Meadow steppe satellite remote sensing intelligent monitoring system based on sky-ground integration

Abstract

The invention discloses a meadow steppe satellite remote sensing intelligent monitoring system based on sky-ground integration, and relates to the technical field of remote sensing monitoring, and the system comprises an environment perception judgment module which is used for obtaining meteorological data and grassland health state data in real time, analyzing the influence of environment change on the monitoring precision, and sending the monitoring result to a satellite remote sensing module; and a data acquisition mode is intelligently adjusted according to an analysis result, and a monitoring mode suitable for the current environmental condition is preferentially selected. According to the meadow steppe satellite remote sensing intelligent monitoring system based on sky-ground integration, through intelligent fusion of multiple data sources, environment adaptive adjustment, dynamic resource optimization and an abnormal data restoration mechanism, the ecological monitoring precision and efficiency in a meadow steppe complex environment are significantly improved; particularly, the defects of the traditional remote sensing technology on the limitation of resolution and precision are overcome in the aspects of dealing with the monitoring requirements of grassland ecosystem detail analysis, local change monitoring and complex meteorological conditions.

Description

Technical Field

[0001] The invention relates to the technical field of remote sensing monitoring, and in particular to a meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration. Background Art

[0002] Although existing satellite remote sensing technology can provide a wide range of monitoring capabilities, especially in wide-area environments, it still faces some technical challenges in grassland ecological monitoring. First, the spatial resolution of satellite remote sensing is low, and it is usually unable to capture the detailed changes in grassland ecosystems, especially in areas with complex terrain and diverse vegetation types such as meadow grasslands. For example, small-scale ecological changes in grasslands, such as different grass species, vegetation density, and soil moisture, are often not accurately reflected by low-resolution remote sensing images. In addition, the spectral resolution of satellite remote sensing is limited, and it is difficult to distinguish between similar vegetation types or vegetation differences at different growth stages. This makes the assessment of grassland health status inaccurate and cannot meet the needs of detailed ecological management. On the other hand, meadow grasslands are usually located in complex terrain areas such as mountains and hills, and have diverse vegetation cover types, such as shrubs, grasslands, wetlands, etc. The performance of these different types of objects in remote sensing images may be affected by factors such as shadows, occlusions, and environmental interference, thereby reducing the accuracy of remote sensing technology in these areas. In addition, the ecological changes in grasslands are often characterized by localization and short-term fluctuations, and existing satellite remote sensing technology is difficult to provide a high enough temporal resolution to capture these subtle changes.

[0003] Therefore, although satellite remote sensing technology has its unique advantages in grassland ecological monitoring, such as large-scale coverage and real-time data collection capabilities, its spatial and spectral resolution limitations make it difficult to conduct detailed monitoring and accurate assessment of ecological changes in complex environments such as meadow steppes. This requires further technological innovation and multi-source data fusion to improve the accuracy and operability of monitoring. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the existing technology, the present invention provides a meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration, which solves the limitations of the spatial and spectral resolution of satellite remote sensing technology, making it difficult to carry out detailed monitoring and accurate assessment of ecological changes in complex environments such as meadow grasslands.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a satellite remote sensing intelligent monitoring system for meadow grassland based on sky-ground integration, including: an environmental perception and judgment module, which is used to obtain meteorological data and grassland health status data in real time, analyze the impact of environmental changes on monitoring accuracy, and intelligently adjust the data collection mode according to the analysis results, and give priority to the monitoring mode suitable for the current environmental conditions; Data collaborative management module, which is used to dynamically schedule satellite remote sensing, drone imagery, and ground sensor data sources according to real-time environmental status and equipment working status, and optimize their collection strategies to ensure coverage and data accuracy of the monitoring area; The data processing module is used to perform weighted fusion of monitoring data from different data sources, and generate a unified data set by combining the resolution, sampling frequency, and spatial distribution of each data source. It is also used to repair data loss, noise, or abnormal data, and adopt interpolation algorithms or multi-source data compensation technology to improve data integrity and accuracy. The data processing module is used to fuse, clean, repair, and enhance the raw data from different data sources to ensure that the final output data meets the required standards in terms of resolution and accuracy. The decision-making response module is used to automatically make decisions and take emergency response measures based on real-time data and system status to deal with emergencies and ensure the smooth execution of monitoring tasks; The resource monitoring module is used to monitor the working status, battery power, and communication quality of each sensor in real time. When the monitoring equipment fails or its performance degrades, it automatically notifies the management personnel and performs corresponding maintenance or replacement operations.

[0006] Preferably, the environment perception judgment module includes: A meteorological data analysis module is used to obtain and analyze meteorological data, including precipitation, temperature, wind speed, and humidity, to assess their potential impact on data collection accuracy and automatically adjust monitoring strategies; The vegetation status judgment module is used to monitor the growth indicators of the grassland in real time, including greening degree, grass height, and grassland density, to evaluate the health status of the grassland and adjust the monitoring method when abnormalities occur.

[0007] Preferably, the use process of the meteorological data analysis module is as follows: first, real-time meteorological data is collected from multiple meteorological sources, including meteorological stations, satellites, and meteorological models. The real-time meteorological data includes precipitation, temperature, wind speed, and humidity. For precipitation, when the precipitation is high, the error of ground sensors will increase, affecting the health monitoring of grasslands; the system will adjust the data collection strategy according to the change of precipitation to reduce the ground data collection tasks affected by the weather; for temperature, extreme temperatures, including high or low temperatures, will affect the growth of grasslands, and temperature changes may also affect the accuracy of remote sensing data from satellites or drones; the system will evaluate the temperature The impact on monitoring accuracy, and satellite remote sensing or high-altitude drones are given priority; for wind speed, under high wind speed conditions, the flight stability of the drone may be affected. The system will automatically adjust the drone's monitoring tasks according to the wind speed and select a more stable monitoring method; for humidity, when the humidity is too high, it affects the performance of the sensor, especially the battery and communication quality. The system will adjust the monitoring frequency or switch the data collection method; based on the analysis of meteorological data, the meteorological data analysis module will automatically adjust the monitoring strategy, that is, the data collection strategy; if environmental factors are not conducive to data collection, reduce the monitoring of the area or time period, or use satellite remote sensing or drones.

