Greening plant root growth monitoring system coupled with environment perception

Abstract

The application provides a greening plant root system growth monitoring system coupling an L system and environment perception, comprising: a sensor network containing a plurality of sensing nodes, each sensing node being configured to collect environmental factor data in a corresponding monitoring area and send the collected environmental factor data to an edge server; the edge server is configured to generate a three-dimensional root system fractal structure according to the environmental factor data uploaded by the sensor network; the early warning server is configured to calculate a growth deviation and generate first early warning information according to the three-dimensional root system fractal structure and the processed environmental factor data sent by the edge server. The application has comprehensive monitoring dimensions and extremely low power consumption, a dynamic response model capable of self-adaptive adjustment according to environmental data is constructed by dynamically coupling the plant root system growth rule and the L system growth model, the model is accurate, a double-channel early warning mechanism is adopted, and precise maintenance and regulation can be realized.

Description

Technical Field

[0001] This application relates to the field of urban green space plant maintenance technology, specifically to a greening plant root growth monitoring system that couples an L-system with environmental perception. Background Technology

[0002] The healthy growth of urban green space plants is crucial for maintaining urban ecological functions and landscape quality. As the primary organs for plant water and nutrient absorption, the root system's growth morphology is directly influenced by environmental factors. Organic matter content and soil moisture content are two of the most critical factors affecting root development and plant growth. The density, depth, biomass, and morphological configuration of plant roots are sensitive indicators reflecting the overall physiological state of the plant and soil suitability, indirectly and profoundly revealing the health status and sustainability of urban green space ecosystems. By monitoring plant roots, a scientific assessment and early warning of above-ground growth patterns and ecological functions can be achieved from the underground root system.

[0003] Currently, the monitoring of urban green space plants relies heavily on manual inspections or single-element environmental sensors, which mainly presents the following problems:

[0004] (1) Single monitoring dimension: Most existing systems only monitor soil moisture or temperature, neglecting the real-time perception of organic matter, an indicator of soil fertility, and cannot comprehensively assess the real environmental conditions for plant growth.

[0005] (2) The model is disconnected from the data: Most existing plant growth models are fixed-rule morphology generation tools that are not dynamically coupled with real-time environmental data and cannot reflect the impact of actual environmental stress on root growth;

[0006] (3) Lack of growth visualization: Traditional monitoring only provides numerical data, which makes it difficult to intuitively show the root growth process, which is not conducive to managers understanding the underground ecological process and making timely interventions.

[0007] Therefore, there is an urgent need for an intelligent monitoring system that can simultaneously sense soil organic matter and moisture, use this data to drive growth models in real time, and realize visualized simulation and early warning of root growth. Summary of the Invention

[0008] To address at least one of the above technical problems, this application provides a greening plant root growth monitoring system that couples an L-system with environmental perception.

[0009] A root growth monitoring system for green plants that couples an L-system with environmental perception includes:

[0010] A sensor network consists of several sensor nodes, each configured to collect environmental factor data within a corresponding monitoring area and send the collected environmental factor data to an edge server.

[0011] The edge server is configured to process environmental factor data uploaded from the sensor network, output dynamic instructions to drive the iteration of the L-system-based dynamic response model based on the empirical formula database and the processed environmental factor data, and drive the L-system-based dynamic response model to iteratively update through the dynamic instructions to generate a three-dimensional root fractal structure.

[0012] The early warning server is configured to receive the three-dimensional root fractal structure generated by the edge server, compare it with the ideal growth curve, and calculate the growth deviation; and to receive the environmental factor data processed by the edge server and compare it with the preset threshold.

[0013] Preferably, each sensing node includes:

[0014] The organic matter and key nutrient content sensor is configured to collect soil organic matter content and the concentration of key available nutrients nitrogen, phosphorus and potassium in the organic matter.

[0015] A soil volumetric moisture sensor is configured to collect the volumetric moisture content in the soil.

[0016] The microcontroller is configured to drive the organic matter and key nutrient content sensor and the soil volumetric moisture content sensor, receive and process the data collected by the organic matter and key nutrient content sensor and the soil volumetric moisture content sensor, and manage the wireless communication module.

[0017] The wireless communication module is configured to send data processed by the microcontroller to the edge server.

