An intelligent farmland condition monitoring and early warning method and system

Abstract

The application discloses an intelligent farmland condition monitoring and early warning method and system, comprising the following steps: constructing a three-dimensional geographic model of a monitored farmland, and dividing the model into a plurality of agricultural monitoring grids; acquiring multi-source farmland condition data, predicting the farmland condition risk level of each grid through a machine learning model, screening high-level grids as target early warning areas, and identifying risk sources and initial monitoring points; establishing a multi-objective decision model based on the spatial coverage, data acquisition accuracy and deployment cost of the initial monitoring points, solving the model by using a genetic algorithm to determine the optimized monitoring points; simulating the farmland condition evolution of the optimized monitoring points in extreme scenarios, screening the optimized monitoring points with a stability index higher than a preset value as final farmland condition early warning nodes, and generating a dynamic monitoring network. The application changes the problem of one-sided farmland condition evaluation and inaccurate risk area positioning in the prior art, and can more timely and accurately respond to farmland condition changes, and significantly enhances the reliability and stability of the monitoring system under complex and extreme conditions.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of crop monitoring, and in particular to an intelligent crop monitoring and early warning method and system. BACKGROUND

[0002] In the field of agricultural production, accurate and efficient crop monitoring and early warning is of great importance. However, the existing crop monitoring and early warning technology has many shortcomings. Traditional crop monitoring methods often rely on manual field investigation, which is not only inefficient, but also difficult to achieve comprehensive and real-time monitoring of large areas of farmland. For example, plant protection personnel obtain crop disease and pest information through manual inspection and visual inspection, which is a huge workload and the accuracy is greatly influenced by personal experience, and the automation and intelligence level is seriously insufficient.

[0003] Some monitoring systems that use sensors and other technologies have achieved a certain degree of automation in data collection, but there are obvious shortcomings in data processing and analysis. On the one hand, the data sources are relatively single, and cannot comprehensively cover the key information of crop growth stages, making it difficult to accurately assess the crop condition. On the other hand, the existing systems lack precision and foresight in risk prediction and early warning, and cannot effectively screen out high-risk areas and develop countermeasures in advance. In addition, the existing technology lacks a scientific optimization method for the layout of monitoring points, resulting in low overall efficiency and poor stability of the monitoring network, and it is difficult to ensure accurate acquisition and timely warning of crop information in extreme situations. SUMMARY

[0004] In order to solve at least one of the above technical problems, the present application provides an intelligent crop monitoring and early warning method and system.

[0005] In a first aspect, the present application provides an intelligent crop monitoring and early warning method, which comprises:

[0006] A three-dimensional geographic model of the monitored farmland is constructed, the model is divided into grids based on soil type, crop distribution and terrain data, and a plurality of agricultural monitoring grids are generated;

[0007] Multi-source crop condition data is obtained, including soil moisture condition, weather index, crop growth stage and historical pest data, the crop condition risk level of each grid is predicted by a machine learning model, the agricultural monitoring grid with a risk level exceeding a preset threshold is selected as a target early warning area, and the risk source and initial monitoring point in the target early warning area are identified;

[0008] The spatial coverage, data acquisition accuracy and deployment cost of the initial monitoring point are taken as optimization objectives, a multi-objective decision model is established, the constraint conditions include the maximum response distance of the monitoring point and the risk source, the minimum data update frequency and the cost upper limit, and an improved genetic algorithm is used to solve the model to determine the optimized monitoring point;

[0009] The simulation optimization monitoring point evolves the farmland condition in extreme scenarios. A stability index is calculated based on the early warning accuracy, response timeliness, and cost fluctuation rate. The optimization monitoring points with a stability index higher than a preset value are selected as the final farmland condition early warning nodes, and a dynamic monitoring network is generated.

[0010] Preferably, the prediction of the farmland condition risk level of each grid by the machine learning model comprises:

[0011] A feature set is constructed, which includes soil pH, nitrogen, phosphorus, and potassium content, cumulative precipitation, temperature difference fluctuation rate, crop disease resistance index, and historical disaster frequency.

[0012] A random forest algorithm is used to train a risk prediction model. The model parameters are optimized through cross-validation, and the probability distribution of drought risk, waterlogging risk, and pest and disease risk of each grid is output.

[0013] The comprehensive risk level is generated by weighted summation according to the risk probability, and the high, medium, and low risk areas are divided. The high risk area is mapped to the target early warning area.

[0014] Preferably, the construction of the multi-objective decision model comprises defining a single objective function, which includes:

[0015] Maximizing spatial coverage:

[0016] ;

[0017] In the formula, is the spatial coverage, is the effective coverage area of the i-th monitoring point, reflecting the physical range of the monitoring point that can collect data, and there are a total of N monitoring points, , is the terrain attenuation coefficient, which quantifies the weakening effect of terrain complexity (such as slope, vegetation density) on coverage effect; is the reference area threshold, which is used to adjust the sensitive interval of the logical function to ensure the nonlinear mapping characteristics of the coverage rate Maximizing data accuracy:

[0018]

[0019] ;

[0020] In the formula, is the data accuracy, is the sensor resolution; is the Euclidean distance between the monitoring point and the risk source; is the data calibration frequency, , is the weight factor;

[0021] ​​Minimize deployment cost:

[0022] ;

[0023] wherein, is the deployment cost, is the hardware cost, is the communication link cost, is the maintenance cost, is the cost coefficient;

[0024] The above single-objective function is fused into a multi-objective decision model by fuzzy analytic hierarchy process, and constraint conditions are added:

[0025] ;

[0026] ;

[0027] ;

[0028] wherein, is the early warning response time, is the upper limit of the early warning response time, is the total cost threshold, is the minimum data accuracy requirement.

