Urban green land plant growth state monitoring and analyzing system and method

Abstract

The invention discloses an urban green land plant growth state monitoring and analyzing system and method, relates to the technical field of big data analysis, and can accurately track the health condition of plants in each sub-region and improve the scientificity and effectiveness of urban green land management through detailed region division and coordinate marking. By means of the plant growth simulation model and the ideal environment growth model which are constructed through the neural network, the system can dynamically predict the plant growth state and conduct personalized management on plant growth conditions in different areas. Various collection means such as environmental factors and remote sensing data are integrated, the growth state of urban green land plants is comprehensively monitored, and the limitation of a traditional method is overcome. By setting the state abnormality threshold and combining the growth deviation trend chart, the system can realize a real-time early warning mechanism, quickly identify potential growth abnormality and ensure that problems are found and solved in time, so that the monitoring error of the remote sensing technology is reduced, and the management efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and in particular to a system and method for monitoring and analyzing the growth status of urban green space plants. Background Art

[0002] Urban green space plants are of great significance in improving air quality, reducing urban temperature, improving soil and water conservation, etc. They can effectively absorb carbon dioxide, release oxygen, and improve the living environment of residents. In addition, green space plants provide habitats, support biodiversity, and enhance the stability of the ecosystem. At the same time, these plants can provide beautiful landscapes, improve the aesthetics of the city, and enhance the mental health and quality of life of residents. In addition, green space also provides urban residents with places for leisure, exercise and socializing, enhances community cohesion, and promotes the sustainable development of the city.

[0003] Urban green space plants are widely distributed in cities. However, existing remote sensing monitoring technologies usually rely on a single data collection method, resulting in a lack of diversity and comprehensiveness in monitoring results. Since it is impossible to capture the growth characteristics of multiple plants and changes in environmental factors at the same time, a single monitoring data often cannot fully reflect the health status of plants. In this way, the limitations of a single data source make it difficult to accurately assess the growth status of urban green space plants, and there is a lack of personalized analysis and management solutions for plant health in different regions. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for monitoring and analyzing the growth status of urban green space plants, so as to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for monitoring and analyzing the growth status of urban green space plants, the method comprising the following steps: Step S1, dividing the area according to the distribution characteristics of urban green space plants, and establishing corresponding coordinate marks based on the divided areas; Step S1-1, dividing the urban green space into multiple sub-areas according to the location distribution characteristics of urban green space plants, combined with plant density and environmental conditions; Step S1-2: according to the divided multiple sub-regions, a coordinate mark is set for each sub-region using a geographic coordinate system, a primary coordinate mark is set at the geometric center point of each sub-region, and a secondary coordinate mark is set at the boundary corner point.

[0006] Dividing urban green space into multiple sub-areas and setting coordinate markers can help accurately locate and manage the plant growth status of each area, improving the accuracy and efficiency of monitoring. By combining plant distribution characteristics, density and environmental conditions, regional analysis can be refined to facilitate dynamic tracking of growth conditions in different areas, achieve targeted management and optimization, and promote the overall health and ecological benefits of urban green space.

[0007] Step S2: comprehensively collect the growth status data of urban green space plants in each area according to the divided and marked areas, and record the plant characteristics and health status corresponding to each area; The growth status data of urban green space plants are comprehensively collected for each sub-area after division. The collected data include growth characteristic data, environmental factor data, plant health data and remote sensing data. The plant characteristic data and health status data corresponding to each sub-area are stored and recorded.

[0008] Step S3: Using the fully collected urban green space plant growth status data, a plant growth simulation model is constructed through a neural network, and an ideal environment growth model is constructed based on preset ideal environmental parameters. The plant growth simulation model is used to simulate the growth status of the corresponding collected data in each area, and key environmental factor data are collected regularly; Step S3-1, inputting growth characteristic data, environmental factor data, plant health data and remote sensing data into a neural network structure for training, and constructing a plant growth simulation model and an ideal environment growth model; Step S3-2 sets a key environmental factor data collection period Q, and obtains key environmental factor data by deploying sensors in each sub-area. The key environmental factor data includes light intensity, soil moisture, temperature, and atmospheric carbon dioxide concentration. The key environmental factor data obtained in each collection period is input into a plant growth simulation model to simulate growth; Step S3-3: Replace the set key environmental factor data with standard data under ideal environmental conditions, and input the ideal environmental growth model to simulate growth.

[0009] By inputting growth characteristic data, environmental factor data, plant health data and remote sensing data into the neural network to build a plant growth simulation model, the growth status of plants in each region can be accurately predicted.

