Intelligent matching and growth simulation method and system for water and soil conservation plants

Abstract

The invention discloses an intelligent matching and growth simulation method and system for water and soil conservation plants. The method comprises the following steps: collecting engineering environment data of a target engineering area; screening and outputting a recommended plant list from the constructed plant knowledge base; a plant recommendation scoring mechanism is introduced, and list sorting is carried out according to the comprehensive score of each candidate plant or plant combination; selecting a single plant A or a plant A and symbiotic plant combination scheme thereof from the recommended plant list, and calculating the prediction radius, prediction height, actual survival rate and withering green state of the plant A in the current month; simulating the growth condition and the withered green state of the plant A in the target month; fusing the plant growth simulation model with a three-dimensional scene, and visually reflecting the growth condition and spatial distribution of the plant A; and automatically outputting the finally determined growth simulation scheme, simulation result and evaluation conclusion. According to the invention, rapid and accurate matching of engineering water conservation plant measures is realized, and realization of a water and soil conservation effect is ensured.

Description

Technical Field

[0001] This invention relates to the field of soil and water conservation technology, specifically to a method and system for intelligent matching and growth simulation of soil and water conservation plants. Background Technology

[0002] As an important means of soil and water conservation, vegetation measures are usually recommended by soil and water conservation professionals based on their understanding of local environmental conditions and their own experience.

[0003] This method has achieved some success in the past, but the following technical problems exist in practical applications: First, each type of water-conserving plant has specific requirements for its own growth environment (such as temperature, altitude, soil type, water conditions, light conditions, etc.). The selection method based on experience lacks the support of scientific data. At the same time, the types of water-conserving plants that can be selected are limited, and it cannot be guaranteed that the most suitable plants can be selected from the existing plants for soil and water conservation. Secondly, designers lack scientific methods to simulate and verify the growth of the selected plants. Currently, they mainly rely on past planting experience for prediction, which makes it difficult to accurately assess the growth status of the plants and the effect of soil and water conservation, thus affecting the overall implementation effect and long-term stability of the project. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention proposes an intelligent matching and growth simulation method and system for soil and water conservation plants. It provides a comprehensive, quantitative, and intelligent method and system for recommending soil and water conservation plants, overcoming the subjective, one-sided, and quantitative deficiencies in plant selection in existing technologies. This not only enables rapid and accurate quantitative assessment of plant-environment compatibility and outputs optimal single-plant or symbiotic plant combination schemes, but also verifies the soil and water conservation effects through pre-simulated plant growth, providing a scientific basis for plant planting and maintenance, and offering quantitative data for soil and water conservation plant planting schemes.

[0005] To achieve the above objectives, this invention designs an intelligent matching and growth simulation method for soil and water conservation plants, which is characterized by the following steps: S1) Establish a plant knowledge base and collect engineering environmental data for the target engineering area; S2) Construct an intelligent matching algorithm or intelligent matching model to filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination. S3) Select a single plant A or plant A and its symbiotic plant combination scheme from the selected recommended plant list, determine the plant A growth simulation scheme, which includes constructing a growth month size coefficient calculation formula, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered state of plant A in the current month; S4) According to the predicted radius, predicted height, actual survival rate and withered state of plant A, a plant growth simulation model is constructed using existing plant modeling software to simulate the growth and withered state of plant A in the target month; S5) Based on the plant A growth simulation result, calculate the water and soil conservation effect index, automatically compare the water and soil conservation effect index with the national standard specified prevention index, and generate an evaluation conclusion; S6) Construct a three-dimensional scene of the target engineering area, fuse the plant growth simulation model with the three-dimensional scene, and visualize the plant A growth and spatial distribution; at the same time, provide a graphical human-computer interaction interface to receive real-time adjustment instructions. If the evaluation conclusion of S5) is not satisfied, select another plant B from the sorted list or increase artificial maintenance measures to change the growth environment of plant A, repeat steps S3)~S5), until the visualized plant growth and spatial distribution meet the set water and soil conservation effect index requirements; the final determined growth simulation scheme, growth simulation result and evaluation conclusion are automatically output as a structured report.

[0006] Further, in S1), the plant knowledge base includes plant name, plant type, growth environment requirement, stress resistance, ecological interaction, functional efficiency, economic and maintenance cost; the growth environment requirement is used to evaluate the matching degree of the plant to the environmental parameters, support environmental adaptation evaluation; the stress resistance is used to describe the drought resistance, waterlogging resistance, cold resistance and disease and pest resistance of the plant, support stress resistance index evaluation; the ecological interaction is used to evaluate the interaction of the plant with other plants in the target vegetation type; the functional efficiency is used to evaluate the water and soil conservation function of the plant; the economic and maintenance cost is used to evaluate the availability of plant seedlings, planting cost and post-maintenance difficulty.

[0007] Further, in S2), the steps of screening the plant list by intelligent matching algorithm are as follows, S21) Store the growth environment requirement characteristics of each plant in the plant knowledge base as a structured data table; S22) Dynamically configure matching rules, compare the engineering environment data of the target engineering area with the plant growth environment requirement characteristics in the structured data table, and select the plant list that meets the conditions according to the matching degree.

[0008] Further, in S2), the steps of screening the plant list by intelligent matching model are as follows, S21) Deep analysis of plant knowledge base data, extraction and quantification of growth environment requirement characteristics of each plant, generation of plant growth environment demand data set; S22) Identify and extract key environmental features from the engineering environment data of the target engineering area, generate environment input data set; S23) Input the environment input data set into the trained intelligent matching model, and the intelligent matching model outputs the recommended plant list through semantic understanding and comprehensive analysis, and provides the main environmental adaptability of the plant in the list.

