Agricultural and pastoral eco-hydrological intelligent management system based on cloud side-end cooperation

Abstract

The invention discloses an agricultural and pastoral eco-hydrological intelligent management system based on cloud side-end cooperation, and relates to the technical field of eco-hydrological management. A sensing layer collects multi-source data through a space base, an air base and a foundation; the transmission layer transmits the multi-source data to the edge layer through a data transmission and priority scheduling mechanism; the edge layer realizes local data analysis and quick response based on the multi-source data, and sends the multi-source data to the cloud platform; the cloud platform integrates a digital twin engine, a model library and a block chain fusion module, and provides comprehensive data processing, simulation prediction and intelligent decision support; and the decision-making layer adopts a multi-objective decision-making optimization algorithm to optimize balance among animal husbandry income, ecological water demand and net ecosystem productivity based on a deep analysis result of the cloud platform, triggers execution of an ecological compensation mechanism, generates a multi-dimensional decision-making instruction, and realizes perception-simulation-decision closed-loop control of the whole process of ecological hydrology.

Description

Technical Field

[0001] The present invention relates to the field of ecological hydrological management technology, and more specifically to an agricultural and animal husbandry ecological hydrological intelligent management system based on cloud-edge-end collaboration. Background Art

[0002] With the intensification of global climate change and human activities, the coupling relationship between hydrological processes and ecosystems in the agricultural-pastoral transition zone, an ecologically fragile and resource-sensitive area, is becoming increasingly complex. Traditional ecohydrological management models are no longer able to meet the needs of efficient water resource allocation, ecological protection, and coordinated development of production in this region. Currently, the informatization of ecohydrological management in the agricultural-pastoral transition zone faces the following key bottlenecks:

[0003] First, data collection suffers from a serious "data silo" problem. Existing monitoring methods primarily include satellite remote sensing, drone inspections, and ground sensors. However, due to the diverse equipment sources, heterogeneous data formats, and non-standard communication protocols, standardized access and integrated analysis of multi-source data is difficult, severely restricting information sharing and system integration.

[0004] Secondly, computing processing methods suffer from high response latency. Currently, most platforms still rely on centralized cloud computing centers for data processing and model calculations, lacking the localized intelligent processing capabilities of edge nodes. For scenarios requiring rapid response (e.g., less than two hours) such as flood warnings, traditional architectures often fail to meet real-time requirements, impacting decision-making timeliness and emergency response capabilities.

[0005] Third, decision-making support suffers from fragmentation and empiricism. A lack of scientific, quantitative trade-offs between ecological protection and animal husbandry production, as well as intelligent decision-making models based on multi-objective optimization, makes it difficult for management strategies to balance ecological and economic benefits. The decision-making process is highly subjective and lacks adaptability.

[0006] Therefore, how to provide an intelligent agricultural and pastoral ecological and hydrological management system based on cloud-edge-end collaboration is an urgent problem that technical personnel in this field need to solve. Summary of the Invention

[0007] In view of this, the present invention provides an agricultural and animal husbandry ecological and hydrological intelligent management system based on cloud-edge-end collaboration. By constructing a multi-level data fusion mechanism, dynamic resource scheduling strategy and intelligent model deduction system under the "cloud-edge-end" collaborative architecture, it realizes the perception-simulation-decision-making closed-loop control of the entire ecological and hydrological process, and improves the water resource utilization efficiency and ecological security guarantee capabilities in arid / semi-arid areas.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] An intelligent agricultural and animal husbandry eco-hydrological management system based on cloud-edge-end collaboration includes: an eco-hydrological information management module and an eco-hydrological source tracing and early warning application module; the eco-hydrological information management module includes a perception layer, a transmission layer, and an edge layer; the eco-hydrological source tracing and early warning application module includes a cloud platform and a decision-making layer;

[0010] The perception layer collects multi-source data through space-based, air-based and ground-based methods;

[0011] The transport layer transmits multi-source data to the edge layer through data transmission and priority scheduling mechanisms;

[0012] The edge layer implements local data analysis and rapid response based on multi-source data, and sends multi-source data to the cloud platform;

[0013] The cloud platform integrates a digital twin engine, model library, and blockchain fusion module to provide comprehensive data processing, simulation prediction, and intelligent decision-making support;

[0014] Based on the in-depth analysis results of the cloud platform, the decision-making layer uses a multi-objective decision optimization algorithm to optimize the balance between pastoral income, ecological water demand and net ecosystem productivity, and trigger the execution of the ecological compensation mechanism to generate multi-dimensional decision instructions.

