Soil moisture content remote monitoring system and method based on big data

Abstract

The invention provides a soil moisture content remote monitoring system and method based on big data, and relates to the technical field of soil moisture content monitoring. Multi-temporal remote sensing images are used for recognizing the phenological stage of crops, collecting meteorological data and measuring soil parameters; calculating the reference water vapor evaporation capacity of the crops based on the meteorological data and the soil parameters, and calculating the actual water vapor evaporation capacity of the crops based on the phenological stage; calculating a soil heat flux value according to the atmospheric stability and the flow resistance coefficient; constructing an entropy balance equation based on the soil heat flux value, and calculating the soil entropy variation; and predicting the soil entropy based on the soil entropy variation, and classifying the soil moisture content.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of soil moisture monitoring, and particularly relates to a soil moisture remote monitoring system and method based on big data. BACKGROUND

[0002] With the development of agricultural scale and intensification, large-scale farmers and agricultural managers need to accurately understand the soil moisture in order to scientifically arrange irrigation, fertilization and other agricultural activities. For example, in arid areas, accurate soil moisture data can help farmers reasonably determine the irrigation time and irrigation amount, avoid water waste, and at the same time ensure that crops are supplied with sufficient water, thereby improving crop yield and quality.

[0003] Accurate soil moisture monitoring is the basis for realizing agricultural machine automation and intelligence. Intelligent agricultural equipment needs to adjust operation parameters such as seeding depth and fertilization amount according to real-time soil moisture information to adapt to different soil conditions, thereby improving agricultural production efficiency and resource utilization efficiency.

[0004] The rise of big data technology provides a powerful means for the storage, processing and analysis of massive soil moisture data. Through comprehensive analysis of long-term accumulated soil moisture data and related meteorological data, crop growth data, etc., the rules and trends of soil moisture changes can be mined, providing a more scientific basis for agricultural production decisions.

[0005] Internet of Things technology enables soil moisture monitoring devices to collect data in real time and transmit it to the cloud, enabling remote and real-time monitoring. The development of sensor technology makes soil moisture monitoring more accurate, enabling the acquisition of multi-dimensional information such as soil moisture, temperature and nutrients, enriching the content of soil moisture monitoring.

[0006] However, traditional soil moisture monitoring methods have limitations. Traditional soil moisture measurement mainly relies on manual field sampling and laboratory analysis, which is tedious and requires a lot of manpower. Moreover, the measurement period is long and cannot reflect the dynamic changes of soil moisture in a timely manner. For example, during the growing season of crops, soil moisture changes rapidly, and manual measurement may not meet the needs of timely adjustment of agricultural activities.

[0007] Some existing automated monitoring devices, such as fixed-point soil moisture sensors, can achieve real-time monitoring to some extent, but have limited monitoring range and are susceptible to environmental interference. Moreover, the data quality of monitoring devices deployed in different regions is uneven, with a high prevalence of data outliers and missing values, affecting the accuracy and reliability of monitoring results. At the same time, these monitoring devices often operate independently, lacking effective data integration and sharing mechanisms, making it difficult to form a comprehensive and systematic soil moisture monitoring system. SUMMARY

[0008] To address the aforementioned technical problems, this invention proposes a remote soil moisture monitoring method based on big data, comprising the following steps:

[0009] S1. Use multi-temporal remote sensing images to identify crop phenological stages, collect meteorological data, and measure soil parameters;

[0010] S2. Calculate the reference water vapor evaporation of crops based on meteorological data and soil parameters, and calculate the actual water vapor evaporation of crops based on phenological stages;

[0011] S3. Calculate the soil heat flux based on atmospheric stability and flow resistance coefficient;

[0012] S4. Construct an entropy balance equation based on soil heat flux and actual water vapor evaporation, and calculate the change in soil entropy.

[0013] S5. Predict soil entropy values ​​based on changes in soil entropy values ​​and classify soil moisture levels.

[0014] In a preferred embodiment, in step S2, the reference water vapor evaporation CT0 of the crop is calculated based on meteorological data and soil parameters.

