Sabina vulgaris planting management system with monitoring function

Abstract

The invention relates to the technical field of plant planting management, and particularly discloses a sabina vulgaris planting management system with a monitoring function, environmental parameters are collected in a planting area, appearance images and multispectral images of sabina vulgaris are shot, and growth indexes and physiological parameters are analyzed and transmitted to a data processing center; the data processing center establishes a database, classifies and stores the collected data, analyzes the data, finds out key factors influencing the growth of the sabina vulgaris, and generates a management decision according to an analysis result and a preset standard; the irrigation and fertilization control module controls irrigation and fertilization; and the disease and insect pest early warning and prevention module identifies and analyzes the acquired image data, judges the disease and insect pest type and occurrence degree, carries out early warning and generates solutions. The environment parameters and growth conditions of the sabina vulgaris planting area are monitored and analyzed in real time, intelligent planting management decision is achieved, the survival rate and growth quality of sabina vulgaris are improved, and the planting cost and management difficulty are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of plant planting management, in particular to a Sabina vulgaris planting management system with a monitoring function. Background Art

[0002] As a key plant species in ecological restoration and windbreak and sand fixation projects, Sabina vulgaris is widely used in various sandy environments. However, its current cultivation and management face many difficulties.

[0003] Under the traditional planting management model, environmental monitoring work is extremely extensive. The environment in the planting area is complex, but it only relies on sparse manual monitoring points or a few simple equipment, which makes it difficult to fully cover the planting area. For example, in a large area of ​​​​Sakhalin juniper planting area, there may be only a few thermometers to measure the temperature, and the temperature changes in areas with different micro-topography and vegetation coverage cannot be accurately captured. Moreover, the monitoring frequency is usually regular manual inspections, which may be once every few days or even weeks, and it is impossible to track the dynamic changes of environmental parameters in real time. For example, during the high temperature period in summer, Sakhalin juniper may cause soil moisture to evaporate rapidly in a short period of time due to sudden extreme high temperatures, and manual monitoring cannot detect the sudden drop in soil moisture in time, resulting in the Sakhalin juniper being in a state of water shortage for a long time, affecting growth and even causing plant death.

[0004] When it comes to monitoring the growth of sapodilla, relying on visual observation to determine its growth status is subject to significant errors. Manual measurement of growth indicators such as plant height and crown width is not only time-consuming and labor-intensive, but also difficult to achieve comprehensively across large planting areas. Only sampling estimates are possible, failing to accurately reflect overall growth. Physiological parameters such as chlorophyll content and moisture content are even more difficult to obtain directly, making it difficult to detect potential problems in the early stages of pests, diseases, or growth stress.

[0005] Traditional pest and disease control methods rely heavily on empirical judgment. Once a pest or disease outbreak occurs, it's often difficult to quickly and accurately identify its type, let alone accurately assess its extent. Due to the lack of effective early warning mechanisms, control efforts often miss the optimal opportunity, leading to widespread pest and disease spread and widespread infestation of sand junipers. This not only increases control costs but can also severely damage the ecological protection of the entire planting area. Furthermore, the lack of scientific evidence in control efforts can lead to overuse of pesticides, resulting in environmental pollution and pesticide residue problems in sand junipers.

[0006] The various deficiencies in existing technologies for the planting and management of Sabina vulgaris result in low planting efficiency and serious waste of resources, making it difficult to meet the current ecological engineering requirements for high-quality planting and management of Sabina vulgaris.

[0007] Therefore, developing a planting management system that can monitor the planting environment and growth conditions of Sabina vulgaris in real time and accurately, and can prevent and control diseases and pests in a timely and effective manner, has become an urgent problem to be solved. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide a planting management system of sand juniper with a monitoring function, which realizes intelligent planting management decision-making by real-time monitoring and analysis of the environmental parameters and growth conditions of the sand juniper planting area, improves the survival rate and growth quality of sand juniper, and reduces planting costs and management difficulty.

