Vegetation growth environment monitoring method and device

Abstract

The invention discloses a vegetation growth environment monitoring method and device, and relates to the technical field of environment monitoring. The method comprises the following steps: acquiring real-time environmental monitoring data of a target area through a plurality of sensor nodes, acquiring a global image of the target area, determining vegetation features according to the global image, and predicting environmental parameters according to the vegetation features and historical environmental parameters; determining an abnormal node according to the real-time data and the prediction data; obtaining a high-definition local image of the target area, and carrying out pest judgment to obtain first-class alarm information; if no abnormal node exists, whether the vegetation growth environment is qualified or not is judged according to the real-time data, and a second type of alarm information is obtained. By deploying sensor nodes to monitor environmental data in real time, using technologies such as image processing to quantify vegetation features, and combining a prediction model and anomaly detection, a data-driven scientific management and maintenance scheme can be provided, so that dependence on experience of managers is reduced, and management efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and device for monitoring a vegetation growth environment. Background Art

[0002] With the acceleration of urbanization, people have higher and higher requirements for the quality of living environment, and urban greening has become an important means to enhance the city's image and improve the quality of life of residents. As an important part of urban greening, the management and maintenance of parks has received increasing attention.

[0003] In the park maintenance industry, vegetation growth monitoring relies too much on the experience and judgment of managers, and there is no quantifiable data for scientific maintenance. In the process of vegetation maintenance, different plants have different requirements for common parameters such as water, nutrients, pH, etc. in different seasons, different regions and different soil conditions. In the conventional maintenance process, maintenance work is often carried out after judgment based on the historical experience of maintenance personnel. This kind of situation requires high personnel training for park maintenance companies, and the quality of maintenance cannot be ensured in the case of large personnel changes. This maintenance method that relies on manual experience will lead to improper vegetation maintenance, such as unnecessary irrigation, fertilization or pruning, waste of resources, and even damage to vegetation health. Manual judgment of vegetation growth status and environmental needs is inefficient and inaccurate. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of low accuracy mentioned in the above background technology and to propose a vegetation growth environment monitoring method and device.

[0005] A first aspect of the present invention provides a method for monitoring a vegetation growth environment, the method comprising:

[0006] The park is divided into multiple sub-areas according to soil quality and vegetation type; multiple sensor nodes are deployed in each sub-area;

[0007] Acquire environmental monitoring data of a target sub-area, use the environmental monitoring data within a first preset time period as baseline data, and use real-time monitoring values ​​of multiple environmental parameters at a first target moment as real-time data; the target sub-area is any one of the multiple sub-areas;

[0008] Acquire a global image of the target sub-area, determine vegetation features according to the global image, and obtain prediction data according to the vegetation features and the benchmark data;

[0009] Determine abnormal nodes according to the real-time data and the predicted data;

[0010] If there is an abnormal node, multiple local images of the target sub-area are obtained, and pest judgment is performed based on the multiple local images to obtain a first judgment result, and a first type of alarm information is generated and issued based on the first judgment result;

[0011] If there is no abnormal node, then determine whether the vegetation growth environment of the target sub-area is qualified based on the real-time data, obtain a second judgment result, generate and issue a second type of alarm information based on the second judgment result, and control the sprinkler equipment based on the second type of alarm information.

[0012] Optionally, the global image includes a multispectral image and an infrared thermal image; the vegetation characteristics include a normalized vegetation index, a leaf area index, and a leaf surface temperature; the benchmark data include soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed, and precipitation; the predicted data include predicted values ​​of soil moisture, predicted values ​​of soil temperature, and predicted values ​​of soil nutrients;

[0013] The determining of vegetation features according to the global image, and obtaining prediction data according to the vegetation features and the reference data includes:

[0014] According to the benchmark data, the monitoring values ​​of multiple environmental parameters at the second target time are combined into a target column vector; the first preset time period includes multiple monitoring times; the second target time is any one of the multiple monitoring times;

[0015] Calculating a normalized vegetation index according to the multispectral image, and calculating a leaf area index according to the normalized vegetation index;

[0016] Obtaining the blade surface temperature according to the infrared thermal imaging at the second target moment;

[0017] Concatenating the leaf surface temperature, the normalized vegetation index, the leaf area index and the target column vector to obtain a feature column vector;

[0018] Concatenate the feature column vectors of multiple monitoring moments within the first preset time period to obtain a feature matrix;

[0019] The feature matrix is ​​used as an input of a pre-trained prediction model to obtain prediction data at a first target moment.

[0020] Optionally, the determining the abnormal node according to the real-time data and the predicted data includes:

[0021] The offset value of the target parameter is calculated according to the predicted value and the real-time monitoring value of the target parameter at the first target time; the target parameter is any one of soil moisture, soil temperature and soil nutrients;

[0022] Obtaining an expected offset vector according to the offset values ​​at different times within the second preset time period;

[0023] Calculating a standard deviation of an offset according to the expected offset vector;

[0024] If the offset standard deviation is greater than a first preset threshold, it is determined that an abnormality occurs in the sensor node corresponding to the target parameter.