[0015]

[0016] Where F is the slope of the saturated water vapor pressure-temperature curve, and R... n For net radiation, G is soil moisture flux, γ is a constant, U is wind speed at the preset height, E is water vapor pressure difference between the preset height and the ground surface, and T represents the 24-hour average temperature.

[0017] Combined with the crop coefficient K corresponding to the phenological stage c Calculate the actual water vapor evaporation rate CT:

[0018] CT=K c ×CT0.

[0019] In a preferred embodiment, step S3 includes the following steps:

[0020] S31, Initial parameter setting for heat flux;

[0021] S32. Based on the initial value of the heat flux, calculate the friction velocity and characteristic temperature to obtain the atmospheric stability;

[0022] S33. Based on atmospheric stability, determine the stability correction term and calculate the flow resistance coefficient;

[0023] S34. Based on the flow resistance coefficient, iteratively solve for the heat flux.

[0024] In a preferred embodiment, in step S32, the friction speed u is calculated.* and characteristic temperature θ * :

[0025]

[0026] Where ρ is the air density, C p φ is the specific heat capacity of air at constant pressure. m This represents the value of the atmospheric momentum change function.

[0027] In a preferred embodiment, the atmospheric stability L is calculated as follows:

[0028]

[0029] Among them, T a Let be the ambient atmospheric temperature, k be a proportionality constant, and g be the gravitational acceleration.

[0030] In a preferred embodiment, in step S33, a stability correction term is determined based on atmospheric stability L and atmospheric standard stability L′.

[0031]

[0032] Calculate the flow resistance coefficient r a :

[0033]

[0034] Where z is the momentum roughness value at the observation height, and z0 is the surface momentum roughness value.

[0035] In a preferred embodiment, in step S34, the flow resistance coefficient r is... a Substituting into the heat flux H formula:

[0036]

[0037] Substitute the heat flux value H into steps S42 and S43, and repeat the calculation of atmospheric stability and update the flow resistance coefficient r. a The iteration continues until the difference between two consecutive calculated values ​​of the heat flux value H is less than a set threshold, at which point the iteration is complete.

[0038] In a preferred embodiment, in step S4, an entropy balance equation is constructed:

[0039] ΔW=P+I-CT-RD

[0040] Where ΔW is the change in soil entropy, P is the precipitation, I is the irrigation amount, CT is the actual water vapor evaporation, R is the surface water runoff, and D is the deep soil infiltration.

[0041] The deep soil permeability D is calculated using the following formula:

[0042]

[0043] Where H is the heat flux value, Δh is the soil water potential difference, and L0 is the soil layer thickness.

[0044] In a preferred embodiment, in step S5, the change in soil entropy ΔW calculated according to the entropy balance equation is combined with the soil entropy W at the current time t. t Predict the soil entropy W at future time t+1. t+1 :

[0045]

[0046] Where v is the soil layer type coefficient, θ b Soil bulk density;

[0047] By comparing the predicted soil entropy value with the entropy threshold, soil moisture levels are classified.

[0048] The present invention also proposes a remote soil moisture monitoring system based on big data to realize the above-mentioned remote soil moisture monitoring method based on big data, including: a data acquisition layer, a data processing layer, a data analysis and prediction layer and a user interaction layer;

[0049] The data acquisition layer is used to identify crop phenological stages using multi-temporal remote sensing images, collect meteorological data, and measure soil parameters.

[0050] The data processing layer calculates the reference water vapor evaporation of crops based on meteorological data and soil parameters, calculates the actual water vapor evaporation of crops based on phenological stages, and calculates the soil heat flux based on atmospheric stability and flow resistance coefficient.

[0051] The data analysis and prediction layer is used to construct an entropy balance equation based on soil heat flux, calculate the change in soil entropy, predict soil entropy based on the change in soil entropy, and classify soil moisture levels.

