A method for dynamically calculating crop water requirement and an intelligent irrigation system

Abstract

The application provides a crop water requirement dynamic calculation method and an intelligent irrigation system, and relates to the technical field of agricultural irrigation.The crop water requirement dynamic calculation method adopts a quantum dot fluorescence probe array to accurately obtain soil water activity with a 0.1mm spatial resolution, and the accuracy is improved by 3-5 times compared with that of a traditional sensor; terahertz spectrum technology is used to analyze leaf cell sap osmotic pressure, so that nondestructive detection of crop physiological water requirement signals is realized, destructive sampling is avoided, a multi-modal fusion model is used in combination with transfer learning and a quantum correction factor, the water requirement calculation error is less than or equal to 3%, the dynamic response speed is improved to the hour level, the blockchain technology ensures data authenticity, the flow control accuracy of a magneto-rheological actuator reaches + / - 2% FS, and the water saving rate is more than 30%.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural irrigation technology, and in particular to a crop water requirement dynamic calculation method and an intelligent irrigation system. BACKGROUND

[0002] In agricultural production, accurate calculation of crop growth water requirement is the core prerequisite for scientific irrigation, and the irrigation system based on accurate water requirement is the key to improve water resource utilization efficiency and ensure high-quality and high-yield crops. Water resources, as an indispensable basic resource for agricultural production, its reasonable use is directly related to the sustainable development of agriculture. With the increasingly prominent global water shortage problem and the promotion of agricultural scale and intensive planting.

[0003] Currently, there are significant limitations in crop water requirement calculation and irrigation control technology: traditional methods rely on soil moisture sensors (such as time domain reflectometry) and empirical formulas (such as Penman-Monteith), soil moisture measurement is mostly single-point volume water content with a spatial resolution of ≤5cm, which is difficult to reflect the water heterogeneity in the root zone micro-domain; crop physiological water requirement signal acquisition relies on destructive sampling (such as leaf water potential measurement), which cannot achieve continuous monitoring; existing irrigation systems have problems such as single data dimension and static calculation model: environmental parameter collection mostly uses traditional weather stations, and the spatial and temporal resolution of wind speed, solar radiation, etc. is insufficient; water requirement calculation does not consider the influence of crop variety specificity and soil porosity, and the dynamic response lag is ≥24 hours; at the same time, the magneto-rheological irrigation actuator mostly uses electromagnetic valves or frequency conversion water pumps, and the flow regulation precision is ≤±5%FS, and the data transmission process is easy to be disturbed, which causes the calculation result to be distorted, resulting in more than 30% of water resource waste, which cannot meet the demand of dynamic and multi-dimensional water requirement perception for precision agriculture. SUMMARY

[0004] Based on the technical problems in the background art, the present application proposes a crop water requirement dynamic calculation method and an intelligent irrigation system to solve the problems in the background art.

[0005] The present application proposes a crop water requirement dynamic calculation method, which comprises:

[0006] S1, using a quantum dot fluorescence probe array to collect multi-dimensional water characteristic parameters of crop root zone soil, the quantum dot fluorescence probe array is composed of CdSe / ZnS core-shell structure quantum dots and mesoporous silica carrier, and soil water data is obtained through the nonlinear mapping relationship between fluorescence intensity decay rate and soil water activity;

[0007] S2, scanning the crop canopy leaves by using a terahertz time-domain spectroscopy system to obtain the characteristic absorption peak intensity in the 0.3-3 THz frequency band, and analyzing the crop physiological water demand signal by establishing a quantitative relationship model between the terahertz absorption coefficient and the leaf cell sap osmotic pressure;

[0008] S3, deploying an environmental field monitoring module based on a millimeter wave radar to collect environmental parameters of crop growth, such as real-time wind speed, atmospheric pressure, and solar radiation flux density, wherein the millimeter wave radar works in the 77 GHz frequency band;

[0009] S4, inputting the obtained soil moisture data, crop physiological water demand signal, and environmental parameters into a multi-modal fusion calculation model based on transfer learning, wherein the multi-modal fusion calculation model corrects the traditional Penman-Monteith formula by introducing a quantum tunneling effect correction factor, and outputs the dynamic water demand value of the crop on an hourly scale;

[0010] S5, using a blockchain node to perform real-time hash verification on the original data and intermediate results in the calculation process to ensure the non-tamperability of the water demand calculation results.

[0011] Preferably, in S1, the excitation wavelength of the quantum dot fluorescence probe array is 365-405 nm, the emission wavelength is 520-680 nm, the spatial resolution is not less than 0.1 mm, and the probe surface is modified with soil colloid specific recognition groups.

