A vegetation growth data monitoring system and method

Abstract

The present invention discloses a vegetation growth data monitoring system and method, which relates to the technical field of environmental monitoring. The problem of insufficient spatial resolution of remote sensing technology is solved by a spatial resolution optimization module; multi-dimensional image data is collected, and spatial detail presentation is optimized by combining image super-resolution processing technology and multi-angle data collection methods, and resolution correction is performed to generate high-precision monitoring images with a unified resolution, realizing accurate identification of small-scale vegetation changes; meteorological data and soil monitoring data are collected in real time, and data cleaning and formatting processing are carried out in combination with historical data to construct a unified growth environment data set to ensure the accuracy of data fusion and analysis; the complexity and interference problems of environmental factors are solved by an environmental factor analysis module; the interference influence coefficient Eic is calculated and evaluated, and early warnings are generated and intervention suggestions are pushed, such as adjusting irrigation and soil management, providing precise dynamic environmental optimization support.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and particularly to a vegetation growth data monitoring system and method. Background Art

[0002] The vegetation growth data monitoring system originated from the development needs of agricultural modernization. The initial monitoring methods mostly relied on manual observation and ground surveys, but this method was inefficient, had poor accuracy, and was limited by time and space. With the introduction of remote sensing technology, satellites and drones have become important tools for vegetation monitoring. By collecting image data of the surface vegetation state in real time, researchers can more comprehensively understand the vegetation growth status. In recent years, with the rapid development of Internet of Things, cloud computing, and big data analysis technologies, the vegetation growth monitoring system has gradually achieved automation and intelligence, capable of accurately collecting environmental parameters and performing real-time analysis to provide decision-making support, and is widely used in fields such as agricultural production and ecological environment protection. The combination of these technologies not only improves the monitoring accuracy, but also greatly enhances the monitoring efficiency and response speed.

[0003] However, in practical applications, the existing vegetation growth data monitoring system still has the following technical problems:

[0004] 1. Insufficient spatial resolution: At present, although remote sensing technology can cover large-scale vegetation monitoring, its spatial resolution is sometimes insufficient. Especially in large-scale area monitoring, it is impossible to accurately identify small-scale vegetation changes. For example, the resolution of satellite images may be too low to accurately reflect the small changes or heterogeneity of ground vegetation, affecting the prediction accuracy.

[0005] 2. Data fusion and standardization problems: The vegetation growth monitoring system usually relies on multiple data sources (such as remote sensing images, sensor data, etc.), but the standardization problem of different data sources is still a challenge. The data formats, accuracies, and collection frequencies of different platforms and devices may vary, resulting in difficulties in data fusion and affecting the reliability and accuracy of comprehensive analysis results.

[0006] 3. Complexity and interference of environmental factors: Vegetation growth is affected by multiple environmental factors, such as climate, soil type, terrain, etc., and the interaction between these factors is relatively complex. Current monitoring systems often have difficulty comprehensively considering the dynamic changes of all environmental factors. For example, errors in meteorological data or malfunctions of sensors themselves may lead to deviations in the prediction of vegetation growth status. Summary of the Invention

[0007] Aiming at the deficiencies of the prior art, the present invention provides a vegetation growth data monitoring system and method, which solves the problems mentioned in the background art.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: A vegetation growth data monitoring system includes a data fusion and standardization module, an environmental factor analysis module, a spatial resolution optimization module, a dynamic monitoring module, a growth trend prediction module, and a report generation module;

[0009] The data fusion and standardization module is used to collect data related to the growth environment of vegetation, including historical meteorological data and historical soil monitoring data; at the same time, it preprocesses and uniformly formats the data related to the growth environment from different sensors, and finally constructs a data set related to the growth environment;

[0010] The environmental factor analysis module is used to analyze the impact of the surrounding environment on the growth of vegetation, including meteorology, soil type, and terrain. Based on the data set related to the growth environment, it calculates and evaluates the interference impact coefficient Eic of the surrounding environment on the vegetation growth trend, and finally issues a warning and conducts intervention according to the evaluation content;

[0011] The spatial resolution optimization module is used to deploy remote sensing image devices and image sensors around the vegetation to collect vegetation image data, and obtain multi-dimensional vegetation image data in real time, including high-resolution remote sensing images and near-ground image sensor data. Then, it performs image super-resolution processing on the multi-dimensional vegetation image data, and combines multi-angle data acquisition technology to adjust the spatial resolution of vegetation monitoring;

[0012] The dynamic monitoring module is used to analyze the multi-dimensional vegetation image data collected by the remote sensing image device and the image sensor, and at the same time calculate the vegetation health coefficient Vhc and conduct dynamic evaluation; then, through the combination of sensors and drones, it dynamically monitors the vegetation growth trend based on time series analysis and collects data related to the vegetation growth trend in real time;

[0013] The growth trend prediction module is used to analyze the data related to the vegetation growth trend collected, and calculate the growth cycle progress value Gcp; by comparing it with the preset growth progress threshold R, it predicts the growth trend and future growth state of the vegetation, and assists in decision-making;

[0014] The report generation module is used to receive and analyze the evaluation content of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time, and then generate a vegetation growth trend monitoring report; finally, it pushes the vegetation growth trend monitoring report to the environmental monitoring terminal and the user operating system through the cloud platform to provide decision support.