[0052] Compared with the prior art, the present invention has the following beneficial technical effects:

[0053] Accurately monitor crop growth dynamics by identifying crop phenological stages (such as seedling, heading, and maturity stages) through remote sensing imagery to grasp the crop growth status in real time; integrate multi-source data by combining meteorological (temperature, humidity, precipitation, wind speed, etc.) and soil parameters (moisture content, texture, etc.) to construct a crop-environment coupled dataset; quantify crop water requirements by accurately calculating actual crop water vapor evaporation based on meteorological data and phenological stages to guide irrigation decisions; and dynamically adapt to climate change by adjusting water vapor evaporation based on real-time meteorological data to cope with short-term weather fluctuations.

[0054] The soil heat flux is quantified by the energy balance model, reflecting the rate of soil moisture loss to the atmosphere and the energy exchange relationship between soil moisture and the atmosphere; the soil moisture stability is quantified to realize dynamic monitoring and prediction of soil moisture throughout the crop growth cycle, and to guide agricultural activities such as precision irrigation and fertilization. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a schematic diagram of the process of the remote soil moisture monitoring method based on big data according to the present invention;

[0057] Figure 2 This is a schematic diagram of the soil moisture prediction process of the present invention;

[0058] Figure 3 This is a schematic diagram of the structure of the big data-based remote soil moisture monitoring system of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0060] In the accompanying drawings of specific embodiments of the present invention, in order to better and more clearly describe the working principle of each component in the system and show the connection relationship of each part in the device, only the relative positional relationship between each component is clearly distinguished. It does not constitute a limitation on the signal transmission direction, connection sequence, or size, dimension, and shape of each part within the component or structure.

[0061] Example 1

[0062] like Figures 1-2 As shown, the remote soil moisture monitoring method based on big data of the present invention includes the following steps:

[0063] S1. Use multi-temporal remote sensing images to identify crop phenological stages, collect meteorological data, and measure soil parameters.

[0064] Vegetation indices were extracted using multi-temporal remote sensing images, which were acquired from Landsat and Sentinel optical satellite imagery series. The extracted vegetation indices included NDVI and EVI.

[0065] By combining supervised classification (such as support vector machine SVM) or time series analysis algorithms (such as dynamic time warping DTW), crop phenological stages (such as sowing period, growth period, and maturity period) can be identified.

[0066] Data such as precipitation, temperature, wind speed, sunshine duration, and air humidity are collected through ground-based meteorological stations and meteorological satellite remote sensing. Soil moisture content, soil temperature, and soil porosity parameters are obtained in real time using sensors (such as TDR and FDR sensors) at soil moisture monitoring stations.

[0067] Regarding the deployment method of soil moisture sensors, soil moisture sensors are buried in layers (such as 0-10cm, 10-30cm, 30-50cm). The soil moisture sensors in each layer are arranged in a grid. The grid density needs to be set according to the land area and soil heterogeneity. The preferred grid density for uniform plots is 100m×100m, and the grid density for large-area monitoring is 500m×500m.

[0068] Prioritize high-precision (error ≤ 2% volumetric moisture content) and low-power (such as TDR, FDR, and capacitive sensors). In areas with abrupt changes in soil type, undulating terrain, or differences in crop planting, soil moisture sensors need to be deployed more densely. In areas prone to moisture anomalies, such as drainage ditches and the edges of irrigation areas, additional sensors are needed.

[0069] S2. Calculate the reference water vapor evaporation of crops based on meteorological data and soil parameters, and calculate the actual water vapor evaporation of crops based on phenological stages.

[0070] S21. Based on meteorological data and soil parameters, calculate the reference water vapor evaporation CT0 for crops:

[0071]

[0072] Where F is the slope of the saturated water vapor pressure-temperature curve, and R... n For net radiation, G is soil moisture flux, γ is a constant, U is wind speed at the preset height, E is water vapor pressure difference between the preset height and the ground surface, and T represents the 24-hour average temperature.

[0073] Calculate the net radiation R by combining surface albedo and solar radiation data. n :

[0074]

[0075] Where α is the albedo, R solarWhere ε is solar radiation, σ is the surface emissivity, and T is a constant. S This refers to the Earth's surface temperature.