[0015] Preferably, the perception layer includes:

[0016] Space-based: Integrate different types of satellites to obtain daily Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), groundwater storage, and precipitation forecast data;

[0017] Airborne: A swarm of drones equipped with multispectral sensors, LiDAR, and thermal infrared sensors will be deployed. The multispectral sensors will perform inversion processing to obtain biomass density, while LiDAR will analyze point clouds to obtain runoff paths, waterlogged areas, and gully development. Thermal infrared sensors will be used to obtain grazing activity and grazing intensity indices. Based on these data, high-precision vegetation coverage heat maps will be generated in real time to optimize grazing paths.

[0018] Foundation: Deploy IoT terminals, including soil multi-parameter meters and livestock smart collars. The soil multi-parameter meters are used to collect soil moisture content and monitor surface parameters. The livestock smart collars are used to monitor livestock feeding behavior and GPS movement trajectories.

[0019] Preferably, the edge layer comprises:

[0020] The regional edge center is equipped with a high-performance server cluster to run the SWAT-HS hydrological model, simulate the watershed-scale water cycle and generate an ecological security index;

[0021] The station edge gateway runs the TensorFlow Lite model to calculate the livestock carrying capacity of the grassland in real time.

[0022] Preferably, the cloud platform layer includes:

[0023] The digital twin engine integrates multi-source data through 3D modeling, supports dynamic parameter injection and real-time rendering, and is used to simulate ecological responses under different scenarios;

[0024] Model library, including hydrological models, ecological models and AI models, for the edge layer and decision-making layer to call;

[0025] The blockchain fusion module uses Hyperledger Fabric to build a consortium chain for blockchain evidence storage and supports the ecological compensation mechanism.

[0026] Preferably, the hydrological model includes the SWAT-HS hydrological model and the HEC-RAS flood simulation model;

[0027] Ecological models include the CENTURY grassland carbon cycle model and the TensorFlow Lite model;

[0028] The AI ​​model is used to optimize grazing paths based on high-precision vegetation cover heat maps.

[0029] Preferably, the SWAT-HS hydrological model is run to calculate the ecological security index ESI:

[0030]

[0031] in, is the soil moisture content, is the critical threshold of soil moisture, is the normalized vegetation index, is the normalized vegetation index benchmark value, For groundwater reserves, is the average value of groundwater reserves over many years, weight coefficient ;

[0032] Run the TensorFlow Lite model to calculate the pasture carrying capacity C in real time:

[0033]

[0034] Where A is grassland area, BD is biomass density, is the restitution coefficient, is the daily feed intake, The number of grazing days.

[0035] Preferably, the ecological compensation mechanism is as follows:

[0036] When the ESI of a grassland is > 0.8 for three consecutive months, compensation is triggered:

[0037]

[0038] in, For grassland ecological compensation, is the coefficient, A is the grassland area, is the price of carbon sinks.

[0039] Preferably, the multi-objective optimization function is:

[0040]

[0041] in, For the economic benefits of animal husbandry, is the ecological water demand, is the net ecosystem productivity, is the ecological security index, For grassland carrying capacity, The maximum pasture carrying capacity is is the soil moisture content, is the critical threshold of soil moisture, 、 、 、 、 is the weight, and ESI is the ecological security index.

[0042] Preferably, the decision-making layer also includes an AR interactive terminal.

[0043] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention discloses an agricultural and animal husbandry ecological and hydrological intelligent management system based on cloud-edge-end collaboration, which has the following advantages:

[0044] 1) Data integration and breaking down “data silos”:

[0045] By integrating multi-source data—space-based (satellite imagery), air-based (LiDAR point clouds), and ground-based (sensor data)—this technology addresses the heterogeneous data formats and lack of unified access standards across traditional monitoring devices. This allows data from different sources to be analyzed on the same platform, improving the comprehensiveness and accuracy of data analysis.

[0046] 2) Real-time and low latency:

[0047] The use of 5G slicing network technology and layered processing architecture provides exclusive bandwidth for emergency data (such as flood warnings and ecological disasters), that is, on-site computing at the edge layer, avoiding the network jumps of traditional cloud center processing and reducing the data transmission distance, thereby ensuring the rapid transmission of information. The response time is less than 50ms, which is much lower than the response time of the traditional cloud center processing mode (>2 hours), meeting the needs of real-time decision-making.

