Regional agricultural disaster real-time monitoring system and method based on Internet of Things and GIS

Abstract

The invention provides a regional agricultural disaster real-time monitoring system and method based on the Internet of Things and GIS, and the system comprises a sensing layer which is used for collecting environment and crop data in real time through sensor nodes, an unmanned plane and a remote sensing satellite which are disposed in a farmland region; the transmission layer is used for transmitting the data acquired by the sensing layer to a cloud platform through a low-power-consumption wide-area Internet of Things technology and the Internet; the platform layer is used for storing and managing the monitoring data with geographic coordinates and operating a disaster analysis model to carry out fusion calculation and intelligent analysis on the data transmitted to a cloud platform so as to identify disaster signs and evaluate risk levels; and the application layer is used for providing a visual monitoring and early warning interface based on the WebGIS technology, displaying monitoring data and disaster risk spatial distribution in real time, and automatically triggering multi-channel release of early warning information when the risk exceeds a threshold value. Upgrading from point location monitoring to area evaluation is realized, and disaster space distribution and evolution trend can be mastered macroscopically and visually.

Description

Technical Field

[0001] This application relates to the field of agricultural information monitoring technology, and in particular to a regional agricultural disaster real-time monitoring system and method based on the Internet of Things and GIS. Background Technology

[0002] my country is a major agricultural country, and the frequent occurrence of regional agricultural disasters such as droughts, floods, pests and diseases, and low-temperature freezing damage poses a serious threat to food security and sustainable agricultural development. Traditional agricultural disaster monitoring mainly relies on manual field inspections and reporting. This method is not only inefficient and costly in terms of manpower, but also suffers from a significant time lag, often only being discovered after the disaster has already become significant, thus missing the best opportunity for early warning and prevention.

[0003] With the development of information technology, some monitoring methods based on single technologies have emerged. For example, some systems use Internet of Things (IoT) technology to deploy sensors for data collection, achieving automated acquisition of environmental parameters. However, their monitoring content is often singular, lacking effective integration of multi-source and heterogeneous data, and typically only providing point-based data, failing to effectively analyze and visualize the spatial distribution and spread trends of disasters at a macro-regional scale. On the other hand, while Geographic Information Systems (GIS) possess powerful spatial data management and analysis capabilities and have been applied in some agricultural monitoring projects, their data sources largely rely on periodic remote sensing imagery or static basic geographic information, lacking support from real-time ground monitoring data. This results in insufficient dynamic perception capabilities for sudden and rapidly evolving disasters (such as sudden outbreaks of pests and diseases, and localized flooding), making it difficult to achieve truly "real-time" monitoring and early warning. Summary of the Invention

[0004] In view of this, embodiments of this application provide a regional agricultural disaster real-time monitoring system and method based on the Internet of Things (IoT) and GIS. One or more embodiments of this application also relate to a regional agricultural disaster real-time monitoring device based on IoT and GIS, a computing device, a computer-readable storage medium, and a computer program, to address the technical deficiencies existing in the prior art.

[0005] In a first aspect, embodiments of this application provide a regional agricultural disaster real-time monitoring system based on the Internet of Things and GIS, including: The perception layer is used to collect environmental and crop data in real time through sensor nodes, drones, and remote sensing satellites deployed in farmland areas; The transport layer is used to transmit the data collected by the sensing layer to the cloud platform via low-power wide-area Internet of Things (IoT) technology and the Internet. The platform layer, as the core data processing platform, includes a GIS spatial database and a disaster analysis model engine. It is used to store and manage monitoring data with geographic coordinates, and to run disaster analysis models to perform fusion calculations and intelligent analysis on the data transmitted to the cloud platform in order to identify disaster signs and assess risk levels. The application layer is used to provide a visual monitoring and early warning interface based on WebGIS technology, display monitoring data and spatial distribution of disaster risks in real time, and automatically trigger the multi-channel release of early warning information when the risk exceeds the threshold.

[0006] In one possible implementation, the perception layer specifically includes: Soil parameter sensor nodes are used to collect soil moisture and soil temperature data; Field weather stations are used to collect data on temperature, humidity, rainfall, and wind speed. Pest and disease monitoring equipment, including spore traps and insect traps, is used to collect basic information on the occurrence of pests and diseases; Drones and remote sensing satellites are used to periodically acquire remote sensing images of regional crop growth.

[0007] In one possible implementation, the disaster analysis model engine of the platform layer integrates at least: A drought index calculation model is used to assess the drought level of a region based on meteorological and soil data. A flood risk assessment model is used to assess the risk of urban flooding by combining topographic, rainfall, and drainage data. Pest and disease spread models are used to simulate the potential spatial spread trends of pests and diseases. A low-temperature freezing damage discrimination model is used to identify low-temperature stress based on time-series temperature data.

[0008] In one possible implementation, the drought index calculation model uses a comprehensive meteorological drought index, wherein the formula for calculating the comprehensive meteorological drought index is:

[0009] in, This represents the comprehensive meteorological drought index. This indicates the actual precipitation in the current period. This represents the average annual precipitation over the same period. This indicates the current volumetric water content of the soil. This indicates the soil volumetric water content threshold suitable for crop growth. This indicates the current actual evapotranspiration. represents potential evapotranspiration, , , Denotes the weight coefficients, and satisfies , representing the contributions of precipitation, soil moisture, and evapotranspiration to drought, respectively.