[0018] In any of the above solutions, the microcontroller is equipped with a timer, through which each sensing node is configured to adopt an intermittent working mode of timed wake-up—data acquisition—data transmission—sleep.

[0019] In any of the above schemes, it is preferable that each sensing node is connected to a solar power system to obtain electrical energy.

[0020] In any of the above embodiments, the edge server preferably includes a first processor, a first memory connected to the first processor, and a first communication interface, wherein:

[0021] The first memory is configured to store an empirical formula database, a dynamic response model based on the L system, and first computer instructions that can be executed by the first processor.

[0022] The first processor is configured to execute the first computer instructions to achieve:

[0023] The system receives multi-source heterogeneous environmental factor data sent by the sensor network through the first communication interface, performs noise reduction, compensation and fusion on the multi-source heterogeneous environmental factor data to obtain unified environmental factor data of the monitoring area, and sends the unified environmental factor data to the early warning server.

[0024] Based on an empirical formula database and unified environmental factor data for the monitoring area, a set of dynamic instructions is output to drive a dynamic response model based on the L-system; and

[0025] The dynamic response model based on the L system, driven by the dynamic command, generates a three-dimensional root fractal structure that matches the unified environmental factor data of the monitoring area, and sends the three-dimensional root fractal structure to the early warning server through the first communication interface.

[0026] In any of the above schemes, the first processor uses an adaptive Kalman filter algorithm to reduce noise in the multi-source heterogeneous data uploaded from the sensor network, combines a time-temperature calibration curve to dynamically compensate the denoised data, and uses a spatiotemporal fusion algorithm to integrate the data from multiple sensor nodes into unified environmental factor data for the monitoring area.

[0027] In any of the above schemes, the empirical formula database is configured as a structured, queryable response rule base, indexed by plant species and growth stage, with each record containing the input range of environmental factors, the corresponding morphological parameter adjustment algorithm, or a lookup table.

[0028] In any of the above schemes, the environmental factors include volumetric water content (θ), organic matter content (OM), and concentrations of key available nutrients nitrogen (N), phosphorus (P), and potassium (K); the morphological parameters include root growth rate (v), specific root length (SRL), branch density (ρ), branch angle (α), and growth discount factor.

[0029] Preferably, in any of the above schemes, the adjustment algorithm and lookup table are determined by systematically mining and engineering the knowledge of existing authoritative literature and public databases in the fields of plant physiology, root ecology and agricultural environment, combined with a large number of published control experiments and field observation studies, and the adjustment algorithm and lookup table have been statistically verified.

[0030] In any of the above schemes, the first processor is configured to drive the dynamic response model based on the L system to iterate at a frequency of not less than 1 Hz, generating a three-dimensional root fractal structure that evolves frame by frame.

[0031] In any of the above embodiments, the early warning server includes a second processor, a second memory connected to the second processor, a second communication interface, and a display output interface, wherein:

[0032] The second memory is configured to store second computer instructions that can be executed by the second processor;

[0033] The second processor is configured to execute the second computer instructions to achieve:

[0034] The system receives environmental factor data processed by the edge server through the second communication interface, compares it with a preset threshold range, and generates a first warning message when the threshold is exceeded.

[0035] The second communication interface receives the three-dimensional root fractal structure generated by the edge server, compares it with the corresponding ideal growth curve, calculates the growth deviation, and obtains the plant health rating.

[0036] The three-dimensional root fractal structure, the first early warning information, and the plant health rating are visualized through the display output interface.

[0037] Preferably, in any of the above solutions, the visualization is output using WebGL or a lightweight 3D engine format.

[0038] In any of the above embodiments, the second processor is preferably configured to execute the second computer instructions to achieve a precision maintenance function, namely, to establish an absorption efficiency model based on the three-dimensional root fractal structure generated by the edge server and the environmental factor data collected by the sensor network, and to predict and calculate the amount of water and nutrients required to maintain the healthy growth of the plant.

[0039] In any of the above schemes, the preferred method is to first analyze the correlation between the growth dynamics of the virtual root system generated by the dynamic modeling module of the L system and the soil water and fertilizer consumption during the same period in order to achieve the precise maintenance function, establish a plant absorption efficiency model, and then combine real-time environmental data to drive the simulation and prediction of root growth in the future period, as well as the monitoring data of current soil water and fertilizer reserves, to calculate the precise amount of water and various nutrients required to maintain healthy growth.