[0048] 3) Intelligent model deduction and optimization decision support:

[0049] The system integrates a variety of advanced eco-hydrological analysis models (such as SWAT-HS, HEC-RAS, CENTURY, and TensorFlow Lite), as well as AI models (deep reinforcement learning and LSTM). This allows for simulation and prediction of eco-hydrological processes, as well as the generation of optimization recommendations and early warning information. Furthermore, the application of the NSGA-II multi-objective genetic algorithm helps resolve the conflict between ecological protection and animal husbandry production, achieving an optimal balance between economic and ecological benefits.

[0050] 4) Blockchain technology ensures data credibility and transparency:

[0051] A consortium blockchain built on Hyperledger Fabric automatically verifies data integrity through smart contracts, ensuring its authenticity and immutability. Furthermore, blockchain technology is used to implement an automated ecological compensation mechanism, enhancing its transparency and efficiency and encouraging herders to actively participate in ecological protection.

[0052] 5) Flexibility and scalability:

[0053] The system design adopts a modular structure, facilitating the addition of new sensors, models, or functional modules based on actual needs, providing strong flexibility and scalability. Furthermore, the "cloud-edge-end" collaborative architecture allows local computing tasks to be performed at the edge, reducing the cloud load and improving overall system performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0055] Figure 1 This is a structural diagram of an agricultural, animal husbandry, ecological and hydrological intelligent management system based on cloud-edge-end collaboration provided by the present invention.

[0056] Figure 2 This is a data processing flow chart provided by the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0058] The embodiment of the present invention discloses an intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration, such as Figure 1 and Figure 2 As shown, it includes: eco-hydrological information management module and eco-hydrological source tracing and early warning application module;

[0059] The eco-hydrological information management module includes the perception layer, transmission layer, and edge layer; the eco-hydrological source tracing and early warning application module includes the cloud platform and decision-making layer;

[0060] The perception layer collects multi-source data through space-based, air-based and ground-based methods;

[0061] The transport layer transmits multi-source data to the edge layer through data transmission and priority scheduling mechanisms;

[0062] The edge layer implements local data analysis and rapid response based on multi-source data, and sends multi-source data to the cloud platform;

[0063] The cloud platform integrates a digital twin engine, model library, and blockchain fusion module to provide comprehensive data processing, simulation prediction, and intelligent decision-making support;

[0064] The decision-making layer, based on the in-depth analysis results of the cloud platform, uses a multi-objective decision-making optimization algorithm to optimize the balance between pastoral income, ecological water demand and net ecosystem productivity, as well as trigger the execution of the ecological compensation mechanism to generate multi-dimensional decision instructions.

[0065] In order to facilitate further understanding of the technical solution of the present invention, a specific introduction is given below:

[0066] 1. Perception Layer (End Device Layer)

[0067] ① Space-based perception:

[0068] [1] Satellite network: Integrates Sentinel-2 (optical), GRACE-FO (gravity) and FY-4A (meteorology), and obtains daily:

[0069] 10m resolution vegetation indices (Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI);

[0070] Groundwater reserves (GWSA);

[0071] 15-minute precipitation forecast data (spatial resolution 4km);

[0072] [2] Data preprocessing: Radiation correction and geometric registration are performed on vegetation index, groundwater storage, and precipitation forecast data at the satellite ground station, and the data are directly transmitted to the cloud platform after preliminary processing at the satellite ground station.

[0073] ②Air-based perception:

[0074] [1] Drone swarm:

[0075] Aircraft configuration: Multi-rotor (DJI M300) for fixed-point scanning, fixed-wing (eBee X) for regional surveys;

[0076] Sensors: Multispectral (RedEdge-MX) inversion processing obtains biomass density (BD) for the TensorFlowLite model to calculate grassland carrying capacity (C) in real time and drive the CENTURY model to predict grassland carbon cycle simulations. LiDAR (Velodyne Puck) point cloud analysis obtains runoff paths, waterlogged areas, and gully development for running a simplified HEC-RAS model to quickly simulate flood inundation ranges. Thermal infrared (FLIR Vue Pro) and multispectral fusion processing obtain the Grazing Activity Index (GAI) and Grazing Intensity Index (GII) for AR interactive terminals to help herders intuitively identify compliant areas.

