Garden soil humidity monitoring method and system

Abstract

The invention provides a garden soil humidity monitoring method and system. The method comprises the following steps: determining water potential permeation confidence among soil layers according to soil humidity data in a garden monitoring area and historical soil humidity data of the garden monitoring area; obtaining an interlayer moisture abnormity mark of the garden monitoring area; determining discrete features of soil humidity in the garden monitoring area based on the soil humidity data and a preset humidity value of the garden monitoring area, and determining a fluctuation trend of soil moisture in the garden monitoring area in a preset time period according to the discrete features and all the water potential permeation confidence pairs; and performing early warning analysis on the soil humidity of the garden monitoring area through the fluctuation trend and the interlayer moisture anomaly mark to obtain early warning information of the soil humidity in the garden monitoring area. By adopting the scheme of the invention, the influence of the dynamic process cutting of the soil moisture on the monitoring of the soil humidity in the garden can be reduced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of humidity monitoring, in particular to a garden soil humidity monitoring method and system. BACKGROUND

[0002] Humidity monitoring refers to a technical system that, through physical sensors, data acquisition equipment and analysis models, collects, processes and interprets the soil moisture content (such as volumetric water content, mass water content) in the monitoring area in real time or periodically, and finally provides quantitative basis for plant water management and risk warning.

[0003] With the development of precision agriculture and smart garden technology, soil humidity monitoring has become a key link in regulating plant growth and optimizing water resource utilization. However, the existing monitoring technology still has significant limitations in complex garden ecological scenarios, and it is difficult to meet the needs of fine management. For example, the dynamic process of soil moisture is fragmented. The infiltration flow of soil moisture in the unsaturated zone (such as interlayer recharge and capillary rise) is a key process affecting humidity changes. However, traditional methods often ignore the hydraulic connection between soil layers and only use a single threshold to determine the wet and dry states, making it difficult to identify abnormal phenomena such as "upper layer drought but lower layer water retention". For example, when the 0-30cm soil layer is quickly dried due to evaporation, if the 30-60cm soil layer has a slow infiltration problem, the traditional warning will misjudge as overall water shortage, leading to ineffective irrigation. Therefore, how to reduce the impact of the dynamic process of soil moisture on the monitoring of soil humidity in the garden has become a problem in the industry. SUMMARY

[0004] The application provides a garden soil humidity monitoring method and system, which can reduce the impact of the dynamic process of soil moisture on the monitoring of soil humidity in the garden.

[0005] In a first aspect, the application provides a garden soil humidity monitoring method, comprising the following steps: A garden soil humidity monitoring method, wherein a plurality of soil humidity sensors are pre-arranged in each soil layer of a garden monitoring area, characterized in that it comprises the following steps: Collecting and preprocessing the soil humidity of each soil layer in the garden monitoring area to obtain soil humidity data in the garden monitoring area; According to the soil humidity data and the historical soil humidity data of the garden monitoring area, the water potential of each soil layer in the garden monitoring area within a preset time period is analyzed by infiltration to obtain the water potential infiltration confidence between each soil layer; The abnormal state of interlayer water flow between each soil layer is judged by the water potential infiltration confidence between each soil layer, and then the interlayer water anomaly label of the garden monitoring area is obtained; determine discrete features of soil moisture in the garden monitoring area based on the soil moisture data and preset moisture values of the garden monitoring area, and perform fluctuation prediction on soil moisture trends of the garden monitoring area according to the discrete features and water potential permeation confidence between all soil layers, to obtain fluctuation trends of soil moisture in the garden monitoring area within a preset time period; perform early warning analysis on soil moisture of the garden monitoring area based on the fluctuation trends and the interlayer water anomaly marker of the garden monitoring area, to obtain early warning information of soil moisture in the garden monitoring area.

[0006] In some embodiments, the water potential permeation analysis on each soil layer of the garden monitoring area within a preset time period according to the soil moisture data and historical soil moisture data of the garden monitoring area includes: obtain historical soil moisture data of the garden monitoring area; determine current permeation features between each soil layer according to the soil moisture data; obtain a preset time period of the garden monitoring area; determine historical permeation features between each soil layer within the preset time period according to the historical soil moisture data; determine water potential permeation confidence between each soil layer according to the current permeation features of each soil layer and the historical permeation features of each soil layer within the preset time period.

[0007] In some embodiments, the abnormal state of interlayer water flow between each soil layer is determined based on the water potential permeation confidence between each soil layer, and the interlayer water anomaly marker of the garden monitoring area is obtained, which specifically includes: construct a threshold range of normal water flow between each adjacent soil layer based on historical interlayer water flow data of the garden monitoring area and soil physicochemical properties; obtain water potential permeation rules between each soil layer; determine water transport features between corresponding soil layers according to the water potential permeation rules between each soil layer and the water potential permeation confidence between each soil layer; compare interlayer water flow between each soil layer according to the threshold range and the water transport features between each soil layer, and mark each interlayer with an abnormal state, to form the interlayer water anomaly marker of the garden monitoring area.

[0008] In some embodiments, the determination of discrete features of soil moisture in the garden monitoring area based on the soil moisture data and preset moisture values of the garden monitoring area specifically includes: obtain preset moisture values and a moisture threshold range of the garden monitoring area; determine a humidity deviation feature of the garden monitoring area according to the soil humidity data and the preset humidity value; determine a humidity proportion feature of the soil humidity data in the humidity threshold range; determine a dispersion feature of the soil humidity in the garden monitoring area according to the humidity deviation feature and the humidity proportion feature.

[0009] In some embodiments, a fluctuation prediction of the soil humidity trend of the garden monitoring area is performed according to the dispersion feature and all water potential penetration confidences, and a fluctuation trend of the soil moisture in the garden monitoring area within a preset time period specifically includes: predict a humidity prediction value data and a fluctuation interval of the soil humidity of the garden monitoring area within a preset time period according to the dispersion feature and all water potential penetration confidences; generate a humidity trend graph of the soil humidity of the garden monitoring area within a preset time period through the humidity prediction value data and the fluctuation interval; extract a fluctuation trend of the soil moisture in the garden monitoring area within a preset time period from the humidity trend graph.

[0010] In some embodiments, a pre-warning analysis of the soil humidity of the garden monitoring area is performed through the fluctuation trend and the interlayer water anomaly mark, and the pre-warning information of the soil humidity in the garden monitoring area specifically includes: associate the fluctuation trend and the interlayer water anomaly mark to calculate a risk pre-warning index of the soil humidity of each soil layer in the garden monitoring area; perform a pre-warning of the soil humidity in the garden monitoring area according to all risk pre-warning indexes to generate soil layer pre-warning information of each soil layer; generate the pre-warning information of the soil humidity in the garden monitoring area through all soil layer pre-warning information.

