A method for predicting soil moisture content in farmland and irrigation

Abstract

The present application provides a method for predicting soil moisture content in farmland and irrigation, which relates to the technical field of irrigation and is used to improve the technical problems of poor soil moisture content prediction and irrigation strategy effects in related technologies. The method includes: obtaining multi-source data, where the multi-source data includes one or more of soil sensor data, remote sensing data, meteorological data, and crop parameters; obtaining a first soil moisture content based on the multi-source data, and the first soil moisture content is used to indicate the water content in the current soil; predicting a second soil moisture content according to the first soil moisture content and the multi-source data, and the second soil moisture content is used to indicate the water content in the soil within a certain period in the future; when the second soil moisture content is less than a preset moisture content, generating an irrigation instruction based on the second soil moisture content and the target moisture content, and the farmland irrigation method performs irrigation according to the irrigation instruction, and the irrigation instruction includes the single irrigation time and the irrigation interval time.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of irrigation, and in particular, to a method for predicting soil moisture content in farmland and irrigation. Background Art

[0002] In traditional farmland irrigation management, irrigation decisions mostly rely on artificial experience or static models based on fixed thresholds, lacking the ability to respond in real time to the dynamic changes of soil moisture and environmental conditions. Existing technologies usually use a single sensor to monitor the water content of the surface soil. However, limited by the sensor accuracy, salt interference, and the characteristics of deep water infiltration, it is difficult to accurately reflect the actual water demand of the crop root layer. In addition, the impacts of meteorological factors (such as rainfall and evaporation) and crop growth stages are not systematically integrated, resulting in inaccurate control of irrigation timing and water volume, which is likely to cause water resource waste or crop water stress. At the same time, with the growth of the global population and the intensification of climate change, agricultural production is facing increasingly severe challenges. In farmland irrigation management, how to accurately predict soil moisture content (i.e., the content and state of water in the soil) and formulate reasonable irrigation strategies based on this is the key to achieving water-saving irrigation and increasing crop yields. Summary of the Invention

[0003] The embodiments of the present application provide a method for predicting soil moisture content in farmland and irrigation, which is used to improve the technical problems in the related art that the effects of soil moisture content prediction and irrigation strategies are poor.

[0004] To achieve the above object, the embodiments of the present application adopt the following technical solutions:

[0005] The present application provides a method for predicting soil moisture content in farmland and irrigation, which is applied to a farmland irrigation method. The method includes: obtaining multi-source data, where the multi-source data includes one or more of soil sensor data, remote sensing data, meteorological data, and crop parameters; obtaining a first soil moisture content based on the multi-source data, where the first soil moisture content is used to indicate the content of water in the current soil; predicting a second soil moisture content according to the first soil moisture content and the multi-source data, where the second soil moisture content is used to indicate the content of water in the soil within a certain period in the future; when the second soil moisture content is less than a preset moisture content, generating an irrigation instruction based on the second soil moisture content and a target moisture content, and the farmland irrigation method irrigates according to the irrigation instruction, and the irrigation instruction includes the single irrigation time and the irrigation interval time.

[0006] In a possible implementation manner, the remote sensing data includes radar echo intensity and rainfall intensity, the meteorological data includes the moving speed of cloud images, and obtaining the first soil moisture content based on the multi-source data includes:

[0007] Obtain a radar decision coefficient based on the radar echo intensity and the cloud map movement speed, where the radar decision coefficient is used to indicate the decision-making influence of the radar soil moisture content measured by the radar on the first soil moisture condition;

[0008] Obtain a sensor decision coefficient based on the rainfall intensity and the crop parameters, where the sensor decision coefficient is used to indicate the decision-making influence of the sensor soil moisture content measured by the soil sensor on the first soil moisture condition, and the crop parameters include the root depth of the current crop;

[0009] Obtain the first soil moisture condition based on the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content, and the sensor soil moisture content.

[0010] In a possible implementation, the soil sensor includes a first sensor and a second sensor, the first sensor includes a capacitive sensor, and the second sensor includes a frequency domain reflectometric sensor.