[0040] The coupled L-system of this application and the environmentally sensitive green plant root growth monitoring system have the following beneficial effects.

[0041] 1. Comprehensive monitoring dimensions and high data value: The core soil fertility indicators and soil moisture content are monitored synchronously and in real time, and the data obtained can more realistically and comprehensively reflect the soil environment for plant growth.

[0042] 2. Precise model for growth visualization and prediction: By dynamically coupling the growth patterns of plant roots with the L-system growth model, a dynamic response model that can adaptively adjust to environmental data is constructed. This not only enables real-time measurement of soil parameters but also allows for high-fidelity simulation and visualization of the three-dimensional dynamic growth process of roots, achieving quantitative assessment of root growth status and short-term trend prediction with significantly improved accuracy.

[0043] 3. Extremely low power consumption and strong engineering practicality: The sensor network adopts an intermittent working mode of timed wake-up, data acquisition, data transmission and sleep. Combined with low-power chips and efficient solar power supply, the sensor network can operate for a long time without mains power, making it fully suitable for the application scenarios of dispersed and unattended urban green spaces, and greatly reducing deployment and maintenance costs.

[0044] 4. Dual-channel early warning mechanism: A dual-channel intelligent early warning mechanism combining "soil parameter threshold early warning" and "growth model status early warning" has been constructed, so that risk signals from either side can be responded to in a timely and complete manner, providing accurate and timely decision-making basis for greening maintenance.

[0045] 5. Precision maintenance and regulation: By predicting the future water and fertilizer needs of plants, a forward-looking precision regulation plan is generated, which transforms maintenance operations from passive response to proactive planning. Through demand-driven precision intervention, the overall scientific nature and management efficiency of urban greening maintenance are improved. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the overall structure of a preferred embodiment of the green plant root growth monitoring system coupled with the L system and environmental perception according to the present invention.

[0047] Figure 2 For example, the coupling L system and the environmental sensing green plant root growth monitoring system according to the present invention Figure 1 A schematic diagram of the sensor node in the embodiment shown.

[0048] Figure 3 For example, the coupling L system and the environmental sensing green plant root growth monitoring system according to the present invention Figure 1 A schematic diagram of the edge server in the embodiment shown.

[0049] Figure 4 For example, the coupling L system and the environmental sensing green plant root growth monitoring system according to the present invention Figure 1 A schematic diagram of the structure of the early warning server in the embodiment shown.

[0050] Figure 5 For example, the coupling L system and the environmental sensing green plant root growth monitoring system according to the present invention Figure 1The illustrated embodiment is a schematic diagram of its workflow.

[0051] Figure 6 This is a schematic diagram showing the relationship between the growth discount factor and soil organic matter / moisture content.

[0052] Figures 7-9 These are simulated root systems of a herbaceous plant after 60 days of growth under different growth discount coefficients.

[0053] The component names indicated by the reference numerals in the figure are as follows:

[0054] 1-Sensor network, 11-Sensing node, 111-Organic matter and key nutrient content sensor, 112-Soil volumetric moisture content sensor, 113-Microcontroller, 114-Wireless communication module; 2-Edge server, 21-First processor, 22-First memory, 23-First communication interface, 3-Early warning server, 31-Second processor, 32-Second memory, 33-Second communication interface, 34-Display output interface, 4-Solar power supply system. Detailed Implementation

[0055] To better understand the present invention, the present invention will be described in detail below with reference to specific embodiments.

[0056] Example 1

[0057] like Figure 1 As shown, a greening plant root growth monitoring system coupled with an L-system and environmental perception includes:

[0058] Sensor network 1 includes several sensor nodes 11, each of which is configured to collect environmental factor data within a corresponding monitoring area and send the collected environmental factor data to edge server 2.

[0059] Edge server 2 is configured to process environmental factor data uploaded by sensor network 1, output dynamic instructions to drive the iteration of dynamic response model based on L system according to empirical formula database and processed environmental factor data, and drive the dynamic response model based on L system to iteratively update through dynamic instructions to generate three-dimensional root fractal structure.