[0010] Step S4, setting a plant remote sensing acquisition cycle, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, using remote sensing technology to monitor each area marked with coordinates according to the plant remote sensing acquisition cycle, and storing the plant remote sensing data actually collected by remote sensing technology in the remote sensing monitoring set, while storing the remote sensing data generated by the synchronized real environment plant growth model in the simulated mapping remote sensing set, and storing the remote sensing data generated by the ideal environment plant growth model in the ideal environment simulated mapping remote sensing set; Step S4-1, setting a plant remote sensing acquisition cycle T, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, wherein the remote sensing monitoring set is used to store plant remote sensing data actually collected by remote sensing technology, the simulated mapping remote sensing set is used to store plant remote sensing data mapped by a plant growth simulation model, and the ideal environment simulated mapping remote sensing set is used to store plant remote sensing data mapped by an ideal environment growth model; Step S4-2: monitor each sub-area marked with coordinates using remote sensing technology according to the plant remote sensing collection cycle; Step S4-3, store the plant remote sensing data of each sub-area collected by actual remote sensing technology into the remote sensing monitoring set, store the plant remote sensing data generated in the corresponding area in the plant growth simulation model into the simulation mapping remote sensing set, and store the plant remote sensing data generated in the corresponding area in the ideal environment growth model into the ideal environment simulation mapping remote sensing set.

[0011] By setting up plant remote sensing collection cycles and constructing remote sensing monitoring collections and simulation mapping remote sensing collections, the actual collected remote sensing data and the data generated by the model can be systematically collected and stored.

[0012] Step S5, setting the environmental monitoring threshold, obtaining the deviation value between the actual plant remote sensing data of each region and the remote sensing data generated by the plant growth simulation model, and recording it as the simulated growth deviation value; at the same time, obtaining the deviation value between the remote sensing monitoring set and the ideal environment simulation mapping remote sensing set, and recording it as the ideal environment deviation value, comparing the remote sensing data difference of the actual adjacent sub-regions with the remote sensing data difference of the synchronous corresponding region, forming a regional growth gradient value, summarizing the simulated growth deviation value and the regional growth gradient value, constructing a growth deviation trend graph and a gradient error trend graph, quantifying the influence of environmental factors on plant growth according to the ideal environment deviation value, selecting the maximum influencing factor, and performing data warning on the growth deviation trend graph in combination with the environmental monitoring threshold; Step S5-1, according to the remote sensing monitoring set, the simulated mapping remote sensing set and the ideal environment simulated mapping remote sensing set, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the plant growth simulation model, recorded as the simulated growth deviation value M, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the ideal environment growth model, recorded as the ideal environment deviation value; Step S5-2, summarizing the simulated growth deviation values ​​M of each sub-region within the plant remote sensing acquisition period T to construct a growth deviation trend graph; Step S5-3: According to the remote sensing monitoring set and the simulated mapping remote sensing set, the plant remote sensing data difference between each adjacent sub-region and the remote sensing data difference of the synchronous corresponding region in the plant growth simulation model are obtained, and the two differences are compared to form the regional growth gradient value G error , the difference calculation formula of plant remote sensing data in actual adjacent sub-areas is as follows: ; In the formula, G actual It is expressed as the difference of plant remote sensing data in actual adjacent sub-areas; R actual，i Represented as the actual plant remote sensing data value of sub-region i; R actual，o It is represented by the actual plant remote sensing data value of sub-area o; The difference calculation formula of plant remote sensing data in adjacent sub-areas in the plant growth simulation model is as follows: ; In the formula, G model It is expressed as the difference between the plant remote sensing data in the corresponding adjacent sub-areas in the plant growth simulation model; R model，i Represented as the plant remote sensing data value of sub-area i in the plant growth simulation model; R model，o It is represented by the plant remote sensing data value of sub-area o in the plant growth simulation model; Region growth gradient value G error The calculation formula is as follows: ; In the formula, G error It is expressed as the difference of plant remote sensing data between actual adjacent sub-regions and the difference of remote sensing data of synchronous corresponding regions in the plant growth simulation model; Step S5-4: Summarize the regional growth gradient values ​​J obtained within the plant remote sensing acquisition period T to construct a gradient error trend graph.

[0013] By analyzing the deviation between the remote sensing monitoring set and the simulated mapping remote sensing set, the growth status and health level of urban green space plants can be effectively evaluated; Step S5-5, according to the ideal environmental deviation value of each sub-region within the plant remote sensing acquisition period T, quantify the specific impact of actual environmental factors on plant growth, the actual environmental factors include light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration, and by comparing the growth performance under actual environmental conditions with that under ideal environmental conditions, select the environmental factor with the largest impact value as the key environmental monitoring object; Step S5-6: Compare the actual value obtained for the key environmental monitoring object with the environmental monitoring threshold: When the value actually obtained for the key environmental monitoring object is less than the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend graph is in a normal state; When the value actually obtained by the key environmental monitoring object is greater than or equal to the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend chart is normal, and an abnormal signal of the key environmental monitoring object is issued.

[0014] Step S6, set the abnormal status threshold, combine the growth deviation trend chart to warn the growth status of the monitored urban green plants, extract the maximum deviation absolute value in the gradient error trend chart, determine the corresponding area according to the maximum deviation absolute value, and conduct secondary monitoring, and judge the growth status of the urban green plants in the area according to the data of the secondary monitoring.