[0009] Further, in S2), the plant recommendation scoring mechanism calculates a comprehensive score for each candidate plant or plant combination, which is generated based on a weighted scoring model represented by the following formula, ; In the formula, S total represents the comprehensive score of a candidate plant or plant combination, S e represents the environmental adaptation score, S s represents the stress resistance index score, S i represents the ecological interaction score, S f represents the functional efficiency score, S c represents the economic and maintenance cost score, W e , W s , W i , W f , W c respectively represent the environmental adaptation, stress resistance index, ecological interaction, functional efficiency, and economic and maintenance cost weights.

[0010] Further, in S3), if plant A is an annual grass species, the growth month type coefficient calculation formula is as follows, ; In the formula, Mc 1The body size coefficient of annual grass species A during its growth month. m The growing month; If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the leaf growth month is as follows. ; In the formula, Mc 2 The body size coefficient of the leaf portion of deciduous shrub A during the month of growth. m The growing month; If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the trunk during the months of growth is as follows. ; In the formula, Mc 3 The body size coefficient of the trunk portion of deciduous shrub A during the months of growth. m The growing month; If plant A is a perennial grass or shrub, the formula for calculating the growth rate correction factor is as follows. ; In the formula, g This is a growth rate correction factor. S The cumulative body size coefficient under normal growth conditions is the ratio of body size under normal growth conditions to standard body size, 0 ≤ 0. S ≤1, r , b These are the formula parameters used to adjust the growth rate of different plants. a It is an index used to regulate the growth rate of different plants.

[0011] Furthermore, in S3), if plant A is a perennial evergreen plant, then plant A's cumulative growth each year, its size is gradually increased according to the growth years, and its actual survival rate is multiplied by the growth years. If plant A is an annual deciduous plant, then plant A will regrow every year, and the actual survival rate will be multiplied by the number of years of growth. If plant A is a perennial deciduous plant, then the leaves of plant A will regenerate every year, and the plant's size will gradually increase according to the number of years of growth. The actual survival rate will be multiplied by the number of years of growth.

[0012] Furthermore, in S3), the predicted radius or predicted height of plant A in the current month t is calculated using the following formula: ; In the formula, D' For plant A, the predicted radius or predicted height for the current month t. D This refers to the standard radius or standard height of plant A, assuming no adverse or favorable external environmental influences, representing the radius or height after maturity. S ( t (This refers to the current month for plant A, without considering corrections for external environmental factors.) t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S ( t- 1) Without considering corrections for external environmental factors, the plant in month A t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. △S( t (This refers to the current month for plant A) t The cumulative increase in body size coefficient without taking into account external environmental adjustments. g This is a growth rate correction factor. S' ( t When considering corrections for external environmental factors, plant A in the current month t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S' ( t- 1) When considering corrections for external environmental factors, plant A month t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. η(t) For plant A in the current month t Body shape correction factor considering the influence of external environment. Mc(t) For plant A in the current month t Body size index for the growth month Mc(t- 1 ) For plant month A t -1 is the growth month size coefficient. S ( t s The initial size coefficient of plant A was not adjusted for external environmental factors during planting. S' ( t sTo adjust the initial size coefficient of plant A during planting, taking into account the external environment, D s This refers to the initial radius or initial height of plant A when it is planted. t For the current month, the value is taken from the month of the planting year. t s From the beginning of the target year to the month t e .

[0013] Furthermore, in S6), the three-dimensional scene of the target engineering area is constructed based on digital elevation model and orthophoto.

[0014] This invention also designs an intelligent matching and growth simulation system for soil and water conservation plants, which is characterized by including a data management module, an intelligent matching module, a growth calculation module, a growth simulation module, an effect evaluation module, and a three-dimensional visualization and report generation module. The data management module is used to collect plant knowledge base and engineering environmental data of the target engineering area; The intelligent matching module is used to construct an intelligent matching algorithm or intelligent matching model, filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination. The growth calculation module is used to select a single plant A or a combination of plant A and its symbiotic plants from the selected recommended plant list, and determine the growth simulation scheme of plant A. The growth simulation scheme includes constructing a formula for calculating the body size coefficient of the growth month, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered green status of plant A in the current month. The growth simulation module is used to construct a plant growth simulation model based on the predicted radius, predicted height, actual survival rate, and withering state of plant A, using existing plant modeling software, to simulate the growth and withering state of plant A in the target month. The effect evaluation module is used to calculate the soil and water conservation effect index based on the growth simulation results, automatically compare the soil and water conservation effect index with the prevention and control index specified in the national standard, and generate an evaluation conclusion. The 3D visualization and report generation module is used to construct a 3D scene of the target engineering area, integrate the plant growth simulation model with the 3D scene, and visualize the growth status and spatial distribution of plant A. At the same time, it provides a graphical human-computer interaction interface to receive real-time adjustment instructions. If the effect evaluation module concludes that the requirements are not met, another plant B is selected from the sorted list, or artificial maintenance measures are added to change the growth environment of plant A. The above growth and simulation process is repeated until the visualized plant growth status and spatial distribution meet the set water and soil conservation effect index requirements. The final determined growth simulation scheme, simulation results and evaluation conclusions are automatically output as a structured report.