[0009] To solve the above technical problems, the present invention provides a technical solution: a Sabina vulgaris planting management system with a monitoring function, comprising:

[0010] The monitoring data acquisition module includes several monitoring nodes evenly distributed throughout the planting area and a sapodilla juniper growth status acquisition unit. The monitoring nodes are equipped with several sensors to collect environmental parameters, and the collected data is wirelessly transmitted to a data processing center. The sapodilla juniper growth status acquisition unit captures appearance and multispectral images of the sapodilla juniper, analyzes growth indicators and physiological parameters, and transmits the data to the data processing center.

[0011] Data processing center: includes a data storage module, a data analysis module, and a decision-making module. The storage module establishes a database and stores the collected data in categories. The analysis module uses a gradient boosting decision tree algorithm to analyze the data and identify key factors affecting the growth of sapodilla. The decision-making module generates management decisions based on the analysis results and preset standards.

[0012] Irrigation and fertilization control module: controls the amount of irrigation water and irrigation time according to the instructions issued by the data processing center, and controls the type, amount and time of fertilizer according to management decisions;

[0013] Pest and disease early warning and prevention module: Identifies and analyzes the collected image data to determine the type and extent of pests and diseases, issues early warnings when the threshold is exceeded, and generates targeted solutions.

[0014] Furthermore, the sensors include a temperature sensor, a humidity sensor, a light intensity sensor, a soil moisture sensor, and a soil pH sensor.

[0015] Furthermore, the sand juniper growth status collection unit uses a drone equipped with a high-definition camera and a multispectral imager to regularly conduct flight photography of the planting area; the high-definition camera captures the appearance image of the sand juniper and analyzes the growth indicators of the sand juniper, including plant height, crown width, and branch and leaf density, through image recognition; the multispectral imager obtains the multispectral image of the sand juniper and analyzes its physiological parameters, including chlorophyll content and water content, to determine the health status of the sand juniper; the sand juniper growth status collection unit transmits the collected data to a data processing center.

[0016] Furthermore, the data storage module classifies and stores the collected environmental parameters and growth status data of Sand Juniper to establish a historical database; the data analysis module uses the gradient boosting decision tree algorithm to analyze the real-time and historical data to find out the key factors affecting the growth of Sand Juniper; the decision module generates planting management decisions based on the data analysis results, combined with the preset Sand Juniper growth standards and environmental suitability range.

[0017] Furthermore, the irrigation and fertilization control module controls the drip irrigation system installed in the planting area to turn on or off and adjust the irrigation water volume and time according to the control instructions issued by the data processing center; and controls the type, amount and time of fertilizer based on the planting management decision generated by the decision module.

[0018] Furthermore, the pest and disease warning and control module uses pest and disease image recognition methods to analyze the images of sand juniper taken by drones and the images of pest and disease samples collected manually to identify the types of pests and diseases and the degree of occurrence; when the degree of occurrence of pests and diseases exceeds the warning threshold, an early warning message is sent to the management personnel, and according to the type of pests and diseases, the preset prevention and control plan library is automatically retrieved to generate corresponding prevention and control measures, and the drone or ground spraying equipment is controlled to carry out pest and disease control operations.

[0019] The advantages of the present invention compared with the prior art are:

[0020] By real-time monitoring of the growth environment and growth status of the sapodilla, the present invention can accurately grasp the needs of the sapodilla, provide precise irrigation, fertilization and pest control decisions, and avoid the blindness and subjectivity of traditional management methods.

[0021] The precise management decisions made by this invention can reduce waste of water, fertilizer, and pesticides, lowering planting costs. Furthermore, timely pest and disease warning and control measures can effectively reduce the damage caused by pests and diseases to sapodilla, improve the survival rate and growth quality of sapodilla, and further reduce planting costs.

[0022] The present invention realizes automation and intelligence of planting management, reduces manual labor intensity and management difficulty, and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The present invention is a system block diagram of a Sabina vulgaris planting management system with a monitoring function.

[0024] Figure 2 The present invention is a workflow diagram of a Sabina vulgaris planting management system with a monitoring function. DETAILED DESCRIPTION

[0025] Various exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention.

