Urban air adsorption purification method based on forestry planning

Abstract

The invention provides an urban air adsorption purification method based on forestry planning, and belongs to the technical field of air purification. The urban air adsorption and purification method based on forestry planning comprises the following steps: step 1, analyzing the pollution condition of urban air to determine the type, concentration and spatial distribution condition of main pollutants; 2, garden plants with high adsorption and purification capacity are selected according to the types and concentrations of the pollutants; step 3, designing a reasonable greening layout and structure according to urban climate, wind direction, terrain and building distribution; 4, based on the spatial distribution condition of the pollution source, a reasonable garden plant planting scheme is formulated, including the planting position, density and form, so that a good purification effect is achieved; 5, the concentration of air pollutants and the growth condition of the garden plants are monitored and evaluated regularly, the planting scheme is adjusted according to the actual situation, the health and vitality of the garden plants are kept, and the efficiency and continuity of air purification are improved.

Description

Technical Field

[0001] The present application relates to the field of air purification technology, and specifically to an urban air adsorption purification method based on forestry planning. Background Art

[0002] With the rapid development of urbanization, urban air pollution is becoming increasingly serious, having a serious impact on residents' health and environmental quality. Traditional air purification methods mainly rely on industrial equipment and pollutant treatment facilities, which are often expensive and difficult to fully solve the problem.

[0003] Plant-based air purification methods have gained increasing attention in recent years. By absorbing harmful substances from the air, purifying it, and releasing oxygen, plants offer a sustainable, economical, and eco-friendly solution for cities. However, existing plant-based air purification methods often lack scientific and systematic approaches, failing to fully consider the diversity and complexity of urban environments.

[0004] Some plant purification systems currently on the market rely primarily on simply increasing the number of plants, but lack scientific research into plant species, distribution, and synergistic effects, making it difficult to guarantee purification results. Furthermore, the lack of accurate predictions of the distribution and changes in urban pollution sources makes it difficult to achieve optimal plant selection and layout.

[0005] Therefore, this application provides an urban air adsorption purification method based on forestry planning. By fully considering the urban environment, pollution sources, plant characteristics and data analysis, it provides a scientific, systematic and sustainable air purification solution, aiming to overcome the shortcomings of existing technologies and provide a more efficient, intelligent and comprehensive urban air purification method. Summary of the Invention

[0006] In order to overcome a series of defects in the prior art, the purpose of this patent is to provide an urban air adsorption purification method based on forestry planning to address the above problems, including the following steps: Step 1: Analyze the pollution status of urban air to determine the types, concentrations and spatial distribution of major pollutants; Step 2: Select garden plants with strong adsorption and purification capabilities based on the type and concentration of pollutants; Step 3: Design a reasonable greening layout and structure based on the city’s climate, wind direction, topography, and building distribution; Step 4: Based on the spatial distribution of pollution sources, formulate a reasonable planting plan for garden plants, including planting location, density and form, to achieve good purification effect; Step 5: Regularly monitor and evaluate the concentration of air pollutants and the growth conditions of garden plants, adjust the planting plan according to actual conditions, maintain the health and vitality of garden plants, and improve the efficiency and sustainability of air purification.

[0007] Furthermore, step 1 includes the following steps: Obtain pollutant concentrations, meteorological parameters, and traffic flow data from various monitoring points, and use satellite remote sensing data as input for spatial data on pollutant distribution; Preprocess the collected data to improve its quality and usability; Conduct exploratory analysis on the pre-processed data to understand the basic characteristics and distribution of the data, as well as the main influencing factors and problems of pollutants; Based on the results of data analysis, a convolutional neural network was selected as the neural network model, with pollutant concentration, meteorological parameters, traffic flow, time series, and spatial coordinates as input variables, and spatial data of pollutant distribution as output variables to construct a prediction model for pollutant concentration and distribution; Use part of the data as a training set to train the convolutional neural network model and adjust the model's parameters and structure to improve the model's fitting and generalization capabilities; Use another part of the data as a test set to evaluate the convolutional neural network model; A convolutional neural network model is used to predict the concentration and distribution of pollutants over a period of time in the future, and a heat map of the prediction results is generated to facilitate air quality monitoring, early warning, and management.