[0012] Preferably, in S2, the time resolution of the terahertz time-domain spectroscopy system is ≤5 fs, the intercellular water transport rate is calculated by the propagation time delay difference of terahertz waves in leaf tissues, the quantitative relationship model is trained using an improved support vector machine algorithm, and the input features include 128 terahertz absorption peak characteristic values.

[0013] Preferably, in S4, the source domain data of transfer learning comes from a crop water demand dataset in a laboratory controllable environment, the target domain is the actual growth environment data in the field, the distribution alignment is realized through an adversarial domain adaptation network, and the calculation formula of the quantum tunneling effect correction factor is: wherein k is the quantum tunneling effect correction factor, α is the soil porosity correction coefficient, β is the crop variety specific parameter, E is the real-time monitored soil water potential, and E0 is the baseline water potential value.

[0014] Preferably, in S5, the blockchain node adopts a consortium chain architecture, includes 3 or more consensus nodes, is respectively deployed in a meteorological station, a soil monitoring terminal, and a crop growth monitoring terminal, adopts a practical Byzantine fault tolerance algorithm for the consensus mechanism, is used for real-time hash verification of the original data and intermediate results in the calculation process by the blockchain node, realizes consensus verification of the non-tamperable water demand calculation results, and the block generation interval is ≤30 s.

[0015] Preferably, S6 is further included, and the temperature sensitivity of the quantum dot fluorescent probe is used to compensate the collected soil moisture data, and the compensation formula is: Wherein, W t is the compensated moisture content, W0 is the original measured value, γ is the temperature coefficient, T is the real-time temperature, and T0 is the calibration temperature.

[0016] The application further provides a dynamic intelligent irrigation system for crop water requirement, which comprises:

[0017] A data acquisition layer comprising an array of quantum dot fluorescent probes, a terahertz time-domain spectroscopy system, and an environmental field monitoring module of a millimeter wave radar;

[0018] An edge computing gateway for receiving original data from the data acquisition layer and executing a multi-modal fusion computing model;

[0019] An irrigation control hub for receiving a dynamic water requirement value output by the edge computing gateway, generating a pulse width modulation signal based on a preset water requirement threshold for a crop growth stage;

[0020] A magneto-rheological irrigation actuator for adjusting irrigation flow and pressure by changing the yield stress of magneto-rheological fluid in response to the pulse width modulation signal, wherein the magneto-rheological irrigation actuator is internally provided with a nanoscale flow sensor.

[0021] Preferably, the edge computing gateway adopts a heterogeneous computing architecture, integrating an FPGA and a RISC-V processor, the FPGA is used for real-time Fourier transform of terahertz spectroscopy data, and the RISC-V processor runs the multi-modal fusion computing model, and the data processing delay is ≤10ms.

[0022] Preferably, the magneto-rheological irrigation actuator comprises a ring-shaped electromagnetic coil and a deformable valve core, the coil current adjustment range is 0-2A, corresponding to an irrigation flow adjustment range of 0-50L / h, and the flow control accuracy is ≤±2%FS.

[0023] Preferably, an unmanned aerial vehicle inspection module is further included, the unmanned aerial vehicle inspection module is provided with a terahertz imager, a crop canopy is scanned in a large range, the scanning result is fused with the measurement result of the ground terahertz time-domain spectroscopy system, and the spatial distribution accuracy of a crop physiological water requirement signal is optimized.

[0024] The application has the following beneficial effects: an array of quantum dot fluorescent probes is used to accurately obtain soil moisture activity with a spatial resolution of 0.1mm, and the accuracy is improved by 3-5 times compared with traditional sensors; terahertz spectroscopy technology is used to analyze leaf cell sap osmotic pressure, and non-destructive detection of a crop physiological water requirement signal is realized, avoiding destructive sampling.

[0025] The multi-modal fusion model combines transfer learning and quantum correction factors, so that the water demand calculation error is less than or equal to 3%, the dynamic response speed is improved to the hour level, the blockchain technology ensures the authenticity of the data, the flow control precision of the magneto-rheological actuator is ± 2% FS, and the water saving rate is more than 30%.

[0026] The unmanned aerial vehicle and ground data fusion optimize the spatial accuracy, the heterogeneous computing gateway handles the delay of less than or equal to 10ms, meets the real-time irrigation demand, and breaks through the time and space limitations and precision bottlenecks of traditional methods. BRIEF DESCRIPTION OF DRAWINGS

[0027] Figure 1 A flowchart of a crop water demand dynamic calculation method is provided for the present application.

[0028] Figure 2 A structural block diagram of a crop water demand dynamic intelligent irrigation system is provided for the present application. DETAILED DESCRIPTION

[0029] REFERENCE Figure 1 With Figure 2 The present application provides a crop water demand dynamic calculation method, and the calculation method is as follows:

[0030] S1, a quantum dot fluorescence probe array is used to collect multi-dimensional water characteristic parameters of the crop root zone soil, and soil water data is obtained through the nonlinear mapping relationship between fluorescence intensity decay rate and soil water activity.

