A garden landscape design method based on virtual reality technology

Abstract

The application discloses a kind of garden landscape design methods based on virtual reality technology, it is related to virtual reality technology field, first, the method is by the pre-processing to the climate data and vegetation growth data collected, and input vegetation prediction analysis model, can accurately predict and calculate the photosynthesis change fluctuation coefficient P (t) in wetland garden, wetland garden land water storage Ws (t) and vegetation health coefficient Hv (t), again by initial setting vegetation health threshold F1 with the vegetation health coefficient Hv (t) obtained by preliminary comparison and evaluation of prediction, can intuitively understand the ecology and growth condition of vegetation in wetland garden in future time period in virtual environment, this kind of dynamic feedback mode based on data driving, so that garden design has high-precision scientific simulation capability in initial stage, help designer real-time adjustment design scheme, to cope with future climate change and vegetation health problem.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of virtual reality technology, in particular to a garden landscape design method based on virtual reality technology. BACKGROUND

[0002] With the development of virtual reality technology, the way of garden design has changed from traditional two-dimensional drawings and physical models to three-dimensional digital models, allowing designers to more intuitively construct scenes and optimize plans. In specific applications, wetland garden design has gradually become an important branch of this technology, which not only needs to consider traditional aesthetics and ecological requirements, but also must cope with complex environmental factors such as climate change, soil moisture, and plant health. Through virtual reality technology combined with meteorological models and vegetation growth data, designers can conduct comprehensive simulation and prediction in a three-dimensional virtual scene to achieve more accurate garden planning.

[0003] At present, in the design of wetland gardens, traditional methods mainly rely on experience and historical climate data for plant configuration and ecological planning. However, these methods are often difficult to cope with complex climate change impacts, especially rising temperatures, changing precipitation patterns, and soil moisture fluctuations. In addition, existing design tools lack real-time simulation of future environmental changes, resulting in inaccurate predictions of vegetation adaptability and potential health problems in extreme weather conditions. Due to the inability to dynamically monitor photosynthetic efficiency, transpiration, and water requirements of vegetation, design plans often need to be adjusted significantly after the project is completed, increasing maintenance costs and management difficulties. SUMMARY

[0004] To address the shortcomings of the prior art, the present application provides a garden landscape design method based on virtual reality technology, which solves the problems mentioned in the background art.

[0005] To achieve the above purpose, the present application is implemented by the following technical scheme: a garden landscape design method based on virtual reality technology, comprising the following steps:

[0006] S1, using wetland garden geographic information and topographic data, establishing a three-dimensional scene of a wetland garden in virtual reality, and integrating with a meteorological model to realistically simulate the environment of the three-dimensional scene of the wetland garden, and collecting climate data and vegetation growth data in the three-dimensional scene of the wetland garden;

[0007] S2, real-time extraction and preprocessing of the collected climate data and vegetation growth data, respectively obtaining a climate data set and a vegetation growth data set, and then constructing a time series database to store the climate data set and the vegetation growth data set;

[0008] S3, by constructing a vegetation prediction analysis model, extracting the climate dataset and the vegetation growth dataset in the time series database and inputting them into the vegetation prediction analysis model, respectively outputting the photosynthesis change fluctuation coefficient P(t), the wetland landscape land water storage amount Ws(t) and the vegetation health coefficient Hv(t) at time t;

[0009] S4, by initially setting the vegetation health threshold F1 and preliminarily comparing and evaluating the vegetation health coefficient Hv(t) obtained by prediction, the health state of the current wetland landscape vegetation in the future time period is analyzed;

[0010] S5, based on the preliminary comparison and evaluation result, the adaptability of the current wetland landscape vegetation is further analyzed, a comprehensive vegetation adaptability algorithm model is constructed, the adaptability coefficient Av(t) of each vegetation is calculated and output, the average environmental adaptability value Amean(t) is obtained by averaging calculation, and the adaptability of the individual vegetation is analyzed by twice comparison with the adaptability coefficient Av(t) of each vegetation in the wetland landscape, and a vegetation design scheme in the wetland landscape is generated.

[0011] Preferably, S1 comprises S11 and S12;

[0012] S11, the geographic data of the wetland landscape is imported into the 3D modeling software using the GIS software, a three-dimensional scene of the wetland landscape is created, the three-dimensional scene includes the terrain, topography, water body distribution and vegetation distribution of the wetland landscape, and the ecological details of the wetland park are further refined through the 3D modeling software, the ecological details include the vegetation types, water flow and footpath;

[0013] The three-dimensional scene of the wetland landscape is integrated with the weather model through the API application program interface, the future climate data output by the weather model is input into the three-dimensional scene of the wetland landscape as time series, a time axis is established through the virtual reality engine, dynamic climate data is input, climate variables in different seasons and different time periods are simulated, and the growth of the vegetation is real-time displayed;

[0014] S12, based on the future climate data and the growth of the vegetation output by the weather model of the three-dimensional scene of the wetland landscape, the climate data and the vegetation growth data of the wetland landscape are real-time collected;

[0015] The climate data includes the environmental humidity H, the environmental temperature T, the radiation intensity Ir, the soil evaporation coefficient Kst, the underground water level change rate Gw and the vegetation transpiration coefficient Tv;

[0016] The vegetation growth data includes the photosynthesis efficiency Pe, the leaf area index LAI and the root water absorption rate Rw.