[0015] Step S6-1: Setting the abnormal state threshold Z max , obtain the data point value in the growth deviation trend chart, record it as the deviation value X, and combine it with the state abnormal threshold Z max To judge and warn the growth status of the monitored urban green space plants; When X<Z max When the growth state of the monitored urban green space plants is in line with the growth expectations in the plant growth simulation model, the growth state of the urban green space plants is normal; When X ≥ Z max When the monitored urban green space plant growth status does not meet the growth expectations in the plant growth simulation model, the urban green space plant growth status is abnormal, and an abnormal growth status warning is issued; Step S6-2: Gradient error trend graph, extract the maximum deviation absolute value G max , according to G max Determine the corresponding regional location and conduct secondary remote sensing monitoring of the area. Compare the data collected by the secondary monitoring with the previous monitoring data to determine whether there is an abnormality or continuous deviation in the growth status of the plant. The average value of each data point in the gradient error trend graph is calculated as follows: ; In the formula, G avg It is represented by the average value of each data point in the gradient error trend graph; N is represented by the difference in plant remote sensing data between each adjacent sub-region and the number of remote sensing data differences in the synchronous corresponding regions in the plant growth simulation model; Maximum absolute value of deviation G max The calculation formula is as follows: ; In the formula, G maxIt is expressed as the maximum absolute value of the deviation in the gradient error trend graph; G error，io It is represented by the corresponding data point values ​​of sub-area i and sub-area o in the gradient error trend graph; max represents taking the maximum value from a set of data; Extraction of G max The corresponding sub-area i and sub-area o data are obtained, and sub-area i and sub-area o are monitored twice, the minimum value of the two monitorings is taken out, and the growth status of urban green plants in the area is judged based on the minimum value combined with the NDVI judgment standard.

[0016] NDVI < 0, water bodies, soil or areas without vegetation: negative values ​​usually indicate water bodies or bare soil; 0≤NDVI<0.2, sparse vegetation: NDVI values ​​in this range usually indicate low vegetation coverage, which may be sparse vegetation such as grass or shrubs; 0.2≤NDVI<0.5, medium vegetation cover: This range indicates medium density vegetation, such as farmland or grassland; 0.5≤NDVI<0.8, high vegetation cover: NDVI values ​​in this range usually indicate high-density vegetation, such as forests or dense bushes; 0.8≤NDVI≤1, very healthy and dense vegetation: Extremely high NDVI values ​​indicate very healthy and lush vegetation conditions, usually mature forests or other dense vegetation.

[0017] By setting abnormal status thresholds and combining them with growth deviation trend charts for early warning, timely monitoring of the growth status of urban green space plants and identification of abnormalities can be achieved.

[0018] A system for monitoring and analyzing the growth status of urban green space plants, the system comprising a data acquisition module, a regional management module, a growth simulation module, a collection management module, a trend chart management module and a status assessment and early warning module; The data acquisition module is used for data information collection; the area management module is used for dividing urban green space plants according to their location distribution characteristics and constructing coordinates for marking; the growth simulation module is used for training according to the collected data input into the neural network structure to simulate the growth of urban green space plants; the collection management module is used to manage the addition and deletion of data in each collection; the trend graph management module is used to construct a trend graph corresponding to the collection framework; the status assessment and early warning module is used to judge the growth status according to the trend graph and perform early warning processing on the areas that meet specific conditions; The output end of the data acquisition module is electrically connected to the input end of the area management module; the output end of the area management module is electrically connected to the input end of the growth simulation module; the output end of the growth simulation module is electrically connected to the input end of the collection management module; the output end of the collection management module is electrically connected to the input end of the trend chart management module; the output end of the trend chart management module is electrically connected to the input end of the status assessment and early warning module.

[0019] The data acquisition module includes an environmental factor acquisition unit and a remote sensing acquisition unit; the environmental factor acquisition unit is used to collect light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration; the remote sensing acquisition unit is used to obtain plant remote sensing data of each sub-area using remote sensing technology; The area management module includes an area division unit and a coordinate marking unit; the area division unit is used to divide the area according to the location distribution of urban green space plants; the coordinate marking unit is used to mark the location of the area; The growth simulation module includes a model training unit and a simulated growth unit; the model training unit is used to input data into a neural network structure for training to construct a plant growth simulation model; the simulated growth unit is used to simulate growth according to the input parameters.

[0020] The collection management module includes an actual collection unit and a simulation collection unit; the actual collection unit is used to store the data actually collected and acquired; the simulation collection unit is used to store the data generated by the simulated growth; The trend graph management module includes a direct trend unit and an adjacent difference trend graph unit; the direct trend unit is used to construct a trend graph of the difference between actual and simulated growth; the adjacent difference trend graph unit is used to construct a trend graph based on the difference between the actual acquisition and simulated mapping of the difference between two adjacent sub-regions; The state evaluation and early warning module includes a state evaluation unit and an early warning unit; the state evaluation unit is used to evaluate the growth state according to the collected data; the early warning unit is used to perform early warning processing on the growth state of urban green space plants in areas that meet specific conditions.

[0021] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention can comprehensively monitor the growth status of urban green space plants through a variety of data collection methods, including environmental factors and remote sensing data. This comprehensive data collection method overcomes the limitations of traditional methods and makes the monitoring results more accurate and comprehensive. Through detailed regional division and coordinate marking, the system can accurately track the health status and growth characteristics of plants in each sub-region, realize scientific assessment of plant health levels, and improve the scientificity and effectiveness of urban green space management.