[0026] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0027] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0028] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0029] The following is a detailed description of a Sabina vulgaris planting management system with a monitoring function according to the present invention with reference to the accompanying drawings.

[0030] Combined with attachment Figure 1-2 , the present invention is introduced in detail.

[0031] A Sabina vulgaris planting management system with a monitoring function, comprising:

[0032] Monitoring data acquisition module

[0033] Several monitoring nodes are evenly set up in the planting area. Each monitoring node is equipped with a temperature sensor, a humidity sensor, a light intensity sensor, a soil moisture sensor, and a soil pH sensor to collect environmental parameters. Let the temperature value collected by the temperature sensor at the i-th monitoring node be T i , the humidity value collected by the humidity sensor is H i , the light intensity value collected by the light intensity sensor is L i , the soil moisture value collected by the soil moisture sensor is The soil pH value collected by the soil pH sensor is i=1, 2, ..., n (n is the number of monitoring nodes). The data collected by these sensors are transmitted to the data processing center through the wireless transmission module.

[0034] The growth status collection unit of the Sabina sylvatica uses drones equipped with high-definition cameras and multi-spectral imagers to regularly conduct aerial photography of the planting area. The HD camera captures the appearance of the Sabina sylvatica and uses image recognition to analyze the growth indicators of the Sabina sylvatica, including plant height h j 、Crown width w j , branch and leaf density d j (j = 1, 2, ..., m, where m is the number of Sabina vulgaris individuals photographed); a multispectral imager was used to obtain multispectral images of Sabina vulgaris and analyze its physiological parameters, including chlorophyll content c j , moisture content This unit collects growth and physiological parameters to determine the health of the sapodilla trees. The unit transmits this data to a data processing center. Meanwhile, images captured by high-definition cameras and multispectral imagers are used for pest and disease image recognition.

[0035] Data Processing Center

[0036] The data storage module collects the environmental parameters and growth data of Sabina vulgaris As well as pest and disease related images are classified and stored to establish a historical database.

[0037] The data analysis module uses the gradient boosting decision tree algorithm to analyze real-time and historical data. The target variable Y represents the growth status of Sabina vulgaris (e.g., good growth, inhibited growth, etc.). The gradient boosting decision tree iteratively trains a series of decision trees f k (X) to approximate the target variable Y, the final prediction model is where α k is the weight of the kth decision tree, and K is the number of decision trees. The model is used to find the key factors affecting the growth of Sabina vulgaris. For pest and disease image recognition, a method based on convolutional neural network (CNN) is used. Let the input pest and disease image be I. After being processed by the convolution layer, pooling layer and fully connected layer of the CNN model, the feature vector F is obtained. I , the probability distribution P of the image belonging to different pests and diseases is calculated by the softmax function class (I), the formula is where z k is the kth value output by the fully connected layer, and C is the number of pest and disease species.

[0038] The decision module is based on the prediction result F(X) obtained by the data analysis module and the pest and disease image recognition result P class (I), combined with the preset growth standard X standardand the suitable range of the environment, and generate planting management decisions. For example, if F(X) shows that the soil moisture is below the suitable range, an irrigation instruction is generated; if P class If the probability of a certain pest type in (I) exceeds the threshold, a prevention and control instruction is generated for the pest.

[0039] Irrigation and fertilization control module

[0040] According to the control instructions issued by the data processing center, the drip irrigation system installed in the planting area is controlled to be turned on or off, and the irrigation water volume V and time t are adjusted. The adjustment of irrigation water volume and time is based on the analysis results of environmental parameters such as soil moisture by the data analysis module. For example, if the soil moisture S H Below threshold Then turn on the drip irrigation system and irrigate Irrigation time t = k2 × V, where k1 and k2 are adjustment coefficients.

[0041] According to the planting management decision generated by the decision module, control the type of fertilizer F type , Fertilizer amount F amount And fertilization time F time The amount and time of fertilization are determined according to the growth index of Sabina vulgaris and the soil nutrient status. For example, if the chlorophyll content c is lower than the threshold c threshold , then choose fertilizer with high nitrogen content, and the fertilizer amount F amount =k3×(c threshold -c), fertilization time F time Determined according to the growth cycle of Sabina vulgaris.