[0017] Preferably, S2 comprises S21 and S22;

[0018] S21, real-time extraction of climate data and vegetation growth data in the wetland garden three-dimensional scene for preprocessing, the preprocessing mode includes data cleaning and normalization processing, after preprocessing, the collection time of the climate data and the vegetation growth data is labeled with a time stamp according to the time point of the dynamic simulation of the wetland garden three-dimensional scene, and after labeling, the climate data set and the vegetation growth data set are obtained by integration;

[0019] The climate data set includes environmental humidity H(t) at time t, environmental temperature T(t) at time t, radiation intensity Ir(t) at time t, soil evaporation coefficient Kst(t) at time t, groundwater level change rate Gw(t) at time t, and vegetation transpiration coefficient Tv(t) at time t;

[0020] The vegetation growth data set includes leaf area index LAI(t) at time t and root water absorption rate Rw(t) at time t;

[0021] S22, reconstruct the time series database and set the write-in port and the write-out port, and store the obtained climate data set and vegetation growth data set in the time series database through the write-in port and in the time series database according to the time stamp order.

[0022] Preferably, S3 comprises S31;

[0023] S31, the vegetation prediction analysis model is constructed by integrating photosynthesis fluctuation algorithm model, water cycle transpiration algorithm model and vegetation health state algorithm model;

[0024] S31 comprises S311, S312 and S313;

[0025] S311, the photosynthesis fluctuation algorithm model is constructed by a nonlinear inhibition model, and the climate data set and the vegetation growth data set are extracted from the write-out port of the time series database and input into the photosynthesis fluctuation algorithm model for calculation to output photosynthesis change fluctuation coefficient P(t) for predicting the photosynthesis change fluctuation of the vegetation at future time t;

[0026] The photosynthesis change fluctuation coefficient P(t) is calculated by the following photosynthesis fluctuation algorithm model:

[0027] ;

[0028] In the formula, Topt represents the standard growth temperature of the plant, which is initially set according to the characteristics of the plant, exp represents an exponential function, represents a temperature adjustment coefficient, Indicates the humidity adjustment coefficient; this formula is a nonlinear inhibition model, in which temperature and humidity affect the photosynthesis efficiency of plants through exponential functions, and excessive high or low temperature will reduce the photosynthesis efficiency, and the change of humidity also affects the physiological response of plants.

[0029] Preferably, S312 constructs a water cycle transpiration algorithm model through integral operation and nonlinear function, and extracts the climate dataset and vegetation growth dataset through the write-out port of the time series database, and inputs them into the water cycle transpiration algorithm model to calculate the wetland landscape land water storage Ws(t) at time t, and analyze the wetland landscape water cycle and transpiration;

[0030] The wetland landscape land water storage Ws(t) is calculated by the following water cycle transpiration algorithm model:

[0031] ;

[0032] In the formula, J(t) represents the rainfall at time t, E(t) represents the water evaporation at time t, Rw(t) represents the root water absorption rate at time t, Gw(t) represents the change rate of groundwater level at time t, and dt represents the micro-variable of time integral variable t; the formula calculates the wetland water resource balance within time t through integral operation, and designers can optimize the water resource distribution of the wetland by simulating the water flow under different seasons and climates in virtual reality, to ensure the water supply of plants.

[0033] Preferably, S313 constructs a vegetation health state algorithm model through multi-parameter coupling nonlinear, and inputs the obtained photosynthetic change fluctuation coefficient P(t) and wetland landscape land water storage Ws(t) into the vegetation health state algorithm model to calculate the overall vegetation health coefficient Hv(t) in the wetland landscape to predict the health state of the vegetation in the wetland landscape;

[0034] The vegetation health coefficient Hv(t) is calculated by the following vegetation health state algorithm model:

[0035] ;

[0036] In the formula, N(t) represents the nutrient supply level of the vegetation at time t, and Dp(t) represents the occurrence rate of diseases and pests at time t, which are initially set during three-dimensional modeling, represents the nutrient adjustment coefficient, represents the root water absorption capacity adjustment coefficient, represents the adjustment coefficient of the influence of diseases and pests on the health of the vegetation.

