Urban vegetable garden three-dimensional cultivation intelligent water and fertilizer regulation and control system and method based on internet of things

Abstract

The application provides an urban vegetable garden three-dimensional cultivation intelligent water and fertilizer regulation system and method based on the Internet of Things, and relates to the technical field of agricultural management. The system collects and analyzes the layered soil moisture content data, the environmental light intensity data of each layer, and the crop leaf area index data at different time points in the target monitoring time period, establishes a vertical water migration model and a light attenuation calculation method, and then realizes the precise control of differentiated irrigation and non-uniform light supplement. In this way, the utilization efficiency of water and fertilizer resources and the balance of crop growth environment can be improved, which helps to optimize the crop growth conditions, thereby improving the crop yield and quality, while reducing water resource waste and energy consumption.

Description

Technical Field

[0001] This invention relates to the field of agricultural management technology, and more specifically, to an intelligent water and fertilizer regulation system and method for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things. Background Technology

[0002] Urban vegetable gardens, as a new agricultural model, utilize vertical cultivation technology to achieve multi-level and multi-dimensional crop planting within a limited space, improving land use efficiency. However, traditional urban vegetable garden cultivation relies heavily on manual experience in water and fertilizer management and environmental control. This approach is not only inefficient but may also lead to water waste, low fertilizer utilization, and uneven environmental conditions, which are detrimental to healthy crop growth and high-efficiency production. With the rapid development of Internet of Things (IoT) technology, data acquisition and precision control technologies based on sensor networks are gradually being applied to agricultural production, providing new solutions for the intelligent and refined management of urban vegetable gardens.

[0003] While existing vertical farming systems for urban vegetable gardens have incorporated IoT technology to some extent, enabling remote monitoring and automated operation, several shortcomings remain in key technological areas. First, soil moisture monitoring is often limited to single-layer or average value collection, failing to accurately reflect the moisture status of soil in each layer of the vertical structure. This leads to irrational irrigation water allocation, failing to meet the actual needs of different crop levels. Second, regarding light control, most systems rely solely on monitoring overall light intensity and uniform supplemental lighting strategies, neglecting the attenuation of light intensity with height within the vertical structure. This extensive supplemental lighting not only increases energy consumption but may also lead to an uneven crop growth environment. Furthermore, integrated water and fertilizer management often employs fixed parameter control, lacking the ability to dynamically adjust based on crop growth needs, easily resulting in wasted water and fertilizer resources and insufficient nutrient supply to crops. These shortcomings severely restrict the resource utilization efficiency and crop production performance of vertical farming systems for urban vegetable gardens. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention is proposed. This invention provides an intelligent water and fertilizer regulation system and method for three-dimensional urban vegetable garden cultivation based on the Internet of Things (IoT). This system can, to a certain extent, solve the problems in multi-layered three-dimensional cultivation structures where gravity and soil inhomogeneity cause rapid downward infiltration of irrigation water from the upper layer, resulting in excessive moisture in the lower soil layer and insufficient moisture in the upper soil layer. Simultaneously, the shading effect leads to insufficient sunlight for the lower crops, ultimately causing significant differences in crop yield and quality.

[0005] According to one aspect of the present invention, an intelligent water and fertilizer control system for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things is provided, comprising:

[0006] The data acquisition module is used to collect layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data for vertical cultivation in urban vegetable gardens, and uploads the data to a cloud database through IoT sensors.

[0007] The water transport modeling module is used to establish a vertical water transport model based on stratified soil moisture content data. By calculating the water infiltration rate between adjacent layers, the differentiated irrigation water replenishment amount of each soil layer can be obtained.

[0008] The light compensation calculation module is used to calculate the light attenuation coefficient based on the ambient light intensity data and crop leaf area index data of each layer, and to determine the non-uniform start-up and shutdown sequence of the supplementary lighting equipment of each layer based on the light attenuation coefficient.

[0009] The environmental control execution module is used to convert the differentiated irrigation water supply into control parameters for each layer of integrated water and fertilizer equipment, and to control the supplemental lighting equipment for each layer according to the non-uniform start-stop sequence.

[0010] Furthermore, the water transport modeling module fits the measured soil moisture data obtained by the data acquisition module to obtain a water characteristic curve, thereby obtaining the hydraulic parameter function and establishing a vertical water transport model based on the Richards equation.

[0011] The hydraulic parameter functions include the unsaturated hydraulic conductivity function and the soil moisture diffusivity function obtained by applying the chain rule.

[0012] Furthermore, the soil moisture diffusivity function can be expressed by the following formula:

[0013] ;

[0014] in, Soil moisture diffusivity, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, This refers to the volumetric water content. Residual moisture content saturated moisture content As the matrix potential, For the scale parameters of the van Genuchten model, The shape parameters of the van Genuchten model. For the van Genuchten model coupling parameters, Porosity distribution index For regularization parameters, As a correction factor, It is in a saturated state. This is the residual state.