[0011] In a possible implementation, the obtaining the first soil moisture condition based on the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content, and the sensor soil moisture content includes:

[0012] Obtain a first initial moisture content of the current area measured by the first sensor and a second initial moisture content of the current area measured by the second sensor;

[0013] Correct the first sensor according to the current soil salinity and a compensation formula, and obtain a third initial moisture content. The compensation formula is:

[0014]

[0015] where, is the first initial moisture content, is the third initial moisture content, EC is the soil conductivity, and K1 is the linear influence coefficient of the conductivity on the moisture content reading;

[0016] When the error value between the second initial moisture content and the third initial moisture content exceeds the error threshold, select the third initial moisture content of the first sensor at an area adjacent to the current area as the sensor soil moisture content of the current area.

[0017] In a possible implementation, the obtaining the first soil moisture condition based on the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content, and the sensor soil moisture content further includes:

[0018] When the error value between the second initial water content and the third initial water content exceeds the error threshold, the fourth initial water content obtained by weighted fusion of the second initial water content and the third initial water content in the current area is used as the sensor soil water content in the current area.

[0019] In a possible implementation manner, the obtaining of the radar decision coefficient based on the radar echo intensity and the cloud map moving speed includes:

[0020] Obtaining a radar decision coefficient according to the radar echo intensity, the cloud map moving speed, and a first decision coefficient formula, where the first decision coefficient formula is:

[0021]

[0022] Wherein, is the radar decision coefficient, is the radar echo intensity, is the cloud map moving speed, and are weight coefficients.

[0023] In a possible implementation manner, the obtaining of the sensor decision coefficient based on the rainfall intensity and the crop parameters includes:

[0024] Obtaining a sensor decision coefficient according to the rainfall intensity, the crop parameters, and a second decision coefficient formula, where the second decision coefficient formula is:

[0025]

[0026] Wherein, is the sensor decision coefficient, is the permeability coefficient reflecting the ability of the soil to allow water to pass through, is the rainfall intensity, is the crop root depth, is the root reference depth.

[0027] In a possible implementation manner, the predicting of the second soil moisture content according to the first soil moisture content and the multi-source data includes:

[0028] Predicting the second soil moisture content based on the first soil moisture content, the multi-source data, and a prediction model, where the prediction model is:

[0029]

[0030] Wherein, is the second soil moisture content, is the first soil moisture content, is the future The cumulative precipitation within a time period is for the future The average temperature within a time period is the crop root depth, and k is the natural attenuation coefficient of soil moisture for the corresponding soil type 、 、 is the environmental coupling coefficient fitted based on historical data is the soil water retention base term

[0031] In a possible implementation, generating the irrigation instruction based on the second soil moisture content and the target moisture content includes:

[0032] Obtain the field capacity and the saturated hydraulic conductivity of the soil in the current area. The field capacity is the maximum water holding capacity of the soil, and the saturated hydraulic conductivity of the soil is the vertical infiltration distance of water in the saturated soil per unit time

[0033] Obtain the irrigation amount based on the target moisture content, the second soil moisture content, and the crop parameters

[0034] Obtain the single irrigation time according to the saturated hydraulic conductivity of the soil and the target wetting depth, and obtain the irrigation interval time according to the first soil moisture content and the field capacity

[0035] In a possible implementation, obtaining the field capacity and the saturated hydraulic conductivity of the soil in the current area includes:

[0036] Obtain the field capacity according to the normalized difference water index of the current area, the initial field capacity of the current area, and the first correction formula. The first correction formula is:

[0037]

[0038] Wherein, is the field capacity is the initial field capacity Learning rate is the deviation between the measured value and the target value of the normalized difference water index is the NDWI deviation threshold

[0039] Obtain the saturated hydraulic conductivity of the soil according to the infiltration rate of the current area, the initial saturated hydraulic conductivity of the current area, and the second correction formula. The first correction formula is:

[0040]

[0041] Wherein, is the saturated hydraulic conductivity of the soil is the initial saturated hydraulic conductivity of the soil is the infiltration rate, which refers to the vertical infiltration depth of water in the soil per unit time. is the reference infiltration rate. is the normalization coefficient. is the adjustment coefficient, indicating the influence intensity of the infiltration rate deviation on the infiltration rate.

[0042] In this way, by integrating multi-source data such as soil sensors, remote sensing, meteorology, and crop parameters, this application realizes the prediction of the future trend of soil moisture in farmland, and generates specific variable irrigation instructions according to the predicted soil moisture, such as single-time duration and interval, improving irrigation efficiency while reducing the risk of water resource waste and soil salinization. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic flowchart of the generation method provided by some embodiments of this application;

[0044] Figure 2 is Figure 1 the schematic flowchart of S200 in some embodiments in

[0045] Figure 3 is Figure 1 the schematic flowchart of S400 in some embodiments in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] Next, the technical solutions in the embodiments of this application will be described with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0047] Hereinafter, terms such as "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0048] In addition, in this application, orientation terms such as "upper", "lower", "left", and "right" may include but are not limited to being defined relative to the schematic placement orientation of the components in the drawings. It should be understood that these directional terms may be relative concepts, and they are used for relative description and clarification, and they may change accordingly with the change of the orientation of the components placed in the drawings.