[0011] In some embodiments, each soil layer in the garden monitoring area is divided into a surface tillage layer, a root active layer, a soil water retention layer, and a deep stable layer.

[0012] In some embodiments, before sensor deployment, a comprehensive survey of the garden monitoring area is performed to determine the soil profile structure, the depth and distribution range of each soil layer, and the number and distribution density of monitoring points in combination with the area, soil heterogeneity factors.

[0013] In some embodiments, the preprocessing includes noise interference elimination, data missing processing, and error processing.

[0014] In a second aspect, the present application provides a garden soil humidity monitoring system, which includes: The collection module is configured to collect soil moisture of each soil layer in the garden monitoring area and perform preprocessing to obtain soil moisture data of the garden monitoring area; The processing module is configured to perform infiltration analysis on water potential of each soil layer in the garden monitoring area within a preset time period according to the soil moisture data and historical soil moisture data of the garden monitoring area, to obtain water potential infiltration confidence between each soil layer. The processing module is further configured to determine an abnormal state of interlayer water flow between each soil layer according to the water potential infiltration confidence between each soil layer, to further obtain an interlayer water anomaly mark of the garden monitoring area. The processing module is further configured to determine a discrete feature of soil moisture in the garden monitoring area based on the soil moisture data and a preset humidity value of the garden monitoring area, to perform fluctuation prediction on a soil moisture trend of the garden monitoring area according to the discrete feature and all water potential infiltration confidences, to obtain a fluctuation trend of soil moisture in the garden monitoring area within a preset time period. The execution module is configured to perform early warning analysis on the soil moisture of the garden monitoring area according to the fluctuation trend and the interlayer water anomaly mark, to obtain early warning information of the soil moisture in the garden monitoring area.

[0015] The technical scheme provided by the embodiments disclosed in the present application has the following beneficial effects: In the garden soil moisture monitoring method and system provided by the present application, first, the soil moisture of each soil layer in the garden monitoring area is collected and preprocessed to obtain soil moisture data of the garden monitoring area; then, infiltration analysis is performed on water potential of each soil layer in the garden monitoring area within a preset time period according to the soil moisture data and historical soil moisture data of the garden monitoring area, to obtain water potential infiltration confidence between each soil layer; then, an abnormal state of interlayer water flow between each soil layer is determined according to the water potential infiltration confidence between each soil layer, to further obtain an interlayer water anomaly mark of the garden monitoring area; then, a discrete feature of soil moisture in the garden monitoring area is determined based on the soil moisture data and a preset humidity value of the garden monitoring area, and a fluctuation prediction is performed on a soil moisture trend of the garden monitoring area according to the discrete feature and all water potential infiltration confidences, to obtain a fluctuation trend of soil moisture in the garden monitoring area within a preset time period; finally, early warning analysis is performed on the soil moisture of the garden monitoring area according to the fluctuation trend and the interlayer water anomaly mark, to obtain early warning information of the soil moisture in the garden monitoring area.

[0016] It can be seen that, in the process of monitoring the garden soil humidity, first, the humidity of each soil layer is collected and pretreated, and abnormal data can be eliminated, environmental interference can be corrected, and the dynamic analysis fault caused by the fragmentation of the basic data in traditional monitoring can be avoided, thereby providing a coherent and reliable humidity data basis for the subsequent link and reducing data fragmentation from the source. The confidence is obtained by combining the historical humidity data to analyze the water potential penetration, breaking the limitation of the fragmentation of real-time data and historical rules, and through the correlation of the penetration characteristics of the same historical scene, the current interlayer water dynamic is supported by historical basis, and the dynamic misjudgment caused by relying only on real-time data is avoided. The confidence is used to judge the interlayer anomaly and mark, solve the dynamic fragmentation problem between soil layers, no longer generally perceive the overall dry and wet, but accurately locate the abnormal soil layer combination and type, clearly present the dynamic anomaly of the water interaction of each soil layer, and make the interlayer water flow process traceable. The trend is predicted by combining the preset humidity to obtain the discrete characteristics and the confidence, breaking the fragmentation of the static threshold and the dynamic trend, reflecting the spatial and temporal humidity difference through the discrete characteristics, combining the confidence to correct the prediction reliability, making the trend prediction can reflect the dynamic change of the water in each soil layer, and avoiding isolated prediction; finally, the trend and the abnormal mark are combined to warn, integrate the local dynamic anomaly and the overall trend, break the fragmentation of the early warning and the overall dynamic fragmentation, generate coherent early warning information covering the global region, and change the monitoring from isolated analysis of each link to dynamic and coherent overall control, effectively reducing the influence of the dynamic process fragmentation of soil water on the monitoring of the soil humidity in the park. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a garden soil humidity monitoring method according to some embodiments of the present application; Figure 2 is a partial sectional view of each soil layer in a garden monitoring area according to some embodiments of the present application; Figure 3 is an exemplary flowchart of determining an interlayer water anomaly mark according to some embodiments of the present application; Figure 4 is a structural schematic diagram of a garden soil humidity monitoring system according to some embodiments of the present application; Figure 5 is a structural schematic diagram of a computer device for implementing a garden soil humidity monitoring method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings in the specification and specific embodiments.

[0019] Reference Figure 1The figure is an exemplary flowchart of a method for monitoring soil moisture in gardens according to some embodiments of this application. The method for monitoring soil moisture in gardens mainly includes the following steps: In some embodiments, the pre-deployment of multiple soil moisture sensors in various soil layers of the garden monitoring area can be achieved through the following steps: Before deploying the sensors, a comprehensive survey of the garden monitoring area is conducted to clarify the soil profile structure, depth and distribution range of each soil layer, and the number and distribution density of monitoring points are determined based on factors such as area and soil heterogeneity; then, suitable soil moisture sensors are selected according to the survey results (the measurement accuracy and range must match the soil type of each soil layer), and the soil profile is excavated layer by layer at each monitoring point according to the preset monitoring soil layer depth. After cleaning the impurities in the profile, the sensor probe is vertically implanted into the corresponding soil layer, ensuring that the probe is in close contact with the surrounding soil and avoiding damage; next, the sensor cable is fixed, waterproof protection is applied, the soil is backfilled and gently compacted to restore the original state; finally, all sensors are powered on for testing, and after confirming that the data acquisition and transmission functions are normal, the sensor number, corresponding soil layer depth and specific deployment location are recorded to complete the deployment work.