[0008] Preferably, the use process of the vegetation status judgment module is as follows: first, the growth index data of the grassland are collected through different data sources, including satellite remote sensing, drone images, and ground sensors, and the growth index data include greening degree, grass height, and grassland density; wherein, greening degree is the green coverage degree of grassland, which is used to judge the growth condition of grassland, grass height reflects the growth height of grassland vegetation, and is an important indicator of grassland health, and grassland density reflects the vegetation coverage degree of grassland, and high-density grassland usually means a better ecological environment; according to the collected growth index data, the health status of the grassland is analyzed, and if the health status of the grassland is found to be abnormal, including too low grass height, decreased greening degree, and uneven grassland density, adjustments will be made automatically, including monitoring method adjustment, data collection frequency adjustment, and emergency response in abnormal situations; wherein, for the monitoring method, Adjustment of the method: If the grassland health shows regional grassland decline, pests and diseases, increase the monitoring frequency of the region, or adjust the monitoring methods to obtain more accurate data; including increasing the use of ground sensors and reducing reliance on satellite remote sensing data to ensure that details can be captured; adjustment of data collection frequency: when the grassland health is good, reduce the data collection frequency to reduce the consumption of monitoring resources; when the grassland health is abnormal, increase the data collection frequency to ensure timely detection of problems; emergency response to abnormal situations: when serious grassland health problems are found, including large-scale grassland withering, pests and diseases, the vegetation status judgment module will work together with the decision response module to trigger an emergency response; including: automatically adjust the monitoring area and enable more drones or ground sensors to conduct high-density monitoring of abnormal areas.

[0009] Preferably, the data collaborative management module includes a resource scheduling module, which dynamically adjusts the collection priority of the data source according to the real-time meteorological conditions and the changes in the grassland growth status, and selects the most appropriate data source for data collection.

[0010] Preferably, the resource scheduling module dynamically adjusts the collection priority of the data source according to the changes in the real-time meteorological conditions and the growth status of the grassland, and the process of selecting the most suitable data source for data collection includes: first, obtaining meteorological data and grassland growth status data in real time, and then evaluating the applicability of different data sources according to the meteorological data to obtain the evaluation results of the real-time meteorological conditions, including: severe weather such as strong winds and heavy precipitation will affect the flight stability of the UAV and the effectiveness of the ground sensors, and satellite remote sensing data is preferred for monitoring; under clear or stable meteorological conditions, the accuracy of the UAV data and the ground sensor data is high, and the data sources of the UAV and the ground sensors are preferred for local fine monitoring; then the applicability of the data source is evaluated according to the grassland growth status data to obtain the evaluation results of the grassland growth status, including: when the grassland grows vigorously, satellite remote sensing and UAVs perform large-scale and high-resolution monitoring, and satellite remote sensing and UAV data are used preferentially; when the grassland growth is affected by drought or frost damage, the high-precision data provided by the ground sensors is more important, and the ground sensors are used preferentially at this time; According to the evaluation results of real-time meteorological conditions and grassland growth status, the collection priority of each data source is dynamically adjusted; the process is: when the meteorological conditions are bad, including too high wind speed or too much precipitation, satellite remote sensing data is selected because it is not affected by ground weather and can provide large-scale monitoring; when the meteorological conditions are good, including under conditions such as moderate wind speed and no precipitation, drones and ground sensors are selected for obtaining high-precision data; in the grassland growth state, when the grassland is growing healthily, satellite remote sensing and drone data are preferred, which have wide coverage and high resolution and are suitable for comprehensive monitoring; when the grassland is limited in growth, growth status data obtained by ground sensors is preferred; Then, according to the adjusted priority, the data source is dynamically scheduled to obtain the scheduling result; the scheduling process includes: based on the fact that satellite remote sensing is suitable for large-scale monitoring, ground sensors are suitable for detailed local data collection, and according to the weather and grassland growth status, the applicable data source is prioritized for data collection; at the same time, when the grassland is growing vigorously or the weather conditions are stable, the frequency of data collection is increased; when the environment is harsh, the frequency of collection is reduced to ensure the key coverage of the monitoring area; Finally, according to the scheduling results, the data collection task is executed to ensure comprehensive coverage of the monitoring area and high accuracy of the data. When equipment fails or the data source is unavailable, the system will automatically switch to the backup data source to ensure the smooth progress of the monitoring task.

[0011] Preferably, the decision response module includes: The logic judgment module is used to automatically evaluate the current monitoring needs based on the real-time collected data and environmental status analysis, generate corresponding collection strategies, and adjust the collection frequency and area of ​​the data source; The emergency response module is used to automatically enable backup equipment or sensors and adjust the monitoring area and data collection strategy when the system detects an emergency, including equipment failure, abnormal climate, and loss of sensor data, to ensure that the monitoring task is not affected.