[0077] Edge processing: NVIDIA Jetson AGX onboard drones generates real-time vegetation coverage heat maps (5cm resolution) for deep reinforcement learning (AI models) to optimize grazing paths.

[0078] ③ Ground perception:

[0079] [1] IoT terminals:

[0080] Soil multi-parameter meter: measures soil moisture content (FDR principle), temperature, and conductivity (accuracy ±2%) at 0-100cm, and uploads data every 15 minutes;

[0081] Livestock smart collar: Integrates GPS / Beidou dual-mode positioning, a three-axis accelerometer, and an RFID tag to monitor livestock feeding behavior and GPS movement trajectories;

[0082] [2] Communication protocol: Adopts LoRaWAN+MQTT protocol, supports low-power wide-area transmission (node ​​life > 3 years).

[0083] 2. Transport Layer and Edge Computing

[0084] 1. Transport layer

[0085] This invention uses 5G slicing network technology to build efficient and low-latency communication channels to meet the data transmission needs in different business scenarios.

[0086] ① Dynamic bandwidth allocation mechanism:

[0087] Emergency channel (used for data with high real-time requirements, such as precipitation warnings and ecological disasters): The transmission path is air-based-transmission layer-edge layer-cloud platform, with exclusive dedicated bandwidth resources to ensure end-to-end latency of less than 50ms, prioritizing emergency response.

[0088] Conventional monitoring channels (such as daily monitoring data such as soil moisture): The transmission path is foundation-transmission layer-edge layer-cloud platform, sharing bandwidth, and delay is controlled within 200ms, taking into account both stability and efficiency.

[0089] Historical data transmission (such as logs and archived data): Schedule transmission during the night when the network is idle. The bandwidth can be automatically adjusted according to the current load without affecting other critical tasks.

[0090] ②QoS guarantee algorithm:

[0091] Traffic scheduling optimization based on Weighted Fair Queueing (WFQ);

[0092] Dynamically adjust the data priority weight of each channel to ensure that high-priority data (such as flood warnings) always obtains the best transmission resources while maintaining the overall system throughput and stability.

[0093] 2. Edge Node Design

[0094] ① Regional edge layer:

[0095] Hardware: Equipped with a high-performance server cluster and NVIDIA A100 GPUs, it supports parallel computing and deep learning inference tasks.

[0096] Core functions: Run the SWAT-HS hydrological model, simulate the water cycle at the basin scale (time step of 1 hour), and generate the Ecological Security Index (ESI). The formula is:

[0097]

[0098] in, is the soil moisture content, is the critical threshold of soil moisture, is the normalized vegetation index, is the normalized vegetation index benchmark value, For groundwater reserves, is the average value of groundwater reserves over many years, weight coefficient , the weights are dynamically adjusted based on principal component analysis (PCA).

[0099] ②Site edge gateway:

[0100] Hardware: The core device is a Raspberry Pi 4 (ARM Cortex-A72 quad-core processor, 4GB RAM) paired with an Intel Neural Compute Stick 2 accelerator, which has lightweight AI inference capabilities;

[0101] Core functionality: TensorFlow Lite model: Real-time calculation of pasture carrying capacity (C):

[0102]

[0103] Where A is grassland area (ha), BD is biomass (kg / ha), is the restitution coefficient (0-1), is the daily feed intake (kg / sheep unit), The number of grazing days.

[0104] Anomaly detection mechanism:

[0105] Use the Isolation Forest algorithm to identify abnormal patterns.

[0106] When a sudden drop in soil moisture of more than 25% / 6 hours is detected, an alarm is triggered and the drone is linked to perform high-frequency scanning to obtain more detailed surface information.