[0042] Pest and disease early warning and control module

[0043] The above-mentioned CNN-based pest and disease image recognition technology was used to analyze the images of Sabina vulgaris taken by drones and the images of pest and disease samples collected manually. class (I) Identify the type of pests and diseases P type (The extent of occurrence can be determined based on factors such as the proportion of the area affected by the pest in the image).

[0044] When the degree of pests and diseases P degree Exceeding the warning threshold P threshold When an emergency occurs, an early warning message is sent to the management staff.

[0045] According to the type of pests and diseases P type Automatically search the preset control program library and generate corresponding control measures. For example, if a certain pest is identified, the pesticide concentration C pesticide =k4×P degree , control drones or ground spraying equipment to carry out pest and disease control operations, and the spraying area is determined according to the scope of pest and disease occurrence.

[0046] The specific implementation process of the Sabina vulgaris planting management system with monitoring function of the present invention is as follows:

[0047] 1. Monitoring data acquisition module

[0048] (1) Environmental parameter collection

[0049] Monitoring Node Layout: 3,000 monitoring nodes were evenly distributed across a 30-hectare area planted with Sabina vulgaris, based on the terrain and planting density, with one monitoring node per 100 square meters. The nodes were distributed in a grid pattern to ensure comprehensive coverage of the plantation and avoid blind spots.

[0050] Sensor Selection and Installation: A high-precision temperature sensor, model DS18B20, with an accuracy of ±0.5°C, was selected. Enclosed in a waterproof housing, it was mounted on a monitoring pole 1.5 meters above the ground to accurately measure air temperature. A humidity sensor, model HIH-4000, with an accuracy of ±3%, was installed at the same height as the temperature sensor on the monitoring pole to measure relative humidity. A light intensity sensor, model TSL2561, with a measurement range of 0-200,000 Lux, was installed in an unobstructed position atop the monitoring pole to ensure unobstructed light measurement. An ECH2O-5TE soil moisture sensor was inserted into the soil at a depth of 25 cm. With an accuracy of ±5%, it accurately measures soil moisture in the main root zone of the Sapodilla juniper. A PH-01 soil pH sensor, with an accuracy of ±0.2, was also inserted vertically into the soil to measure soil pH.

[0051] Wireless Transmission Setup: Each monitoring node is equipped with a wireless transmission module based on LoRa technology, which features low power consumption and long-distance transmission. The transmission distance can reach 1-3 kilometers, meeting the data transmission needs of large planting areas. Data collected by each sensor is first aggregated into the node's microcontroller. After preliminary processing, the data is sent to the receiving base station in the data processing center via the wireless transmission module using a specific communication protocol, such as a custom data packet format. The receiving base station then transmits the data to the data processing center server.

[0052] (2) Collection of Sabina vulgaris growth status

[0053] Drone Operation Planning: A DJI Matrice 300 RTK drone was used. The drone was set to fly at an altitude of 50 meters and a speed of 8 meters per second, following a pre-set "S"-shaped path to capture images of the planting area. This mission was carried out weekly. The flight path planning ensured a 30% overlap between adjacent flight paths to ensure accurate image stitching and analysis.

[0054] Equipment and Data Collection: The drone is equipped with a 48-megapixel high-definition camera, model FC6310, which is used to capture images of the exterior of the samovar. Image recognition algorithms can accurately analyze growth indicators such as plant height, crown width, and branch and leaf density. It is also equipped with a multispectral imager, such as the MicaSense RedEdge-MX, which has five wavelength bands and can capture multispectral images of samovar for analysis of physiological parameters such as chlorophyll content and moisture content. During flight, the high-definition camera and multispectral imager operate synchronously, and the captured image data is stored in real time on the drone's high-capacity memory card. After the flight, the data is rapidly transmitted to the data processing center via a wireless data transmission module.

