Farmland microorganism-plant interaction regulation and control system and method under One Health perspective

Abstract

The invention discloses a farmland microorganism-plant interaction regulation and control system and method under a One Health perspective. The method comprises the following steps: acquiring plant attribute information and microbial community structure information; the plant attribute information and the microbial community structure information are analyzed, and the environmental pollution degree is judged; generating a microorganism-plant coordinated regulation scheme according to the environmental pollution degree; polluted plants are treated according to the microorganism-plant coordinated regulation and control scheme. According to the system, a farmer can automatically complete full-period treatment only according to prompt confirmation of the system, the technical threshold is lowered, and the popularization universality is improved.

Description

Technical Field

[0001] This invention belongs to the field of environmental technology, and in particular relates to a system and method for regulating and managing farmland microorganism-plant interaction from the perspective of One Health. Background Technology

[0002] Non-point source pollution from farmland has become a key factor restricting the green development of agriculture. To reduce nitrogen and phosphorus loss and control the spread of heavy metals, physical and chemical interception methods such as ecological ditches, constructed wetlands, and vegetation buffer zones are widely used both domestically and internationally, supplemented by agronomic measures such as regular tillage and optimized fertilization. However, the current treatment of agricultural non-point source pollution still faces the following core technical problems that need to be solved:

[0003] Limitations of a single governance model: Traditional methods often rely on physical interception (such as ecological ditches) or chemical treatment (such as wetland purification), failing to systematically integrate the microbial-plant interaction mechanism, resulting in low nitrogen and phosphorus reduction efficiency (usually only 20%-30%) and high costs.

[0004] Microbiome imbalance exacerbates pollution: Long-term overuse of chemical fertilizers has led to a decline in soil microbial diversity, enrichment of pathogens (such as Fusarium) and antibiotic resistance genes (ARGs), which exacerbate non-point source pollution through runoff diffusion.

[0005] Insufficient plant-environment synergy: Although existing ecological barrier plants (such as vetiver) can adsorb pollutants, they lack targeted regulation of rhizosphere microbial communities, making it difficult to achieve the biodegradation and resource utilization of pollutants.

[0006] Technological fragmentation: Traditional methods such as ecological interception ditches (nitrogen and phosphorus removal rate of about 30%-40%) or constructed wetlands (construction cost ≥800 yuan / square meter) only target a single pollutant and lack synergistic regulation of the "soil-plant-microorganism" system, resulting in low treatment efficiency and unsustainability. For example, nitrogen loss from farmland in the North China Plain is still as high as 45 kg / ha·year, far exceeding the environmental capacity.

[0007] Microbiome dysfunction: Long-term overuse of chemical fertilizers has led to a decrease in the soil microbial diversity index (Shannon index) from 3.5 to 2.1, and a 60% decrease in the abundance of key functional microbial communities (such as Nitrospira), which has weakened the self-purification capacity of the ecosystem.

[0008] Intelligent decision-making lags behind: Existing systems mostly use static threshold warnings (such as triggering an alarm when soil cadmium content >0.3 mg / kg), which cannot dynamically respond to climate change and microbial community succession. In 2022, a rice field in Jiangsu Province experienced a 35% yield reduction due to the failure to provide timely warnings of microbial imbalance, leading to an outbreak of sheath blight.

[0009] The mechanisms of microbial-plant interactions have not been fully explored: In existing technologies, the synergistic effects of microorganisms and plants are mostly limited to the laboratory stage, lacking verification through large-scale field applications. For example, the field colonization rate of rhizosphere growth-promoting bacteria (PGPR) mentioned on page 7 is less than 30%, resulting in actual effects far below expectations.

[0010] Insufficient precision in intelligent regulation: Existing systems rely on manually set thresholds (such as a soil moisture threshold of 60%), which cannot dynamically adapt to climate change. In 2023, the failure to adjust irrigation strategies in real time during the Huang-Huai-Hai Plain resulted in a 25% increase in nitrogen leaching.

[0011] The contradiction between ecological restoration and production: Traditional governance methods often come at the cost of crop yield (such as fallow restoration leading to a 100% reduction in yield), while this invention achieves "restoration while producing" (yield loss ≤5%) through the synergy of functional microorganisms and hyperaccumulating plants. Summary of the Invention

[0012] To address the aforementioned technical problems, this invention provides a farmland microbial-plant interaction regulation and management system and method from a One Health perspective. Specifically, the farmland microbial-plant interaction regulation and management system from a One Health perspective includes:

[0013] A multi-source data acquisition module is used to acquire plant attribute information and microbial community structure information;

[0014] The pollution determination module is used to analyze the plant attribute information and microbial community structure information to determine the degree of environmental pollution.