[0060] The early warning server 3 is configured to receive the three-dimensional root fractal structure generated by the edge server 2 and compare it with the ideal growth curve to calculate the growth deviation; and to receive the environmental factors processed by the edge server 2 and compare them with the preset threshold.

[0061] like Figure 2 As shown, each sensing node 11 includes:

[0062] The organic matter and key nutrient content sensor 111 is configured to collect soil organic matter content and the concentration of key available nutrients nitrogen, phosphorus and potassium in the organic matter.

[0063] Soil volumetric moisture sensor 112 is configured to collect the volumetric moisture content in the soil;

[0064] The microcontroller 113 is configured to drive the organic matter and key nutrient content sensor 111 and the soil volumetric moisture content sensor 112 to work, receive and process the data collected by the organic matter and key nutrient content sensor 111 and the soil volumetric moisture content sensor 112, and manage the wireless communication module 113.

[0065] The wireless communication module 114 is configured to send data processed by the microcontroller 113 to the edge server 2.

[0066] The microcontroller 113 is equipped with a timer, through which each sensor node 11 is configured to operate in an intermittent mode of timed wake-up, data acquisition, data transmission, and sleep. Each sensor node 11 is connected to the solar power system 4 to obtain electrical energy.

[0067] Specifically, the sensor network 1 is the key hardware foundation of the monitoring system. Each sensor node 11 adopts a modular design, facilitating installation, maintenance, and replacement. When setting up the sensor nodes 11, they are rationally arranged according to the area of ​​the monitoring region and the density of plant distribution. Each sensor node 11 undergoes protective treatment to effectively resist soil pollution and corrosion. The organic matter and key nutrient content sensor 111 in the sensor node 11 can measure the organic matter content in the soil while simultaneously detecting the concentrations of key available nutrients nitrogen (N), phosphorus (P), and potassium (K) in the organic matter through specific chemically sensitive materials or near-infrared spectral characteristics, providing a data basis for directly assessing the immediate fertility supply level of the soil. The soil volumetric water content sensor 112 in the sensor node 11, based on the principles of time-domain reflectometry or frequency-domain reflectometry, accurately senses the moisture content in the soil and measures the soil volumetric water content, providing a data basis for determining the water availability of plants. The microcontroller 113 in the sensing node 11 uses a low-power chip (such as the STM32L4 series), and the wireless communication module 114 also uses a low-power wireless communication chip (such as the LoRa communication module). The microcontroller 113 has a built-in timer, which can wake up the sensing node 11 according to a preset period, so that each sensing node 11 works intermittently in the mode of timed wake-up-data acquisition-data transmission-sleep. The low-power chip combined with the intermittent working mode of the sensing node 11 enables the static power consumption of the sensing node 11 to be controlled within 50 microamps, thereby significantly extending the continuous working time of the sensing node 11 under solar power supply, and providing a guarantee for the large-area, long-term stable acquisition of environmental factor data.

[0068] The solar power supply system 4 can be implemented using existing technology. In this embodiment, it is preferred that the energy collection unit in the solar power supply system 4 adopts a lightweight flexible monocrystalline silicon solar panel, which can be bent and attached to irregular surfaces such as light poles and pergolas to maximize the use of urban space for photovoltaic power generation. It adopts an MPPT charging management chip, which can track the maximum power point of the solar panel in real time and provide high energy collection efficiency even under low light conditions.

[0069] like Figure 3 As shown, the edge server 2 includes a first processor 21, a first memory 22 connected to the first processor 21, and a first communication interface 23, wherein:

[0070] The first memory 22 is configured to store an empirical formula database, a dynamic response model based on the L system, and first computer instructions that can be executed by the first processor 21.

[0071] The first processor 21 is configured to execute the first computer instructions to achieve:

[0072] The system receives multi-source heterogeneous environmental factor data sent by sensor network 1 through the first communication interface 23, performs noise reduction, compensation and fusion on the multi-source heterogeneous environmental factor data to obtain unified environmental factor data of the monitoring area, and sends the unified environmental factor data to the early warning server 3.

[0073] Based on an empirical formula database and unified environmental factor data for the monitoring area, a set of dynamic instructions is output to drive a dynamic response model based on the L-system; and

[0074] The dynamic response model based on the L system, driven by the dynamic instruction, generates a three-dimensional root fractal structure that matches the unified environmental factor data of the monitoring area, and sends the three-dimensional root fractal structure to the early warning server 3 through the first communication interface 23.