[0049] In this application, unless otherwise specified or limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. In addition, the term "electrical connection" can be a way of achieving electrical connection for signal transmission.

[0050] As used herein, "about," "substantially," or "approximately" includes the stated value and reference values ​​that are within an acceptable range of deviation from the particular value, where the acceptable range of deviation is determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement method).

[0051] In the embodiments of the present application, the words "exemplarily" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the words "exemplarily" or "for example" are used.

[0052] In traditional farmland irrigation management, irrigation decisions mostly rely on manual experience or static models based on fixed thresholds, lacking the ability to respond to dynamic changes in soil moisture and environmental conditions in real time. Existing technologies usually use a single sensor to monitor surface soil moisture content, but due to limitations in sensor accuracy, salt interference, and deep water penetration characteristics, it is difficult to accurately reflect the actual water demand of the crop root layer. In addition, the impact of meteorological factors (such as rainfall and evaporation) and crop growth stages has not been systematically integrated, resulting in inaccurate control of irrigation timing and water volume, which can easily lead to water resource waste or crop water stress. At the same time, with the growth of the global population and the intensification of climate change, agricultural production is facing increasingly severe challenges. In farmland irrigation management, how to accurately predict soil moisture (i.e., the content and state of water in the soil) and formulate reasonable irrigation strategies based on this is the key to achieving water-saving irrigation and increasing crop yields.

[0053] The present application provides a method for predicting soil moisture and irrigation in farmland, which is used to improve the technical problem of poor soil moisture prediction and irrigation strategy effects in related technologies. Figure 1 , Figure 2 as well as Figure 3 As shown, the method includes:

[0054] S100, acquiring multi-source data, where the multi-source data includes one or more of soil sensor data, remote sensing data, meteorological data, and crop parameters.

[0055] Exemplarily, data such as soil humidity, temperature, and conductivity can be obtained through soil sensors. Specifically, the soil sensors can include capacitive sensors and frequency domain reflectometric sensors, which are respectively used to measure the soil water content at different depths. Data such as satellite cloud images and vegetation indices can be obtained through remote sensing devices. For example, satellite remote sensing can provide information such as cloud movement speed and vegetation health status. Meteorological data such as rainfall intensity, wind speed, and temperature can be obtained through weather stations. Crop parameters such as the root depth and growth stage of the current crop can be obtained from agricultural databases or on-site measurements.

[0056] Exemplarily, the initial water content θ of the surface soil (0 - 20 cm) is obtained through a capacitive sensor (the first sensor) 1 , and the soil conductivity EC and temperature are measured synchronously. The initial water content θ of the deep soil (30 cm, 50 cm) is obtained through a frequency domain reflectometric sensor (the second sensor) 2 . Remote sensing data is received, including the radar echo intensity Rd (unit: dBZ) and the satellite cloud image movement speed x (unit: km / h). Meteorological data is obtained, including the rainfall intensity Ry (unit: mm / h) and the air temperature T (unit: °C). Crop parameters are obtained, including the root depth Dz (unit: cm) and the root reference depth Db (such as the default 50 cm).

[0057] Exemplarily, in a sandy soil corn field, through the above steps: the capacitive sensor measures θ 1 = 25% (EC = 1.2 mS / cm, temperature 28 °C), and the frequency domain reflectometric sensor measures θ 2 = 20%. The radar echo intensity Rd = 65 dBZ (strong rainfall signal), the cloud image movement speed x = 25 km / h (severe convective weather), the current rainfall intensity Ry = 0 mm / h, and the root depth Dz = 50 cm. It can be understood that the radar echo intensity can be retrieved from the meteorological radar reflection signal intensity. The cloud image movement speed can be calculated by analyzing the displacement speed of the cloud layer through the satellite cloud image time series. The root depth can be obtained through a crop growth model or on-site measurement in the field, and the root depth can characterize the water absorption capacity of the crop.