[0015] Furthermore, the water infiltration rate between adjacent layers is calculated using the soil moisture content distribution at any time and location obtained from the vertical water transport model;

[0016] The theoretical water replenishment amount is obtained by calculating the difference between the current soil moisture content and the target moisture content of each soil layer. Then, it is corrected according to the water infiltration rate between the adjacent layers to finally determine the differentiated irrigation water replenishment amount.

[0017] Furthermore, the water penetration time is calculated based on the water infiltration rate between adjacent layers, the water penetration rate and thickness of each soil layer are used to make corrections, the set irrigation duration is compared with the penetration time, and the amount of infiltrated water that each soil layer can receive from top to bottom is calculated layer by layer. Finally, the actual water replenishment of each layer is the theoretical water replenishment requirement minus the infiltration replenishment of the upper layer.

[0018] Furthermore, the light compensation calculation module obtains an initial attenuation model based on the Beer-Lambert law and linear regression analysis using the ambient light intensity data and crop leaf area index data;

[0019] By using the leaf aggregation parameter to correct the error caused by the uneven distribution of leaves in the initial attenuation model, a light intensity attenuation model is obtained.

[0020] The light intensity attenuation model is used to predict the light intensity at any height.

[0021] Furthermore, the light intensity attenuation model can be expressed by the following formula:

[0022] ;

[0023] in,

[0024] ;

[0025] ;

[0026] in, The light intensity at a distance of z meters from the top of the canopy. The intensity of incident light at the top of the canopy. Based on the extinction coefficient, Leaf area index, This is the leaf aggregation coefficient. This is the vertical distribution correction function. For the height compensation coefficient, The total height of the canopy. The vertical distance from the top of the canopy. Let be the leaf area index of the i-th layer. Let be the light intensity of the i-th layer. This is a parameter for the uniformity of leaf distribution. The leaf density response coefficient, The number of blades per unit area. This is the baseline coefficient for the vertical distribution. It is a high decay index. This represents the spatial decay rate.

[0027] According to another aspect of the present invention, a smart water and fertilizer regulation method for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things is provided, comprising:

[0028] Collect layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data for the three-dimensional cultivation of the urban vegetable garden, and upload the layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data to the cloud database through IoT sensors;

[0029] Based on the stratified soil moisture content data, a vertical water transport model was established, and the differentiated irrigation water replenishment amount of each soil layer was obtained by calculating the water infiltration rate between adjacent layers.

[0030] Based on the ambient light intensity data of each layer and the crop leaf area index data, the light attenuation coefficient is calculated, and the non-uniform start-up and shutdown sequence of the supplementary lighting equipment in each layer is determined based on the light attenuation coefficient.

[0031] The differentiated irrigation water supply is converted into control parameters for each layer of integrated water and fertilizer equipment, and the supplementary lighting equipment for each layer is controlled according to the non-uniform start-stop sequence.

[0032] Compared with existing technologies, the intelligent water and fertilizer regulation system and method for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things provided by this invention collects and analyzes stratified soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data at different time points within the target monitoring period. It then establishes a vertical water transport model and a light attenuation calculation method, thereby achieving precise control of differentiated irrigation and non-uniform lighting. This significantly improves the utilization efficiency of water and fertilizer resources and the balance of the crop growth environment, helping to optimize crop growth conditions, thereby increasing crop yield and quality, while reducing water waste and energy consumption. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0034] Figure 1 This is a system block diagram of an intelligent water and fertilizer regulation system for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things, according to an embodiment of the present invention.

[0035] Figure 2 This is a schematic diagram of the soil moisture characteristic curve obtained by fitting the van Genuchten model in the IoT-based intelligent water and fertilizer regulation system for three-dimensional cultivation of urban vegetable gardens according to an embodiment of the present invention. Detailed Implementation

[0036] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0037] Figure 1 This is a system block diagram of an intelligent water and fertilizer control system for vertical cultivation of urban vegetable gardens based on the Internet of Things, according to an embodiment of the present invention. Figure 1 As shown, the IoT-based intelligent water and fertilizer control system for integrated urban vegetable garden cultivation includes:

[0038] The data acquisition module is used to collect data on the layered soil moisture content, ambient light intensity of each layer, and crop leaf area index of the three-dimensional cultivation of urban vegetable gardens, and uploads the data to the cloud database through IoT sensors.

[0039] The water transport modeling module is used to establish a vertical water transport model based on stratified soil moisture content data. By calculating the water infiltration rate between adjacent layers, the differentiated irrigation water replenishment amount of each soil layer can be obtained.

[0040] The light compensation calculation module is used to calculate the light attenuation coefficient based on the ambient light intensity data and crop leaf area index data of each layer, and to determine the non-uniform start-up and shutdown sequence of the supplementary lighting equipment in each layer based on the light attenuation coefficient.