[0020] In some embodiments, reference Figure 2 As shown, this figure is a partial cross-sectional view of various soil layers in the garden monitoring area in some embodiments of this application, such as... Figure 2 The soil layers in the garden monitoring area can be divided from the ground down into the topsoil layer, root active layer, soil water retention layer, and deep stable layer. The ground is the vegetation growth zone, and roots grow within the soil layers. The topsoil layer (0-30cm) is most significantly affected by rainfall, irrigation, and evaporation, with drastic humidity fluctuations, requiring monitoring of "short-term moisture changes." The root active layer (30-60cm) directly affects plant water absorption efficiency, requiring monitoring of "dynamic water supply capacity." The soil water retention layer (60-90cm) has slow moisture changes and serves as a "replenishment source" for the root active layer, requiring monitoring of "interlayer infiltration and reserves." The deep stable layer (below 90cm) has consistently stable humidity and can be used as a "benchmark layer" to determine whether there is abnormal water infiltration from the upper layers (e.g., whether there is deep leakage and waste).

[0021] In step 101, soil moisture in each soil layer of the garden monitoring area is collected and preprocessed to obtain soil moisture data in the garden monitoring area.

[0022] In a specific implementation, the soil humidity sensors arranged in each soil layer are started to collect real-time data according to a preset collection frequency (for example, once per hour). After the sensors convert the original signals of the soil humidity in each soil layer into electrical signals, the signals are sent to the data processing center through a wired or wireless transmission module. After receiving the data, the data processing center first filters the original data to eliminate abnormal values exceeding the sensor range and noise data caused by transmission interference. Then, according to the data loss condition, the data is supplemented by using the mean value interpolation of adjacent time periods or the data of other monitoring points in the same soil layer. Subsequently, the data is corrected by combining the sensor factory calibration parameters and the real-time environmental temperature to eliminate system errors. Finally, the data is integrated into structured soil humidity data according to the soil layer classification and time sorting, and the preprocessing process is completed.

[0023] It should be noted that the soil humidity in the soil humidity data in the present application represents the quantitative representation of the water content in the soil, which can be used to reflect the current water filling degree of the soil.

[0024] In step 102, the water potential penetration confidence between each soil layer is obtained by performing penetration analysis on the water potential of each soil layer in the preset time period according to the soil humidity data and the historical soil humidity data of the garden monitoring area.

[0025] In some embodiments, the water potential penetration confidence between each soil layer can be obtained by performing penetration analysis on the water potential of each soil layer in the preset time period according to the soil humidity data and the historical soil humidity data of the garden monitoring area, which can be achieved by the following steps: Obtain the historical soil humidity data of the garden monitoring area; Determine the current penetration characteristics between each soil layer according to the soil humidity data; Obtain the preset time period of the garden monitoring area; Determine the historical penetration characteristics between each soil layer in the preset time period according to the historical soil humidity data; Determine the water potential penetration confidence between each soil layer according to the current penetration characteristics of each soil layer and the historical penetration characteristics of each soil layer in the preset time period.

[0026] In the above steps, the historical soil humidity data of the garden monitoring area can be obtained from the database or historical archives of the garden monitoring system.

[0027] In a specific implementation, the current infiltration characteristics between the soil layers are determined according to the soil moisture data: the soil moisture data (such as the volumetric water content) of each soil layer collected and pre-processed is combined with the soil physical and chemical parameters (bulk density, porosity, clay content) of each soil layer, the soil moisture data is converted into the matric potential of each soil layer, which can be achieved by the Van Genuchten soil water characteristic curve model, and the water potential difference between adjacent soil layers is calculated; the water infiltration rate, the infiltration flux per unit time, and the infiltration direction (such as the upper layer infiltrating downward and the lower layer infiltrating upward) between the current adjacent soil layers are calculated by combining the soil layer thickness, the hydraulic conductivity (determined by the soil texture), and the soil moisture data of the soil layer, which can be calculated by using the Darcy's law, and these parameters are integrated to form the current infiltration characteristics between the soil layers, wherein the current infiltration characteristics represent the characteristics of the water infiltration state between the soil layers in the current monitoring period; in other embodiments, other ways can also be used to determine the current infiltration characteristics, which are not limited here.

[0028] The preset period of the garden monitoring area is obtained: according to the garden management needs (such as irrigation plan making, disease and pest control period) or ecological monitoring targets (such as water dynamic monitoring in the critical period of plant growth), the preset period is determined, for example, taking the garden management needs or the ecological monitoring targets as the core, combining the plant biological characteristics, the occurrence law of diseases and pests, the soil water retention capacity, and the historical meteorological data for comprehensive adaptation: if aiming at the irrigation plan making, the target plant water demand period needs to be based on, such as 10 days of irrigation for each tree bud period, 5 days of irrigation for each turf green-up period, combined with the soil texture adjustment, the sandy soil has poor water retention, so the preset period is shortened to 5-7 days, the clay soil has good water retention, so it is set to 10-12 days, and the historical irrigation interval and soil moisture change curve in the same period are referred to, to ensure that the period covers one complete water demand period and reserves 2-3 days of adjustment window; if focusing on disease and pest control, the duration of the high incidence period of diseases and pests needs to be taken as the benchmark, such as about 20 days of high incidence period of powdery mildew in summer and about 15 days of high incidence period of aphids, and a monitoring prediction period of 3-5 days in advance is superimposed to facilitate early detection, and the correlation between humidity and disease and pest occurrence is combined, such as high humidity easily inducing root rot, if the prediction period has more rainfall, the period is shortened to 10-13 days; if aiming at the water dynamic monitoring in the critical period of plant growth, such as the flowering period and the fruit enlargement period, the actual duration of the critical period needs to be strictly matched, such as 10 days of full bloom period of Chinese rose and 7 days of cherry blossom period, the starting point of the period is advanced by 2-3 days to capture the water accumulation before the critical period, and the end point is delayed by 1-2 days to track the water decline trend after the critical period, and the historical meteorological data in the same period of the critical period, such as the number of rainy days in the past 3 years, is combined, if extreme weather is predicted, the period is compressed to the critical period + 1 day, to ensure accurate capture of water dynamics, and in summary, the period length is usually set to 7-15 days, and the time node division in the period (such as per day) is also specified.

[0029] In addition, in specific implementation, the historical infiltration characteristics between the soil layers in the preset time period are determined according to the historical soil moisture data: historical data samples similar to the current preset time period and weather conditions are filtered from the historical soil moisture data, and the number of samples needs to be no less than three groups to ensure representativeness; then, the same method as that for calculating the current infiltration characteristics (for example, the Van Genuchten soil moisture characteristic curve model + Darcy's law) is used to calculate the daily infiltration rate, flux and direction between the soil layers in the preset time period in each historical sample, and the average infiltration rate and average flux between the soil layers in the preset time period are obtained by averaging the historical infiltration parameters between the soil layers in the same time period, and the historical infiltration characteristics between the soil layers in the preset time period are formed by all the above parameters, wherein the historical infiltration characteristics represent the characteristics of the water infiltration law between the soil layers in the same scenario in the preset time period; in other embodiments, the historical infiltration characteristics can also be determined in other ways, which are not limited here.