[0010] In one possible implementation, the pest and disease spread model uses a spatial transmission risk index for quantitative assessment, and the formula for calculating the spatial transmission risk index is as follows:

[0011] in, Indicates the spatial transmission risk index, This represents the Euclidean distance between point i and evaluation unit j. This represents the effective transmission attenuation coefficient of a specific pest or disease under current weather conditions. This represents the wind speed factor for the current time period. This indicates the weight of wind-borne pests and diseases. This represents the insect migration rate factor for the current time period. This indicates the weight of insect-borne diseases and pests.

[0012] In one possible implementation, the transport layer specifically employs at least one low-power wide-area IoT technology selected from LoRa, NB-IoT, and 4G / 5G to construct the data transmission network.

[0013] In one possible implementation, the application layer is specifically used for: The spatial distribution of disaster risk levels is rendered and displayed in real time on an electronic map using different colors or legends, generating thematic maps of disaster risk. It provides an interface for configuring early warning rules, allowing users to set personalized early warning thresholds for different disaster types and regions; When the risk level output by the disaster analysis model exceeds the preset threshold, the system will automatically issue a warning to end users in the target area via at least one of the following methods: SMS, application push, or web platform pop-up.

[0014] In one possible implementation, the GIS spatial database of the platform layer also stores historical disaster data and basic geographic information data, and associates them with real-time monitoring data for time-series trend analysis and model calibration.

[0015] In one possible implementation, the system further includes a feedback optimization module for collecting user feedback on early warning information and adaptively adjusting the parameters of the disaster analysis model or the early warning threshold based on the feedback data.

[0016] Secondly, embodiments of this application provide a method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS, including: Real-time environmental and crop data are collected through sensor nodes, drones, and remote sensing satellites deployed in farmland areas. The collected data is transmitted to the cloud platform via low-power wide-area IoT technology and the Internet. In the cloud platform, GIS spatial databases are used to store and manage monitoring data with geographic coordinates, and disaster analysis models are run to perform data fusion calculations and intelligent analysis in order to identify disaster signs and assess risk levels; Based on WebGIS technology, it provides a visual monitoring and early warning interface, which displays monitoring data and spatial distribution of disaster risks in real time, and automatically triggers the multi-channel release of early warning information when the risk exceeds the threshold.

[0017] Thirdly, embodiments of this application provide a regional agricultural disaster real-time monitoring device based on the Internet of Things and GIS, comprising: The sensing module is used to collect environmental and crop data in real time through sensor nodes deployed in farmland areas, drones, and remote sensing satellites; The transmission module is used to transmit the data collected by the sensing layer to the cloud platform via low-power wide-area Internet of Things technology and the Internet; The processing module, located on the cloud platform, uses a GIS spatial database to store and manage monitoring data with geographic coordinates, and runs a disaster analysis model to perform data fusion calculations and intelligent analysis in order to identify disaster signs and assess risk levels. The display module provides a visual monitoring and early warning interface based on WebGIS technology, which displays monitoring data and the spatial distribution of disaster risks in real time, and automatically triggers the multi-channel release of early warning information when the risk exceeds the threshold.

[0018] Fourthly, embodiments of this application provide a computing device, including: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-described method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS are implemented.

[0019] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the aforementioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0020] Sixthly, embodiments of this application provide a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0021] The technical solution provided in this application constructs an integrated "air-ground-space" data acquisition network through multiple sensor nodes deployed in the perception layer, drones, and remote sensing satellites. This enables comprehensive and real-time acquisition of multi-source data, including soil moisture, meteorological elements, pest and disease information, and crop growth. Subsequently, the transmission layer utilizes low-power wide-area IoT technology to efficiently and stably aggregate the dispersed node data to the cloud platform. At the platform layer, the system uses a GIS spatial database to perform integrated storage and management of multi-source data with precise geographic coordinates. It also integrates multiple disaster analysis models (such as drought index models and pest and disease spread models) for data fusion and intelligent analysis, thereby dynamically identifying disaster signs and generating risk level assessment results with spatial location. Finally, the application layer uses WebGIS technology to visualize the analysis results in the form of electronic map thematic maps and automatically triggers the release of early warning information accurate to specific areas based on preset rules. The implementation of this solution deeply integrates the real-time sensing capabilities of the Internet of Things with the powerful spatial management, analysis, and visualization capabilities of GIS, creating beneficial synergistic effects: First, it upgrades from point-based monitoring to area-based assessment, enabling a macroscopic and intuitive understanding of the spatial distribution and evolution trends of disasters, thus solving the problem of limited visibility in traditional monitoring methods; Second, relying on precise spatial positioning and model analysis, it significantly improves the early detection of disasters, the accuracy of risk assessment, and the targeting and timeliness of early warning information dissemination, winning valuable time for taking precise prevention and control measures and effectively reducing disaster losses. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the architecture of a regional agricultural disaster real-time monitoring system based on the Internet of Things and GIS, provided in one embodiment of this application; Figure 2 This is a flowchart illustrating a method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS, provided in one embodiment of this application. Figure 3 This is a structural block diagram of a computing device provided in one embodiment of this application. Detailed Implementation

[0023] Many specific details are set forth in the following description to provide a full understanding of this application. However, this application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this application; therefore, this application is not limited to the specific embodiments disclosed below.

[0024] The terminology used in one or more embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of one or more embodiments of this application. The singular forms “a” and “the” as used in one or more embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in one or more embodiments of this application refers to and includes any or all possible combinations of one or more associated listed items.