[0012] Preferably, the logic judgment module is used to automatically evaluate the current monitoring needs based on the real-time collected data and environmental status analysis, generate corresponding collection strategies, and adjust the collection frequency and area of ​​the data source. The process includes: real-time collection of data from multiple sources to obtain real-time collected data, including meteorological data, grassland growth status data, and monitoring equipment status data; meteorological data includes temperature, humidity, wind speed, and precipitation; grassland growth status data includes greening degree, grass height, and grassland density; monitoring equipment status data includes sensor battery power, communication quality, and equipment failure status; the environmental perception judgment module evaluates the current meteorological conditions and grassland growth status, performs preliminary analysis based on the real-time collected data, and determines the monitoring needs; The analysis results are obtained based on the real-time collected data. The process is as follows: Analyze the impact of precipitation and wind speed in the current meteorological conditions on the monitoring task; including: in heavy rain or high wind weather, the drone cannot work normally, and the frequency of satellite remote sensing data collection needs to be increased; when the meteorological conditions are stable, the drone performs high-precision monitoring and the frequency of drone data collection is increased; according to the greening degree and grass height of the grassland growth conditions, the monitoring needs are judged, including: when the grassland grows vigorously, large-scale monitoring is carried out through satellite remote sensing and drones, and the frequency of ground sensor data collection is reduced; when the grassland growth is affected by drought and frost, the frequency of ground sensor data collection is increased first to obtain higher-precision local data; check the working status of the equipment in real time, including battery power and communication quality, to ensure that the equipment is running well; if equipment failure or performance degradation is found, adjust the monitoring strategy and enable backup equipment; Based on monitoring needs and analysis results, the corresponding collection strategies are automatically generated, including: automatically adjusting the priority of data sources according to weather and grassland growth status; including: giving priority to satellite remote sensing data under unfavorable weather conditions, and giving priority to drones for detailed monitoring when grasslands are growing vigorously; automatically adjusting the collection frequency according to real-time analysis results, including: if the grassland growth status changes significantly, then increase the monitoring frequency of the area, and when weather conditions are unstable, reduce reliance on high-frequency data collection and give priority to low-frequency data collection; Optimize the spatial area of ​​data collection according to environmental changes and monitoring needs, including: areas with dense grassland growth need more frequent and detailed monitoring, and under abnormal meteorological conditions, monitoring needs to be focused on local areas, especially where abnormal phenomena occur; In the event of sudden equipment failure, data loss, or extreme weather changes, the logic judgment module will respond immediately and automatically adjust according to the preset emergency response rules to obtain adjustment results, including: enabling backup equipment and adjusting collection strategies; if the main equipment is found to be unable to work normally, the system will automatically enable backup equipment or data sources; when the grassland growth state changes dramatically or weather conditions change suddenly, the system will adjust the collection area and frequency in real time to cope with sudden environmental changes and ensure that the monitoring task is not affected.

[0013] The monitoring method of the meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration includes the following steps: a: Obtain meteorological data and grassland growth status data in real time, analyze and evaluate environmental impacts through the environmental perception and judgment module, and generate data collection strategies; b: According to the real-time environment and equipment status, the data sources of satellite remote sensing, drone images and ground sensors are dispatched through the data collaborative management module to ensure optimal resource allocation; c: Transmit the collected data to the data processing module to fuse, repair and enhance the data to improve data accuracy and reliability; d: Monitor the system status in real time through the decision response module, automatically adjust the data collection mode according to logical judgment, and initiate emergency response measures when failures or abnormalities occur.

[0014] Preferably, the scheduling strategy in step 2 includes: automatically selecting the most appropriate monitoring method according to meteorological data, grassland growth status and equipment status, and dynamically adjusting the data collection frequency and area; the data processing in step 3 includes: weighted fusion of satellite remote sensing, drone imagery and ground sensor data, using data repair algorithms to fill in missing data, and using enhancement algorithms to improve data resolution and accuracy; the emergency response measures in step 4 include: enabling backup sensors, adjusting monitoring areas and data collection strategies, and automatically notifying management personnel to repair or replace equipment when it fails.

[0015] (III) Beneficial effects The present invention provides a meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration. It has the following beneficial effects: (I) The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration has significantly improved the accuracy and efficiency of ecological monitoring in complex meadow grassland environments through intelligent fusion of multiple data sources, environmental adaptive adjustment, dynamic resource optimization and abnormal data repair mechanism. In particular, it has made up for the shortcomings of traditional remote sensing technology in terms of resolution and accuracy limitations in responding to the needs of detailed analysis of grassland ecosystems, local change monitoring and monitoring under complex meteorological conditions.

[0016] (2) The meadow grassland satellite remote sensing intelligent monitoring system based on the integration of sky and ground can obtain meteorological data in real time and analyze its impact on data collection through the environmental perception and judgment module, and intelligently adjust the monitoring strategy. It can dynamically adjust the data collection method according to the real-time meteorological conditions and grassland growth conditions. It can automatically select the best monitoring method and collection frequency according to meteorological conditions, grassland health and equipment status, so as to ensure that grassland ecological changes can be accurately captured in different environments, avoiding the problem that traditional technologies cannot handle complex meteorological conditions and environmental changes.