[0107] 3. Cloud Platform

[0108] 1. Digital Twin Engine:

[0109] This invention constructs a watershed digital twin by integrating LiDAR point clouds (5cm accuracy), Sentinel-2 imagery, and geological data. Through virtual modeling and real-time data-driven development, it dynamically maps the physical watershed into digital space, supporting the simulation, prediction, and decision-making optimization of ecohydrological processes. In dynamic simulations and scenario-based scenarios, the digital twin engine simulates ecohydrological responses under different management strategies (grazing intensity, precipitation changes). Specifically, these simulations include predicting grassland degradation trends, assessing flood inundation extent, quantifying changes in carbon sequestration potential, and calculating grazing carrying capacity. These simulation results provide managers with a scientific basis for developing more effective ecological protection and resource utilization strategies. In multi-source data fusion, the digital twin engine integrates space-based (satellite imagery), air-based (LiDAR point cloud) and ground-based (sensor data) observation data into a unified three-dimensional space, solving the problem of data silos (its main technical advantage is supporting spatiotemporal matching and data assimilation, for example: fusing drone LiDAR terrain data with Sentinel-2 imagery to generate high-precision land use maps; combining soil moisture sensor data with the GRACE-FO groundwater model to analyze water cycle paths.); in terms of intelligent decision support, the digital twin engine provides real-time virtual visualization output, such as grazing boundaries and grazing routes, and supports dynamic parameter injection (such as precipitation scenario simulation, soil moisture and vegetation cover changes), realizing real-time rendering of eco-hydrological responses, and enhancing the visualization and interactivity of decision-making.

[0110] 2. Model Library:

[0111] The model library integrates a variety of ecohydrological analysis models, providing algorithmic support for data-driven decision-making. These models are used for diverse analytical tasks, such as predicting hydrological changes, assessing grassland productivity, and optimizing grazing paths. The model library provides a centralized location for storing and managing these models, making them easily accessible and updatable.

[0112] In subsequent steps, the model library may be used in the data processing phase, such as for in-depth analysis in the cloud platform or real-time computing at the edge node. For example, when an edge gateway detects abnormal data, it may need to call on lightweight models in the model library for rapid analysis. Furthermore, in the decision-making phase, models in the model library are used to generate optimization recommendations or early warning information.

[0113] The model library runs through the entire eco-hydrological network platform system of the agricultural-pastoral transition zone, playing a key role in in-depth analysis of multi-source data, multi-model implementation of water-grass-livestock coupling system analysis, multi-scenario simulation and deduction, and intelligent decision-making. The specific model types are as follows:

[0114] Hydrological models: SWAT-HS is used for basin-scale water cycle simulation, and HEC-RAS is used for rapid simulation of flood inundation range;

[0115] Ecological models: CENTURY for grassland carbon cycle simulation, and TensorFlow Lite for local grassland stocking capacity assessment;

[0116] AI models: Deep reinforcement learning (DRL) is used to optimize grazing paths, and LSTM is used to predict drought risks.

[0117] 3. Blockchain integration module

[0118] ①Data storage:

[0119] [1] Chain structure: A consortium chain is built based on Hyperledger Fabric, with nodes including multiple participants such as the government, scientific research institutions, and herders' associations, ensuring trusted data sharing and collaborative governance;

[0120] [2] Evidence storage process:

[0121] The sensor data is hashed with SHA-256 and uploaded to the blockchain;

[0122] The data block header contains timestamp, GPS coordinates and device ID to ensure the data source is traceable;

[0123] Smart contracts automatically verify data integrity to prevent tampering and forgery.

[0124] ②Ecological compensation:

[0125] [1] The blockchain-based ecological compensation mechanism is automated through smart contracts:

[0126] When the ESI of a grassland is > 0.8 for three consecutive months, compensation is triggered:

[0127]

[0128] in, For grassland ecological compensation, is the coefficient, A is the grassland area, is the carbon sink price (yuan / ton).

[0129] 4. Decision-making Level

[0130] ① Multi-objective optimization:

[0131] In order to achieve a balance between ecological and economic benefits, the present invention adopts a multi-objective optimization method to construct the following objective function:

[0132]

[0133] in, For the economic benefits of animal husbandry, is the ecological water demand, is the net ecosystem productivity, is the ecological security index, For grassland carrying capacity, The maximum pasture carrying capacity is is the soil moisture content, is the critical threshold of soil moisture, 、 、 、 、 is the weight, and ESI is the ecological security index.

[0134] The solution algorithm uses the NSGA-II multi-objective genetic algorithm, which outputs a Pareto frontier solution set for decision makers to select the optimal compromise solution. This method effectively solves the problem of traditional empirical decision-making, which is difficult to balance multiple objectives, and improves the scientific nature and adaptability of decision-making.

