Urban residential area plant configuration mode optimization verification method and system based on GPR

Abstract

The invention relates to the field of urban residential planning, and discloses a GPR-based urban residential area plant configuration mode optimization verification method and system, and the method comprises the following steps: building a relation model between plant configuration and environmental factors through a GPR (Gaussian process regression) model, and the mathematical expression of the model is f (x)-GP (u (x), k (x, x '), f (x) is a predicted value of plant configuration, u (x) is a mean value function, k (x, x ') is a covariance function, the environmental factors comprise soil types, illumination conditions, climate data and other ecological factors, a Bayesian optimization algorithm is utilized to carry out parameter optimization on the plant configuration, an objective function of an optimization process is expressed as argmaxx (u (x) + beta sigma (x)), sigma (x) is uncertainty of a model, beta is a regulatory factor, and k (x, x') is a mean value function. The system comprises a data acquisition module, a model establishment module, an optimization module and a verification module which are connected with one another through data interfaces.

Description

Technical Field

[0001] The invention relates to the field of urban residential planning, and in particular to a method and system for optimizing and verifying plant configuration patterns in urban residential areas based on GPR. Background Art

[0002] With the acceleration of urbanization, the greening and plant configuration of urban residential areas are facing increasingly severe challenges. The complexity and diversity of the urban environment require that plant configuration not only consider aesthetics, but also meet the multiple needs of ecology, environment and residents' lives. Therefore, how to scientifically and reasonably configure plants has become an important topic in urban planning and landscape design.

[0003] Traditional plant configuration methods mostly rely on experience and intuition, lacking systematic and scientific basis. This leads to poor plant configuration results, serious waste of resources, and may even cause problems such as poor plant growth and ecological imbalance. In recent years, the development of machine learning and data analysis technology has provided new ideas for plant configuration. Gaussian process regression (GPR), as a powerful non-parametric Bayesian regression model, can effectively process complex environmental data and model the relationship between plant growth and environmental factors.

[0004] The advantage of Gaussian process regression is that it can provide uncertainty assessment of predictions, which is suitable for processing environmental data with high uncertainty. In the optimization of plant configuration patterns, GPR can reveal the growth potential of different plant configuration schemes under specific environmental conditions by learning historical data, thereby providing a scientific basis for decision makers. At the same time, GPR's dynamic update capability enables it to adapt to environmental changes and provide support for the continuous optimization of plant configuration.

[0005] In the existing technology, there is still a lack of plant configuration optimization systems that integrate GPR algorithms and real-time data collection. Using advanced sensor technology and machine learning algorithms, a GPR-based plant configuration pattern optimization verification system has been developed, which can monitor environmental factors in real time, dynamically adjust plant configuration plans, and improve plant growth effects. It has important application value and market prospects.

[0006] Therefore, the development of a GPR-based urban residential plant configuration pattern optimization verification method and system can effectively solve the deficiencies in the existing plant configuration and provide an intelligent and scientific solution for urban greening management, which has important research significance and practical application value. Summary of the invention

[0007] The purpose of the present invention is to solve the shortcomings of the prior art and provide a method and system for optimizing and verifying plant configuration patterns in urban residential areas based on GPR.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] The optimization and verification method of plant configuration pattern in urban residential areas based on GPR includes the following steps:

[0010] The relationship model between plant configuration and environmental factors is established through Gaussian process regression model (GPR), and the mathematical expression of the model is: f(x)~GP(u(x),k(x,x'))

[0011] Where; f(x) is the predicted value of plant configuration, u(x) is the mean function, and k(x,x') is the covariance function.

[0012] Preferably, the environmental factors include soil type, light conditions, climate data and other ecological factors.

[0013] First, the Bayesian optimization algorithm is used to optimize the parameters of plant configuration. The objective function of the optimization process is expressed as: argmax x (u(x)+βσ(x))

[0014] Among them, σ(x) is the uncertainty of the model and β is the adjustment factor.