[0076] S22, Combined with the crop coefficient K corresponding to the phenological stage c Calculate the actual water vapor evaporation rate CT:

[0077] CT=K c ×CT0

[0078] S3. Calculate the soil heat flux based on atmospheric stability and flow resistance coefficient.

[0079] Typical wet areas (areas with sufficient moisture, such as water bodies and areas with high vegetation cover) and dry areas (areas with scarce moisture, such as bare soil and arid areas) are selected from the imagery to set boundary conditions for the energy balance equation. Wet areas are assumed to be close to the potential water vapor evaporation (i.e., the maximum water vapor evaporation when moisture is sufficient), and dry areas are assumed to have surface flux close to zero. This constrains subsequent parameters based on atmospheric stability and flow resistance coefficients to ensure their rationality under different moisture conditions.

[0080] Based on the energy balance relationship between dry and wet zones, and considering wind speed and atmospheric stratification stability, the flow resistance coefficient r can be calculated. a r a The resistance to water vapor and heat transfer is a key parameter for calculating the heat flux H.

[0081] The specific steps are as follows:

[0082] S31, Initial parameter setting for heat flux value H.

[0083] Make an initial assumption about the heat flux value H, setting H=0 or giving an initial value based on experience.

[0084] S32. Based on the initial value of the heat flux H, calculate the friction speed and characteristic temperature to obtain the atmospheric stability.

[0085] Calculate the friction velocity u based on the initial value of the heat flux H. * and characteristic temperature θ * :

[0086]

[0087] Where ρ is the air density, C p The specific heat capacity of air at constant pressure. This is the value of the atmospheric momentum change function (which needs to be looked up in a table or calculated based on atmospheric stability).

[0088] Here, the friction speed u * Characteristic velocities that characterize the intensity of near-surface atmospheric turbulence, reflecting the frictional effect of the surface on airflow; characteristic temperature θ. *The temperature associated with sensible heat flux is used to quantify atmospheric heat transfer processes and reflect the intensity of turbulent heat transport.

[0089] Calculate atmospheric stability L:

[0090]

[0091] Among them, T a Let L be the ambient atmospheric temperature, k be a proportionality constant, and g be the gravitational acceleration. Atmospheric stability L is used to determine atmospheric conditions, such as stable, neutral, or unstable.

[0092] S33. Based on atmospheric stability and standard atmospheric stability, determine the stability correction term and calculate the flow resistance coefficient r. a ;

[0093] Determine the stability correction term based on atmospheric stability L and atmospheric standard stability L′.

[0094]

[0095] Calculate the flow resistance coefficient r a :

[0096]

[0097] Where z is the momentum roughness value at the observation height, and z0 is the surface momentum roughness value.

[0098] S34. Based on the flow resistance coefficient, iteratively solve for the heat flux H.

[0099] The flow resistance coefficient r a Substituting into the heat flux H formula:

[0100]

[0101] Substitute the new H into steps S42 and S43, and repeat the calculation of atmospheric stability and update the flow drag coefficient r. a The iteration continues until the difference between two consecutive calculated values ​​of the heat flux value H is less than a set threshold, at which point the iteration is complete.

[0102] S4. Construct an entropy balance equation based on soil heat flux and actual water vapor evaporation, and calculate the change in soil entropy.

[0103] The CT calculation results from step S2 and the H calculation results from step S3 are combined with the heat flux value H, irrigation amount I, actual water vapor evaporation CT, surface water runoff R, and deep soil infiltration D, and substituted into the entropy balance equation to comprehensively analyze the changes in soil entropy in the region.

[0104] Construct the entropy balance equation:

[0105] ΔW=P+I-CT-RD

[0106] Where ΔW is the change in soil entropy, P is the precipitation, I is the irrigation amount, CT is the actual water vapor evaporation, R is the surface water runoff, and D is the deep soil infiltration.

[0107] The deep soil infiltration rate D is calculated using the following formula:

[0108]

[0109] Where H is the heat flux value H, Δh is the soil water potential difference, and L0 is the soil layer thickness (mm).

