Automatic sprinkling irrigation method and system for gardens

Abstract

The invention is suitable for the technical field of intelligent agricultural irrigation, and provides an automatic sprinkling irrigation method and system for gardens, and the method comprises the following steps: obtaining soil state information, environmental meteorological information and plant physiological information in real time; based on the blade total conductance prediction model, predicting the blade total conductance in real time; determining a transpiration rate prediction value of the plant according to the leaf total conductance prediction value, and predicting the water demand of the plant in real time; predicting the soil evaporation capacity based on the soil evaporation capacity prediction model; predicting the leaf residual moisture evaporation capacity based on the leaf residual moisture evaporation capacity prediction model; according to the plant water demand, the soil evaporation capacity and the leaf residual water evaporation capacity which are predicted in real time, the needed spray irrigation amount is determined, and the spray irrigation process is dynamically adjusted in real time. According to the invention, the water demand of plants and the required sprinkling irrigation amount can be accurately predicted, so that the sprinkling irrigation process can be dynamically adjusted in real time, the phenomena of excessive irrigation or insufficient irrigation and the like are avoided, and the purpose of saving water resources and energy is achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent agricultural irrigation, and particularly relates to an automatic sprinkler irrigation method and system for gardens. Background Art

[0002] At present, most of the garden industry uses traditional irrigation methods such as timed sprinkler irrigation and watering; among them, the traditional sprinkler irrigation method cannot dynamically adjust the sprinkler irrigation process according to the actual water demand of plants, and it is easy to have phenomena such as over-irrigation or under-irrigation, resulting in waste of water resources and energy.

[0003] An intelligent sprinkler irrigation system is to automatically sprinkle plants by combining technologies such as the Internet of Things, big data, cloud computing and sensors. Although the existing intelligent sprinkler irrigation system can adjust the sprinkler irrigation process according to actual environmental factors, its prediction accuracy of the actual water demand of plants is relatively low, so there are still problems such as over-irrigation or under-irrigation. Summary of the Invention

[0004] The purpose of the present invention is to provide an automatic sprinkler irrigation method for gardens, aiming to solve the above technical problems.

[0005] The present invention is implemented as follows. An automatic sprinkler irrigation method for gardens includes the following steps:

[0006] Obtain the soil state information, environmental meteorological information and plant physiological information of the garden to be sprinkler irrigated in real time; the plant physiological information includes: leaf stomatal conductance, leaf characteristic length and abscisic acid concentration;

[0007] Based on a preset total leaf conductance prediction model, according to the soil state information, environmental meteorological information and plant physiological information, predict the total leaf conductance in real time to obtain a total leaf conductance prediction value;

[0008] According to the total leaf conductance prediction value, determine the predicted transpiration rate of the plant and predict the water demand of the plant in real time;

[0009] Based on a preset soil evaporation prediction model, predict the soil evaporation in real time; the soil evaporation refers to the amount of water lost due to water evaporation in the soil;

[0010] Based on a preset residual leaf water evaporation prediction model, predict the residual leaf water evaporation in real time; the residual leaf water evaporation refers to the residual amount after the water falling on the surface of the plant leaves during sprinkler irrigation is absorbed by the leaves;

[0011] According to the real-time predicted water demand of the plant, soil evaporation and residual leaf water evaporation, determine the required sprinkler irrigation amount and dynamically adjust the sprinkler irrigation process in real time.

[0012] Preferably, the soil state information includes soil water content and soil salinity; the environmental meteorological information includes wind speed, light intensity, relative air humidity, atmospheric carbon dioxide concentration, and air temperature; the step of predicting the total leaf conductance in real time according to the soil state information, environmental meteorological information, and plant physiological information based on a preset total leaf conductance prediction model, specifically includes:

[0013] Determine the abscisic acid concentration influencing factor according to the abscisic acid concentration, soil water content, and soil salinity of the plant;

[0014] Determine the environmental influencing factor according to the light intensity, relative air humidity, atmospheric carbon dioxide concentration, and air temperature;

[0015] Determine the leaf boundary layer conductance according to the wind speed and leaf characteristic length;

[0016] Based on a preset total leaf conductance prediction model, use the leaf stomatal conductance, abscisic acid concentration influencing factor, environmental influencing factor, and leaf boundary layer conductance of the current plant as input features to predict the total leaf conductance in real time and output the predicted value of the total leaf conductance.

[0017] Preferably, the plant physiological information further includes leaf temperature; the environmental meteorological information further includes atmospheric pressure; the step of determining the predicted value of the plant transpiration rate according to the predicted value of the total leaf conductance and predicting the water requirement of the plant in real time, specifically includes:

[0018] Determine the internal leaf water vapor pressure according to the leaf temperature;

[0019] Determine the air water vapor pressure according to the relative air humidity and air temperature;

[0020] Determine the predicted value of the plant transpiration rate according to the predicted value of the total leaf conductance, internal leaf water vapor pressure, air water vapor pressure, and atmospheric pressure;

[0021] Predict the water requirement of the plant in real time according to the predicted value of the plant transpiration rate.

[0022] Preferably, the step of predicting the water requirement of the plant in real time according to the predicted value of the plant transpiration rate, specifically includes:

[0023] Obtain the ground projection area of the garden to be sprinkler-irrigated and the total single-sided area of the plant leaves, and determine the leaf area index according to the ground projection area of the sprinkler-irrigated garden and the total single-sided area of the plant leaves;

[0024] Predict the water requirement of the plant in real time according to the predicted value of the plant transpiration rate and the leaf area index.