[0017] (3) The meadow grassland satellite remote sensing intelligent monitoring system based on the integration of sky and ground, through the data collaborative management module, combines meteorological data, grassland health status and equipment working status, dynamically optimizes the selection of data sources and resource scheduling, to ensure accurate coverage of the monitoring area. When the grassland health status is abnormal, the system can automatically increase the monitoring frequency of the area, enable more drones and ground sensors, and conduct high-precision local monitoring. When the meteorological conditions are poor or the equipment fails, the system will automatically select the most suitable backup equipment to ensure that the monitoring task is not affected. This adaptive scheduling enables the monitoring system to always maintain efficient operation under complex and changing environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the framework of the meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration; Figure 2 The figure is a flow chart of the meadow grassland satellite remote sensing intelligent monitoring method of the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] See also Figure 1 and Figure 2The present invention provides a technical solution: a meadow grassland satellite remote sensing intelligent monitoring method based on sky-ground integration, comprising the following steps: a: Obtain meteorological data and grassland growth status data in real time, analyze and evaluate environmental impacts through the environmental perception and judgment module, and generate data collection strategies; b: According to the real-time environment and equipment status, the data sources of satellite remote sensing, drone images and ground sensors are dispatched through the data collaborative management module to ensure optimal resource allocation; c: Transmit the collected data to the data processing module to fuse, repair and enhance the data to improve data accuracy and reliability; d: Monitor the system status in real time through the decision response module, automatically adjust the data collection mode according to logical judgment, and initiate emergency response measures when failures or abnormalities occur.

[0021] The scheduling strategy in step 2 includes: automatically selecting the most appropriate monitoring method based on meteorological data, grassland growth status and equipment status, and dynamically adjusting the data collection frequency and area; the data processing in step 3 includes: weighted fusion of satellite remote sensing, drone imagery and ground sensor data, using data repair algorithms to fill in missing data, and using enhancement algorithms to improve data resolution and accuracy; the emergency response measures in step 4 include: enabling backup sensors, adjusting monitoring areas and data collection strategies, and automatically notifying management personnel to repair or replace equipment when it fails.

[0022] See also Figure 1 The present invention provides a technical solution: a meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration, including: Environmental perception and judgment module, used to obtain meteorological data and grassland health status data in real time, analyze the impact of environmental changes on monitoring accuracy, and intelligently adjust the data collection mode according to the analysis results, giving priority to the monitoring method suitable for the current environmental conditions; Data collaborative management module, which is used to dynamically schedule satellite remote sensing, drone imagery, and ground sensor data sources according to real-time environmental status and equipment working status, and optimize their collection strategies to ensure coverage and data accuracy of the monitoring area; The data processing module is used to perform weighted fusion of monitoring data from different data sources, and generate a unified data set by combining the resolution, sampling frequency, and spatial distribution of each data source. It is also used to repair data loss, noise, or abnormal data, and adopt interpolation algorithms or multi-source data compensation technology to improve data integrity and accuracy. The data processing module is used to fuse, clean, repair, and enhance the raw data from different data sources to ensure that the final output data meets the required standards in terms of resolution and accuracy. The decision-making response module is used to automatically make decisions and take emergency response measures based on real-time data and system status to deal with emergencies and ensure the smooth execution of monitoring tasks; The resource monitoring module is used to monitor the working status, battery power, and communication quality of each sensor in real time. When the monitoring equipment fails or its performance degrades, it automatically notifies the management personnel and performs corresponding maintenance or replacement operations.

[0023] Among them, the environmental perception and judgment module includes a meteorological data analysis module and a vegetation status judgment module; the meteorological data analysis module is used to obtain and analyze meteorological data, which include precipitation, temperature, wind speed, and humidity, to evaluate their potential impact on data collection accuracy and automatically adjust the monitoring strategy; the vegetation status judgment module is used to monitor the growth indicators of the grassland in real time, including greening degree, grass height, and grassland density, to evaluate the health of the grassland and adjust the monitoring method when abnormalities occur.

[0024] It should be further explained that in the specific implementation process, the use process of the meteorological data analysis module is as follows: first, real-time meteorological data is collected from multiple meteorological sources, including meteorological stations, satellites, and meteorological models. Real-time meteorological data includes precipitation, temperature, wind speed, and humidity. For precipitation, when precipitation is high, it will cause the error of ground sensors to increase, affecting the health monitoring of grasslands; the system will adjust the data collection strategy according to the change of precipitation to reduce the ground data collection tasks affected by weather; for temperature, extreme temperatures, including high or low temperatures, will affect the growth of grasslands, and temperature changes may also affect the accuracy of remote sensing data from satellites or drones; The system will evaluate the impact of temperature on monitoring accuracy and give priority to satellite remote sensing or high-altitude drones; for wind speed, the flight stability of the drone may be affected under high wind speed conditions. The system will automatically adjust the drone's monitoring tasks according to the wind speed and select a more stable monitoring method; for humidity, when the humidity is too high, it affects the performance of the sensor, especially the battery and communication quality. The system will adjust the monitoring frequency or switch the data collection method; based on the analysis of meteorological data, the meteorological data analysis module will automatically adjust the monitoring strategy, that is, the data collection strategy; if environmental factors are not conducive to data collection, the monitoring of the area or time period will be reduced, or satellite remote sensing or drones will be used.

[0025] It needs to be further explained that in the specific implementation process, the vegetation status judgment module is used as follows: first, through different data sources, including satellite remote sensing, drone images, and ground sensors, grassland growth index data are collected. The growth index data include greening degree, grass height, and grassland density; among them, greening degree is the green coverage of grassland, which is used to judge the growth status of grassland. Grass height reflects the growth height of grassland vegetation and is an important indicator of grassland health. Grass density reflects the vegetation coverage of grassland. High-density grassland usually means a better ecological environment; according to the collected growth index data, the health status of grassland is analyzed. If the health status of grassland is found to be abnormal, including too low grass height, decreased greening degree, and uneven grassland density, adjustments will be made automatically, including monitoring method adjustment, data collection frequency adjustment, and emergency response in abnormal situations; among them , for the adjustment of monitoring methods: if the grassland health shows regional grassland decline, pests and diseases, the monitoring frequency of the region will be increased, or the monitoring methods will be adjusted to obtain more accurate data; including increasing the use of ground sensors and reducing reliance on satellite remote sensing data to ensure that details can be captured; for the adjustment of data collection frequency: when the grassland health is good, reduce the frequency of data collection to reduce the consumption of monitoring resources; and when the grassland health is abnormal, increase the frequency of data collection to ensure timely detection of problems; for emergency response in abnormal situations: when serious grassland health problems are found, including large-scale grassland withering, pests and diseases, the vegetation status judgment module will work together with the decision response module to trigger an emergency response; including: automatically adjusting the monitoring area and enabling more drones or ground sensors to conduct high-density monitoring of abnormal areas.