[0015] Preferably, the data fusion and standardization module first arranges environmental sensors, remote sensing image devices, and ground collection terminals within the vegetation monitoring area to monitor and collect real-time data on the vegetation growth environment; the growth environment-related data also includes real-time meteorological data and real-time soil monitoring data; secondly, the growth environment-related data collected from different sources is subjected to data cleaning and denoising through a preprocessing step to remove redundant and invalid data; subsequently, unified formatting processing is performed to eliminate data inconsistencies caused by differences in device types, data formats, and timestamps through a standardization algorithm; finally, based on the growth environment-related data generated after formatting processing, a growth environment-related data set is constructed.

[0016] Preferably, the environmental factor analysis module includes an environmental calculation unit and an environmental assessment unit;

[0017] The environmental calculation unit is used to extract subordinate parameters related to meteorology, soil type, and terrain based on the growth environment-related data set, including the temperature variation amplitude Tva, soil water content Sfw, light intensity change rate Lir, and terrain slope coefficient Tgc, and calculate and obtain the interference influence coefficient Eic through the following formula:

[0018]

[0019] The environmental assessment unit conducts a comparative assessment by comparing the preset interference influence threshold Q with the interference influence coefficient Eic, issues a warning, and takes intervention measures; the specific content is as follows:

[0020] If the interference influence coefficient Eic ≤ the interference influence threshold Q, it indicates that the current surrounding environment is normal, there is no interference or the interference is within an acceptable range for the vegetation growth trend. At this time, the current data is recorded, and a "normal environment" status report is generated;

[0021] If the interference influence coefficient Eic > the interference influence threshold Q, it indicates that the current surrounding environment is abnormal, and the interference to the vegetation growth trend has exceeded the safe range. At this time, intervention measures are taken; including the system automatically generating a warning signal and pushing the warning signal to the monitoring terminal and user equipment.

[0022] Preferably, the spatial resolution optimization module first deploys high-resolution remote sensing image devices and near-ground image sensors in the vegetation monitoring area to collect multi-dimensional vegetation image data of the target area. The remote sensing image devices provide overall image coverage of a large range, and the near-ground image sensors capture local high-precision image details. Secondly, image super-resolution processing technology is used for fusion to eliminate the loss of details and blurring problems caused by data resolution differences. Subsequently, based on the multi-angle data acquisition technology, the multi-dimensional vegetation image data obtained at different times, angles, and devices are integrated, and the spatial details of the target area are optimized through the angle fusion algorithm. Finally, the resolution of the fused multi-dimensional vegetation image data is corrected and adjusted to generate a monitoring image with a unified resolution.

[0023] Preferably, the dynamic monitoring module includes a health calculation and evaluation unit and a vegetation growth monitoring unit;

[0024] Based on the multi-dimensional vegetation image data collected by the remote sensing image devices and image sensors, the health calculation and evaluation unit analyzes the key growth parameters of the vegetation through feature extraction algorithms, including leaf area Vmj, vegetation coverage Vfg, photosynthetic efficiency Vgh, and vegetation canopy surface temperature Vgc, and calculates and obtains the vegetation health coefficient Vhc by combining the following formula:

[0025]

[0026] By comparing and evaluating the preset vegetation health threshold W with the vegetation health coefficient Vhc, the following content is generated:

[0027] If the vegetation health coefficient Vhc ≥ the vegetation health threshold W, it indicates that the vegetation growth state is within the healthy range. The system records the current state and marks it as "normal", and at the same time, monitors the vegetation growth in real time;

[0028] If the vegetation health coefficient Vhc < the vegetation health threshold W, it indicates that the vegetation growth state is abnormal. At this time, further analyze the specific abnormal reasons and take corresponding measures.

[0029] Preferably, the vegetation growth monitoring unit works in cooperation with sensors and drones deployed in the vegetation monitoring area. The sensors are used to collect ground growth environment data in real time, and the drones are equipped with multi-spectral imaging devices to perform periodic image scans on the target area to capture multi-dimensional growth image data of the vegetation. Subsequently, the ground growth environment data and multi-dimensional growth image data are synchronously uploaded to the monitoring platform, and based on time series analysis technology, the dynamic change trends of the continuous ground growth environment data and multi-dimensional growth image data are analyzed to extract vegetation growth-related data, including vegetation photosynthetic volatility Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr.

[0030] Preferably, the growth trend prediction module includes a growth trend calculation unit and a growth trend evaluation unit;

[0031] The growth trend calculation unit is used to extract the photosynthetic volatility Pvr of vegetation, the stem thickening rate Scr, the root activity Rai, and the canopy greenness change rate Cgr, and calculate the growth cycle progress value Gcp by combining the following formula:

[0032]

[0033] Preferably, the growth trend evaluation unit compares and evaluates the preset growth cycle progress threshold R with the growth cycle progress value Gcp to generate the following evaluation content:

[0034] If the growth cycle progress value Gcp ≥ the growth cycle progress threshold R, it means that the growth cycle progress of the vegetation is normal or ahead of schedule; the system is marked as "normal", and the progress data is recorded for subsequent analysis;

[0035] If the growth cycle progress value Gcp < the growth cycle progress threshold R, it means that the growth cycle progress of the vegetation lags behind the expectation, and there are problems of environmental impact or insufficient management; the system is marked as "abnormal", and at this time, the interference reasons are further evaluated, including abnormal photosynthesis efficiency, abnormal soil nutrients, abnormal root development, and damaged canopy.