[0025] Preferably, the soil state information further includes surface temperature, soil temperature gradient, soil thermal conductivity, and soil depth; the step of predicting the soil evaporation in real time based on a preset soil evaporation prediction model specifically includes:

[0026] Determine the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity, and soil depth;

[0027] Determine the sensible heat flux factor according to the surface temperature, air temperature, and wind speed;

[0028] Based on a preset soil evaporation prediction model, use the light intensity, leaf area index, soil heat flux factor, and sensible heat flux factor as input features to predict the soil evaporation in real time.

[0029] Preferably, the step of predicting the residual leaf water evaporation in real time based on a preset residual leaf water evaporation prediction model specifically includes:

[0030] Obtain the current sprinkler irrigation process in real time; the sprinkler irrigation process includes the sprinkler irrigation angle, spraying speed, and sprinkler irrigation flow rate;

[0031] Determine the landing distance of the sprinkler water mist according to the current sprinkler irrigation angle, spraying speed, and wind speed;

[0032] Determine the leaf water absorption factor according to the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity;

[0033] Based on a preset residual leaf water evaporation prediction model, use the sprinkler irrigation flow rate, the landing distance of the sprinkler water mist, and the leaf water absorption factor as input features to predict the residual leaf water evaporation in real time.

[0034] Another object of the present invention is to provide an automatic sprinkler irrigation system for a garden, which is used to implement the above automatic sprinkler irrigation method, and includes:

[0035] A garden information acquisition module, which is used to acquire the soil state information, environmental meteorological information, and plant physiological information of the garden to be sprinkler irrigated in real time; the plant physiological information includes: leaf stomatal conductance, leaf characteristic length, and abscisic acid concentration;

[0036] A leaf total conductance prediction module, which is used to predict the leaf total conductance in real time based on a preset leaf total conductance prediction model according to the soil state information, environmental meteorological information, and plant physiological information, and obtain the predicted value of the leaf total conductance;

[0037] A plant water demand prediction module, which is used to determine the predicted value of the plant transpiration rate according to the predicted value of the leaf total conductance and predict the plant water demand in real time;

[0038] A soil evaporation prediction module for predicting the soil evaporation in real time based on a preset soil evaporation prediction model; the soil evaporation refers to the amount of water lost from the soil due to water evaporation.

[0039] A leaf residual water evaporation prediction module for predicting the leaf residual water evaporation in real time based on a preset leaf residual water evaporation prediction model; the leaf residual water evaporation refers to the residual amount of water on the surface of plant leaves after part of the water falling on the leaves during sprinkler irrigation is absorbed by the leaves.

[0040] A sprinkler irrigation process adjustment module for determining the required sprinkler irrigation amount according to the real-time predicted water demand of plants, soil evaporation and leaf residual water evaporation, and dynamically adjusting the sprinkler irrigation process in real time.

[0041] Preferably, the soil state information includes soil water content and soil salinity; the environmental meteorological information includes wind speed, light intensity, air relative humidity, atmospheric carbon dioxide concentration and air temperature; the leaf total conductance prediction module specifically includes:

[0042] An abscisic acid concentration influence factor determination unit for determining the abscisic acid concentration influence factor according to the abscisic acid concentration of plants, soil water content and soil salinity.

[0043] An environmental influence factor determination unit for determining the environmental influence factor according to light intensity, air relative humidity, atmospheric carbon dioxide concentration and air temperature.

[0044] A leaf boundary layer conductance determination unit for determining the leaf boundary layer conductance according to wind speed and leaf characteristic length.

[0045] A leaf total conductance prediction unit for predicting the leaf total conductance in real time based on a preset leaf total conductance prediction model, taking the leaf stomatal conductance, abscisic acid concentration influence factor, environmental influence factor and leaf boundary layer conductance of the current plant as input features, and outputting the leaf total conductance prediction value.

[0046] Preferably, the plant physiological information further includes leaf temperature; the environmental meteorological information further includes atmospheric pressure; the plant water demand prediction module specifically includes:

[0047] An internal water vapor pressure determination unit for determining the internal water vapor pressure of the leaf according to the leaf temperature.

[0048] An air water vapor pressure determination unit for determining the air water vapor pressure according to air relative humidity and air temperature.

[0049] A transpiration rate prediction value determination unit for determining the plant transpiration rate prediction value according to the leaf total conductance prediction value, internal water vapor pressure of the leaf, air water vapor pressure and atmospheric pressure.

[0050] A plant water requirement prediction unit for predicting the plant water requirement in real time according to the predicted transpiration rate of the plant.

[0051] Preferably, the soil state information further includes surface temperature, soil temperature gradient, soil thermal conductivity and soil depth; the soil evaporation prediction module specifically includes:

[0052] A soil heat flux factor determination unit for determining the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity and soil depth;

[0053] A sensible heat flux factor determination unit for determining the sensible heat flux factor according to the surface temperature, air temperature and wind speed;

[0054] A soil evaporation prediction unit for predicting the soil evaporation in real time based on a preset soil evaporation prediction model, taking the light intensity, leaf area index, soil heat flux factor and sensible heat flux factor as input features;

[0055] The leaf residual water evaporation prediction module specifically includes:

[0056] An irrigation process acquisition unit for acquiring the current irrigation process in real time; the irrigation process includes irrigation angle, spraying speed and irrigation flow rate;

[0057] An irrigation water droplet landing distance determination unit for determining the irrigation water droplet landing distance according to the current irrigation angle, spraying speed and wind speed;

[0058] A leaf water absorption factor determination unit for determining the leaf water absorption factor according to the leaf stomatal conductance, leaf temperature, air temperature and air relative humidity;

[0059] A leaf residual water evaporation prediction unit for predicting the leaf residual water evaporation in real time based on a preset leaf residual water evaporation prediction model, taking the irrigation flow rate, irrigation water droplet landing distance and leaf water absorption factor as input features.