[0025] It should be understood that although the terms first, second, etc., may be used to describe various information in one or more embodiments of this application, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first may also be referred to as second without departing from the scope of one or more embodiments of this application, and similarly, second may also be referred to as first. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0026] This application provides a regional agricultural disaster real-time monitoring system and method based on the Internet of Things and GIS. This application also relates to a regional agricultural disaster real-time monitoring device based on the Internet of Things and GIS, a computing device, and a computer-readable storage medium, which will be described in detail in the following embodiments.

[0027] Figure 1 This is a schematic diagram of the architecture of a regional agricultural disaster real-time monitoring system based on the Internet of Things and GIS, provided as an embodiment of this application.

[0028] Reference Figure 1 As shown, the system may include: The perception layer 101 is used to collect environmental and crop data in real time through sensor nodes, drones and remote sensing satellites deployed in farmland areas; The transmission layer 102 is used to transmit the data collected by the perception layer to the cloud platform via low-power wide-area Internet of Things technology and the Internet. Platform layer 103, as the core data processing platform, includes a GIS spatial database and a disaster analysis model engine. It is used to store and manage monitoring data with geographic coordinates, and run disaster analysis models to perform fusion calculations and intelligent analysis on the data transmitted to the cloud platform in order to identify disaster signs and assess risk levels. Application layer 104 is used to provide a visual monitoring and early warning interface based on WebGIS technology, display monitoring data and spatial distribution of disaster risks in real time, and automatically trigger the multi-channel release of early warning information when the risk exceeds the threshold.

[0029] In some embodiments, the perception layer of this system constructs an integrated air-space-ground monitoring network that coordinates ground sensor nodes, low-altitude UAVs, and space remote sensing satellites. Specifically, ground sensor nodes can be deployed in a grid pattern in farmland areas. These ground sensor nodes include soil moisture sensors, temperature and humidity sensors, spore traps, etc., to collect high-precision location-based environmental and pest data in real time. UAVs equipped with multispectral imagers are used to perform low-altitude remote sensing at preset intervals to acquire spatial variation information of crop growth at the field scale. Combined with large-scale, periodic macroscopic image data provided by remote sensing satellites, synchronous monitoring of the crop growth period and the extent of disaster impact in the region can be achieved.

[0030] In some embodiments, soil parameter sensor nodes are installed in a buried manner, arranged in a grid at different depths in the crop root zone, to directly measure soil volumetric water content and temperature parameters, providing underlying data support for drought monitoring and precision irrigation; field meteorological stations are located above the crop canopy, integrating multiple types of sensors to simultaneously collect key meteorological elements such as air temperature, air humidity, rainfall, and wind speed and direction, forming the main body of microclimate environment monitoring; in the pest and disease monitoring equipment, spore traps capture airborne pathogenic spores through timed triggering collectors, while insect traps automatically count target insects using sex pheromones or phototrap principles, and the two together construct an automated identification system for the precursors of pest and disease outbreaks; UAVs and remote sensing satellites serve as aerospace monitoring platforms, respectively equipped with multispectral cameras and high-resolution sensors, to periodically acquire remote sensing image data such as Normalized Difference Vegetation Index (NDVI) and Leaf Area Index (LAI) reflecting crop growth status.

[0031] Through a multi-layered and multi-type sensing system, firstly, it achieves three-dimensional data coverage from the underground root system and the surface canopy to the near-Earth atmosphere, eliminating the vertical spatial data gaps present in traditional monitoring; secondly, by combining fixed-point continuous monitoring with periodic areal scanning, it ensures the temporal continuity of key parameter measurements and realizes spatial visualization of crop growth and disaster impact, providing a complete data foundation for multi-scale and multi-dimensional comprehensive disaster analysis at the platform level.

[0032] In some embodiments, the transport layer of this system achieves reliable uploading of sensing data by constructing a heterogeneous converged network. In one implementation, for widely distributed sensor nodes with small data volumes, low-power wide-area IoT technologies such as LoRa or NB-IoT are preferentially used to build a self-organizing network, transmitting monitoring data such as soil and meteorological data to a centralized field gateway with extremely low power consumption. For large-capacity data such as high-definition images collected by drones, high-speed transmission is achieved through 4G / 5G networks. All data is ultimately aggregated to a unified access point in the cloud via the Internet. This configuration of the transport layer firstly allows for deep coverage of vast farmland areas using LPWAN technology, effectively solving the problems of weak signal and high deployment costs of traditional wireless networks in remote farmland, while significantly reducing the power consumption of terminal nodes and ensuring continuous operation for several years. Secondly, through heterogeneous network convergence, comprehensive adaptation from low-speed, small-data to high-speed, large-data systems is achieved, ensuring real-time and reliable transmission of all types of sensing data, optimizing overall network resource utilization, providing a stable and continuous data stream for the platform layer, and laying the foundation for the system's real-time monitoring and early warning capabilities.

[0033] In some embodiments, the platform layer in this system serves as the intelligent hub of the system. Specifically, it uses a GIS spatial database to uniformly store and manage multi-source heterogeneous data (such as soil moisture, meteorological parameters, pest and disease information, and remote sensing images) uploaded by the perception layer and carrying precise geographic coordinates, thus constructing a spatiotemporally integrated data foundation. On this basis, the disaster analysis model engine calls multiple integrated professional analysis models for collaborative calculation. Specifically, it uses a drought index calculation model to integrate precipitation, soil moisture, and evapotranspiration data to quantify drought levels; it uses a flood risk assessment model to overlay topography, rainfall, and drainage network data to simulate urban flooding risks; it uses a pest and disease diffusion model to combine meteorological factors and spatial distance to simulate disease transmission paths; and it uses a low-temperature freezing damage discrimination model to analyze temporal changes in temperature and identify frost stress. Through this platform-level processing method, firstly, it enables seamless integration from multi-source data storage to intelligent analysis and decision-making, transforming discrete environmental parameters into comprehensive disaster risk maps with clear spatial locations and quantitative levels, thus solving the problem of data disconnect between traditional methods and decision-making. Secondly, through the collaborative analysis and spatial coupling of multiple professional models, it achieves simultaneous and accurate identification and risk assessment of complex disasters such as drought, floods, pests and diseases, and frost damage, overcoming the limitations of single-model application scenarios and significantly improving the sensitivity of early disaster identification and the comprehensiveness of risk assessment, providing direct and reliable quantitative evidence for accurate early warning and scientific decision-making at the application layer.