[0008] Furthermore, the specific structure of the prediction model for pollutant concentration and distribution includes: Input layer: Input data of size 256x256x8, including three bands of pollutant concentration, meteorological parameters, traffic flow, time series, spatial coordinates and remote sensing images, is normalized to the range of [-1,1]; Convolutional layer 1: Use 32 5x5 convolution kernels with a stride of 1 and the same padding to perform convolution on the input data and output a feature map of size 256x256x32; Activation layer 1: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 1, and the output size remains unchanged; Pooling layer 1: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 1 and output a feature map of size 128x128x32; Convolutional layer 2: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 1, outputting a feature map of size 128x128x64; Activation layer 2: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 2, and the output size remains unchanged; Pooling layer 2: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 2 and output a feature map of size 64x64x64; Convolutional layer 3: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 2, outputting a feature map of size 64x64x128; Activation layer 3: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 3, and the output size remains unchanged; Pooling layer 3: Use average pooling type, size 2x2, stride 2, downsample the output of activation layer 3, and output a feature map of size 32x32x128; Skip connection: concatenate the outputs of pooling layer 1, pooling layer 2, and pooling layer 3 to obtain a feature map with an output size of 32x32x224; Global average pooling layer: performs global average pooling on the output of the skip connection to obtain a feature vector with an output size of 224; Fully connected layer: uses one neuron to multiply the output of the global average pooling layer by a weight matrix, and then adds a bias vector to obtain a feature vector with an output size of 1; Activation layer: Use the Sigmoid function as the activation function to perform a nonlinear transformation on the output of the fully connected layer. The output size remains unchanged and is used as the final output of the model.

[0009] Furthermore, step 2 includes the following steps: Consider the plant's growth environment, type, characteristics, and resistance to and resilience to pollutants. Select plants that are suitable for the local climate, soil, and water conditions to ensure their healthy growth and adsorption and purification effects. Also, try to choose plants with a high leaf area index and a long growing season to increase their adsorption area and duration for pollutants. Consider the synergistic effect of plants with other plants, and choose plant combinations that can complement each other and enhance adsorption and purification capabilities to increase the efficiency of air quality improvement.

[0010] Further, the selection of garden plants specifically includes the following steps: Define objectives and constraints: Based on the pollution status of urban air, maximize the plant's ability to adsorb and purify major pollutants as the objective function, and determine the plant's planting location, density, and form as the constraints; Generate candidate solutions: Select plants with strong adsorption and purification capabilities, and generate plant combinations based on the synergistic effects of plants; Evaluate candidate solutions: Evaluate and score each candidate solution based on the objective function and constraints; Select the optimal solution: Based on the evaluation results, one or more optimal solutions are selected from the candidate solutions as the result of plant selection.

[0011] Furthermore, step 3 includes the following steps: Collect and analyze the city's topography, climate, wind direction, and building distribution to understand the city's natural characteristics, environmental issues, greening needs, and development potential; Based on the data analysis results, determine the goals and indicators of urban greening, including green coverage rate, greening level, greening form and greening effect; According to greening goals and indicators, design a reasonable greening layout and structure, including green space system, green space classification, green space distribution and green space combination; Based on the distribution and characteristics of air pollution, and utilizing the principles and methods of urban planning and landscape design, combined with the city's topography, climate, wind direction, and building distribution, optimize the layout and structure of green spaces to increase green coverage, increase greening levels, optimize greening forms, and enhance greening effects; Evaluate and optimize greening layout and structural plans to ensure the scientific nature and feasibility of the plans.

[0012] Furthermore, step 4 includes the following steps: Analyze the type, location, intensity, and emission characteristics of pollution sources, and assess the extent and scope of their impact on air quality; Based on the garden plants selected in step 2 and the requirements of their growth environment, design reasonable planting location, density and form.