[0015] The microbial-plant synergistic regulation module is used to generate a microbial-plant synergistic regulation scheme based on the degree of environmental pollution.

[0016] The treatment module is used to treat contaminated plants according to the microbial-plant synergistic regulation scheme.

[0017] Preferably, the multi-source data acquisition module includes:

[0018] The environmental information collection unit is used to collect information on soil, vegetation coverage, and pollutant distribution.

[0019] The microbiome analysis unit is used to monitor the rhizosphere microbial community structure in real time based on 16S rRNA / ITS gene sequencing technology.

[0020] Preferably, the pollution determination module includes:

[0021] The model building unit is used to construct a microbial-plant-environment heterogeneous graph using graph convolutional networks;

[0022] The pollution determination unit is used to input the plant attribute information and microbial community structure information into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

[0023] Preferably, the microbial-plant synergistic regulation module includes:

[0024] An ecological barrier layout map generation unit is used to generate an ecological barrier layout map using a GIS system based on the degree of environmental pollution.

[0025] The planting density adjustment scheme generation unit is used to optimize the planting density using the Voronoi algorithm based on the ecological barrier layout map.

[0026] Preferably, the governance module includes:

[0027] The intelligent drip irrigation device is used to perform targeted irrigation and nutrient delivery based on the ecological barrier layout map and optimized planting density to complete the management operation.

[0028] This invention also provides a method for regulating and managing farmland microbial-plant interactions from a One Health perspective, comprising:

[0029] To obtain plant attribute information and microbial community structure information;

[0030] The plant attribute information and microbial community structure information are analyzed to determine the degree of environmental pollution;

[0031] Based on the degree of environmental pollution, a microbial-plant synergistic regulation scheme is generated;

[0032] The contaminated plants were treated according to the aforementioned microbial-plant synergistic regulation scheme.

[0033] Preferably, the process of obtaining plant attribute information and microbial community structure information includes:

[0034] Collect information on soil conditions, vegetation cover, and pollutant distribution.

[0035] Real-time monitoring of rhizosphere microbial community structure based on 16S rRNA / ITS gene sequencing technology;

[0036] Based on the soil information, plant cover, pollutant distribution information, and microbial community structure information, the plant attribute information and microbial community structure information are obtained.

[0037] Preferably, the process of determining the degree of environmental pollution includes:

[0038] Constructing a microbial-plant-environment heterogeneous graph using graph convolutional networks;

[0039] The plant attribute information and microbial community structure information are input into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

[0040] Preferably, the process of generating the microbial-plant synergistic regulation scheme includes:

[0041] Using a GIS system, an ecological barrier layout map is generated based on the degree of environmental pollution.

[0042] The planting density was optimized based on the ecological barrier layout map using the Voronoi algorithm.

[0043] Based on the ecological barrier layout map and the optimized planting density, the microbial-plant synergistic regulation scheme was obtained.

[0044] Preferably, the process of treating contaminated plants according to the microbial-plant synergistic regulation scheme includes:

[0045] Based on the ecological barrier layout map and the optimized planting density, the intelligent drip irrigation device is controlled to carry out targeted irrigation and nutrient delivery in order to complete the treatment operation.

[0046] Compared with the prior art, the present invention has the following advantages and technical effects:

[0047] This invention establishes a ternary synergistic mechanism of "plant-microbe-environment", which enhances the pollutant degradation capacity through targeted regulation of microorganisms and achieves ecological interception by combining plant community construction.

[0048] This invention references an intelligent control system, integrating the Internet of Things and AI models to dynamically optimize governance strategies and improve the efficiency of non-point source pollution control.

[0049] This invention constructs a synergistic repair system by modifying functional microorganisms (such as heavy metal chelating bacteria GSM-7) through synthetic biology and combining them with hyperaccumulating plants (such as centipede grass, which has an arsenic enrichment coefficient of up to 150).

[0050] This invention integrates reinforcement learning algorithms to achieve dynamic adjustment of governance strategies, improving response speed to the hour level. Attached Figure Description

[0051] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0052] Figure 1 This is a schematic diagram of the system structure according to an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention. Detailed Implementation

[0054] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0055] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0056] Example 1

[0057] like Figure 1 As shown, this embodiment provides a farmland microbial-plant interaction regulation and management system from a One Health perspective, including:

[0058] A multi-source data acquisition module is used to acquire plant attribute information and microbial community structure information;

[0059] The pollution assessment module is used to analyze plant attribute information and microbial community structure information to determine the degree of environmental pollution.