[0055] 2. Data Processing Center

[0056] (1) Data storage module

[0057] Server configuration: Dell PowerEdge R740xd high-performance server is used as the hardware foundation of the data processing center. It is equipped with two Intel Xeon Silver 4210R processors with 16 cores, 64GB DDR4 memory, and two 1TB solid-state drives forming a RAID 1 array to ensure the efficiency and security of data storage.

[0058] Database construction: Install the PostgreSQL relational database management system on the server and create multiple data tables based on the data type. For example, create the "environment_data" table to store environmental parameter data. The table structure includes the fields "node_id" (monitoring node number), "temperature" (temperature value), "humidity" (humidity value), "light_intensity" (light intensity value), "soil_moisture" (soil moisture value), "soil_ph" (soil pH value), and "measurement_time" (measurement time). Create the "sabina_vulgaris_growth_data" table to store Sabina vulgaris growth status data. The table includes the fields "plant_id" (Sabina vulgaris individual number), "height" (plant height), "crown_width" (crown width), "branch_density" (branch and leaf density), "chlorophyll_content" (chlorophyll content), and "water_content" (water content). For pest and disease related images, the image files are stored in a specific file directory, and a "pest_disease_images" table is created in the database to record the image file name, shooting time, shooting location, and corresponding preliminary pest and disease judgment information.

[0059] (2) Data Analysis Module

[0060] Gradient Boosting Decision Tree Model Training: A gradient boosting decision tree model was constructed using the Python Scikit-learn library. A training set of 500,000 records of environmental parameters and sapodilla juniper growth data from the past two years was extracted from a historical database. The number of decision trees, K, was set to 100, and the learning rate (i.e., the update step size of α_k) was set to 0.1. Model parameters were adjusted through cross-validation to improve the model's generalization ability. After several hours of training, the model achieved over 85% accuracy in predicting sapodilla juniper growth status on the test set.

[0061] Pest and disease image recognition model construction: A convolutional neural network (CNN) model was built based on the TensorFlow deep learning framework for pest and disease image recognition. 5,000 images of common pests and diseases of Sabina vulgaris were collected, covering 20 different pest and disease categories, with an average of 250 images for each category. Data augmentation was performed on the images, such as random rotation, horizontal flipping, and brightness adjustment, to expand the dataset to 20,000 images. The model structure consists of five convolutional layers, each followed by a ReLU activation function and a maximum pooling layer, followed by two fully connected layers. The output layer uses a softmax function to calculate the probability distribution of images belonging to different pest and disease categories. After 100 epochs of training, the model achieved a recognition accuracy of 90% on the validation set.

[0062] (3) Decision-making module

[0063] Preset Standards and Ranges: Based on the biological characteristics of sabinia vulgaris and extensive planting experience, preset environmental parameter ranges are established for its growth. For example, the ideal temperature range is 15°C-28°C, relative humidity is 30%-60%, soil moisture is 15%-25%, and soil pH is 7-8.5. Normal growth ranges for sabinia vulgaris are also established, such as plant height growth of 3-5 cm per month and crown width expansion of 10-15 cm per year. These standards and ranges are stored in the "sabina_vulgaris_standards" table in the database.

[0064] Decision generation logic: The decision module obtains the prediction results F(X) and the pest and disease image recognition results P of the data analysis module in real time. class (I). When F(X) shows soil moisture S H Below threshold (If set to 15%), according to the formula Calculate the irrigation water volume V, where k1 is set to 50 (in liters / square meter); then calculate the irrigation time t according to t=k2×V, where k2 is set to 0.02 (in hours / liter). If P class If the probability of a particular pest or disease type in (I) exceeds a threshold (e.g., set to 0.6), the corresponding control measures for that pest or disease are retrieved from a preset control scheme library. The control scheme library is stored in the "pest_disease_control_schemes" table in the database and contains information such as the pest or disease type, the corresponding pesticide type, concentration ratio, and application method.