[0030] In addition, in specific implementation, the water potential infiltration confidence between the soil layers is determined according to the current infiltration characteristics of the soil layers and the historical infiltration characteristics of the soil layers in the preset time period: the deviation rate of the current infiltration characteristics and the historical infiltration characteristics between the soil layers is calculated first, which can be calculated by the formula "deviation rate = |current infiltration characteristics - historical infiltration characteristics| / historical infiltration characteristics x 100%"; a deviation rate threshold is set, which can be set by the standard deviation of the historical infiltration characteristics (the standard deviation reflects the stability of the historical data, and the smaller the standard deviation, the more reliable the historical characteristics) (for example, when the historical standard deviation is less than or equal to 5%, the deviation rate threshold is set to 10%; when the standard deviation is greater than 5%, the threshold is set to 15%); the deviation rate of the current infiltration characteristics and the historical infiltration characteristics is judged by the deviation rate threshold, so as to obtain the water potential infiltration confidence between the soil layers, for example, if the deviation rate of the current infiltration characteristics and the historical infiltration characteristics is less than or equal to the deviation rate threshold, and the number of historical samples is greater than or equal to 5, the water potential infiltration confidence is set to 0.8-1.0 (the smaller the deviation rate and the larger the sample size, the higher the confidence); if the deviation rate is greater than the threshold or the number of historical samples is less than 3, the confidence is adjusted according to the deviation degree and the sample size (for example, when the deviation rate is 15%-20% and the sample size is 3-4, the confidence is set to 0.6-0.7; when the deviation rate is greater than 20% or the sample size is less than 3, the confidence is set to 0.3-0.5), and finally the corresponding water potential infiltration confidence is given to each soil layer; in other embodiments, the water potential infiltration confidence can also be determined in other ways, which are not limited here.

[0031] It should be noted that the water potential infiltration confidence in the present application represents the parameter value of the degree of agreement between the current water infiltration law between the soil layers in the garden monitoring area and the historical infiltration law in the same scenario, and reflects the reliability of the soil water potential infiltration state analyzed based on the current soil moisture data and the historical data.

[0032] In step 103, the abnormal state of interlayer water flow between each soil layer is determined by the water potential penetration confidence between each soil layer, and then the interlayer water anomaly marker of the garden monitoring area is obtained.

[0033] In some embodiments, with reference to Figure 3 As shown in the figure, which is an exemplary flow chart for determining the interlayer water anomaly marker in some embodiments of the present application, the determination of the abnormal state of interlayer water flow between each soil layer by the water potential penetration confidence between each soil layer, and then the interlayer water anomaly marker of the garden monitoring area can be realized by the following steps: First, in step 1031, the threshold range of normal water flow between each adjacent soil layer is constructed based on the historical interlayer water flow data and soil physical and chemical properties of the garden monitoring area; Second, in step 1032, the water potential penetration law between each soil layer is obtained; Then, in step 1033, the water transport characteristics between the corresponding soil layers are determined according to the water potential penetration law between each soil layer and the water potential penetration confidence between each soil layer; Finally, in step 1034, the interlayer water flow between each soil layer is compared according to the threshold range and the water transport characteristics between each soil layer, and the abnormal interlayer between each soil layer is marked, and then the interlayer water anomaly marker of the garden monitoring area is formed.

[0034] In specific implementation, the threshold range of normal water flow between each adjacent soil layer is constructed based on the historical interlayer water flow data and soil physical and chemical properties of the garden monitoring area: first, the historical interlayer water flow data of the past 3-5 years are retrieved from the garden monitoring database, and the normal working condition data without soil compaction and irrigation abnormal interference factors are selected, and the soil physical and chemical property data (such as bulk density, porosity, clay content) of each soil layer in the area are collected; then, the historical water flow data (penetration rate, penetration flux) of each group are statistically analyzed, and the mean μ and standard deviation σ of each group of data are calculated; combined with the influence of soil physical and chemical properties on water flow (such as high clay content, low penetration rate, and appropriate reduction of the upper limit of the threshold), the normal penetration rate threshold range and the normal penetration flux threshold range of each adjacent soil layer are determined, which can be realized by the statistical method of "μ±2σ" (covering more than 95% of normal data), for example, the normal penetration rate threshold of 0-20cm and 20-40cm soil layer is set to 0.3-0.7cm / h, and the normal penetration flux threshold is set to 0.8-1.6L / (m²・h), forming the threshold range of normal water flow between each adjacent soil layer.

[0035] The water potential penetration law between the soil layers is obtained based on the current soil humidity data and the historical soil humidity data of each adjacent soil layer, the humidity data is converted into the matric potential of each soil layer, which can be converted by the van Genuchten soil water characteristic curve model, and the total water potential is calculated combined with the soil layer depth to obtain the water potential difference between adjacent soil layers; combined with the hydraulic conductivity of each soil layer (determined by soil texture), the penetration rate, penetration flux and penetration direction between adjacent soil layers at different time nodes (such as every hour in the current monitoring period) are calculated, which can be calculated by using Darcy's law; through the time series analysis of these data, the change trend of the water potential with time and the change relationship of the penetration rate, penetration flux with the water potential difference of each adjacent soil layer under the current environmental conditions (such as temperature, humidity) are summarized, for example, "the penetration rate is increased by 0.05 cm / h for every 0.1 MPa increase in water potential difference", to form the water potential penetration law between the soil layers, wherein the water potential penetration law represents the law of the penetration state of the water potential between the soil layers.

[0036] In addition, in specific implementation, the water migration characteristics between the corresponding soil layers are determined according to the water potential penetration law between the soil layers and the water potential penetration confidence between the soil layers: first, the key penetration parameters in the water potential penetration law of each adjacent soil layer are extracted, and then these parameters are corrected by the water potential penetration confidence between the soil layers (for example, if the confidence is high, such as 0.8 or more, the parameter correction amplitude is small, and the predicted value is taken as 95%-100%; if the confidence is low, such as 0.5 or less, the parameter correction amplitude is large, and the predicted value is taken as 70%-85% to reduce the influence of unreliable data); subsequently, the corrected penetration rate, penetration flux and penetration direction are integrated, and the stability index of water migration (such as the change rate of the penetration rate between two adjacent time nodes, and the change rate ≤10% is stable, and >10% is unstable) is calculated, and finally the water migration characteristics containing "penetration rate (corrected), penetration flux (corrected), penetration direction, stability" are formed, wherein the water migration characteristics represent the characteristics of the interlayer water flow state; in other embodiments, other ways can also be used to determine, which are not limited here.