[0036] Preferably, the report generation module is used to comprehensively analyze the vegetation health coefficient Vhc and the growth cycle progress value Gcp, extract key evaluation content, including health status classification, abnormal parameter indicators, and growth trend prediction; then, based on the analysis results, a vegetation growth trend monitoring report is automatically generated; the content of the vegetation growth trend monitoring report includes the current vegetation health level, the comparison result of the growth progress, the specific location and possible reasons of the abnormal area, the prediction trend of the future growth state, and the intervention measures recommended by the system; then, the generated vegetation growth trend monitoring report is pushed to the environmental monitoring terminal and the user operation system through the cloud platform.

[0037] A method for monitoring vegetation growth trend data includes the following steps:

[0038] Step 1: Collect data related to the growth environment of vegetation, including historical meteorological data and historical soil monitoring data; at the same time, preprocess and uniformly format the data related to the growth environment from different sensors, and finally construct a data set related to the growth environment;

[0039] Step 2: Analyze the impact of the surrounding environment on the growth of vegetation, including meteorology, soil type, and terrain, calculate the interference impact coefficient Eic of the surrounding environment on the growth trend of vegetation based on the data set related to the growth environment, and evaluate it. Finally, issue a warning and carry out intervention according to the evaluation content;

[0040] Step 3: Deploy remote sensing image devices and image sensors around the vegetation to collect vegetation images, and obtain multi-dimensional vegetation image data in real time, including high-resolution remote sensing images and near-ground image sensor data. Then, perform image super-resolution processing on the multi-dimensional vegetation image data, and combine with multi-angle data acquisition technology to adjust the spatial resolution of vegetation monitoring.

[0041] Step 4: Analyze the multi-dimensional vegetation image data collected by the remote sensing image devices and image sensors. At the same time, calculate the vegetation health coefficient Vhc and conduct dynamic evaluation. Then, through the combination of sensors and drones, dynamically monitor the growth trend of the vegetation based on time series analysis and collect data related to the growth trend of the vegetation in real time.

[0042] Step 5: Analyze the data related to the growth trend of the vegetation collected, and calculate the growth cycle progress value Gcp. By comparing with the preset growth progress threshold R, predict the growth trend and future growth state of the vegetation to assist in decision-making.

[0043] Step 6: Receive and analyze the evaluation content of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time. Then, generate a vegetation growth trend monitoring report. Finally, push the vegetation growth trend monitoring report to the environmental monitoring terminal and the user operation system through the cloud platform to provide decision-making support.

[0044] The present invention provides a vegetation growth trend data monitoring system and method, which has the following beneficial effects:

[0045] (1) For the vegetation growth trend data monitoring system and method, the problem of insufficient spatial resolution in current remote sensing technology for large-scale monitoring is solved through the spatial resolution optimization module. By deploying high-resolution remote sensing image devices and near-ground image sensors to work together in the vegetation monitoring area, multi-dimensional image data of the target area is collected. Combining image super-resolution processing technology eliminates the problem of detail loss caused by data resolution differences. Using multi-angle data acquisition technology to integrate multi-dimensional vegetation image data obtained at different times, angles, and by different devices, optimizing the spatial detail presentation of the target area through an angle fusion algorithm, and performing resolution correction and adjustment on the fused multi-dimensional vegetation image data to generate high-precision monitoring images with a unified resolution, which can achieve accurate identification of small-scale vegetation changes and comprehensively improve the accuracy and effect of vegetation monitoring.

[0046] (2) The vegetation growth data monitoring system and method solve the formatting and standardization problems of different data sources through the data fusion and standardization module; by deploying environmental sensors, remote sensing image devices and ground collection terminals in the vegetation monitoring area to collect real-time meteorological data and real-time soil monitoring data, and combining historical meteorological data and historical soil monitoring data, unified preprocessing is carried out, including data cleaning and denoising to remove redundant data; then, through the standardization algorithm, data inconsistencies caused by equipment types, data formats and timestamp differences are eliminated, and finally a data set related to the growth environment is constructed to provide reliable data support for the data analysis of subsequent modules, solving the accuracy and reliability problems of data fusion and analysis.

[0047] (3) The vegetation growth data monitoring system and method solve the complexity and interference problems of environmental factors through the environmental factor analysis module; through the environmental calculation unit, based on the data set related to the growth environment, subordinate parameters related to meteorology, soil type and terrain are extracted, including the temperature variation amplitude Tva, soil water content Sfw, light intensity change rate Lir and terrain slope coefficient Tgc, and the interference influence coefficient Eic is calculated by combining formulas; then, through the environmental evaluation unit, the interference influence coefficient Eic is evaluated based on the preset interference influence threshold Q; if Eic is higher than Q, the system generates a warning signal according to the abnormal parameters and pushes intervention suggestions, including adjusting irrigation frequency and water supply, optimizing soil management and adjusting regional environmental conditions; effectively solving the comprehensive interference analysis and precise management problems of multi-dimensional environmental factors, and providing dynamic environmental optimization support for the healthy growth of vegetation. Brief Description of the Drawings

[0048] Figure 1 It is a schematic diagram of the framework structure of a vegetation growth data monitoring system of the present invention;