[0013] Furthermore, step 5 includes the following steps: Select appropriate monitoring equipment and monitoring indicators, and determine the monitoring frequency and time according to the types and characteristics of garden plants; Install or use monitoring equipment at different parts and locations of garden plants, dynamically record monitoring data, and upload the data to a data management platform for data analysis and visualization; Based on the results of data analysis, evaluate the growth status of garden plants and the air purification effect, and determine whether the planting plan needs to be adjusted; According to the content of the adjusted planting plan, take corresponding management measures to maintain the health and vitality of garden plants and improve the efficiency and sustainability of air purification.

[0014] Compared with the prior art, this application has at least the following technical effects or advantages.

[0015] This application uses advanced technologies such as satellite remote sensing and neural network models to predict the distribution of urban air pollution, and adopts a data-driven approach to develop personalized landscaping plans based on the types and concentrations of pollutants and the absorption capacity of different vegetation. It optimizes green space selection, layout, plant selection, etc., which can effectively purify urban air and improve environmental quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of an urban air adsorption purification method based on forestry planning disclosed in an embodiment of this application.

[0017] Figure 2 This is a structural diagram of the prediction model for pollutant concentration and distribution in this application. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Throughout the drawings, identical or similar reference numerals represent identical or similar elements or elements having identical or similar functions. The described embodiments are only some, not all, of the embodiments of the present invention.

[0019] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0020] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0021] Reference Figure 1 , a method for urban air adsorption purification based on forestry planning, comprising the following steps: Step 1: Analyze the pollution status of urban air to determine the types, concentrations and spatial distribution of major pollutants; Step 2: Select garden plants with strong adsorption and purification capabilities based on the type and concentration of pollutants; Step 3: Design a reasonable greening layout and structure based on the city’s climate, wind direction, topography, and building distribution; Step 4: Based on the spatial distribution of pollution sources, formulate a reasonable planting plan for garden plants, including planting location, density and form, to achieve good purification effect; Step 5: Regularly monitor and evaluate the concentration of air pollutants and the growth conditions of garden plants, adjust the planting plan according to actual conditions, maintain the health and vitality of garden plants, and improve the efficiency and sustainability of air purification.

[0022] In the present embodiment, step 1 needs to use modern air monitoring technology to obtain detailed urban air quality data, and by analyzing the types, concentrations and spatial distribution of major pollutants, a comprehensive urban air quality map is formulated, including the monitoring and analysis of key pollutants such as particulate matter, nitrogen oxides, and volatile organic compounds. Step 2 is based on the analysis results of step 1, and selects garden plants that have good adsorption and purification capabilities for specific pollutants. For example, some plants can effectively adsorb particulate matter, while other plants may have a better adsorption capacity for nitrogen oxides. Consider the adsorption efficiency, growth rate and adaptability of plants to ensure that they can grow healthily and maximize their benefits in the urban environment. Step 3 comprehensively considers factors such as urban climate, wind direction, topography and building distribution to design the most suitable garden structure and layout. For example, under the influence of wind direction, the position of the adsorption plants is reasonably set to maximize their adsorption capacity and ensure that air flow is promoted to the maximum extent. Based on the spatial distribution of pollution sources determined in Step 1, Step 4 develops a planting plan for landscape plants, determining the location, density, and form of plant planting in each area to ensure optimal air purification in key areas. This includes forming adsorption zones or creating green barriers to effectively isolate and mitigate airborne pollutants. Step 5 establishes a regular monitoring system to track the concentration of air pollutants and the growth status of landscape plants. Through real-time data, the landscape plant planting plan is adjusted in a timely manner to adapt to changes in the urban environment and maintain the health and vitality of the plants, helping to improve air purification efficiency and maintain the sustainability of the system.

[0023] Furthermore, step 1 includes the following steps: Obtain pollutant concentrations, meteorological parameters, and traffic flow data from various monitoring points, and use satellite remote sensing data as input for spatial data on pollutant distribution; Preprocess the collected data to improve its quality and usability; Conduct exploratory analysis on the pre-processed data to understand the basic characteristics and distribution of the data, as well as the main influencing factors and problems of pollutants; Based on the results of data analysis, a convolutional neural network was selected as the neural network model, with pollutant concentration, meteorological parameters, traffic flow, time series, and spatial coordinates as input variables, and spatial data of pollutant distribution as output variables to construct a prediction model for pollutant concentration and distribution; Use part of the data as a training set to train the convolutional neural network model and adjust the model's parameters and structure to improve the model's fitting and generalization capabilities; Use another part of the data as a test set to evaluate the convolutional neural network model; A convolutional neural network model is used to predict the concentration and distribution of pollutants over a period of time in the future, and a heat map of the prediction results is generated to facilitate air quality monitoring, early warning, and management.