[0037] Preferably, S4 includes S41;

[0038] S41, based on the initial setting of the vegetation health index, the vegetation health threshold F1 is compared with the obtained vegetation health coefficient Hv(t) for preliminary evaluation, and the health status of the vegetation in the future prediction stage is analyzed. The specific evaluation content is as follows:

[0039] When the vegetation health coefficient Hv(t) is greater than or equal to the vegetation health threshold F1, it indicates that the health status of the current vegetation in the future prediction stage is normal, and the vegetation design of the wetland garden does not need to be adjusted;

[0040] When the vegetation health coefficient Hv(t) is less than the vegetation health threshold F1, it indicates that the health status of the current vegetation in the future prediction stage is abnormal, and the vegetation design of the wetland garden needs to be adjusted.

[0041] Preferably, S5 includes S51, S52 and S53;

[0042] S51, when the preliminary comparative evaluation identifies that the health status in the future prediction stage is abnormal, the adaptability coefficient Av(t) of each vegetation is calculated and output through the comprehensive vegetation adaptability algorithm model;

[0043] The adaptability coefficient Av(t) of each vegetation is calculated and output through the following comprehensive vegetation adaptability algorithm model;

[0044] ;

[0045] In the formula, Av i (t) represents the adaptability coefficient of the i-th vegetation at time t, Tmax and Tmin represent the upper limit value and the lower limit value of the temperature tolerance of the vegetation, respectively.

[0046] Preferably, S52, based on the adaptability coefficient Av(t) of each vegetation obtained, the adaptability of the whole vegetation community of the wetland garden is calculated, and the average environmental adaptability value Amean(t) is obtained by averaging calculation;

[0047] The average environmental adaptability value Amean(t) is calculated and output through the following algorithm formula;

[0048] ;

[0049] In the formula, N represents the total number of vegetation samples in the wetland garden.

[0050] Preferably, S53, based on the average environmental adaptability value Amean(t) of the capital in the wetland garden and the adaptability coefficient Av(t) of each vegetation in the wetland garden, secondary comparative evaluation is carried out, and wetland garden vegetation adjustment suggestions are generated. The specific evaluation content is as follows:

[0051] When the adaptability coefficient Av(t) is greater than or equal to the average environmental adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is normal, at this time, the wetland landscape environment optimization suggestion is generated, the wetland landscape environment is adjusted, and the health status of the vegetation i in the future stage is maintained;

[0052] When the adaptability coefficient Av(t) is less than the average environmental adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is abnormal, at this time, the wetland landscape vegetation optimization suggestion is generated, and the variety of the wetland landscape vegetation is replaced.

[0053] Beneficial effects

[0054] The application provides a garden landscape design method based on virtual reality technology. The method has the following beneficial effects:

[0055] (1) The method simulates the three-dimensional scene environment of the wetland landscape by integrating virtual reality technology, geographical information of the wetland landscape and a meteorological model. The method not only provides an intuitive three-dimensional visual scene, but also synchronously collects and processes real-time climate data and vegetation growth data. By inputting the data into a time series database and a vegetation prediction analysis model, the system can dynamically output a photosynthetic fluctuation coefficient, a wetland water storage amount and a vegetation health status.

[0056] (2) The method can accurately predict and calculate a photosynthetic fluctuation coefficient P(t), a wetland landscape land water storage amount Ws(t) and a vegetation health coefficient Hv(t) in the wetland landscape by preprocessing the collected climate data and vegetation growth data and inputting the data into the vegetation prediction analysis model. By preliminarily comparing and evaluating the vegetation health threshold F1 and the vegetation health coefficient Hv(t) obtained by prediction, the ecological and growth conditions of the vegetation in the wetland landscape in the future time period can be intuitively understood in the virtual environment. This data-driven dynamic feedback mode enables the garden design to have high-precision scientific simulation capability in the early stage, helps designers to adjust the design scheme in real time, and responds to future climate change and vegetation health problems.

[0057] (3) The method is based on a comprehensive vegetation adaptability algorithm model, and further calculates the adaptability coefficient Av(t) of each vegetation by combining the preliminary evaluation result of the vegetation health coefficient Hv(t) and the health threshold F1, and performing secondary comparison and analysis with the average environmental adaptability value Amean(t) of the overall vegetation in the wetland landscape. This method can accurately evaluate the adaptability of each plant under future climate conditions, help designers generate an optimized garden vegetation configuration scheme, effectively improve the ecological stability and sustainability of the wetland landscape, and avoid future vegetation health problems. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1A garden landscape design method based on virtual reality technology. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work are within the protection scope of the present application.

