in particular to a landscape garden planting planning management system based on terrain environment analysis. Background Art

[0002] Garden plants are plant materials suitable for landscaping, including woody and herbaceous flowering, foliage or fruiting plants, as well as protective plants and economic plants suitable for gardens, green spaces and scenic spots. Plants used for indoor flower decoration are also garden plants. Garden plants are divided into two categories: woody garden plants and herbaceous garden plants. In addition, they also include ferns, aquatic plants, cactus succulents and carnivorous plants. As people's living standards continue to improve, people's pursuit of the quality of garden plants is gradually increasing.

[0003] At present, garden plants are often planned and managed through artificial selection during planting, which can easily place plants in an environment that is not conducive to their growth, thus causing problems such as difficulty in plant growth.

[0004] Therefore, there is an urgent need for a landscape planting planning and management system based on terrain environment analysis to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a landscape gardening planting planning and management system based on terrain environment analysis, which can provide comprehensive and accurate information support for garden design, thereby improving the efficiency and quality of garden planning.

[0006] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0007] Provide a landscape planting planning and management system based on terrain environment analysis, including:

[0008] The data acquisition and processing module is used to collect environmental data on the topography, climate and soil of the target garden area and pre-process it using data cleaning and normalization algorithms;

[0009] Data feature extraction module: used to extract key features from preprocessed environmental data to form a multi-dimensional environmental feature vector;

[0010] Environmental area division module: used to perform cluster analysis on garden areas through adaptive clustering algorithm, classify areas with similar environmental characteristics into the same category, and form different environmental areas;

[0011] Plant demand module: used to construct a plant demand map, associate plants with environmental characteristics, and form a plant demand map.

[0012] Preferably, the data collection and processing module performs a preprocessing process of cleaning the environmental data, including:

[0013] The collected topography, climate, and soil in the target garden area are input into the set D = {D 1 , D 2 , …, D n}, Q = {Q 1 , Q 2 , …, Q n}、T={T 1 , T 2 , …, T n}, where n represents the total amount of data collected, and the data in the data sets D, Q, and T are screened for data outliers, missing values, error values, and duplicate values, data filling is performed on missing values, data deletion is performed on duplicate values, and smoothing is performed on outliers and error values ​​based on the binning algorithm;

[0014] The data acquisition and processing module performs a preprocessing process of normalizing the environmental data, including:

[0015] The original data in the cleaned data sets D, Q, and T are linearly transformed to the range of [0, 1]:

[0016]

[0017] Among them, V x Represents the value of the data after linear transformation, S old represents the mean of the original data, S min Represents the minimum value in the original data, S max Indicates the maximum value in the original data.

[0018] Preferably, the performing smoothing on the abnormal values ​​and the error values ​​based on a binning algorithm comprises:

[0019] Arrange the data in data sets D, Q, and T according to their numerical values;

[0020] Divide the data sets D, Q, and T into several boxes according to the number of record rows, and each box has the same number of records;

[0021] Replace all the data in a bin with the mean of all the data in that bin:

[0022]

[0023] Among them, x i is the i-th data point in the box, and m is the total number of data points in the box;

[0024] The smoothed data sets D, Q, and T are obtained.

[0025] Preferably, the feature extraction process performed by the data feature extraction module includes:

[0026] Perform feature extraction on terrain data:

[0027] Construct triangular surfaces within the target garden area;

[0028] Establish a space equation for each triangular face to describe its geometric shape;

[0029] Calculate the vertical distance from the point projected on the ground plane to the triangle surface, and find the point with the largest distance as the most significant terrain feature point in the current triangle surface;

[0030] By setting different scale factors, the precision of terrain feature extraction can be controlled;

[0031] Using the extracted terrain feature points, the triangular surface is further split and divided to iteratively extract terrain features;

[0032] Extract climate characteristics:

[0033] Calculate the average values ​​of temperature, precipitation and wind speed in the climate data of the target garden area within a certain period of time;

[0034] Extract soil characteristics:

[0035] Extract the type, texture and fertility of soil data in the target garden area, analyze and extract features of its physical and chemical properties;

[0036] The terrain, climate and soil characteristics extracted above are integrated into a multi-dimensional environmental feature vector:

[0037] V=)t,c,s)

[0038] Among them, t is the terrain characteristics, c is the climate characteristics, and s is the soil characteristics.