[0034] In some embodiments, the drought index calculation model uses a comprehensive meteorological drought index, wherein the formula for calculating the comprehensive meteorological drought index is: Formula 1 in, This represents the comprehensive meteorological drought index. This indicates the actual precipitation in the current period. This represents the average annual precipitation over the same period. This indicates the current volumetric water content of the soil. This indicates the soil volumetric water content threshold suitable for crop growth. This indicates the current actual evapotranspiration. represents potential evapotranspiration, , , Denotes the weight coefficients, and satisfies , representing the contributions of precipitation, soil moisture, and evapotranspiration to drought, respectively.

[0035] Using the above calculation formula, multi-source data coupling and weighted integration can be achieved. Specifically, it can be based on... Compare with the actual precipitation in the current period Compared with the average precipitation over the same period This reflects the degree of drought caused by abnormal precipitation; it can be based on Compare current soil volumetric water content The threshold of soil volumetric water content required for crop growth This reflects the actual shortage of soil moisture supply in the root zone; further, based on Determine the current actual evapotranspiration With potential evaporation The ratio is used to characterize the actual water dissipation pressure of crops under atmospheric evaporation demand. Finally, configurable weighting coefficients are used. , , ,satisfy This method linearly weights and fuses the indicators from these three dimensions to form a comprehensive drought assessment value. Firstly, it overcomes the limitations of traditional drought indices (such as the SPI, which relies solely on precipitation) that only consider a single water factor. By comprehensively considering the key links in the complete water cycle—atmospheric precipitation, soil water storage, and crop water consumption—it achieves a multi-dimensional and mechanistic comprehensive diagnosis of agricultural drought, significantly improving the accuracy and biological significance of drought monitoring. Secondly, the configurability of the weighting coefficients gives the model strong regional adaptability and crop specificity. For example, in crop areas with shallow root systems, the weight of the precipitation component can be increased. In crop areas with well-developed root systems, the weight of the soil moisture term can be increased. This enables precise assessments across different agricultural scenarios. It provides core algorithmic support for generating scientific and reliable drought risk levels, directly improving the overall system's early warning accuracy.

[0036] In some embodiments, the pest and disease spread model uses a spatial transmission risk index for quantitative assessment, and the formula for calculating the spatial transmission risk index is as follows: Formula 2 in, Indicates the spatial transmission risk index, This represents the Euclidean distance between point i and evaluation unit j. This represents the effective transmission attenuation coefficient of a specific pest or disease under current weather conditions. This represents the wind speed factor for the current time period. This indicates the weight of wind-borne pests and diseases. This represents the insect migration rate factor for the current time period. This indicates the weight of insect-borne diseases and pests.

[0037] Formula 2 above allows for the quantification of the spatial diffusion dynamics of pathogens / insects. Specifically, this formula consists of the multiplication of two key parts: the first part... It is a spatial decay function, where The Euclidean distance represents the distance between the diseased field or insect source i and the unit j to be evaluated. This is the effective transmission attenuation coefficient of a specific pest or disease under current meteorological conditions such as temperature and humidity. This function simulates the natural law that risk decreases exponentially with increasing distance. Part Two It is a propagation driving force function that simultaneously considers two main pathways: wind propagation and autonomous insect migration. (Current wind speed factor) and The product of (wind propagation weight) represents the effectiveness of wind propagation of spores, mycelia, etc. (Insect migration rate factor, related to temperature and wind speed) and The product of (insect vector propagation weights) quantifies the migratory and dispersal capabilities of vector insects such as winged aphids and planthoppers. Finally, the spatial attenuation is multiplied by the propagation driving force to obtain the comprehensive SPRI value. This calculation method couples the distance attenuation law in physics with the disease and pest propagation mechanism in biology, enabling dynamic and quantitative simulation of risk propagation processes, overcoming the static and subjective limitations of traditional methods that rely solely on artificially defined buffer zones. Furthermore, it allows for modeling through different pathways (wind, insect vectors) and the introduction of adjustable weighting coefficients. and This enables the model to possess strong adaptability to different pests and diseases, allowing it to accurately depict the unique spread patterns of different pests and diseases (such as airborne powdery mildew and insect-borne rice dwarf virus) by adjusting parameters, thereby generating high-precision risk distribution heat maps. This provides crucial spatial decision-making basis for implementing precise targeted prevention and control by region and level, greatly improving the predictability and efficiency of pest and disease control.