[0029] Preferably, the extreme scenario includes:

[0030] Meteorological extreme event: spatiotemporal distribution pattern of continuous drought, heavy rain and flood, low temperature and frost damage;

[0031] Biological disaster event: coupling relationship between pest and disease spread path, egg hatching rate and crop susceptible period;

[0032] Human intervention event: simulation of soil salinization caused by irrigation interruption and excessive fertilization.

[0033] Preferably, the simulation optimizes the crop condition evolution of the monitoring points under the extreme scenario, including:

[0034] Constructing a multi-dimensional scenario library according to the extreme scenario;

[0035] Based on computational fluid dynamics and Agent-Based model, dynamically deduce the propagation trajectory of the risk source in various scenarios, and evaluate the data capture efficiency and early warning delay of the monitoring nodes to generate simulation results;

[0036] According to the simulation results, calculate the stability index:

[0037] ;

[0038] wherein, is the stability score, To improve the accuracy of early warnings, The average response time, Cost volatility; For normalized weights.

[0039] Preferably, the method further includes:

[0040] The monitoring network topology is updated in real time through collaborative inspections by drone swarms and ground sensors.

[0041] When a sudden increase in local risk level is detected, the monitoring point density adaptive adjustment algorithm is automatically triggered to add mobile monitoring nodes in the target area, while shutting down redundant nodes in low-risk areas to reduce energy consumption.

[0042] Secondly, the present invention also provides an intelligent agricultural condition monitoring and early warning system, the system comprising:

[0043] Grid division units are used to construct a three-dimensional geographic model of the monitored farmland. The model is divided into grids based on soil type, crop distribution and terrain data to generate multiple agricultural monitoring grids.

[0044] The monitoring point screening unit is used to acquire multi-source agricultural data, including soil moisture, meteorological indicators, crop growth stages and historical pest and disease data. It uses machine learning models to predict the agricultural risk level of each grid, screens agricultural monitoring grids with risk levels exceeding a preset threshold as target early warning areas, and identifies risk sources and initial monitoring points within the target early warning areas.

[0045] The monitoring point optimization unit is used to establish a multi-objective decision model with the initial monitoring point spatial coverage, data acquisition accuracy and deployment cost as optimization objectives. The constraints include the maximum response distance between the monitoring point and the risk source, the minimum data update frequency and the cost limit. An improved genetic algorithm is used to solve the model to determine the optimal monitoring points.

[0046] The early warning node determination unit is used to simulate and optimize the evolution of agricultural conditions at monitoring points under extreme scenarios. Based on the early warning accuracy, response timeliness, and cost volatility, it calculates stability indicators, selects optimized monitoring points with stability indicators higher than preset values ​​as the final agricultural early warning nodes, and generates a dynamic monitoring network.

[0047] Thirdly, the present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the method as described in the first aspect above and any possible implementation thereof.

[0048] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in the first aspect above and any possible implementation thereof.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0050] This invention constructs a three-dimensional geographic model of the farmland to be monitored and divides it into grids based on soil type, crop distribution, and topographic data. This allows for precise subdivision of farmland into multiple agricultural monitoring grids, laying the foundation for subsequent refined monitoring. After acquiring multi-source agricultural data, a machine learning model is used to predict the agricultural risk level of each grid. This efficiently selects agricultural monitoring grids with risk levels exceeding a preset threshold as target early warning areas and accurately identifies risk sources and initial monitoring points, overcoming the previous problems of one-sided agricultural assessments and inaccurate risk area location. By establishing a multi-objective decision-making model and using an improved genetic algorithm to solve it, optimal monitoring points are determined. This process fully considers key factors such as spatial coverage of monitoring points, data acquisition accuracy, and deployment costs. Compared to the traditional arbitrary or unreasonable layout of monitoring points, this significantly improves the scientific rigor and rationality of the monitoring network, effectively controlling costs while ensuring data quality. By simulating and optimizing the evolution of agricultural conditions at monitoring points under extreme scenarios, and calculating stability indicators based on early warning accuracy, response timeliness, and cost volatility, optimized monitoring points with stability indicators higher than preset values ​​are selected as the final agricultural condition early warning nodes, and a dynamic monitoring network is generated. This significantly enhances the reliability and stability of the monitoring system under complex and extreme conditions, enabling it to respond to changes in agricultural conditions more promptly and accurately, providing strong support for agricultural production, and realizing the transformation from traditional extensive agricultural condition monitoring and early warning to a precise, efficient, intelligent, and stable modern agricultural condition monitoring and early warning model.

[0051] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the accompanying drawings used in the embodiments of the present invention or the background art will be described below.