[0037] In addition, in the implementation, the interlayer water flow between each soil layer is compared according to the threshold range and the water migration characteristics between each soil layer, and each layer with an abnormality is marked, and then an interlayer water abnormality mark of the garden monitoring area is formed: the water migration characteristics of each adjacent soil layer are compared with the corresponding normal water flow threshold range, if the penetration rate or the penetration flux in the water migration characteristics exceeds the threshold range (for example, the penetration rate is 0.2 cm / h < lower limit 0.3 cm / h, or 1.8 L / (m2·h) > upper limit 1.6 L / (m2·h)), or the penetration direction is abnormal (for example, in the dry season, the lower layer penetrates to the upper layer, but there is no underground water supply, or in the rainy season, the upper layer penetrates to the lower layer and suddenly stops), or the stability index is abnormal (for example, the penetration rate change rate is 15% > 10% and lasts for 2 monitoring periods), it is determined that the interlayer has a water flow abnormality; then the abnormal interlayer is marked in the format of “soil layer combination-abnormal type-abnormal degree”, the abnormal type is divided into “penetration too slow”, “penetration too fast”, “penetration direction abnormal” and “poor stability”, and the abnormal degree is divided into “mild”, “moderate” and “severe” according to the range of exceeding the threshold or the duration of the abnormality (for example, the penetration rate exceeding the threshold by 10%-20% is mild, 20%-30% is moderate, and > 30% is severe), for example, “0-20 cm and 20-40 cm soil layer-penetration too slow-moderate”; finally, all the abnormal marks are summarized to form the interlayer water abnormality mark of the garden monitoring area, which covers the position, type and degree of the abnormal interlayer; in other embodiments, other ways can also be used to determine the interlayer water abnormality mark, which is not limited here.

[0038] It should be noted that the interlayer water abnormality mark in the present application represents the structured identification of the interlayer with a water flow abnormality between each adjacent soil layer in the garden monitoring area, which can be used to locate the abnormal position, and to clarify the nature and severity of the abnormality of the garden monitoring area.

[0039] In step 104, the discrete characteristics of soil humidity in the garden monitoring area are determined based on the soil humidity data and the preset humidity value of the garden monitoring area, the soil humidity trend of the garden monitoring area is predicted based on the discrete characteristics and all the water potential penetration confidence, and the fluctuation trend of the soil water in the garden monitoring area within a preset period is obtained.

[0040] In some embodiments, the discrete characteristics of soil humidity in the garden monitoring area can be determined based on the soil humidity data and the preset humidity value of the garden monitoring area by the following steps: The preset humidity value and the humidity threshold range of the garden monitoring area are obtained; The humidity deviation characteristics of the garden monitoring area are determined according to the soil humidity data and the preset humidity value; determining a humidity proportion feature of the soil humidity data in the humidity threshold range; determining a dispersion feature of soil humidity in the garden monitoring area according to the humidity deviation feature and the humidity proportion feature.

[0041] In specific implementation, the preset humidity value and the humidity threshold range of the garden monitoring area are acquired: first, the preset humidity value of each soil layer is determined according to the growth water demand characteristics of the main plant types in the garden and the water retention capacity of the soil type, which can be determined by using the plant physiology determination method, the soil physics analysis method or the coupling modeling method, wherein the preset humidity value represents the humidity value of the soil layer in the garden monitoring area under the normal growth state of the plant; then, the humidity threshold range is divided according to the plant water stress critical value (such as the humidity lower than 12% in drought stress or higher than 28% in waterlogging stress), which is usually divided into the "suitable interval" (matching the normal growth demand of the plant), the "light warning interval" (paying attention to the change of water) and the "severe warning interval" (requiring emergency regulation), wherein the humidity threshold range represents the humidity range for judging whether the soil water in the garden monitoring area meets the growth demand of the garden plant and whether the soil water function is normal; in other embodiments, other ways can also be used to acquire, which is not limited here.

[0042] In addition, in specific implementation, the humidity deviation feature of the garden monitoring area is determined according to the soil humidity data and the preset humidity value: first, the soil humidity data is compared with the preset humidity value of the corresponding soil layer, and the absolute deviation and the relative deviation rate of each data point are calculated; then, the deviation data is counted according to the soil layer, and the deviation mean, the deviation standard deviation, the maximum deviation value and the corresponding position are calculated, the deviation mean can reflect the overall deviation level, the deviation standard deviation can reflect the dispersion degree of the deviation, the maximum deviation value and the corresponding position; finally, the deviation statistics of each soil layer are integrated to form the humidity deviation feature containing the soil layer number-deviation mean-deviation standard deviation-extreme deviation information, wherein the humidity deviation feature represents the feature that the humidity in the garden monitoring area deviates from the preset humidity; in other embodiments, other ways can also be used to determine, which is not limited here.

[0043] In addition, in a specific implementation, the proportion of the soil humidity data in the humidity threshold range is determined by first splitting the soil humidity data according to soil layers, and then counting the total sample quantity of each group of data; the sample quantity of each soil layer data falling within the "suitable interval", the "light warning interval", and the "heavy warning interval" of the humidity threshold range is counted; then the proportion of the humidity in each interval is calculated, for example, the proportion of the humidity = interval sample quantity / total sample quantity x 100%; meanwhile, the spatial and temporal distribution characteristics of the proportion of the humidity are analyzed, for example, the proportion of the suitable interval in the data collected at 9 o'clock in the morning is 82%, and the proportion of the suitable interval decreases to 68% at 5 o'clock in the afternoon; the proportion of the suitable interval in the east region is 85%, and the proportion of the suitable interval in the west region is only 65%; finally, the proportion of the humidity characteristic including the soil layer, the proportion of each interval, and the difference in the spatial and temporal distribution is formed; in other embodiments, the proportion of the humidity characteristic can also be determined in other ways, which are not limited here.

[0044] In addition, in a specific implementation, the dispersion characteristic of the soil humidity in the garden monitoring area is determined according to the humidity deviation characteristic and the proportion of the humidity characteristic: first, a judgment index system of the dispersion characteristic is set, for example, the deviation standard deviation > 3%, the proportion of the heavy warning interval > 5%, and the difference in the proportion of different time periods / regions > 20% are defined as high dispersion index, the deviation standard deviation 1%-3%, the proportion of the light warning interval 10%-20%, and the difference in the proportion of space and time 10%-20% are defined as medium dispersion index, and the deviation standard deviation < 1%, the proportion of the suitable interval > 85%, and the difference in the proportion of space and time < 10% are defined as low dispersion index; then, the deviation standard deviation and the extreme deviation rate in the humidity deviation characteristic are matched with the proportion of each interval and the difference in the proportion of space and time in the proportion of the humidity characteristic based on the judgment index system, for example, if the deviation standard deviation of the 0-30 cm soil layer is 3.2% (high dispersion index), the proportion of the heavy warning interval is 7% (high dispersion index), and the difference in the proportion of the east and west regions is 20% (high dispersion index), the dispersion degree of the soil layer is determined as high dispersion degree; finally, the dispersion degree judgment results of all soil layers are integrated to obtain the dispersion characteristic of the soil humidity in the garden monitoring area; in other embodiments, the dispersion characteristic of the soil humidity can also be determined in other ways, which are not limited here.