[0031] Among them, the multi-dimensional parameters can more comprehensively reflect the true situation of soil moisture, avoid the limitations of single parameter measurement, and thus improve the accuracy and reliability of the soil moisture data;Since the quantum dot fluorescence probe array has a spatial resolution of not less than 0.1mm, the multi-dimensional water characteristic parameters can capture the water change of the soil micro-domain, which helps to understand the fine distribution of soil moisture in the root zone and can provide more detailed information for irrigation;Different soils have different physical and chemical properties, and the multi-dimensional water characteristic parameters can consider the influence of these factors on soil moisture, and better adapt to various complex soil environments.

[0032] The quantum dot fluorescence probe array is composed of CdSe / ZnS core-shell structure quantum dots and mesoporous silica carrier, is used for in-depth crop root zone, and accurately captures multi-dimensional water feature parameters in soil. The special structure can ensure stable work in complex soil environment. The excitation wavelength of the quantum dot fluorescence probe array is 365-405 nm, the emission wavelength is 520-680 nm, the spatial resolution is not less than 0.1 mm, and the probe surface is modified with soil colloid specific recognition groups. Through specific excitation wavelength and emission wavelength, the quantum dot fluorescence probe array can emit specific fluorescence. When contacting with soil water, the fluorescence intensity decays. By using the nonlinear mapping relationship between the fluorescence intensity and the soil water activity, combined with the high spatial resolution and the recognition groups on the surface, the soil water data can be more accurately obtained.

[0033] For example, in a certain soil environment, when the soil water activity changes, the fluorescence intensity of the quantum dot fluorescence probe array will change accordingly. By measuring the change and according to the pre-established nonlinear mapping model (experimental design: under different soil water activity conditions, the quantum dot fluorescence probe array is used for measurement to obtain corresponding fluorescence intensity decay rate data; the soil water activity can be adjusted by controlling the water content, humidity and other factors of the soil; data collection: under multiple different soil water activity levels, the experiment is repeated to collect a large number of corresponding data pairs of fluorescence intensity decay rate and soil water activity; model selection and training: select a nonlinear mathematical model support vector regression, divide the collected data into a training set and a test set, use the training set to train the model, and adjust the parameters of the model so that the model can best fit the relationship between the fluorescence intensity decay rate and the soil water activity), the soil water content and other related data can be accurately calculated. The excitation wavelength of 365-405 nm and the emission wavelength of 520-680 nm can reduce the interference of other substances in the soil and improve the recognition degree of the fluorescence signal. The spatial resolution of not less than 0.1 mm can capture the water change in the soil microdomain. The soil colloid specific recognition groups on the surface enhance the specific recognition ability of the soil water, and further improve the accuracy and reliability of the soil water data.

[0034] S2, scanning the crop canopy leaves by using a terahertz time-domain spectroscopy system to obtain the characteristic absorption peak intensity (0.3-3 THz band, which is the intensity value of the characteristic absorption peak of the crop canopy leaves to the terahertz wave in the 0.3-3 THz band, which is a single numerical value reflecting the strength of the absorption peak, and is directly related to the material composition and structure of the leaves) to realize non-destructive detection of the physiological state of crops. By establishing a quantitative relationship model between the terahertz absorption coefficient and the osmotic pressure of the leaf cell sap, the physiological water demand signal of crops is analyzed.

[0035] The time resolution of the terahertz time-domain spectroscopy system is ≤5 fs. The intercellular water transport rate is calculated by the propagation delay difference of terahertz waves in leaf tissue. The quantitative relationship model is trained using an improved support vector machine algorithm. The input features include 128 terahertz absorption peak feature values ​​(the absorption peak feature value is a multi-dimensional vector that contains more information about the terahertz absorption peak, which can more comprehensively describe the spectral characteristics of the leaf; when establishing the quantitative relationship model between the terahertz absorption coefficient and the osmotic pressure of leaf cell sap, using 128 terahertz absorption peak feature values ​​as input features can provide richer data information for the model, thereby improving the accuracy and reliability of the model).

[0036] The specific training steps for the improved support vector machine algorithm are as follows:

[0037] Calculate the characteristic value of each terahertz absorption peak (denoted as x). i The mutual information I(x) between the leaf cell sap osmotic pressure (denoted as y) and the leaf cell sap osmotic pressure. i (y), the formula is:

[0038] ;

[0039] Where P(x) i Let y) be the joint probability distribution, and P(x, y) be the probability distribution. i P(y) represents the marginal probability distribution.