[0041] The environmental control execution module is used to convert the differentiated irrigation water supply into control parameters for each layer of integrated water and fertilizer equipment, and to control the supplemental lighting equipment of each layer according to the non-uniform start-stop sequence, thereby achieving balanced control of the crop growth environment of each layer in the three-dimensional cultivation structure.

[0042] The data acquisition module collects various data from the vertical cultivation of urban vegetable gardens, specifically including: In each cultivation layer of the vertical cultivation system, capacitive soil moisture sensors embedded in the cultivation substrate collect layered soil moisture content data every 30 minutes. These sensors are vertically positioned at four depths in each cultivation layer: 0-5 cm, 5-10 cm, 10-15 cm, and 15-20 cm. Simultaneously, three measuring points are set at each depth horizontally, forming a monitoring grid. Photonic sensors installed at both ends of each cultivation rack collect ambient light intensity data for each layer every 10 minutes. The photosensitive surfaces of these sensors are parallel to the horizontal plane of the cultivation layer. The module also includes a plant canopy map. The mobile data acquisition device collects crop canopy images every 24 hours and uses image processing algorithms to calculate crop leaf area index data. The acquisition accuracy of stratified soil moisture content data is ±2%, the acquisition accuracy of ambient light intensity data for each layer is ±3μmol / m²·s, and the calculation accuracy of crop leaf area index data is ±0.1. The stratified soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data are uploaded to the cloud database in real time through IoT sensor nodes with MQTT protocol. The data transmission frequency of the IoT sensor nodes is once every 5 minutes. When the collected data is abnormal, the IoT sensor nodes automatically send an alarm message to the control center.

[0043] On the other hand, after acquiring the layered soil moisture content data collected by the IoT sensors, the water transport modeling module performs data preprocessing on the dynamic changes in soil moisture content over 24 hours, removing outliers and smoothing the data.

[0044] After data preprocessing, the measured data of matrix moisture content θ and matrix potential ψ collected by soil moisture sensors at each layer are used to analyze the data through van... The Genuchten model is fitted to obtain the soil moisture characteristic curve, which describes the functional relationship between matrix potential ψ and water content θ. Once the functional relationship is determined, the unsaturated hydraulic conductivity function K(θ) is derived according to Darcy's law. At the same time, the chain rule is used to transform the first derivative of matrix potential ψ with respect to spatial location into the first derivative with respect to water content θ, thereby obtaining the soil moisture diffusivity function D(θ). After the unsaturated hydraulic conductivity function K(θ) and the soil moisture diffusivity function D(θ) are determined, they are substituted into the one-dimensional vertical water movement equation in the Richards equation, and the finite difference method is used to solve it numerically, thereby establishing a vertical water transport model. If it is necessary to verify the accuracy of the vertical water transport model, the predicted values ​​of the model are compared with the measured layered soil moisture content data. When the prediction error is less than 5%, the vertical water transport model can be considered to be established. After the vertical water transport model is established, the water infiltration flux between adjacent cultivation layers can be calculated using this model.

[0045] Specifically, the chain rule is used to transform the first derivative of the matrix potential ψ with respect to spatial location into the first derivative with respect to water content θ, thereby obtaining the soil moisture diffusivity function as follows:

[0046] Based on the moisture characteristic curve obtained from the aforementioned van Genuchten model, the specific water capacity C(θ) is calculated using the numerical difference method. Specific water capacity C(θ) is expressed as the first derivative of the matrix potential ψ with respect to the water content θ. After obtaining the specific water capacity C(θ), according to the water potential gradient driving principle in Darcy's law, the partial derivative of the matrix potential ψ with respect to the spatial position z is expressed as the product of the specific water capacity C(θ) and the partial derivative of the water content θ with respect to the spatial position z, transforming the mathematical principle based on the chain rule. After completing the derivative transformation, multiplying the unsaturated hydraulic conductivity function K(θ) with the specific water capacity C(θ) yields the soil moisture diffusivity function D(θ), where D(θ) represents the soil medium's ability to diffuse water. Once the soil moisture diffusivity function D(θ) is determined, combined with the influence of gravity, the governing equation for vertical water transport can be rewritten in the form of water content θ as the dependent variable, thus simplifying the solution process of the water transport model. More specifically, the soil moisture diffusivity function can be expressed by the following formula:

[0047] ;

[0048] ;

[0049] in,

[0050] ;

[0051] in, Soil moisture diffusivity (cm² / h) The unsaturated hydraulic conductivity (cm / h) The saturated hydraulic conductivity (cm / h) The volumetric moisture content (cm³ / cm³) Residual moisture content (cm³ / cm³) The saturated moisture content is (cm³ / cm³). The matrix potential (cm) The scaling parameters (cm⁻¹) for the van Genuchten model. For the shape parameters (dimensionless) of the van Genuchten model, For the van Genuchten model coupling parameters, Pore ​​distribution index (dimensionless), This is a regularization parameter used to prevent the denominator from approaching zero. This is a correction factor used to avoid the problem of subtracting smaller numbers from larger ones. It is in a saturated state. This is the residual state.