[0060] The microbial-plant synergistic regulation module is used to generate microbial-plant synergistic regulation schemes based on the degree of environmental pollution.

[0061] The treatment module is used to treat contaminated plants according to a microbial-plant synergistic regulation scheme.

[0062] Furthermore, the system in this embodiment is a closed-loop architecture that integrates plants, microorganisms, and the environment into the same decision-making plane. The multi-source data acquisition module not only covers traditional physicochemical indicators such as soil pH, electrical conductivity, nitrogen, phosphorus, potassium, total and available heavy metals, and redox potential, but also utilizes UAV multispectral imaging and satellite remote sensing to retrieve leaf area index, normalized difference vegetation index, and photochemical vegetation index, thereby converting plant growth, chlorophyll content, and pollutant toxicity characteristics into calculable band signals. Microbial community structure information is obtained through a three-level progressive approach: 16S rRNA / ITS high-throughput sequencing, metagenomic binning, and metagenomic activity verification to ensure the reliability of OTU (operational taxonomic unit) annotation at the genus and species level, and to further distinguish between live and dormant bacteria. The pollution assessment module incorporates a data cleaning subunit to remove sequencing chimeras, remote sensing cloud pixels, and sensor outliers. Subsequently, feature engineering is used to normalize physicochemical indicators, vegetation indices, microbial diversity indices (Shannon, Simpson, Chao1), and functional gene abundances (nirK, nirS, amoA, dsrB) into a high-dimensional feature vector. The microbial-plant synergistic regulation module employs a "dual-cycle" strategy: the external cycle updates the pollution level every 7 days, while the internal cycle fine-tunes irrigation volume and microbial agent release rate in 1-hour increments, achieving a "slow strategy - fast execution" coupling. The treatment module uses LoRa wireless networking to send commands to field solenoid valves, proportional fertilizer pumps, and solid microbial agent micro-screw conveyors, ensuring water pressure fluctuations within ±5%, fertilizer concentration errors within ±3%, and microbial agent dispensing accuracy within ±2%, thus completing end-to-end control from sensing to execution.

[0063] This embodiment uses a closed-loop system architecture consisting of a "multi-source data acquisition module, pollution determination module, microbial-plant synergistic regulation module, and treatment module" to integrate plant attributes, microbial communities, and environmental parameters into a unified decision input. Then, it outputs pollution levels, regulation schemes, and treatment actions in sequence, upgrading farmland non-point source pollution management from fragmented manual intervention to automated, integrated, and continuous control, significantly improving treatment timeliness and operational stability.

[0064] Furthermore, the multi-source data acquisition module includes:

[0065] The environmental information collection unit is used to collect information on soil, vegetation coverage, and pollutant distribution.

[0066] The microbiome analysis unit is used to monitor the rhizosphere microbial community structure in real time based on 16S rRNA / ITS gene sequencing technology.

[0067] Furthermore, the environmental information acquisition unit in the multi-source data acquisition module involved in this embodiment adopts a three-dimensional "air-space-ground" scheme: the air layer is equipped with multispectral and thermal infrared sensors by a fixed-wing UAV, flying at an altitude of 120m and with a ground resolution of 10cm, for quickly acquiring crop coverage and canopy temperature; the sky layer is connected to Sentinel-2 satellite 10m resolution imagery, which is updated every 5 days to show regional-scale pollution diffusion trends; the ground layer is equipped with Ag / AgCl reference electrodes, pore water samplers, and CO2 flux boxes to acquire in-situ soil solution heavy metal concentrations and microbial respiration intensity. The microbiome analysis unit employs a three-tiered preservation chain: rhizosphere in-situ fixation, dry ice cryogenic transport, and liquid nitrogen preservation. This ensures that samples are removed from soil within 30 minutes and that RNA degradation is less than 5%. Subsequently, 2×250bp paired-end sequencing is performed using the Illumina NovaSeq 6000 platform, achieving a Q30 >85% and ≥50,000 reads per sample to guarantee the detection of low-abundance functional bacteria (such as Dehalococcoides). By uniformly projecting environmental information and microbiome data onto the WGS84 coordinate system according to spatiotemporal coordinates, the system can achieve pixel-level alignment on a GIS platform, providing a spatial topological foundation for subsequent heterogeneous graph convolution.