[0060] The automatic irrigation method for gardens provided by the present invention can accurately predict the plant water requirement and the required irrigation amount in a certain future time according to the soil state information, environmental meteorological information and plant physiological information acquired in real time, and in combination with the preset leaf total conductance prediction model, soil evaporation prediction model and leaf residual water evaporation prediction model, and then can dynamically adjust the irrigation process in real time to avoid phenomena such as over-irrigation or under-irrigation, so as to achieve the purpose of saving water resources and energy. Description of the Drawings

[0061] Figure 1 It is a schematic flowchart of the automatic irrigation method for gardens provided by the embodiment of the present invention.

[0062] Figure 2 It is a schematic flow chart of step S200 in the automatic sprinkler irrigation method for gardens provided by the embodiments of the present invention.

[0063] Figure 3 It is a schematic flow chart of step S300 in the automatic sprinkler irrigation method for gardens provided by the embodiments of the present invention.

[0064] Figure 4 It is a schematic flow chart of step S400 in the automatic sprinkler irrigation method for gardens provided by the embodiments of the present invention.

[0065] Figure 5 It is a schematic flow chart of step S500 in the automatic sprinkler irrigation method for gardens provided by the embodiments of the present invention.

[0066] Figure 6 It is a schematic structural diagram of the automatic sprinkler irrigation system for gardens provided by the embodiments of the present invention.

[0067] Figure 7 It is a schematic structural diagram of the total leaf conductance prediction module provided by the embodiments of the present invention.

[0068] Figure 8 It is a schematic structural diagram of the plant water demand prediction module provided by the embodiments of the present invention.

[0069] Figure 9 It is a schematic structural diagram of the soil evaporation prediction module provided by the embodiments of the present invention.

[0070] Figure 10 It is a schematic structural diagram of the leaf residual water evaporation prediction module provided by the embodiments of the present invention. Detailed implementation manners

[0071] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0072] As Figure 1 shown, in an embodiment of the present invention, an automatic sprinkler irrigation method for gardens is provided, including the following steps:

[0073] S100. Real-time obtain the soil state information, environmental meteorological information and plant physiological information of the garden to be irrigated;

[0074] S200. Based on a preset total leaf conductance prediction model, according to the soil state information, environmental meteorological information and plant physiological information, real-time predict the total leaf conductance to obtain a total leaf conductance prediction value;

[0075] S300. Determine the predicted transpiration rate of the plant based on the predicted total leaf conductance, and predict the water requirement of the plant in real time;

[0076] S400. Predict the soil evaporation in real time based on a preset soil evaporation prediction model; the soil evaporation refers to the amount of water lost from the soil due to water evaporation;

[0077] S500. Predict the residual leaf water evaporation in real time based on a preset residual leaf water evaporation prediction model; the residual leaf water evaporation refers to the residual amount of water on the surface of the plant leaves after a part of the water sprayed during irrigation is absorbed by the leaves;

[0078] S600. Determine the required irrigation amount according to the predicted water requirement of the plant, soil evaporation, and residual leaf water evaporation in real time, and dynamically adjust the irrigation process in real time.

[0079] It should be noted that the above-provided automatic irrigation method is mainly applied to the irrigation of gardens, but is not limited thereto, and can also be applied to the irrigation of other agricultural areas such as crop planting areas and orchards. Specifically, the automatic irrigation method can accurately predict the water requirement of the plant and the required irrigation amount according to the real-time obtained soil condition information, environmental meteorological information, and plant physiological information, and in combination with the preset total leaf conductance prediction model, soil evaporation prediction model, and residual leaf water evaporation prediction model. Furthermore, it can dynamically adjust the irrigation process of the irrigation equipment in real time to avoid phenomena such as over-irrigation or under-irrigation, so as to achieve the purpose of saving water resources and energy; in practical applications, multiple nozzles of the irrigation equipment can be evenly distributed and installed around the garden. Wireless networks, various types of sensors, monitors and other hardware devices can be deployed in the garden, and a weather station and other facilities can be set up near the garden to facilitate the accurate acquisition of environmental meteorological information.

[0080] In specific applications, in step S100, the soil state information includes, but is not limited to, surface temperature, soil temperature gradient, soil thermal conductivity, soil depth, soil water content, soil salinity and other information; the environmental meteorological information includes, but is not limited to, air temperature, air relative humidity, atmospheric pressure, wind speed, light intensity, atmospheric carbon dioxide concentration, precipitation and other information; the plant physiological information includes, but is not limited to, leaf temperature, leaf stomatal conductance, leaf characteristic length, abscisic acid concentration and other information; among them, the environmental meteorological information can be obtained through facilities such as weather stations; the soil state information can be collected through various types of sensors; the leaf temperature can be measured by an infrared thermometer or a thermal imager; the leaf stomatal conductance is a key driving factor for the plant transpiration rate and can be measured by a steady-state porometer. The principle is to calculate the stomatal conductance by measuring the water vapor diffusion rate on the leaf surface, but the accuracy is poor and errors are likely to occur, and generally need to be corrected; the leaf characteristic length can be determined by methods such as direct measurement, image analysis or geometric estimation; the abscisic acid concentration can be measured by methods such as enzyme-linked immunosorbent assay or high performance liquid chromatography.

[0081] In a preferred embodiment of the present invention, as Figure 2 shown, based on a preset leaf total conductance prediction model, according to the soil state information, environmental meteorological information and plant physiological information, the step of predicting the leaf total conductance in real time to obtain the leaf total conductance prediction value, that is, step S200 specifically includes:

[0082] S210. Determine the abscisic acid concentration influence factor according to the abscisic acid concentration, soil water content and soil salinity of the plant;

[0083] S220. Determine the environmental influence factor according to the light intensity, air relative humidity, atmospheric carbon dioxide concentration and air temperature;

[0084] S230. Determine the leaf boundary layer conductance according to the wind speed and leaf characteristic length;

[0085] S240. Based on a preset leaf total conductance prediction model, use the leaf stomatal conductance, abscisic acid concentration influence factor, environmental influence factor and leaf boundary layer conductance of the current plant as input features to predict the leaf total conductance in real time and output the leaf total conductance prediction value.