[0135] ② AR interactive terminal:

[0136] This invention introduces Microsoft HoloLens 2 augmented reality glasses as a human-computer interaction terminal to improve the intelligence level of on-site operations:

[0137] Real-time overlay of virtual grazing boundaries: green indicates grazing areas, red indicates prohibited grazing areas, helping herders intuitively identify compliant areas;

[0138] Voice prompts for key indicators: such as "Soil moisture ahead is 12%, recommended to stay <2 hours", assisting herders in making immediate decisions;

[0139] Gesture operation to call historical data comparison: users can use sliding gestures to view the difference in NDVI between this month and last month, and understand the changing trend of grassland health status.

[0140] The specific implementation steps of the present invention are as follows:

[0141] 1. Network system construction

[0142] ① Perception layer:

[0143] Space-based: Access Sentinel-2, GRACE-FO, and FY-4A data, and update vegetation index, groundwater storage, and precipitation forecast data daily and upload them directly to the cloud platform;

[0144] Airborne: UAV aerial survey data (LiDAR + multispectral) is transmitted to the edge layer via the 5G slicing network of the transport layer for pre-processing and then uploaded to the cloud platform;

[0145] Foundation: IoT sensors (soil multi-parameter meters, livestock smart collars) are transmitted to the edge layer via LoRaWAN at the transport layer, pre-processed by the site edge gateway, and synchronized to the cloud platform;

[0146] ②Transport layer:

[0147] 5G network slicing: allocate independent channels for emergency data (such as heavy rain warnings) with a latency of <50ms

[0148] Beidou short message: ensures data transmission in areas without network coverage (such as monitoring points in desert areas)

[0149] ③Edge layer:

[0150] Regional edge centers: Run the SWAT-HS model to generate weekly water supply and demand reports;

[0151] Station edge gateway: Real-time calculation of pasture carrying capacity,

[0152] ④ Cloud Platform:

[0153] Digital Twin Engine: Build a 3D watershed model to simulate ecological responses under different grazing / precipitation scenarios

[0154] Decision Cockpit: Visual display of Ecological Security Index (ESI), Water Pressure Level (WPL), etc.

[0155] 2. Intelligent application scenarios

[0156] ① Grassland degradation early warning:

[0157] The edge gateway collects and analyzes NDVI (Normalized Difference Vegetation Index) and soil moisture data from the sensor layer in real time. If the NDVI in a particular area drops by more than 15% and the soil moisture content falls below 10%, an alarm is triggered and the relevant data is stored using blockchain technology.

[0158] After receiving data uploaded by the edge gateway, the cloud platform uses historical data and a deep reinforcement learning (DRL) model to assess the risk of grassland degradation in the affected area over the next three months. If the predicted probability of degradation exceeds 80%, a detailed ecological security report is generated.

[0159] Based on the assessment results, the decision-making level automatically issues a grazing ban to prevent further deterioration. This ban is directly sent to local herders via augmented reality (AR) glasses, and a smart eco-compensation contract is simultaneously activated to ensure that affected areas receive appropriate financial compensation or restoration measures.

[0160] ② Flood risk prevention and control:

[0161] The perception layer uses space-based satellites (such as the FY-4A meteorological satellite) to continuously monitor regional precipitation. If the cumulative precipitation exceeds 50mm within 24 hours, an initial warning signal is immediately generated and the edge layer is notified to initiate emergency response procedures.

[0162] Upon receiving the warning signal, the edge layer quickly activated the lightweight HEC-RAS flood model. This model, combined with LiDAR (Velodyne Puck) point cloud analysis, captured runoff paths, ponding areas, and gully development. This model then ran a simplified HEC-RAS model to rapidly simulate the flood inundation area. The inundation map was generated within 10 minutes, with an accuracy of ±5 meters.

[0163] The LiDAR terrain data and precipitation data are fused and pre-processed, compressed and uploaded to the cloud platform. The cloud platform integrates all relevant information, including simulation results and real-time meteorological data, and hashes the warning event on the chain. At the same time, the full-featured SWAT-HS model is called to verify the reliability of the edge layer model simulation results, forming comprehensive flood warning information and pushing the final instructions to the decision-making level.

[0164] Decision-makers broadcast early warning information to residents in relevant areas through the 5G network, provide specific evacuation guidelines, and guide livestock to move to safe areas.