[0015] The advantages of this invention are: 1. This invention can quickly analyze engineering survey reports, automatically match and quantitatively evaluate the suitability of different plant schemes, directly output a recommended list and symbiotic combinations, and provide clear scores and basis. This reduces the workload of engineers who rely on personal experience for screening, improves the scientificity and efficiency of vegetation planning and design, and at the same time reduces the engineering risks caused by improper vegetation configuration from the source by avoiding unsuitable plant selection, thus ensuring the long-term stability and benefits of soil and water conservation projects. 2. This invention systematically considers various factors affecting plant growth and introduces a scientific plant recommendation scoring mechanism to select suitable plants for the target engineering area. Then, it establishes growth functions for each plant and, combined with environmental data of the target engineering area, simulates the growth process of specific plants. By monitoring the simulated plant growth, the effectiveness of soil and water conservation is verified and tracked, ensuring the realization of the soil and water conservation effect. 3. In simulating the plant growth process, this invention provides a scientific basis for plant planting and maintenance, and provides quantitative data for soil and water conservation plant planting schemes, such as maintenance needs for watering and fertilization, which helps to predict and optimize the soil and water conservation effect. 4. It has changed the traditional water and soil conservation plant configuration mode that relies on manual experience. By constructing a digital system that integrates intelligent matching, growth calculation, growth simulation, three-dimensional visualization and effect evaluation, it provides engineering designers with an efficient, scientific and visual decision-making tool, improving the accuracy and optimization efficiency of scheme design. The present invention provides a method and system for intelligent matching and growth simulation of soil and water conservation plants. This method and system not only enables rapid and accurate matching of engineering soil and water conservation plant measures, but also ensures the realization of soil and water conservation effects. It provides a scientific basis for plant planting and maintenance, and provides quantitative data for soil and water conservation plant planting schemes. It has broad application prospects and is applicable to various engineering soil and water conservation projects and ecological restoration projects. Attached Figure Description

[0016] Figure 1 This is a flowchart of the present invention; Figure 2a This is a screenshot of the grass seed growth model in this embodiment of the invention at time 4s. Figure 2b This is a screenshot of the grass seed growth model in this embodiment of the invention at time 9s; Figure 3a This is a screenshot of the shrub growth model in this embodiment of the invention at time 7s; Figure 3b This is a screenshot of the shrub growth model in this embodiment of the invention at time 18s. Detailed Implementation

[0017] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Example

[0018] like Figure 1 As shown, the present invention provides an intelligent matching and growth simulation method for soil and water conservation plants, comprising the following steps: S1) Establish a plant knowledge base and collect engineering environmental data for the target engineering area.

[0019] Specifically, the plant knowledge base includes plant names, plant types (trees / shrubs / grass species), growth environment requirements, stress resistance, ecological interaction, functional efficacy, economic and maintenance costs, etc.

[0020] The growth environment requirements are used to assess the degree of plant matching with environmental parameters and support the evaluation of environmental adaptability. The growth environment requirements include the optimal range and tolerable range of continuous variables such as temperature, altitude, and pH value, as well as the complete matching, partial matching / acceptable, and non-matching types of categorical variables such as soil type.

[0021] The term "stress resistance" describes a plant's drought tolerance, waterlogging tolerance, cold tolerance, and resistance to diseases and pests, supporting the evaluation of stress resistance indicators. Stress resistance includes, but is not limited to, drought tolerance, cold tolerance, waterlogging tolerance, and resistance to diseases and pests.

[0022] The ecological interactivity is used to assess the interaction between the plant and other plants in the target vegetation type, such as symbiotic effects or competitive relationships.

[0023] The functional efficacy is used to assess the soil and water conservation function of plants, which includes, but is not limited to, the degree of system development (soil stabilization capacity), canopy coverage (reducing splash erosion), and growth rate (rapid formation of protection).

[0024] The economic and maintenance costs are used to assess the availability of plant seedlings, planting costs, and the difficulty of subsequent management, including but not limited to seedling availability, maintenance difficulty, and cost level.

[0025] In addition, based on design reports, survey reports, and other materials, the environmental description of the target project area is analyzed to extract key environmental features. The environmental data includes: site conditions, temperature, altitude, soil, pH value, moisture (rainfall and flooding, etc.), and sunlight.

[0026] S2) Construct an intelligent matching algorithm or intelligent matching model to filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination.

[0027] The steps to filter the plant list using an intelligent matching algorithm are as follows: S21) Store the growth environment requirements of each plant in the plant knowledge base as a structured data table; S22) Dynamically configure matching rules, compare the engineering environment data of the target engineering area with the plant growth environment requirements in the structured data table, and select a list of plants that meet the conditions based on the matching degree.

[0028] Specifically, the steps for selecting the plant list using an intelligent matching model are as follows: S21) Perform in-depth analysis of plant knowledge base data, extract and quantify the growth environment requirements of each plant, and generate a plant growth environment requirement dataset. S22) Identify and extract key environmental features from the engineering environment data of the target engineering area to generate an environmental input dataset; S23) Input the environmental input dataset into the trained intelligent matching model. The intelligent matching model outputs a list of recommended plants through semantic understanding and comprehensive analysis, and provides the main environmental adaptability descriptions for the plants in the list.

[0029] The plant recommendation scoring mechanism calculates a comprehensive score for each candidate plant or plant combination. This comprehensive score is generated based on a weighted scoring model, which is expressed by the following formula: ; In the formula, S total This represents the overall score of a candidate plant or plant combination. S e This indicates the environmental adaptability score. S s This indicates the score of resilience indicators. S i Indicates the ecological interactivity score. S fIndicates functional performance score, S c Indicates the economic and maintenance cost score. S e , S s , S i , S f , S c It needs to be converted to a percentage score. W e , W s , W i , W f , W c These represent the weights of environmental adaptability, resilience indicators, ecological interactivity, functional effectiveness, and economic and maintenance costs, respectively.