[0040] Retain the top 30% of features in mutual information ranking (i.e., I(x)). i If y) ≥ threshold, first calculate the mutual information I(x) corresponding to the eigenvalues ​​of all 128 terahertz absorption peaks. i ,y), and press I (x i Sort the features (x, y) from largest to smallest; take the top 30% of features after sorting and calculate the minimum mutual information value of these features; compare "1.2 times the mean mutual information value of all features" with the above "minimum mutual information value of the top 30% of features", and take the smaller value as the final threshold to ensure that the I(x, y) of the top 30% of features is equal to the minimum mutual information value of the top 30% of features. i If y) are all greater than or equal to the threshold, the remaining 70% of features with mutual information less than the threshold are removed to achieve redundant feature removal.

[0041] Core features strongly correlated with leaf cell sap osmotic pressure are selected from 128 terahertz absorption peak features (usually 20-30 are retained) to reduce input dimensions and improve computational efficiency.

[0042] The osmotic pressure of leaf cell sap was divided into three intervals (hypotonic: <0.5MPa; mesotonic: 0.5-1.5MPa; hypertonic: >1.5MPa), with each interval corresponding to different kernel function parameters;

[0043] The hybrid kernel function of "RBF kernel + polynomial kernel" is used, and the expression is:

[0044] ;

[0045] wherein K(x, x j ) is a hybrid kernel function, which is designed to fit the piecewise nonlinear relationship between "THz absorption peak characteristic value and leaf cell sap osmotic pressure", a is a weight coefficient (low osmotic interval a=0.3, medium osmotic interval a=0.5, high osmotic interval a=0.7, and the weight coefficient is adjusted adaptively through training data); γ1 is the RBF kernel parameter (control local fitting accuracy), λ is the polynomial kernel degree (control global trend fitting, take 2-3), c is the offset (fixed as 1), x, x j are 128 THz absorption peak characteristic vectors of two leaf samples (each dimension corresponds to the absorption peak intensity of 0.3-3 THz frequency band, that is, "128 THz absorption peak characteristic values" in the application).

[0046] The kernel function parameters are solved by "particle swarm optimization algorithm (PSO)", and the target is to minimize the prediction error (MAE) in the interval.

[0047] For the piecewise nonlinear relationship between "THz absorption coefficient and osmotic pressure", a dynamic kernel function is designed to improve the fitting accuracy of different osmotic pressure intervals.

[0048] The input THz absorption peak characteristic value x i is assigned a weight w i (w i is positively correlated with the mutual information I(x i , y) of the characteristic, that is );

[0049] The loss function is improved as:

[0050] ;

[0051] wherein n is the total number of input THz absorption peak characteristic values (corresponding to 128 THz absorption peak characteristic values in S2, that is, n=128); x is a THz absorption peak characteristic vector of a single crop canopy leaf sample (containing n THz absorption peak characteristic values x i , i=1, 2,..., n), ε is set to 0.03 MPa (i.e. the allowed osmotic pressure prediction error is ≤3%), and the weight w iThe high information features, such as the 10.5 THz absorption peak directly related to the cell sap, are given a higher weight in the loss calculation, and the influence of noise features is weakened. f(x) is the predicted value of the model for x (the model is a quantitative relationship model trained based on an improved support vector machine (SVM) algorithm, and its core function is to predict the leaf cell sap osmotic pressure through the input terahertz spectral features).

[0052] The training process of the improved support vector machine algorithm needs to meet certain constraints to ensure reproducibility:

[0053] 1. Data set: The source data is leaf samples in a laboratory controllable environment (500 groups, covering 3 crop varieties and 5 growth stages), each group containing 128 terahertz absorption peak feature values + measured cell sap osmotic pressure (measured by an ice point osmometer, accuracy ± 0.01 MPa).

[0054] 2. Parameter range:

[0055] Penalty parameter C ∈ [5, 20] (determined by 5-fold cross-validation, the optimal value is usually 10); the penalty parameter C is used to balance the control of the support vector machine model on "training data fitting accuracy" and "model generalization ability", for example: the larger the C value, the more severe the model's punishment for incorrect classification (or prediction deviation) in the training data, which will try to fit all training samples as much as possible, and may even over-learn the noise in the training data, leading to model "overfitting" (good fitting for training data, but prediction accuracy decreases for new data); the smaller the C value, the higher the model's tolerance for incorrect classification, and it tends to pursue a simple decision boundary, which may lead to "underfitting" (lower fitting accuracy for both training data and new data).

[0056] RBF kernel parameter gamma 1 ∈ [0.1, 1.0] (0.5 for the medium osmotic interval, 0.8 for the high osmotic / low osmotic interval);

[0057] Polynomial kernel degree lambda = 2 (fixed, to avoid overfitting caused by high-order terms).