[0049] Figure 2 It is a schematic diagram of the step flow of a vegetation growth data monitoring method of the present invention. Detailed Embodiments

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention. Embodiment 1

[0051] Please refer to Figure 1, the present invention provides a vegetation growth data monitoring system, including a data fusion and standardization module, an environmental factor analysis module, a spatial resolution optimization module, a dynamic monitoring module, a growth trend prediction module, and a report generation module;

[0052] The data fusion and standardization module is used to collect data related to the growth environment of vegetation, including historical meteorological data and historical soil monitoring data; at the same time, preprocess and uniformly format the data related to the growth environment from different sensors, and finally construct a data set related to the growth environment;

[0053] The environmental factor analysis module is used to analyze the impact of the surrounding environment on the growth of vegetation, including meteorology, soil type, and terrain. Based on the data set related to the growth environment, calculate and evaluate the interference impact coefficient Eic of the surrounding environment on the vegetation growth trend, and finally issue a warning and carry out intervention according to the evaluation content;

[0054] The spatial resolution optimization module is used to deploy remote sensing image devices and image sensors around the vegetation to collect vegetation image data, obtain real-time multi-dimensional vegetation image data, including high-resolution remote sensing images and near-ground image sensor data, then perform image super-resolution processing on the multi-dimensional vegetation image data, and combine multi-angle data acquisition technology to adjust the spatial resolution of vegetation monitoring;

[0055] The dynamic monitoring module is used to analyze the multi-dimensional vegetation image data collected by the remote sensing image device and the image sensor, calculate the vegetation health coefficient Vhc at the same time, and conduct dynamic evaluation; then, through the combination of sensors and drones, dynamically monitor the vegetation growth trend based on time series analysis and collect real-time data related to the vegetation growth trend;

[0056] The growth trend prediction module is used to analyze the data related to the vegetation growth trend collected, and calculate the growth cycle progress value Gcp; by comparing with the preset growth progress threshold R, predict the growth trend and future growth state of the vegetation, and assist in decision-making;

[0057] The report generation module is used to receive and analyze the evaluation content of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time, and then generate a vegetation growth trend monitoring report; finally, push the vegetation growth trend monitoring report to the environmental monitoring terminal and the user operating system through the cloud platform to provide decision-making support.

[0058] In this embodiment, the data fusion and standardization module constructs a unified data set related to the growth environment by collecting historical meteorological data and historical soil monitoring data in real time, and combining data cleaning and formatting processing, ensuring the accuracy and reliability of data fusion;

[0059] The environmental factor analysis module extracts the temperature variation amplitude Tva, soil water content Sfw, light intensity change rate Lir, and terrain slope coefficient Tgc, calculates the interference impact coefficient Eic, and compares it with the preset interference impact threshold Q for evaluation. It can timely detect the impact of abnormal environments on vegetation, generate early warnings, and provide effective environmental intervention suggestions.

[0060] The spatial resolution optimization module optimizes the spatial detail presentation of the target area through the collaborative work of high-resolution remote sensing image equipment and near-ground image sensors, combines image super-resolution processing technology and multi-angle data acquisition technology, generates high-precision vegetation monitoring images with a unified resolution, and realizes the accurate monitoring of small-scale vegetation changes.

[0061] The dynamic monitoring module collects multi-dimensional image data of vegetation in real time through remote sensing image equipment and image sensors, combines drone multi-spectral images and ground sensor data, calculates the vegetation health coefficient Vhc, and conducts dynamic evaluation to ensure the real-time tracking of vegetation growth.

[0062] The growth trend prediction module analyzes the photosynthetic volatility Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr of vegetation, calculates the growth cycle progress value Gcp, and compares it with the growth cycle progress threshold R to accurately predict the growth trend and future growth state of vegetation, providing support for scientific decision-making.

[0063] The report generation module generates a monitoring report covering health status classification, growth trend prediction, and intervention suggestions by comprehensively analyzing the vegetation health coefficient Vhc and the growth cycle progress value Gcp, and pushes it to the monitoring terminal and user operating system through the cloud platform, providing efficient support for vegetation management. Embodiment 2

[0064] The data fusion and standardization module first arranges environmental sensors, remote sensing image equipment, and ground acquisition terminals in the vegetation monitoring area to monitor and collect data related to the vegetation growth environment in real time. The data related to the growth environment also includes real-time meteorological data and real-time soil monitoring data. Secondly, the collected data related to the growth environment from different sources is subjected to data cleaning and denoising through preprocessing steps to remove redundant and invalid data. Subsequently, unified formatting processing is performed to eliminate data inconsistencies caused by differences in equipment types, data formats, and timestamps through a standardization algorithm. Finally, a data set related to the growth environment is constructed based on the data related to the growth environment generated after formatting processing.