[0052] Furthermore, the specific process of substituting the soil moisture diffusivity function D(θ) into the one-dimensional vertical water movement equation in the Richards equation and performing a numerical solution is as follows:

[0053] First, the one-dimensional vertical water movement equation is expressed as a hybrid form of the Richards equation. After obtaining the soil moisture diffusivity function D(θ), it is substituted into the equation to obtain the governing equation with water content θ as the dependent variable. To discretize this governing equation, a backward difference scheme in time and a central difference scheme in space are used, with a time step of 1 hour and a spatial step of 1 centimeter. After determining the computational grid, the water content of each grid node is iteratively calculated. When advancing the time layer, the Crank-Nicolson implicit difference scheme is used to improve computational stability. At the same time, the Picard iteration method is introduced to handle nonlinear terms. If the difference in water content between two adjacent iterations is less than a preset threshold of 10⁻, a condition is met. 6 When the iteration of the current time layer is considered to have converged, the time step is considered to be automatically reduced when the moisture content changes drastically and appropriately increased when the change is gradual. Finally, the soil moisture content distribution at any time and location can be obtained through this numerical solution scheme. That is, the calculation of the soil moisture content distribution can be expressed by the following formula:

[0054] ;

[0055] in,

[0056] ;

[0057] ;

[0058] in, Let (cm³ / cm³) be the Picard iteration value of the i-th spatial node at the (n+1)-th time level. Let be the water content (cm³ / cm³) of the i-th spatial node at the n-th time layer. The time step is (h). Spatial step size (cm) Residual moisture content (cm³ / cm³) The saturated moisture content is (cm³ / cm³). The saturated hydraulic conductivity (cm / h) The scaling parameters (cm⁻¹) for the van Genuchten model. For the shape parameters (dimensionless) of the van Genuchten model, Let m be the coupling parameters of the van Genuchten model, and m = 1 - 1 / n (dimensionless). The porosity distribution index is dimensionless.

[0059] Furthermore, based on the measured moisture content data of each soil profile layer, the difference between the current moisture content and the target moisture content (preferably 75% of field capacity) of each soil layer is calculated. Then, based on the soil moisture characteristic curve, the theoretical water replenishment required for each soil layer to reach the target moisture content from the current moisture content is calculated. After that, the water infiltration rate of each soil layer is corrected. When the infiltration rate of the upper soil layer is large, the actual water replenishment of the lower soil layer should be the difference between the theoretical water replenishment and the infiltration replenishment of the upper layer. Finally, based on the crop root distribution characteristics, the water replenishment of the soil located in the main root layer should be appropriately increased by 10-20% to meet the crop's water requirements, thus obtaining the final differentiated irrigation water replenishment for each soil layer.

[0060] The method for correction based on the water infiltration rate of each soil layer is as follows: Based on the calculated infiltration rate of each soil layer, the time required for water to penetrate each layer is calculated according to the infiltration rate and soil layer thickness. Then, based on the set irrigation duration, the amount of infiltrated water that each soil layer can receive from the upper layers is calculated. Starting from the uppermost soil layer, if the irrigation duration exceeds the time required for water to penetrate that layer, the amount of infiltrated water exceeding that time is calculated. The same method is then used to calculate the amount of infiltrated water that the second, third, and subsequent lower soil layers can receive. Finally, the total water replenishment for each soil layer is equal to the difference between the initially calculated theoretical water replenishment and the sum of the amount of infiltrated water that the layer can receive from the upper layers.

[0061] For example, taking strawberry cultivation in a three-layer vertical cultivation system as an example, this illustrates the determination of differentiated irrigation water replenishment: The top layer of soil, being directly exposed to the natural environment, experiences significant evaporation loss and strong crop transpiration, resulting in the fastest water consumption rate. When the moisture content of the top layer soil is detected to be lower than the target value, a high-frequency, low-dose irrigation strategy should be adopted, such as keeping each irrigation session short but with relatively short intervals. The middle layer, being shaded by the upper layer, experiences less evaporation loss and can receive some infiltrated water from the upper layer. Its irrigation water replenishment should be calculated based on the theoretical replenishment amount, minus the amount of water infiltrated from the upper layer. A medium-frequency irrigation strategy is adopted. The bottom layer of soil continuously receives water from the upper layer, and its actual water requirement is the least. Therefore, a low-frequency irrigation method with a slightly larger water volume per irrigation can be used, and the irrigation time should be extended to ensure that the water is fully absorbed by the soil. When the water infiltration rate of the upper soil is faster, the irrigation amount of the middle and lower layers should be reduced accordingly to prevent soil oversaturation. In case of high temperature, the irrigation frequency of each layer should be appropriately increased, but the difference in irrigation amount from top to bottom should still be maintained. Through this differentiated irrigation strategy, it is ensured that crops in each layer can receive a suitable water supply.