[0026] The calculation formula of the meteorological data analysis module is: ; Among them, Sadjusted is the adjusted monitoring strategy, indicating the monitoring means to be selected and the adjusted collection frequency, which can be a specific strategy code or adjustment parameter; T is the real-time temperature (unit: °C), P is the real-time precipitation (unit: mm / h), W is the real-time wind speed (unit: m / s), and H is the real-time humidity (unit: %); : are weight coefficients related to temperature, precipitation, wind speed and humidity, respectively, and their sum is 1, indicating the influence of each meteorological factor in the adjustment strategy; : are the influence functions of temperature, precipitation, wind speed and humidity, indicating the influence of each meteorological factor on the monitoring accuracy; Among them, the temperature influence function : ; The optimal temperature range is 20°C to 30°C, and data collection is not affected; if it is lower than 5°C or higher than 35°C, the temperature is too low or too high. At this time, the monitoring accuracy may be affected and the weight needs to be reduced; if the temperature is lower than -10°C or higher than 40°C, the temperature is too extreme and you should choose to adjust the monitoring method or stop collecting data; Precipitation impact function : ; When the precipitation is between 0 and 5 mm / h, it is low precipitation, and data collection is not affected. When the precipitation is between 5 and 20 mm / h or exceeds 20 mm / h, it is too high. At this time, the accuracy of ground sensors may be impaired, and the system will reduce their use and give priority to satellite remote sensing. Wind speed effect function : ; When the wind speed is between 0 and 5 m / s, the wind speed is low and data collection is not affected. When the wind speed is between 5 and 10 m / s or exceeds 10 m / s, the wind speed is too high and will affect the flight stability of the drone. Therefore, reduce the use of the drone and choose other methods. Humidity influence function : ; When the humidity is within the appropriate range of 40% to 70%, data collection is not affected; when the humidity is between 70% and 90% or exceeds 90%, the humidity is too high. At this time, the humidity affects the performance of the ground sensor. The system will reduce the frequency of ground sensor collection and give priority to remote sensing data. Real-time acquisition of meteorological data: The system obtains meteorological data in real time through various sensors: temperature T=28°C, precipitation P=12 mm / h, wind speed W=8 m / s, humidity H=78%; Calculate each influence function: f T (28) = 1 (temperature is within the appropriate range), f P (12) = 0.5 (precipitation is in the medium range), f W (8) = 0.5 (wind speed in the medium range), f H (78) = 0.5 (humidity is high); Calculate the adjusted strategy based on the actual weight coefficient: Let w T =0.3, w P =0.2, w W =0.2, w H =0.3, then: S adjusted=0.3×1+0.2×0.5+0.2×0.5+0.3×0.5=0.3+0.1+0.1+0.15=0.65; S adjusted =0.65 means that the system will choose a relatively balanced monitoring strategy, that is, giving priority to the use of satellite remote sensing and drones, increasing the frequency of data collection, but reducing the frequency of using ground sensors.

[0027] S adjusted The specific meaning is determined by the policy mapping table set as follows:

[0028] The system receives meteorological data (temperature, humidity, wind speed, precipitation) in real time and calculates S through meteorological data analysis functions. adjusted According to S adjusted The system queries the strategy mapping table to obtain the corresponding monitoring plan. Based on the results of the mapping table, the system will automatically configure the monitoring strategy, including data collection frequency, sensor selection, and optimized resource allocation: Data collection frequency: increase or decrease the data collection frequency of satellites, drones, and ground sensors; Sensor selection: automatically choose whether to enable specific sensors based on meteorological conditions, such as giving priority to satellite remote sensing and remote monitoring technology in severe weather, and reducing the use of ground sensors; Optimize resource allocation: the system will dynamically adjust the allocation of monitoring resources to ensure that monitoring work is not affected under different meteorological conditions.

[0029] If S adjusted =0.65, the system will choose the conventional monitoring scheme, which means that all sensors can be used for monitoring at a moderate frequency. Specifically, the equipment used includes satellite remote sensing, ground sensors, and drones; the data collection frequency is moderate to ensure the timeliness and quality of the monitoring data; according to the wind speed and precipitation in the specific weather conditions, satellite remote sensing and ground sensors are given priority for high-frequency monitoring; when the meteorological conditions change, the system will recalculate S adjusted , and adjust the monitoring scheme according to the new mapping value.