[0045] It should be noted that the dispersion characteristic of the soil humidity in the present application represents the dispersion degree characteristic of the soil humidity in different time dimensions in the garden monitoring area, which can be used to monitor whether the soil humidity of each sampling point in the monitoring range is uniform or whether the humidity of a sampling point at different times is stable.

[0046] It should be noted that the overall discrete causes in the garden monitoring area, such as the large humidity deviation caused by soil compaction, form a soil moisture dispersion feature including the dispersion degree classification of each soil layer, the core judgment index, and the overall discrete cause. For example, the soil moisture dispersion feature of the garden monitoring area is: 0-30cm soil layer (high dispersion, deviation standard deviation 3.2%, severe warning proportion 7%, 30-60cm soil layer (moderate dispersion, deviation standard deviation 2.1%, mild warning proportion 15%, and the overall discrete cause is mainly soil compaction and uneven irrigation.

[0047] In some embodiments, the soil moisture trend of the garden monitoring area is predicted according to the dispersion feature and all water potential penetration confidence, and the fluctuation trend of the soil moisture in the garden monitoring area within a preset time period can be achieved by the following steps: According to the dispersion feature and all water potential penetration confidence, the humidity prediction value data and the fluctuation interval of the soil moisture of the garden monitoring area within a preset time period are predicted; A humidity trend map of the soil moisture of the garden monitoring area within a preset time period is generated by the humidity prediction value data and the fluctuation interval; The fluctuation trend of the soil moisture in the garden monitoring area within a preset time period is extracted from the humidity trend map.

[0048] In specific implementation, according to the dispersion feature and all water potential penetration confidence, the humidity prediction value data and the fluctuation interval of the garden monitoring area within a preset time period are predicted: first, a suitable time series prediction model is selected, for example, an autoregressive integrated moving average model or a long short-term memory neural network can be selected, and a model verified by historical data is preferred, and the dispersion feature and the water potential penetration confidence are used as input variables, wherein the dispersion feature of the high-confidence soil layer is given a weight of 1.2 times to enhance the influence of reliable data, and the dispersion feature of the low-confidence soil layer is given a penalty weight of 0.8 times to weaken the interference of unreliable data; then, the historical data of the dispersion feature-water potential penetration confidence-soil moisture in the same period in the past 3 years is used as a training sample to train the model, for example, the model can be trained by a sliding window method, and the window size can be set to 5 collection periods, so that the model learns the correlation between the two and the humidity change; after training, the current dispersion feature and the confidence data of each soil layer are input, and the daily humidity prediction value of each soil layer within a preset time period is output to obtain the humidity prediction value data of the garden monitoring area within a preset time period, and the fluctuation interval of the soil moisture is calculated based on the standard deviation in the dispersion feature; wherein, the fluctuation interval of the soil moisture represents the fluctuation range of the soil moisture within a preset time period; in other embodiments, other ways can also be used to determine, which is not limited here.

[0049] In addition, in specific implementation, the humidity trend graph of the soil humidity of the garden monitoring area in the preset time period is generated by using the humidity prediction value data and the fluctuation interval. In constructing the graph, the horizontal axis is set as the time node of the preset time period, such as 1 node per day, and the vertical axis is divided into two layers: the upper layer is a soil layering axis, and the lower layer is a humidity value axis, which is matched with the preset humidity threshold range; the graph body draws a humidity prediction value change curve for each soil layer, and different colors are used to distinguish the soil layers, and the curve is filled with a semi-transparent shadow on both sides to represent the fluctuation interval, such as a blue curve corresponding to a light blue shadow; meanwhile, a discrete feature marking column is marked on the right side of the graph, such as a red star mark for a time period with a discrete standard deviation greater than 5%, which indicates that the humidity difference is large; an orange triangle mark for a soil layer with a confidence level less than 0.6, which indicates that the data reliability is low; and a humidity threshold reference line is added at the bottom of the graph, with a green dotted line for the appropriate interval and a yellow / red dotted line for the warning interval, to ensure that the graph simultaneously presents the prediction trend, the fluctuation range and the key reference standard, and finally constructs the humidity trend graph of the soil humidity of the garden monitoring area in the preset time period. For example, the graph can also be constructed in a space-time two-dimensional visualization manner, wherein the humidity trend graph represents the trend of the soil humidity of the garden monitoring area in the preset time period, and can be used for garden management personnel to quickly master the future change rule, potential risk and data reliability of the soil humidity; in other embodiments, other methods can also be used for generation, which are not limited here.

[0050] In addition, in specific implementation, the fluctuation trend of the soil moisture in the garden monitoring area in the preset time period is extracted from the humidity trend graph. First, the graph is analyzed in the soil layer-time dimension: from the time dimension, the trend of the prediction value curve of each soil layer is observed to determine the overall trend; from the fluctuation amplitude, the width of the fluctuation interval is measured, and the fluctuation change is confirmed in combination with the discrete feature marking column to determine whether the fluctuation change is related to the increase of the humidity difference; then, key turning points are extracted, such as the prediction value of the 0-30 cm soil layer falling to 14% on the 5th day, which is a turning point of drought risk; finally, the trend reliability is evaluated in combination with the confidence level marking column, such as a high confidence level soil layer with a high reliability of a continuous downward trend, and a low confidence level soil layer with a fluctuation intensification trend that needs to be marked with uncertainty, and the overall trend direction, layered fluctuation characteristics, key risk nodes and trend reliability are integrated to form a fluctuation trend, so as to obtain the fluctuation trend of the soil moisture in the garden monitoring area in the preset time period; in other embodiments, other methods can also be used for extraction, which are not limited here.

[0051] It should be noted that the fluctuation trend in the present application represents the trend of the fluctuation degree of the soil moisture in the garden monitoring area in the preset time period, which can be used to determine how the soil humidity changes, how large the change amplitude is, whether there is a risk and whether the conclusion is reliable.

[0052] In step 105, the fluctuation trend and the interlayer moisture anomaly mark are used to perform early warning analysis on the soil moisture of the garden monitoring area, and early warning information of the soil moisture in the garden monitoring area is obtained.

[0053] In some embodiments, the early warning information of the soil moisture in the garden monitoring area can be obtained by using the following steps: The fluctuation trend and the interlayer moisture anomaly mark are associated to calculate a risk early warning index of the soil moisture corresponding to each soil layer in the garden monitoring area. The soil moisture in the garden monitoring area is early warned according to all the risk early warning indexes to generate soil layer early warning information of each soil layer. The early warning information of the soil moisture in the garden monitoring area is generated by all the soil layer early warning information.