[0086] In step S210, the abscisic acid concentration influencing factor is determined by the current abscisic acid concentration of the plant, the soil water content, and the soil salt content. Among them, abscisic acid is a key hormone in plants that responds to adversity (such as drought and salt stress). It induces stomatal closure, thereby affecting leaf stomatal conductance. The soil water content and soil salt content not only directly affect the magnitude of leaf stomatal conductance but also indirectly affect the magnitude of leaf stomatal conductance by influencing the concentration of abscisic acid. Therefore, by integrating information such as abscisic acid concentration, soil water content, and soil salt content, the leaf stomatal conductance can be corrected to ensure a more accurate prediction of the total leaf conductance.

[0087] In step S220, the environmental influencing factor is determined by light intensity, relative air humidity, atmospheric carbon dioxide concentration, and air temperature. Among them, leaf stomatal conductance is positively correlated with light intensity, positively correlated with relative air humidity, negatively correlated with atmospheric carbon dioxide concentration, and related to air temperature but not linearly. The stronger the light intensity, the greater the leaf stomatal conductance; the greater the relative air humidity, the greater the leaf stomatal conductance; when the atmospheric carbon dioxide concentration increases, the leaf stomatal conductance decreases; within the appropriate temperature range, the leaf stomatal conductance increases with the increase in temperature, but when the temperature is too high, the leaf stomatal conductance will instead decrease. Therefore, by integrating information such as light intensity, relative air humidity, atmospheric carbon dioxide concentration, and air temperature, the leaf stomatal conductance can be corrected to ensure a more accurate prediction of the total leaf conductance.

[0088] Specifically, the calculation formulas for the environmental influencing factor and the abscisic acid concentration influencing factor are as follows:

[0089] ;

[0090] ;

[0091] In the formula, f e is the environmental influencing factor; f a is the abscisic acid concentration influencing factor; C A is the current abscisic acid concentration of the plant; W s is the soil water content; C s is the soil salt content; R L is the ratio of the average light intensity within a certain future time t to the current light intensity; R RH is the ratio of the average relative air humidity within a certain future time t to the current relative air humidity; R T is the ratio of the average air temperature within a certain future time t to the current air temperature; R CCis the ratio of the average atmospheric carbon dioxide concentration over a certain future time period \(t\) to the current atmospheric carbon dioxide concentration; wherein, the average light intensity, average relative air humidity, average air temperature, and average atmospheric carbon dioxide concentration over a certain future time period \(t\) can all obtain real-time data and prediction data through meteorological stations and satellite remote sensing, and the average value is calculated using the integration method; \(w1\), \(w2\), \(w3\), \(w4\), \(w5\), and \(a\) are all empirical constants, which can be determined according to specific plant types, and the optimal values are determined through a deep learning model.

[0092] In step S230, the leaf boundary layer conductance refers to the ease of gas (such as carbon dioxide and water vapor) diffusion through the boundary layer near the leaf surface; the leaf boundary layer conductance is affected by factors such as wind speed and leaf shape; generally speaking, the greater the wind speed, the thinner the boundary layer, the higher the leaf boundary layer conductance, and the easier the gas exchange; there is a synergistic effect between the leaf boundary layer conductance and the leaf stomatal conductance, jointly affecting the transpiration rate of plants.

[0093] Specifically, the calculation formula for the leaf boundary layer conductance is as follows:

[0094] ;

[0095] In the formula, \(D\) b is the leaf boundary layer conductance; \(d\) is the leaf characteristic length; \(u\) is the wind speed; \(k\) is an empirical constant, generally taking a value of 0.147.

[0096] In step S240, the method for constructing the leaf total conductance prediction model is as follows: Obtain historical information data, and according to the historical information data, determine the historical leaf boundary layer conductance, abscisic acid concentration influencing factor, and environmental influencing factor using the above method; use the historical leaf stomatal conductance, leaf boundary layer conductance, abscisic acid concentration influencing factor, and environmental influencing factor as input features, and perform model training and optimization based on a Bayesian neural network and a loss function containing a physical constraint term (ensuring that the predicted value of the leaf total conductance conforms to the Penman-Monteith equation) to construct a leaf total conductance prediction model, and evaluate and verify the above model using the coupling error between the predicted leaf total conductance and the predicted transpiration rate as an evaluation index.

[0097] In a preferred embodiment of the present invention, as Figure 3 shown, the steps of determining the predicted transpiration rate of the plant based on the predicted value of the leaf total conductance and real-time predicting the water requirement of the plant, that is, step S300 specifically includes:

[0098] S310. Determine the water vapor pressure inside the leaf according to the leaf temperature;

[0099] S320. Determine the air water vapor pressure according to the relative air humidity and air temperature;

[0100] S330. Determine the predicted transpiration rate of the plant according to the predicted total leaf conductance, the vapor pressure inside the leaf, the vapor pressure of the air, and the atmospheric pressure;

[0101] S340. Predict the water requirement of the plant in real time according to the predicted transpiration rate of the plant.

[0102] Specifically, the calculation formula for the predicted transpiration rate is as follows:

[0103] ;

[0104] In the formula, Tr is the predicted transpiration rate of the plant; D t is the predicted total leaf conductance; e i is the vapor pressure inside the leaf; e a is the vapor pressure of the air; P is the atmospheric pressure.