[0058] 3. Training termination condition: osmotic pressure prediction error MAE on the test set ≤ 0.025 MPa (i.e. ≤ 2.5%, meeting the requirement that the overall water requirement calculation error ≤ 3%).

[0059] The terahertz time-domain spectroscopy system scans the leaf with a time resolution of ≤5 fs. When the terahertz wave propagates in the leaf tissue, different water content and physiological states will cause different time delay differences. The intercellular water transport rate is calculated by measuring the time delay difference. The quantitative relationship model is trained by combining the 128 terahertz absorption peak characteristic values and the improved support vector machine algorithm. The relationship between the terahertz absorption coefficient and the leaf cell sap osmotic pressure is established. The 128 terahertz absorption peak characteristic values of the leaf obtained by the terahertz time-domain spectroscopy system are input into the quantitative relationship model trained by the improved support vector machine algorithm. The process of converting the "leaf cell sap osmotic pressure value" output by the model into information that can directly reflect the crop water requirement state (such as "mild water shortage", "moderate water shortage", "sufficient water", etc.) is to convert the abstract physiological parameter (osmotic pressure) into a specific water requirement signal that can guide irrigation decision-making.

[0060] The high time resolution of ≤5 fs can accurately capture the subtle changes of the terahertz wave in the leaf, improving the measurement accuracy. The 128 terahertz absorption peak characteristic values provide a rich data basis for the quantitative relationship model, combined with the improved support vector machine algorithm, making the model prediction more accurate, and more accurately analyzing the crop physiological water requirement signal. For example, when the crop is in a water shortage state, the leaf cell sap osmotic pressure will change, and the propagation characteristics of the terahertz wave in the leaf tissue will also change. The characteristics such as absorption peak intensity detected by the terahertz time-domain spectroscopy system will also change. Through quantitative relationship model analysis, the current physiological water requirement signal of the crop can be obtained, realizing non-destructive and real-time monitoring, and ensuring the accuracy of the crop's own demand data.

[0061] S3, deploy a millimeter wave radar-based environment field monitoring module to collect environmental parameters for crop growth: real-time wind speed, atmospheric pressure, and solar radiation flux density, providing comprehensive environmental data. The millimeter wave radar works in the 77GHz frequency band and can accurately and real-time obtain the above environmental parameters.

[0062] For example, through real-time monitoring of atmospheric pressure, the influence of weather systems on the crop growing environment can be understood, because changes in atmospheric pressure are often related to weather changes, which in turn affect the water requirement of crops. Real-time wind speed monitoring helps to evaluate the evaporation rate of water in the crop canopy and soil surface. When the wind speed is high, the water evaporation accelerates, and the crop water requirement may increase. Solar radiation flux density directly affects the photosynthesis and transpiration of crops, which in turn affects the water requirement of crops. By accurately measuring the solar radiation flux density, the water requirement of crops under different light conditions can be more accurately calculated. By collecting these environmental parameters comprehensively, the richness and accuracy of the environmental data are ensured.

[0063] S4, input the acquired soil moisture data, crop physiological water demand signal and environmental data into a multi-modal fusion calculation model based on transfer learning, the model corrects the traditional Penman-Monteith formula by introducing a quantum tunneling effect correction factor, and outputs the dynamic water demand value of the crop at the hourly scale.

[0064] The source domain data of the transfer learning comes from the crop water demand data set in the laboratory controllable environment, and the target domain is the actual growth environment data in the field. Through the adversarial domain adaptation network, the distribution alignment is realized, so that the model can better adapt to the complex environment in the field. The transfer learning can use the laboratory data to improve the adaptability of the model in the actual environment in the field, reduce the amount of data collection and model training time in the field; the adversarial domain adaptation network realizes the distribution alignment of the source domain and the target domain data, and improves the generalization ability of the model;

[0065] The calculation formula of the quantum tunneling effect correction factor is: . Wherein, k is the quantum tunneling effect correction factor, alpha is the soil porosity correction coefficient, for example, the porosity of sandy soil is larger, and the water transfer is faster, so the alpha value is different from that of clay soil with smaller porosity; beta is a crop variety specific parameter, different crop varieties have different physiological characteristics such as root structure and leaf stomatal density, so the demand and utilization efficiency of water are different. This parameter reflects the difference in water demand characteristics of different crop varieties; E is the real-time monitored soil water potential, which reflects the energy state of water in the soil. Real-time monitoring of soil water potential can timely understand the dynamic change of soil moisture; E0 is the reference water potential value, which is used as a reference standard to calculate the correction factor. The quantum tunneling effect correction factor considers the soil porosity and crop variety specificity and other factors, so that the modified traditional Penman-Monteith formula is more accurate, and the hourly scale dynamic water demand value output can timely reflect the change of crop water demand, and improve the timeliness and accuracy of irrigation.