[0065] In this embodiment, by deploying environmental sensors, remote sensing image devices, and ground acquisition terminals in the vegetation monitoring area, the efficient acquisition of real-time meteorological data (including temperature, humidity, rainfall, etc.) and real-time soil monitoring data (including soil moisture content, soil nutrient concentration, etc.) is achieved, ensuring the comprehensiveness and timeliness of data sources; through data cleaning and denoising processes, redundant and invalid data are removed, improving data quality; through unified formatting processing and standardization algorithms, data inconsistencies caused by device types, data formats, and timestamp differences are eliminated, ensuring the fusion accuracy and consistency of multi-source data; the finally generated data set related to the growth environment provides a unified and reliable high-quality data input for subsequent modules, laying a solid foundation for the comprehensive monitoring and analysis of vegetation growth; this module is of great significance in the system. It not only solves the problem of multi-source data fusion, improves the operation efficiency and analysis accuracy of the monitoring system, but also provides solid data support for growth prediction, environmental assessment, and intervention decision-making through standardized data management, and is the basic guarantee for the efficient operation of the vegetation growth data monitoring system. Embodiment 3

[0066] The environmental factor analysis module includes an environmental calculation unit and an environmental assessment unit;

[0067] The environmental calculation unit is used to extract subordinate parameters related to meteorology, soil type, and terrain based on the data set related to the growth environment, including the temperature variation amplitude Tva, the soil moisture content Sfw, the light intensity change rate Lir, and the terrain slope coefficient Tgc, and calculate and obtain the interference influence coefficient Eic through the following formula:

[0068]

[0069] The environmental assessment unit conducts a comparative assessment by comparing the preset interference influence threshold Q with the interference influence coefficient Eic, issues a warning, and conducts an intervention; the specific content is as follows:

[0070] If the interference influence coefficient Eic ≤ the interference influence threshold Q, it indicates that the current surrounding environment is normal, there is no interference to the vegetation growth or the interference is within an acceptable range. At this time, the current data is recorded, and a "normal environment" status report is generated;

[0071] If the interference influence coefficient Eic > the interference influence threshold Q, it indicates that the current surrounding environment is abnormal, and the interference to the vegetation growth has exceeded the safe range. At this time, intervention measures are taken; including the system automatically generating a warning signal and pushing the warning signal to the monitoring terminal and the user device.

[0072] The spatial resolution optimization module first deploys high-resolution remote sensing image equipment and near-ground image sensors in the vegetation monitoring area to collect multi-dimensional image data of vegetation in the target area. The remote sensing image equipment provides overall image coverage of a large area, and the near-ground image sensors capture local high-precision image details. Secondly, image super-resolution processing technology is used for fusion to eliminate the loss of details and blurring problems caused by differences in data resolution. Subsequently, based on the multi-angle data acquisition technology, the multi-dimensional image data of vegetation obtained at different times, angles, and by different devices are integrated, and the spatial details of the target area are optimized through the angle fusion algorithm. Finally, the resolution of the fused multi-dimensional image data of vegetation is corrected and adjusted to generate a monitoring image with a unified resolution.

[0073] The dynamic monitoring module includes a health calculation and evaluation unit and a vegetation growth monitoring unit;

[0074] Based on the multi-dimensional image data of vegetation collected by the remote sensing image equipment and the image sensors, the health calculation and evaluation unit analyzes the key growth parameters of vegetation through feature extraction algorithms, including leaf area Vmj, vegetation coverage Vfg, photosynthetic efficiency Vgh, and vegetation canopy surface temperature Vgc, and calculates and obtains the vegetation health coefficient Vhc by combining the following formula:

[0075]

[0076] By comparing and evaluating the preset vegetation health threshold W with the vegetation health coefficient Vhc, the following content is generated:

[0077] If the vegetation health coefficient Vhc ≥ the vegetation health threshold W, it indicates that the vegetation growth state is within the healthy range. The system records the current state and marks it as "normal", and at the same time, monitors the vegetation growth in real time;

[0078] If the vegetation health coefficient Vhc < the vegetation health threshold W, it indicates that the vegetation growth state is abnormal. At this time, the specific abnormal reasons are further analyzed and corresponding measures are taken.

[0079] The vegetation growth monitoring unit works in cooperation by deploying sensors and drones in the vegetation monitoring area. The sensors are used to collect ground growth environment data in real time, and the drones are equipped with multi-spectral image equipment to perform periodic image scans on the target area to capture multi-dimensional growth image data of vegetation. Subsequently, the ground growth environment data and the multi-dimensional growth image data are synchronously uploaded to the monitoring platform, and based on time series analysis technology, the dynamic change trends of the continuous ground growth environment data and the multi-dimensional growth image data are analyzed to extract vegetation growth-related data, including vegetation photosynthetic volatility Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr.

[0080] The growth trend prediction module includes a growth trend calculation unit and a growth trend evaluation unit;

[0081] The growth trend calculation unit is used to extract the photosynthetic volatility Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr of the vegetation, and calculate the growth cycle progress value Gcp by combining the following formula:

[0082]

[0083] The growth trend evaluation unit compares and evaluates the preset growth cycle progress threshold R with the growth cycle progress value Gcp to generate the following evaluation content:

[0084] If the growth cycle progress value Gcp ≥ the growth cycle progress threshold R, it indicates that the growth cycle progress of the vegetation is normal or ahead of schedule; the system is marked as "normal", and the progress data is recorded for subsequent analysis;

[0085] If the growth cycle progress value Gcp < the growth cycle progress threshold R, it indicates that the growth cycle progress of the vegetation lags behind the expectation, and there are problems of environmental impact or insufficient management; the system is marked as "abnormal", and at this time, the interference reasons are further evaluated, including abnormal photosynthesis efficiency, abnormal soil nutrients, abnormal root development, and canopy damage.