[0022] 2. The present invention uses a neural network to construct a plant growth simulation model, and can dynamically predict the growth status of plants by analyzing plant growth characteristics and real-time environmental data. This intelligent growth simulation method enables the system to respond promptly to plant growth conditions in different regions and provide personalized management solutions.

[0023] 3. The present invention achieves real-time early warning of plant growth status by setting abnormal state thresholds and combining growth deviation trend graphs. This early warning mechanism can quickly identify potential growth anomalies by analyzing the deviation between actual monitoring data and simulated data, and then take targeted measures. The secondary monitoring function allows the system to conduct in-depth analysis of abnormal areas to ensure timely discovery and resolution of problems, and can also reduce the errors caused by remote sensing technology in monitoring different areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a flow chart of a method for monitoring and analyzing the growth status of urban green space plants according to the present invention; Figure 2 The present invention is a schematic diagram of the structure of a system for monitoring and analyzing the growth status of urban green space plants. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1: Figure 1 As shown, the present invention provides a technical solution, a method for monitoring and analyzing the growth status of urban green space plants, and the method for monitoring and analyzing the growth status comprises the following steps: Step S1, dividing the area according to the distribution characteristics of urban green space plants, and establishing corresponding coordinate marks based on the divided areas; Step S1-1, dividing the urban green space into multiple sub-areas according to the location distribution characteristics of urban green space plants, combined with plant density and environmental conditions; Step S1-2: according to the divided multiple sub-regions, a coordinate mark is set for each sub-region using a geographic coordinate system, a primary coordinate mark is set at the geometric center point of each sub-region, and a secondary coordinate mark is set at the boundary corner point.

[0027] Step S2: comprehensively collect the growth status data of urban green space plants in each area according to the divided and marked areas, and record the plant characteristics and health status corresponding to each area; The growth status data of urban green space plants are comprehensively collected for each sub-area after division. The collected data include growth characteristic data, environmental factor data, plant health data and remote sensing data. The plant characteristic data and health status data corresponding to each sub-area are stored and recorded.

[0028] Step S3: Using the fully collected urban green space plant growth status data, a plant growth simulation model is constructed through a neural network, and an ideal environment growth model is constructed based on preset ideal environmental parameters. The plant growth simulation model is used to simulate the growth status of the corresponding collected data in each area, and key environmental factor data are collected regularly; Step S3-1, inputting growth characteristic data, environmental factor data, plant health data and remote sensing data into a neural network structure for training, and constructing a plant growth simulation model and an ideal environment growth model; Step S3-2 sets a key environmental factor data collection period Q, and obtains key environmental factor data by deploying sensors in each sub-area. The key environmental factor data includes light intensity, soil moisture, temperature, and atmospheric carbon dioxide concentration. The key environmental factor data obtained in each collection period is input into a plant growth simulation model to simulate growth; Step S3-3: Replace the set key environmental factor data with standard data under ideal environmental conditions, and input the ideal environmental growth model to simulate growth.

[0029] Step S4, setting a plant remote sensing acquisition cycle, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, using remote sensing technology to monitor each area marked with coordinates according to the plant remote sensing acquisition cycle, and storing the plant remote sensing data actually collected by remote sensing technology in the remote sensing monitoring set, while storing the remote sensing data generated by the synchronized real environment plant growth model in the simulated mapping remote sensing set, and storing the remote sensing data generated by the ideal environment plant growth model in the ideal environment simulated mapping remote sensing set; Step S4-1, setting a plant remote sensing acquisition cycle T, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, wherein the remote sensing monitoring set is used to store plant remote sensing data actually collected by remote sensing technology, the simulated mapping remote sensing set is used to store plant remote sensing data mapped by a plant growth simulation model, and the ideal environment simulated mapping remote sensing set is used to store plant remote sensing data mapped by an ideal environment growth model; Step S4-2: monitor each sub-area marked with coordinates using remote sensing technology according to the plant remote sensing collection cycle; Step S4-3, store the plant remote sensing data of each sub-area collected by actual remote sensing technology into the remote sensing monitoring set, store the plant remote sensing data generated in the corresponding area in the plant growth simulation model into the simulation mapping remote sensing set, and store the plant remote sensing data generated in the corresponding area in the ideal environment growth model into the ideal environment simulation mapping remote sensing set.