[0030] The scoring methods for each factor are shown below.

[0031] a. Environmental adaptability: a1. For continuous variables (such as temperature, altitude, pH value, etc.), the degree of fit is expressed by the following formula. ; In the formula, Match(E) This indicates the environmental fit of a continuous variable. E Represents the actual value of a continuous variable. P min This represents the minimum value of a continuous variable. P max This represents the maximum value of a continuous variable. P outerMin This represents the minimum tolerable value for a continuous variable. P outerMax This represents the maximum tolerable value for a continuous variable. a2. For categorical variables (such as soil type), a direct score is given: 1.0 for a perfect match; 0.6 for a partial match / acceptable match; and 0.0 for no match.

[0032] The final score for environmental adaptability is the sum of the scores for each category and their weights. However, if any subcategory has a score of 0, the score is 0.

[0033] b. Resistance Indicators: For resistance indicators that need to be considered, such as drought resistance, cold resistance, flood resistance, and resistance to diseases and pests, assign weights with a score range of 0–5 points, with 5 being the strongest. If no relevant data is available, the default score is 3 points, and the weights are set according to the characteristics of the project.

[0034] c. Ecological interaction: This considers the interactions between the plant and other plants in the target vegetation type, such as symbiotic effects (positive bonus) or competitive relationships (negative bonus). The calculated score ranges from 0 to 100 points; scores exceeding this range are truncated.

[0035] ; In the formula, A baseline score of 50 indicates no significant interaction. Sym This represents the intensity coefficient of each symbiotic relationship (e.g., nitrogen fixation: +2, shading protection: +1). Com This represents the intensity coefficient of each type of competition (e.g., competing for light, competing for water: -2). C sym , C Com These represent adjustment coefficients (usually taken as 0.5 to 2, used to control the magnitude of the impact).

[0036] d. Functional effectiveness: For functional effectiveness indicators to be considered, such as root development, canopy coverage, growth rate, and litter volume, assign weights with scores of 0-5 points. 5 points for significant functional effectiveness, and 0 points for no effect. If no relevant data is available, the default score is 3 points.

[0037] e. Economic and maintenance costs: For economic and maintenance cost indicators to be considered, such as seedling availability rating data (e.g., easy to obtain = 5, rare = 1); maintenance difficulty rating data (e.g., low maintenance = 5, high maintenance = 1); cost level rating data (e.g., cheap = 5, expensive = 1). If no relevant data is available, the default score is 3.

[0038] This embodiment takes typical grass species A and B as examples, and the main scoring parameters are shown in Table 1 and Table 2 below.

[0039] Table 1. Main scoring parameters for environmental suitability factors of grass species A and B.

[0040] Table 2. Other key factor scoring parameters for grass species A and B

[0041] In addition, the scoring weights can be adjusted according to the characteristics of the project. The scoring weights determined in this embodiment are shown in Table 3.

[0042] Table 3 Scoring Weighting Table

[0043] The actual engineering parameters and weighting indicators of this embodiment are shown in Table 4 below.

[0044] Table 4. Actual Engineering Parameters and Weighting Indicators

[0045] The scores of each parameter are converted into a percentage score and multiplied by the weighting coefficient to obtain the comprehensive score results of this embodiment, as shown in Table 5 below.

[0046] Table 5 Overall Scoring Results

[0047] As shown in Table 5 above, grass species A has a higher overall score than grass species B, so grass species A is the preferred choice.

[0048] Preferably, the intelligent matching algorithm or intelligent matching model is further configured with a feedback optimization mechanism. The feedback optimization mechanism is used to receive actual planting performance data of plants in the target engineering area and use the data to iteratively optimize the plant knowledge base and the intelligent matching algorithm and intelligent matching model to continuously improve the accuracy of plant recommendations.

[0049] S3) Select a single plant A or a combination of plant A and its symbiotic plants from the selected recommended plant list, and determine the plant A growth simulation scheme. The growth simulation scheme includes constructing a formula for calculating the body size coefficient of the growth month, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered green state of plant A in the current month.

[0050] Specifically, if plant A is an annual grass species, the formula for calculating the body size coefficient for the growth month is as follows. ;

[0051] In the formula, Mc 1 The body size coefficient of annual grass species A during its growth month. m The month of growth.

[0052] If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the leaf growth month is as follows. ; In the formula, Mc 2 The body size coefficient of the leaf portion of deciduous shrub A during the month of growth. m The month of growth.

[0053] If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the trunk during the months of growth is as follows. ; In the formula, Mc 3 The body size coefficient of the trunk portion of deciduous shrub A during the months of growth. m The month of growth.

[0054] In addition, it is necessary to develop a table showing the correspondence between the growth month of plant A and the corresponding plant size coefficient and withered green status for the growth month of plant A; and to develop a table showing the correspondence between water conditions, fertilizer conditions, plant planting status, saline-alkali soil conditions, plant interactions and the survival rate coefficient and growth month size correction coefficient of plant A.

[0055] In this embodiment, taking a certain annual grass species A as an example, the radius r after shaping is... 01 The value is 15cm, and the height is h. 01 The value is 20cm. The monthly body size coefficient and withering status of the normal growth over a year are calculated and shown in Table 6 below.

[0056] Table 6 Monthly Body Size Coefficient of a Certain Annual Grass Species A under Normal Growth

[0057] In this embodiment, taking a deciduous shrub B as an example, the radius r after shaping is... 02 The value is 150cm, and the height is h. 02 The value is 100cm. The monthly body shape coefficient of the leaves and the monthly body shape coefficient of the trunk are calculated using the above formulas. The monthly body shape coefficient and withered green status during normal growth in a year are shown in Table 7.