[0025] Optionally, the multiple local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information;

[0026] The performing pest judgment according to the plurality of local images to obtain a first judgment result, and generating and issuing a first type of alarm information according to the first judgment result comprises:

[0027] Using each high-definition image as an input to a pre-trained pest detection model to obtain a first judgment result;

[0028] If the first judgment result is that there is an insect pest, generating an insect pest alarm message;

[0029] If the first judgment result is that there is no insect pest, a fault alarm message is generated.

[0030] Optionally, the sprinkler irrigation equipment includes a spraying mode and a drip irrigation mode; judging whether the vegetation growth environment of the target sub-area is qualified according to the real-time data, obtaining a second judgment result, generating and issuing a second type of alarm information according to the second judgment result, and controlling the sprinkler irrigation equipment according to the second type of alarm information includes:

[0031] Determining a threshold range of each environmental parameter according to the vegetation type of the target sub-area;

[0032] If the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, the target environmental parameter is judged to be unqualified, and the judgment result is included in the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters;

[0033] If the second type of alarm information contains information indicating that the soil moisture is unqualified, turning on the spraying mode of the sprinkler irrigation equipment;

[0034] If the second type of alarm information contains information that the soil temperature is unqualified, the drip irrigation mode of the sprinkler irrigation equipment is turned on.

[0035] A second aspect of the present invention provides a vegetation growth environment monitoring device, the device comprising:

[0036] A partitioning module is used to divide the area according to the soil quality and vegetation type of the park to obtain multiple sub-areas; each sub-area is deployed with multiple sensor nodes;

[0037] A data acquisition module, used to acquire environmental monitoring data of a target sub-area, using the environmental monitoring data within a first preset time period as the baseline data, and using the real-time monitoring values ​​of multiple environmental parameters at a first target moment as the real-time data; the target sub-area is any one of the multiple sub-areas;

[0038] A prediction module, used to obtain a global image of a target sub-area, determine vegetation features according to the global image, and obtain prediction data according to the vegetation features and the reference data;

[0039] An abnormality judgment module, used to determine abnormal nodes according to the real-time data and the predicted data;

[0040] A first alarm module, configured to obtain a plurality of local images of the target sub-area if an abnormal node exists, and perform pest judgment based on the plurality of local images to obtain a first judgment result, and generate and issue a first type of alarm information based on the first judgment result;

[0041] The second alarm module is used to determine whether the vegetation growth environment of the target sub-area is qualified based on the real-time data if there are no abnormal nodes, obtain a second judgment result, generate and issue a second type of alarm information based on the second judgment result, and control the sprinkler equipment based on the second type of alarm information.

[0042] Optionally, the global image includes a multispectral image and an infrared thermal image; the vegetation characteristics include a normalized vegetation index, a leaf area index, and a leaf surface temperature; the benchmark data include soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed, and precipitation; the predicted data include predicted values ​​of soil moisture, predicted values ​​of soil temperature, and predicted values ​​of soil nutrients;

[0043] The prediction module comprises:

[0044] A first time step composition module is used to compose a target column vector from the monitoring values ​​of multiple environmental parameters at the second target time according to the benchmark data; the first preset time period includes multiple monitoring times; the second target time is any one of the multiple monitoring times;

[0045] A first vegetation feature calculation module, used to calculate a normalized vegetation index according to the multispectral image, and calculate a leaf area index according to the normalized vegetation index;

[0046] a second vegetation feature calculation module, which obtains the leaf surface temperature according to the infrared thermal imaging at the second target moment;

[0047] A second time step composition module is used to concatenate the leaf surface temperature, the normalized vegetation index, the leaf area index and the target column vector to obtain a feature column vector;

[0048] A feature determination module, used for concatenating feature column vectors of multiple monitoring moments within the first preset time period to obtain a feature matrix;

[0049] The model prediction module is used to use the feature matrix as an input of a pre-trained prediction model to obtain prediction data at a first target moment.

[0050] Optionally, the abnormality judgment module includes:

[0051] an offset value calculation module, used to calculate the offset value of the target parameter according to the predicted value and the real-time monitoring value of the target parameter at the first target time; the target parameter is any one of soil moisture, soil temperature and soil nutrients;

[0052] A multi-time-step offset value statistics module, used to obtain an expected offset vector according to the offset values ​​at different times within a second preset time period;

[0053] A standard deviation calculation module, used to calculate the offset standard deviation according to the expected offset vector;

[0054] The abnormal node determination module is used to determine that an abnormality occurs in the sensor node corresponding to the target parameter if the offset standard deviation is greater than a first preset threshold.

[0055] Optionally, the multiple local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information;

[0056] The first alarm module comprises:

[0057] The pest detection module is used to use each high-definition image as an input of a pre-trained pest detection model to obtain a first judgment result;

[0058] A pest alarm module, configured to generate pest alarm information if the first judgment result is that there is pest;

[0059] A fault alarm module is used to generate fault alarm information if the first judgment result is that there is no insect pest.