[0024] This example, through a series of meticulous and systematic steps, provides a scientific basis and effective tools for urban air purification methods, enabling them to continuously adapt and optimize in the face of ever-changing urban environments. By integrating advanced data analysis techniques and neural network models, this approach is expected to improve prediction accuracy and real-time performance, while providing a cleaner and healthier living environment for urban residents.

[0025] like Figure 2 As shown, further, the specific structure of the prediction model for pollutant concentration and distribution includes: Input layer: Input data of size 256x256x8, including three bands of pollutant concentration, meteorological parameters, traffic flow, time series, spatial coordinates and remote sensing images, is normalized to the range of [-1,1]; Convolutional layer 1: Use 32 5x5 convolution kernels with a stride of 1 and the same padding to perform convolution on the input data and output a feature map of size 256x256x32; Activation layer 1: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 1, and the output size remains unchanged; Pooling layer 1: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 1 and output a feature map of size 128x128x32; Convolutional layer 2: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 1, outputting a feature map of size 128x128x64; Activation layer 2: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 2, and the output size remains unchanged; Pooling layer 2: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 2 and output a feature map of size 64x64x64; Convolutional layer 3: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 2, outputting a feature map of size 64x64x128; Activation layer 3: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 3, and the output size remains unchanged; Pooling layer 3: Use average pooling type, size 2x2, stride 2, downsample the output of activation layer 3, and output a feature map of size 32x32x128; Skip connection: concatenate the outputs of pooling layer 1, pooling layer 2, and pooling layer 3 to obtain a feature map with an output size of 32x32x224; Global average pooling layer: performs global average pooling on the output of the skip connection to obtain a feature vector with an output size of 224; Fully connected layer: uses one neuron to multiply the output of the global average pooling layer by a weight matrix, and then adds a bias vector to obtain a feature vector with an output size of 1; Activation layer: Use the Sigmoid function as the activation function to perform a nonlinear transformation on the output of the fully connected layer. The output size remains unchanged and is used as the final output of the model.

[0026] To evaluate the model's classification ability and accuracy, we used metrics such as confusion matrix, precision, recall, and F1 score. The confusion matrix shows the correspondence between the model's predicted and actual categories, as well as the number of correct and incorrect predictions. Precision refers to the proportion of samples predicted by the model to be of a certain category that actually belong to that category. Recall refers to the proportion of samples predicted by the model to be of that category that actually belong to that category. The F1 score is the harmonic mean of precision and recall, and provides a comprehensive measure of the model's classification performance. Generally speaking, higher values ​​of these metrics indicate better classification ability and accuracy. We use the Air Quality Index (AQI) to categorize air quality into four categories: excellent (0-50), good (51-100), lightly polluted (101-150), and moderately polluted (151-200). Our test set contains 100 samples, each of which has a model output value and an actual observation value. The model output value is converted into a discrete category. The model output value between 0-0.25 is classified as the excellent category, the model output value between 0.25-0.5 is classified as the good category, and so on. Then, we use the confusion matrix to show the correspondence between the model's predicted categories and the actual categories, as well as the number of correct predictions and incorrect predictions of the model, as shown in Table 1: Table 1 Actual / Forecast excellent good Light pollution Moderate pollution excellent 23 2 0 0 good 1 22 2 0 Light pollution 0 1 23 1 Moderate pollution 0 0 1 24 Indicators such as precision, recall, and F1 score are used to further quantify the classification ability and accuracy of the model, as shown in Table 2.

[0027] Table 2 category Accuracy Recall F1 score excellent 0.96 0.92 0.94 good 0.88 0.88 0.88 Light pollution 0.88 0.92 0.90 Moderate pollution 0.96 0.96 0.96 From Table 1 and Table 2, we can see that the confusion matrix and classification evaluation indicators have good classification ability and accuracy in all categories, without obvious wrong predictions, and the values ​​of each indicator are relatively high, indicating that the classification performance of the model is relatively good.