[0058] S200. Obtain a first soil moisture condition based on the multi-source data, and the first soil moisture condition is used to indicate the water content in the current soil.

[0059] Exemplarily, the obtaining of the first soil moisture condition includes the following steps:

[0060] S210. Obtain a radar decision coefficient based on the radar echo intensity and the cloud image movement speed. The radar decision coefficient is used to indicate the decision influence of the radar soil water content measured by the radar on the first soil moisture condition. Exemplarily, the radar decision coefficient can be calculated through the first decision coefficient formula:

[0061]

[0062] Among them, is the radar decision coefficient, is the radar echo intensity, is the moving speed of the cloud image, and are the weight coefficients. It can be understood that the unit of the radar echo intensity is dBZ, and the unit of the moving speed of the cloud image is km / h.

[0063] It can be understood that in the above formula, 70 dBZ is an example of the heavy rainfall threshold provided by this application to standardize the radar echo intensity and quantify the influence weight of precipitation on soil moisture. This value can be specifically set by technicians based on requirements. can map the moving speed of the cloud image to the interval [0, 1], and 15 km / h is the critical value, indicating a fast-moving heavy rainfall system. K2 and K3 can be fitted through historical data to balance the contributions of radar and cloud image data.

[0064] According to the parameters obtained in the above steps, can be calculated.

[0065] S220. Obtain the sensor decision coefficient based on the rainfall intensity and the crop parameters. The sensor decision coefficient is used to indicate the decision influence of the sensor soil moisture measured by the soil sensor on the first soil moisture, and the crop parameters include the root depth of the current crop. Specifically, the sensor decision coefficient can be calculated by the second decision coefficient formula:

[0066]

[0067] Among them, is the sensor decision coefficient, is the permeability coefficient reflecting the ability of the soil to allow water to pass through, is the rainfall intensity, is the crop root depth, is the reference root depth. Among them, the unit of the rainfall intensity is mm / h, and the unit of the root depth is cm.

[0068] It can be understood that in the above formula, this part suppresses the sensor weight through the rainfall intensity (no suppression when Ry = 0), can standardize the root depth (for example, Db = 50 cm can be used as the reference value), and the deeper the root, the higher the weight of the sensor data. For reflecting the seepage characteristics of sandy soil, it can be calibrated through seepage experiments to establish a mapping table corresponding to the soil type. Exemplarily, the rainfall intensity can be obtained through a rain gauge or radar inversion. The root depth can be retrieved from an agricultural database according to the crop type and the current growth stage, etc.

[0069] Based on the parameters obtained in the above steps, it can be calculated that .

[0070] S230. Obtain the first soil moisture condition based on the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content, and the sensor soil moisture content. Specifically, the first soil moisture condition can be calculated by the following formula:

[0071]

[0072] where, is the first soil moisture condition, θradar is the radar soil moisture content, and θsensor is the sensor soil moisture content. It can be understood that before calculation, it is necessary to first and be normalized. Such as

[0073] Based on the above parameters, it can be calculated that .

[0074] In one embodiment, the soil sensor includes a first sensor and a second sensor. The first sensor includes a capacitive sensor, and the second sensor includes a frequency domain reflectometric sensor. Specifically, the capacitive sensor can be used to measure the surface soil moisture content, and the frequency domain reflectometric sensor can be used to measure the deep soil moisture content. Among them, the capacitive sensor can obtain the moisture content by measuring the dielectric constant of the soil, and the frequency domain reflectometric sensor can obtain the moisture content by measuring the reflection characteristics of electromagnetic waves.

[0075] Exemplarily, before calculating the first soil moisture condition, the determination of the sensor soil moisture content can include:

[0076] Obtain the first initial moisture content of the current area measured based on the first sensor, and the second initial moisture content of the current area measured based on the second sensor;

[0077] Correct the first sensor according to the current soil salinity and the compensation formula to obtain the third initial moisture content. The compensation formula is:

[0078]

[0079] where, is the first initial moisture content, is the third initial water content, EC is the soil conductivity, and K1 is the linear influence coefficient of conductivity on the water content reading, which can be calibrated through experiments. For example, when K1 = 0.05, it means that every 1 mS / cm conductivity causes a 0.05% overestimation of the capacitance sensor reading. EC can be measured by the built-in electrodes of the sensor to reflect the current salt concentration of the soil. In this way, the interference of salt on the dielectric constant measurement can be eliminated, and the accuracy of the surface water content can be improved.