[0066] For example, at a certain moment, the real-time soil water potential E is obtained by measurement, combined with the known soil porosity correction coefficient alpha, crop variety specificity parameter beta and reference water potential value E0, the quantum tunneling effect correction factor k is calculated, which is substituted into the modified Penman-Monteith formula, so that the accurate hourly scale dynamic water demand value of the crop at that moment can be obtained.

[0067] S5, the original data and intermediate results in the calculation process are checked in real time by using the blockchain node, so as to ensure the non-tamperability of the water demand calculation result.

[0068] The blockchain node adopts a consortium chain architecture, and contains more than 3 consensus nodes, which are respectively deployed in the weather station, the soil monitoring terminal and the crop growth monitoring terminal. The original data and intermediate results of each are respectively obtained through the consensus nodes of the weather station, the soil monitoring terminal and the crop growth monitoring terminal, consensus verification is carried out by using a practical Byzantine fault-tolerant algorithm, real-time hash checking is carried out on the data, and the checked results are stored on the blockchain. The interval of block generation is ≤30s, so that the data cannot be tampered with (the consensus mechanism is used for the real-time hash checking of the original data and intermediate results in the calculation process by the blockchain node, and the consensus verification when the calculation result of the water requirement cannot be tampered with).

[0069] The consortium chain architecture ensures the credibility and convenience of management of the blockchain node; the more than 3 consensus nodes are distributed in different terminals, which improves the reliability and security of data verification; the practical Byzantine fault-tolerant algorithm can effectively deal with node failure and malicious attacks, and ensure the correctness of the consensus; real-time hash checking and ≤30s block generation interval ensure the real-time and tamper-proof nature of the data, avoid interference and distortion in the data transmission process, and provide data protection for the accuracy of the calculation result of the water requirement. For example, the environmental data such as real-time wind speed and atmospheric pressure collected by the weather station are uploaded to the blockchain network through the consensus node deployed therein, and the soil moisture data collected by the soil monitoring terminal and the crop physiological water requirement signal data collected by the crop growth monitoring terminal are also uploaded through the respective consensus nodes.

[0070] S6, based on the temperature sensitivity of the quantum dot fluorescent probe, the collected soil moisture data is temperature compensated to eliminate the influence of temperature on the measurement result.

[0071] The compensation formula is: wherein W t is the compensated moisture content, W0 is the original measurement value, γ is the temperature coefficient, T is the real-time temperature, and T0 is the calibration temperature.

[0072] Considering the temperature sensitivity of the quantum dot fluorescent probe, temperature compensation can eliminate the interference of temperature change on the measurement result of soil moisture, make the obtained soil moisture data more accurate and reliable, provide more accurate basic data, and improve the calculation accuracy of the whole system. For example, at a certain moment, the real-time temperature T changes, if temperature compensation is not performed, the original measurement value W0 of the soil moisture measured by the quantum dot fluorescent probe may be deviated due to the influence of temperature. By using the compensation formula, the compensated moisture content W t is calculated by using the known temperature coefficient γ, the calibration temperature T0 and the real-time temperature T. This value more truly reflects the actual moisture content of the soil, and provides reliable soil moisture data.

[0073] In a specific application, first, the quantum dot fluorescence probe array is used to obtain soil moisture data by virtue of the nonlinear mapping relationship between the fluorescence intensity decay rate and the soil water activity; then, the terahertz time-domain spectroscopy system is used to scan the crop canopy leaves, and the physiological water demand signal of the crop is analyzed based on the established quantitative relationship model between the terahertz absorption coefficient and the leaf cell sap osmotic pressure; then, the environmental field monitoring module of the millimeter wave radar is used to collect environmental parameters; then, these data are input into the multi-modal fusion calculation model, and the dynamic water demand value is calculated by the corrected formula; finally, the data are checked by the blockchain node to ensure the reliability of the results; the data can be collected in multiple dimensions, covering soil, crops and environment, and the crop water demand condition can be comprehensively reflected; the use of the quantum dot fluorescence probe array improves the accuracy of the soil moisture data; the terahertz time-domain spectroscopy system realizes nondestructive detection of the physiological water demand signal of the crop, avoiding damage to the crop caused by traditional sampling; the environmental field monitoring module of the millimeter wave radar can obtain environmental parameters in real time and accurately; the multi-modal fusion calculation model improves the accuracy and dynamics of the water demand calculation; the blockchain technology ensures the credibility of the data, ensures scientific irrigation, and greatly reduces the waste of water resources caused by inaccurate data.