[0030] Step S5, setting the environmental monitoring threshold, obtaining the deviation value between the actual plant remote sensing data of each region and the remote sensing data generated by the plant growth simulation model, and recording it as the simulated growth deviation value; at the same time, obtaining the deviation value between the remote sensing monitoring set and the ideal environment simulation mapping remote sensing set, and recording it as the ideal environment deviation value, comparing the remote sensing data difference of the actual adjacent sub-regions with the remote sensing data difference of the synchronous corresponding region, forming a regional growth gradient value, summarizing the simulated growth deviation value and the regional growth gradient value, constructing a growth deviation trend graph and a gradient error trend graph, quantifying the influence of environmental factors on plant growth according to the ideal environment deviation value, selecting the maximum influencing factor, and performing data warning on the growth deviation trend graph in combination with the environmental monitoring threshold; Step S5-1, according to the remote sensing monitoring set, the simulated mapping remote sensing set and the ideal environment simulated mapping remote sensing set, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the plant growth simulation model, recorded as the simulated growth deviation value M, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the ideal environment growth model, recorded as the ideal environment deviation value; Step S5-2, summarizing the simulated growth deviation values ​​M of each sub-region within the plant remote sensing acquisition period T to construct a growth deviation trend graph; Step S5-3: According to the remote sensing monitoring set and the simulated mapping remote sensing set, the plant remote sensing data difference between each adjacent sub-region and the remote sensing data difference of the synchronous corresponding region in the plant growth simulation model are obtained, and the two differences are compared to form the regional growth gradient value G error , the difference calculation formula of plant remote sensing data in actual adjacent sub-areas is as follows: ; In the formula, G actual It is expressed as the difference of plant remote sensing data in actual adjacent sub-areas; R actual，i Represented as the actual plant remote sensing data value of sub-region i; R actual，o It is represented by the actual plant remote sensing data value of sub-area o; The difference calculation formula of plant remote sensing data in adjacent sub-areas in the plant growth simulation model is as follows: ; In the formula, G model It is expressed as the difference between the plant remote sensing data in the corresponding adjacent sub-areas in the plant growth simulation model; Rmodel，i Represented as the plant remote sensing data value of sub-area i in the plant growth simulation model; R model，o It is represented by the plant remote sensing data value of sub-area o in the plant growth simulation model; Region growth gradient value G error The calculation formula is as follows: ; In the formula, G error It is expressed as the difference of plant remote sensing data between actual adjacent sub-regions and the difference of remote sensing data of synchronous corresponding regions in the plant growth simulation model; Step S5-4, summarizing the regional growth gradient values ​​J obtained within the plant remote sensing acquisition period T to construct a gradient error trend graph; Step S5-5, according to the ideal environmental deviation value of each sub-region within the plant remote sensing acquisition period T, quantify the specific impact of actual environmental factors on plant growth, the actual environmental factors include light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration, and by comparing the growth performance under actual environmental conditions with that under ideal environmental conditions, select the environmental factor with the largest impact value as the key environmental monitoring object; Step S5-6: Compare the actual value obtained for the key environmental monitoring object with the environmental monitoring threshold: When the value actually obtained for the key environmental monitoring object is less than the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend graph is in a normal state; When the value actually obtained by the key environmental monitoring object is greater than or equal to the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend chart is normal, and an abnormal signal of the key environmental monitoring object is issued.

[0031] Step S6, set the abnormal status threshold, combine the growth deviation trend chart to warn the growth status of the monitored urban green plants, extract the maximum deviation absolute value in the gradient error trend chart, determine the corresponding area according to the maximum deviation absolute value, and conduct secondary monitoring, and judge the growth status of the urban green plants in the area according to the data of the secondary monitoring.

[0032] Step S6-1: Setting the abnormal state threshold Z max , obtain the data point value in the growth deviation trend chart, record it as the deviation value X, and combine it with the state abnormal threshold Z max To judge and warn the growth status of the monitored urban green space plants; When X<Z max When the growth state of the monitored urban green space plants is in line with the growth expectations in the plant growth simulation model, the growth state of the urban green space plants is normal; When X ≥ Z maxWhen the monitored urban green space plant growth status does not meet the growth expectations in the plant growth simulation model, the urban green space plant growth status is abnormal, and an abnormal growth status warning is issued; Step S6-2: Gradient error trend graph, extract the maximum deviation absolute value G max , according to G max Determine the corresponding regional location and conduct secondary remote sensing monitoring of the area. Compare the data collected by the secondary monitoring with the previous monitoring data to determine whether there is an abnormality or continuous deviation in the growth status of the plant. The average value of each data point in the gradient error trend graph is calculated as follows: ; In the formula, G avg It is represented by the average value of each data point in the gradient error trend graph; N is represented by the difference in plant remote sensing data between each adjacent sub-region and the number of remote sensing data differences in the synchronous corresponding regions in the plant growth simulation model; Maximum absolute value of deviation G max The calculation formula is as follows: ; In the formula, G max It is expressed as the maximum absolute value of the deviation in the gradient error trend graph; G error，io It is represented by the corresponding data point values ​​of sub-area i and sub-area o in the gradient error trend graph; max represents taking the maximum value from a set of data; Extraction of G max The corresponding sub-area i and sub-area o data are obtained, and sub-area i and sub-area o are monitored twice, the minimum value of the two monitorings is taken out, and the growth status of urban green plants in the area is judged based on the minimum value combined with the NDVI judgment standard.

[0033] For example, region A, region B, and region C; regions A and B are adjacent regions, and regions B and C are also adjacent regions; The plant remote sensing data obtained by actual remote sensing technology are: A: 0.8; B: 0.6; C: 0.5; The plant remote sensing data obtained by the remote sensing technology corresponding to the simulation mapping are: A: 0.7; B: 0.65; C: 0.55; Calculate the difference in plant remote sensing data between actual adjacent areas: Area AB: 0.8-0.6=0.2; Area BC: 0.6-0.5=0.1; Calculate the difference in plant remote sensing data between simulated adjacent areas: Area AB: 0.7-0.65=0.05; Area BC: 0.65-0.55=0.1; Calculation of regional growth gradient value: G error (A, B) = 0.2-0.05 = 0.015; G error (B,C)=0.1-0.1=0; Set the abnormal status threshold Z max =0.1; Then area A: 0.8-0.7=0.1=Z max ; X=Z max , it is judged that the growth state of the urban green space plants in area A does not meet the growth expectations in the plant growth simulation model, and the growth state of the urban green space plants in area A is abnormal, and an abnormal growth state warning is issued; Take out the maximum deviation absolute value G max ; The corresponding area that meets the conditions is area AB, and secondary monitoring is performed on area A and area B. The secondary monitoring data are: A: 0.75; B: 0.6; According to the NDVI judgment standard, both Area A and Area B are judged to have high vegetation cover: NDVI values ​​in this range usually indicate high-density vegetation, such as forests or dense bushes.