[0015] Preferably, the system includes a data acquisition module, a model building module, an optimization module and a verification module, and the modules are interconnected via a data interface.

[0016] Preferably, the data acquisition module is used to obtain real-time environmental factor data related to plant growth, including soil properties, climate conditions and light intensity, and the data set is represented as:

[0017] Among them, x i is the environmental factor, y i are the corresponding plant growth indicators.

[0018] Preferably, the model building module uses a machine learning algorithm to implement Gaussian process regression and has a dynamic update function that can automatically adjust model parameters according to new data.

[0019] Preferably, the optimization module uses an evolutionary algorithm or a particle swarm optimization algorithm to perform global optimization of plant configuration, and the update formula of the algorithm is:

[0020] v i (t+1) =w·v i (t) +c1·r1·(pbest i -x i (t) )+c2·r2·(gbest-xi (t) )

[0021] Among them, v is the speed, pbest is the individual best position, and gbest is the global best position.

[0022] The verification module compares the prediction accuracy of the model with the actual plant growth data and uses the mean square error (MSE) to evaluate the prediction accuracy of the model. The calculation formula is:

[0023]

[0024] Among them, yi is the actual observed value, is the predicted value.

[0025] Preferably, the system includes providing a user-friendly interface, allowing the user to intuitively view the optimization results of plant configuration and the influence of its environmental factors.

[0026] Compared with the prior art, the GPR-based urban residential area plant configuration pattern optimization verification method and system provided by the present invention have the following beneficial effects:

[0027] (1) The Gaussian process regression (GPR)-based plant configuration optimization system provided by this patent can provide a scientific basis for plant configuration in urban residential areas through the analysis and modeling of historical data, helping planners make more reasonable decisions;

[0028] (2) Real-time data monitoring: The system integrates a variety of sensors that can collect and monitor environmental factors (such as soil moisture, temperature, and light intensity) in real time to ensure the timeliness and accuracy of data and provide better environmental conditions for plant growth;

[0029] (3) Dynamic optimization capability: Through the dynamic update function of GPR, the system can automatically adjust model parameters and plant configuration schemes according to new environmental data, adapt to changes in the urban environment, and ensure the sustainability and effectiveness of plant growth;

[0030] (4) Reduce resource waste: This system reduces unnecessary plant resource input and maintenance costs by optimizing plant configuration plans, improves resource utilization efficiency of urban greening, and promotes sustainable development;

[0031] (5) Improve plant growth effects: Through scientific plant configuration and optimization plans, the growth potential and health level of plants can be effectively improved, improving the urban ecological environment and the quality of life of residents;

[0032] (6) Enhanced ecological adaptability: This system can provide personalized plant configuration solutions based on specific urban environmental needs and plant growth characteristics, promoting ecological diversity and ecosystem stability;

[0033] (7) User-friendly interface: The system is designed with a good user experience, facilitating user interaction and visual operations, making it easy for non-professional users to use and promoting the concept of intelligent urban management. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a schematic diagram of the process structure of the GPR-based urban residential area plant configuration pattern optimization verification method and system of the present invention. DETAILED DESCRIPTION

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0037] like Figure 1 As shown, the urban residential area plant configuration pattern optimization verification method based on GPR provided by the embodiment of the present invention includes the following steps:

[0038] The relationship model between plant configuration and environmental factors is established through the Gaussian process regression model (GPR). The mathematical expression of the model is: f(x)~GP(u(x),k(x,x'))

[0039] Where; f(x) is the predicted value of plant configuration, u(x) is the mean function, and k(x,x') is the covariance function.

[0040] In one embodiment provided by the present invention, the environmental factors include soil type, light conditions, climate data and other ecological factors.

[0041] The Bayesian optimization algorithm is used to optimize the parameters of plant configuration. The objective function of the optimization process is expressed as: argmax x (u(x)+βσ(x))

[0042] Among them, σ(x) is the uncertainty of the model and β is the adjustment factor.