[0080] According to the above parameters, it can be calculated that .

[0081] When the error value between the second initial water content and the third initial water content exceeds the error threshold, select the third initial water content of the first sensor at the area adjacent to the current area as the sensor soil water content of the current area.

[0082] Exemplarily, the error threshold can be set to 15%. At this time, the error |24.94% - 20%| = 4.94% < 15% between the second initial water content and the third initial water content, and the third initial water content of the first sensor can be used as the sensor soil water content of the current area.

[0083] When the error value between the second initial water content and the third initial water content does not exceed the error threshold, the first initial water content of the current area measured by the first sensor can be used as the sensor soil water content, or the fourth initial water content obtained by weighted fusion according to the second initial water content and the third initial water content of the current area can be used as the sensor soil water content of the current area.

[0084] For example, in some examples, the weight coefficients of the two are 0.3 and 0.7 respectively, then .

[0085] S300. Predict the second soil moisture condition according to the first soil moisture condition and the multi-source data, where the second soil moisture condition is used to indicate the water content in the soil within a certain future time period. Exemplarily, the prediction of the second soil moisture condition includes:

[0086] Predict the second soil moisture condition based on the first soil moisture condition, multi-source data, and a prediction model. Specifically, the prediction model can be expressed by the following formula:

[0087]

[0088] where, is the second soil moisture condition, is the first soil moisture condition, is the future The cumulative precipitation within a time period is the average temperature within a future time period, is the crop root depth, k is the natural attenuation coefficient of soil moisture for the corresponding soil type, and and is the environmental coupling coefficient, is the soil water retention base term. Among them, k, α, β, and γ can be obtained by regression analysis fitting of historical soil moisture data or set or optimized by technicians according to requirements or experimental results.

[0089] For example, when k = 0.05 (attenuation coefficient of sandy soil), α = 0.8, β = 2.5, γ = 0.12, and ε = 5%,

[0090] In the above formula, the natural loss of moisture is simulated through the exponential decay term (for example, when k = 0.05 / h, it indicates rapid infiltration of sandy soil). When there is no rainfall in the future 3 hours (P(t) = 0), the contribution of this term is 0. ln(Dz + 1) reflects the non-linear effect of root water absorption (when Dz = 50cm, ln(51) = 3.93). It can be measured by the laboratory pressure membrane method. For example, ε = 5% can represent the water retention capacity of the sandy soil base.

[0091] S400. When the second soil moisture content is less than the preset moisture content, an irrigation instruction is generated based on the second soil moisture content and the target moisture content. The farmland irrigation method irrigates according to the irrigation instruction, and the irrigation instruction includes the single irrigation time and the irrigation interval time.

[0092] Exemplarily, the generation of the irrigation instruction includes the following steps:

[0093] S410. Obtain the field capacity and the saturated hydraulic conductivity of the soil in the current area. The field capacity is the maximum water holding capacity of the soil, and the saturated hydraulic conductivity of the soil is the vertical infiltration distance of water in saturated soil per unit time.

[0094] Exemplarily, the field capacity is obtained according to the normalized difference water index of the current area, the initial field capacity of the current area, and the first correction formula. The first correction formula is:

[0095]

[0096] Among them, is the field capacity, is the initial field capacity, is the learning rate, used to control the influence intensity of the NDWI deviation on θf1, is the deviation between the measured value and the target value of the Normalized Difference Water Index, is the NDWI deviation threshold, such as 0.15.

[0097] Among them, the Normalized Difference Water Index can be obtained through satellite remote sensing, the initial field water holding capacity can be obtained through soil sample analysis, and the NDWI deviation threshold can be obtained through fitting historical data.

[0098] The saturated hydraulic conductivity of the soil is obtained according to the infiltration rate of the current area, the initial saturated hydraulic conductivity of the soil in the current area, and the second correction formula. The second correction formula is:

[0099]

[0100] Among them, is the saturated hydraulic conductivity of the soil, is the initial saturated hydraulic conductivity of the soil, is the infiltration rate, which refers to the vertical infiltration depth of water in the soil per unit time, is the reference infiltration rate, is the normalization coefficient, is the adjustment coefficient, indicating the influence intensity of the infiltration rate deviation on the infiltration rate.