[0034] Embodiment 2, as Figure 2 As shown, the present invention provides a system for monitoring and analyzing the growth status of urban green space plants, which includes a data acquisition module, a regional management module, a growth simulation module, a collection management module, a trend chart management module and a status assessment and early warning module; The data acquisition module is used for data information collection; the area management module is used for dividing urban green space plants according to their location distribution characteristics and constructing coordinates for marking; the growth simulation module is used for training according to the collected data input into the neural network structure to simulate the growth of urban green space plants; the collection management module is used to manage the addition and deletion of data in each collection; the trend graph management module is used to construct a trend graph corresponding to the collection framework; the status assessment and early warning module is used to judge the growth status according to the trend graph and perform early warning processing on the areas that meet specific conditions; The output end of the data acquisition module is electrically connected to the input end of the area management module; the output end of the area management module is electrically connected to the input end of the growth simulation module; the output end of the growth simulation module is electrically connected to the input end of the collection management module; the output end of the collection management module is electrically connected to the input end of the trend chart management module; the output end of the trend chart management module is electrically connected to the input end of the status assessment and early warning module.

[0035] The data acquisition module includes an environmental factor acquisition unit and a remote sensing acquisition unit; the environmental factor acquisition unit is used to collect light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration; the remote sensing acquisition unit is used to obtain plant remote sensing data of each sub-area using remote sensing technology; The area management module includes an area division unit and a coordinate marking unit; the area division unit is used to divide the area according to the location distribution of urban green space plants; the coordinate marking unit is used to mark the location of the area; The growth simulation module includes a model training unit and a simulated growth unit; the model training unit is used to input data into a neural network structure for training to construct a plant growth simulation model; the simulated growth unit is used to simulate growth according to the input parameters.

[0036] The collection management module includes an actual collection unit and a simulation collection unit; the actual collection unit is used to store the data actually collected and acquired; the simulation collection unit is used to store the data generated by the simulated growth; The trend graph management module includes a direct trend unit and an adjacent difference trend graph unit; the direct trend unit is used to construct a trend graph of the difference between actual and simulated growth; the adjacent difference trend graph unit is used to construct a trend graph based on the difference between the actual acquisition and simulated mapping of the difference between two adjacent sub-regions; The state evaluation and early warning module includes a state evaluation unit and an early warning unit; the state evaluation unit is used to evaluate the growth state according to the collected data; the early warning unit is used to perform early warning processing on the growth state of urban green space plants in areas that meet specific conditions.

[0037] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for monitoring and analyzing the growth status of urban green space plants, characterized in that: The growth status monitoring and analysis method comprises the following steps: Step S1, dividing the area according to the distribution characteristics of urban green space plants, and establishing corresponding coordinate marks based on the divided areas; Step S2: comprehensively collect the growth status data of urban green space plants in each area according to the divided and marked areas, and record the plant characteristics and health status corresponding to each area; Step S3: Using the fully collected urban green space plant growth status data, a plant growth simulation model is constructed through a neural network, and an ideal environment growth model is constructed based on preset ideal environmental parameters. The plant growth simulation model is used to simulate the growth status of the corresponding collected data in each area, and key environmental factor data are collected regularly; Step S4, setting a plant remote sensing acquisition cycle, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, using remote sensing technology to monitor each area marked with coordinates according to the plant remote sensing acquisition cycle, and storing the plant remote sensing data actually collected by remote sensing technology in the remote sensing monitoring set, while storing the remote sensing data generated by the synchronized real environment plant growth model in the simulated mapping remote sensing set, and storing the remote sensing data generated by the ideal environment plant growth model in the ideal environment simulated mapping remote sensing set; Step S5, setting the environmental monitoring threshold, obtaining the deviation value between the actual plant remote sensing data of each region and the remote sensing data generated by the plant growth simulation model, and recording it as the simulated growth deviation value; at the same time, obtaining the deviation value between the remote sensing monitoring set and the ideal environment simulation mapping remote sensing set, and recording it as the ideal environment deviation value, comparing the remote sensing data difference of the actual adjacent sub-regions with the remote sensing data difference of the synchronous corresponding region, forming a regional growth gradient value, summarizing the simulated growth deviation value and the regional growth gradient value, constructing a growth deviation trend graph and a gradient error trend graph, quantifying the influence of environmental factors on plant growth according to the ideal environment deviation value, selecting the maximum influencing factor, and performing data warning on the growth deviation trend graph in combination with the environmental monitoring threshold; Step S6, set the abnormal status threshold, combine the growth deviation trend chart to warn the growth status of the monitored urban green plants, extract the maximum deviation absolute value in the gradient error trend chart, determine the corresponding area according to the maximum deviation absolute value, and conduct secondary monitoring, and judge the growth status of the urban green plants in the area according to the data of the secondary monitoring.