[0053] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the specification, serve to illustrate the technical solutions of this disclosure.

[0054] Figure 1 A flowchart illustrating an intelligent agricultural condition monitoring and early warning method provided in an embodiment of the present invention;

[0055] Figure 2 for Figure 1 A flowchart illustrating the sub-steps of step S20;

[0056] Figure 3 This is a schematic diagram of the structure of an intelligent agricultural condition monitoring and early warning system provided in an embodiment of the present invention;

[0057] Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0060] Please see Figure 1 , Figure 1 This is a flowchart illustrating an intelligent agricultural condition monitoring and early warning method provided in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0061] S10. Construct a three-dimensional geographic model of the farmland to be monitored, and divide the model into grids based on soil type, crop distribution and terrain data to generate multiple agricultural monitoring grids;

[0062] Traditional agricultural monitoring relies on manual sampling, which is insufficient to cover complex terrain and diverse planting structures. Three-dimensional models can intuitively reflect the three-dimensional structure of farmland, and grid-based division can subdivide the monitoring area into controllable units, improving monitoring accuracy.

[0063] Topographic elevation data was acquired using LiDAR from drones, and crop distribution was extracted by combining this with satellite remote sensing imagery. A spatial distribution model of soil types was constructed using soil sampling points. A continuous topographic surface was generated using Kriging interpolation, and grids were created at resolutions of 50m×50m or 100m×100m using ArcGIS grid analysis tools. Each grid was assigned attributes such as soil texture, fertility level, and crop variety. This standardized monitoring unit provides a unified spatial framework for subsequent multi-source data fusion, improving monitoring coverage compared to traditional methods.

[0064] S20. Acquire multi-source agricultural data, including soil moisture, meteorological indicators, crop growth stages and historical pest and disease data. Predict the agricultural risk level of each grid through machine learning models, screen agricultural monitoring grids with risk levels exceeding preset thresholds as target early warning areas, and identify risk sources and initial monitoring points within the target early warning areas.

[0065] A single data source cannot fully reflect changes in agricultural conditions. Machine learning can uncover hidden patterns in data and enable early risk identification.

[0066] In this step, data acquisition includes: 1) Soil moisture: deploying a distributed TDR sensor network; 2) Meteorological indicators: accessing data from the meteorological bureau's micro-meteorological stations; 3) Crop growth: extracting the NDVI index using a UAV multispectral camera; 4) Pests and diseases: integrating historical pest and disease monitoring data with satellite pest and disease remote sensing inversion results. A random forest algorithm is used, with historical disaster data as labels, to train a risk prediction model. A 12-dimensional feature vector is input, and a risk score of 0-10 is output. A risk threshold ≥7 is set as a high-risk area. Spatial overlay analysis is used to identify risk sources (such as continuously cropped fields) and initial monitoring points (risk center locations). This improves the accuracy of early warnings, allowing for earlier issuance of warnings compared to traditional manual forecasting.

[0067] See Figure 2 In one embodiment, the step of predicting the agricultural risk level of each grid using a machine learning model includes:

[0068] S201. Construct a feature set, which includes soil pH value, nitrogen, phosphorus and potassium content, cumulative precipitation, temperature fluctuation rate, crop disease resistance index and frequency of historical disasters;

[0069] Multi-source data integration:

[0070] Soil data: pH value and nitrogen, phosphorus and potassium content (EC value inversion) are collected in real time through a distributed sensor network.

[0071] Meteorological data: Accumulated precipitation and daily temperature range data for the past 30 days were obtained from the Meteorological Bureau API;

[0072] Crop data: Chlorophyll content was extracted from UAV hyperspectral images and combined with a variety database to generate a disease resistance index;

[0073] Historical data: Establish a GIS spatial database to record the location, intensity, and frequency of disasters over the past 5 years;

[0074] The Z-score method is used to normalize continuous features, and the contribution of each feature is calculated using the Gini index of random forest. Redundant features (importance less than 0.05) are removed, and finally 12 core features are retained. Feature dimension compression can reduce the amount of computation and improve the training speed of the model.

[0075] S202. The risk prediction model is trained using the random forest algorithm. The model parameters are optimized through cross-validation, and the probability distribution of drought risk, waterlogging risk and pest and disease risk for each grid is output.

[0076] The training and test sets were divided in a 7:3 ratio. The number of decision trees was set to 200, with a maximum depth of 8 layers. Five-fold cross-validation was used, and the evaluation metrics included the area under the ROC curve, precision, and recall. Then, soft voting was performed on the output of each tree to generate the final probability distribution.

[0077] S203. Generate a comprehensive risk level by weighted summation of risk probabilities, divide the risk into high, medium and low risk zones, and map the high risk zone to the target warning zone.

[0078] A comprehensive risk level is generated by weighted summation of risk probabilities: high-risk area: R ≥ 0.7; medium-risk area: 0.4 ≤ R < 0.7; low-risk area: R < 0.4. The probability grid is converted into vector polygons and spatially overlaid with the grid data from step S10. This enables a quantitative expression of risk, improving accuracy compared to traditional qualitative assessments. The generated risk heatmap can intuitively display the spatial distribution of risks, providing a basis for precise prevention and control.