[0060] Embodiment 1

[0061] The present application provides a garden landscape design method based on virtual reality technology, please refer to Figure 1 , comprising the following steps:

[0062] S1, using wetland garden geographic information and terrain data, establishing a three-dimensional scene of the wetland garden in virtual reality, and integrating with a weather model, to simulate the three-dimensional scene environment of the wetland garden, and collect climate data and vegetation growth data in the three-dimensional scene of the wetland garden;

[0063] S2, real-time extraction of the collected climate data and vegetation growth data for preprocessing, respectively obtaining a climate data set and a vegetation growth data set, and then constructing a time series database to store the climate data set and the vegetation growth data set;

[0064] S3, by constructing a vegetation prediction analysis model, extracting the climate data set and the vegetation growth data set in the time series database and inputting them into the vegetation prediction analysis model, respectively outputting the photosynthetic change fluctuation coefficient P(t), the wetland garden land water storage amount Ws(t) and the vegetation health coefficient Hv(t) at time t;

[0065] S4, by initially setting the vegetation health threshold F1 and preliminarily comparing and evaluating the vegetation health coefficient Hv(t) obtained by prediction, analyzing the health status of the current wetland garden vegetation in the future time period;

[0066] S5, based on the preliminary comparison and evaluation result, further analyzing the adaptability of the current wetland garden vegetation, constructing a comprehensive vegetation adaptability algorithm model to calculate and output the adaptability coefficient Av(t) of each vegetation, then performing average calculation to obtain the average environmental adaptability value Amean(t), and performing secondary comparison with the adaptability coefficient Av(t) of each vegetation in the wetland garden, analyzing the adaptability of individual vegetation, and generating a vegetation design scheme in the wetland garden.

[0067] In this embodiment, the method constructs a virtual reality three-dimensional scene by using geographic information and topographic data of the wetland garden, and integrates with a meteorological model to accurately simulate the wetland environment under different climate conditions. Subsequently, climate data and vegetation growth data are collected in real time and stored through preprocessing and time series database, providing a reliable foundation for subsequent analysis. Through the vegetation prediction analysis model, the photosynthetic fluctuation coefficient P(t), the wetland garden land water storage amount Ws(t), and the vegetation health coefficient Hv(t) in the future time period can be predicted. Then, the vegetation health coefficient Hv(t) is compared with the set health threshold F1 to evaluate and identify the vegetation with abnormal health status. Finally, through the comprehensive vegetation adaptability algorithm model, the adaptability coefficient Av(t) of each vegetation is calculated and compared with the average adaptability value Amean(t) to generate an optimized vegetation design scheme. Compared with existing design methods, this method integrates meteorological models and virtual reality scenes to achieve higher precision in ecological simulation and future environment prediction. Through real-time data processing and dynamic analysis, not only can vegetation health problems be identified in advance, but also the wetland garden vegetation design can be adjusted according to adaptability evaluation to ensure that the wetland garden design can cope with future climate change, reduce maintenance costs and ecological risks. This method significantly improves the scientificity and sustainability of the design, optimizes the stability and resource management efficiency of the garden ecosystem, and achieves the effect improvement that traditional technology cannot achieve

[0068] Embodiment 2

[0069] This embodiment is an explanation and description in Embodiment 1, please refer to Figure 1 , specifically: S1 includes S11 and S12;

[0070] S11, using GIS software to import the geographic data of the wetland garden into 3D modeling software to create a three-dimensional scene of the wetland garden, the three-dimensional scene including the terrain, topography, water distribution and vegetation distribution of the wetland garden. Further, through the 3D modeling software, the ecological details of the wetland park are further refined, including vegetation types, water flow and footpaths;

[0071] Then, through the API application interface, the three-dimensional scene of the wetland garden is integrated with the meteorological model. The meteorological model outputs future climate data, which is input as a time series into the three-dimensional scene of the wetland garden. Through the virtual reality engine, a time axis is established to input dynamic climate data, simulate climate variables in different seasons and time periods, and display the growth of vegetation in real time;

[0072] S12, based on the meteorological model outputting future climate data and the growth of vegetation based on the three-dimensional scene of the wetland garden, real-time collection of climate data and vegetation growth data of the wetland garden;

[0073] The climate data includes environmental humidity H, environmental temperature T, radiation intensity Ir, soil evaporation coefficient Kst, groundwater level change rate Gw, and vegetation transpiration coefficient Tv.

[0074] The vegetation growth data includes photosynthetic efficiency Pe, leaf area index LAI, and root water absorption rate Rw.

[0075] In this embodiment, the method imports the geographical data of the wetland garden by using GIS software, and refines ecological details such as vegetation types, water flow, and path arrangement by using 3D modeling software, to create a highly accurate three-dimensional scene. Then, the scene is integrated with the weather model through an API interface, future climate data is input, and climate changes in different time periods and seasons are simulated. Through the time axis function of the virtual reality engine, the growth of vegetation under different climate conditions is displayed in real time. Further, through the weather model output of the three-dimensional scene, key climate data and vegetation growth data are collected in real time, providing a scientific basis for subsequent analysis and design optimization. This process brings significant improvements compared to traditional design techniques. First, through the deep combination of virtual reality technology and weather models, highly dynamic and refined climate and vegetation simulation is achieved, which can more accurately predict the impact of future climate change on the ecology of the garden.