[0030] The data collaborative management module includes a resource scheduling module, which dynamically adjusts the data source collection priority according to the changes in real-time meteorological conditions and grassland growth status, and selects the most appropriate data source for data collection. The process includes: first, obtaining meteorological data and grassland growth status data in real time, and then evaluating the applicability of different data sources based on the meteorological data to obtain the evaluation results of real-time meteorological conditions, including: severe weather such as strong winds and heavy precipitation will affect the flight stability of drones and the effectiveness of ground sensors, and satellite remote sensing data is preferred for monitoring; under clear or stable meteorological conditions, the accuracy of drone data and ground sensor data is high, and drone and ground sensor data sources are preferred for local fine monitoring; then, the applicability of the data source is evaluated based on the grassland growth status data, and the evaluation results of grassland growth status are obtained, including: when grasslands grow vigorously, satellite remote sensing and drones conduct large-scale and high-resolution monitoring, and satellite remote sensing and drone data are used first; when grassland growth is affected by drought or frost damage, the high-precision data provided by ground sensors is more important, and ground sensors are used first at this time; According to the evaluation results of real-time meteorological conditions and grassland growth status, the collection priority of each data source is dynamically adjusted; the process is: when the meteorological conditions are bad, including too high wind speed or too much precipitation, satellite remote sensing data is selected because it is not affected by ground weather and can provide large-scale monitoring; when the meteorological conditions are good, including under conditions such as moderate wind speed and no precipitation, drones and ground sensors are selected for obtaining high-precision data; in the grassland growth state, when the grassland is growing healthily, satellite remote sensing and drone data are preferred, which have wide coverage and high resolution and are suitable for comprehensive monitoring; when the grassland is limited in growth, growth status data obtained by ground sensors is preferred; Then, according to the adjusted priority, the data source is dynamically scheduled to obtain the scheduling result; the scheduling process includes: based on the fact that satellite remote sensing is suitable for large-scale monitoring, ground sensors are suitable for detailed local data collection, and according to the weather and grassland growth status, the applicable data source is prioritized for data collection; at the same time, when the grassland is growing vigorously or the weather conditions are stable, the frequency of data collection is increased; when the environment is harsh, the frequency of collection is reduced to ensure the key coverage of the monitoring area; Finally, according to the scheduling results, the data collection task is executed to ensure the comprehensive coverage of the monitoring area and the high accuracy of the data. When the equipment fails or the data source is unavailable, the system will automatically switch to the backup data source to ensure the smooth progress of the monitoring task; The process of generating a unified data set by the data processing module includes: receiving monitoring data from different data sources in real time, wherein each data source provides different types of data, including satellite remote sensing data, drone data and ground sensor data, wherein satellite remote sensing data is a remote sensing image of a large area, usually with a large spatial coverage range, but with low resolution; drone data is a high-resolution local area image, suitable for fine monitoring, but with a small coverage range; ground sensor data is real-time acquisition of physical parameters, including temperature, humidity, and soil moisture, usually providing high-precision local data, but with limited coverage; performing quality assessment on the different data sources received to obtain quality assessment results, wherein the quality assessment content includes: assessing the size of the coverage area of ​​each data source, determining which data sources are suitable for filling the vacant areas of the data source, and obtaining the coverage range; comparing the spatial resolution of each data source, identifying the difference in precision between the data sources, ensuring that the appropriate data source is used for fine monitoring, and obtaining the resolution; assessing the data accuracy of each data source according to the specific monitoring objectives, and obtaining the accuracy requirements; and then, based on the quality assessment results of each data source, The specific steps of weighted fusion are as follows: first, the weight of each data source is calculated according to the coverage, resolution and accuracy requirements of the data source; generally speaking: data sources with a larger coverage, that is, satellite remote sensing, have a lower weight because their resolution is lower; drone data with higher resolution has a higher weight and is suitable for supplementing more detailed local data; ground sensor data with higher accuracy has a higher weight and is used to supplement or correct data missing or errors in other data sources; then, different data sources are weightedly fused according to the weights, and Kalman filtering is used for data fusion to finally generate a unified data set; the fused data is denoised and repaired, data standardized, and accuracy improved, including: for denoising and repair, interpolation algorithms and multi-source data compensation technology are used to repair the noise or missing parts in the fused data to ensure data integrity; for data standardization, the fused data is standardized to ensure that the data from different data sources have consistent scales and units, which is convenient for subsequent analysis and decision-making; for accuracy improvement, super-resolution reconstruction is used to improve the resolution and accuracy of the data to improve the quality of the final output data.

[0031] The formula for weighted data fusion is as follows: ; in, is the final dataset after fusion. The data provided by the i-th data source, is the weight of the i-th data source, reflecting the trust, accuracy and applicability of the data source; is the total number of data sources; Assume three data sources: satellite remote sensing data D 1，Weight w1=0.3; UAV data D 2， Weight w2=0.5; ground sensor data D 3， The weight w3=0.2; these three data sources provide grassland greenness in the same area, and the grassland greenness is between 0-100, then D1=70, D2=85, D3=75, according to the weighted fusion formula: =78.5; that is, the fused result, which represents the overall assessment value of the greenness of the grassland in the area. This value combines the advantages of various data sources and adjusts the weights of the quality and accuracy of different data sources; the fused greenness value is used to assess the health of the grassland. If the value is lower than the preset greenness threshold, the system can automatically trigger an emergency response, increase the monitoring frequency of the area, or enable different monitoring methods; the decision response module can adjust the collection strategy based on the fused data. If the greenness of the area drops sharply, more drones or ground sensors will be mobilized for local refined monitoring.

[0032] The decision response module includes a logic judgment module and an emergency response module. The logic judgment module is used to automatically evaluate the current monitoring needs based on real-time collected data and environmental status analysis, generate corresponding collection strategies, and adjust the collection frequency and area of ​​the data source; the emergency response module is used to automatically enable backup equipment or sensors when the system detects an emergency, including equipment failure, abnormal climate, and sensor data loss, and adjust the monitoring area and data collection strategy to ensure that the monitoring task is not affected.