[0058] Table 7. Body type coefficient of a certain deciduous shrub B

[0059] In this embodiment, the correspondence between water conditions, fertilizer conditions, plant planting status, saline-alkali land conditions and the plant growth month survival rate coefficient and growth month body size correction coefficient is shown in Table 8 below.

[0060] Table 8 Survival rate coefficient and body size correction coefficient for the growing month

[0061] Note: If artificial maintenance is implemented, water and fertilizer application can be adjusted according to the actual frequency; if pest and disease control measures are in place, adjustments can be made based on the effectiveness of the control measures. Saline-alkali land is an environmental condition that is difficult to change, so adjustments are not recommended.

[0062] After calculating the survival rate coefficient and growth rate correction coefficient of plant A in the growing month, the actual survival rate and body size of the plant over many years are accumulated according to the plant species classification.

[0063] Specifically, if plant A is a perennial evergreen plant, then plant A's cumulative growth each year will result in a gradually increasing size according to the number of years of growth, and the actual survival rate will be multiplied by the number of years of growth. If plant A is an annual deciduous plant, then plant A will regrow every year, and the actual survival rate will be multiplied by the number of years of growth. If plant A is a perennial deciduous plant, then the leaves of plant A will regenerate every year, and the plant's size will gradually increase according to the number of years of growth. The actual survival rate will be multiplied by the number of years of growth.

[0064] For the actual survival rate, if the survival rate in the first year is 50% and the survival rate in the second year is 50%, and the survival rate coefficient in the second year is 1.0, then the actual survival rate in the second year is 25%. For the body size, if the growth increases by 10cm in the first year and by 5cm in the second year, then the cumulative increase in growth in the second year is 15cm.

[0065] Based on the above formulas and table parameters, considering the planting month, the predicted target month, water conditions (flooded / sufficient / appropriate / shortage / drought), fertilizer conditions (excessive / abundant / appropriate / lacking / absent), plant planting status (seed / germination / seedling / whole plant), saline-alkali soil conditions (slight / weak / medium / strong), plant interactions (mutualism / absence / competition), plant planting month radius, and plant planting month height, the predicted radius, predicted height, actual survival rate, and withered green status of the plants in the target month can be calculated.

[0066] If plant A is a perennial grass or shrub, the formula for calculating the growth rate correction factor is as follows. ; In the formula, g This is a growth rate correction factor. S The cumulative body size coefficient under normal growth conditions is the ratio of body size under normal growth conditions to standard body size, 0 ≤ 0. S ≤1, r , b These are the formula parameters used to adjust the growth rate of different plants. aIt is an index used to regulate the growth rate of different plants.

[0067] For grass species A and shrub B, the values ​​of r, a, and b are 2.0, 0.75, and 1.0, respectively.

[0068] For the branches of shrub B, r, a, and b are 2.0, 0.5, and 1.0 respectively.

[0069] Preferably, the predicted radius or predicted height of plant A in the current month t is calculated using the following formula: ; In the formula, D' For plant A, the predicted radius or predicted height for the current month t. D This refers to the standard radius or standard height of plant A, assuming no adverse or favorable external environmental influences, representing the radius or height after maturity. S ( t (This refers to the current month for plant A, without considering corrections for external environmental factors.) t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S ( t- 1) Without considering corrections for external environmental factors, the plant in month A t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. △S( t (This refers to the current month for plant A) t The cumulative increase in body size coefficient without taking into account external environmental adjustments. g This is a growth rate correction factor. S' ( t When considering corrections for external environmental factors, plant A in the current month t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S' ( t- 1) When considering corrections for external environmental factors, plant A month t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. η(t) For plant A in the current month t Body shape correction factor considering the influence of external environment. Mc(t) For plant A in the current month t Body size index for the growth month Mc(t- 1 ) For plant month A t -1 is the growth month size coefficient. S ( t s The initial size coefficient of plant A was not adjusted for external environmental factors during planting. S' ( t s To adjust the initial size coefficient of plant A during planting, taking into account the external environment, D s This refers to the initial radius or initial height of plant A when it is planted. t For the current month, the value is taken from the month of the planting year. t s From the beginning of the target year to the month t e .

[0070] The actual survival rate of plant A is calculated using the following formula. The survival rate is calculated every year, while the annual survival rate remains constant. S n =S n-1 *α n *β n； In the formula, S n This represents the actual survival rate for the current year. S n-1 This represents the actual survival rate of the previous year in the current year. α n The survival rate for the current year. β n This represents the survival rate coefficient for the current year.

[0071] S4) Based on the predicted radius, predicted height, actual survival rate and withering state of plant A, use existing plant modeling software to construct a plant growth simulation model to simulate the growth and withering state of plant A in the target month.

[0072] The plant growth simulation model includes simulations of multiple stages from germination to growth and shaping; the rendering color of the plant in the model is adjusted based on the withered green state of plant A in the target month, and the plant growth is simulated based on the survival rate of plant A in the target month.

[0073] Specifically, a plant growth simulation model is constructed using existing plant modeling software such as Blender, for example. Figures 2a~2b Figures 3a and 3b show screenshots of the grass and shrub growth model in this embodiment at a certain moment.

[0074] S5) Based on the plant A growth simulation results, calculate the soil and water conservation effect index, automatically compare the soil and water conservation effect index with the prevention and control indexes specified in the national standards, and generate the evaluation conclusion.