[0076] Embodiment 3

[0077] This embodiment is an explanation and description in Embodiment 2, please refer to Figure 1 , in particular: S2 includes S21 and S22;

[0078] S21, real-time extraction of climate data and vegetation growth data in the wetland garden three-dimensional scene for preprocessing, the preprocessing mode includes data cleaning and normalization processing, after preprocessing, the collection time of climate data and vegetation growth data is labeled with time stamp according to the time point of dynamic simulation of wetland garden three-dimensional scene, and after labeling, the climate data set and the vegetation growth data set are obtained by integration;

[0079] The climate data set includes environmental humidity H(t) at time t, environmental temperature T(t) at time t, radiation intensity Ir(t) at time t, soil evaporation coefficient Kst(t) at time t, groundwater level change rate Gw(t) at time t, and vegetation transpiration coefficient Tv(t) at time t;

[0080] The vegetation growth data set includes leaf area index LAI(t) at time t and root water absorption rate Rw(t) at time t;

[0081] S22, reconstruct the time series database and set the write-in port and the write-out port, write the obtained climate data set and vegetation growth data set into the time series database in the order of time stamp sequence through the write-in port for storage.

[0082] In this embodiment, the method standardizes the collected meteorological and vegetation growth data through data cleaning and normalization processing, and labels the data with timestamps at the dynamic simulation time points, ensuring data accuracy and timeliness. At the same time, these data form complete climate data sets and vegetation growth data sets after integration, and then through the construction of a time series database, the preprocessed data is stored in order of timestamp, and write and write-out ports are set, facilitating subsequent analysis and calling.

[0083] Embodiment 4

[0084] This embodiment is an explanation and description in embodiment 3, please refer to Figure 1 , specifically: S3 includes S31;

[0085] S31, the vegetation prediction analysis model is constructed by integrating photosynthesis fluctuation algorithm model, water cycle transpiration algorithm model and vegetation health state algorithm model;

[0086] S31 includes S311, S312 and S313;

[0087] S311, the photosynthesis fluctuation algorithm model is constructed by a nonlinear inhibition model, and then the climate data set and the vegetation growth data set are extracted through the write-out port of the time series database and input into the photosynthesis fluctuation algorithm model to calculate and output the photosynthesis change fluctuation coefficient P(t) for predicting the photosynthesis change fluctuation of vegetation at future time t;

[0088] The photosynthesis change fluctuation coefficient P(t) is calculated and output by the following photosynthesis fluctuation algorithm model;

[0089] ;

[0090] In the formula, Topt represents the standard growth temperature of the plant, which is initially set according to the characteristics of the plant, exp represents the exponential function, represents the temperature adjustment coefficient, represents the humidity adjustment coefficient; this formula is a nonlinear inhibition model, in which temperature and humidity affect the photosynthesis efficiency of the plant through the exponential function, and high or low temperature will reduce the photosynthesis efficiency, and the change of humidity also affects the physiological response of the plant.

[0091] S312, the water cycle transpiration algorithm model is constructed by integral operation and nonlinear function, and then the climate data set and the vegetation growth data set are extracted through the write-out port of the time series database and input into the water cycle transpiration algorithm model to calculate and output the wetland landscape land water storage amount Ws(t) at time t to analyze the wetland landscape water cycle and transpiration;

[0092] The wetland garden land water storage amount Ws(t) is calculated and output by the following water cycle transpiration algorithm model;

[0093] ;

[0094] In the formula, J(t) represents the rainfall at time t, E(t) represents the water evaporation at time t, Rw(t) represents the root water absorption rate at time t, Gw(t) represents the change rate of groundwater level at time t, and dt represents the micro-variable of time integral variable t; the formula calculates the wetland water resource balance within time t through integral operation, and through simulating water flow under different seasons and climates in virtual reality, designers can optimize the water resource distribution of the wetland to ensure the water supply of plants.

[0095] S313, construct a vegetation health state algorithm model through multi-parameter coupling nonlinearity, and combine the obtained photosynthetic change fluctuation coefficient P(t) and wetland garden land water storage amount Ws(t) to input into the vegetation health state algorithm model to calculate and output the overall vegetation health coefficient Hv(t) in the wetland garden, and predict the health state of the vegetation in the wetland garden;

[0096] The vegetation health coefficient Hv(t) is calculated and output by the following vegetation health state algorithm model;

[0097] ;

[0098] In the formula, N(t) represents the nutrient supply level of the vegetation at time t, and Dp(t) represents the disease and pest occurrence rate at time t, which are initially set during three-dimensional modeling, represents the nutrient adjustment coefficient, represents the root water absorption capacity adjustment coefficient, represents the adjustment coefficient of the influence of diseases and pests on vegetation health.