[0060] Optionally, the sprinkler irrigation equipment includes a spraying mode and a drip irrigation mode; the second alarm module includes:

[0061] A threshold determination module, used to determine the threshold range of each environmental parameter according to the vegetation type of the target sub-area;

[0062] A parameter alarm module, for judging that the target environmental parameter is unqualified if the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, and incorporating the judgment result into the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters;

[0063] A humidity control module, configured to turn on the spraying mode of the sprinkler irrigation device if the second type of alarm information contains information indicating that the soil humidity is unqualified;

[0064] The temperature control module is used to turn on the drip irrigation mode of the sprinkler irrigation equipment if the second type of alarm information contains information that the soil temperature is unqualified.

[0065] Beneficial effects of the present invention:

[0066] The present invention proposes a vegetation growth environment monitoring method, which includes: dividing a region according to soil quality and vegetation type in a park to obtain multiple sub-regions; deploying multiple sensor nodes in each sub-region; acquiring environmental monitoring data of a target sub-region, taking environmental monitoring data within a first preset time period as baseline data, taking real-time monitoring values ​​of multiple environmental parameters at a first target moment as real-time data, and the target sub-region is any one of the multiple sub-regions; acquiring a global image of the target sub-region, determining vegetation features according to the global image, and obtaining prediction data according to the vegetation features and the baseline data; determining abnormal nodes according to the real-time data and the prediction data; if there are abnormal nodes, acquiring multiple local images of the target sub-region, performing pest judgment according to the multiple local images, obtaining a first judgment result, and generating and issuing a first type of alarm information according to the first judgment result; if there are no abnormal nodes, judging whether the vegetation growth environment of the target sub-region is qualified according to the real-time data, obtaining a second judgment result, and generating and issuing a second type of alarm information according to the second judgment result.

[0067] By deploying sensor nodes to monitor environmental data in real time, using image processing and other technologies to quantify vegetation characteristics, and combining predictive models and anomaly detection, it is possible to provide data-driven scientific management and maintenance solutions, thereby reducing reliance on management personnel's experience and improving management efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] The present invention will be further described below in conjunction with the accompanying drawings.

[0069] Figure 1 A flow chart of a vegetation growth environment monitoring method is provided for an embodiment of the present invention;

[0070] Figure 2 A structural diagram of a vegetation growth environment monitoring device is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0071] 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.

[0072] The embodiment of the present invention provides a method for monitoring the vegetation growth environment. Figure 1 , Figure 1 A flow chart of a vegetation growth environment monitoring method provided by an embodiment of the present invention. The method comprises the following steps:

[0073] S101, dividing the park into regions according to soil quality and vegetation type to obtain multiple sub-regions.

[0074] S102, obtaining environmental monitoring data of a target sub-area, taking the environmental monitoring data within a first preset time period as baseline data, and taking real-time monitoring values ​​of a plurality of environmental parameters at a first target moment as real-time data.

[0075] S103, obtaining a global image of the target sub-area, determining vegetation features according to the global image, and obtaining prediction data according to the vegetation features and the benchmark data.

[0076] S104, determining abnormal nodes based on real-time data and predicted data.

[0077] S105: If there is an abnormal node, multiple local images of the target sub-area are obtained, and pest judgment is performed based on the multiple local images to obtain a first judgment result, and a first type of alarm information is generated and issued based on the first judgment result.

[0078] S106, if there is no abnormal node, judge whether the vegetation growth environment of the target sub-area is qualified according to the real-time data, obtain a second judgment result, generate and issue a second type of alarm information according to the second judgment result, and control the sprinkler equipment according to the second type of alarm information.

[0079] Wherein, each sub-area is deployed with a plurality of sensor nodes; and the target sub-area is any one of the plurality of sub-areas.

[0080] A vegetation growth environment monitoring method provided by an embodiment of the present invention deploys sensor nodes to monitor environmental data in real time, uses image processing and other technologies to quantify vegetation characteristics, and combines prediction models and anomaly detection to provide data-driven scientific management and maintenance solutions, thereby reducing dependence on the experience of management personnel, improving management efficiency and accuracy, and ensuring high-quality vegetation management and maintenance.

[0081] In one implementation, by comparing real-time data with predicted data, abnormal nodes can be quickly identified, that is, areas where sensors fail or environmental conditions change abnormally. This anomaly detection mechanism helps to take timely remedial measures to prevent problems from escalating and ensure the healthy growth of vegetation.

[0082] In one implementation, the first preset time period may be 6 hours before the first target time.

[0083] In one implementation, this method can reduce the park maintenance company's reliance on personnel experience and reduce personnel training costs. New employees can also perform effective maintenance based on system data to ensure the stability of maintenance quality.

[0084] In one embodiment, the global image includes a multispectral image and an infrared thermal image; the vegetation characteristics include a normalized vegetation index, a leaf area index, and a leaf surface temperature; the baseline data include soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed, and precipitation; the prediction data include a predicted value of soil moisture, a predicted value of soil temperature, and a predicted value of soil nutrients;

[0085] Step S103 includes:

[0086] Step 1: According to the benchmark data, multiple environmental parameter monitoring values ​​at the second target time are combined into a target column vector.