[0074] Referring to Figure 1 With Figure 2 , the embodiment of the present application also provides a crop water demand dynamic intelligent irrigation system, which comprises a data acquisition layer, an edge computing gateway, an irrigation control hub and a magneto-rheological irrigation execution mechanism, and specifically:

[0075] The data acquisition layer comprises a quantum dot fluorescence probe array, a terahertz time-domain spectroscopy system and an environmental field monitoring module of a millimeter wave radar, is responsible for comprehensively and accurately collecting various data related to crop growth, and is the data source basis of the whole system; the quantum dot fluorescence probe array accurately collects soil moisture data in the crop root zone by virtue of its unique structure and performance; the terahertz time-domain spectroscopy system nondestructively scans the crop canopy leaves to obtain the physiological water demand signal of the crop; and the environmental field monitoring module of the millimeter wave radar monitors parameters such as wind speed, atmospheric pressure and solar radiation flux density of the crop growth environment in real time.

[0076] The edge computing gateway is used for receiving the original data of the data acquisition layer and executing a multi-modal fusion calculation model, quickly processing data, reducing data transmission delay and improving system response speed. The edge computing gateway adopts a heterogeneous computing architecture, integrates an FPGA and a RISC-V processor, the FPGA is used for real-time Fourier transform of terahertz spectroscopy data, and the RISC-V processor runs the multi-modal fusion calculation model; the data processing delay is less than or equal to 10 ms; for example, when the data acquisition layer collects new data, the edge computing gateway can process and calculate the data in a very short time, and timely transmit the processing result to the irrigation control hub, so that the irrigation system can quickly respond to the change of crop water demand, and precise irrigation is realized.

[0077] An irrigation control hub receives the dynamic water demand value output by the edge computing gateway, generates a pulse width modulation signal based on a preset water demand threshold for the crop growth stage, and controls the action of the magneto-rheological irrigation actuator. For example, when the dynamic water demand value exceeds the water demand threshold for the current crop growth stage, the irrigation control hub increases the duty cycle of the pulse width modulation signal to control the magneto-rheological irrigation actuator to increase the irrigation flow and pressure to meet the water demand of the crop. Conversely, when the dynamic water demand value is below the threshold, the duty cycle of the pulse width modulation signal is reduced to reduce the irrigation flow and pressure, avoiding waste of water resources.

[0078] The preset water demand threshold for the crop growth stage in the above content is obtained by the following method:

[0079] Collect laboratory controllable environment water demand data of target crops (such as wheat and corn) at each growth stage (seedling stage, jointing stage, filling stage, and mature stage) (determined by artificial weighing method and lysimeter method).

[0080] Collect historical data of actual field irrigation water demand of the same crop in the same region (combined with historical records of local weather stations and soil monitoring terminals).

[0081] Input the above data into the multi-modal fusion calculation model in S4, and determine the water demand threshold interval for each growth stage (such as the water demand threshold for the jointing stage of wheat is 10-15 L / ㎡・h) through model iterative optimization (with crop yield and water use efficiency as objective functions).

[0082] Adjust the threshold to match the actual water demand law of the crop through small-scale field verification (select 5% of the planting area to test the threshold adaptability).

[0083] A magneto-rheological irrigation actuator is used to respond to the pulse width modulation signal and adjust the irrigation flow and pressure by changing the yield stress of the magneto-rheological fluid. The magneto-rheological irrigation actuator has a nanoscale flow sensor built-in to achieve precise irrigation. The magneto-rheological irrigation actuator includes a ring-shaped electromagnetic coil and a deformable valve core. The coil current adjustment range is 0-2A, corresponding to an irrigation flow adjustment range of 0-50L / h, and the flow control accuracy is ≤±2%FS.

[0084] The irrigation control center generates a pulse width modulation signal input to the annular electromagnetic coil, the coil generates a magnetic field of corresponding intensity, the yield stress of the magneto-rheological fluid changes under the action of the magnetic field, the deformable valve core is pushed to change the opening degree, thereby adjusting the irrigation flow and pressure, the nanoscale flow sensor monitors the flow in real time and feeds back, the cooperation of the annular electromagnetic coil and the deformable valve core makes the flow regulation more flexible and accurate; the nanoscale flow sensor can monitor the flow in real time, realize closed-loop control, and improve the regulation accuracy, the flow control accuracy is ≤±2%FS, which is much higher than that of the traditional electromagnetic valve or variable frequency water pump; the coil current regulation range of 0-2A corresponds to the flow range of 0-50L / h, which can meet the irrigation needs of different crops and different growth stages, reduce water resource waste, and improve irrigation efficiency, for example, when the irrigation control center sends out a pulse width modulation signal to increase the irrigation flow, the annular electromagnetic coil current increases, a stronger magnetic field is generated, the yield stress of the magneto-rheological fluid changes, the opening degree of the deformable valve core increases, and the irrigation flow increases, at the same time, the nanoscale flow sensor monitors the flow change in real time and feeds back the flow data to the irrigation control center, if the flow does not reach the expected value, the irrigation control center will further adjust the pulse width modulation signal until the flow reaches the set value, realizing accurate irrigation, the precise flow control capability is much higher than that of the traditional electromagnetic valve or variable frequency water pump, the coil current regulation range of 0-2A corresponds to the flow range of 0-50L / h, which can meet the irrigation needs of different crops and different growth stages, effectively reduce water resource waste, and improve irrigation efficiency.