[0079] This embodiment introduces "temperature fluctuation rate" as a sensitive indicator for crop stress early warning, constructs "historical disaster frequency-spatial autocorrelation" feature to capture risk clustering effect; adopts ensemble learning to reduce the overfitting risk of a single decision tree; and achieves parameter self-optimization through cross-validation to reduce manual parameter tuning costs.

[0080] S30. With the initial monitoring point's spatial coverage, data acquisition accuracy, and deployment cost as optimization objectives, a multi-objective decision model is established. The constraints include the maximum response distance between the monitoring point and the risk source, the minimum data update frequency, and the cost ceiling. An improved genetic algorithm is used to solve the model to determine the optimal monitoring point.

[0081] Traditional monitoring point deployment relies on experience, which can easily lead to low coverage or wasted costs. Multi-objective optimization can balance technical indicators and economic constraints.

[0082] In one embodiment, the construction of the multi-objective decision model includes defining a single-objective function, including:

[0083] Maximize spatial coverage:

[0084] ;

[0085] In the formula, For spatial coverage, For the first The effective coverage area of ​​each monitoring point reflects the physical range within which data can be collected by that monitoring point. One monitoring point, , This is the terrain attenuation coefficient, used to quantify the weakening effect of terrain complexity (such as slope and vegetation density) on the cover effect. The baseline area threshold is used to adjust the sensitive region of the logic function, ensuring the non-linear mapping characteristics of the coverage.

[0086] Maximize data precision:

[0087] ;

[0088] In the formula, For data accuracy, For sensor resolution; The Euclidean distance between the monitoring point and the risk source; To calibrate the data frequency, , As a weighting factor;

[0089] Minimize deployment costs:

[0090] ;

[0091] In the formula, For deployment costs, For hardware costs, For communication link costs, To maintain costs, This is the cost coefficient;

[0092] The above single-objective functions are fused into a multi-objective decision model using fuzzy hierarchical analysis, and constraints are added:

[0093] ;

[0094] ;

[0095] ;

[0096] In the formula, For early warning response time, This is the upper limit for the early warning response time. The total cost threshold, This represents the minimum data accuracy requirement.

[0097] The spatial coverage function adopts an S-shaped logistic growth model. Simulate the terrain attenuation effect. When the effective area of ​​the monitoring point... Exceeding the threshold At this time, the coverage efficiency exhibits an accelerating improvement characteristic, consistent with the diminishing marginal benefits law of actual monitoring equipment coverage. The data accuracy function introduces an inverse distance-squared proportional term. This reflects the physical law that monitoring resolution decreases with distance, and also through calibration frequency. Ensuring long-term data reliability. The cost model employs a linear combination approach, quantifying and adding together factors such as hardware, communication, and maintenance.

[0098] The subjective ambiguity of expert judgment is addressed using triangular fuzzy numbers, and a fuzzy judgment matrix is ​​constructed to determine the weights of each objective. The fuzzy weights are then transformed into deterministic weight coefficients using the λ-cut method. A weighted summation method is employed to transform the multi-objective problem into a single-objective optimization problem, which is then determined by the analytic hierarchy process (AHP).

[0099] In the specific implementation and solution process:

[0100] 1) Parameter calibration stage:

[0101] Terrain attenuation coefficient , The average slope was calculated using DEM elevation data. Establish mapping relationship ;

[0102] Benchmark area Take 60% of the nominal coverage area of ​​the monitoring equipment as the initial value;

[0103] Weighting factors , The entropy weight method is used for calculation, for example. .

[0104] 2) Model solution process:

[0105] 2.1) Data Acquisition: GIS geographic data, equipment parameter database, cost database;

[0106] 2.2) Constraint Handling: Use the penalty function method to... Equal constraints are incorporated into the objective function;

[0107] 2.3) Optimization solution: The NSGA-II multi-objective genetic algorithm is used, with a population size of 100 and 500 iterations.

[0108] 2.4) Pareto front analysis: Outputs a set of non-dominated solutions for decision-makers to choose from.

[0109] 3) Deployment verification:

[0110] Monte Carlo simulation: Randomly generating 1000 terrain-cost combinations to verify the robustness of the model;

[0111] On-site debugging: Collect actual coverage data after deployment and provide feedback for correction. , parameter.

[0112] This model, based on Pareto optimality theory, integrates three conflicting objective functions using fuzzy hierarchical analysis to form a unified evaluation system. The core idea is to find a set of non-dominated solutions (Pareto optimal solution set) that simultaneously optimizes the three objective functions while satisfying constraints.

[0113] The terrain attenuation effect is described by the Logistic function, which is more in line with the actual monitoring scenario than the traditional linear model. The inverse square law in physics is introduced to quantify the impact of the distance between the monitoring point and the risk source on the data accuracy. The weight of each target is dynamically determined by the fuzzy hierarchical analysis method to adapt to the needs of different agricultural scenarios.

[0114] S40. Simulate and optimize the evolution of agricultural conditions at monitoring points under extreme scenarios. Calculate stability indicators based on early warning accuracy, response timeliness, and cost volatility. Select optimized monitoring points with stability indicators higher than preset values ​​as the final agricultural condition early warning nodes and generate a dynamic monitoring network.