[0110] S5. Predict soil entropy values ​​based on changes in soil entropy values ​​and classify soil moisture levels.

[0111] Soil entropy prediction: Based on the change in soil entropy ΔW calculated according to the entropy balance equation, combined with the soil entropy W at the current time t. t Predict the soil entropy W at future time t+1. t+1 :

[0112]

[0113] Where v is the soil layer type coefficient, θ b This refers to the bulk density of the soil.

[0114] By comparing the predicted soil entropy value with the entropy threshold, soil moisture levels are classified (such as drought, suitable, and excessively wet), and a moisture prediction report is generated to provide a basis for decision-making in agricultural irrigation scheduling and drought relief.

[0115] Table 1 Soil Moisture Level

[0116]

[0117] Decision support applications

[0118] Drought warning: When W t+1 Irrigation is initiated when the value falls below the first entropy threshold.

[0119] Drainage recommendations: When W t+1 When the second entropy threshold is reached, drainage is recommended.

[0120] Irrigation scheduling: Determine the irrigation amount and timing based on the forecast results.

[0121] Example 2

[0122] Using technologies such as drones and satellite remote sensing, we can obtain geographic information data of the soil, including topography, landforms, and soil types. Combined with the classified soil moisture levels, we can obtain the spatiotemporal distribution information of the soil moisture levels.

[0123] A three-dimensional topographic model of the soil is constructed based on the geographic information data of the soil.

[0124] Based on the three-dimensional terrain model, soil type, soil texture and other attribute information are added to form a multi-dimensional digital twin model of soil.

[0125] Geographic Information System (GIS) technology is used to perform spatial analysis and visualization of the model, enabling an intuitive presentation of the soil.

[0126] The mapping of soil moisture levels involves integrating soil moisture levels with a three-dimensional digital twin model and mapping the soil moisture levels to the corresponding locations in the model using methods such as spatial interpolation.

[0127] A dynamic update mechanism is adopted to update the soil moisture information in the model according to the changes in soil moisture level, so as to realize the dynamic visualization of soil moisture.

[0128] Example 3

[0129] like Figure 3 The diagram shown is a structural schematic of the remote soil moisture monitoring system of the present invention, which includes: a data acquisition layer, a data processing layer, a data analysis and prediction layer, and a user interaction layer.

[0130] I. Data Acquisition Layer

[0131] The data acquisition layer is used to identify crop phenological stages using multi-temporal remote sensing images, collect meteorological data, and measure soil parameters. It includes: a remote sensing image acquisition module, a meteorological data acquisition module, and a soil parameter measurement module.

[0132] Remote sensing image acquisition module: Utilizing remote sensing equipment mounted on satellites or drones, this module acquires multi-temporal remote sensing images to identify crop phenological stages. It uses satellite remote sensing (such as the Landsat and Sentinel series) or drone remote sensing equipment to acquire multi-temporal remote sensing images of the study area, which are then used to extract vegetation information and surface features, supporting the identification and analysis of crop phenological stages.

[0133] Meteorological data acquisition module: This module collects meteorological data, including precipitation, temperature, wind speed, and sunshine duration, through various sensors at the meteorological station, such as rain gauges, thermometers, and anemometers. By deploying meteorological sensors (such as rain gauges, temperature sensors, anemometers, and humidity sensors), it collects real-time meteorological data on precipitation, temperature, wind speed, air humidity, and sunshine duration, providing basic meteorological elements for subsequent calculations of water vapor evaporation and water balance analysis.

[0134] Soil parameter measurement module: This module uses equipment such as soil moisture sensors, soil temperature sensors, and soil texture analyzers to measure soil parameters such as moisture content, temperature, and texture. Utilizing soil sensors (such as TDR soil moisture sensors and soil temperature sensors) and laboratory testing methods, it measures parameters such as soil moisture content, soil temperature, soil texture, and soil porosity to reflect soil physical properties and provide basic soil data for calculating water vapor evaporation and water balance analysis.