[0165] Decision-makers may also use AR devices to provide intuitive operational guidance to on-site rescue personnel to improve response efficiency.

[0166] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0167] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration, characterized by: include: Ecological hydrological information management module and ecological hydrological source tracing and early warning application module; The eco-hydrological information management module includes the perception layer, transmission layer, and edge layer; the eco-hydrological source tracing and early warning application module includes the cloud platform and decision-making layer; The perception layer collects multi-source data through space-based, air-based and ground-based methods; The transport layer transmits multi-source data to the edge layer through data transmission and priority scheduling mechanisms; The edge layer implements local data analysis and rapid response based on multi-source data, and sends multi-source data to the cloud platform; The cloud platform integrates a digital twin engine, model library, and blockchain fusion module to provide comprehensive data processing, simulation prediction, and intelligent decision-making support; Based on the in-depth analysis results of the cloud platform, the decision-making layer uses a multi-objective decision optimization algorithm to optimize the balance between pastoral income, ecological water demand and net ecosystem productivity, and trigger the execution of the ecological compensation mechanism to generate multi-dimensional decision instructions.

2. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 1 is characterized in that: The perception layer includes: Space-based: Integrate different types of satellites to obtain daily Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), groundwater storage, and precipitation forecast data; Airborne: A swarm of drones equipped with multispectral sensors, LiDAR, and thermal infrared sensors will be deployed. The multispectral sensors will perform inversion processing to obtain biomass density, while LiDAR will analyze point clouds to obtain runoff paths, waterlogged areas, and gully development. Thermal infrared sensors will be used to obtain grazing activity and grazing intensity indices. Based on these data, high-precision vegetation coverage heat maps will be generated in real time to optimize grazing paths. Foundation: Deploy IoT terminals, including soil multi-parameter meters and livestock smart collars. The soil multi-parameter meters are used to collect soil moisture content and monitor surface parameters. The livestock smart collars are used to monitor livestock feeding behavior and GPS movement trajectories.

3. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 1 is characterized in that: The edge layer includes: The regional edge center is equipped with a high-performance server cluster to run the SWAT-HS hydrological model, simulate the watershed-scale water cycle and generate an ecological security index; The station edge gateway runs the TensorFlow Lite model to calculate the livestock carrying capacity of the grassland in real time.

4. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 2 is characterized in that: The cloud platform layer includes: The digital twin engine integrates multi-source data through 3D modeling, supports dynamic parameter injection and real-time rendering, and is used to simulate ecological responses under different scenarios; Model library, including hydrological models, ecological models and AI models, for the edge layer and decision-making layer to call; The blockchain fusion module uses Hyperledger Fabric to build a consortium chain for blockchain evidence storage and supports the ecological compensation mechanism.

5. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 4 is characterized in that: Hydrological models include the SWAT-HS hydrological model and the HEC-RAS flood simulation model; Ecological models include the CENTURY grassland carbon cycle model and the TensorFlow Lite model; The AI ​​model is used to optimize grazing paths based on high-precision vegetation cover heat maps.

6. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 5 is characterized in that: Run the SWAT-HS hydrological model to calculate the ecological security index ESI: ； in, The soil moisture content, is the critical threshold of soil moisture, is the normalized vegetation index, is the normalized vegetation index benchmark value, For groundwater reserves, is the average value of groundwater reserves over many years, weight coefficient ; Run the TensorFlow Lite model to calculate the pasture carrying capacity C in real time: ； Where A is grassland area, BD is biomass density, is the restitution coefficient, is the daily feed intake, The number of grazing days.

7. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 6 is characterized in that: The specific ecological compensation mechanism is as follows: When the ESI of a grassland is > 0.8 for three consecutive months, compensation is triggered: ； in, For grassland ecological compensation, is the coefficient, A is the grassland area, is the price of carbon sinks.

8. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 1 is characterized in that: The multi-objective optimization function is: ； in, For the economic benefits of animal husbandry, is the ecological water demand, is the net ecosystem productivity, is the ecological security index, For grassland carrying capacity, The maximum pasture carrying capacity is is the soil moisture content, is the critical threshold of soil moisture, 、 、 、 、 is the weight, and ESI is the ecological security index.

9. The intelligent agricultural and animal husbandry ecological and hydrological management system based on cloud-edge-end collaboration according to claim 1 is characterized in that: The decision-making layer also includes AR interactive terminals.

Images