[0115] Conventional monitoring networks are prone to failure under extreme weather conditions; stability assessments can enhance system robustness.

[0116] Preferably, the extreme scenarios include:

[0117] Extreme meteorological events: the spatiotemporal distribution patterns of persistent drought, torrential rain and flooding, and low-temperature freezing damage;

[0118] Biological disaster events: the coupling relationship between pest and disease spread pathways, insect egg hatching rates, and crop susceptibility periods;

[0119] Human intervention events: simulation of soil salinization caused by irrigation interruption and excessive fertilization.

[0120] In one embodiment, the simulation optimization of agricultural condition evolution at monitoring points under extreme scenarios includes:

[0121] A multi-dimensional scenario library is constructed based on extreme scenarios;

[0122] Based on computational fluid dynamics and agent-based models, the propagation trajectory of risk sources in various scenarios is dynamically simulated, and the data acquisition efficiency and early warning delay of monitoring nodes are evaluated to generate simulation results.

[0123] Calculate the stability index based on the simulation results:

[0124] ;

[0125] In the formula, For stability rating, To improve the accuracy of early warnings, The average response time, Cost volatility; For normalized weights.

[0126] This scheme constructs a highly stable agricultural monitoring and early warning network by simulating agricultural conditions under extreme scenarios and combining multi-dimensional dynamic assessment and optimization screening mechanisms. Its core principle lies in:

[0127] Extreme scenario simulation: Using a multi-dimensional scenario database, we simulate the impact of three types of extreme events—meteorological, biological, and human-induced—on agricultural systems, and quantify the risk propagation path and the response capabilities of monitoring nodes.

[0128] Dynamic stability assessment: based on early warning accuracy Average response time Cost volatility Constructing composite indicators Monitoring points with strong anti-interference capabilities were selected.

[0129] Network adaptive optimization: By dynamically monitoring the network generation mechanism, the system ensures that early warning nodes automatically adjust to changes in the environment, thereby improving the overall robustness of the system.

[0130] Specifically, in implementation, it includes

[0131] 1) Construction of a multi-dimensional scenario library:

[0132] Data fusion: Integrate meteorological satellite data, soil sensor records, historical outbreak patterns of pests and diseases, and human intervention logs to build an extreme event database covering spatiotemporal dimensions.

[0133] Context parameterization includes the following three types:

[0134] Meteorological events: Define drought index, rainfall intensity-duration-frequency curve, and low temperature duration threshold.

[0135] Biological disasters: Establish a correlation matrix between the spread rate of pests and diseases and temperature, humidity, and crop growth stage.

[0136] Human-induced events: Simulation of irrigation interruption cycles and fertilizer application-soil electrical conductivity relationship models.

[0137] 2) Dynamic simulation of risk transmission:

[0138] Computational Fluid Dynamics (CFD) Modeling:

[0139] Simulate the spatial diffusion process of meteorological disasters (such as floods) and output the risk coverage area and propagation speed. Example: Simulate storm runoff paths using the Navier-Stokes equations to predict the inundation area of ​​farmland.

[0140] Agent-based model (ABM):

[0141] Construct a pest and disease transmission agent and define migration rules (such as the probability of wind spread and the influence of host crop density). Example: Simulate an exponential outbreak caused by the overlap of insect egg hatching rate and crop susceptibility period.

[0142] 3) Monitoring node evaluation and selection:

[0143] Data capture efficiency calculation: Calculates the probability that a monitoring node successfully identifies a risk event in the simulation. = Number of correct warnings / Total number of risk events.

[0144] Response timeliness quantification: Records the average delay time from when a risk reaches the monitoring area to when an alert is triggered. .

[0145] Cost fluctuation analysis: Calculate the coefficient of variation of node maintenance costs under extreme scenarios. , Standard deviation (mean).

[0146] Stability index calculation: based on Formula calculation, weight allocation can be The values ​​are 0.5, 0.3, and 0.2 respectively.

[0147] 4) Dynamic monitoring network generation:

[0148] Node optimization: Filtering Monitoring points with values ​​greater than a threshold (e.g., 0.8) form the backbone network.

[0149] Redundancy design: Deploy backup nodes in critical areas to automatically switch over when the backbone node fails.

[0150] Real-time updates: Dynamically adjust node weights by combining Internet of Things (IoT) data streams to adapt to sudden environmental changes.

[0151] In summary, this embodiment improves early warning accuracy and shortens the average response time in continuous drought simulation; through Optimization resulted in a 40% reduction in node maintenance cost volatility and a significant decrease in the risk of budget overruns under extreme scenarios. In rainstorm and flood scenarios, the dynamic network maintained over 85% of its nodes in effective operation. Under coupled pest and disease events, the monitoring network coverage was greatly improved. The generated risk heatmap and node stability map can guide agricultural insurance pricing and emergency resource pre-allocation. This solution, through a closed-loop "simulation-optimization-verification" approach, provides a complete solution for agricultural disaster early warning, from theory to engineering implementation, and is particularly suitable for the precision agriculture management needs in the context of intensified climate change.