[0028] Furthermore, step 2 includes the following steps: Consider the plant's growth environment, type, characteristics, and resistance to and resilience to pollutants. Select plants that are suitable for the local climate, soil, and water conditions to ensure their healthy growth and adsorption and purification effects. Also, try to choose plants with a high leaf area index and a long growing season to increase their adsorption area and duration for pollutants. Consider the synergistic effect of plants with other plants, and choose plant combinations that can complement each other and enhance adsorption and purification capabilities to increase the efficiency of air quality improvement.

[0029] This example constructs a diverse garden plant community by comprehensively considering the plant's ecological characteristics, growth environment, resistance, resilience, and synergistic effects, maximizing its benefits in urban air purification. This not only helps improve air quality but also provides a pleasant and healthy living environment for urban residents.

[0030] Further, the selection of garden plants specifically includes the following steps: Define objectives and constraints: Based on the pollution status of urban air, maximize the plant's ability to adsorb and purify major pollutants as the objective function, and determine the plant's planting location, density, and form as the constraints; Generate candidate solutions: Select plants with strong adsorption and purification capabilities, and generate plant combinations based on the synergistic effects of plants; Evaluate candidate solutions: Evaluate and score each candidate solution based on the objective function and constraints; Select the optimal solution: Based on the evaluation results, one or more optimal solutions are selected from the candidate solutions as the result of plant selection.

[0031] This embodiment can ensure that the selected garden plant scheme achieves the best air purification effect in actual implementation through clear goals, reasonable generation of candidate solutions, a comprehensive evaluation process and a scientific selection mechanism.

[0032] Furthermore, the objective function and constraints are determined by considering the types of pollutants, vegetation types, pollution monitoring data, and plant resource database. The selection process of garden plants is expressed as follows: maxf(x) x stg i (x)≤0, i=1,2,...,m h j (x)=0,j=1,2,...,n Where x represents the selection scheme of candidate plants or plant combinations, f(x) represents the adsorption and purification capacity of plants, g i (x) and h j(x) represents some scalar function, which represents the constraint condition.

[0033] The goal of the optimization problem in this embodiment is to find a plant selection scheme x such that the objective function f(x) reaches its maximum value while satisfying a series of constraints g i (x) and h j Solving this optimization problem will provide the best garden plant selection plan for urban air purification, thereby maximizing air quality.

[0034] Furthermore, step 3 includes the following steps: Collect and analyze the city's topography, climate, wind direction, and building distribution to understand the city's natural characteristics, environmental issues, greening needs, and development potential; Based on the data analysis results, determine the goals and indicators of urban greening, including green coverage rate, greening level, greening form and greening effect; According to greening goals and indicators, design a reasonable greening layout and structure, including green space system, green space classification, green space distribution and green space combination; Based on the distribution and characteristics of air pollution, and utilizing the principles and methods of urban planning and landscape design, combined with the city's topography, climate, wind direction, and building distribution, optimize the layout and structure of green spaces to increase green coverage, increase greening levels, optimize greening forms, and enhance greening effects; Evaluate and optimize greening layout and structural plans to ensure the scientific nature and feasibility of the plans.

[0035] This example uses a comprehensive urban analysis, taking into account natural characteristics such as topography, climate, wind direction, and building distribution. Integrating the data analysis results, a scientific and rational urban greening plan is developed. This plan aims to clarify the goals and indicators of urban greening, including green coverage, greening levels, greening forms, and greening effects, to meet the city's environmental improvement needs. A rational greening layout and structure is designed, including green space systems, green space classifications, green space distribution, and green space combinations, to maximize the city's green coverage rate and enhance the greening effect through optimized layout and structure. During this process, special attention is paid to the distribution and characteristics of air pollution. Incorporating urban planning and landscape design principles, green space layout is optimized through rational plant selection and layout to address air quality issues. Ultimately, through the evaluation and optimization of the greening layout and structure plan, the scientific and feasible nature of the plan is ensured. This series of steps aims to make urban greening more in line with nature, adapt to urban needs, and create a more livable environment for urban residents.