[0039] Preferably, the cluster analysis process performed by the environmental zone division module includes:

[0040] The minimum spanning tree of the garden area is constructed using the extracted feature vectors;

[0041] Adaptively find the crop size, prune the minimum spanning tree and split it into a forest;

[0042] Get all the leaf nodes of the forest and reconstruct the minimum spanning tree. According to the preset number of clusters α, prune the α-1 longest edges of the minimum spanning tree to obtain a forest containing α trees. Then calculate the centroid of each tree in the forest and set it as the initial cluster center.

[0043] Through the iterative optimization process, the cluster centers are continuously adjusted until the convergence conditions are met.

[0044] Preferably, the process of constructing a plant demand map executed by the plant demand module includes:

[0045] Obtain a list of desired plants in the target garden area;

[0046] The correlation coefficient is used to measure the correlation between plant growth conditions and environmental characteristics, and then match plants with their adapted environments, which is specifically expressed as:

[0047]

[0048] Among them, X i and Y i Respectively represent the values ​​of the two variables of the i-th sample, and They represent the average values ​​of two variables, and r represents the correlation coefficient between the two variables.

[0049] Preferably, the landscape gardening planting planning and management system further includes:

[0050] The environmental adaptability assessment module jointly analyzes the terrain adaptability index, soil matching index and climate adaptability index to obtain the environmental adaptability coefficient. Based on the relationship between the environmental adaptability coefficient and the threshold, it determines whether to optimize, including selecting more suitable plants, local land leveling or adjusting soil fertility.

[0051] The calculation method of the terrain adaptability index TAI is:

[0052]

[0053] Where R is the plant root depth, H avg is the average terrain depth of the target area, S is the regional slope coefficient;

[0054] The soil matching index SMI is calculated as follows:

[0055]

[0056] Among them, M is the nutrient type, j is the nutrient type, s j is the concentration of the jth nutrient in the soil, n j is the jth nutrient requirement concentration of the plant;

[0057] The calculation method of the climate adaptation index CAI is:

[0058]

[0059] Where T is the current temperature, T opt is the growth temperature of the plant, T max and T mira are the upper and lower limits of temperature that plants can tolerate, respectively;

[0060] The calculation formula of the environmental adaptability coefficient is:

[0061] AEC=α·TAI+β·SMI+γ·CAI

[0062] Among them, α, β, γ represent the weight coefficients of each item respectively, and α+β+γ=1;

[0063] If the environmental adaptability coefficient is lower than the threshold, optimization measures are recommended, including selecting more suitable plants, local land leveling or soil fertility adjustment; if the environmental adaptability coefficient is not lower than the threshold, it indicates that the environmental adaptability of the plant meets the requirements and no measures are taken.

[0064] Preferably, the landscape gardening planting planning and management system further includes an environmental adaptability dynamic feedback module.

[0065] The environmental adaptability dynamic feedback module is used to monitor and adjust the environmental adaptability coefficient in real time, and realize environmental adaptive optimization through the following steps:

[0066] Real-time data fusion: dynamically acquire terrain, soil and climate change data, and update terrain adaptation index, soil matching index and climate adaptation index;

[0067] Threshold hierarchical control: When the environmental adaptability coefficient is lower than the first warning threshold, non-destructive optimization measures are recommended; when the environmental adaptability coefficient is lower than the second warning threshold, mandatory optimization measures are triggered;

[0068] Priority sorting of optimization measures: Based on the weight distribution of each sub-item of the environmental adaptability coefficient, the corresponding optimization plans are executed in order of priority.

[0069] Preferably, the landscape gardening planting planning and management system further includes:

[0070] The environmental impact intelligent assessment module is used to predict the medium- and long-term impact of environmental changes on plant growth through historical data and real-time environmental data, and generate optimization plans, including the following steps:

[0071] Historical trend analysis: Based on historical environmental monitoring data, the time series prediction model is used to output abnormal trend results; the trend results include the time point when the key parameters exceed the risk threshold and the corresponding credibility;

[0072] Plant adaptability simulation: Combined with abnormal trend results, evaluate the long-term adaptability of plants and output the growth risk score of plants. The output range of the risk score is 0-1. The higher the value, the greater the growth risk of plants in this environment.

[0073] Optimization plan generation: Dynamically adjust plant configuration and regional planning based on plant growth risk scores.