[0075] The first processor 21 uses an adaptive Kalman filter algorithm to reduce noise in the multi-source heterogeneous data uploaded by the sensor network 1, combines the time-temperature calibration curve to dynamically compensate the denoised data, and uses a spatiotemporal fusion algorithm to integrate the data of multiple sensor nodes 11 into unified environmental factor data of the monitoring area. Through the above operations, the accuracy of the data uploaded by the sensor network 1 can be effectively guaranteed, and the randomness of single-point measurement can be overcome.

[0076] The empirical formula database is configured as a structured, queryable response rule base, indexed by plant species and growth stage. Each record contains the input range of environmental factors and the corresponding morphological parameter adjustment algorithm or lookup table. The environmental factors include soil volumetric water content (θ), organic matter content (OM), and concentrations of key available nutrients nitrogen (N), phosphorus (P), and potassium (K). The morphological parameters include root growth rate (v), specific root length (SRL), branch density (ρ), branch angle (α), and growth discount coefficient. The adjustment algorithm and lookup table are determined through systematic knowledge mining and engineering reconstruction of existing authoritative literature and public databases in plant physiology, root ecology, and agricultural environment, combined with numerous published controlled experiments and field observation studies. Furthermore, the adjustment algorithm and lookup table have been statistically validated. The first processor 21 is configured to drive the L-system-based dynamic response model iteratively at a frequency of not less than 1 Hz, generating a frame-by-frame evolving three-dimensional root fractal structure.

[0077] It should be noted that the edge server 2 is deployed near the monitoring area to avoid data delays caused by long-distance data transmission. The first processor 21 adopts a high-performance industrial-grade processor (such as Intel Core i5 / i7 series or ARM Cortex-A9 series) to ensure that it has strong data processing and parallel computing capabilities, and can effectively process the massive amount of diverse and heterogeneous data uploaded by the sensor network 1. The first memory 22 preferably adopts a large-capacity solid-state drive. In addition to storing empirical formula databases, dynamic response models based on L-systems, and first computer instructions that can be executed by the first processor 21, it can also be used to store raw data, processed data, and generated three-dimensional root fractal structure data uploaded by the sensor network 1, which facilitates subsequent querying, tracing, and data analysis. The first communication interface 23 adopts a combination of wired communication interface (such as Ethernet interface) and wireless communication interface (such as LoRa communication interface), so that it can communicate with the early warning server 3 through the wired communication interface and communicate with the sensor network 1 through the wireless communication interface. It also supports communication with other peripherals (such as computers and mobile phones) to facilitate data viewing and function debugging by maintenance personnel.

[0078] like Figure 4 As shown, the early warning server 3 includes a second processor 31, a second memory 32 connected to the second processor 31, a second communication interface 33, and a display output interface 34, wherein:

[0079] The second memory 32 is configured to store second computer instructions that can be executed by the second processor 31;

[0080] The second processor 31 is configured to execute the second computer instructions to achieve:

[0081] The second communication interface 33 receives environmental factor data processed by the edge server 2, compares it with a preset threshold range, and generates a first warning message when the threshold is exceeded.

[0082] The second communication interface 33 receives the three-dimensional root fractal structure generated by the edge server 2, compares it with the corresponding ideal growth curve, calculates the growth deviation, and obtains the plant health rating.

[0083] The three-dimensional root fractal structure, the first early warning information, and the plant health rating are visualized through the display output interface 34.

[0084] The visualization is output using WebGL or a lightweight 3D engine format.

[0085] The second processor 31 is also configured to execute the second computer instructions to achieve a precise maintenance function, namely, based on the three-dimensional root fractal structure generated by the edge server 2 and the environmental factor data collected by the sensor network 1, to establish an absorption efficiency model and predict and calculate the amount of water and nutrients required to maintain healthy plant growth. To achieve this precise maintenance function, the correlation between the growth dynamics of the virtual root system generated by the dynamic modeling module of the L system in the recent period and the corresponding soil water and fertilizer consumption is analyzed to establish a plant absorption efficiency model. Then, combined with real-time environmental data to drive the simulation and prediction of root growth in the future period, and the current soil water and fertilizer storage monitoring data, the precise amount of water and various nutrients required to maintain healthy growth is calculated.