[0086] In this embodiment, through the collaborative work of each module, the precise monitoring, dynamic analysis, and scientific decision-making support of the vegetation growth trend are realized; the environmental factor analysis module extracts the temperature variation amplitude Tva, soil water content Sfw, light intensity change rate Lir, and terrain slope coefficient Tgc through the environmental calculation unit, calculates the interference influence coefficient Eic by using the formula to quantify the interference degree of environmental factors on the vegetation growth, and through the environmental evaluation unit, compares and evaluates with the preset interference influence threshold Q to generate an environmental warning and put forward intervention suggestions to ensure the dynamic optimization of the vegetation growth environment; the spatial resolution optimization module collects multi-dimensional image data through high-resolution remote sensing image equipment and near-ground image sensors, and combines the image super-resolution processing technology to optimize the monitoring accuracy, eliminate the problem of detail loss caused by resolution differences, and generate a high-precision monitoring image with a unified resolution to realize the precise monitoring of small-scale vegetation changes;

[0087] The dynamic monitoring module calculates the vegetation health coefficient Vhc and conducts dynamic evaluation through the health calculation and evaluation unit based on the feature extraction of leaf area Vmj, vegetation coverage Vfg, photosynthetic efficiency Vgh, and vegetation canopy surface temperature Vgc, compares it with the preset vegetation health threshold W to determine the vegetation health status. If it is abnormal, it analyzes specific parameter problems and proposes optimization measures. At the same time, through the vegetation growth trend monitoring unit, it combines the dynamic data such as the vegetation photosynthetic volatility Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr collected by the sensor and the drone in cooperation to analyze the vegetation growth trend;

[0088] The growth trend prediction module calculates the growth cycle progress value Gcp through the growth trend calculation unit, compares it with the growth cycle progress threshold R, and the growth trend evaluation unit generates an evaluation of the vegetation growth state and predicts the future trend. If the growth cycle progress value Gcp is lower than the threshold R, it locates the interference cause and optimizes the management plan; through the dynamic collection, calculation, and evaluation of each lower-level parameter, the system can comprehensively grasp the vegetation growth state, accurately diagnose problems, and provide scientific intervention and management suggestions, which is an important basis for realizing the intelligent monitoring and optimized management of vegetation growth. Embodiment 4

[0089] The report generation module is used to comprehensively analyze the vegetation health coefficient Vhc and the growth cycle progress value Gcp, extract key evaluation contents, including health status classification, abnormal parameter indicators, and growth trend prediction; then, it automatically generates a vegetation growth trend monitoring report based on the analysis results; the content of the vegetation growth trend monitoring report includes the current vegetation health level, the comparison result of the growth progress, the specific location and possible reasons of the abnormal area, the predicted trend of the future growth state, and the intervention measures recommended by the system; then, the generated vegetation growth trend monitoring report is pushed to the environmental monitoring terminal and the user operation system through the cloud platform.

[0090] In this embodiment, the report generation module comprehensively analyzes the vegetation health coefficient Vhc and the growth cycle progress value Gcp, extracts key evaluation contents such as health status classification, abnormal parameter indicators, and growth trend prediction in an all-round way, and realizes the systematic summary and intuitive display of the vegetation growth status; through the automatically generated vegetation growth monitoring report, it covers the current vegetation health level, the comparison result of the growth progress, the specific location and possible reasons of the abnormal area, the prediction trend of the future growth state, and the intervention measures recommended by the system, providing users with a comprehensive and detailed decision-making reference; through the cloud platform, the monitoring report is pushed to the environmental monitoring terminal and the user operation system in real time, ensuring the efficient transmission and transparent management of the vegetation growth information; the significance of this module in the system is reflected in that through the closed-loop of data analysis and report generation, it improves the intelligent level and user experience of the system, enables the vegetation monitoring results to be presented in an intuitive and easy-to-understand form, quickly locates problems and puts forward optimization suggestions, ensuring that users can take scientific decision-making and management measures in a timely manner, and finally realizing the accurate control and dynamic optimization of the vegetation growth state. Embodiment 5

[0091] Please refer to Figure 2 , a method for monitoring vegetation growth data, comprising the following steps:

[0092] Step 1: Collect data related to the growth environment of vegetation, including historical meteorological data and historical soil monitoring data; at the same time, preprocess and uniformly format the data related to the growth environment from different sensors, and finally construct a data set related to the growth environment;

[0093] Step 2: Analyze the impact of the surrounding environment on the growth of vegetation, including meteorology, soil type and terrain, calculate the interference impact coefficient Eic of the surrounding environment on the vegetation growth based on the data set related to the growth environment, and evaluate it. Finally, issue a warning and conduct an intervention according to the evaluation content;

[0094] Step 3: Deploy remote sensing image equipment and image sensors around the vegetation to collect vegetation images, and obtain real-time multi-dimensional vegetation image data, including high-resolution remote sensing images and near-ground image sensor data. Then, perform image super-resolution processing on the multi-dimensional vegetation image data, and combine multi-angle data acquisition technology to adjust the spatial resolution of vegetation monitoring;

[0095] Step 4: Analyze the multi-dimensional vegetation image data collected by the remote sensing image equipment and the image sensors, calculate the vegetation health coefficient Vhc at the same time, and conduct dynamic evaluation; then, through the combination of sensors and drones, dynamically monitor the vegetation growth based on time series analysis, and collect real-time data related to the vegetation growth;

[0096] Step Five: Analyze the vegetation growth-related data collected and calculate the growth cycle progress value Gcp; by comparing it with the preset growth progress threshold R, predict the growth trend and future growth state of the vegetation to assist in decision-making.