[0099] S4 includes S41;

[0100] S41, based on the vegetation health index, initially set the vegetation health threshold F1 and preliminarily compare and evaluate the obtained vegetation health coefficient Hv(t), analyze the health state of the vegetation in the future prediction stage, and the specific evaluation contents are as follows;

[0101] When the vegetation health coefficient Hv(t) is greater than or equal to the vegetation health threshold F1, it indicates that the health state of the current vegetation in the future prediction stage is normal, and at this time the vegetation design of the wetland garden does not need to be adjusted;

[0102] When the vegetation health coefficient Hv(t) < vegetation health threshold F1, it indicates that the current vegetation is in an abnormal health state in the future prediction stage, and the vegetation design of the wetland garden needs to be adjusted.

[0103] In this embodiment, the method constructs a photosynthesis fluctuation algorithm model through a nonlinear suppression model, predicts the fluctuation coefficient P(t) of the photosynthesis of the vegetation in the future time period using climate and vegetation data, and effectively simulates the photosynthesis efficiency under different temperature and humidity conditions. Then, through a water cycle transpiration algorithm model, combined with rainfall, evaporation, root water absorption rate, etc., the water storage amount Ws(t) of the wetland garden is dynamically calculated, and the water resource allocation strategy of the wetland is optimized. Finally, the vegetation health state algorithm combines multi-parameter coupling to output the vegetation health coefficient Hv(t), thereby predicting the health state of the vegetation in the future wetland garden, and preliminarily comparing and evaluating through the set health threshold F1 to determine whether the garden design needs to be adjusted. The algorithm model combines dynamic data processing and nonlinear analysis, realizes comprehensive prediction of photosynthesis, transpiration and vegetation health, and improves the prediction accuracy. Secondly, through the combination of the time series database and the algorithm model, the designer can make decisions on the health state of the vegetation in advance based on future climate change and ecological data, avoiding the problem that the traditional design cannot cope with future climate challenges. These improvements ultimately improve the scientificity, environmental adaptability and sustainability of the wetland garden design, ensuring that the garden landscape can remain healthy and stable under future extreme climate conditions.

[0104] Embodiment 5

[0105] This embodiment is an explanation and description in Embodiment 4, please refer to Figure 1 , specifically: S5 includes S51, S52 and S53;

[0106] S51, when the preliminary comparison and evaluation identifies that the health state is abnormal in the future prediction stage, the adaptability coefficient Av(t) of each vegetation is calculated and output through a comprehensive vegetation adaptability algorithm model;

[0107] The adaptability coefficient Av(t) of each vegetation is calculated and output through the following comprehensive vegetation adaptability algorithm model;

[0108] ;

[0109] In the formula, Av i (t) represents the adaptability coefficient of the i-th vegetation at time t, Tmax and Tmin represent the upper limit value and the lower limit value of the temperature tolerance of the vegetation, respectively.

[0110] S52, based on the acquired adaptability coefficient Av(t) of each vegetation, the adaptability of the overall vegetation community of the wetland garden is calculated, and the average environment adaptability value Amean(t) is acquired by averaging calculation;

[0111] The average environment adaptability value Amean(t) is calculated and output by the following algorithm formula;

[0112] ;

[0113] In the formula, N represents the total number of vegetation samples in the wetland garden.

[0114] S53, based on the acquired average environment adaptability value Amean(t) of the capital in the wetland garden and the adaptability coefficient Av(t) of each vegetation in the wetland garden, secondary comparison and evaluation are performed, and wetland garden vegetation adjustment suggestions are generated. The specific evaluation contents are as follows:

[0115] When the adaptability coefficient Av(t) is greater than or equal to the average environment adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is normal, at this time, the wetland garden environment optimization suggestion is generated, the wetland garden environment is adjusted, and the health status of the vegetation i in the future stage is maintained.

[0116] When the adaptability coefficient Av(t) is less than the average environment adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is abnormal, at this time, the wetland garden vegetation optimization suggestion is generated, and the species of the wetland garden vegetation is adjusted for replacement.

[0117] In this embodiment, the method further analyzes the adaptability of vegetation in the wetland garden by integrating the vegetation adaptability algorithm model and provides optimization suggestions. When the preliminary assessment finds that the health status of certain vegetation is abnormal under future environmental conditions, the system quantifies the adaptability of each vegetation to future climate conditions by calculating the adaptability coefficient Av(t) of each vegetation. Subsequently, based on the adaptability coefficient of each vegetation, the system calculates the average environmental adaptability value Amean(t) of the entire garden and generates specific optimization suggestions by comparing it with the adaptability coefficient Av(t) of individual vegetation. When the adaptability of a certain vegetation is lower than the average value, the system proposes a vegetation replacement suggestion to ensure the health status of the entire garden vegetation under future environmental conditions; while the adaptability of vegetation higher than the average value, the system suggests to further optimize its growth conditions through environmental adjustment. This method brings significant improvement compared to traditional methods. Through the dual analysis of individual vegetation and group adaptability, it can identify plant species that may face climate challenges in advance and avoid the risk of deterioration of vegetation health status. This method makes the garden design scheme more scientific and dynamic through data-driven adaptability analysis, thereby improving the environmental adaptability and sustainability of the garden landscape. At the same time, the automatically generated vegetation optimization suggestions greatly reduce the complexity of later maintenance and adjustment, ensuring the long-term ecological stability of the garden design.