[0086] It should be noted that the early warning server 3 is deployed in the monitoring center, which facilitates centralized monitoring of multiple monitoring areas. The first processor 31 adopts a high-performance processor (such as the Intel Xeon series), which has strong computing and data processing capabilities. The second memory 32 adopts a large-capacity disk array or solid-state drive to store preset threshold ranges, ideal growth curves, early warning information, health rating data, three-dimensional root fractal structure data, precision maintenance data, etc., supporting long-term storage and fast query of massive amounts of data. The second communication interface 33 adopts a high-speed Ethernet interface to realize high-speed data interaction with the edge server 2. The display output interface 34 adopts common interfaces such as HDMI and VGA, which can be connected to display devices such as monitors and projectors, facilitating real-time viewing of various data and early warning information.

[0087] like Figure 5 As shown, the workflow of the coupled L system and the environmental sensing green plant root growth monitoring system includes:

[0088] Step 1: The sensor node collects soil environmental factor data and sends it to the edge server in a "timed wake-up - data collection - data transmission - sleep" mode;

[0089] Step 2: The edge server receives environmental factor data, processes it to obtain unified environmental factor data for the monitoring area; based on the unified environmental factor data, a set of dynamic instructions is obtained to drive the dynamic response model based on the L system, resulting in a three-dimensional root fractal structure; the unified environmental factor data and the three-dimensional root fractal structure are sent to the early warning server.

[0090] Step 3: The early warning server compares the unified environmental factor data with the preset threshold range to generate the first early warning information; it compares the three-dimensional root fractal structure with the ideal growth curve to obtain the growth deviation and plant health rating; it provides precise maintenance suggestions; and it displays the information visually.

[0091] Specifically, in step 1, the organic matter and key nutrient content sensors in the sensing nodes collect the soil organic matter content and the concentrations of key available nutrients nitrogen, phosphorus, and potassium in the organic matter, and the soil volumetric water content sensor collects the volumetric water content in the soil. The microcontroller performs simple processing (such as analog-to-digital conversion) on the environmental factor data collected by the sensors and then sends it to the edge server through the wireless communication module.

[0092] In step 2, after the edge server receives the environmental factor data:

[0093] First, the environmental factor data is denoised using an adaptive Kalman filter algorithm. Then, the denoised data is dynamically compensated using a time-temperature calibration curve. Finally, the dynamic compensation data from multiple sensor nodes is fused using a spatiotemporal fusion algorithm to obtain unified environmental factor data.

[0094] Then, based on the unified environmental factor data, by querying the empirical formula database, morphological parameters that match the unified environmental factor data are determined. The morphological parameters include root growth rate (v), specific root length (SRL), branch density (ρ), branch angle (α), and growth discount coefficient. The morphological parameters are related to the plant species and growth stage. Based on the morphological parameters, a set of dynamic instructions is formed to drive the dynamic response model based on the L system.

[0095] Then, the dynamic instruction drives the dynamic response model based on the L system to update and iterate at a frequency of not less than 1Hz, generating a three-dimensional root fractal structure that evolves frame by frame and matches the unified environmental factor data of the monitoring area.

[0096] Finally, the unified environmental factor data and the three-dimensional root fractal structure are sent to the early warning server.

[0097] It should be noted that in step 2, the growth discount coefficient is an instantaneous input factor of the dynamic response model based on the L system. It is obtained by querying the empirical formula database based on unified environmental factor data at each calculation time. It is a parameter that drives the next growth step of the dynamic response model based on the L system, and it simulates the limitation of environmental factor data on the future growth potential of the root system.

[0098] It should be further explained that, compared with the traditional L system, in step 2, the morphological parameters are dynamically updated based on unified environmental factor data, and the dynamically updated morphological parameters are injected into the iteration rules of the L system to replace the fixed morphological parameters in the traditional L system. This realizes a dynamic response model based on the L system and finally generates a three-dimensional root fractal structure that accurately matches the current environment, so that the virtual root system simulated by the model can perceive and respond to changes in soil conditions like a real plant.