[0097] Step Six: Receive and analyze the evaluation content of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time, then generate a vegetation growth monitoring report; finally, push the vegetation growth monitoring report to the environmental monitoring terminal and the user operating system through the cloud platform to provide decision support.

[0098] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vegetation growth data monitoring system, characterized in that: It includes data fusion and standardization module, environmental factor analysis module, spatial resolution optimization module, dynamic monitoring module, growth prediction module and report generation module; The data fusion and standardization module is used to collect data related to the growth environment of vegetation, including historical meteorological data and historical soil monitoring data; at the same time, the growth environment related data from different sensors are pre-processed and uniformly formatted, and finally a growth environment related data set is constructed; The environmental factor analysis module is used to analyze the impact of the surrounding environment on the growth of vegetation, including weather, soil type and terrain. Based on the data set related to the growth environment, the interference impact coefficient Eic of the surrounding environment on the growth of vegetation is calculated and evaluated. Finally, an early warning is issued and intervention is carried out according to the evaluation content. The environmental factor analysis module includes an environmental calculation unit and an environmental assessment unit; The environmental calculation unit is used to extract the lower parameters related to meteorology, soil type and terrain based on the growth environment related data set, including the temperature change amplitude Tva, soil moisture content Sfw, light intensity change rate Lir and terrain slope coefficient Tgc, and obtain the interference influence coefficient Eic by calculating the following formula: ； The spatial resolution optimization module is used to deploy remote sensing imaging equipment and image sensors around vegetation to collect vegetation images, obtain vegetation multi-dimensional image data in real time, including high-resolution remote sensing images and near-ground image sensor data, and then perform image super-resolution processing on the vegetation multi-dimensional image data, and adjust the spatial resolution of vegetation monitoring in combination with multi-angle data acquisition technology; The dynamic monitoring module is used to analyze the multi-dimensional image data of vegetation collected by remote sensing imaging equipment and image sensors, calculate the vegetation health coefficient Vhc, and perform dynamic evaluation; then, through the combination of sensors and drones, the vegetation growth is dynamically monitored based on time series analysis, and vegetation growth-related data is collected in real time; The dynamic monitoring module includes a health calculation and evaluation unit and a vegetation growth monitoring unit; The health calculation and evaluation unit analyzes the key growth parameters of vegetation, including leaf area Vmj, vegetation coverage Vfg, photosynthetic efficiency Vgh and vegetation canopy surface temperature Vgc, through a feature extraction algorithm based on the multi-dimensional vegetation image data collected by remote sensing imaging equipment and image sensors, and obtains the vegetation health coefficient Vhc by combining the following formula: ； The growth prediction module is used to analyze the collected vegetation growth-related data and calculate the growth cycle progress value Gcp; by comparing it with the preset growth progress threshold R, the growth trend and future growth status of the vegetation are predicted to assist in decision making; The growth potential prediction module includes a growth potential calculation unit and a growth potential evaluation unit; The growth potential calculation unit is used to extract the vegetation photosynthetic fluctuation rate Pvr, the stem thickening rate Scr, the root activity Rai and the canopy greenness change rate Cgr, and calculate the growth cycle progress value Gcp in combination with the following formula: ； The report generation module is used to receive and analyze the evaluation content of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time, and then generate a vegetation growth monitoring report; finally, the vegetation growth monitoring report is pushed to the environmental monitoring terminal and the user operating system through the cloud platform to provide decision support.

2. The vegetation growth data monitoring system according to claim 1, characterized in that: The data fusion and standardization module first monitors and collects vegetation growth environment related data in real time by deploying environmental sensors, remote sensing imaging equipment and ground acquisition terminals in the vegetation monitoring area; the growth environment related data also includes real-time meteorological data and real-time soil monitoring data; secondly, the growth environment related data collected from different sources are cleaned and denoised through a preprocessing step to remove redundant and invalid data; then unified formatting is performed to eliminate data inconsistencies caused by differences in device type, data format and timestamp through a standardized algorithm; finally, a growth environment related data set is constructed based on the growth environment related data generated after the formatting process.

3. The vegetation growth data monitoring system according to claim 2, characterized in that: The environmental assessment unit compares and evaluates the preset interference impact threshold Q with the interference impact coefficient Eic, issues an early warning and intervenes; the specific contents are as follows: If the interference impact coefficient Eic≤interference impact threshold Q, it means that the current surrounding environment is normal and there is no interference with the growth of vegetation or the interference is within an acceptable range. At this time, the current data is recorded and a "normal environment" status report is generated; If the interference impact coefficient Eic>interference impact threshold Q, it means that the current surrounding environment is abnormal and the interference to vegetation growth has exceeded the safe range. At this time, intervention measures are taken; including the system automatically generating early warning signals and pushing early warning signals to monitoring terminals and user devices.