[0062] On the other hand, ambient light intensity data of the top layer and each canopy layer are collected, and the leaf area index of each layer of crop is measured. The light compensation calculation module, based on Beer-Lambert's law, calculates that the intensity of light decreases exponentially with increasing penetration depth as it passes through the plant canopy. Based on the measured light intensity data, the light intensity ratio between adjacent layers is calculated, and combined with the difference in leaf area index between the two layers, the light attenuation coefficient for that interval can be obtained. After obtaining the light attenuation coefficients between each layer, a light intensity attenuation model from the top to the bottom layer is established. This model can predict the light intensity at any height. To determine the start-up and shutdown sequence of the supplemental lighting equipment, the required light intensity threshold for the crop is first set. When the actual light intensity of a certain layer is low... When the light intensity threshold is reached, the supplemental lighting equipment in that layer needs to be activated. The specific activation time depends on the dynamic changes in natural light intensity. After determining the activation time of each layer's supplemental lighting equipment, considering the spillover effect of upper-layer supplemental lighting on lower-layer supplemental lighting, the activation time of lower-layer supplemental lighting equipment should lag behind that of upper-layer supplemental lighting. The lag time is calculated based on the light attenuation coefficient and supplemental light intensity. At the same time, the shutdown time of each layer's supplemental lighting equipment should also exhibit a gradient change, usually shutting down sequentially from upper to lower layers. The shutdown time interval is also determined based on the light attenuation model. Finally, the activation and shutdown times of each layer's supplemental lighting equipment are integrated to form a non-uniform timing control scheme. This scheme can ensure that crops receive appropriate light intensity at different heights while avoiding waste of supplemental lighting resources.

[0063] The specific process for establishing a light intensity attenuation model from the top to the bottom layer is as follows: First, light intensity data of the vertical profile at multiple time points are collected using a quantum light sensor to obtain the incident light intensity at the top layer and the transmitted light intensity at each layer. Simultaneously, the leaf area index of plants at each layer is measured using a leaf area meter. After obtaining the above basic data, a light intensity attenuation equation is constructed based on the Beer-Lambert law. The natural logarithm of the measured light intensity ratio at each layer is then used to perform regression analysis with the leaf area index to obtain the light attenuation coefficient. After establishing the initial attenuation model, a leaf aggregation parameter is introduced to correct the error of the uniform distribution assumption. The aggregation coefficient is calculated using measured leaf distribution parameters. Finally, the model is validated and the parameters are optimized using measured data to obtain an attenuation model that accurately describes the change in light intensity with canopy height. The equation is shown below:

[0064] ;

[0065] in,

[0066] ;

[0067] in,

[0068] ;

[0069] ;

[0070] in, The light intensity at a distance of z meters from the top of the canopy. The intensity of incident light at the top of the canopy. Based on the extinction coefficient, Leaf area index, This is the leaf aggregation coefficient. This is the vertical distribution correction function. For the high compensation coefficient, The total height of the canopy. The vertical distance from the top of the canopy. Let i be the leaf area index of the i-th layer. Let be the light intensity of the i-th layer. This is a parameter for the uniformity of leaf distribution. The leaf density response coefficient, The number of blades per unit area. This is the baseline coefficient for the vertical distribution. It is a high decay index. This represents the spatial decay rate.

[0071] The specific steps for calculating the light attenuation coefficient are as follows: First, light intensity data are collected at different heights of the plant community. Specific collection locations include the incident light intensity I0 at the top layer and the transmitted light intensity I at each layer. i When collecting data, choose a sunny day with stable light conditions, and simultaneously measure the leaf area index (LAI) at the corresponding location; after obtaining the light data, calculate the ratio I of light intensity for each layer. i / I0, taking the natural logarithm of this ratio gives ln(I i / I0); then, according to the Beer-Lambert law, ln(I i A linear regression of LAI (i.e., LAI) yields a straight line whose slope is the light attenuation coefficient k. To improve calculation accuracy, the influence of leaf tilt angle needs to be considered. The average projection coefficient is obtained by measuring the leaf angle and incorporated into the calculation formula. When the leaf distribution is uneven, a leaf distribution correction coefficient Ω is introduced, resulting in the corrected light attenuation coefficient k' = k × Ω. The light attenuation coefficient calculated using this method can accurately reflect the weakening effect of plant communities on light, providing a basis for controlling supplemental lighting equipment.

[0072] The calculation of leaf aggregation parameter first involves taking photos of the plant canopy from the sky at different heights using a digital camera, converting the images into binary images, and then calculating the porosity. Next, the leaf area index is measured at the same location using a leaf area meter, and the theoretical porosity is calculated based on the measured leaf area index. Once the measured porosity and the theoretical porosity are obtained, the ratio between the two is the leaf aggregation parameter.