[0099] In step 3, after the early warning server receives the unified environmental factor data and the three-dimensional root fractal structure:

[0100] First, the early warning server compares the unified environmental factor data with the preset threshold range. When the preset threshold range is exceeded, the first early warning information is generated. The first early warning information includes whether the environmental factor data is normal, abnormal, or severely abnormal.

[0101] At the same time, the early warning server compares the three-dimensional root fractal structure with the ideal growth curve to obtain the growth deviation and plant health rating, which includes healthy, lagging, and severely lagging.

[0102] Finally, the first warning information, growth deviation, and plant health rating are displayed visually.

[0103] It should be noted that the growth deviation is a core diagnostic indicator used to quantify the overall difference between the actual growth state of plant roots at a specific time point and the theoretical state that should be achieved under ideal conditions at the same age. It assesses the deviation between the cumulative results of root development and the expected goal. It is obtained by comparing the overall root state simulated by the model up to the current moment with the ideal baseline state at that moment at a specific and comparable time point (such as a specific growth age).

[0104] It should be further explained that the early warning server can also achieve precise maintenance function. That is, based on the three-dimensional root fractal structure generated by the edge server and the environmental factor data collected by the sensor network, it establishes an absorption efficiency model to predict and calculate the amount of water and nutrients required to maintain healthy plant growth. Specifically, it first analyzes the correlation between the growth dynamics of the virtual root system generated by the dynamic modeling module of the L system and the soil water and fertilizer consumption during the same period in the recent period (e.g., the past 7-10 days) to establish a plant absorption efficiency model. Then, it combines real-time environmental data to drive the simulation prediction of root growth in the future period (e.g., 1-3 days) and the current soil water and fertilizer storage monitoring data to calculate the precise amount of water and various nutrients required to maintain healthy growth. For example, if the early warning server predicts that the root biomass will increase by 5% in the next 48 hours, combined with the absorption efficiency model and the current soil moisture content, it can give a precise maintenance suggestion: "To maintain the best growth potential, it is recommended to implement pulse irrigation in the coordinate (X,Y) area, with a water replenishment of Z liters." This represents a fundamental shift from "watering and fertilizing based on the current state of the soil" to "precise replenishment based on the future needs of plants," greatly improving resource utilization efficiency and the scientific nature of maintenance.

[0105] To more intuitively demonstrate the impact of environmental factors on plant root growth, Figure 6 A schematic diagram illustrating the relationship between the growth discount factor determined in the edge server and the soil organic matter / moisture content is shown. Figure 7, Figure 8 and Figure 9 The following diagrams show the root system simulations of a certain herbaceous plant after 60 days of growth, with growth discount factors of 1.0, 0.8, and 0.6, respectively. Figure 6 It can be seen that within the optimal range of soil organic matter / moisture content, the growth discount coefficient is 1, meaning that environmental factors do not restrict root growth; the greater the deviation from the optimal range, the lower the growth discount coefficient, meaning that environmental factors impose greater restrictions on root growth. Figure 7 , Figure 8 , Figure 9 It can also be observed that the root growth of this herbaceous plant is at its best when the growth discount factor is 1.0, while the root growth of this herbaceous plant deteriorates significantly when the growth discount factor is 0.6.

[0106] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the foregoing embodiments have described the present invention in detail, those skilled in the art should understand that modifications can be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein, and these substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the present invention.

Claims

1. A root growth monitoring system for green plants that couples an L-system with environmental sensing, characterized in that: include: A sensor network consists of several sensor nodes, each configured to collect environmental factor data within a corresponding monitoring area and send the collected environmental factor data to an edge server. The edge server is configured to process environmental factor data uploaded from the sensor network, output dynamic instructions to drive the iteration of the L-system-based dynamic response model based on the empirical formula database and the processed environmental factor data, and drive the L-system-based dynamic response model to iteratively update through the dynamic instructions to generate a three-dimensional root fractal structure. The early warning server is configured to receive the three-dimensional root fractal structure generated by the edge server, compare it with the ideal growth curve, and calculate the growth deviation; and to receive the environmental factor data processed by the edge server and compare it with the preset threshold.