[0038] In some embodiments, the GIS spatial database at the platform layer also stores historical disaster data and basic geographic information data, and is associated with real-time monitoring data for time-series trend analysis and model calibration. Specifically, the GIS spatial database not only stores real-time monitoring data streams from the perception layer, but also systematically integrates historical disaster databases and basic geographic information data. The historical disaster database may contain at least one of the following: the time, location, type, and intensity of disasters over the years. The basic geographic information data may include at least one of the following: topographic elevation, soil type, water system distribution, and land use map. Through a spatial engine and timestamps, these three types of data are associated and fused under a unified coordinate reference, constructing a "data cube" covering the spatiotemporal dimensions. Based on this, the system uses time-series analysis algorithms to compare current environmental parameters with historical data from the same period and to detect anomalies. Simultaneously, it performs pattern matching between real-time monitoring data and historical typical cases, providing crucial prior knowledge and verification benchmarks for the disaster analysis model. Through this architecture, by integrating historical context with real-time dynamics, the system can identify progressive and cumulative risks that exceed instantaneous thresholds (such as slowly developing seasonal droughts), significantly improving the sensitivity and predictability of early disaster identification. Secondly, it provides disaster analysis models with the ability to continuously self-calibrate. By comparing prediction results with actual historical cases, the models can dynamically optimize their internal parameters, thereby effectively adapting to regional specificities and the impact of climate change, ensuring the stability and reliability of the system's long-term monitoring and early warning accuracy.

[0039] In some embodiments, the application layer of this system implements monitoring and early warning functions by building a WebGIS visualization platform based on a B / S architecture. The specific implementation process is as follows: using the spatial analysis engine of the geographic information system, the disaster risk assessment results output by the platform layer are overlaid and rendered in real time with the electronic map base map, and the risk spatial distribution of disasters such as drought and floods is dynamically displayed on the web page using heat maps of different colors or hierarchical symbols; at the same time, the integrated chart component synchronously displays the data time series curves of key monitoring points; the system's preset early warning rule engine continuously compares the real-time risk level with the set threshold. Once the condition is triggered, the system immediately generates early warning information containing specific location and risk description through the integrated call gateway and message push service, and simultaneously sends SMS messages to the mobile phones of managers in the preset area, pushes alarms to professional APPs, and pops up strong reminders on the web interface. This approach transforms abstract disaster data into a visually intuitive "single map," enabling managers to quickly grasp the overall situation and accurately pinpoint risk hotspots, greatly improving decision-making efficiency and accuracy. Secondly, it establishes an automated closed loop from risk identification to information dissemination, achieving "early warning upon discovery" and completely solving the time delay problem caused by traditional manual assessment and notification. Finally, it ensures full coverage of early warning information through multiple channels such as SMS, APP, and Web, significantly improving the timeliness and reliability of agricultural disaster emergency response.

[0040] In one implementation, the system can utilize the spatial rendering capabilities of a WebGIS engine to associate disaster risk level data calculated at the platform layer with administrative divisions or geographic grids, rendering it in real-time on an electronic map using different colors, for example, a gradient from green to red; or it can render it in real-time on the electronic map using different legends, for example, using dotted symbols of different densities. This real-time rendering method can dynamically generate a thematic map of disaster risk covering the entire region, achieving macro-level control of risk with a single map. Simultaneously, the system provides a graphical user interface through an early warning rule configuration interface, allowing managers to set multi-level early warning thresholds (e.g., mild, moderate, severe) for different disasters such as drought, floods, and pests based on crop type, growth stage, and regional characteristics. When the real-time risk value output by the backend model engine exceeds any preset threshold, the system immediately triggers a multi-channel release mechanism, sending brief alerts to affected farmers via SMS based on the spatial layer of the disaster impact area, pushing out early warnings containing detailed risk maps and analysis reports via a professional app, and displaying pop-ups and strong audio alerts on the web monitoring screen. By transforming abstract data into intuitive, spatialized thematic maps, the system achieves "visualization and localization" of disaster risks, enabling managers to instantly identify high-risk areas and their spread directions, significantly improving situational awareness and decision-making efficiency. Secondly, configurable early warning rules endow the system with high flexibility and adaptability, meeting the precise management needs of different crops and regions, and avoiding false alarms or missed alarms caused by a "one-size-fits-all" approach. Finally, an automated and differentiated multi-channel information dissemination system ensures that different users, from macro-level decision-makers to frontline producers, can receive the most critical early warning information in the most convenient way at the first moment, bridging the "last mile" of disaster early warning and significantly improving the timeliness of emergency response and the effectiveness of prevention and control measures, thereby minimizing disaster losses.

[0041] In some embodiments, the system further includes a feedback optimization module for collecting user feedback on early warning information and adaptively adjusting the parameters of the disaster analysis model or the early warning threshold based on the feedback data. Specifically, after the system publishes early warning information through the application layer, it automatically generates online feedback channels. For example, a "true / false" button and an "actual situation notes" column can be embedded in the App's early warning page. The system proactively collects on-site feedback from farmers or managers regarding whether a disaster has occurred and its actual impact. After these spatiotemporally labeled feedback data are aggregated to the platform layer, the system automatically compares the feedback results with the original early warning records and quantitatively evaluates the early warning performance of a specific disaster model over a period of time through statistical calculations (such as accuracy, false alarm rate, and missed alarm rate). When the evaluation indicators of a certain type of disaster model are consistently lower than the preset standard (such as three consecutive false alarms or a monthly accuracy rate lower than 85%), the system immediately initiates an adaptive optimization process, using the feedback data set to dynamically fine-tune the key parameters of the model or the corresponding early warning threshold in the application layer through regression analysis or a Bayesian update algorithm. Dynamically fine-tuning the key parameters of the model may include adjusting the weighting coefficients α, β, and γ of the ICMI formula. Dynamically fine-tuning the corresponding early warning thresholds in the application layer can include adjusting personalized early warning thresholds for different disaster types and regions. This feedback optimization module constructs a complete closed loop from early warning issuance to effect verification and model optimization, enabling the system to continuously evolve by "learning in practice," fundamentally solving the problem of early warning accuracy degradation caused by environmental changes or regional differences in traditional static models. Secondly, through data-driven optimization based on real feedback, false alarms and missed alarms can be significantly reduced, continuously improving the reliability and credibility of early warning information, thereby enhancing users' reliance on the system and their willingness to use it. Finally, this self-optimizing characteristic greatly reduces the reliance on professional modelers in the later stages of system maintenance, achieving reduced operation and maintenance costs and self-maintaining long-term monitoring accuracy, ensuring efficient and reliable operation of the system throughout its entire lifecycle.