[0118] While embodiments of the present application have been shown and described with reference to particular embodiments thereof, it will be understood by those skilled in the art that various changes in form and details can be made therein without departing from the spirit and scope of the application. The scope of the application is defined by the appended claims and their equivalents.

Claims

1. A virtual reality technology-based garden landscape design method, characterized in that: The method comprises the following steps: S1, using wetland garden geographic information and terrain data, a three-dimensional scene of the wetland garden in virtual reality is established, and is integrated with a meteorological model to simulate the three-dimensional scene environment of the wetland garden and collect climate data and vegetation growth data in the three-dimensional scene of the wetland garden; The climate data comprises environmental humidity H, environmental temperature T, radiation intensity Ir, soil evaporation coefficient Kst, underground water level change rate Gw and vegetation transpiration coefficient Tv; The vegetation growth data comprises photosynthesis efficiency Pe, leaf area index LAI and root water absorption rate Rw; S2, the collected climate data and vegetation growth data are preprocessed in real time, climate data sets and vegetation growth data sets are obtained, and a time sequence database is constructed to store the climate data sets and the vegetation growth data sets; The climate data sets comprise environmental humidity H(t) at time t, environmental temperature T(t) at time t, radiation intensity Ir(t) at time t, soil evaporation coefficient Kst(t) at time t, underground water level change rate Gw(t) at time t and vegetation transpiration coefficient Tv(t) at time t; The vegetation growth data sets comprise leaf area index LAI(t) at time t and root water absorption rate Rw(t) at time t; S3, a vegetation prediction analysis model is constructed, the climate data sets and the vegetation growth data sets in the time sequence database are input into the vegetation prediction analysis model, and photosynthesis change fluctuation coefficient P(t), wetland garden land water storage amount Ws(t) and vegetation health coefficient Hv(t) at time t are output respectively; The S3 comprises S31; S31, the vegetation prediction analysis model is constructed by a photosynthesis fluctuation algorithm model, a water cycle transpiration algorithm model and a vegetation health state algorithm model; The S31 comprises S311, S312 and S313; S311, the photosynthesis fluctuation algorithm model is constructed by a nonlinear inhibition model, the climate data sets and the vegetation growth data sets are extracted through a write-out port of the time sequence database and input into the photosynthesis fluctuation algorithm model, photosynthesis change fluctuation coefficient P(t) is calculated and output, and photosynthesis change fluctuation of the vegetation at future time t is predicted; The photosynthesis change fluctuation coefficient P(t) is calculated and output by the following photosynthesis fluctuation algorithm model; ； wherein Topt represents the standard growth temperature of the plant, exp represents the exponential function, represents the temperature regulation coefficient, represents the humidity regulation coefficient; S312, the water cycle transpiration algorithm model is constructed by integral operation and a nonlinear function, the climate data sets and the vegetation growth data sets are extracted through the write-out port of the time sequence database and input into the water cycle transpiration algorithm model, wetland garden land water storage amount Ws(t) at time t is calculated and output, and wetland garden water cycle and transpiration are analyzed; The wetland garden land water storage amount Ws(t) is calculated and output by the following water cycle transpiration algorithm model; ； In the formula, J(t) represents rainfall at time t, E(t) represents water evaporation at time t, Rw(t) represents root water absorption rate at time t, Gw(t) represents underground water level change rate at time t, and dt represents a micro variable of time integral variable t; S313, a vegetation health state algorithm model is constructed through multi-parameter coupling nonlinearity, and the obtained photosynthesis change fluctuation coefficient P(t) and wetland garden land water storage Ws(t) are input into the vegetation health state algorithm model for calculation and output of a wetland garden overall vegetation health coefficient Hv(t), so that the health state of the vegetation in the wetland garden is predicted; The vegetation health coefficient Hv(t) is calculated and output through the following vegetation health state algorithm model: ； In the formula, N(t) represents the nutrient supply level of the vegetation at time t, Dp(t) represents the disease and pest occurrence rate at time t, represents a nutrient adjustment coefficient, represents a root water absorption capacity adjustment coefficient, represents an adjustment coefficient of the influence of diseases and pests on the health of the vegetation; S4, the vegetation health threshold F1 is initially set, and the vegetation health coefficient Hv(t) obtained through prediction is preliminarily compared and evaluated, so that the health state of the current wetland garden vegetation in a future time period is analyzed; S5, based on the preliminary comparison and evaluation result, the adaptability of the current wetland garden vegetation is further analyzed, a comprehensive vegetation adaptability algorithm model is constructed, an adaptability coefficient Av(t) of each vegetation is calculated and output, an average environmental adaptability value Amean(t) is obtained through average calculation, and the adaptability