[0065] 3. Irrigation and fertilization control module

[0066] (1) Irrigation control

[0067] Drip irrigation system installation: Drip irrigation pipes were laid in the planting area, using 50mm diameter PVC pipes for the main pipes and 20mm diameter PE pipes for the branch pipes. The drippers were spaced 30cm apart. DN25 electric valves were installed, each controlling a specific irrigation area and connected to the data processing center via an RS485 communication interface.

[0068] Irrigation Execution: When the data processing center issues an irrigation command, the irrigation control submodule receives it and, based on the calculated irrigation volume V and time t, controls the opening of the electric valves in the corresponding area. For example, if the calculated irrigation volume for a particular area is 5,000 liters and the irrigation time is 100 minutes, the valves in that area will be opened at a steady flow rate for 100 minutes to ensure adequate watering for the sapodilla trees. During the irrigation process, flow meters and pressure sensors installed on the pipelines monitor the irrigation volume and pressure in real time. This data is fed back to the data processing center. If an anomaly is detected, such as a deviation of more than 10% between the actual irrigation volume and the calculated value, an alarm is automatically triggered and the valve opening is adjusted.

[0069] (2) Fertilization control

[0070] Fertilization equipment includes multiple fertilizer storage tanks for nitrogen, phosphate, potash, and compound fertilizers. ProMinent Gamma / 3 metering pumps connect the tanks to the fertilization pipelines, precisely controlling fertilizer delivery. The fertilization pipelines are laid parallel to the drip irrigation lines, and a fertilizer mixer mixes the fertilizer with irrigation water before delivering it to the roots of the savana.

[0071] Fertilization decision execution: Fertilization decision generated by the decision module, such as when the chlorophyll content c is lower than the threshold c threshold (If it is set to 30mg / g), choose urea with high nitrogen content as fertilizer, according to formula F amount =k3×(c threshold -c) Calculate the amount of fertilizer Famount , k3 is set to 0.5 (unit is g / m2). Fertilization time F time Fertilization is determined based on the growth cycle of the Sabina vulgaris. For example, during the peak growth periods of spring and summer, fertilizer is applied monthly; during the slower growth periods of autumn and winter, fertilizer is applied every two months. The fertilization control submodule controls the metering pump to apply fertilizer according to the calculated amount and the set time. A flow sensor also monitors the fertilizer delivery during the fertilization process to ensure accurate fertilization.

[0072] 4. Pest and disease early warning and control module

[0073] (1) Identification and early warning of pests and diseases

[0074] Image analysis process: After the images of Sabina vulgaris taken by drones and the images of pest and disease samples collected manually are transmitted to the data processing center, the pest and disease early warning and control module uses the trained CNN model for analysis. First, the image is preprocessed, including normalization and denoising, and then input into the model for calculation to obtain the probability distribution P of the image belonging to different pest and disease types. class (I). At the same time, the proportion of the area affected by pests and diseases is calculated through image segmentation algorithm to determine the degree of occurrence of pests and diseases P degree For example, if the probability of an image being diagnosed with rust of sandy cypress is 0.8 and the affected area ratio reaches 20%, then it is determined that rust of sandy cypress has occurred and the degree of occurrence is moderate.

[0075] Early warning release mechanism: When the degree of pests and diseases is P degree Exceeding the warning threshold P threshold When a warning threshold is set (for example, for sandy cypress rust, moderate or above is set), the warning submodule sends an alert message to the manager's mobile phone via SMS. The message contains detailed information such as the type of pest, location, and severity. At the same time, a prominent warning prompt pops up on the planting management app and web management platform. Managers can click on the prompt to view relevant pest images and detailed analysis reports.

[0076] (2) Implementation of prevention and control measures

[0077] Retrieval and deployment of prevention and control plans: According to the identified pest and disease types P type For example, for rust of sandy cypress, the control submodule automatically searches the preset control scheme library. From the "pest_disease_control_schemes" table, it finds the control scheme for rust of sandy cypress, determines to use triadimefon as the pesticide, and adjusts the pesticide concentration C pesticide =k4×P degree , k4 is set to 0.1 (in grams per liter), if the degree P degree If the content of pesticide is 20%, the concentration of the prepared pesticide is 2 g / L.