[0073] On the other hand, the specific method for determining the start-up and shutdown sequence of supplemental lighting equipment based on the calculated light intensity of each layer is as follows: First, set the minimum light intensity threshold Imin and the optimal light intensity threshold Iopt required by the crop at different growth stages. When the actual light intensity of a certain layer is lower than Imin, the supplemental lighting equipment for that layer must be activated. When the actual light intensity is between Imin and Iopt, determine whether to activate supplemental lighting based on the crop's light demand curve. Then, based on the calculated light intensity attenuation model, predict the natural light intensity at each time period and at each layer location throughout the day, and compare the predicted values ​​with the light thresholds. The specific time period for each layer of supplementary lighting equipment to be activated is obtained. Then, the illumination superposition effect of the supplementary lighting equipment is considered. Since the upper layer of supplementary lighting will produce a certain amount of overflow illumination to the lower layer, it is necessary to calculate the overflow contribution of the upper layer of supplementary lighting to the lower layer, and add this contribution to the actual illumination intensity of the lower layer to reassess whether supplementary lighting is needed. Finally, based on the assessment results, the activation and deactivation times of each layer of supplementary lighting equipment are determined sequentially from the top layer. Usually, a top-down gradient activation strategy is adopted, that is, the activation time of the lower layer of supplementary lighting equipment should be later than that of the upper layer, and the deactivation time should be earlier than that of the upper layer. The time interval is determined according to the vertical transmission effect in the illumination attenuation model.

[0074] It should be noted that determining I at different growth stages min and I opt The specific values ​​need to be determined through a combination of methods: Through light response curve measurement experiments, the net photosynthetic rate of crops is measured under different light intensities, and light response curves are plotted. From these curves, the I value corresponding to the light compensation point can be obtained. min I corresponding to the light saturation point opt The initial reference values ​​are determined; then, growth indicators at multiple growth stages are measured, including plant height, leaf area, and dry matter accumulation, and the dynamic changes of these indicators under different light conditions are analyzed to adjust the threshold range for different growth stages accordingly; next, the characteristics of crop varieties are considered, for example, the threshold standards need to be raised for light-loving crops, while the threshold requirements can be appropriately lowered for shade-tolerant crops; at the same time, by analyzing historical cultivation data, the yield and quality performance under different light conditions are summarized; finally, through small-scale experiments, the thresholds are verified and optimized, and each threshold is gradually adjusted to meet the crop growth requirements and be practically operable.

[0075] For example, the natural light intensity of each layer is obtained at key times of day (such as sunrise, midday, and before sunset), and these measured values ​​are compared with the minimum and optimal light thresholds required by the crop at its current growth stage. When the top layer has sufficient natural light, no supplemental lighting is needed. Supplemental lighting is activated in the middle layer when the light intensity drops below the optimal threshold in the afternoon but is still above the minimum threshold. The supplemental lighting intensity is the difference between the actual light intensity and the optimal threshold for that layer. Since the bottom layer has the weakest natural light, supplemental lighting needs to be activated earlier after sunrise. The initial supplemental lighting intensity is the difference between the actual light intensity and the minimum light threshold. After the supplemental lighting in the middle layer is activated, the supplemental lighting intensity in the bottom layer needs to be reduced accordingly, considering the spillover effect of the supplemental lighting in the upper layer. The reduction amount is the contribution value of the supplemental lighting spillover in the middle layer. Based on this, a differentiated supplemental lighting sequence is formed: the bottom layer activates supplemental lighting earliest and for the longest duration, the middle layer activates later and for a shorter duration, and the top layer does not require supplemental lighting throughout the day. The supplemental lighting intensity is also dynamically adjusted according to changes in time and spatial location.