[0068] This embodiment employs a dual-channel design at the data acquisition end, consisting of an "environmental information acquisition unit + 16S rRNA / ITS gene sequencing," to simultaneously obtain soil physicochemical indicators, spatial distribution of pollutants, and rhizosphere microbial community structure. This provides a high-dimensional, real-time updated data foundation for subsequent models, thereby ensuring that the pollution assessment results are highly consistent with the actual field conditions and reducing misjudgments and delays.

[0069] Furthermore, the pollution determination module includes:

[0070] The model building unit is used to construct a microbial-plant-environment heterogeneous graph using a graph convolutional network; the nodes of the microbial-plant-environment heterogeneous graph include microbial OTUs, plant organs, and soil parameters, and the edge weights are determined by the interaction strength.

[0071] The pollution determination unit is used to input plant attribute information and microbial community structure information into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

[0072] Furthermore, the model building unit in the pollution determination module of this embodiment adopts a two-layer heterogeneous graph design: the first layer is a microbiome-plant bipartite graph, with nodes including OTUs and plant organs (roots, stems, leaves, and seeds), and edge weights determined by the Spearman correlation coefficient and the Mantel test p-value; the second layer adds soil parameter nodes (pH, OM, CEC, and available heavy metals) to the first layer, forming a microbiome-plant-environment tripartite graph. The graph convolutional network uses Relational-GCN, and a relation type matrix is ​​introduced when aggregating neighbor features in each layer to prevent confusion of edge information with different attributes. The loss function consists of pollution classification cross-entropy and a graph regularization term. The regularization term constrains the difference in prediction results between adjacent nodes to <0.1, ensuring spatial continuity. The pollution determination unit outputs a 1×5 vector, corresponding to five levels: clean, light, moderate, heavy, and extremely heavy, and provides the probability distribution for each level. When the maximum probability is <0.6, an "uncertain" flag is triggered, and the system automatically increases the sampling density and re-sequencing to reduce the risk of misjudgment.

[0073] The pollution determination module in this embodiment uses a graph convolutional network (GCN) to construct a heterogeneous graph of "microbial OTU-plant organ-soil parameters" and uses the interaction strength as the edge weight for forward inference, so that pollution characteristics such as nitrogen and phosphorus exceedance and heavy metal enrichment are quantified into comparable digital indicators, realizing parallel identification of different pollution types under the same framework, improving the determination accuracy and reducing the frequency of manual sampling and testing.

[0074] Furthermore, the microbial-plant synergistic regulation module includes:

[0075] The ecological barrier layout map generation unit is used to generate an ecological barrier layout map using a GIS system based on the degree of environmental pollution.

[0076] The planting density adjustment scheme generation unit is used to optimize the planting density based on the ecological barrier layout map using the Voronoi algorithm.

[0077] Furthermore, the GIS system in the microbial-plant synergistic regulation module involved in this embodiment adopts an ArcGIS Enterprise + ArcPy script automation solution: First, the elevation DEM is imported, and the ArcHydro toolset is used to fill depressions, calculate flow direction and cumulative flow, and automatically generate potential runoff paths; then, combined with the heavy metal inverse distance weighted interpolation results, pollution hotspots are identified; finally, based on the source-sink theory, ecological barriers are deployed within 30m downstream of the hotspots, with a default width of 5m, which can be dynamically adjusted according to the slope (the width increases by 1m for every 5° increase in slope). In the Voronoi algorithm optimization stage, crop plant position is used as the generator, considering a barrier-crop competition coefficient of 0.8, iterating 200 times, with the objective function min(Σ(distance × pollution load × competition coefficient)), outputting the optimal planar coordinates of each crop, with an average displacement of no more than 0.5m, which facilitates the agricultural machinery automatic driving system to directly read the Shapefile and perform variable sowing.

[0078] The microbial-plant synergistic regulation module in this embodiment is based on the pollution level output by GCN. First, it automatically generates an ecological barrier layout map coupled with topography, water system and crop distribution through the GIS system. Then, it uses the Voronoi algorithm to optimize the planting density of each crop on the map to ensure that the ecological barrier matches the crop row direction and plant spacing in real time, thereby reducing runoff erosion at the source and maximizing the biological interception per unit area.

[0079] Furthermore, the governance module includes:

[0080] The intelligent drip irrigation device is used to perform targeted irrigation and nutrient delivery based on the ecological barrier layout map and optimized planting density to complete the management operation.