[0087] Step 2: Calculate the normalized vegetation index based on the multispectral image, and calculate the leaf area index based on the normalized vegetation index.

[0088] Step three, obtaining the blade surface temperature based on the infrared thermal imaging at the second target moment.

[0089] Step 4: Concatenate the leaf surface temperature, normalized vegetation index, leaf area index and target column vector to obtain a feature column vector.

[0090] Step 5: Concatenate the feature column vectors of multiple monitoring moments within a preset time period to obtain a feature matrix.

[0091] Step six: Use the feature matrix as the input of the pre-trained prediction model to obtain the prediction data for the first target moment.

[0092] The first preset time period includes multiple monitoring moments; and the second target moment is any one of the multiple monitoring moments.

[0093] In one implementation, more comprehensive vegetation information can be obtained by combining multispectral images and infrared thermal imaging. The multispectral images can be obtained by drone photography, and the infrared thermal imaging can be obtained by an infrared thermal imager fixed at a high altitude.

[0094] In one implementation, soil parameters are predicted using parameter data highly correlated with soil temperature, soil moisture, and soil nutrients, which can improve prediction accuracy.

[0095] Parameter 1. Photosynthetically Active Radiation (PAR): Photosynthetically active radiation affects plant photosynthesis and transpiration. Higher photosynthetically active radiation increases plant transpiration, resulting in reduced soil moisture. Photosynthetically active radiation directly affects soil surface temperature. Stronger light radiation increases soil surface temperature. Photosynthetically active radiation indirectly affects plant demand for and absorption of soil nutrients by affecting plant photosynthesis and growth.

[0096] Parameter 2. Air temperature: Air temperature affects the evaporation rate of soil moisture. Higher air temperatures will accelerate the evaporation of soil moisture, thereby reducing soil moisture. Air temperature directly affects the temperature of the soil surface. Higher air temperatures usually lead to higher soil temperatures. Air temperature has an impact on soil microbial activity, which in turn affects the decomposition and release of soil nutrients. Higher temperatures usually promote microbial activity and are conducive to the release of nutrients.

[0097] Parameter 3. Air humidity: Air humidity affects the evaporation rate of water. Higher air humidity can slow down the evaporation of soil water, thereby increasing soil moisture.

[0098] Parameter 4. Wind speed: Wind speed affects the evaporation rate of water. Higher wind speed will directly speed up the evaporation of soil water, thereby reducing soil moisture. Wind speed affects soil temperature by promoting the evaporation of water on the soil surface. Higher wind speed can take away more heat and affect soil temperature. Wind speed also affects the transpiration rate of plants, thereby indirectly accelerating the absorption of water by plant roots, thereby reducing soil moisture.

[0099] Parameter 5. Precipitation: Precipitation directly increases soil moisture, thereby increasing soil humidity. Precipitation has little direct effect on soil temperature, but precipitation can affect soil thermal conductivity by wetting the soil surface, thus indirectly affecting temperature. Precipitation affects soil nutrient cycling. Large amounts of precipitation can wash away and dilute nutrients in the soil, but can also increase the availability of soil nutrients by promoting plant growth and the dissolution of nutrients.

[0100] Parameter 6. Normalized Difference Vegetation Index (NDVI): NDVI reflects the density and health of vegetation. Plant transpiration and root water absorption directly affect the maintenance of soil moisture. Areas with high NDVI usually have more plant cover, which helps reduce solar radiation on the soil surface and lower soil temperature. High NDVI usually means that plants are growing well and that plants have a strong ability to absorb soil nutrients.

[0101] Parameter 7. Leaf Area Index (LAI): LAI reflects the leaf area of ​​plants. Vegetation with large leaf area can reduce the evaporation of soil moisture, thereby maintaining higher soil moisture. Higher LAI values ​​are usually accompanied by denser vegetation cover, providing more shade and lowering soil temperature.

[0102] Parameter 8. Leaf surface temperature (LST): Leaf surface temperature can reflect the intensity of transpiration. High leaf surface temperature is usually associated with higher transpiration, thereby reducing soil moisture. Leaf surface temperature indirectly affects plant growth and nutrient absorption. Excessive temperature may affect plant health, thereby affecting the absorption of soil nutrients.

[0103] In one implementation, predictions can be made through a long short-term memory network (LSTM) model. LSTM relies on its special gating mechanism to effectively capture long-term dependencies in time series data and can provide more accurate predictions than traditional statistical models. The model includes an input layer, a first LSTM layer, a second LSTM layer, and three output layers; the predicted values ​​of soil moisture, soil temperature, and soil nutrients are obtained through independent output layers respectively;

[0104] The training process of the model includes:

[0105] 1. Data preparation

[0106] Collect the monitoring data of the environment and vegetation in the past two years, and extract the monitoring data when the vegetation is growing healthily as the sample data set;

[0107] The data set is divided into training set, validation set and test set in a ratio of 14:3:3;

[0108] Extract time series data from sample data according to the preset time step (30 minutes);

[0109] Split the time series data into subsequences of fixed length (number of time steps), for example, each subsequence can contain 12 time steps;

[0110] Create a corresponding label (the value of the next time step) for each subsequence;

[0111] Normalize the eigenvalues, that is, scale them to the range [0, 1].