[0078] Control Operations: For areas with mild pest and disease infestations, ground-based pesticide application equipment, such as knapsack sprayers, is used manually to precisely spray affected plants. For areas with moderate or severe pest and disease infestations, drones are deployed for pesticide application. Equipped with specialized spray equipment, drones automatically adjust the spray volume and range based on the scope and severity of the pest and disease. After application, images of the juniper trees are regularly collected for pest and disease identification and analysis, and control effectiveness is evaluated. If effectiveness is poor, the control plan is adjusted, such as by increasing the pesticide concentration or changing the type of pesticide, until the pest and disease are effectively controlled.

[0079] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A Sabina vulgaris planting management system with monitoring function, characterized in that: include: The monitoring data acquisition module includes several monitoring nodes evenly distributed throughout the planting area and a sapodilla juniper growth status acquisition unit. The monitoring nodes are equipped with several sensors to collect environmental parameters, and the collected data is wirelessly transmitted to a data processing center. The sapodilla juniper growth status acquisition unit captures appearance and multispectral images of the sapodilla juniper, analyzes growth indicators and physiological parameters, and transmits the data to the data processing center. Data processing center: includes a data storage module, a data analysis module, and a decision-making module. The storage module establishes a database and stores the collected data in categories. The analysis module uses a gradient boosting decision tree algorithm to analyze the data and identify key factors affecting the growth of sapodilla. The decision-making module generates management decisions based on the analysis results and preset standards. Irrigation and fertilization control module: controls the amount of irrigation water and irrigation time according to the instructions issued by the data processing center, and controls the type, amount and time of fertilizer according to management decisions; Pest and disease early warning and prevention module: Identifies and analyzes the collected image data to determine the type and extent of pests and diseases, issues early warnings when the threshold is exceeded, and generates targeted solutions.

2. The Sabina vulgaris planting management system with monitoring function according to claim 1, characterized in that: The sensors include a temperature sensor, a humidity sensor, a light intensity sensor, a soil moisture sensor, and a soil pH sensor.

3. The Sabina vulgaris planting management system with monitoring function according to claim 2, characterized in that: The sand juniper growth status collection unit uses a drone equipped with a high-definition camera and a multispectral imager to regularly conduct flight photography of the planting area; the high-definition camera captures the appearance image of the sand juniper and analyzes the growth indicators of the sand juniper, including plant height, crown width, and branch and leaf density, through image recognition; the multispectral imager obtains the multispectral image of the sand juniper and analyzes its physiological parameters, including chlorophyll content and water content, to determine the health status of the sand juniper; the sand juniper growth status collection unit transmits the collected data to a data processing center.

4. The Sabina vulgaris planting management system with monitoring function according to claim 3, characterized in that: The data storage module classifies and stores the collected environmental parameters and growth status data of Sand Juniper to establish a historical database; the data analysis module uses the gradient boosting decision tree algorithm to analyze real-time and historical data to find out the key factors affecting the growth of Sand Juniper; the decision module generates planting management decisions based on the data analysis results, combined with the preset Sand Juniper growth standards and environmental suitability range.

5. The Sabina vulgaris planting management system with monitoring function according to claim 4, characterized in that: The irrigation and fertilization control module controls the drip irrigation system installed in the planting area to open or close according to the control instructions issued by the data processing center, and adjusts the irrigation water volume and time; and controls the type, amount and time of fertilizer based on the planting management decision generated by the decision module.

6. The Sabina vulgaris planting management system with monitoring function according to claim 5, characterized in that: The pest and disease warning and control module uses pest and disease image recognition methods to analyze images of sand juniper taken by drones and images of pest and disease samples collected manually to identify the types of pests and diseases and the extent of their occurrence. When the extent of pest and disease occurrence exceeds the warning threshold, an early warning message is sent to the management personnel. According to the type of pest and disease, the module automatically retrieves the preset prevention and control plan library, generates corresponding prevention and control measures, and controls drones or ground spraying equipment to carry out pest and disease control operations.

Images