[0105] The vapor pressure inside the leaf can be regarded as equal to the saturated vapor pressure at the leaf temperature; specifically, it can be calculated according to the leaf temperature, and the saturated vapor pressure at the leaf temperature can be calculated through the Magnus formula as the vapor pressure inside the leaf;

[0106] The vapor pressure of the air can be obtained through the relative air humidity RH and the air temperature T a The calculation formula for the vapor pressure of the air is as follows:

[0107] ;

[0108] In the formula, RH is the relative air humidity; T a is the air temperature; is the saturated vapor pressure at the air temperature, which can be calculated according to the current air temperature through the Magnus formula.

[0109] In a preferred embodiment of the present invention, the step of predicting the water requirement of the plant in real time according to the predicted transpiration rate of the plant specifically includes:

[0110] Obtain the surface projection area of the garden to be irrigated and the total single-sided leaf area of the plant, and determine the leaf area index according to the surface projection area of the irrigated garden and the total single-sided leaf area of the plant;

[0111] Predict the water requirement of the plant in real time according to the predicted transpiration rate of the plant and the leaf area index.

[0112] Specifically, the prediction formula for the water requirement of the plant is as follows:

[0113] ;

[0114] ;

[0115] Wherein, W p is the predicted value of the water requirement of plants within a certain future time t; Tr is the predicted value of the transpiration rate of plants; L is the leaf area index; A l is the total single-sided area of the leaves of the plants; A g is the surface projection area of the garden to be sprinkler-irrigated; the leaf area index can be obtained by collecting the leaves within a certain surface projection area and then measuring the single-sided area of the leaves; or the leaf area index can be determined by the light transmission principle measurement method, multi-spectral or hyperspectral remote sensing data.

[0116] In a preferred embodiment of the present invention, as Figure 4 shown, the steps of predicting the soil evaporation amount in real time based on a preset soil evaporation amount prediction model, that is, step S400 specifically includes:

[0117] S410. Determine the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity and soil depth;

[0118] S420. Determine the sensible heat flux factor according to the surface temperature, air temperature and wind speed;

[0119] S430. Based on the preset soil evaporation amount prediction model, use the light intensity, leaf area index, soil heat flux factor and sensible heat flux factor as input features to predict the soil evaporation amount in real time.

[0120] It should be noted that the soil evaporation amount is actually the amount of water lost from the soil surface to the atmosphere through physical evaporation. In practical applications, the soil heat flux refers to the heat exchange amount between the ground surface and the soil, which is related to the soil temperature gradient, soil thermal conductivity and soil depth, etc.; the sensible heat flux refers to the turbulent heat exchange amount between the ground surface and the atmosphere, which is related to the surface temperature, air temperature, wind speed, air density and air specific heat capacity, etc.; according to the existing energy balance equation, the soil heat flux, sensible heat flux and net radiation are related to the bare soil evaporation amount (the amount of water lost from the soil surface without vegetation cover to the atmosphere through physical evaporation), and the net radiation is positively correlated with the light intensity; therefore, according to the light intensity, soil heat flux factor and sensible heat flux factor, the bare soil evaporation amount can be predicted; in addition, since the soil in the garden belongs to the soil with vegetation, and for the soil with vegetation, the influence of vegetation coverage on the soil evaporation amount needs to be considered. Generally, the vegetation coverage is determined by the leaf area index. Therefore, in the embodiments of the present invention, by introducing the leaf area index and combining the light intensity, soil heat flux factor and sensible heat flux factor, the soil evaporation amount can be accurately predicted.

[0121] Specifically, the method for constructing the soil evaporation prediction model is as follows: Using historical light intensity, leaf area index, soil heat flux factor, and sensible heat flux factor as input features, the random forest algorithm is used for model training to construct the soil evaporation prediction model.

[0122] In a preferred embodiment of the present invention, as Figure 5 shown, the steps of predicting the residual leaf moisture evaporation amount in real time based on the preset residual leaf moisture evaporation prediction model, that is, step S500 specifically includes:

[0123] S510. Obtain the current sprinkler irrigation process in real time; the sprinkler irrigation process includes the sprinkler irrigation angle, spraying speed, and sprinkler irrigation flow rate;

[0124] S520. Determine the distance of the sprinkler water mist landing point according to the current sprinkler irrigation angle, spraying speed, and wind speed;

[0125] S530. Determine the leaf water absorption factor according to the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity;

[0126] S540. Based on the preset residual leaf moisture evaporation prediction model, use the sprinkler irrigation flow rate, the distance of the sprinkler water mist landing point, and the leaf water absorption factor as input features to predict the residual leaf moisture evaporation amount in real time.

[0127] It should be noted that for garden sprinkler irrigation, since the soil in the garden is relatively closed, the water for sprinkler irrigation, except for falling on the surface of plant leaves, will basically enter the soil and will not flow out; in addition, a small part of the water falling on the surface of plant leaves will enter the plant body through the stomata on the leaf surface (most of the water on the leaf surface will evaporate and be lost, only a small part will diffuse into the plant body through the stomata on the leaf surface) and be absorbed by the plant. The absorption amount is affected by the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity. Therefore, it can be evaluated by the leaf water absorption factor; while the remaining part will be lost due to physical evaporation, and the amount of this part of the loss is the residual leaf moisture evaporation amount; therefore, the loss amount of sprinkler irrigation includes not only the soil evaporation amount but also the residual leaf moisture evaporation amount. When predicting the required sprinkler irrigation amount in the future, these two parts of the loss need to be considered.