[0101] The initial θf2 = 28% is obtained according to the measurement and calculation by technicians or the current soil historical data, etc., = 2.5 cm / h, the infiltration rate Vs = 0.7 cm / h, ΔNDWI = 0.04 (calculated by the measured value of satellite remote sensing NDWI and the target value (such as 0.38)), and α = 0.02 is set. Then:

[0102] 。

[0103]

[0104] In the above example, for the convenience of calculation, the reference infiltration rate Vj of loam is set to 0.5 cm / h (example), the normalization coefficient Vg is 0.5 cm / h, and the adjustment coefficient ρ is set to 0.1 to limit the correction range within ±10%.

[0105] S420. Obtain the irrigation amount based on the target soil moisture, the second soil moisture, and the crop parameters. The target soil moisture can be obtained through the agricultural database or user settings, the second soil moisture can be obtained through the aforementioned steps, and the crop parameters can be obtained from the agricultural database or on-site measurement. Specifically, the irrigation amount can be calculated by the following formula:

[0106]

[0107] Among them, V is the irrigation amount, θtarget is the target soil moisture (the water requirement threshold of crops set based on empirical values, e.g., θtarget = θf × 80%), is the root depth of the crop, S is the area to be irrigated, and the area of 1 mu is 666.7 square meters.

[0108] Based on the above parameters, it can be calculated that .

[0109] S430. Obtain the single irrigation time according to the saturated hydraulic conductivity of the soil and the target wetting depth, and obtain the irrigation interval time according to the first soil moisture and the field capacity.

[0110] Exemplarily, the single irrigation time can be calculated by the following formula:

[0111]

[0112] Among them, Ton is the single irrigation time, Dwet is the target wetting depth, which can be set according to the root distribution of the crop, e.g., Dwet = 30 cm, Ks is the saturated hydraulic conductivity of the soil, and η is the irrigation efficiency, such as 20% seepage loss in sandy soil.

[0113] Exemplarily, the irrigation interval time can be calculated by the following formula:

[0114]

[0115] Among them, Toff is the irrigation interval time, θd is the first soil moisture, and θf1 is the field capacity.

[0116] Based on the above parameters, it can be calculated that:

[0117]

[0118] seconds

[0119] In summary, the irrigation instruction can include a water volume of 2.72 m³ / mu, a single irrigation of 7.21 seconds, an interval of 17.9 seconds, and the irrigation system implements the irrigation task of a water volume of m³ / mu, a single irrigation of 7.21 seconds, and an interval of 17.9 seconds.

[0120] Through the description of the above embodiments, those skilled in the art can clearly understand that the diagnostic method in the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence or the part that contributes to the related technology, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to enable a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0121] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above division of each functional module is used as an example for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0122] In several embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules or units is only a logical functional division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0123] The units described as separate components may or may not be physically separated. The components displayed as units may be one physical unit or multiple physical units, that is, they can be located in one place or distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0124] In addition, the functional units in the various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware.

[0125] The above content is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for predicting soil moisture and irrigation in farmland, applied to farmland irrigation, characterized in that: The method comprises: Acquiring multi-source data, the multi-source data including one or more of soil sensor data, remote sensing data, meteorological data, and crop parameters; Acquire a first soil moisture condition based on the multi-source data, where the first soil moisture condition is used to indicate the current moisture content in the soil; Predicting a second soil moisture condition according to the first soil moisture condition and the multi-source data, wherein the second soil moisture condition is used to indicate the moisture content in the soil within a certain period of time in the future; When the second soil moisture condition is less than a preset soil moisture condition, an irrigation instruction is generated based on the second soil moisture condition and a target soil moisture condition, and the farmland irrigation method performs irrigation according to the irrigation instruction, wherein the irrigation instruction includes a single irrigation time and an irrigation interval time; The remote sensing data includes radar echo intensity and cloud map moving speed, the meteorological data includes rainfall intensity, and the first soil moisture condition is obtained based on the multi-source data, including: Acquire a radar decision coefficient based on the radar echo intensity and the cloud map moving speed, wherein the radar decision coefficient is used to indicate the decision influence of the radar soil moisture content measured by the radar on the first soil moisture condition; acquiring a sensor decision coefficient based on the rainfall intensity and the crop parameter, the sensor decision coefficient being used to indicate a decision influence of the sensor soil moisture content measured by the soil sensor on the first soil moisture condition, the crop parameter comprising a root depth of a current crop; Obtaining the first soil moisture condition according to the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content, and the sensor soil moisture content; The obtaining of the radar decision coefficient based on the radar echo intensity and the cloud map moving speed comprises: The radar decision coefficient is obtained according to the radar echo intensity, the cloud map moving speed and the first decision coefficient formula, and the first decision coefficient formula is: in, is the radar decision coefficient, is the radar echo intensity, is the cloud map moving speed, , is the weight coefficient; The obtaining of a sensor decision coefficient based on the rainfall intensity and the crop parameter comprises: The sensor decision coefficient is obtained according to the rainfall intensity, the crop parameter and the second decision coefficient formula, and the second decision coefficient formula is: in, is the sensor decision coefficient, The permeability coefficient reflects the soil's ability to allow water to pass through. is the rainfall intensity, is the crop root depth, is the reference depth of the root system.