[0043] The system includes a data acquisition module, a model building module, an optimization module and a verification module, and the modules are interconnected through data interfaces.

[0044] In another embodiment provided by the present invention, the data acquisition module is used to obtain environmental factor data related to plant growth in real time, including soil characteristics, climate conditions and light intensity, and the data set is represented as:

[0045]

[0046] Among them, xi is the environmental factor and yi is the corresponding plant growth index.

[0047] The model building module uses machine learning algorithms to implement Gaussian process regression and has a dynamic update function that can automatically adjust model parameters based on new data.

[0048] The optimization module uses evolutionary algorithm or particle swarm optimization algorithm to perform global optimization of plant configuration. The update formula of the algorithm is:

[0049] v i (t+1) =w·v i (t) +c1·r1·(pbest i -x i (t) )+c2·r2·(gbest-x i (t) )

[0050] Among them, v is the speed, pbest is the individual best position, and gbest is the global best position.

[0051] The verification module compares the model with the actual plant growth data and uses the mean square error (MSE) to evaluate the prediction accuracy of the model. The calculation formula is:

[0052]

[0053] Among them, yi is the actual observed value, is the predicted value.

[0054] The system includes providing a user-friendly interface that enables users to intuitively view the optimization results of plant configuration and the influence of its environmental factors.

[0055] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A GPR-based urban residential area plant configuration pattern optimization verification method, characterized in that: The following steps are involved: The relationship model between plant configuration and environmental factors is established through Gaussian process regression model (GPR), and the mathematical expression of the model is: f(x)~GP(u(x),k(x,x')) in; f(x) is the predicted value of the plant configuration, u(x) is the mean function, and k(x,x') is the covariance function.

2. The GPR-based urban residential area plant configuration pattern optimization verification method according to claim 1 is characterized in that: The environmental factors include soil type, light conditions, climate data and other ecological factors.

3. The GPR-based urban residential area plant configuration pattern optimization verification method according to claim 1 is characterized in that: The Bayesian optimization algorithm is used to optimize the parameters of plant configuration. The objective function of the optimization process is expressed as: argmax x (u(x)+βσ(x)) Among them, σ(x) is the uncertainty of the model and β is the adjustment factor.

4. The GPR-based urban residential area plant configuration pattern optimization verification system according to claim 1 is characterized in that: The system comprises a data acquisition module, a model building module, an optimization module and a verification module, and the modules are interconnected through data interfaces.

5. According to the GPR-based urban residential area plant configuration pattern optimization verification system of claim 1, the data acquisition module is used to obtain environmental factor data related to plant growth in real time, including soil properties, climate conditions and light intensity, and the data set is represented as: in, x i is the environmental factor, y i are the corresponding plant growth indicators.

6. The GPR-based urban residential area plant configuration pattern optimization verification system according to claim 1 is characterized in that: The model building module uses a machine learning algorithm to implement Gaussian process regression and has a dynamic update function that can automatically adjust model parameters according to new data.

7. The GPR-based urban residential area plant configuration pattern optimization verification system according to claim 1 is characterized in that: The optimization module uses an evolutionary algorithm or a particle swarm optimization algorithm to perform global optimization of plant configuration. The update formula of the algorithm is: Among them, v is the speed, pbest is the individual best position, and gbest is the global best position.

8. The GPR-based urban residential area plant configuration pattern optimization verification system according to claim 1 is characterized in that: The verification module compares the prediction accuracy of the model with the actual plant growth data and uses the mean square error (MSE) to evaluate the prediction accuracy of the model. The calculation formula is: Among them, yi is the actual observed value, is the predicted value.

9. The GPR-based urban residential area plant configuration pattern optimization verification system according to claim 1 is characterized in that: The system also includes providing a user-friendly interface that enables users to intuitively view the optimization results of plant configuration and the impact of its environmental factors.

Images