[0135] II. Data Processing Layer

[0136] The data processing layer calculates the reference water vapor evaporation rate of crops based on meteorological data and soil parameters, calculates the actual water vapor evaporation rate of crops based on phenological stages, and calculates the soil heat flux based on atmospheric stability and flow resistance coefficients. The data processing layer includes: a phenological stage identification unit, a water vapor evaporation rate calculation unit, an energy balance calculation unit, and a water balance calculation unit.

[0137] Phenological Stage Identification Unit: This unit processes and analyzes remote sensing images, combines them with a phenological feature database, identifies the phenological stage of crops, and encodes it. It performs radiometric correction and vegetation index calculations (such as NDVI) on remote sensing images, combines them with a phenological feature database to identify the phenological stage of crops (such as sowing period, growing period, maturity period), and encodes it, providing a basis for determining the crop coefficient in water vapor evaporation calculations.

[0138] Evaporation Calculation Unit: Based on meteorological data and soil parameters, the reference evaporation of crops is calculated using models such as Penman-Monteith; then, combined with the crop coefficient corresponding to the phenological stage, the actual evaporation is calculated. Inputting meteorological data, soil parameters, and phenological stage discrimination results, the unit uses models such as Penman-Monteith and remote sensing evaporation models (e.g., SEBAL) to calculate crop evaporation (CT), quantifying the regional water evaporation and plant transpiration processes.

[0139] Energy balance calculation unit: Calculates soil heat flux based on atmospheric stability and flow resistance coefficient, combined with relevant parameters.

[0140] Water balance calculation unit: Based on data such as soil heat flux, an entropy balance equation is constructed to calculate the change in soil entropy. Integrating meteorological data (precipitation), soil parameters, and CT calculation results, the data are substituted into the entropy balance equation ΔW=P+I-CT-RD to calculate the change in soil moisture, analyze the water balance in the region, and clarify the surplus or deficit of soil moisture.

[0141] III. Data Analysis and Prediction Layer

[0142] The data analysis and prediction layer is used to construct an entropy balance equation based on soil heat flux, calculate the change in soil entropy, predict soil entropy based on the change in soil entropy, and classify soil moisture levels. The data analysis and prediction layer includes: a soil moisture prediction unit, a level classification unit, and an intelligent early warning unit.

[0143] Soil moisture prediction unit: Based on changes in soil entropy, combined with historical soil moisture data and time series analysis methods, it predicts future soil entropy values. Based on soil moisture changes calculated using water balance, and combined with initial soil moisture content, it predicts soil moisture for future periods. Simultaneously, it compares the predicted soil moisture content with suitable crop moisture thresholds to classify soil moisture levels (e.g., drought, suitable, excessively wet), ultimately outputting the soil moisture prediction results to provide data support for decisions regarding agricultural irrigation, drought resistance, and disaster reduction.

[0144] Grade classification unit: The predicted soil entropy value is compared with the suitable moisture threshold for crops to classify the soil moisture level, such as drought, suitable, and excessively wet.

[0145] Intelligent early warning unit: Set soil moisture warning thresholds (such as extreme drought and flood thresholds). When the prediction result triggers the threshold, it will automatically send warning information to users via SMS, APP push, email and other means to help users respond quickly to abnormal soil moisture.

[0146] Choosing an appropriate threshold to trigger soil moisture warnings involves considering crop type, soil texture, climate conditions, and historical data and experience.

[0147] The threshold should be selected based on crop type, as different crops have significantly different soil moisture requirements at different growth stages. For example, drought-tolerant crops (such as cacti and sesame) require relatively little water, and their drought warning threshold may be set lower, triggering a drought warning when the soil entropy percentage is around 10%-12%. Conversely, water-loving crops (such as rice and lotus) require more water, and a drought warning may be triggered when the soil entropy percentage is below 20%-25%. Furthermore, crops have shallow root systems during the seedling stage and are more sensitive to surface soil moisture; during vigorous growth, their water demand is high and their ability to utilize deeper soil moisture is enhanced, so the warning threshold also needs to be adjusted according to the characteristics of these growth stages.