[0112] 2. Training process

[0113] Input the training set subsequence into the model to obtain the prediction result;

[0114] Calculate the loss value based on the predicted results and the true label (using the root mean square error as the loss function);

[0115] Use the back-propagation algorithm to calculate the gradient and update the model parameters through the optimization algorithm (Adam optimizer);

[0116] Iterate training to complete multiple training cycles.

[0117] 3. Model Evaluation

[0118] Use the validation set to evaluate the model performance after each training cycle, and adjust the model's hyperparameters, such as the number of hidden units and learning rate, based on the evaluation results;

[0119] After training, the test set is used to evaluate the final performance of the model and calculate the loss and evaluation indicators on the test set, such as accuracy, F1 score, etc.

[0120] 4. Model Tuning

[0121] The model hyperparameters can be optimized using the sparrow search algorithm.

[0122] In one embodiment, step S104 includes:

[0123] Step 1: Calculate the offset value of the target parameter according to the predicted value and real-time monitoring value of the target parameter at the first target moment.

[0124] Step 2: Obtain an expected offset vector according to the offset values ​​at different times within a second preset time period.

[0125] Step 3: Calculate the offset standard deviation based on the expected offset vector.

[0126] Step 4: If the offset standard deviation is greater than the first preset threshold, it is determined that the sensor node corresponding to the target parameter is abnormal.

[0127] The target parameter is any one of soil moisture, soil temperature and soil nutrients.

[0128] In one implementation, the system can detect abnormal conditions in real time by calculating the offset between the real-time monitoring value and the predicted value. For example, if the actual value of soil moisture is offset from the predicted value by more than the expected range, it may indicate a sensor failure or an abnormal environmental condition. Accurately identifying abnormalities in sensor nodes helps to maintain and calibrate sensors in a timely manner, preventing the degradation of data quality from affecting subsequent analysis and decision-making. Timely detection of abnormal environmental conditions helps to maintain vegetation in a timely manner and prevent the expansion of disasters, such as insect infestations.

[0129] In one implementation, the second preset time period may be 5.5 hours before the first target time plus the first target time.

[0130] In one implementation, by accurately detecting and locating abnormal sensor nodes, resources can be effectively managed and allocated, reducing the need for manual inspection and improving the overall efficiency of the system.

[0131] In one embodiment, the plurality of local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information;

[0132] Step S105 includes:

[0133] Step 1: Use each high-definition image as an input to a pre-trained pest detection model to obtain a first judgment result.

[0134] Step 2: If the first judgment result is that there is insect pest, then generate insect pest alarm information.

[0135] Step three: if the first judgment result is that there is no insect pest, a fault alarm message is generated.

[0136] In one implementation, high-definition images can be used to capture vegetation details in greater detail, thereby improving the accuracy of pest detection. High-definition images can more clearly show signs of pests, such as insect holes and eggs, allowing detection models to identify smaller anomalies. High-definition images can be acquired by drones.

[0137] In one implementation, managers can take different actions based on different types of alarms (pest or fault). For example, a pest alarm may require the application of pesticides or physical removal, while a fault alarm may require checking sensors or image acquisition devices. By clarifying the alarm type, managers can allocate resources more specifically, optimize the processing process, and improve overall response efficiency and problem solving speed.

[0138] In one implementation, the pest detection model may be a YOLOv5 model, which is trained by collecting images of vegetation infested with pests.

[0139] In one embodiment, step S106 includes:

[0140] Step 1: Determine the threshold range of each environmental parameter according to the vegetation type of the target sub-area.

[0141] Step 2: If the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, the target environmental parameter is judged to be unqualified, and the judgment result is included in the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters.

[0142] In one embodiment, the sprinkler irrigation device includes a spraying mode and a drip irrigation mode; step S106 includes:

[0143] Step 1: Determine the threshold range of each environmental parameter according to the vegetation type of the target sub-area.

[0144] Step 2: If the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, the target environmental parameter is judged to be unqualified, and the judgment result is included in the second type of alarm information.

[0145] Step three: if the second type of alarm information contains information that the soil moisture is unqualified, the spraying mode of the sprinkler equipment is turned on.

[0146] Step 4: If the second type of alarm information contains information that the soil temperature is unqualified, the drip irrigation mode of the sprinkler equipment is turned on.

[0147] The target environment parameter is any one of multiple environment parameters.

[0148] In one implementation, different vegetation types have different requirements for environmental parameters, so setting threshold ranges based on specific vegetation types makes monitoring more accurate. For example, some plants are more sensitive to soil moisture, while others are more sensitive to temperature changes. This flexibility improves the adaptability and accuracy of monitoring.