[0054] In a specific implementation, the fluctuation trend and the interlayer moisture anomaly mark are associated to calculate a risk early warning index of the soil moisture corresponding to each soil layer in the garden monitoring area. First, a correlation dimension mapping table is established, and the soil layer, trend direction, fluctuation amplitude, key risk node, and trend reliability in the fluctuation trend are one-to-one corresponding to the soil layer combination, anomaly type, and anomaly degree in the interlayer moisture anomaly mark, for example, the fluctuation trend of the 0-30 cm soil layer is only associated with the anomaly mark involving the soil layer. Then, the weight values of each correlation factor are set: anomaly degree, such as severe 1.0, moderate 0.7, and mild 0.4; trend direction, such as continuous decline 0.8, stable 0.2, and continuous rise 0.1; key node, such as reaching severe warning 1.0, mild warning 0.6, and no node 0.0; and trend reliability, such as taking 1.0 times coefficient when confidence is greater than 0.8, and taking 0.6 times coefficient when confidence is less than 0.6. The risk early warning index is calculated by using a weighted summation formula, for example, the formula is early warning index = anomaly degree weight × anomaly type influence coefficient + trend direction weight × fluctuation amplitude coefficient + key node weight × trend reliability coefficient, and finally the risk early warning index of each soil layer is obtained. The risk early warning index represents a parameter value of the risk degree of the soil moisture corresponding to each soil layer in the garden monitoring area, and can be used to judge the risk of the water infiltration state of the soil moisture corresponding to each soil layer in the garden monitoring area. In other embodiments, other ways can also be used to determine, which is not limited here.

[0055] In addition, in specific implementation, the soil moisture in the garden monitoring area is warned according to all the risk warning indexes to generate soil layer warning information of each soil layer: first, the warning level threshold is divided: into severe warning, moderate warning, mild warning, and no warning, and each warning corresponds to a corresponding threshold interval, and then the indexes and levels are matched one by one according to the soil layer, if the threshold interval corresponding to the risk warning index of the soil layer belongs to moderate warning, it means that the soil layer has a continuous downward trend in the future preset period, and there is a moderate slow seepage problem with the adjacent lower soil layer, which leads to insufficient water supply, so the irrigation water supply amount needs to be focused on; if the risk warning index of the adjacent lower soil layer belongs to mild warning, it means that the soil layer humidity is overall stable, but there is a mild seepage direction anomaly, such as occasional upward capillary rise, combined with the trend reliability, whether the seepage anomaly intensifies needs to be monitored regularly; finally, structured soil layer warning information is generated for each soil layer, in the format of soil layer number-warning level-warning basis (trend + anomaly mark)-core risk-suggested monitoring frequency, wherein the soil layer warning information represents the structured warning information generated for a single soil layer in the garden monitoring area, focusing on the humidity risk of the soil layer, and is the basis for subsequent integration of regional warning; in other embodiments, other ways of warning can also be used, which are not limited here.

[0056] In addition, in specific implementation, the warning information of the soil moisture in the garden monitoring area is generated through all the soil layer warning information: first, the spatial and temporal dimensions of the soil layer warning information are integrated: spatially, the warning level distribution of each soil layer in different regions is counted, a regional warning heat map is drawn, for example, it can be drawn by a spatial interpolation method such as Kriging interpolation, and a high-risk area is marked; temporally, the overlapping period of key risk nodes of each soil layer is extracted to determine the overall high-risk period of the region; then the regional warning level is comprehensively judged: for example, if ≥30% of the soil layers are severely warned, or ≥50% of the soil layers are moderately warned, the overall region is determined to be severely warned; if 10%-30% of the soil layers are severely warned, or 30%-50% of the soil layers are moderately warned, the region is determined to be moderately warned; if only individual soil layers are mildly warned, the region is determined to be mildly warned; finally, complete regional warning information is generated, including the overall warning level of the region, the range and period of the high-risk area, the core soil layer involved, the abnormal cause summary (such as slow seepage + continuous drought), and the targeted control suggestion (such as priority drip irrigation in the west area, loosening 30-60cm soil layer), and then the warning information of the soil moisture in the garden monitoring area is obtained.

[0057] It should be noted that the warning information in the present application is the global warning information covering the entire monitoring area generated after integrating all the soil layer warning information, which provides global decision reference for garden managers to clearly understand the overall regional risk, where to focus on, and what overall measures to take, rather than being limited to a single soil layer.

[0058] In addition, another aspect of the present application provides a garden soil humidity monitoring system, which, in some embodiments, comprises Figure 4 FIG. 4 is a structural schematic diagram of a garden soil humidity monitoring system according to some embodiments of the present application, which comprises a collection module 401, a processing module 402, and an execution module 403, which are described as follows: The collection module 401 is mainly used for collecting and preprocessing the soil humidity of each soil layer in the garden monitoring area to obtain the soil humidity data of the garden monitoring area. The processing module 402 is used for performing infiltration analysis on the water potential of each soil layer in the garden monitoring area within a preset time period according to the soil humidity data and the historical soil humidity data of the garden monitoring area to obtain the water potential infiltration confidence between each soil layer. It should be noted that the processing module 402 is also used for judging the abnormal state of interlayer water flow between each soil layer according to the water potential infiltration confidence between each soil layer to obtain the interlayer water anomaly marker of the garden monitoring area. In addition, it should be noted that the processing module 402 is also used for determining the discrete features of the soil humidity in the garden monitoring area based on the soil humidity data and the preset humidity value of the garden monitoring area, performing fluctuation prediction on the soil humidity trend of the garden monitoring area according to the discrete features and all the water potential infiltration confidences, and obtaining the fluctuation trend of the soil moisture in the garden monitoring area within a preset time period. The execution module 403 is mainly used for performing early warning analysis on the soil humidity of the garden monitoring area according to the fluctuation trend and the interlayer water anomaly marker to obtain the early warning information of the soil humidity in the garden monitoring area.

[0059] In addition, the present application also provides a computer device, which comprises a memory and a processor, the memory stores codes, and the processor is configured to acquire the codes and execute the above-mentioned garden soil humidity monitoring method.

[0060] In some embodiments, referring to Figure 5 FIG. 5 is a structural schematic diagram of a computer device for implementing the garden soil humidity monitoring method according to some embodiments of the present application. The garden soil humidity monitoring method in the above-mentioned embodiments can be implemented by the computer device shown in Figure 5 which comprises at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0061] The processor 501 can be a general central processing unit (CPU), or an application specific integrated circuit (ASIC).

[0062] The communication bus 502 can be used to transmit information between the above components.

[0063] The memory 503 can be a readonly memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable readonly memory (EEPROM), a compact disc readonly memory (CDROM) or other optical disk storage, a magneto-optical disk storage, a magnetic disk or other magnetic storage device, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 503 can exist independently, and is connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0064] The memory 503 is used to store program code for implementing the solutions of the present application, and the processor 501 is used to control the execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The methods used in the above embodiments can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0065] The communication interface 504 uses any transceiver-like device to communicate with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0066] In a particular implementation, as one embodiment, the computer device can include multiple processors, each of which can be a single CPU processor or a multi-CPU processor. A processor herein can refer to one or more devices, circuits, and / or processing cores for processing data, such as computer program instructions.