[0148] Soil texture should be considered when selecting a threshold: Soil texture affects the soil's water retention and release capacity. Sandy soils have coarse particles and large pores, allowing water to easily infiltrate and escape, resulting in poor water retention. Therefore, the drought warning threshold is relatively low, possibly around 10%-15%. Clay soils, on the other hand, have fine particles and small pores, resulting in strong water retention but poor aeration. The drought warning threshold can be appropriately increased, for example, to 18%-22%. Loam soils have moderate water retention and aeration properties, with a threshold falling between the two. Furthermore, the degree of soil salinization also affects crop water absorption. In severely salinized soils, even with a high percentage of soil entropy, crops may still be affected by physiological drought, requiring adjustments to the warning threshold based on actual conditions.

[0149] Threshold selection should be based on climatic conditions: In arid regions or during the dry season, with scarce rainfall and high evaporation rates, soil moisture loss is rapid. The drought warning threshold should be appropriately lowered to facilitate timely detection of soil water shortages and allow for proactive irrigation measures. In humid regions or during the rainy season, with frequent rainfall and typically high soil moisture content, the flood warning threshold needs to be raised. A flood warning should be triggered when the soil entropy percentage reaches a certain level (e.g., exceeding 80%-90% of field capacity), prompting preparations for drainage. Furthermore, meteorological factors such as temperature, wind speed, and air humidity also affect soil moisture evaporation, thus influencing threshold settings. For example, under conditions of high temperature, strong winds, and low humidity, soil moisture evaporation is rapid, and the drought warning threshold can be appropriately lowered.

[0150] Thresholds are selected based on historical data and experience: Long-term soil moisture monitoring data for the region is analyzed to understand the patterns of soil moisture variation, including the range of moisture fluctuations in different seasons and years. Based on this, reasonable early warning thresholds are set. Simultaneously, the long-accumulated planting experience of local farmers is considered. They have an intuitive understanding of the relationship between soil moisture and crop growth, such as judging soil moisture status by observing crop growth characteristics (e.g., leaf curling, color changes). This experience can help determine the early warning thresholds.

[0151] IV. User Interaction Layer:

[0152] Data display module: Displays real-time, historical, and forecast data of soil moisture in intuitive formats such as charts and maps for easy viewing by users.

[0153] Decision support module: Based on soil moisture levels and crop growth needs, it provides users with decision-making suggestions on irrigation scheduling, drought resistance and disaster reduction, etc.

[0154] Communication module: Supports remote data transmission and enables information interaction between users and the system, such as access and operation through mobile apps, web pages, etc.

[0155] Table 2. Correspondence between soil moisture monitoring data accuracy and early warning threshold

[0156]

[0157] In a preferred embodiment, the soil moisture remote monitoring system further includes a historical data backtracking and analysis layer, which stores historical moisture data, prediction results and related meteorological and soil data, supports querying historical records by time and region, and provides data comparison analysis (same-year comparison, month-on-month comparison) and trend fitting (such as moisture change curve prediction) functions to help users discover long-term moisture patterns.

[0158] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0159] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0160] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0161] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. The databases involved in the embodiments provided in this application can include at least one of relational and non-relational databases. Non-relational databases can include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0162] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0163] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for remote monitoring of soil moisture based on big data, characterized in that, Includes the following steps: S1. Use multi-temporal remote sensing images to identify crop phenological stages, while simultaneously collecting meteorological data and measuring soil parameters; S2. Calculate the reference water vapor evaporation of crops based on meteorological data and soil parameters, and calculate the actual water vapor evaporation of crops based on phenological stages; S3. Calculate the soil heat flux based on atmospheric stability and flow resistance coefficient; S4. Construct an entropy balance equation based on soil heat flux and actual water vapor evaporation, and calculate the change in soil entropy. S5. Predict soil entropy values ​​based on changes in soil entropy values ​​and classify soil moisture levels.