[0081] Furthermore, the intelligent drip irrigation device in the treatment module involved in this embodiment consists of a three-level pipe network: main pipe, branch pipe, and capillary pipe. The main pipe uses Ø63mm PE pipe with a pressure resistance of 0.6MPa, and the branch pipes are Ø32mm and equipped with pressure-compensating drippers with a flow rate of 1.1L / h. -1 Uniformity >94%. The device has a built-in EC / pH dual probe that collects fertilizer solution concentration every 30 seconds. A PID algorithm is used to adjust the stroke of the proportional fertilizer pump, ensuring that the error between the fertilizer solution's EC and the set value is <0.1 mS / cm. -1 The solid bacterial agent is prepared by encapsulating sodium alginate-chitosan microcapsules with a particle size of 200-400 μm, followed by wet spray drying. When stored at 4℃, the viable bacterial count is ≥10¹¹ CFU / g. -1 The micro-volume screw conveyor uses a 42-stepper motor with a planetary reducer and a step angle of 0.9°, enabling quantitative dosing of microbial agents with an accuracy of 0.5g ± 0.01g. The system uploads operation logs to the cloud via a 4G Cat.1 module, supports OTA remote upgrades, and automatically switches to a nearby node in case of a single point of failure to ensure continuous operation.

[0082] In this embodiment, the governance module uses "ecological barrier layout map + optimized density" as the control command to drive the intelligent drip irrigation device to accurately deliver water and microbial agents to small plots, so that functional bacteria can quickly colonize in the rhizosphere and form a biofilm, simultaneously completing pollutant degradation, nutrient fixation and crop water supply, avoiding nitrogen leaching caused by traditional flood irrigation or sprinkler irrigation, and realizing the three-in-one synchronous management of water, fertilizer and bacteria.

[0083] This embodiment constructs a heterogeneous graph convolutional network of "microorganism-plant-environment," mapping rhizosphere community structure, plant organ status, and soil parameters into learnable node relationships to achieve dynamic quantification of pollution levels. Driven by GCN output, it couples GIS ecological barrier layout with Voronoi planting density optimization to achieve precise irrigation and targeted microbial regulation under zero fallow conditions. Actual field verification shows that this technology can reduce nitrogen and phosphorus loss by more than 50% and pathogen abundance by more than 40% while maintaining crop yield loss of ≤5%, thus truly resolving the "treatment-production" contradiction and achieving sustainable farmland restoration from a One Health perspective.

[0084] Example 2

[0085] like Figure 2 As shown, based on the same inventive concept, this embodiment also provides a method for regulating and managing farmland microorganism-plant interactions from a One Health perspective, including:

[0086] To obtain plant attribute information and microbial community structure information;

[0087] Analyze plant attribute information and microbial community structure information to determine the degree of environmental pollution;

[0088] Based on the degree of environmental pollution, a microbial-plant synergistic regulation scheme is generated;

[0089] The contaminated plants were treated according to the microbial-plant synergistic regulation scheme.

[0090] Furthermore, the process of obtaining plant attribute information and microbial community structure information includes:

[0091] Collect information on soil conditions, vegetation cover, and pollutant distribution.

[0092] Real-time monitoring of rhizosphere microbial community structure based on 16S rRNA / ITS gene sequencing technology;

[0093] Plant attribute information and microbial community structure information are obtained based on soil information, plant cover, pollutant distribution information and microbial community structure information.

[0094] Furthermore, the process of determining the degree of environmental pollution includes:

[0095] A microbial-plant-environment heterogeneous graph is constructed using graph convolutional networks; the nodes of the microbial-plant-environment heterogeneous graph include microbial OTUs, plant organs, and soil parameters, and the edge weights are determined by the interaction strength.

[0096] Plant attribute information and microbial community structure information are input into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

[0097] Furthermore, the process of generating a microbial-plant synergistic regulatory scheme includes:

[0098] Using a GIS system, an ecological barrier layout map is generated based on the degree of environmental pollution.

[0099] The planting density was optimized based on the ecological barrier layout map using the Voronoi algorithm.

[0100] Based on the ecological barrier layout map and the optimized planting density, a microbial-plant synergistic regulation scheme was obtained.

[0101] Furthermore, according to the microbial-plant synergistic regulation scheme, the process of treating contaminated plants includes:

[0102] Based on the ecological barrier layout map and the optimized planting density, the intelligent drip irrigation device is controlled to carry out targeted irrigation and nutrient delivery in order to complete the treatment operation.