[0036] Furthermore, step 4 includes the following steps: Analyze the type, location, intensity, and emission characteristics of pollution sources, and assess the extent and scope of their impact on air quality; Based on the garden plants selected in step 2 and the requirements of their growth environment, design reasonable planting location, density and form.

[0037] By designing and adjusting step 4 in this embodiment, the green space system will more effectively cope with the impact of pollution sources and improve the overall level of urban air quality.

[0038] Furthermore, step 5 includes the following steps: Select appropriate monitoring equipment and monitoring indicators, and determine the monitoring frequency and time according to the types and characteristics of garden plants; Install or use monitoring equipment at different parts and locations of garden plants, dynamically record monitoring data, and upload the data to a data management platform for data analysis and visualization; Based on the results of data analysis, evaluate the growth status of garden plants and the air purification effect, and determine whether the planting plan needs to be adjusted; According to the content of the adjusted planting plan, take corresponding management measures to maintain the health and vitality of garden plants and improve the efficiency and sustainability of air purification.

[0039] In this embodiment, through regular monitoring, evaluation and adjustment, not only can problems be discovered in a timely manner and corresponding improvements be made, but the configuration of garden plants can also be optimized and the overall efficiency of the air purification system can be improved. This process is a key step in continuously improving and optimizing urban air quality.

Claims

1. A method for urban air adsorption purification based on forestry planning, characterized in that: The following steps are involved: Step 1: Analyze the pollution status of urban air to determine the types, concentrations and spatial distribution of major pollutants; Step 2: Select garden plants with strong adsorption and purification capabilities based on the type and concentration of pollutants; Step 3: Design a reasonable greening layout and structure based on the city’s climate, wind direction, topography, and building distribution; Step 4: Based on the spatial distribution of pollution sources, formulate a reasonable planting plan for garden plants, including planting location, density and form, to achieve good purification effect; Step 5: Regularly monitor and evaluate the concentration of air pollutants and the growth conditions of garden plants, adjust the planting plan according to actual conditions, maintain the health and vitality of garden plants, and improve the efficiency and sustainability of air purification.

2. The urban air adsorption purification method based on forestry planning according to claim 1 is characterized in that: Step 1 includes the following steps: Obtain pollutant concentrations, meteorological parameters, and traffic flow data from various monitoring points, and use satellite remote sensing data as input for spatial data on pollutant distribution; Preprocess the collected data to improve its quality and usability; Conduct exploratory analysis on the pre-processed data to understand the basic characteristics and distribution of the data, as well as the main influencing factors and problems of pollutants; Based on the results of data analysis, a convolutional neural network was selected as the neural network model, with pollutant concentration, meteorological parameters, traffic flow, time series, and spatial coordinates as input variables, and spatial data of pollutant distribution as output variables to construct a prediction model for pollutant concentration and distribution; Use part of the data as a training set to train the convolutional neural network model and adjust the model's parameters and structure to improve the model's fitting and generalization capabilities; Use another part of the data as a test set to evaluate the convolutional neural network model; A convolutional neural network model is used to predict the concentration and distribution of pollutants over a period of time in the future, and a heat map of the prediction results is generated to facilitate air quality monitoring, early warning, and management.