[0067] The computer device described above can be a general purpose computer device or a special purpose computer device. In a particular implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0068] In addition, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the garden soil humidity monitoring method described above.

[0069] Although the preferred embodiments of the present application have been described, those skilled in the art who are informed of the basic inventive concept can make additional changes and modifications to the embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0070] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.

Claims

1. A method for monitoring soil moisture in gardens, wherein, The method involves pre-deploying multiple soil moisture sensors in various soil layers within a garden monitoring area, characterized by the following steps: Soil moisture in each soil layer of the garden monitoring area is collected and preprocessed to obtain soil moisture data for the garden monitoring area. Based on the soil moisture data and the historical soil moisture data of the garden monitoring area, the water potential of each soil layer in the garden monitoring area is analyzed within a preset time period to obtain the water potential permeability confidence level between each soil layer. The abnormal state of interlayer water flow between soil layers is judged by the water potential permeability confidence level between each soil layer, thereby obtaining the interlayer water anomaly marker in the garden monitoring area. Based on the soil moisture data and the preset moisture value of the garden monitoring area, the discrete characteristics of soil moisture in the garden monitoring area are determined. Based on the discrete characteristics and all water potential permeability confidence levels, the fluctuation trend of soil moisture in the garden monitoring area is predicted to obtain the fluctuation trend of soil moisture in the garden monitoring area within a preset time period. By analyzing the fluctuation trend and the interlayer moisture anomaly markers, an early warning analysis of soil moisture in the garden monitoring area is performed to obtain early warning information on soil moisture in the garden monitoring area.

2. The method as described in claim 1, characterized in that, Based on the soil moisture data and historical soil moisture data of the garden monitoring area, the water potential permeability analysis of each soil layer in the garden monitoring area within a preset time period is performed to obtain the water potential permeability confidence level between each soil layer, specifically including: Obtain historical soil moisture data for the garden monitoring area; The current permeability characteristics between each soil layer are determined based on the soil moisture data. Obtain the preset time period for the garden monitoring area; Based on the historical soil moisture data, determine the historical infiltration characteristics of each soil layer over a preset time period; The confidence level of water potential permeability between soil layers is determined based on the current permeability characteristics of each soil layer and the historical permeability characteristics of each soil layer over a preset time period.

3. The method as described in claim 1, characterized in that, The abnormal state of interlayer water flow between soil layers is judged by the water potential permeability confidence level between each soil layer, and the interlayer water anomaly markers in the garden monitoring area are obtained, specifically including: Based on historical interlayer water flow data and soil physicochemical properties of the garden monitoring area, a threshold range for normal water flow between adjacent soil layers was constructed. To obtain the water potential and seepage patterns between different soil layers; The water transport characteristics between soil layers are determined based on the water potential permeability patterns and the confidence levels of water potential permeability between soil layers. Based on the threshold range and the water transport characteristics between each soil layer, the interlayer water flow between each soil layer is compared, and each interlayer with abnormality is marked, thereby forming an anomaly marker for interlayer water flow in the garden monitoring area.

4. The method as described in claim 1, characterized in that, Determining the discrete characteristics of soil moisture in the garden monitoring area based on the soil moisture data and the preset moisture value of the garden monitoring area specifically includes: Obtain the preset humidity value and humidity threshold range of the garden monitoring area; The humidity deviation characteristics of the garden monitoring area are determined based on the soil moisture data and the preset humidity value. Determine the humidity percentage characteristics of the soil moisture data within the humidity threshold range; The discrete characteristics of soil moisture in the garden monitoring area are determined based on the humidity deviation characteristics and the humidity percentage characteristics.

5. The method as described in claim 1, characterized in that, Based on the discrete characteristics and all water potential permeability confidence levels, the soil moisture trend of the garden monitoring area is predicted to fluctuate, and the specific fluctuation trend of soil moisture in the garden monitoring area within a preset time period includes: Based on the discrete features and all water potential and permeability confidence levels, predict the humidity forecast data and soil moisture fluctuation range of the garden monitoring area within a preset time period; A humidity trend map of soil moisture in the garden monitoring area within a preset time period is generated using the predicted humidity data and the fluctuation range. The fluctuation trend of soil moisture in the garden monitoring area within a preset time period is extracted from the humidity trend map.

6. The method as described in claim 1, characterized in that, By analyzing the fluctuation trend and the interlayer moisture anomaly markers to obtain early warning information on soil moisture in the garden monitoring area, the following specific information is obtained: The fluctuation trend and the interlayer moisture anomaly markers are correlated to calculate the risk warning index of soil moisture corresponding to each soil layer in the garden monitoring area; Based on all risk warning indices, soil moisture in the garden monitoring area is warned, so as to generate soil layer warning information for each soil layer. Early warning information on soil moisture within the garden monitoring area is generated based on all soil layer early warning information.

7. The method as described in claim 1, characterized in that, The soil layers in the garden monitoring area are divided into the topsoil, root active layer, soil water retention layer, and deep stabilization layer.

8. The method as described in claim 1, characterized in that, Before deploying sensors, a comprehensive survey of the garden monitoring area is conducted to clarify the soil profile structure, depth and distribution range of each soil layer, and to determine the number and distribution density of monitoring points based on the area and soil heterogeneity factors.

9. The method as described in claim 1, characterized in that, The preprocessing includes noise removal, missing data handling, and error handling.

10. A garden soil moisture monitoring system, characterized in that, include: The data acquisition module is used to collect soil moisture of each soil layer in the garden monitoring area and perform preprocessing to obtain soil moisture data of the garden monitoring area. The processing module is used to perform permeability analysis on the water potential of each soil layer in the garden monitoring area within a preset time period based on the soil moisture data and the historical soil moisture data of the garden monitoring area, and to obtain the water potential permeability confidence level between each soil layer. The processing module is also used to judge the abnormal state of interlayer water flow between soil layers based on the water potential permeability confidence between each soil layer, and then obtain the interlayer water abnormality marker of the garden monitoring area. The processing module is further configured to determine the discrete characteristics of soil moisture in the garden monitoring area based on the soil moisture data and the preset humidity value of the garden monitoring area, and to predict the fluctuation trend of soil moisture in the garden monitoring area based on the discrete characteristics and all water potential permeability confidence values, so as to obtain the fluctuation trend of soil moisture in the garden monitoring area within a preset time period. The execution module is used to perform early warning analysis on the soil moisture in the garden monitoring area based on the fluctuation trend and the interlayer moisture anomaly marker, and obtain early warning information on the soil moisture in the garden monitoring area.

Images