2. The method for remote monitoring of soil moisture based on big data according to claim 1, characterized in that, In step S2, the reference water vapor evaporation CT0 of the crop is calculated based on meteorological data and soil parameters. Where F is the slope of the saturated water vapor pressure-temperature curve, and R... n For net radiation, G is soil moisture flux, γ is a constant, U is wind speed at the preset height, E is water vapor pressure difference between the preset height and the ground surface, and T represents the 24-hour average temperature. Combined with the crop coefficient K corresponding to the phenological stage c Calculate the actual water vapor evaporation rate CT: CT=K c ×CT0。 3. The method for remote monitoring of soil moisture based on big data according to claim 1, characterized in that, Step S3 includes the following steps: S31. Set the initial parameters for heat flux; S32. Based on the initial value of the heat flux, calculate the friction velocity and characteristic temperature to obtain the atmospheric stability; S33. Based on atmospheric stability, determine the stability correction term and calculate the flow resistance coefficient; S34. Based on the flow resistance coefficient, iteratively solve for the heat flux.

4. The method for remote monitoring of soil moisture based on big data according to claim 3, characterized in that, In step S32, the friction speed u is calculated. * and characteristic temperature θ * : Where H is the heat flux, ρ is the air density, and C is the air density. p φ is the specific heat capacity of air at constant pressure. m The value is a function of atmospheric momentum change, and the flow drag coefficient is r. a .

5. The method for remote monitoring of soil moisture based on big data according to claim 4, characterized in that, Calculate atmospheric stability L: Among them, T a Let be the ambient atmospheric temperature, k be a proportionality constant, and g be the gravitational acceleration.

6. The method for remote monitoring of soil moisture based on big data according to claim 5, characterized in that, In step S33, a stability correction term is determined based on atmospheric stability L and atmospheric standard stability L′. Calculate the flow resistance coefficient r a : Where z is the momentum roughness value at the observation height, and z0 is the surface momentum roughness value.

7. The method for remote monitoring of soil moisture based on big data according to claim 6, characterized in that, In step S34, the flow resistance coefficient r a Substituting into the heat flux H formula: Substitute the heat flux value H into steps S42 and S43, and repeat the calculation of atmospheric stability and update the flow resistance coefficient r. a The iteration continues until the difference between two consecutive calculated values ​​of the heat flux value H is less than a set threshold, at which point the iteration is complete.

8. The method for remote monitoring of soil moisture based on big data according to claim 7, characterized in that, In step S4, the entropy balance equation is constructed: ΔW=P+I-CT-RD Where ΔW is the change in soil entropy, P is the precipitation, I is the irrigation amount, CT is the actual water vapor evaporation, R is the surface water runoff, and D is the deep soil infiltration. The deep soil permeability D is calculated using the following formula: Where H is the heat flux value, Δh is the soil water potential difference, and L0 is the soil layer thickness.

9. The method for remote monitoring of soil moisture based on big data according to claim 8, characterized in that, In step S5, the change in soil entropy ΔW calculated based on the entropy balance equation is combined with the soil entropy W at the current time t. t Predict the soil entropy W at future time t+1. t+1 : Where v is the soil layer type coefficient, θ b Soil bulk density; By comparing the predicted soil entropy value with the entropy threshold, soil moisture levels are classified.

10. A remote soil moisture monitoring system based on big data, used to implement the remote soil moisture monitoring method based on big data as described in any one of claims 1-9, characterized in that, include: Data acquisition layer, data processing layer, data analysis and prediction layer, and user interaction layer; The data acquisition layer is used to identify crop phenological stages using multi-temporal remote sensing images, collect meteorological data, and measure soil parameters. The data processing layer calculates the reference water vapor evaporation of crops based on meteorological data and soil parameters, calculates the actual water vapor evaporation of crops based on phenological stages, and calculates the soil heat flux based on atmospheric stability and flow resistance coefficient. The data analysis and prediction layer is used to construct an entropy balance equation based on soil heat flux, calculate the change in soil entropy, predict soil entropy based on the change in soil entropy, and classify soil moisture levels.

Images