coefficient Av(t) of each vegetation in the wetland garden is compared again, so that the adaptability of the individual vegetation is analyzed, and a wetland garden vegetation design scheme is generated; S53, based on the comparison and evaluation of the average environmental adaptability value Amean(t) of the capital in the wetland garden and the adaptability coefficient Av(t) of each vegetation in the wetland garden, a wetland garden vegetation adjustment suggestion is generated, and specific evaluation contents are as follows: When the adaptability coefficient Av(t) is greater than or equal to the average environmental adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is normal, at this time, a wetland garden environment optimization suggestion is generated, the wetland garden environment is adjusted, and the health state of the vegetation i in the future stage is maintained; When the adaptability coefficient Av(t) is less than the average environmental adaptability value Amean(t), it indicates that the adaptability of the current vegetation i is abnormal, at this time, a wetland garden vegetation optimization suggestion is generated, and the species of the wetland garden vegetation is adjusted. 2.The garden landscape design method based on virtual reality technology according to claim 1, characterized in that: The S1 includes S11 and S12; S11, the geographic data of the wetland garden is imported into 3D modeling software by using GIS software, a three-dimensional scene of the wetland garden is created, the three-dimensional scene includes the terrain, topography, water body distribution and vegetation distribution of the wetland garden, and the ecological details of the wetland park are further refined by using the 3D modeling software, the ecological details include the vegetation types, water flow and footpaths; The three-dimensional scene of the wetland garden and the meteorological model are integrated through an API application program interface, future climate data output by the meteorological model is input into the three-dimensional scene of the wetland garden as a time sequence, a time axis is established through a virtual reality engine, dynamic climate data are input, climate variables in different seasons and different time periods are simulated, and the growth of the vegetation is displayed in real time; S12, output future climate data and vegetation growth conditions based on the meteorological model of the wetland garden three-dimensional scene, and collect climate data and vegetation growth data of the wetland garden in real time. 3.The garden landscape design method based on virtual reality technology according to claim 2, characterized in that: The S2 includes S21 and S22. S21, real-time extraction of climate data and vegetation growth data in the wetland garden three-dimensional scene for preprocessing, the preprocessing mode including data cleaning and normalization processing, and after preprocessing, the collection time of the climate data and the vegetation growth data is labeled with a time stamp according to the time point of the dynamic simulation of the wetland garden three-dimensional scene, and after labeling, the climate data set and the vegetation growth data set are obtained by integration. S22, reconstruct the time series database and set the write-in port and the write-out port, write the obtained climate data set and vegetation growth data set into the time series database for storage in the order of time stamp. 4.The garden landscape design method based on virtual reality technology according to claim 1, characterized in that: The S4 includes S41. S41, based on the vegetation health index, the vegetation health threshold F1 is initially set and compared with the obtained vegetation health coefficient Hv(t) for preliminary evaluation, and the health status of the vegetation in the future prediction stage is analyzed, and the specific evaluation content is as follows. When the vegetation health coefficient Hv(t) is greater than or equal to the vegetation health threshold F1, it indicates that the health status of the current vegetation in the future prediction stage is normal, and the vegetation design of the wetland garden does not need to be adjusted. When the vegetation health coefficient Hv(t) is less than the vegetation health threshold F1, it indicates that the health status of the current vegetation in the future prediction stage is abnormal, and the vegetation design of the wetland garden needs to be adjusted. 5.The garden landscape design method based on virtual reality technology according to claim 4, characterized in that: The S5 includes S51, S52 and S53. S51, when the preliminary comparison and evaluation identifies that the health status in the future prediction stage is abnormal, the adaptability coefficient Av(t) of each vegetation is calculated and output through the comprehensive vegetation adaptability algorithm model. The adaptability coefficient Av(t) of each vegetation is calculated and output through the following comprehensive vegetation adaptability algorithm model. ； wherein Av i (t) represents the adaptability coefficient of the ith vegetation at time t, Tmax and Tmin represent the upper and lower limits of the vegetation temperature tolerance, respectively. 6.The garden landscape design method based on virtual reality technology according to claim 5, characterized in that: S52, based on the adaptability coefficient Av(t) of each vegetation, the adaptability of the overall vegetation community of the wetland garden is calculated, and the average environmental adaptability value Amean(t) is obtained by averaging calculation. The average environmental adaptability value Amean(t) is calculated and output through the following algorithm formula. ； In the formula, N represents the total number of vegetation samples in the wetland garden.

Images