[0152] Preferably, in one embodiment, the method further includes:

[0153] The monitoring network topology is updated in real time through collaborative inspections by drone swarms and ground sensors.

[0154] When a sudden increase in local risk level is detected, the monitoring point density adaptive adjustment algorithm is automatically triggered to add mobile monitoring nodes in the target area, while shutting down redundant nodes in low-risk areas to reduce energy consumption.

[0155] Ground sensors are widely deployed in the monitoring area to collect various environmental data such as temperature, humidity, gas concentration, and vibration. Simultaneously, a drone swarm is formed, with each drone equipped with high-precision sensors, communication modules, and positioning systems. The drone swarm and ground sensors establish communication connections via wireless networks (such as 5G or self-organizing networks) to form a monitoring network.

[0156] Ground sensors continuously collect data and transmit it to the control center in real time. A swarm of drones conducts regular inspections along preset routes. During these inspections, the drones use their onboard sensors to collect data on areas that are difficult for ground sensors to cover or key monitoring areas. The data collected by the drones is also transmitted back to the control center. Based on the received data from the drones and ground sensors, the control center uses graph theory algorithms (such as the minimum spanning tree algorithm and Dijkstra's algorithm) to construct and update the monitoring network topology in real time. This topology visually represents the location, connections, and data transmission paths of each monitoring node, providing fundamental data support for subsequent risk monitoring and node adjustments.

[0157] The control center pre-sets a risk assessment model that comprehensively considers factors such as the type of monitoring data, numerical trends, and comparisons with historical data to classify the monitoring area into risk levels (e.g., low, medium, and high). The control center continuously analyzes the data transmitted from each monitoring node to assess the risk level of each area in real time.

[0158] When the control center detects a sudden increase in the local risk level of a certain area (e.g., from low risk to high risk), it automatically triggers an adaptive adjustment algorithm for monitoring point density. This algorithm first calculates the number and location of additional mobile monitoring nodes needed in the target area based on the scope of the risk area, the risk type, and the distribution of existing monitoring nodes. Then, the control center sends instructions to the drone swarm, dispatching some drones as mobile monitoring nodes to fly to the target area, hover at designated locations, or fly along specific trajectories to collect data in real time, thereby increasing the monitoring density of the target area. Simultaneously, the control center evaluates monitoring nodes in low-risk areas, shutting down redundant nodes (i.e., ground sensor nodes with high data similarity and minimal impact on overall monitoring) to reduce unnecessary energy consumption. During the node adjustment process, the control center continuously monitors the network status to ensure the stability and integrity of data transmission.

[0159] By coordinating drone swarms with ground sensors for inspection, comprehensive and blind-spot-free coverage of the monitored area can be achieved. Drones can quickly reach areas inaccessible to ground sensors (such as mountainous areas, rooftops, and hazardous areas) to collect data, compensating for the blind spots of ground sensors. Simultaneously, the real-time updated monitoring network topology accurately reflects the working status and data transmission paths of each monitoring node. When the local risk level surges, node adjustments are rapidly triggered, adding mobile monitoring nodes to the target area. This results in denser and more accurate monitoring data, enabling timely detection of subtle changes in risk areas and providing reliable data support for risk warning and management, effectively improving the accuracy and timeliness of monitoring. Furthermore, it reduces equipment uptime, lowers maintenance costs and replacement frequency, further reducing operating costs and improving the economic efficiency and sustainability of the monitoring system.

[0160] In summary, this invention constructs a three-dimensional geographic model of the monitored farmland and divides it into grids based on soil type, crop distribution, and topographic data. This allows for precise subdivision of farmland into multiple agricultural monitoring grids, laying the foundation for subsequent refined monitoring. After acquiring multi-source agricultural data, a machine learning model is used to predict the agricultural risk level of each grid. This efficiently selects agricultural monitoring grids with risk levels exceeding a preset threshold as target early warning areas and accurately identifies risk sources and initial monitoring points, overcoming the previous problems of one-sided agricultural assessments and inaccurate risk area location. By establishing a multi-objective decision-making model and using an improved genetic algorithm to solve it, optimal monitoring points are determined. This process fully considers key factors such as spatial coverage of monitoring points, data acquisition accuracy, and deployment costs. Compared to traditional arbitrary or unreasonable monitoring point layouts, this significantly improves the scientific rigor and rationality of the monitoring network, effectively controlling costs while ensuring data quality. By simulating and optimizing the evolution of agricultural conditions at monitoring points under extreme scenarios, and calculating stability indicators based on early warning accuracy, response timeliness, and cost volatility, optimized monitoring points with stability indicators higher than preset values ​​are selected as the final agricultural condition early warning nodes, and a dynamic monitoring network is generated. This significantly enhances the reliability and stability of the monitoring system under complex and extreme conditions, enabling it to respond to changes in agricultural conditions more promptly and accurately, providing strong support for agricultural production, and realizing the transformation from traditional extensive agricultural condition monitoring and early warning to a precise, efficient, intelligent, and stable modern agricultural condition monitoring and early warning model.