[0074] Preferably, the growth risk score is the sum of all key parameter risk values ​​multiplied by their weights; the key parameter risk value is the time length from the time point when the key parameter breaks through the risk threshold to the current time, and the corresponding credibility value.

[0075] Compared with the prior art, the beneficial effects of the present invention are:

[0076] The present invention provides a landscape planting planning and management system based on terrain environment analysis. Firstly, by collecting and processing environmental data such as terrain, climate, soil, etc. of the target garden area, comprehensive and accurate information support is provided for planting planning, so that the planning is more in line with the natural laws of plant growth. Secondly, through scientific planting planning and management, the system helps to build a more stable and sustainable ecological environment. Then, reasonable plant configuration can improve soil quality, increase biodiversity, regulate climate, etc., and create a more livable living environment for people. Finally, since the system can perform intelligent matching and recommendation according to the growth habits and environmental conditions of the plants, the frequency of death and replacement caused by the plants' inability to adapt to the environment can be reduced, thereby reducing the maintenance cost of the garden. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a structural schematic diagram of a landscape gardening planting planning and management system based on terrain environment analysis of the present invention;

[0078] Figure 2 It is one of the flow charts of the landscape gardening planting planning and management method based on terrain environment analysis of the present invention;

[0079] Figure 3 This is the second flow chart of the planting planning management method based on the principle of split mirrors of terrain environment analysis of the present invention;

[0080] Figure 4 This is the third flow chart of the planting planning and management method based on the principle of storyboard analysis of terrain environment of the present invention. DETAILED DESCRIPTION

[0081] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the application equally.

[0082] Embodiment 1, as Figure 1 As shown, this embodiment provides a landscape gardening planting planning and management system based on terrain environment analysis, including:

[0083] The data collection and processing module is used to collect the environmental data of the target garden area and pre-process the environmental data;

[0084] Feature extraction module: used to extract key features from preprocessed environmental data to form a multi-dimensional environmental feature vector;

[0085] Region division module: used to classify regions with similar environmental characteristics into the same category to form different regions;

[0086] Regional plant demand analysis module: used to associate plant demand with environmental characteristics to form a plant demand map.

[0087] The preprocessing process performed by the data acquisition and processing module includes:

[0088] The collected topography, climate, and soil in the target garden area are input into the set D = {D 1 , D 2 , …, D n}, Q = {Q 1 , Q 2 , …, Q n}、T={T 1 , T 2 , …, T n}, where n represents the total amount of data collected, and the data in the data sets D, Q, and T are screened for data outliers, missing values, error values, and duplicate values, and data filling is performed on the missing values, specifically:

[0089] df_fi ll=df.fi ll na(df.mean())

[0090] Perform data removal on duplicate values, specifically:

[0091] df_drop = df.dropna()

[0092] Smoothing of outliers and error values ​​based on binning algorithms, including:

[0093] Arrange the data in data sets D, Q, and T according to their numerical values;

[0094] Divide the data sets D, Q, and T into several boxes according to the number of record rows, and each box has the same number of records;

[0095] Replace all the data in a bin with the mean of all the data in that bin:

[0096]

[0097] Among them, x i is the i-th data point in the box, and m is the total number of data points in the box;

[0098] Obtain smoothed data sets D, Q, T;

[0099] The processed data is converted into a consistent format for subsequent analysis. In this embodiment, the pre-processed environmental text data is converted into a date and time format, and then a minimum-maximum normalization operation is performed:

[0100] The original data in the cleaned data sets D, Q, and T are linearly transformed to the range of [0, 1]:

[0101]

[0102] Among them, V x Represents the value of the data after linear transformation, S old represents the mean of the original data, S min Represents the minimum value in the original data, S max Indicates the maximum value in the original data.

[0103] The feature extraction process performed by the feature extraction module includes:

[0104] Extract features from terrain data and determine the range of terrain features to be extracted:

[0105] Construct triangular faces within the target garden area to simulate the terrain surface;

[0106] Establish a space equation for each triangular face to describe its geometric shape;

[0107] Calculate the vertical distance from the point projected on the ground plane to the triangle surface, and find the point with the largest distance as the most significant terrain feature point in the current triangle surface;

[0108] By setting different scale factors, the precision of terrain feature extraction can be controlled;

[0109] Using the extracted terrain feature points, the triangular surface is further split and divided to iteratively extract terrain features;

[0110] Extract climate characteristics:

[0111] Calculate the average values ​​of temperature, precipitation and wind speed in the climate data of the target garden area within a certain period of time;

[0112] Extract soil characteristics:

[0113] Extract the type, texture and fertility of soil data in the target garden area, analyze and extract features of its physical and chemical properties;

[0114] The terrain, climate and soil characteristics extracted above are integrated into a multi-dimensional environmental feature vector:

[0115] V=(t,c,s)

[0116] Among them, t is the terrain characteristics, c is the climate characteristics, and s is the soil characteristics.