4. The vegetation growth data monitoring system according to claim 3, characterized in that: The spatial resolution optimization module first deploys high-resolution remote sensing imaging equipment and near-ground image sensors in the vegetation monitoring area to collect multi-dimensional vegetation image data in the target area, wherein the remote sensing imaging equipment provides a large-scale overall image coverage, and the near-ground image sensor captures local high-precision image details; Secondly, image super-resolution processing technology is used for fusion to eliminate the problem of detail loss and blur caused by differences in data resolution. Subsequently, based on multi-angle data acquisition technology, the multi-dimensional image data of vegetation acquired at different times, angles and devices are integrated, and the spatial detail presentation of the target area is optimized through the angle fusion algorithm. Finally, the resolution of the fused multi-dimensional image data of vegetation is corrected and adjusted to generate a monitoring image with uniform resolution.

5. The vegetation growth data monitoring system according to claim 4, characterized in that: The health calculation and evaluation unit is also used to compare and evaluate the preset vegetation health threshold W with the vegetation health coefficient Vhc to generate the following content: If the vegetation health coefficient Vhc ≥ the vegetation health threshold W, it means that the vegetation growth state is in the healthy range. The system records the current state and marks it as "normal", and monitors the vegetation growth in real time. If the vegetation health coefficient Vhc is less than the vegetation health threshold W, it means that the vegetation growth state is abnormal. At this time, the specific cause of the abnormality should be further analyzed and corresponding measures should be taken.

6. The vegetation growth data monitoring system according to claim 5, characterized in that: The vegetation growth monitoring unit works in collaboration with drones by deploying sensors in the vegetation monitoring area. The sensors are used to collect ground growth environment data in real time, while the drones are equipped with multispectral imaging equipment to perform periodic image scanning of the target area to capture multi-dimensional growth image data of the vegetation. The ground growth environment data and the multi-dimensional growth image data are then uploaded to the monitoring platform synchronously. The dynamic change trends of the continuous ground growth environment data and the multi-dimensional growth image data are analyzed based on time series analysis technology to extract vegetation growth-related data, including vegetation photosynthetic fluctuation rate Pvr, stem thickening rate Scr, root activity Rai, and canopy greenness change rate Cgr.

7. The vegetation growth data monitoring system according to claim 1, characterized in that: The growth potential assessment unit compares and assesses the preset growth cycle progress threshold R with the growth cycle progress value Gcp to generate the following assessment content: If the growth cycle progress value Gcp≥growth cycle progress threshold R, it means that the growth cycle progress of the vegetation is normal or ahead of schedule; the system marks it as "normal" and records the progress data for subsequent analysis; If the growth cycle progress value Gcp is less than the growth cycle progress threshold R, it means that the growth cycle progress of the vegetation lags behind expectations and there are problems of environmental impact or insufficient management; the system marks it as "abnormal" and further evaluates the causes of the disturbance, including abnormal photosynthesis efficiency, abnormal soil nutrients, abnormal root development, and canopy damage.

8. The vegetation growth data monitoring system according to claim 7, characterized in that: The report generation module is used to conduct a comprehensive analysis of the vegetation health coefficient Vhc and the growth cycle progress value Gcp, and extract key evaluation contents, including health status classification, abnormal parameter indicators and growth trend prediction; Subsequently, a vegetation growth monitoring report is automatically generated based on the analysis results; the content of the vegetation growth monitoring report includes the current vegetation health level, growth progress comparison results, the specific location and possible causes of abnormal areas, future growth status prediction trends and intervention measures recommended by the system; the generated vegetation growth monitoring report is then pushed to the environmental monitoring terminal and user operating system through the cloud platform.

9. A vegetation growth data monitoring method, applied to a vegetation growth data monitoring system according to any one of claims 1 to 8, characterized in that: The following steps are involved: Step 1: Collect data related to the vegetation growth environment, including historical meteorological data and historical soil monitoring data; at the same time, pre-process and uniformly format the growth environment data from different sensors, and finally construct a growth environment related data set; Step 2: Analyze the impact of the surrounding environment on the growth of vegetation, including weather, soil type and terrain. Based on the data set related to the growth environment, calculate and evaluate the interference coefficient Eic of the surrounding environment on the growth of vegetation. Finally, issue an early warning and intervene based on the evaluation content. Step 3: Deploy remote sensing imaging equipment and image sensors around vegetation to collect vegetation images, and obtain vegetation multi-dimensional image data in real time, including high-resolution remote sensing images and near-ground image sensor data. Then, perform image super-resolution processing on the vegetation multi-dimensional image data, and adjust the spatial resolution of vegetation monitoring by combining multi-angle data acquisition technology. Step 4: Analyze the multi-dimensional image data of vegetation collected by remote sensing imaging equipment and image sensors, calculate the vegetation health coefficient Vhc, and conduct dynamic evaluation; then, through the combination of sensors and drones, dynamically monitor the growth of vegetation based on time series analysis, and collect relevant data on vegetation growth in real time; Step 5: Analyze the collected vegetation growth-related data and calculate the growth cycle progress value Gcp; by comparing it with the preset growth progress threshold R, predict the growth trend and future growth status of the vegetation to assist in decision-making; Step 6: Receive and analyze the evaluation contents of the vegetation health coefficient Vhc and the growth cycle progress value Gcp in real time, and then generate a vegetation growth monitoring report; finally, push the vegetation growth monitoring report to the environmental monitoring terminal and the user operating system through the cloud platform to provide decision support.

Images