[0161] See Figure 3 In one embodiment, the present invention also provides an intelligent agricultural condition monitoring and early warning system, the system comprising:

[0162] Grid division unit 100 is used to construct a three-dimensional geographic model of the monitored farmland. The model is divided into grids based on soil type, crop distribution and terrain data to generate multiple agricultural monitoring grids.

[0163] The monitoring point screening unit 200 is used to acquire multi-source agricultural data, including soil moisture, meteorological indicators, crop growth stages and historical pest and disease data. It uses a machine learning model to predict the agricultural risk level of each grid, screens agricultural monitoring grids with risk levels exceeding a preset threshold as target early warning areas, and identifies risk sources and initial monitoring points within the target early warning areas.

[0164] The monitoring point optimization unit 300 is used to establish a multi-objective decision model with the initial monitoring point spatial coverage, data acquisition accuracy and deployment cost as optimization objectives. The constraints include the maximum response distance between the monitoring point and the risk source, the minimum data update frequency and the cost limit. An improved genetic algorithm is used to solve the model to determine the optimal monitoring point.

[0165] The early warning node determination unit 400 is used to simulate and optimize the evolution of agricultural conditions at monitoring points under extreme scenarios. Based on the early warning accuracy, response timeliness, and cost volatility, it calculates stability indicators, selects optimized monitoring points with stability indicators higher than preset values ​​as the final agricultural early warning nodes, and generates a dynamic monitoring network.

[0166] It is understood that the system provided in this embodiment has functions or includes modules that can be used to execute the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0167] The present invention also provides an electronic device including a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs a method as described in any of the above possible implementations.

[0168] The present invention also provides a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor of an electronic device, cause the processor to perform a method as described in any of the above possible implementations.

[0169] Please see Figure 4 , Figure 4 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention.

[0170] The electronic device 2 includes a processor 21, a memory 22, an input device 23, and an output device 24. The processor 21, memory 22, input device 23, and output device 24 are coupled together via connectors, which may include various interfaces, transmission lines, or buses, etc., and are not limited in this embodiment of the invention. It should be understood that in various embodiments of the invention, coupling refers to mutual connection through a specific method, including direct connection or indirect connection through other devices, such as through various interfaces, transmission lines, buses, etc.

[0171] The processor 21 can be one or more graphics processing units (GPUs). If the processor 21 is a GPU, the GPU can be a single-core GPU or a multi-core GPU. Optionally, the processor 21 can be a processor group composed of multiple GPUs, with the multiple processors coupled to each other via one or more buses. Optionally, the processor can also be other types of processors, etc., and this embodiment of the invention is not limited thereto.

[0172] The memory 22 can be used to store computer program instructions, as well as various types of computer program code, including program code for executing the present invention. Optionally, the memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM), which is used for related instructions and data.

[0173] Input device 23 is used to input data and / or signals, and output device 24 is used to output data and / or signals. Input device 23 and output device 24 can be independent devices or an integrated device.

[0174] It is understood that in this embodiment of the invention, the memory 22 can be used not only to store related instructions, but also the specific data stored in the memory is not limited.

[0175] Understandable Figure 4 This is merely a simplified design of an electronic device. In practical applications, the electronic device may also include other necessary components, including, but not limited to, any number of input / output devices, processors, memory, etc., and all video analysis devices that can implement embodiments of the present invention are within the protection scope of the present invention.

[0176] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0177] Those skilled in the art will readily understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. Those skilled in the art will also readily understand that the various embodiments of the present invention have different focuses, and for the sake of convenience and brevity, the same or similar parts may not be repeated in different embodiments. Therefore, parts not described or not described in detail in one embodiment can be referred to in other embodiments.

[0178] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0179] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0180] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0181] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital versatile discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0182] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An intelligent agricultural condition monitoring and early warning method, characterized in that, The method includes: A three-dimensional geographic model of the farmland under monitoring is constructed. Based on soil type, crop distribution and topographic data, the model is divided into grids to generate multiple agricultural monitoring grids. Acquire multi-source agricultural data, including soil moisture, meteorological indicators, crop growth stages and historical pest and disease data, predict the agricultural risk level of each grid through machine learning models, screen agricultural monitoring grids with risk levels exceeding preset thresholds as target early warning areas, and identify risk sources and initial monitoring points within the target early warning areas. With the initial monitoring point spatial coverage, data acquisition accuracy, and deployment cost as optimization objectives, a multi-objective decision model is established. The constraints include the maximum response distance between the monitoring point and the risk source, the minimum data update frequency, and the cost ceiling. An improved genetic algorithm is used to solve the model to determine the optimal monitoring point. The simulation optimizes the evolution of agricultural conditions at monitoring points under extreme scenarios. Stability indices are calculated based on early warning accuracy, response timeliness, and cost volatility. Optimized monitoring points with stability indices higher than preset values ​​are selected as the final agricultural early warning nodes, and a dynamic monitoring network is generated. The simulated and optimized monitoring points' agricultural condition evolution under extreme scenarios includes: A multi-dimensional scenario library is constructed based on extreme scenarios; Based on computational fluid dynamics and agent-based models, the propagation trajectory of risk sources in various scenarios is dynamically simulated, and the data acquisition efficiency and early warning delay of monitoring nodes are evaluated to generate simulation results. Calculate the stability index based on the simulation results: ； In the formula, For stability rating, To improve the accuracy of early warnings, The average response time, Cost volatility; For normalized weights.