[0033] Among them, the logic judgment module automatically evaluates the current monitoring needs based on the real-time collected data and environmental status analysis, generates the corresponding collection strategy, and adjusts the collection frequency and area of ​​the data source. The process includes: real-time collection of data from multiple sources to obtain real-time collected data, including meteorological data, grassland growth status data and monitoring equipment status data; meteorological data include temperature, humidity, wind speed, precipitation, grassland growth status data include greening degree, grass height, grassland density, monitoring equipment status data include sensor battery power, communication quality, equipment failure status; environmental perception judgment module evaluates the current meteorological conditions and grassland growth status, conducts preliminary analysis based on real-time collected data, and determines monitoring needs; analyzes based on real-time collected data to obtain analysis results, the process is: analyze the current meteorological conditions The impact of precipitation and wind speed on monitoring tasks; including: in heavy rain or high wind weather, drones cannot work normally, and the frequency of satellite remote sensing data collection needs to be increased; when meteorological conditions are stable, drones conduct high-precision monitoring and increase the frequency of drone data collection; according to the greening degree and grass height of the grassland growth conditions, the monitoring needs are judged, including: when the grassland grows vigorously, large-scale monitoring is carried out through satellite remote sensing and drones, and the frequency of ground sensor data collection is reduced; when the grassland growth is affected by drought and frost, the frequency of ground sensor data collection is increased first to obtain higher-precision local data; real-time inspection of the working status of the equipment, including battery power and communication quality, to ensure that the equipment is running well; if equipment failure or performance degradation is found, the monitoring strategy is adjusted and the backup equipment is enabled; Based on monitoring needs and analysis results, the corresponding collection strategies are automatically generated, including: automatically adjusting the priority of data sources according to the weather and grassland growth status; including: giving priority to satellite remote sensing data under unfavorable meteorological conditions, and giving priority to drones for detailed monitoring when grasslands are growing vigorously; automatically adjusting the collection frequency according to real-time analysis results, including: if the grassland growth status changes significantly, then increase the monitoring frequency of the region, and when meteorological conditions are unstable, reduce reliance on high-frequency data collection and give priority to low-frequency data collection; optimize the spatial area of ​​data collection according to environmental changes and monitoring needs, including: areas with dense grassland growth need to be monitored more frequently and in detail, and under abnormal meteorological conditions, the monitoring focus needs to be placed on local areas, especially where abnormal phenomena occur; In the event of sudden equipment failure, data loss, or extreme weather changes, the logic judgment module will respond immediately and automatically adjust according to the preset emergency response rules to obtain adjustment results, including: enabling backup equipment and adjusting collection strategies; if the main equipment is found to be unable to work properly, the system will automatically enable backup equipment or data sources; when the grassland growth status changes dramatically or weather conditions change suddenly, the system will adjust the collection area and frequency in real time to cope with sudden environmental changes and ensure that the monitoring task is not affected; the generated collection strategy and adjustment results will be transmitted to the data source scheduling module to implement automated strategy adjustments to ensure that monitoring tasks are executed according to the latest requirements; when the equipment is in good condition, data collection is performed according to the automatically adjusted collection frequency and area; in emergency situations, backup equipment is enabled and the monitoring area and frequency are adjusted according to the adjusted strategy.

[0034] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. The satellite remote sensing intelligent monitoring system for meadow grassland based on sky-ground integration is characterized by: include: Environmental perception and judgment module, used to obtain meteorological data and grassland health status data in real time, analyze the impact of environmental changes on monitoring accuracy, and intelligently adjust the data collection mode according to the analysis results, giving priority to the monitoring method suitable for the current environmental conditions; Data collaborative management module, which is used to dynamically schedule satellite remote sensing, drone imagery, and ground sensor data sources according to real-time environmental status and equipment working status, and optimize their collection strategies to ensure coverage and data accuracy of the monitoring area; The data processing module is used to perform weighted fusion of monitoring data from different data sources, combining the resolution, sampling frequency, and spatial distribution of each data source to generate a unified data set. It is also used to repair data loss, noise, or abnormal data, using interpolation algorithms or multi-source data compensation technology to improve data integrity and accuracy; The decision-making response module is used to automatically make decisions and take emergency response measures based on real-time data and system status to deal with emergencies and ensure the smooth execution of monitoring tasks; The resource monitoring module is used to monitor the working status, battery power, and communication quality of each sensor in real time. When the monitoring equipment fails or its performance degrades, it automatically notifies the management personnel and performs corresponding maintenance or replacement operations.

2. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 1 is characterized by: The environment perception judgment module includes: A meteorological data analysis module is used to obtain and analyze meteorological data, including precipitation, temperature, wind speed, and humidity, to assess their potential impact on data collection accuracy and automatically adjust monitoring strategies; The vegetation status judgment module is used to monitor the growth indicators of the grassland in real time, including greening degree, grass height, and grassland density, to evaluate the health status of the grassland and adjust the monitoring method when abnormalities occur.

3. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 2 is characterized by: The use process of the meteorological data analysis module is as follows: first, real-time meteorological data is collected from multiple meteorological sources, including meteorological stations, satellites, and meteorological models. The real-time meteorological data includes precipitation, temperature, wind speed, and humidity. The data collection strategy is adjusted according to changes in precipitation to reduce ground data collection tasks affected by weather; the impact of temperature on monitoring accuracy is evaluated, and satellite remote sensing or high-altitude drones are given priority; the monitoring tasks of drones are automatically adjusted according to wind speed, and more stable monitoring methods are selected; the monitoring frequency is adjusted or the data collection method is switched; based on the analysis of meteorological data, the meteorological data analysis module will automatically adjust the monitoring strategy, that is, the data collection strategy.

4. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 3 is characterized by: The use process of the vegetation status judgment module is as follows: first, the growth index data of the grassland is collected through different data sources; the health status of the grassland is analyzed based on the collected growth index data. If the health status of the grassland is found to be abnormal, adjustments will be made automatically, including monitoring method adjustment, data collection frequency adjustment and emergency response in abnormal situations; among them, for monitoring method adjustment: if the health status of the grassland shows grassland decline, pests and diseases in the region, the monitoring frequency of the region will be increased, or the monitoring means will be adjusted; for data collection frequency adjustment: when the grassland health status is good, the data collection frequency will be reduced; when the grassland health status is abnormal, the data collection frequency will be increased; for emergency response in abnormal situations: when serious health problems are found in the grassland, including large-scale grassland withering, pests and diseases, the vegetation status judgment module will work together with the decision response module to trigger an emergency response.

5. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 4 is characterized by: The data collaborative management module includes a resource scheduling module, which dynamically adjusts the collection priority of the data source according to the real-time meteorological conditions and the changes in the grassland growth status, and selects the most appropriate data source for data collection.

6. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 5 is characterized by: The resource scheduling module dynamically adjusts the data source collection priority according to the changes in the real-time meteorological conditions and the grassland growth status, and the process of selecting the most suitable data source for data collection includes: firstly acquiring meteorological data and grassland growth status data in real time, and then evaluating the applicability of different data sources according to the meteorological data to obtain the evaluation result of the real-time meteorological conditions; then evaluating the applicability of the data source according to the grassland growth status data to obtain the evaluation result of the grassland growth status; According to the evaluation results of real-time meteorological conditions and grassland growth status, the collection priority of each data source is dynamically adjusted; the process is: when the meteorological conditions are bad, satellite remote sensing data is selected; when the meteorological conditions are good, the data from drones and ground sensors are selected; in the grassland growth status, when the grassland is growing healthily, the data provided by satellite remote sensing and drones are given priority; when the grassland growth is restricted, the growth status data obtained by ground sensors is given priority; Subsequently, according to the adjusted priority, the data source is dynamically scheduled to obtain the scheduling result; the scheduling process includes: based on satellite remote sensing, it is suitable for large-scale monitoring, and ground sensors are suitable for detailed local data collection. According to the weather and grassland growth status, the applicable data source is given priority for data collection; at the same time, when the grassland is growing vigorously or the meteorological conditions are stable, the data collection frequency is increased; when the environment is harsh, the collection frequency is reduced to ensure the key coverage of the monitoring area; finally, according to the scheduling results, the data collection task is executed.

7. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 6 is characterized by: The decision response module includes: The logic judgment module is used to automatically evaluate the current monitoring needs based on the real-time collected data and environmental status analysis, generate corresponding collection strategies, and adjust the collection frequency and area of ​​the data source; The emergency response module is used to automatically enable backup equipment or sensors and adjust the monitoring area and data collection strategy when the system detects an emergency, including equipment failure, abnormal climate, and loss of sensor data, to ensure that the monitoring task is not affected.

8. The meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 7 is characterized by: The logic judgment module is used to automatically evaluate the current monitoring needs based on the real-time collected data and environmental status analysis, generate corresponding collection strategies, and adjust the collection frequency and area of ​​the data source. The process includes: collecting data from multiple sources in real time to obtain real-time collected data, including meteorological data, grassland growth status data, and monitoring equipment status data; the environmental perception judgment module evaluates the current meteorological conditions and grassland growth status, performs preliminary analysis based on the real-time collected data, and determines the monitoring needs; The analysis results are obtained based on the real-time collected data. The process is as follows: analyze the impact of precipitation and wind speed in the current meteorological conditions on the monitoring task; determine the monitoring needs based on the greening degree and grass height in the grassland growth conditions; check the working status of the equipment in real time, including battery power and communication quality, to ensure that the equipment is running well; if equipment failure or performance degradation is found, adjust the monitoring strategy and enable backup equipment; Based on monitoring needs and analysis results, the corresponding collection strategy is automatically generated, including: automatically adjusting the priority of the data source according to the weather and grassland growth status; automatically adjusting the collection frequency according to the real-time analysis results; optimizing the spatial area for data collection according to environmental changes and monitoring needs; in the event of sudden equipment failure, data loss, or extreme weather changes, the logic judgment module responds immediately and automatically adjusts according to the preset emergency response rules to obtain adjustment results, including: enabling backup equipment and adjusting the collection strategy.

9. The monitoring method of the meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to any one of claims 1 to 8, characterized in that: The following steps are involved: a: Obtain meteorological data and grassland growth status data in real time, analyze and evaluate environmental impacts through the environmental perception and judgment module, and generate data collection strategies; b: According to the real-time environment and equipment status, the data sources of satellite remote sensing, drone images and ground sensors are dispatched through the data collaborative management module to ensure optimal resource allocation; c: Transmit the collected data to the data processing module to fuse, repair and enhance the data to improve data accuracy and reliability; d: Monitor the system status in real time through the decision response module, automatically adjust the data collection mode according to logical judgment, and initiate emergency response measures when failures or abnormalities occur.

10. The monitoring method of the meadow grassland satellite remote sensing intelligent monitoring system based on sky-ground integration according to claim 9 is characterized in that: The scheduling strategy in step b includes: automatically selecting the most appropriate monitoring method according to meteorological data, grassland growth status and equipment status, and dynamically adjusting the data collection frequency and area; the data processing in step c includes: weighted fusion of satellite remote sensing, drone imagery and ground sensor data, using data repair algorithms to fill in missing data, and using enhancement algorithms to improve data resolution and accuracy; the emergency response measures in step d include: enabling backup sensors, adjusting monitoring areas and data collection strategies, and automatically notifying management personnel to repair or replace equipment when it fails.

Images