[0149] In one implementation, the environmental parameters measured by the sensor are compared with the threshold parameters. If the parameters are not within the threshold range, a system warning is issued to notify relevant maintenance personnel to perform maintenance, thereby enhancing the timeliness and scientificity of vegetation maintenance.

[0150] In one implementation, the environment can be automatically controlled by linking the sprinkler irrigation equipment to ensure the quality of vegetation maintenance. The spraying mode and drip irrigation mode can be turned on at the same time to achieve efficient cooling and humidification.

[0151] In one embodiment, the collection of sensor data includes the following steps:

[0152] 1. Sensor connection: First, connect various types of sensors to the corresponding interfaces of the data acquisition instrument. These sensors are responsible for sensing and measuring physical parameters in the environment or equipment.

[0153] 2. Data acquisition: The sensor converts the detected physical quantity into electrical signals, and the data acquisition instrument converts these analog electrical signals into digital signals through its built-in analog-to-digital conversion (ADC) circuit.

[0154] 3. Data processing: The collected digital data will be initially processed inside the data collector. This may include data filtering to remove noise, data compression to reduce storage space requirements, etc.

[0155] 4. Data storage: The processed data will be temporarily stored in the internal memory of the collector, such as flash memory or random access memory (RAM).

[0156] 5. Data transmission: According to the preset time interval or trigger conditions, the data collector transmits the stored data to the host computer (such as computer, server) or cloud platform through wired (such as Ethernet, USB, etc.) or wireless (such as Wi-Fi, Bluetooth, cellular network, etc.) communication methods.

[0157] 6. Remote control and configuration: In some applications, administrators can use remote communication to configure parameters of the data logger, start / stop data collection, change data collection frequency, and so on.

[0158] The embodiment of the present invention provides a vegetation growth environment monitoring device. Figure 2 , Figure 2 This is a structural diagram of a vegetation growth environment monitoring device provided by an embodiment of the present invention. The device includes:

[0159] A partitioning module is used to divide the area according to the soil quality and vegetation type of the park to obtain multiple sub-areas; each sub-area is deployed with multiple sensor nodes;

[0160] A data acquisition module, used to acquire environmental monitoring data of a target sub-area, using environmental monitoring data within a first preset time period as baseline data, and using real-time monitoring values ​​of multiple environmental parameters at a first target moment as real-time data; the target sub-area is any one of the multiple sub-areas;

[0161] A prediction module is used to obtain a global image of the target sub-area, determine vegetation features based on the global image, and obtain prediction data based on the vegetation features and benchmark data;

[0162] The abnormal judgment module is used to determine abnormal nodes based on real-time data and predicted data;

[0163] A first alarm module is used to obtain multiple local images of the target sub-area if there is an abnormal node, and perform pest judgment based on the multiple local images to obtain a first judgment result, and generate and issue a first type of alarm information based on the first judgment result;

[0164] The second alarm module is used to determine whether the vegetation growth environment of the target sub-area is qualified based on real-time data if there are no abnormal nodes, obtain a second judgment result, generate and issue a second type of alarm information based on the second judgment result, and control the sprinkler equipment based on the second type of alarm information.

[0165] A vegetation growth environment monitoring device provided in an embodiment of the present invention can provide a data-driven scientific management and maintenance plan by deploying sensor nodes to monitor environmental data in real time, using image processing and other technologies to quantify vegetation characteristics, and combining prediction models and anomaly detection, thereby reducing dependence on the experience of management personnel and improving management efficiency and accuracy.

[0166] In one embodiment, the global image includes a multispectral image and an infrared thermal image; the vegetation characteristics include a normalized vegetation index, a leaf area index, and a leaf surface temperature; the baseline data include soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed, and precipitation; the prediction data include a predicted value of soil moisture, a predicted value of soil temperature, and a predicted value of soil nutrients;

[0167] The prediction module includes:

[0168] A first time step composition module is used to compose a target column vector from the monitoring values ​​of multiple environmental parameters at the second target time according to the benchmark data; the first preset time period includes multiple monitoring times; the second target time is any one of the multiple monitoring times;

[0169] A first vegetation feature calculation module is used to calculate a normalized vegetation index according to the multispectral image, and calculate a leaf area index according to the normalized vegetation index;

[0170] The second vegetation feature calculation module obtains the leaf surface temperature according to the infrared thermal imaging at the second target moment;

[0171] The second time step composition module is used to concatenate the leaf surface temperature, the normalized vegetation index, the leaf area index and the target column vector to obtain a feature column vector;

[0172] A feature determination module, used for concatenating feature column vectors of multiple monitoring moments within a first preset time period to obtain a feature matrix;

[0173] The model prediction module is used to use the feature matrix as the input of the pre-trained prediction model to obtain the prediction data at the first target moment.

[0174] In one embodiment, the abnormality determination module includes:

[0175] An offset value calculation module, used to calculate an offset value of a target parameter according to a predicted value and a real-time monitoring value of the target parameter at a first target time; the target parameter is any one of soil moisture, soil temperature, and soil nutrients;

[0176] A multi-time-step offset value statistics module, used to obtain an expected offset vector according to the offset values ​​at different times within a second preset time period;

[0177] A standard deviation calculation module, used for calculating the offset standard deviation according to the expected offset vector;

[0178] The abnormal node determination module is used to determine that the sensor node corresponding to the target parameter is abnormal if the offset standard deviation is greater than a first preset threshold.