[0076] On the other hand, the environmental control execution module converts differentiated irrigation water replenishment into control parameters for the integrated water and fertilizer equipment and combines this with the non-uniform start-stop sequence of the supplemental lighting equipment to achieve environmental balance control. The specific process is as follows: First, the flow parameters of the integrated water and fertilizer equipment are determined based on the differentiated water replenishment of each soil layer. When the water replenishment of a certain layer is large, the diameter of the outlet holes in the irrigation pipe for that layer is increased or the number of outlet holes is added accordingly. Precise flow control is achieved by adjusting the water supply pressure. Simultaneously, the fertilizer-solution ratio is configured based on the nutrient requirements of the crop at its current growth stage. When the crop is in the vegetative growth stage, the nitrogen fertilizer ratio is increased, while the potassium fertilizer ratio is increased accordingly after entering the reproductive growth stage. During the water and fertilizer delivery process, the fertilizer application rate is dynamically adjusted based on soil moisture data fed back by soil sensors. If the soil moisture content of a certain layer is close to the target value, the irrigation flow rate is reduced and the fertilizer concentration is increased accordingly. When implementing supplemental lighting control, the start-up and shutdown sequence of the supplemental lighting equipment needs to be coordinated with water and fertilizer irrigation. If the supplemental lighting equipment of a certain layer is on, the irrigation intensity of that layer should be appropriately increased to compensate for the increased water consumption of the crops. For crops located at the top layer, due to sufficient natural light and strong transpiration, the irrigation frequency should be higher than that of the lower layers, but the amount of water irrigated at one time can be appropriately reduced. For crops at the bottom layer, considering the weakened growth potential caused by insufficient light, the irrigation time should be extended to ensure sufficient absorption. Finally, based on the temperature and humidity changes monitored by the sensors of each layer, the irrigation and supplemental lighting strategies should be adjusted in a timely manner. When the temperature is too high, the temperature can be lowered by increasing the irrigation frequency, while reducing the supplemental lighting intensity. Conversely, when the temperature is too low, the irrigation frequency should be reduced and the supplemental lighting intensity should be increased accordingly. Through this dynamic regulation method, the overall balance of the growth environment of crops at each layer can be achieved.

[0077] In summary, the IoT-based intelligent water and fertilizer regulation system for vertical urban vegetable garden cultivation, based on embodiments of the present invention, is explained. It collects and analyzes stratified soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data at different time points within a target monitoring period. This data is used to establish a vertical water transport model and a light attenuation calculation method, thereby achieving precise control of differentiated irrigation and non-uniform lighting. This significantly improves the efficiency of water and fertilizer resource utilization and the balance of the crop growth environment, helping to optimize crop growth conditions, thereby increasing crop yield and quality, while reducing water waste and energy consumption.

[0078] Here, those skilled in the art will understand that the specific operations of each step in the above-described IoT-based intelligent water and fertilizer regulation method for vertical cultivation of urban vegetable gardens have been referenced above. Figures 1 to 2 The IoT-based intelligent water and fertilizer control system for vertical cultivation in urban vegetable gardens has been described in detail, and therefore, its repeated description will be omitted. Figure 2 In the diagram, the vertical axis represents the volumetric moisture content (cm³ / cm³), ranging from 0 to 0.5, reflecting the water content per unit volume of soil. The horizontal axis represents the soil water potential (-kPa), using a logarithmic scale, from 0.1 to 10.5 The system reflects the soil's water-holding capacity. Three curves represent: Sandy (orange line), with the worst water-holding capacity and steepest curve; Loamy (green line), with moderate water-holding capacity; and Clay (blue line), with the best water-holding capacity and gentlest curve. Two gray dashed lines mark important water states: Field Capacity (33 kPa), representing the amount of water the soil can retain after natural drainage; and Permanent Wilting Point (1500 kPa), representing the critical point at which plants can no longer absorb water from the soil. By visually demonstrating the water-holding characteristics and changing patterns of three different soil textures—sandy, loam, and clay—this system helps understand the water-holding capacity of different soils under various water potentials. Combining the field capacity and permanent wilting point, two key water state points, can scientifically guide irrigation decisions, optimize water management strategies, and determine appropriate irrigation timing and water volume. This, in turn, provides a basis for precision irrigation control and fertigation equipment parameter settings in vertical farming systems.

[0079] In summary, the IoT-based intelligent water and fertilizer regulation method for three-dimensional urban vegetable garden cultivation, based on embodiments of the present invention, has been elucidated. It collects and analyzes stratified soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data at different time points within the target monitoring period. A vertical water transport model and a light attenuation calculation method are established to achieve precise control of differentiated irrigation and non-uniform lighting. This significantly improves the utilization efficiency of water and fertilizer resources and the balance of the crop growth environment, helping to optimize crop growth conditions, thereby increasing crop yield and quality, while reducing water waste and energy consumption.

Claims

1. An intelligent water and fertilizer control system for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things, characterized in that, include: The data acquisition module is used to collect layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data for vertical cultivation in urban vegetable gardens, and uploads the data to a cloud database through IoT sensors. The water transport modeling module is used to establish a vertical water transport model based on the layered soil moisture content data, and to obtain the differentiated irrigation water replenishment amount of each soil layer by calculating the water infiltration rate between adjacent layers. The light compensation calculation module is used to calculate the light attenuation coefficient based on the ambient light intensity data and crop leaf area index data of each layer, and to determine the non-uniform start-up and shutdown sequence of the supplementary lighting equipment of each layer based on the light attenuation coefficient. The environmental control execution module is used to convert the differentiated irrigation water supply into control parameters for each layer of integrated water and fertilizer equipment, and to control the supplementary lighting equipment for each layer according to the non-uniform start-stop sequence. The water transport modeling module fits the water characteristic curve based on the layered soil moisture content data collected by the data acquisition module, and then obtains the hydraulic parameter function and establishes a vertical water transport model based on the Richards equation. The hydraulic parameter functions include the unsaturated hydraulic conductivity function and the soil moisture diffusivity function obtained by using the chain rule; The soil moisture diffusivity function is expressed by the following formula: ； in, Soil moisture diffusivity, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, This refers to the volumetric water content. Residual moisture content saturated moisture content As the matrix potential, For the scale parameters of the van Genuchten model, The shape parameters of the van Genuchten model. For the van Genuchten model coupling parameters, Porosity distribution index For regularization parameters, As a correction factor, It is in a saturated state. This is the residual state.