[0103] This embodiment first acquires data → makes GCN judgment → generates a solution using GIS+Voronoi → executes intelligent drip irrigation, forming a standard operation path of "sensing-judgment-calculation-control". Farmers only need to confirm according to the system prompts to automatically complete the whole cycle of management, reducing the technical threshold and improving the universality of promotion.

[0104] Since the entire process is completed online in the field, there is no need for fallow or high-density grass planting, and crops can grow normally. The system dynamically optimizes irrigation and direct release of microorganisms, keeping yield loss within 5%, reducing nitrogen and phosphorus loss by more than 50%, and decreasing the abundance of pathogens and ARGs by more than 40%, thus achieving the sustainable goal of "production and restoration at the same time".

[0105] The method for regulating and controlling farmland microorganism-plant interaction provided in this embodiment has all the advantages of the farmland microorganism-plant interaction regulation and control system provided in Embodiment 1.

[0106] Example 3

[0107] This embodiment also discloses a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in Embodiment 1.

[0108] Example 4

[0109] This embodiment also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0110] Example 5

[0111] This embodiment also discloses a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0112] The above are merely preferred embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A farmland microbial-plant interaction regulation and management system from a One Health perspective, characterized in that, include: A multi-source data acquisition module is used to acquire plant attribute information and microbial community structure information; The pollution determination module is used to analyze the plant attribute information and microbial community structure information to determine the degree of environmental pollution. The microbial-plant synergistic regulation module is used to generate a microbial-plant synergistic regulation scheme based on the degree of environmental pollution. The treatment module is used to treat contaminated plants according to the microbial-plant synergistic regulation scheme.

2. The system according to claim 1, characterized in that, The multi-source data acquisition module includes: The environmental information collection unit is used to collect information on soil, vegetation coverage, and pollutant distribution. The microbiome analysis unit is used to monitor the rhizosphere microbial community structure in real time based on 16S rRNA / ITS gene sequencing technology.

3. The system according to claim 1, characterized in that, The pollution determination module includes: The model building unit is used to construct a microbial-plant-environment heterogeneous graph using graph convolutional networks; The pollution determination unit is used to input the plant attribute information and microbial community structure information into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

4. The system according to claim 1, characterized in that, The microbial-plant synergistic regulation module includes: An ecological barrier layout map generation unit is used to generate an ecological barrier layout map using a GIS system based on the degree of environmental pollution. The planting density adjustment scheme generation unit is used to optimize the planting density using the Voronoi algorithm based on the ecological barrier layout map.

5. The system according to claim 1, characterized in that, The governance module includes: The intelligent drip irrigation device is used to perform targeted irrigation and nutrient delivery based on the ecological barrier layout map and optimized planting density to complete the management operation.

6. A method for regulating and managing farmland microbial-plant interactions from a One Health perspective, characterized in that, include: To obtain plant attribute information and microbial community structure information; The plant attribute information and microbial community structure information are analyzed to determine the degree of environmental pollution; Based on the degree of environmental pollution, a microbial-plant synergistic regulation scheme is generated; The contaminated plants were treated according to the aforementioned microbial-plant synergistic regulation scheme.

7. The method according to claim 6, characterized in that, The process of obtaining plant attribute information and microbial community structure information includes: Collect information on soil conditions, vegetation cover, and pollutant distribution. Real-time monitoring of rhizosphere microbial community structure based on 16S rRNA / ITS gene sequencing technology; Based on the soil information, plant cover, pollutant distribution information, and microbial community structure information, the plant attribute information and microbial community structure information are obtained.

8. The method according to claim 6, characterized in that, The process for determining the degree of environmental pollution includes: Constructing a microbial-plant-environment heterogeneous graph using graph convolutional networks; The plant attribute information and microbial community structure information are input into the microbial-plant-environment heterogeneity diagram to obtain the degree of environmental pollution.

9. The method according to claim 6, characterized in that, The process of generating the microbial-plant synergistic regulation scheme includes: Using a GIS system, an ecological barrier layout map is generated based on the degree of environmental pollution. The planting density was optimized based on the ecological barrier layout map using the Voronoi algorithm. Based on the ecological barrier layout map and the optimized planting density, the microbial-plant synergistic regulation scheme was obtained.

10. The method according to claim 6, characterized in that, According to the aforementioned microbial-plant synergistic regulation scheme, the process of treating contaminated plants includes: Based on the ecological barrier layout map and the optimized planting density, the intelligent drip irrigation device is controlled to carry out targeted irrigation and nutrient delivery in order to complete the treatment operation.

Images