[0179] In one embodiment, the plurality of local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information;

[0180] The first alarm module includes:

[0181] The pest detection module is used to use each high-definition image as an input of a pre-trained pest detection model to obtain a first judgment result;

[0182] The pest alarm module is used to generate pest alarm information if the first judgment result is that there is pest;

[0183] The fault alarm module is used to generate fault alarm information if the first judgment result is that there is no insect pest.

[0184] In one embodiment, the sprinkler irrigation device includes a spray mode and a drip irrigation mode;

[0185] The second alarm module includes:

[0186] A threshold determination module is used to determine the threshold range of each environmental parameter according to the vegetation type of the target sub-area;

[0187] A parameter alarm module, for judging that the target environmental parameter is unqualified if the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, and incorporating the judgment result into the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters;

[0188] A humidity control module, used for turning on the spraying mode of the sprinkler irrigation equipment if the second type of alarm information contains information that the soil humidity is unqualified;

[0189] The temperature control module is used to turn on the drip irrigation mode of the sprinkler irrigation equipment if the second type of alarm information contains information that the soil temperature is unqualified.

[0190] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A vegetation growth environment monitoring method, characterized in that: The method comprises: The park is divided into multiple sub-areas according to soil quality and vegetation type; multiple sensor nodes are deployed in each sub-area; Acquire environmental monitoring data of a target sub-area, use the environmental monitoring data within a first preset time period as baseline data, and use real-time monitoring values ​​of multiple environmental parameters at a first target moment as real-time data; the target sub-area is any one of the multiple sub-areas; Acquire a global image of the target sub-area, determine vegetation features according to the global image, and obtain prediction data according to the vegetation features and the benchmark data; Determine abnormal nodes according to the real-time data and the predicted data; If there is an abnormal node, multiple local images of the target sub-area are obtained, and pest judgment is performed based on the multiple local images to obtain a first judgment result, and a first type of alarm information is generated and issued based on the first judgment result; If there is no abnormal node, then determine whether the vegetation growth environment of the target sub-area is qualified based on the real-time data, obtain a second judgment result, generate and issue a second type of alarm information based on the second judgment result, and control the sprinkler equipment based on the second type of alarm information.

2. The vegetation growth environment monitoring method according to claim 1, characterized in that: The global image includes multispectral image and infrared thermal image; the vegetation characteristics include normalized vegetation index, leaf area index and leaf surface temperature; the benchmark data includes soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed and precipitation; the predicted data includes predicted value of soil moisture, predicted value of soil temperature and predicted value of soil nutrients; The determining of vegetation features according to the global image, and obtaining prediction data according to the vegetation features and the reference data includes: According to the benchmark data, the monitoring values ​​of multiple environmental parameters at the second target time are combined into a target column vector; the first preset time period includes multiple monitoring times; the second target time is any one of the multiple monitoring times; Calculating a normalized vegetation index according to the multispectral image, and calculating a leaf area index according to the normalized vegetation index; Obtaining the blade surface temperature according to the infrared thermal imaging at the second target moment; Concatenating the leaf surface temperature, the normalized vegetation index, the leaf area index and the target column vector to obtain a feature column vector; Concatenate the feature column vectors of multiple monitoring moments within the first preset time period to obtain a feature matrix; The feature matrix is ​​used as an input of a pre-trained prediction model to obtain prediction data at a first target moment.

3. The vegetation growth environment monitoring method according to claim 2, characterized in that: The determining of abnormal nodes according to the real-time data and the predicted data comprises: The offset value of the target parameter is calculated based on the predicted value and the real-time monitoring value of the target parameter at the first target time; the target parameter is any one of soil moisture, soil temperature, and soil nutrients; Obtaining an expected offset vector according to the offset values ​​at different times within the second preset time period; Calculating a standard deviation of an offset according to the expected offset vector; If the offset standard deviation is greater than a first preset threshold, it is determined that an abnormality occurs in the sensor node corresponding to the target parameter.

4. The vegetation growth environment monitoring method according to claim 3, characterized in that: The multiple local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information; The performing pest judgment according to the plurality of local images to obtain a first judgment result, and generating and issuing a first type of alarm information according to the first judgment result comprises: Using each high-definition image as an input to a pre-trained pest detection model to obtain a first judgment result; If the first judgment result is that there is an insect pest, generating an insect pest alarm message; If the first judgment result is that there is no insect pest, a fault alarm message is generated.