[0117] The cluster analysis process performed by the region division module includes:

[0118] The minimum spanning tree of the garden area is constructed using the extracted feature vectors;

[0119] Adaptively find the crop size, prune the minimum spanning tree and split it into a forest;

[0120] Get all the leaf nodes of the forest and reconstruct the minimum spanning tree. According to the preset number of clusters α, prune the α-1 longest edges of the minimum spanning tree to obtain a forest containing α trees. Then calculate the centroid of each tree in the forest and set it as the initial cluster center.

[0121] Through the iterative optimization process, the cluster centers are continuously adjusted until the convergence conditions are met.

[0122] The process of forming a plant demand map executed by the plant demand analysis module in the region includes:

[0123] Obtain a list of desired plants in the target garden area;

[0124] The correlation coefficient is used to measure the correlation between plant growth conditions and environmental characteristics, and then match plants with their adapted environments, which is specifically expressed as:

[0125]

[0126] Among them, X i and Y i Respectively represent the values ​​of the two variables of the i-th sample, and They represent the average values ​​of two variables, and r represents the correlation coefficient between the two variables.

[0127] Embodiment 2: The difference between the embodiment of the present invention and embodiment 1 is that the landscape gardening planting planning and management system further includes:

[0128] The environmental adaptability assessment module jointly analyzes the terrain adaptability index, soil matching index and climate adaptability index to obtain the environmental adaptability coefficient. Based on the relationship between the environmental adaptability coefficient and the threshold, it determines whether to optimize, including selecting more suitable plants, local land leveling or adjusting soil fertility.

[0129] Explanation: The terrain adaptation index is used to measure whether the plant is suitable for the current terrain; the soil matching index is based on the matching of the basic demand of the plant for soil nutrient concentration and the actual state of the current soil, reducing the reliance on complex dynamic calculations; the climate adaptation index is used to measure the climate adaptability of the plant;

[0130] It needs to be further explained in the embodiment of the present invention that the terrain adaptability index TAI is calculated as follows:

[0131]

[0132] Where R is the plant root depth, H avg is the average terrain depth of the target area, S is the regional slope coefficient;

[0133] The soil matching index SMI is calculated as follows:

[0134]

[0135] Among them, M is the nutrient type, j is the nutrient type, s j is the concentration of the jth nutrient in the soil, n j is the jth nutrient requirement concentration of the plant;

[0136] The calculation method of the climate adaptation index CAI is:

[0137]

[0138] Where T is the current temperature, T opt is the growth temperature of the plant, T max and T mira are the upper and lower limits of temperature that plants can tolerate, respectively;

[0139] It needs to be further explained in the embodiment of the present invention that the calculation formula of the environmental adaptability coefficient is:

[0140] AEC=α·TAI+β·SMI+γ·CAI

[0141] Among them, α, β, γ represent the weight coefficients of each item respectively, and α+β+γ=1;

[0142] If the environmental adaptability coefficient is lower than the threshold, optimization measures are recommended, including selecting more suitable plants, local land leveling or soil fertility adjustment; if the environmental adaptability coefficient is not lower than the threshold, it indicates that the environmental adaptability of the plant meets the requirements and no measures are taken.

[0143] In a possible embodiment, the landscape gardening planting planning and management system further includes an environmental adaptability dynamic feedback module.