[0075] Specifically, the effectiveness of soil and water conservation is judged based on the forest and grassland coverage rate specified in GB / T 50434-2018 "Standards for Soil and Water Conservation in Production and Construction Projects". For example, the standard values ​​for soil and water conservation in the red soil region of southern China are 35%, 22% and 19% for the first, second and third levels, respectively.

[0076] The evaluation conclusions of this embodiment are shown in Table 9 below.

[0077] S6) Construct a 3D scene of the target engineering area, integrate the plant growth simulation model with the 3D scene, and visualize the growth status and spatial distribution of plant A. At the same time, provide a graphical human-computer interaction interface to receive real-time adjustment instructions. For example, if the evaluation conclusion of S5) is that the requirements are not met, select another plant B from the sorted list, or add artificial maintenance measures to change the growth environment of plant A, and repeat steps S3) to S5) until the visualized plant growth status and spatial distribution meet the set water and soil conservation effect index requirements. The final determined growth simulation scheme, growth simulation results and evaluation conclusions are automatically output as a structured report.

[0078] Specifically, the 3D scene of the target engineering area is constructed based on a digital elevation model and orthophotos. The growth of plant A in the 3D scene of the target engineering area is simulated based on the plant's current monthly survival rate and planting density. The number of plants in the current month is calculated as: current monthly survival rate × planting quantity. Surviving plants can be randomly or evenly distributed within the planting area.

[0079] The structured report in this embodiment is shown in Table 9 below.

[0080] Table 9 Structured Report of the Implementation Examples

[0081] The forest and grassland coverage rate is calculated using the projected area of ​​a plant model, without considering overlapping areas. The calculated forest and grassland coverage rate is compared with the index value to determine whether the soil and water conservation effect has been achieved. In Example 1 above, the forest and grassland coverage rate is 25.34%, which is greater than the Level II standard for soil and water conservation and meets the soil and water conservation effect. In Example 2, the forest and grassland coverage rate is 10.53%, which is less than the Level III standard for soil and water conservation and does not meet the soil and water conservation effect.

[0082] The present invention provides a method for intelligent matching and growth simulation of soil and water conservation plants, which further includes step S7), comprehensive calculation, optimization, and control of soil and water conservation plant costs. The specific steps are as follows: S71) Calculate the costs of soil and water conservation plant measures, such as watering, fertilization, pest and disease control, and maintenance, based on plant type, unit price, and maintenance input to achieve soil and water conservation effects. S72) Based on the objectives of minimizing cost, survival rate and plant coverage, multi-objective optimization is carried out. Based on the three optimization objectives of plant cost, survival rate and coverage, environmental basic parameters, initial planting cost of various plants, maintenance frequency and cost are considered. The NSGA-II multi-objective optimization algorithm is used to solve the Pareto optimal solution to find the best plant configuration and supporting maintenance plan. S73) During the monitoring and tracking simulation period, meteorological and rainfall data is integrated, and maintenance status is set according to actual watering, fertilization, pest and disease control, and maintenance treatment. The system tracks and controls costs, and can provide the latest optimized maintenance plan to meet the objectives after weather changes.

[0083] Example 2 The present invention also designs an intelligent matching and growth simulation system for soil and water conservation plants, including a data management module 1, an intelligent matching module 2, a growth calculation module 3, a growth simulation module 4, an effect evaluation module 5, and a three-dimensional visualization and report generation module 6.

[0084] The data management module 1 is used to collect plant knowledge base and engineering environmental data of the target engineering area.

[0085] The intelligent matching module 2 is communicatively connected to the data management module 1 and is used to construct an intelligent matching algorithm or intelligent matching model, filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination.

[0086] The growth calculation module 3 is communicatively connected to the data management module 1 and the intelligent matching module 2. It is used to select a single plant A or a combination of plant A and its symbiotic plants from the selected recommended plant list, and determine the growth simulation scheme of plant A. The growth simulation scheme includes constructing a formula for calculating the body size coefficient of the growth month, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered green state of plant A in the current month.

[0087] The growth simulation module 4 is communicatively connected to the data management module 1, the intelligent matching module 2, and the growth calculation module 3. It is used to construct a plant growth simulation model based on the predicted radius, predicted height, actual survival rate, and withering state of plant A using existing plant modeling software, and to simulate the growth and withering state of plant A in the target month.

[0088] First, set the start time of the simulation, then add the plant types to be simulated. Multiple simulation types can be added, and plant symbiosis or competition relationships can be set. Then, set the basic environmental parameters, including water, fertilizer, saline-alkali land, pests and diseases, plant interactions, etc. Among them, water, fertilizer, saline-alkali land, and plant interactions affect the entire simulation cycle, while pests and diseases only cover the time period of their influence.

[0089] Then, configure the maintenance plan. For pest and disease control, settings are configured on a per-use basis to offset or mitigate the impact of pests and diseases, based on the timing and effectiveness of the control measures. Water and fertilizer settings are configured by time period and frequency to correct for the effects of existing water and fertilizer conditions in the environment; however, there is no corrective effect outside of these time periods. Plant interactions, including symbiotic or competing plants, will have an impact throughout the simulation period. If the survival rate of symbiotic or competing plants decreases to a certain level or reaches zero during the simulation period, the effect disappears.

[0090] The effect evaluation module 5 is communicatively connected to the data management module 1, the intelligent matching module 2, the growth calculation module 3, and the growth simulation module 4. It is used to calculate the soil and water conservation effect index based on the growth simulation results, automatically compare the soil and water conservation effect index with the prevention and control indexes specified in the national standards, and generate an evaluation conclusion.