2. The intelligent water and fertilizer control system for three-dimensional urban vegetable garden cultivation based on the Internet of Things as described in claim 1, characterized in that, The water infiltration rate between adjacent layers is calculated using the soil moisture content distribution at any time and location obtained from the vertical water transport model. The theoretical water replenishment amount is obtained by calculating the difference between the current soil moisture content and the target moisture content of each soil layer. The amount is then corrected based on the water infiltration rate between the adjacent layers to determine the differentiated irrigation water replenishment amount.

3. The intelligent water and fertilizer control system for three-dimensional urban vegetable garden cultivation based on the Internet of Things as described in claim 2, characterized in that, The water penetration time is calculated based on the water infiltration rate between adjacent layers and the infiltration rate and thickness of each soil layer. The set irrigation duration is compared with the penetration time, and the amount of infiltrated water that each soil layer can receive from top to bottom is calculated layer by layer. The actual water replenishment of each layer is the difference between the theoretical water replenishment requirement and the infiltration replenishment of the upper layer.

4. The intelligent water and fertilizer control system for three-dimensional urban vegetable garden cultivation based on the Internet of Things as described in claim 3, characterized in that, The light compensation calculation module uses Beer-Lambert's law and linear regression analysis to obtain an initial attenuation model from the ambient light intensity data and crop leaf area index data. By using the leaf aggregation parameter to correct the error caused by the uneven distribution of leaves in the initial attenuation model, a light intensity attenuation model is obtained. The light intensity attenuation model is used to predict the light intensity at any height.

5. The intelligent water and fertilizer control system for three-dimensional urban vegetable garden cultivation based on the Internet of Things as described in claim 4, characterized in that, The light intensity attenuation model can be expressed by the following formula: ； in, ； ； in, The light intensity at a distance of z meters from the top of the canopy. The intensity of incident light at the top of the canopy. Based on the extinction coefficient, Leaf area index, This is the leaf aggregation coefficient. This is the vertical distribution correction function. For the height compensation coefficient, The total height of the canopy. The vertical distance from the top of the canopy. Let be the leaf area index of the i-th layer. Let be the light intensity of the i-th layer. This is a parameter for the uniformity of leaf distribution. The leaf density response coefficient, The number of blades per unit area. This is the baseline coefficient for the vertical distribution. It is a high decay index. This represents the spatial decay rate.

6. A smart water and fertilizer regulation method for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things, characterized in that, include: Collect layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data for the three-dimensional cultivation of the urban vegetable garden, and upload the layered soil moisture content data, ambient light intensity data for each layer, and crop leaf area index data to the cloud database through IoT sensors; Based on the stratified soil moisture content data, a vertical water transport model was established, and the differentiated irrigation water replenishment amount of each soil layer was obtained by calculating the water infiltration rate between adjacent layers. Based on the ambient light intensity data of each layer and the crop leaf area index data, the light attenuation coefficient is calculated, and the non-uniform start-up and shutdown sequence of the supplementary lighting equipment in each layer is determined based on the light attenuation coefficient. The differentiated irrigation water supply is converted into control parameters for each layer of integrated water and fertilizer equipment, and the supplementary lighting equipment for each layer is controlled according to the non-uniform start-stop sequence. Based on the collected stratified soil moisture content data, a moisture characteristic curve is fitted, and then the hydraulic parameter function is obtained and a vertical water transport model of Richards equation is established. The hydraulic parameter functions include the unsaturated hydraulic conductivity function and the soil moisture diffusivity function obtained by using the chain rule; The soil moisture diffusivity function is expressed by the following formula: ； in, Soil moisture diffusivity, Unsaturated hydraulic conductivity For saturated hydraulic conductivity, This refers to the volumetric water content. Residual moisture content saturated moisture content As the matrix potential, For the scale parameters of the van Genuchten model, The shape parameters of the van Genuchten model. For the van Genuchten model coupling parameters, Porosity distribution index For regularization parameters, As a correction factor, It is in a saturated state. This is the residual state.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the intelligent water and fertilizer control system for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things, as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the intelligent water and fertilizer control system for three-dimensional cultivation of urban vegetable gardens based on the Internet of Things, as described in any one of claims 1 to 5.

Images