[0042] In one implementation, when the system determines from feedback data that the evaluation index of a certain type of disaster model is consistently below a preset standard, its adaptive optimization process will first focus on the dynamic fine-tuning of the model's key parameters. Specifically, taking the ICMI Integrated Meteorological Drought Index as an example, the system will combine the large amount of feedback data collected (such as "the warning is true and it is a severe drought", "the warning is false", etc.) with the original data used for model calculation ( , , , , , A new training sample set is formed. Then, regression analysis or a Bayesian update algorithm is used to recalculate the weight coefficients that best match the model output to the actual feedback. , , For example, if feedback repeatedly indicates that drought has occurred when soil moisture is adequate but rainfall is severely insufficient, the algorithm will automatically increase the weight of the rainfall component. At the same time, the weight of the soil moisture item was adjusted accordingly. This process makes the model's internal computational logic more consistent with the local disaster-causing mechanisms. The technical effect of this process is that it enables the "self-calibration" of the model's core algorithm, allowing the abstract mathematical model to continuously evolve based on feedback from the real world. This transforms it from a static "black box" into an intelligent agent with learning capabilities, thereby significantly improving the accuracy of disaster assessment and its robustness to different regional environments.

[0043] In one implementation, when initiating the adaptive optimization process, the system dynamically adjusts the warning threshold at the application layer. This process is independent of model parameter optimization and primarily targets user-preset thresholds used to trigger alarms. The system statistically analyzes historical warning records and user feedback. For example, it may find that the originally set "moderate drought" threshold (e.g., ICMI > 0.6) has led to an excessively high frequency of false alarms in a specific area (i.e., warnings are issued but the actual disaster is minor or has not occurred), or that the original "severe pest and disease" threshold has failed to capture actual disasters in a timely manner (i.e., missed reports). In this case, the optimization algorithm (e.g., based on the redefinition of confidence intervals) will automatically raise the "moderate drought" threshold for that area to ICMI > 0.65, or appropriately lower the lower limit threshold for the "severe pest and disease" risk level, based on this feedback evidence. The core technological effect of this mechanism is that it enables "refinement" and "regional customization" of early warning release strategies. By dynamically adapting to the vulnerability and management tolerance of different disaster-bearing bodies in different regions, it effectively filters out unnecessary interference alarms while ensuring that no real high-risk risks are overlooked. As a result, it significantly improves the signal-to-noise ratio of early warning information and user trust, and guides the allocation of prevention and control resources to achieve more precise and efficient results.

[0044] This technical solution comprehensively collects farmland environment and crop data through an integrated "air-space-ground" sensor network constructed at the perception layer, and stably transmits the data to the cloud platform via a low-power wide-area network at the transmission layer. At the platform layer, a GIS spatial database is used to uniformly manage multi-source data with geographic coordinates, and integrated multi-disaster analysis models are used for fusion calculation and intelligent diagnosis to achieve accurate identification and level assessment of disaster risks. At the application layer, the analysis results are visualized as risk thematic maps based on WebGIS, and multi-channel early warning releases are automatically triggered according to preset rules. The system also collects on-site feedback through a feedback optimization module, driving adaptive adjustments to model parameters and early warning thresholds to form a continuously optimized closed loop. Overall, it achieves full-link automation and intelligence from data collection and intelligent analysis to decision services, completely transforming the traditional disaster monitoring model that relies on manual labor. Secondly, through the deep integration of IoT and GIS, it overcomes the technical challenges of spatiotemporal fusion of multi-source data and accurate spatial assessment of disasters, achieving "early detection, accurate location, and precise assessment" of disasters. Finally, it constructs a monitoring and early warning system with self-learning and self-evolution capabilities, significantly improving the system's long-term reliability, early warning accuracy, and overall effectiveness in agricultural disaster prevention and mitigation.

[0045] See Figure 2 , Figure 2 A flowchart is shown of a method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS according to an embodiment of this application, which specifically includes the following steps.

[0046] Step 201: Collect environmental and crop data in real time through sensor nodes, drones, and remote sensing satellites deployed in farmland areas; Step 202: Transmit the collected data to the cloud platform using low-power wide-area IoT technology and the Internet; Step 203: In the cloud platform, use the GIS spatial database to store and manage monitoring data with geographic coordinates, and run the disaster analysis model to perform data fusion calculation and intelligent analysis in order to identify disaster signs and assess risk levels; Step 204: Based on WebGIS technology, provide a visual monitoring and early warning interface to display monitoring data and the spatial distribution of disaster risks in real time, and automatically trigger the multi-channel release of early warning information when the risk exceeds the threshold.