[0128] In step S520, the distance of the sprinkler water mist landing point refers to the distance between the geometric center point of the sprinkler water mist and the nozzle, which, together with the sprinkler flow rate, will jointly affect the amount of water falling on the leaf surface during sprinkler irrigation. Of course, the total leaf area (twice the total area of one side of the leaf) will also affect the amount of water falling on the leaf surface during sprinkler irrigation, so it can also be used as an input feature for model training. However, generally, since the change in the total leaf area within a short period is small, the influence of the total leaf area on the prediction result of the evaporation amount of the remaining water on the leaves can be ignored. The distance of the sprinkler water mist landing point can be obtained based on the sprinkler angle θ0, the ejection speed v0, the wind speed u, and the angle β (0° ≤ β ≤ 180°) between the wind direction and the ejection direction. The specific calculation formula is as follows:

[0129] ;

[0130] In the formula, x is the distance of the sprinkler water mist landing point; θ0 is the sprinkler angle; v0 is the ejection speed; u is the wind speed; β is the angle between the wind direction and the ejection direction, 0° ≤ β ≤ 180°; λ is the wind speed correction coefficient (empirical value), which is related to the nozzle type, water droplet size, water droplet density, etc.; g is the acceleration due to gravity.

[0131] Specifically, the construction method of the prediction model for the evaporation amount of the remaining water on the leaves is as follows: Using the historical sprinkler flow rate, the distance of the sprinkler water mist landing point, and the leaf water absorption amount factor as input features, and adopting the random forest algorithm for model training to construct a prediction model for the evaporation amount of the remaining water on the leaves.

[0132] In step S600, when predicting the required sprinkler irrigation amount, the influence of precipitation generally needs to be considered, and the precipitation can be predicted through a weather station. Specifically, the prediction formula for the required sprinkler irrigation amount is as follows:

[0133] ;

[0134] In the formula, W p is the predicted value of the plant water requirement within a certain future time t; W e is the predicted value of the soil evaporation amount within a certain future time t, which is predicted through the above soil evaporation amount prediction model; W l is the predicted value of the evaporation amount of the remaining water on the leaves within a certain future time t, which is predicted through the above prediction model for the evaporation amount of the remaining water on the leaves; W r is the predicted value of the precipitation within a certain future time t.

[0135] In practical applications, by predicting the required sprinkler irrigation amount within a certain future time t in real time, the sprinkler irrigation processes such as the sprinkler flow rate, the sprinkler irrigation time, the sprinkler angle, and the ejection speed can be dynamically adjusted in real time to avoid phenomena such as over-irrigation or under-irrigation, so as to achieve the purpose of saving water resources and energy.

[0136] Such asFigure 6 As shown in the figure, in another embodiment of the present invention, an automatic sprinkler irrigation system for a garden is further provided to implement the above automatic sprinkler irrigation method, specifically including:

[0137] A garden information acquisition module 10, configured to acquire the soil state information, environmental meteorological information, and plant physiological information of the garden to be sprinkler-irrigated in real time; the plant physiological information includes: leaf stomatal conductance, leaf characteristic length, and abscisic acid concentration;

[0138] A leaf total conductance prediction module 20, configured to predict the leaf total conductance in real time based on a preset leaf total conductance prediction model according to the soil state information, environmental meteorological information, and plant physiological information, and obtain a leaf total conductance prediction value;

[0139] A plant water requirement prediction module 30, configured to determine a predicted transpiration rate value of the plant according to the leaf total conductance prediction value and predict the plant water requirement in real time;

[0140] A soil evaporation prediction module 40, configured to predict the soil evaporation in real time based on a preset soil evaporation prediction model; the soil evaporation refers to the amount of water lost from the soil due to water evaporation;

[0141] A leaf residual water evaporation prediction module 50, configured to predict the leaf residual water evaporation in real time based on a preset leaf residual water evaporation prediction model; the leaf residual water evaporation refers to the residual amount of water on the surface of the plant leaves after a part of the water falling on the leaves during sprinkler irrigation is absorbed by the leaves;

[0142] A sprinkler irrigation process adjustment module 60, configured to determine the required sprinkler irrigation amount according to the plant water requirement, soil evaporation, and leaf residual water evaporation predicted in real time, and dynamically adjust the sprinkler irrigation process in real time.

[0143] In a preferred embodiment of the present invention, as Figure 7 shown, the leaf total conductance prediction module 20 specifically includes:

[0144] An abscisic acid concentration influence factor determination unit 21, configured to determine an abscisic acid concentration influence factor according to the abscisic acid concentration, soil water content, and soil salinity of the plant;

[0145] An environmental influence factor determination unit 22, configured to determine an environmental influence factor according to the light intensity, air relative humidity, atmospheric carbon dioxide concentration, and air temperature;

[0146] A leaf boundary layer conductance determination unit 23, configured to determine the leaf boundary layer conductance according to the wind speed and leaf characteristic length;

[0147] The total leaf conductance prediction unit 24 is configured to, based on a preset total leaf conductance prediction model, use the leaf stomatal conductance, abscisic acid concentration influencing factor, environmental influencing factor, and leaf boundary layer conductance of the current plant as input features to predict the total leaf conductance in real time and output a predicted value of the total leaf conductance.

[0148] In a preferred embodiment of the present invention, as Figure 8 shown, the plant water requirement prediction module 30 specifically includes:

[0149] The internal water vapor pressure determination unit 31 is configured to determine the internal water vapor pressure of the leaf according to the leaf temperature;

[0150] The air water vapor pressure determination unit 32 is configured to determine the air water vapor pressure according to the air relative humidity and air temperature;

[0151] The transpiration rate predicted value determination unit 33 is configured to determine a predicted value of the plant transpiration rate according to the predicted value of the total leaf conductance, the internal water vapor pressure of the leaf, the air water vapor pressure, and the atmospheric pressure;

[0152] The plant water requirement prediction unit 34 is configured to predict the plant water requirement in real time according to the predicted value of the plant transpiration rate.