2. The farmland soil moisture prediction and irrigation method according to claim 1, characterized in that: The soil sensor includes a first sensor and a second sensor, the first sensor includes a capacitive sensor, and the second sensor includes a frequency domain reflectance sensor.

3. The farmland soil moisture prediction and irrigation method according to claim 2, characterized in that: The obtaining the first soil moisture condition according to the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content and the sensor soil moisture content includes: Acquire a first initial moisture content of the current area measured based on the first sensor, and a second initial moisture content of the current area measured based on the second sensor; The first sensor is corrected according to the current soil salinity and the compensation formula to obtain the third initial water content. The compensation formula is: in, is the first initial water content, is the third initial water content, EC is the soil electrical conductivity, and K1 is the linear influence coefficient of electrical conductivity on the water content reading; When the error value between the second initial moisture content and the third initial moisture content exceeds an error threshold, the third initial moisture content of the first sensor in an area adjacent to the current area is selected as the sensor soil moisture content of the current area.

4. The farmland soil moisture prediction and irrigation method according to claim 3, characterized in that: The obtaining the first soil moisture condition according to the radar decision coefficient, the sensor decision coefficient, the radar soil moisture content and the sensor soil moisture content further includes: When the error value between the second initial moisture content and the third initial moisture content does not exceed the error threshold, the fourth initial moisture content obtained by weighted fusion of the second initial moisture content and the third initial moisture content of the current area is used as the sensor soil moisture content of the current area.

5. The farmland soil moisture prediction and irrigation method according to claim 4, characterized in that: The predicting a second soil moisture condition according to the first soil moisture condition and the multi-source data comprises: The second soil moisture condition is predicted based on the first soil moisture condition, the multi-source data and a prediction model, wherein the prediction model is: in, For the second soil moisture condition, For the first soil moisture condition, For the future The accumulated precipitation during the period, For the future The average temperature during the period, is the crop root depth, k is the natural moisture attenuation coefficient of the corresponding soil type, , , is the environmental coupling coefficient based on historical data fitting, A base item for soil moisture retention.

6. The farmland soil moisture prediction and irrigation method according to claim 1, characterized in that: The step of generating an irrigation instruction based on the second soil moisture condition and the target soil moisture condition comprises: Obtain the field water holding capacity and soil saturated hydraulic conductivity of the current area, wherein the field water holding capacity is the maximum water holding capacity of the soil, and the soil saturated hydraulic conductivity is the vertical penetration distance of water in saturated soil per unit time; Obtaining an irrigation amount based on the target soil moisture, the second soil moisture and the crop parameter; The single irrigation time is obtained according to the soil saturated hydraulic conductivity and the target wetting depth, and the irrigation interval time is obtained according to the first soil moisture condition and field water holding capacity.

7. The farmland soil moisture prediction and irrigation method according to claim 6, characterized in that: The obtaining of the field water holding capacity and soil saturated hydraulic conductivity of the current area includes: The field water holding capacity is obtained according to the normalized difference water index of the current area, the initial field water holding capacity of the current area and the first correction formula, wherein the first correction formula is: in, is the field water holding capacity, is the initial field water capacity, learning rate, is the deviation between the measured value and the target value of the normalized difference moisture index, is the NDWI deviation threshold; The soil saturated hydraulic conductivity is obtained according to the infiltration rate of the current area, the initial soil saturated hydraulic conductivity of the current area and the second correction formula, wherein the first correction formula is: in, is the saturated hydraulic conductivity of soil, is the initial soil saturated hydraulic conductivity, is the infiltration rate, which refers to the vertical penetration depth of water in the soil per unit time. is the base permeation rate, is the normalization coefficient, is the adjustment coefficient, indicating the influence strength of the permeation rate deviation on the permeation rate.

Images