[0047] In one possible implementation, environmental and crop data are collected in real time using sensor nodes deployed in farmland areas, drones, and remote sensing satellites, including: Soil moisture and soil temperature data are collected through soil parameter sensor nodes; Data on temperature, humidity, rainfall, and wind speed were collected through field weather stations; Pest and disease monitoring equipment, including spore traps and insect traps, is used to collect basic information on the occurrence of pests and diseases. The region's crop growth is periodically acquired using drones and remote sensing satellites.

[0048] In one possible implementation, the following operations are performed specifically within the cloud platform: The drought level of a region is assessed based on meteorological and soil data using a drought index calculation model. The risk of urban flooding is assessed by combining a flood risk assessment model with topographic, rainfall, and drainage data. Simulate the potential spatial spread trend of pests and diseases using a pest and disease spread model; Low-temperature stress was identified based on time-series temperature data using a low-temperature freezing damage discrimination model.

[0049] In one possible implementation, the drought index calculation model uses a comprehensive meteorological drought index, wherein the formula for calculating the comprehensive meteorological drought index is:

[0050] in, This represents the comprehensive meteorological drought index. This indicates the actual precipitation in the current period. This represents the average annual precipitation over the same period. This indicates the current volumetric water content of the soil. This indicates the soil volumetric water content threshold suitable for crop growth. This indicates the current actual evapotranspiration. represents potential evapotranspiration, , , Denotes the weight coefficients, and satisfies , representing the contributions of precipitation, soil moisture, and evapotranspiration to drought, respectively.

[0051] In one possible implementation, the pest and disease spread model uses a spatial transmission risk index for quantitative assessment, and the formula for calculating the spatial transmission risk index is as follows:

[0052] in, Indicates the spatial transmission risk index, This represents the Euclidean distance between point i and evaluation unit j. This represents the effective transmission attenuation coefficient of a specific pest or disease under current weather conditions. This represents the wind speed factor for the current time period. This indicates the weight of wind-borne pests and diseases. This represents the insect migration rate factor for the current time period. This indicates the weight of insect-borne diseases and pests.

[0053] In one possible implementation, transmitting the data collected by the sensing layer to the cloud platform via low-power wide-area IoT technology and the Internet includes constructing a data transmission network using at least one of LoRa, NB-IoT, and 4G / 5G low-power wide-area IoT technologies.

[0054] In one possible implementation, a visual monitoring and early warning interface is provided based on WebGIS technology, displaying real-time monitoring data and the spatial distribution of disaster risks, and automatically triggering the multi-channel dissemination of early warning information when the risk exceeds a threshold, including: The spatial distribution of disaster risk levels is rendered and displayed in real time on an electronic map using different colors or legends, generating thematic maps of disaster risk. It provides an interface for configuring early warning rules, allowing users to set personalized early warning thresholds for different disaster types and regions; When the risk level output by the disaster analysis model exceeds the preset threshold, the system will automatically issue a warning to end users in the target area via at least one of the following methods: SMS, application push, or web platform pop-up.

[0055] In one possible implementation, the GIS spatial database also stores historical disaster data and basic geographic information data, and is associated with real-time monitoring data for time-series trend analysis and model calibration.

[0056] In one possible implementation, the method also includes collecting user feedback on the early warning information and adaptively adjusting the parameters of the disaster analysis model or the early warning threshold based on the feedback data.

[0057] Corresponding to the above method embodiments, this application also provides an embodiment of a regional agricultural disaster real-time monitoring device based on the Internet of Things and GIS, the device comprising: The sensing module is used to collect environmental and crop data in real time through sensor nodes deployed in farmland areas, drones, and remote sensing satellites; The transmission module is used to transmit the data collected by the sensing layer to the cloud platform via low-power wide-area Internet of Things technology and the Internet; The processing module, located on the cloud platform, uses a GIS spatial database to store and manage monitoring data with geographic coordinates, and runs a disaster analysis model to perform data fusion calculations and intelligent analysis in order to identify disaster signs and assess risk levels. The display module provides a visual monitoring and early warning interface based on WebGIS technology, which displays monitoring data and the spatial distribution of disaster risks in real time, and automatically triggers the multi-channel release of early warning information when the risk exceeds the threshold.

[0058] The above is a schematic scheme of a regional agricultural disaster real-time monitoring device based on the Internet of Things (IoT) and GIS according to this embodiment. It should be noted that the technical solution of this regional agricultural disaster real-time monitoring device based on IoT and GIS belongs to the same concept as the technical solution of the aforementioned regional agricultural disaster real-time monitoring method based on IoT and GIS. Details not described in detail in the technical solution of the regional agricultural disaster real-time monitoring device based on IoT and GIS can be found in the description of the technical solution of the aforementioned regional agricultural disaster real-time monitoring method based on IoT and GIS.

[0059] Figure 3 A structural block diagram of a computing device 300 according to an embodiment of this application is shown. The components of the computing device 300 include, but are not limited to, a memory 310 and a processor 320. The processor 320 is connected to the memory 310 via a bus 330, and a database 350 is used to store data.

[0060] The computing device 300 also includes an access device 340, which enables the computing device 300 to communicate via one or more networks 360. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 340 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0061] In one embodiment of this application, the aforementioned components of the computing device 300 and Figure 3 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 3The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this application. Those skilled in the art can add or replace other components as needed.

[0062] The computing device 300 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 300 can also be a mobile or stationary server.

[0063] The processor 320 executes computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things (IoT) and GIS. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned method for real-time monitoring of regional agricultural disasters based on IoT and GIS belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned method for real-time monitoring of regional agricultural disasters based on IoT and GIS.