[0144] The environmental adaptability dynamic feedback module is used to monitor and adjust the environmental adaptability coefficient in real time, and realize environmental adaptive optimization through the following steps:

[0145] Real-time data fusion: dynamically acquire terrain, soil and climate change data, and update terrain adaptation index, soil matching index and climate adaptation index;

[0146] Threshold-based hierarchical regulation: When the environmental adaptability coefficient is lower than the first warning threshold, non-destructive optimization measures (such as adjusting irrigation frequency or plant pruning) are recommended; when the environmental adaptability coefficient is lower than the second warning threshold, mandatory optimization measures (such as improving soil, adjusting plant configuration or terrain management) are triggered;

[0147] Priority sorting of optimization measures: Based on the weight distribution of each sub-item of the environmental adaptability coefficient, the corresponding optimization plans are executed in order of priority;

[0148] Effect verification and iteration: After the optimization measures are implemented, the adjustment effect is monitored in real time. If the environmental adaptability coefficient has not recovered to above the threshold, continue to iterate and adjust.

[0149] Explanation: The first warning threshold is used to indicate mild or potential risks of plants under environmental stress. When the first warning threshold is reached, the growth condition of the plant may not have been seriously affected, but early intervention is required to prevent the risk from expanding; the first warning threshold is used to trigger non-destructive optimization measures (such as adjusting irrigation frequency, plant pruning, etc.).

[0150] Acquisition method: Empirical data method: Based on historical data statistics of the same type of plants in similar environments, calculate the critical values ​​of key parameters (such as soil nutrients, temperature and humidity, etc.) that are close to but not yet reached the allowable range; for example, when the soil nutrients of plants are within 10% of the lower limit, the growth performance may decline slightly but no obvious harm will occur.

[0151] Expert setting method: experts in ecology and agricultural planting set warning thresholds based on experience and scientific research; for example, soil moisture below 40% (but above 30%) can be used as the first warning;

[0152] The second warning threshold indicates that the environmental adaptability or growth condition of the plant has been seriously threatened. When the second warning threshold is reached, the plant may not grow normally or even face the risk of dying. The second warning threshold is used to trigger mandatory optimization measures (such as soil improvement, plant reconfiguration, terrain improvement, etc.).

[0153] How to obtain:

[0154] Critical value method:

[0155] Determine the critical range of key parameters based on the physical and physiological tolerance limits of the plant; for example:

[0156] The lowest temperature that plants can tolerate is 5°C, and temperatures below this can be directly used as the second warning threshold;

[0157] Experimental research method:

[0158] Controlled experiments verify the growth limits of plants under different environmental conditions, such as:

[0159] Test the allowable limit of soil salt concentration of a certain plant. When the concentration exceeds 1.5%, the plant will wilt on a large scale. 1.5% can be used as the second warning threshold.

[0160] In a possible embodiment, the landscape gardening planting planning and management system further includes:

[0161] The environmental impact intelligent assessment module is used to predict the medium- and long-term impact of environmental changes on plant growth through historical data and real-time environmental data, and generate optimization plans, including the following steps:

[0162] Historical trend analysis: Based on historical environmental monitoring data, use time series prediction models (such as seasonal autoregressive integrated moving average models) to output abnormal trend results; the trend results include the time point and corresponding credibility when key parameters exceed the risk threshold. The key parameters refer to parameters that affect plant growth, including terrain settlement, soil fertility degradation, etc.; such as the specific time when soil fertility deteriorates to the extent that affects plant health; provide a credibility range for each trend prediction result to quantify the reliability of the result;

[0163] Plant adaptability simulation: Combined with abnormal trend results, evaluate the long-term adaptability of plants and output the growth risk score of plants. The output range of the risk score is 0-1. The higher the value, the greater the growth risk of plants in this environment.

[0164] Optimization plan generation: Dynamically adjust plant configuration and regional planning based on plant growth risk scores;

[0165] Specific optimization measures include:

[0166] Plant configuration optimization: Introduce stress-tolerant plants (such as drought-resistant and salt-tolerant plants) in advance for high-risk areas;

[0167] Environmental control measures: Take corresponding measures for high-risk factors (such as increasing shading, optimizing irrigation patterns, strengthening soil improvement, etc.);

[0168] Dynamic adjustment mechanism: monitors changes in risk scores in real time to ensure the effectiveness of optimization plans and makes further adjustments based on environmental dynamics.

[0169] Explanation: Combined with abnormal trend results, high-risk areas and high-risk factors can be accurately identified through historical data analysis and real-time monitoring to support optimized decisions in garden planting planning; high-risk areas are geographical ranges where plant growth is predicted to face significant challenges based on abnormal trend results, usually manifested as abnormal accumulation of key environmental parameters (such as slope, humidity or soil nutrients) in a specific space or the superposition of multiple factors, such as waterlogging in low-lying areas caused by long-term drought or concentrated precipitation; by combining the time point and credibility of the key parameters breaking through the risk threshold in the trend results, the system can clearly define the spatial scope of the high-risk areas and take targeted measures in advance.