3. The urban air adsorption purification method based on forestry planning according to claim 2 is characterized in that: The specific structure of the prediction model for pollutant concentration and distribution includes: Input layer: Input data of size 256x256x8, including three bands of pollutant concentration, meteorological parameters, traffic flow, time series, spatial coordinates and remote sensing images, is normalized to the range of [-1,1]; Convolutional layer 1: Use 32 5x5 convolution kernels with a stride of 1 and the same padding to perform convolution on the input data and output a feature map of size 256x256x32; Activation layer 1: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 1, and the output size remains unchanged; Pooling layer 1: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 1 and output a feature map of size 128x128x32; Convolutional layer 2: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 1, outputting a feature map of size 128x128x64; Activation layer 2: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 2, and the output size remains unchanged; Pooling layer 2: uses the average pooling type with a size of 2x2 and a stride of 2 to downsample the output of activation layer 2 and output a feature map of size 64x64x64; Convolutional layer 3: Use 64 3x3 convolution kernels with a stride of 1 and the same padding to perform convolution on the output of pooling layer 2, outputting a feature map of size 64x64x128; Activation layer 3: Use the ReLU function as the activation function to perform nonlinear transformation on the output of convolution layer 3, and the output size remains unchanged; Pooling layer 3: Use average pooling type, size 2x2, stride 2, downsample the output of activation layer 3, and output a feature map of size 32x32x128; Skip connection: concatenate the outputs of pooling layer 1, pooling layer 2, and pooling layer 3 to obtain a feature map with an output size of 32x32x224; Global average pooling layer: performs global average pooling on the output of the skip connection to obtain a feature vector with an output size of 224; Fully connected layer: uses one neuron to multiply the output of the global average pooling layer by a weight matrix, and then adds a bias vector to obtain a feature vector with an output size of 1; Activation layer: Use the Sigmoid function as the activation function to perform a nonlinear transformation on the output of the fully connected layer. The output size remains unchanged and is used as the final output of the model.

4. The urban air adsorption purification method based on forestry planning according to claim 1 is characterized in that: Step 2 includes the following steps: Consider the plant's growth environment, type, characteristics, and resistance to and resilience to pollutants. Select plants that are suitable for the local climate, soil, and water conditions to ensure their healthy growth and adsorption and purification effects. Also, try to choose plants with a high leaf area index and a long growing season to increase their adsorption area and duration for pollutants. Consider the synergistic effect of plants with other plants, and choose plant combinations that can complement each other and enhance adsorption and purification capabilities to increase the efficiency of air quality improvement.

5. The urban air adsorption purification method based on forestry planning according to claim 4 is characterized in that: The selection of garden plants specifically includes the following steps: Define objectives and constraints: Based on the pollution status of urban air, maximize the plant's ability to adsorb and purify major pollutants as the objective function, and determine the plant's planting location, density, and form as the constraints; Generate candidate solutions: Select plants with strong adsorption and purification capabilities, and generate plant combinations based on the synergistic effects of plants; Evaluate candidate solutions: Evaluate and score each candidate solution based on the objective function and constraints; Select the optimal solution: Based on the evaluation results, one or more optimal solutions are selected from the candidate solutions as the result of plant selection.

6. The urban air adsorption purification method based on forestry planning according to claim 1 is characterized in that: Step 3 includes the following steps: Collect and analyze the city's topography, climate, wind direction, and building distribution to understand the city's natural characteristics, environmental issues, greening needs, and development potential; Based on the data analysis results, determine the goals and indicators of urban greening, including green coverage rate, greening level, greening form and greening effect; According to greening goals and indicators, design a reasonable greening layout and structure, including green space system, green space classification, green space distribution and green space combination; Based on the distribution and characteristics of air pollution, and utilizing the principles and methods of urban planning and landscape design, combined with the city's topography, climate, wind direction, and building distribution, optimize the layout and structure of green spaces to increase green coverage, increase greening levels, optimize greening forms, and enhance greening effects; Evaluate and optimize greening layout and structural plans to ensure the scientific nature and feasibility of the plans.

7. The urban air adsorption purification method based on forestry planning according to claim 1 is characterized in that: Step 4 includes the following steps: Analyze the type, location, intensity, and emission characteristics of pollution sources, and assess the extent and scope of their impact on air quality; Based on the garden plants selected in step 2 and the requirements of their growth environment, design reasonable planting location, density and form.

8. The urban air adsorption purification method based on forestry planning according to claim 1 is characterized in that: Step 5 includes the following steps: Select appropriate monitoring equipment and monitoring indicators, and determine the monitoring frequency and time according to the types and characteristics of garden plants; Install or use monitoring equipment at different parts and locations of garden plants, dynamically record monitoring data, and upload the data to a data management platform for data analysis and visualization; Based on the results of data analysis, evaluate the growth status of garden plants and the air purification effect, and determine whether the planting plan needs to be adjusted; According to the content of the adjusted planting plan, take corresponding management measures to maintain the health and vitality of garden plants and improve the efficiency and sustainability of air purification.

Images