[0064] An embodiment of this application also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the above-described method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0065] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the aforementioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS. Details not described in detail in the technical solution of the storage medium can be found in the description of the aforementioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0066] An embodiment of this application also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the above-described method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0067] The above is an illustrative scheme of a computer program according to this embodiment. It should be noted that the technical solution of this computer program belongs to the same concept as the technical solution of the above-mentioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS. For details not described in detail in the technical solution of the computer program, please refer to the description of the technical solution of the above-mentioned method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS.

[0068] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0070] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this application.

[0071] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0072] The preferred embodiments disclosed above are merely illustrative of this application. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments of this application. These embodiments are selected and specifically described in this application to better explain the principles and practical applications of the embodiments of this application, thereby enabling those skilled in the art to better understand and utilize this application. This application is limited only by the claims and their full scope and equivalents.

Claims

1. A regional agricultural disaster real-time monitoring system based on the Internet of Things and GIS, characterized in that, The system includes: The perception layer is used to collect environmental and crop data in real time through sensor nodes, drones, and remote sensing satellites deployed in farmland areas; The transport layer is used to transmit the data collected by the sensing layer to the cloud platform via low-power wide-area Internet of Things (IoT) technology and the Internet. The platform layer, as the core data processing platform, includes a GIS spatial database and a disaster analysis model engine. It is used to store and manage monitoring data with geographic coordinates, and to run disaster analysis models to perform fusion calculations and intelligent analysis on the data transmitted to the cloud platform in order to identify disaster signs and assess risk levels. The application layer is used to provide a visual monitoring and early warning interface based on WebGIS technology, display monitoring data and spatial distribution of disaster risks in real time, and automatically trigger the multi-channel release of early warning information when the risk exceeds the threshold.

2. The system according to claim 1, characterized in that, The perception layer specifically includes: Soil parameter sensor nodes are used to collect soil moisture and soil temperature data; Field weather stations are used to collect data on temperature, humidity, rainfall, and wind speed. Pest and disease monitoring equipment, including spore traps and insect traps, is used to collect basic information on the occurrence of pests and diseases; Drones and remote sensing satellites are used to periodically acquire remote sensing images of regional crop growth.

3. The system according to claim 1, characterized in that, The disaster analysis model engine of the platform layer integrates at least the following: A drought index calculation model is used to assess the drought level of a region based on meteorological and soil data. A flood risk assessment model is used to assess the risk of urban flooding by combining topographic, rainfall, and drainage data. Pest and disease spread models are used to simulate the potential spatial spread trends of pests and diseases. A low-temperature freezing damage discrimination model is used to identify low-temperature stress based on time-series temperature data.

4. The system according to claim 3, characterized in that, The drought index calculation model uses a comprehensive meteorological drought index, and the formula for calculating the comprehensive meteorological drought index is as follows: in, This represents the comprehensive meteorological drought index. This indicates the actual precipitation in the current period. This represents the average annual precipitation over the same period. This indicates the current volumetric water content of the soil. This indicates the soil volumetric water content threshold suitable for crop growth. This indicates the current actual evapotranspiration. represents potential evapotranspiration, , , Denotes the weight coefficients, and satisfies , representing the contributions of precipitation, soil moisture, and evapotranspiration to drought, respectively.

5. The system according to claim 3, characterized in that, The pest and disease spread model uses a spatial transmission risk index for quantitative assessment. The formula for calculating the spatial transmission risk index is as follows: in, Indicates the spatial transmission risk index, This represents the Euclidean distance between point i and evaluation unit j. This represents the effective transmission attenuation coefficient of a specific pest or disease under current weather conditions. This represents the wind speed factor for the current time period. This indicates the weight of wind-borne pests and diseases. This represents the insect migration rate factor for the current time period. This indicates the weight of insect-borne diseases and pests.

6. The system according to claim 1, characterized in that, The transmission layer specifically employs at least one low-power wide-area IoT technology among LoRa, NB-IoT, and 4G / 5G to construct the data transmission network.

7. The system according to claim 1, characterized in that, The application layer is specifically used for: The spatial distribution of disaster risk levels is rendered and displayed in real time on an electronic map using different colors or legends, generating thematic maps of disaster risk. It provides an interface for configuring early warning rules, allowing users to set personalized early warning thresholds for different disaster types and regions; When the risk level output by the disaster analysis model exceeds the preset threshold, the system will automatically issue a warning to end users in the target area via at least one of the following methods: SMS, application push, or web platform pop-up.

8. The system according to claim 1, characterized in that, The GIS spatial database of the platform layer also stores historical disaster data and basic geographic information data, and is associated with real-time monitoring data for time-series trend analysis and model calibration.

9. The system according to claim 1, characterized in that, The system also includes a feedback optimization module, which collects user feedback on early warning information and adaptively adjusts the parameters of the disaster analysis model or the early warning threshold based on the feedback data.

10. A method for real-time monitoring of regional agricultural disasters based on the Internet of Things and GIS, characterized in that, The method includes: Real-time environmental and crop data are collected through sensor nodes, drones, and remote sensing satellites deployed in farmland areas. The collected data is transmitted to the cloud platform via low-power wide-area IoT technology and the Internet. In the cloud platform, GIS spatial databases are used to store and manage monitoring data with geographic coordinates, and disaster analysis models are run to perform data fusion calculations and intelligent analysis in order to identify disaster signs and assess risk levels; Based on WebGIS technology, it provides a visual monitoring and early warning interface, which displays monitoring data and spatial distribution of disaster risks in real time, and automatically triggers the multi-channel release of early warning information when the risk exceeds the threshold.

Images