2. The method for monitoring and analyzing the growth status of urban green space plants according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1, dividing the urban green space into multiple sub-areas according to the location distribution characteristics of urban green space plants, combined with plant density and environmental conditions; Step S1-2: according to the divided multiple sub-regions, a coordinate mark is set for each sub-region using a geographic coordinate system, a primary coordinate mark is set at the geometric center point of each sub-region, and a secondary coordinate mark is set at the boundary corner point.

3. The method for monitoring and analyzing the growth status of urban green space plants according to claim 2, characterized in that: In step S2, the growth status data of urban green space plants are comprehensively collected for each divided sub-area. The comprehensively collected data include growth characteristic data, environmental factor data, plant health data and remote sensing data, and the plant characteristic data and health status data corresponding to each sub-area are stored and recorded.

4. The method for monitoring and analyzing the growth status of urban green space plants according to claim 3, characterized in that: The specific steps of step S3 are as follows: Step S3-1, inputting growth characteristic data, environmental factor data, plant health data and remote sensing data into a neural network structure for training, and constructing a plant growth simulation model and an ideal environment growth model; Step S3-2, setting a key environmental factor data collection period Q, acquiring key environmental factor data by deploying sensors in each sub-area, wherein the key environmental factor data includes light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration, and inputting the key environmental factor data acquired in each collection period into a plant growth simulation model to simulate growth; Step S3-3: Replace the set key environmental factor data with standard data under ideal environmental conditions, and input the ideal environmental growth model to simulate growth.

5. The method for monitoring and analyzing the growth status of urban green space plants according to claim 4, characterized in that: The specific steps of step S4 are as follows: Step S4-1, setting a plant remote sensing acquisition cycle T, constructing a remote sensing monitoring set, a simulated mapping remote sensing set and an ideal environment simulated mapping remote sensing set, wherein the remote sensing monitoring set is used to store plant remote sensing data actually collected by remote sensing technology, the simulated mapping remote sensing set is used to store plant remote sensing data mapped by a plant growth simulation model, and the ideal environment simulated mapping remote sensing set is used to store plant remote sensing data mapped by an ideal environment growth model; Step S4-2: monitor each sub-area marked with coordinates using remote sensing technology according to the plant remote sensing collection cycle; Step S4-3, store the plant remote sensing data of each sub-area collected by actual remote sensing technology into the remote sensing monitoring set, store the plant remote sensing data generated in the corresponding area in the plant growth simulation model into the simulation mapping remote sensing set, and store the plant remote sensing data generated in the corresponding area in the ideal environment growth model into the ideal environment simulation mapping remote sensing set.

6. The method for monitoring and analyzing the growth status of urban green space plants according to claim 5, characterized in that: The specific steps of step S5 are as follows: Step S5-1, according to the remote sensing monitoring set, the simulated mapping remote sensing set and the ideal environment simulated mapping remote sensing set, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the plant growth simulation model, recorded as the simulated growth deviation value M, obtain the deviation value between the actual plant remote sensing data of each sub-region and the plant remote sensing data generated by the ideal environment growth model, recorded as the ideal environment deviation value; Step S5-2, summarizing the simulated growth deviation values ​​M of each sub-region within the plant remote sensing acquisition period T to construct a growth deviation trend graph; Step S5-3: According to the remote sensing monitoring set and the simulated mapping remote sensing set, the plant remote sensing data difference between each adjacent sub-region and the remote sensing data difference of the synchronous corresponding region in the plant growth simulation model are obtained, and the two differences are compared to form the regional growth gradient value G error , the difference calculation formula of plant remote sensing data in actual adjacent sub-areas is as follows: ； In the formula, G actual It is expressed as the difference of plant remote sensing data in actual adjacent sub-areas; R actual，i Represented as the actual plant remote sensing data value of sub-region i; R actual，o It is represented by the actual plant remote sensing data value of sub-area o; The difference calculation formula of plant remote sensing data in adjacent sub-areas in the plant growth simulation model is as follows: ； In the formula, G model It is expressed as the difference between the plant remote sensing data in the corresponding adjacent sub-areas in the plant growth simulation model; R model，i Represented as the plant remote sensing data value of sub-area i in the plant growth simulation model; R model，o It is represented by the plant remote sensing data value of sub-area o in the plant growth simulation model; Region growth gradient value G error The calculation formula is as follows: ； In the formula, G error It is expressed as the difference of plant remote sensing data between actual adjacent sub-regions and the difference of remote sensing data of synchronous corresponding regions in the plant growth simulation model; Step S5-4, summarizing the regional growth gradient values ​​J obtained within the plant remote sensing acquisition period T to construct a gradient error trend graph; Step S5-5, according to the ideal environmental deviation value of each sub-region within the plant remote sensing acquisition period T, quantify the specific impact of actual environmental factors on plant growth, the actual environmental factors include light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration, and by comparing the growth performance under actual environmental conditions with that under ideal environmental conditions, select the environmental factor with the largest impact value as the key environmental monitoring object; Step S5-6: Compare the actual value of the key environmental monitoring object with the environmental monitoring threshold: When the value actually obtained for the key environmental monitoring object is less than the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend graph is in a normal state; When the value actually obtained by the key environmental monitoring object is greater than or equal to the environmental monitoring threshold, it is judged that the data fluctuation of the growth deviation trend chart is normal, and an abnormal signal of the key environmental monitoring object is issued.