2. The green plant root growth monitoring system coupled with the L system and environmental perception as described in claim 1, characterized in that: Each sensing node includes: The organic matter and key nutrient content sensor is configured to collect soil organic matter content and the concentration of key available nutrients nitrogen, phosphorus and potassium in the organic matter. A soil volumetric moisture sensor is configured to collect the volumetric moisture content in the soil. The microcontroller is configured to drive the organic matter and key nutrient content sensor and the soil volumetric moisture content sensor, receive and process the data collected by the organic matter and key nutrient content sensor and the soil volumetric moisture content sensor, and manage the wireless communication module. The wireless communication module is configured to send data processed by the microcontroller to the edge server.

3. The green plant root growth monitoring system coupled with the L system and environmental perception as described in claim 2, characterized in that: The microcontroller is equipped with a timer, through which each sensing node is configured to operate in an intermittent mode of timed wake-up, data acquisition, data transmission, and sleep.

4. The greening plant root growth monitoring system coupled with the L system and environmental perception as described in claim 2, characterized in that: Each sensor node is connected to a solar power system to obtain electrical energy.

5. The greening plant root growth monitoring system coupled with the L system and environmental perception as described in claim 1, characterized in that: The edge server includes a first processor, a first memory connected to the first processor, and a first communication interface, wherein: The first memory is configured to store an empirical formula database, a dynamic response model based on the L system, and first computer instructions that can be executed by the first processor. The first processor is configured to execute the first computer instructions to achieve: The system receives multi-source heterogeneous environmental factor data sent by the sensor network through the first communication interface, performs noise reduction, compensation and fusion on the multi-source heterogeneous environmental factor data to obtain unified environmental factor data of the monitoring area, and sends the unified environmental factor data to the early warning server. Based on an empirical formula database and unified environmental factor data for the monitoring area, a set of dynamic instructions is output to drive a dynamic response model based on the L-system; and The dynamic response model based on the L system, driven by the dynamic command, generates a three-dimensional root fractal structure that matches the unified environmental factor data of the monitoring area, and sends the three-dimensional root fractal structure to the early warning server through the first communication interface.

6. The greening plant root growth monitoring system coupled with the L system and environmental perception as described in claim 5, characterized in that: The first processor uses an adaptive Kalman filter algorithm to reduce noise in the multi-source heterogeneous data uploaded from the sensor network, combines a time-temperature calibration curve to dynamically compensate the denoised data, and uses a spatiotemporal fusion algorithm to integrate the data from multiple sensor nodes into unified environmental factor data for the monitoring area.

7. The green plant root growth monitoring system coupled with the L system and environmental perception as described in claim 5, characterized in that: The empirical formula database is configured as a structured, queryable response rule base, indexed by plant species and growth stage. Each record contains the input range of environmental factors and the corresponding morphological parameter adjustment algorithm or lookup table. The environmental factors include volumetric water content (θ), organic matter content (OM), and concentrations of key available nutrients nitrogen (N), phosphorus (P), and potassium (K). The morphological parameters include root growth rate (v), specific root length (SRL), branch density (ρ), branch angle (α), and growth discount factor.

8. The greening plant root growth monitoring system coupled with the L system and environmental perception as described in claim 5, characterized in that: The first processor is configured to drive the dynamic response model based on the L system to iterate at a frequency of not less than 1 Hz, generating a three-dimensional root fractal structure that evolves frame by frame.

9. The green plant root growth monitoring system coupled with environmental perception as described in claim 1, characterized in that: The early warning server includes a second processor, a second memory connected to the second processor, a second communication interface, and a display output interface, wherein: The second memory is configured to store second computer instructions that can be executed by the second processor; The second processor is configured to execute the second computer instructions to achieve: The system receives environmental factor data processed by the edge server through the second communication interface, compares it with a preset threshold range, and generates a first warning message when the threshold is exceeded. The second communication interface receives the three-dimensional root fractal structure generated by the edge server, compares it with the corresponding ideal growth curve, calculates the growth deviation, and obtains the plant health rating. The three-dimensional root fractal structure, the first early warning information, and the plant health rating are visualized through the display output interface.

10. The greening plant root growth monitoring system coupled with the L system and environmental perception as described in claim 9, characterized in that: The second processor is also configured to execute the second computer instructions to achieve a precision maintenance function, namely, to establish an absorption efficiency model based on the three-dimensional root fractal structure generated by the edge server and the environmental factor data collected by the sensor network, and to predict and calculate the amount of water and nutrients required to maintain the healthy growth of the plant.

Images