[0170] High-risk factors are environmental conditions that directly threaten plant health based on the identification of abnormal trend analysis, and are the core reason for the formation of high-risk areas. High-risk factors are obtained by quantifying specific parameters (such as soil salt concentration higher than the allowable range, and temperature higher than the plant tolerance value for a long time), and their development direction and possible impact are clarified in combination with trend forecasts. For example, if the abnormal trend shows that the humidity in a certain area will be lower than the suitable range for a long time in the future, drought will be marked as a high-risk factor. Based on the linkage analysis of high-risk areas and high-risk factors, the system generates optimization plans to dynamically respond to potential threats by adjusting plant configuration, soil improvement or irrigation strategies.

[0171] What needs to be further explained in the embodiments of the present invention is that the growth risk score is the sum of all key parameter risk values ​​multiplied by their weights; the key parameter risk value is the time length from the time point when the key parameter breaks through the risk threshold to the current time, and the corresponding credibility value.

[0172] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A landscape planting planning and management system based on terrain environment analysis, characterized in that: include: The data collection and processing module is used to collect the environmental data of the target garden area and pre-process the environmental data; Feature extraction module: used to extract key features from preprocessed environmental data to form a multi-dimensional environmental feature vector; Region division module: used to classify regions with similar environmental characteristics into the same category to form different regions; Regional plant demand analysis module: used to associate plant demand with environmental characteristics to form a plant demand map.

2. A landscape gardening planting planning and management system based on terrain environment analysis according to claim 1, characterized in that: The preprocessing process performed by the data acquisition and processing module includes: The collected topography, climate, and soil in the target garden area are input into the set D = {D1, D2, ..., D n }, Q={Q1,Q2,…,Q n }, T={T1,T2,…,T n }, where n represents the total amount of data collected, and the data in the data sets D, Q, and T are screened for data outliers, missing values, error values, and duplicate values, data filling is performed on missing values, data deletion is performed on duplicate values, and smoothing is performed on outliers and error values ​​based on the binning algorithm; The original data in the cleaned data sets D, Q, and T are linearly transformed to the range of [0, 1]: Among them, V x Represents the value of the data after linear transformation, S old represents the mean of the original data, S min Represents the minimum value in the original data, S max Indicates the maximum value in the original data.

3. A landscape gardening planting planning and management system based on terrain environment analysis according to claim 2, characterized in that: The performing smoothing processing on the abnormal values ​​and the error values ​​based on the binning algorithm includes: Arrange the data in data sets D, Q, and T according to their numerical values; Divide the data sets D, Q, and T into several boxes according to the number of record rows, and each box has the same number of records; Replace all the data in a bin with the mean of all the data in that bin: Among them, x i is the i-th data point in the box, and m is the total number of data points in the box; The smoothed data sets D, Q, and T are obtained.

4. The landscape gardening planting planning and management system based on terrain environment analysis according to claim 1 is characterized in that: The feature extraction process performed by the feature extraction module includes: Perform feature extraction on terrain data: Construct triangular surfaces within the target garden area; Establish a space equation for each triangular face to describe its geometric shape; Calculate the vertical distance from the point projected on the ground plane to the triangle surface, and find the point with the largest distance as the most significant terrain feature point in the current triangle surface; By setting different scale factors, the precision of terrain feature extraction can be controlled; Using the extracted terrain feature points, the triangular surface is further split and divided to iteratively extract terrain features; Extract climate characteristics: Calculate the average values ​​of temperature, precipitation and wind speed in the climate data of the target garden area within a certain period of time; Extract soil characteristics: Extract the type, texture and fertility of soil data in the target garden area, analyze and extract features of its physical and chemical properties; The terrain, climate and soil characteristics extracted above are integrated into a multi-dimensional environmental feature vector: V=(t,c,s) Among them, t is the terrain characteristics, c is the climate characteristics, and s is the soil characteristics.