7. The method for monitoring and analyzing the growth status of urban green space plants according to claim 6, characterized in that: The specific steps of step S6 are as follows: Step S6-1, setting the abnormal state threshold Z max , obtain the data point value in the growth deviation trend chart, record it as the deviation value X, and combine it with the state abnormal threshold Z max To judge and warn the growth status of the monitored urban green space plants; When X<Z max When the growth state of the monitored urban green space plants is in line with the growth expectations in the plant growth simulation model, the growth state of the urban green space plants is normal; When X ≥ Z max When the monitored urban green space plant growth status does not meet the growth expectations in the plant growth simulation model, the urban green space plant growth status is abnormal, and an abnormal growth status warning is issued; Step S6-2: Gradient error trend graph, extract the maximum deviation absolute value G max , according to G max Determine the corresponding regional location and conduct secondary remote sensing monitoring of the area. Compare the data collected by the secondary monitoring with the previous monitoring data to determine whether there is an abnormality or continuous deviation in the growth status of the plant. The average value of each data point in the gradient error trend graph is calculated as follows: ； In the formula, G avg It is represented by the average value of each data point in the gradient error trend graph; N is represented by the difference in plant remote sensing data between each adjacent sub-region and the number of remote sensing data differences in the synchronous corresponding regions in the plant growth simulation model; Maximum absolute value of deviation G max The calculation formula is as follows: ； In the formula, G max It is expressed as the maximum absolute value of the deviation in the gradient error trend graph; G error，io It is represented by the corresponding data point values ​​of sub-area i and sub-area o in the gradient error trend graph; max represents taking the maximum value from a set of data; Extraction of G max The corresponding sub-area i and sub-area o data are collected, and sub-area i and sub-area o are monitored twice, the minimum value of the two monitorings is taken out, and the growth status of urban green plants in the area is judged based on the minimum value combined with the NDVI judgment standard.

8. A system for monitoring and analyzing the growth status of urban green space plants, which is applied to a method for monitoring and analyzing the growth status of urban green space plants as claimed in any one of claims 1 to 7, characterized in that: The growth status monitoring and analysis system includes a data acquisition module, a regional management module, a growth simulation module, a collection management module, a trend chart management module and a status assessment and early warning module; The data acquisition module is used for data information collection; the area management module is used for dividing urban green space plants according to their location distribution characteristics and constructing coordinates for marking; the growth simulation module is used for training according to the collected data input into the neural network structure to simulate the growth of urban green space plants; the collection management module is used to manage the addition and deletion of data in each collection; The trend graph management module is used to construct a trend graph corresponding to the collection framework; the state assessment and early warning module is used to judge the growth state according to the trend graph and perform early warning processing on the areas that meet specific conditions; The output end of the data acquisition module is electrically connected to the input end of the area management module; the output end of the area management module is electrically connected to the input end of the growth simulation module; the output end of the growth simulation module is electrically connected to the input end of the collection management module; the output end of the collection management module is electrically connected to the input end of the trend chart management module; the output end of the trend chart management module is electrically connected to the input end of the status assessment and early warning module.

9. The urban green space plant growth status monitoring and analysis system according to claim 8, characterized in that: The data acquisition module includes an environmental factor acquisition unit and a remote sensing acquisition unit; the environmental factor acquisition unit is used to collect light intensity, soil moisture, temperature and atmospheric carbon dioxide concentration; the remote sensing acquisition unit is used to obtain plant remote sensing data of each sub-area using remote sensing technology; The area management module includes an area division unit and a coordinate marking unit; the area division unit is used to divide the area according to the location distribution of urban green space plants; the coordinate marking unit is used to mark the location of the area; The growth simulation module includes a model training unit and a simulated growth unit; the model training unit is used to input data into a neural network structure for training to construct a plant growth simulation model; the simulated growth unit is used to simulate growth according to the input parameters.

10. The urban green space plant growth status monitoring and analysis system according to claim 8, characterized in that: The collection management module includes an actual collection unit and a simulation collection unit; the actual collection unit is used to store the data actually collected and acquired; the simulation collection unit is used to store the data generated by the simulated growth; The trend graph management module includes a direct trend unit and an adjacent difference trend graph unit; the direct trend unit is used to construct a difference trend graph between actual and simulated growth; The adjacent difference trend graph unit is used to construct a trend graph according to the difference between the actual acquisition and the simulated mapping of the difference between two adjacent sub-regions; The state evaluation and early warning module includes a state evaluation unit and an early warning unit; the state evaluation unit is used to evaluate the growth state according to the collected data; the early warning unit is used to perform early warning processing on the growth state of urban green space plants in areas that meet specific conditions.

Images