[0153] In a preferred embodiment of the present invention, as Figure 9 shown, the soil evaporation prediction module 40 specifically includes:

[0154] The soil heat flux factor determination unit 41 is configured to determine the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity, and soil depth;

[0155] The sensible heat flux factor determination unit 42 is configured to determine the sensible heat flux factor according to the surface temperature, air temperature, and wind speed;

[0156] The soil evaporation prediction unit 43 is configured to, based on a preset soil evaporation prediction model, use the light intensity, leaf area index, soil heat flux factor, and sensible heat flux factor as input features to predict the soil evaporation in real time;

[0157] In a preferred embodiment of the present invention, as Figure 10 shown, the leaf residual water evaporation prediction module 50 specifically includes:

[0158] The sprinkler irrigation process acquisition unit 51 is configured to acquire the current sprinkler irrigation process in real time; the sprinkler irrigation process includes the sprinkler irrigation angle, spraying speed, and sprinkler irrigation flow rate;

[0159] The sprinkler water droplet landing distance determination unit 52 is configured to determine the sprinkler water droplet landing distance according to the current sprinkler irrigation angle, spraying speed, and wind speed;

[0160] The leaf water absorption factor determination unit 53 is configured to determine the leaf water absorption factor according to the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity;

[0161] The leaf residual water evaporation prediction unit 54 is configured to, based on a preset leaf residual water evaporation prediction model, use the sprinkler irrigation flow rate, the distance of the sprinkler water droplet landing point, and the leaf water absorption factor as input features to predict the leaf residual water evaporation amount in real time.

[0162] It should be noted that the above-mentioned modules and units can be implemented in the form of a computer program. The computer program can run on a computer device. The computer program constituting each module can be stored in the memory of the computer device so that the processor executes each step of the above method.

[0163] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps.

[0164] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to the memory, storage, database, or other media used in the embodiments provided in the present application can include non-volatile and / or volatile memories.

[0165] The above-mentioned embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the patent of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. An automatic sprinkler irrigation method for a garden, characterized in that, It includes the following steps: Obtain the soil state information, environmental meteorological information, and plant physiological information of the garden to be sprinkler-irrigated in real time; The plant physiological information includes: leaf stomatal conductance, leaf characteristic length, and abscisic acid concentration; Based on a preset leaf total conductance prediction model, according to the soil state information, environmental meteorological information, and plant physiological information, predict the leaf total conductance in real time to obtain the predicted value of the leaf total conductance; According to the predicted value of the leaf total conductance, determine the predicted value of the plant transpiration rate and predict the plant water requirement in real time; Based on a preset soil evaporation prediction model, predict the soil evaporation in real time; the soil evaporation refers to the amount of water lost from the soil due to water evaporation; Based on a preset leaf residual water evaporation prediction model, predict the leaf residual water evaporation in real time; the leaf residual water evaporation refers to the residual amount of water on the surface of the plant leaves after part of the water falling on the leaves during sprinkler irrigation is absorbed by the leaves; According to the plant water requirement, soil evaporation, and leaf residual water evaporation predicted in real time, determine the required sprinkler irrigation amount and dynamically adjust the sprinkler irrigation process in real time.

2. The automatic sprinkler method for a garden according to claim 1, characterized in that, The soil state information includes soil water content and soil salinity; the environmental meteorological information includes wind speed, light intensity, air relative humidity, atmospheric carbon dioxide concentration, and air temperature; the step of predicting the leaf total conductance in real time based on a preset leaf total conductance prediction model according to the soil state information, environmental meteorological information, and plant physiological information specifically includes: Determine the abscisic acid concentration influencing factor according to the abscisic acid concentration, soil water content, and soil salinity of the plant; Determine the environmental influencing factor according to the light intensity, air relative humidity, atmospheric carbon dioxide concentration, and air temperature; Determine the leaf boundary layer conductance according to the wind speed and leaf characteristic length; Based on a preset leaf total conductance prediction model, use the leaf stomatal conductance, abscisic acid concentration influencing factor, environmental influencing factor, and leaf boundary layer conductance of the current plant as input features to predict the leaf total conductance in real time and output the predicted value of the leaf total conductance.

3. The automatic sprinkler irrigation method for a garden according to claim 2, wherein The plant physiological information further includes leaf temperature; the environmental meteorological information further includes atmospheric pressure; the step of determining the predicted value of the plant transpiration rate according to the predicted value of the leaf total conductance and predicting the plant water requirement in real time specifically includes: Determine the internal leaf water vapor pressure according to the leaf temperature; Determine the air water vapor pressure according to the air relative humidity and air temperature; Determine the predicted value of the plant transpiration rate according to the predicted value of the leaf total conductance, internal leaf water vapor pressure, air water vapor pressure, and atmospheric pressure; Predict the plant water requirement in real time according to the predicted value of the plant transpiration rate.

4. The automatic sprinkler method for a garden according to claim 3, characterized in that, The step of predicting the plant water requirement in real time according to the predicted value of the plant transpiration rate specifically includes: Obtain the surface projection area of the garden to be sprinkler-irrigated and the total single-sided area of the plant leaves, and determine the leaf area index according to the surface projection area of the garden to be sprinkler-irrigated and the total single-sided area of the plant leaves; Predict the plant water requirement in real time according to the predicted value of the plant transpiration rate and the leaf area index.

5. The automatic sprinkler irrigation method for a garden according to claim 4, characterized in that, The soil state information further includes surface temperature, soil temperature gradient, soil thermal conductivity, and soil depth; the steps of predicting the soil evaporation rate in real time based on a preset soil evaporation rate prediction model specifically include: Determine the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity, and soil depth; Determine the sensible heat flux factor according to the surface temperature, air temperature, and wind speed; Based on the preset soil evaporation rate prediction model, use the light intensity, leaf area index, soil heat flux factor, and sensible heat flux factor as input features to predict the soil evaporation rate in real time.