2. The intelligent agricultural condition monitoring and early warning method according to claim 1, characterized in that, The method of predicting the agricultural risk level of each grid using a machine learning model includes: Construct a feature set, which includes soil pH, nitrogen, phosphorus and potassium content, cumulative precipitation, temperature fluctuation rate, crop disease resistance index and frequency of historical disasters; A risk prediction model was trained using the random forest algorithm, and the model parameters were optimized through cross-validation. The probability distributions of drought risk, waterlogging risk, and pest and disease risk for each grid were then output. A comprehensive risk level is generated by weighted summation of risk probabilities, dividing the risk into high, medium, and low risk zones, and mapping the high-risk zone to the target warning zone.

3. The intelligent agricultural condition monitoring and early warning method according to claim 1, characterized in that, The construction of the multi-objective decision model includes defining a single-objective function, including: Maximize spatial coverage: ； In the formula, For spatial coverage, For the first The effective coverage area of ​​each monitoring point reflects the physical range within which data can be collected by that monitoring point. One monitoring point, , This is the terrain attenuation coefficient, used to quantify the weakening effect of terrain complexity on coverage; The baseline area threshold is used to adjust the sensitive region of the logic function, ensuring the non-linear mapping characteristics of the coverage. Maximize data precision: ； In the formula, For data accuracy, For sensor resolution; The Euclidean distance between the monitoring point and the risk source; To calibrate the data frequency, , As a weighting factor; Minimize deployment costs: ； In the formula, For deployment costs, For hardware costs, For communication link costs, To maintain costs, This is the cost coefficient; The above single-objective functions are fused into a multi-objective decision model using fuzzy hierarchical analysis, and constraints are added: ； ； ； In the formula, For early warning response time, This is the upper limit for the early warning response time. The total cost threshold, This represents the minimum data accuracy requirement.

4. The intelligent agricultural condition monitoring and early warning method according to claim 1, characterized in that, The extreme scenarios include: Extreme meteorological events: the spatiotemporal distribution patterns of persistent drought, torrential rain and flooding, and low-temperature freezing damage; Biological disaster events: the coupling relationship between pest and disease spread pathways, insect egg hatching rates, and crop susceptibility periods; Human intervention events: simulation of soil salinization caused by irrigation interruption and excessive fertilization.

5. The intelligent agricultural condition monitoring and early warning method according to claim 1, characterized in that, The method further includes: The monitoring network topology is updated in real time through collaborative inspections by drone swarms and ground sensors. When a sudden increase in local risk level is detected, the monitoring point density adaptive adjustment algorithm is automatically triggered to add mobile monitoring nodes in the target area, while shutting down redundant nodes in low-risk areas to reduce energy consumption.

6. An intelligent agricultural condition monitoring and early warning system, characterized in that, The system includes: Grid division units are used to construct a three-dimensional geographic model of the monitored farmland. The model is divided into grids based on soil type, crop distribution and terrain data to generate multiple agricultural monitoring grids. The monitoring point screening unit is used to acquire multi-source agricultural data, including soil moisture, meteorological indicators, crop growth stages and historical pest and disease data. It uses machine learning models to predict the agricultural risk level of each grid, screens agricultural monitoring grids with risk levels exceeding a preset threshold as target early warning areas, and identifies risk sources and initial monitoring points within the target early warning areas. The monitoring point optimization unit is used to establish a multi-objective decision model with the initial monitoring point spatial coverage, data acquisition accuracy and deployment cost as optimization objectives. The constraints include the maximum response distance between the monitoring point and the risk source, the minimum data update frequency and the cost limit. An improved genetic algorithm is used to solve the model to determine the optimal monitoring points. The early warning node determination unit is used to simulate and optimize the evolution of agricultural conditions at monitoring points under extreme scenarios. Based on the early warning accuracy, response timeliness, and cost volatility, it calculates stability indicators, selects optimized monitoring points with stability indicators higher than preset values ​​as the final agricultural early warning nodes, and generates a dynamic monitoring network. The simulated and optimized monitoring points' agricultural condition evolution under extreme scenarios includes: A multi-dimensional scenario library is constructed based on extreme scenarios; Based on computational fluid dynamics and agent-based models, the propagation trajectory of risk sources in various scenarios is dynamically simulated, and the data acquisition efficiency and early warning delay of monitoring nodes are evaluated to generate simulation results. Calculate the stability index based on the simulation results: ； In the formula, For stability rating, To improve the accuracy of early warnings, The average response time, Cost volatility; For normalized weights.

7. An electronic device, characterized in that, include: The electronic device includes a processor and a memory, the memory being used to store computer program code, the computer program code including computer instructions, wherein when the processor executes the computer instructions, the electronic device performs the intelligent agricultural condition monitoring and early warning method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which includes program instructions that, when executed by a processor of an electronic device, cause the processor to perform the intelligent agricultural condition monitoring and early warning method according to any one of claims 1 to 5.

Images