[0091] The 3D visualization and report generation module 6 is communicatively connected to the data management module 1, intelligent matching module 2, growth calculation module 3, growth simulation module 4, and effect evaluation module 5. It is used to construct a 3D scene of the target engineering area, integrate the plant growth simulation model with the 3D scene, and visualize the growth status and spatial distribution of plant A. At the same time, it provides a graphical human-computer interaction interface to receive real-time adjustment instructions. If the evaluation conclusion of the effect evaluation module 5 is that the requirements are not met, another plant B is selected from the sorted list, or artificial maintenance measures are added to change the growth environment of plant A. The above growth and simulation process is repeated until the visualized plant growth status and spatial distribution meet the set water and soil conservation effect index requirements. The final determined growth simulation scheme, simulation results, and evaluation conclusions are automatically output as a structured report.

[0092] Instantiate and render the predicted dimensions obtained from the calculation engine, and construct a 3D scene of the target engineering area based on the digital elevation model (DEM) and orthophotos; integrate the plant model with the 3D scene to reflect the plant growth and spatial distribution; provide a graphical user interface (GUI) to receive real-time adjustment commands from users for environmental parameters, plant species, planting plans, etc., and recalculate; provide a timeline control to support dynamic playback of the continuous growth process of plants from planting to the target month.

[0093] Specifically, the system is built on a B / S (browser / server) architecture or a C / S (client / server) architecture, and the 3D visualization and interaction module is developed based on WebGL technology or 3D engines such as Unity / Unreal Engine, enabling users to access and interact with it through a web browser or a dedicated client.

[0094] The present invention provides a method and system for intelligent matching and growth simulation of soil and water conservation plants. This method and system not only enables rapid and accurate matching of engineering soil and water conservation plant measures, but also ensures the realization of soil and water conservation effects. It provides a scientific basis for plant planting and maintenance, and provides quantitative data for soil and water conservation plant planting schemes. It has broad application prospects and is applicable to various engineering soil and water conservation projects and ecological restoration projects.

[0095] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A method for intelligent matching and growth simulation of soil and water conservation plants, characterized in that, Includes the following steps: S1) Establish a plant knowledge base and collect engineering environmental data for the target engineering area; S2) Construct an intelligent matching algorithm or intelligent matching model to filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination. S3) Select a single plant A or a combination of plant A and its symbiotic plants from the selected recommended plant list, and determine the plant A growth simulation scheme. The growth simulation scheme includes constructing a formula for calculating the body size coefficient of the growth month, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered green state of plant A in the current month. S4) Based on the predicted radius, predicted height, actual survival rate and withering state of plant A, use existing plant modeling software to construct a plant growth simulation model to simulate the growth and withering state of plant A in the target month. S5) Based on the plant A growth simulation results, calculate the soil and water conservation effect index, automatically compare the soil and water conservation effect index with the prevention and control index specified in the national standard, and generate the evaluation conclusion. S6) Construct a 3D scene of the target engineering area, integrate the plant growth simulation model with the 3D scene, and visualize the growth status and spatial distribution of plant A. At the same time, provide a graphical human-computer interaction interface to receive real-time adjustment instructions. If the evaluation conclusion of S5) is that the requirements are not met, select another plant B from the sorted list, or add artificial maintenance measures to change the growth environment of plant A, and repeat steps S3) to S5) until the visualized plant growth status and spatial distribution meet the set water and soil conservation effect index requirements. The final determined growth simulation scheme, growth simulation results and evaluation conclusions are automatically output as a structured report.

2. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 1, characterized in that: In S1), the plant knowledge base includes plant name, plant type, growth environment requirements, stress resistance, ecological interaction, functional effectiveness, and economic and maintenance costs; the growth environment requirements are used to assess the degree of plant matching with environmental parameters and support environmental adaptability evaluation; the stress resistance is used to describe the plant's drought resistance, waterlogging resistance, cold resistance, and disease and pest resistance, and support stress resistance index evaluation; the ecological interaction is used to assess the interaction between the plant and other plants in the target vegetation type; the functional effectiveness is used to assess the plant's soil and water conservation function; and the economic and maintenance costs are used to assess the availability of plant seedlings, planting costs, and the difficulty of subsequent management.

3. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 2, characterized in that: In S2), the steps for selecting the plant list using the intelligent matching algorithm are as follows: S21) Store the growth environment requirements of each plant in the plant knowledge base as a structured data table; S22) Dynamically configure matching rules, compare the engineering environment data of the target engineering area with the plant growth environment requirements in the structured data table, and select a list of plants that meet the conditions based on the matching degree.

4. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 2, characterized in that: In S2), the steps for selecting the plant list using the intelligent matching model are as follows: S21) Perform in-depth analysis of plant knowledge base data, extract and quantify the growth environment requirements of each plant, and generate a plant growth environment requirement dataset. S22) Identify and extract key environmental features from the engineering environment data of the target engineering area to generate an environmental input dataset; S23) Input the environmental input dataset into the trained intelligent matching model. The intelligent matching model outputs a list of recommended plants through semantic understanding and comprehensive analysis, and provides the main environmental adaptability descriptions for the plants in the list.

5. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 3 or 4, characterized in that: In S2), the plant recommendation scoring mechanism calculates a comprehensive score for each candidate plant or plant combination. The comprehensive score is generated based on a weighted scoring model, which is expressed by the following formula. In the formula, S total This represents the overall score of a candidate plant or plant combination. S e This indicates the environmental adaptability score. S s This indicates the score of resilience indicators. S i Indicates the ecological interactivity score. S f Indicates functional performance score, S c Indicates the economic and maintenance cost score. W e , W s , W i , W f , W c These represent the weights of environmental adaptability, resilience indicators, ecological interactivity, functional effectiveness, and economic and maintenance costs, respectively.

6. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 1, characterized in that: In S3), if plant A is an annual grass species, the formula for calculating the body size coefficient of the growth month is as follows. In the formula, Mc 1 The body size coefficient of annual grass species A during its growth month. m The growing month; If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the leaf growth month is as follows. In the formula, Mc 2 The body size coefficient of the leaf portion of deciduous shrub A during the month of growth. m The growing month; If plant A is a deciduous shrub, the formula for calculating the body size coefficient of the trunk during the months of growth is as follows. In the formula, Mc 3 The body size coefficient of the trunk portion of deciduous shrub A during the months of growth. m The growing month; If plant A is a perennial grass or shrub, the formula for calculating the growth rate correction factor is as follows. In the formula, g This is a growth rate correction factor. S The cumulative body size coefficient under normal growth conditions is the ratio of body size under normal growth conditions to standard body size, 0 ≤ 0. S ≤1, r , b These are the formula parameters used to adjust the growth rate of different plants. a It is an index used to regulate the growth rate of different plants.

7. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 6, characterized in that: In S3), if plant A is a perennial evergreen plant, then plant A's cumulative growth each year, its size is gradually increased according to the growth years, and its actual survival rate is multiplied by the growth years. If plant A is an annual deciduous plant, then plant A will regrow every year, and the actual survival rate will be multiplied by the number of years of growth. If plant A is a perennial deciduous plant, then the leaves of plant A will regenerate every year, and the plant's size will gradually increase according to the number of years of growth. The actual survival rate will be multiplied by the number of years of growth.

8. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 7, characterized in that: In S3), the predicted radius or predicted height of plant A in the current month t is calculated using the following formula. In the formula, D' For plant A, the predicted radius or predicted height for the current month t. D This refers to the standard radius or standard height of plant A, assuming no adverse or favorable external environmental influences, representing the radius or height after maturity. S ( t (This refers to the current month for plant A, without considering corrections for external environmental factors.) t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S ( t- 1) Without considering corrections for external environmental factors, the plant in month A t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. △S( t (This refers to the current month for plant A) t The cumulative increase in body size coefficient without taking into account external environmental adjustments. g This is a growth rate correction factor. S' ( t When considering corrections for external environmental factors, plant A in the current month t The cumulative body shape coefficient is calculated monthly and then accumulated over the months. S' ( t- 1) When considering corrections for external environmental factors, plant A month t- 1. Cumulative body shape coefficient: This is calculated monthly and accumulated over the months. (t) For plant A in the current month t Body shape correction factor considering the influence of external environment. Mc(t) For plant A in the current month t Body size index for the growth month Mc(t- 1 ) For plant month A t -1 is the growth month size coefficient. S ( t s The initial size coefficient of plant A was not adjusted for external environmental factors during planting. S' ( t s To adjust the initial size coefficient of plant A during planting, taking into account the external environment, D s This refers to the initial radius or initial height of plant A when it is planted. t For the current month, the value is taken from the month of the planting year. t s From the beginning of the target year to the month t e .

9. The intelligent matching and growth simulation method for soil and water conservation plants according to claim 1, characterized in that: In S6), the 3D scene of the target engineering area is constructed based on digital elevation model and orthophoto.

10. A smart matching and growth simulation system for soil and water conservation plants, characterized in that, It includes a data management module (1), an intelligent matching module (2), a growth calculation module (3), a growth simulation module (4), an effect evaluation module (5), and a three-dimensional visualization and report generation module (6). The data management module (1) is used to collect plant knowledge base and engineering environmental data of the target engineering area; The intelligent matching module (2) is used to construct an intelligent matching algorithm or intelligent matching model, filter and output a list of recommended plants from the constructed plant knowledge base, and introduce a plant recommendation scoring mechanism to sort the list according to the comprehensive score of each candidate plant or plant combination. The growth calculation module (3) is used to select a single plant A or a combination scheme of plant A and its symbiotic plants from the selected recommended plant list, and determine the growth simulation scheme of plant A. The growth simulation scheme includes constructing a formula for calculating the body size coefficient of the growth month, and combining the corresponding growth rate correction coefficient and survival rate coefficient to calculate the predicted radius, predicted height, actual survival rate and withered green state of plant A in the current month. The growth simulation module (4) is used to construct a plant growth simulation model based on the predicted radius, predicted height, actual survival rate and withering state of plant A, using existing plant modeling software, to simulate the growth and withering state of plant A in the target month. The effect evaluation module (5) is used to calculate the soil and water conservation effect index based on the growth simulation results, automatically compare the soil and water conservation effect index with the prevention and control index specified in the national standard, and generate an evaluation conclusion. The three-dimensional visualization and report generation module (6) is used to construct a three-dimensional scene of the target engineering area, integrate the plant growth simulation model with the three-dimensional scene, and visualize the growth status and spatial distribution of plant A. At the same time, it provides a graphical human-computer interaction interface to receive real-time adjustment instructions. If the evaluation conclusion of the effect evaluation module (5) is that the requirements are not met, another plant B is selected from the sorting list, or artificial maintenance measures are added to change the growth environment of plant A. The above growth and simulation process is repeated until the visualized plant growth status and spatial distribution meet the set water and soil conservation effect index requirements. The final determined growth simulation scheme, simulation results and evaluation conclusions are automatically output as a structured report.

Images