6. The automatic sprinkler irrigation method for a garden according to claim 4, wherein The steps of predicting the residual water evaporation rate of leaves in real time based on a preset residual water evaporation rate prediction model of leaves specifically include: Obtain the current sprinkler irrigation process in real time; the sprinkler irrigation process includes the sprinkler irrigation angle, spraying speed, and sprinkler irrigation flow rate; Determine the distance of the sprinkler water mist landing point according to the current sprinkler irrigation angle, spraying speed, and wind speed; Determine the leaf water absorption factor according to the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity; Based on the preset residual water evaporation rate prediction model of leaves, use the sprinkler irrigation flow rate, the distance of the sprinkler water mist landing point, and the leaf water absorption factor as input features to predict the residual water evaporation rate of leaves in real time.

7. An automatic sprinkler system for a garden, which is used to implement the automatic sprinkler method described in any one of claims 1-6, and is characterized in that, Including: A garden information acquisition module for acquiring the soil state information, environmental meteorological information, and plant physiological information of the garden to be sprinkler irrigated in real time; The plant physiological information includes: leaf stomatal conductance, leaf characteristic length, and abscisic acid concentration; A leaf total conductance prediction module for predicting the leaf total conductance in real time based on a preset leaf total conductance prediction model according to the soil state information, environmental meteorological information, and plant physiological information to obtain a leaf total conductance prediction value; A plant water demand prediction module for determining a transpiration rate prediction value of the plant according to the leaf total conductance prediction value and predicting the plant water demand in real time; A soil evaporation rate prediction module for predicting the soil evaporation rate in real time based on a preset soil evaporation rate prediction model; the soil evaporation rate refers to the amount of water lost from the soil due to water evaporation; A residual water evaporation rate prediction module of leaves for predicting the residual water evaporation rate of leaves in real time based on a preset residual water evaporation rate prediction model of leaves; the residual water evaporation rate of leaves refers to the residual amount after the water falling on the surface of the plant leaves during sprinkler irrigation is absorbed by the leaves; A sprinkler irrigation process adjustment module for determining the required sprinkler irrigation amount according to the plant water demand, soil evaporation rate, and residual water evaporation rate of leaves predicted in real time and dynamically adjusting the sprinkler irrigation process in real time.

8. The automatic sprinkler system for a garden according to claim 7, characterized in that, The soil state information includes soil water content and soil salt content; the environmental meteorological information includes wind speed, light intensity, air relative humidity, atmospheric carbon dioxide concentration, and air temperature; the leaf total conductance prediction module specifically includes: An abscisic acid concentration influence factor determination unit for determining the abscisic acid concentration influence factor according to the abscisic acid concentration of the plant, soil water content, and soil salt content; An environmental influence factor determination unit for determining the environmental influence factor according to the light intensity, air relative humidity, atmospheric carbon dioxide concentration, and air temperature; The leaf boundary layer conductance determination unit is used to determine the leaf boundary layer conductance according to the wind speed and the leaf characteristic length; The total leaf conductance prediction unit is used to, based on a preset total leaf conductance prediction model, take the leaf stomatal conductance, abscisic acid concentration influencing factor, environmental influencing factor, and leaf boundary layer conductance of the current plant as input features, and predict the total leaf conductance in real time, and output the total leaf conductance prediction value.

9. The automatic sprinkler system for a garden according to claim 8, characterized in that, The plant physiological information further includes the leaf temperature; the environmental meteorological information further includes the atmospheric pressure; the plant water requirement prediction module specifically includes: The internal water vapor pressure determination unit is used to determine the internal water vapor pressure of the leaf according to the leaf temperature; The air water vapor pressure determination unit is used to determine the air water vapor pressure according to the air relative humidity and the air temperature; The transpiration rate prediction value determination unit is used to determine the plant transpiration rate prediction value according to the total leaf conductance prediction value, the internal water vapor pressure of the leaf, the air water vapor pressure, and the atmospheric pressure; The plant water requirement prediction unit is used to predict the plant water requirement in real time according to the plant transpiration rate prediction value.

10. The automatic sprinkler system for a garden according to claim 9, characterized in that, The soil state information further includes the surface temperature, soil temperature gradient, soil thermal conductivity, and soil depth; the soil evaporation prediction module specifically includes: The soil heat flux factor determination unit is used to determine the soil heat flux factor according to the soil temperature gradient, soil thermal conductivity, and soil depth; The sensible heat flux factor determination unit is used to determine the sensible heat flux factor according to the surface temperature, air temperature, and wind speed; The soil evaporation prediction unit is used to, based on a preset soil evaporation prediction model, take the light intensity, leaf area index, soil heat flux factor, and sensible heat flux factor as input features, and predict the soil evaporation in real time; The leaf residual water evaporation prediction module specifically includes: The sprinkler irrigation process acquisition unit is used to acquire the current sprinkler irrigation process in real time; the sprinkler irrigation process includes the sprinkler irrigation angle, spraying speed, and sprinkler irrigation flow rate; The sprinkler water mist landing point distance determination unit is used to determine the sprinkler water mist landing point distance according to the current sprinkler irrigation angle, spraying speed, and wind speed; The leaf water absorption amount factor determination unit is used to determine the leaf water absorption amount factor according to the leaf stomatal conductance, leaf temperature, air temperature, and air relative humidity; The leaf residual water evaporation prediction unit is used to, based on a preset leaf residual water evaporation prediction model, take the sprinkler irrigation flow rate, sprinkler water mist landing point distance, and leaf water absorption amount factor as input features, and predict the leaf residual water evaporation in real time.

Images