5. The landscape gardening planting planning and management system based on terrain environment analysis according to claim 1 is characterized in that: The cluster analysis process performed by the region division module includes: The minimum spanning tree of the garden area is constructed using the extracted feature vectors; Adaptively find the crop size, prune the minimum spanning tree and split it into a forest; Get all the leaf nodes of the forest and reconstruct the minimum spanning tree. According to the preset number of clusters α, prune the α-1 longest edges of the minimum spanning tree to obtain a forest containing α trees. Then calculate the centroid of each tree in the forest and set it as the initial cluster center. Through the iterative optimization process, the cluster centers are continuously adjusted until the convergence conditions are met.

6. The landscape gardening planting planning and management system based on terrain environment analysis according to claim 1 is characterized in that: The process of forming a plant demand map executed by the plant demand analysis module in the region includes: Obtain a list of desired plants in the target garden area; The correlation coefficient is used to measure the correlation between plant growth conditions and environmental characteristics, and then match plants with their adapted environments, which is specifically expressed as: Among them, X i and Y i Respectively represent the values ​​of the two variables of the i-th sample, and They represent the average values ​​of two variables, and r represents the correlation coefficient between the two variables.

7. The landscape gardening planting planning and management system based on terrain environment analysis according to claim 1 is characterized in that: Also includes: The environmental adaptability assessment module jointly analyzes the terrain adaptability index, soil matching index and climate adaptability index to obtain the environmental adaptability coefficient. Based on the relationship between the environmental adaptability coefficient and the threshold, it determines whether to optimize, including selecting more suitable plants, local land leveling or adjusting soil fertility. The calculation method of the terrain adaptability index TAI is: Where R is the plant root depth, H avg is the average terrain depth of the target area, S is the regional slope coefficient; The soil matching index SMI is calculated as follows: Among them, M is the nutrient type, j is the nutrient type, s j is the concentration of the jth nutrient in the soil, n j is the jth nutrient requirement concentration of the plant; The calculation method of the climate adaptation index CAI is: Where T is the current temperature, T opt is the growth temperature of the plant, T max and T mira are the upper and lower limits of temperature that plants can tolerate, respectively; The calculation formula of the environmental adaptability coefficient is: AEC=α·TAI+β·SMI+γ·CAI Among them, α, β, γ represent the weight coefficients of each item respectively, and α+β+γ=1; If the environmental adaptability coefficient is lower than the threshold, optimization measures are recommended, including selecting more suitable plants, local land leveling or soil fertility adjustment; if the environmental adaptability coefficient is not lower than the threshold, it indicates that the environmental adaptability of the plant meets the requirements and no measures are taken.

8. The landscape gardening planting planning and management system based on terrain environment analysis according to claim 7 is characterized in that: It also includes an environmental adaptability dynamic feedback module. The environmental adaptability dynamic feedback module is used to monitor and adjust the environmental adaptability coefficient in real time, and realize environmental adaptive optimization through the following steps: Real-time data fusion: dynamically acquire terrain, soil and climate change data, and update terrain adaptation index, soil matching index and climate adaptation index; Threshold hierarchical control: When the environmental adaptability coefficient is lower than the first warning threshold, non-destructive optimization measures are recommended; When the environmental adaptability coefficient is lower than the second warning threshold, mandatory optimization measures are triggered; Priority sorting of optimization measures: Based on the weight distribution of each sub-item of the environmental adaptability coefficient, the corresponding optimization plans are executed in order of priority.

9. A landscape gardening planting planning and management system based on terrain environment analysis according to claim 7 or 8, characterized in that: Also includes, The environmental impact intelligent assessment module is used to predict the medium- and long-term impact of environmental changes on plant growth through historical data and real-time environmental data, and generate optimization plans, including the following steps: Historical trend analysis: Based on historical environmental monitoring data, the time series prediction model is used to output abnormal trend results; the trend results include the time point when the key parameters exceed the risk threshold and the corresponding credibility; Plant adaptability simulation: Combined with abnormal trend results, evaluate the long-term adaptability of plants and output the growth risk score of plants. The output range of the risk score is 0-1. The higher the value, the greater the growth risk of plants in this environment. Optimization plan generation: Dynamically adjust plant configuration and regional planning based on plant growth risk scores.

10. A landscape garden planting planning and management system based on terrain environment analysis according to claim 9, characterized in that: The growth risk score is the sum of all key parameter risk values ​​multiplied by their weights; the key parameter risk value is the time length from the time point when the key parameter breaks through the risk threshold to the current time, and the corresponding credibility value.

Images