5. The vegetation growth environment monitoring method according to claim 3, characterized in that: The sprinkler irrigation equipment includes a spray mode and a drip irrigation mode; The method of judging whether the vegetation growth environment of the target sub-area is qualified according to the real-time data, obtaining a second judgment result, generating and issuing a second type of alarm information according to the second judgment result, and controlling the sprinkler irrigation equipment according to the second type of alarm information includes: Determining a threshold range of each environmental parameter according to the vegetation type of the target sub-area; If the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, the target environmental parameter is judged to be unqualified, and the judgment result is included in the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters; If the second type of alarm information contains information indicating that the soil moisture is unqualified, turning on the spraying mode of the sprinkler irrigation equipment; If the second type of alarm information contains information that the soil temperature is unqualified, the drip irrigation mode of the sprinkler irrigation equipment is turned on.

6. A vegetation growth environment monitoring device, characterized in that: The device comprises: A partitioning module is used to divide the area according to the soil quality and vegetation type of the park to obtain multiple sub-areas; each sub-area is deployed with multiple sensor nodes; A data acquisition module, used to acquire environmental monitoring data of a target sub-area, using the environmental monitoring data within a first preset time period as the baseline data, and using the real-time monitoring values ​​of multiple environmental parameters at a first target moment as the real-time data; the target sub-area is any one of the multiple sub-areas; A prediction module, used to obtain a global image of a target sub-area, determine vegetation features according to the global image, and obtain prediction data according to the vegetation features and the reference data; An abnormality judgment module, used to determine abnormal nodes according to the real-time data and the predicted data; A first alarm module, configured to obtain a plurality of local images of the target sub-area if an abnormal node exists, and perform pest judgment based on the plurality of local images to obtain a first judgment result, and generate and issue a first type of alarm information based on the first judgment result; The second alarm module is used to determine whether the vegetation growth environment of the target sub-area is qualified based on the real-time data if there are no abnormal nodes, obtain a second judgment result, generate and issue a second type of alarm information based on the second judgment result, and control the sprinkler equipment based on the second type of alarm information.

7. The vegetation growth environment monitoring device according to claim 6, characterized in that: The global image includes multispectral image and infrared thermal image; the vegetation characteristics include normalized vegetation index, leaf area index and leaf surface temperature; the benchmark data includes soil moisture, soil temperature, soil nutrients, photosynthetically active radiation, air temperature, air humidity, wind speed and precipitation; the predicted data includes predicted value of soil moisture, predicted value of soil temperature and predicted value of soil nutrients; The prediction module comprises: A first time step composition module is used to compose a target column vector from the monitoring values ​​of multiple environmental parameters at the second target time according to the benchmark data; the first preset time period includes multiple monitoring times; the second target time is any one of the multiple monitoring times; A first vegetation feature calculation module, used to calculate a normalized vegetation index according to the multispectral image, and calculate a leaf area index according to the normalized vegetation index; a second vegetation feature calculation module, which obtains the leaf surface temperature according to the infrared thermal imaging at the second target moment; A second time step composition module is used to concatenate the leaf surface temperature, the normalized vegetation index, the leaf area index and the target column vector to obtain a feature column vector; A feature determination module, used for concatenating feature column vectors of multiple monitoring moments within the first preset time period to obtain a feature matrix; The model prediction module is used to use the feature matrix as an input of a pre-trained prediction model to obtain prediction data at a first target moment.

8. The vegetation growth environment monitoring device according to claim 7, characterized in that: The abnormality judgment module comprises: an offset value calculation module, used to calculate the offset value of the target parameter according to the predicted value and the real-time monitoring value of the target parameter at the first target time; the target parameter is any one of soil moisture, soil temperature and soil nutrients; A multi-time-step offset value statistics module, used to obtain an expected offset vector according to the offset values ​​at different times within a second preset time period; A standard deviation calculation module, used to calculate the offset standard deviation according to the expected offset vector; The abnormal node determination module is used to determine that an abnormality occurs in the sensor node corresponding to the target parameter if the offset standard deviation is greater than a first preset threshold.

9. The vegetation growth environment monitoring device according to claim 8, characterized in that: The multiple local images include high-definition images of vegetation at each node; the first type of alarm information includes pest alarm information and fault alarm information; The first alarm module comprises: The pest detection module is used to use each high-definition image as an input of a pre-trained pest detection model to obtain a first judgment result; An insect pest alarm module, configured to generate an insect pest alarm message if the first judgment result is that there is an insect pest; A fault alarm module is used to generate fault alarm information if the first judgment result is that there is no insect pest.

10. The vegetation growth environment monitoring device according to claim 8, characterized in that: The sprinkler irrigation equipment includes a spray mode and a drip irrigation mode; The second alarm module comprises: A threshold determination module, used to determine the threshold range of each environmental parameter according to the vegetation type of the target sub-area; A parameter alarm module, for judging that the target environmental parameter is unqualified if the real-time monitoring value of the target environmental parameter exceeds the corresponding threshold range, and incorporating the judgment result into the second type of alarm information; the target environmental parameter is any one of the multiple environmental parameters; A humidity control module, configured to turn on the spraying mode of the sprinkler irrigation device if the second type of alarm information contains information indicating that the soil humidity is unqualified; The temperature control module is used to turn on the drip irrigation mode of the sprinkler irrigation equipment if the second type of alarm information contains information that the soil temperature is unqualified.

Images