[0085] The crop water requirement dynamic intelligent irrigation system also comprises an unmanned aerial vehicle inspection module, the unmanned aerial vehicle is equipped with a terahertz imager, a large range of crop canopy scanning is realized, the scanning results are combined with the measurement results of the ground terahertz time-domain spectrum system, and the spatial distribution accuracy of the crop physiological water requirement signal is optimized.

[0086] The unmanned aerial vehicle inspection module can realize large range of crop canopy scanning, and make up for the limitation of the measurement range of the ground terahertz time-domain spectrum system; the large-area data acquired by the terahertz imager is combined with the local detailed data on the ground, the spatial distribution of the crop physiological water requirement signal can be more comprehensively and accurately reflected, the judgment accuracy of the water requirement conditions of crops in different regions is improved, more comprehensive basis for accurate irrigation is ensured, for example, in a large area of farmland, the ground terahertz time-domain spectrum system can only measure a limited number of points, while the unmanned aerial vehicle equipped with a terahertz imager can scan the crop canopy of the entire farmland and acquire large-area crop physiological water information, the large-range data obtained by the unmanned aerial vehicle scanning are combined with the local detailed data measured by the ground terahertz time-domain spectrum system, the water requirement conditions of crops in different regions can be more accurately judged, and more comprehensive basis is provided, through data fusion, it can be found that crops in some regions of the farmland may be in a water shortage situation, and these regions may be missed in ground measurement, so as to guide the irrigation system to carry out targeted irrigation on these regions, and improve the accuracy and effectiveness of irrigation.

[0087] The above description is only the preferred embodiment of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can make equivalent substitutions or changes according to the technical solution and the inventive concept of the present application within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A method for dynamically calculating crop water requirement, characterized in that, The method comprises: S1, using a quantum dot fluorescence probe array to collect multi-dimensional water characteristic parameters of the crop root zone soil, the quantum dot fluorescence probe array being composed of CdSe / ZnS core-shell structure quantum dots and mesoporous silica carriers, and soil water data being obtained through a nonlinear mapping relationship between fluorescence intensity decay rate and soil water activity; S2, using a terahertz time-domain spectroscopy system to scan crop canopy leaves to obtain characteristic absorption peak intensity in a 0.3-3 THz frequency band, and analyzing crop physiological water demand signals by establishing a quantitative relationship model between terahertz absorption coefficient and leaf cell sap osmotic pressure; S3, deploying an environmental field monitoring module based on a millimeter wave radar to collect environmental parameters of crop growth, such as real-time wind speed, atmospheric pressure and solar radiation flux density, the millimeter wave radar working in a 77 GHz frequency band; S4, inputting the obtained soil water data, crop physiological water demand signals and environmental parameters into a multi-modal fusion calculation model based on transfer learning, the multi-modal fusion calculation model correcting a traditional Penman-Monteith formula by introducing a quantum tunneling effect correction factor, and outputting crop hourly scale dynamic water demand values; In S4, the source domain data of migration learning comes from the crop water requirement dataset in the laboratory controllable environment, and the target domain is the actual growth environment data in the field. The distribution alignment is realized through the adversarial domain adaptation network, and the calculation formula of the quantum tunneling effect correction factor is: wherein k is the quantum tunneling effect correction factor, α is the soil porosity correction coefficient, β is the crop variety specific parameter, E is the real-time monitored soil water potential, and E0 is the baseline water potential value. S5, using a blockchain node to perform real-time hash checking on original data and intermediate results in the calculation process to ensure that the water demand calculation results are tamper-proof.

2. The method for dynamically calculating the crop water requirement according to claim 1, characterized in that, In S1, the excitation wavelength of the quantum dot fluorescence probe array is 365-405 nm, the emission wavelength is 520-680 nm, the spatial resolution is not less than 0.1 mm, and the probe surface is modified with soil colloid specific recognition groups.

3. The method of claim 1, wherein, In S2, the time resolution of the terahertz time-domain spectroscopy system is ≤5 fs, the intercellular water transport rate is calculated by the propagation time delay difference of terahertz waves in leaf tissues, the quantitative relationship model is obtained by training using an improved support vector machine algorithm, and the input features include 128 terahertz absorption peak feature values.

4. The method for dynamically calculating crop water requirement according to claim 1, characterized in that, In S5, the blockchain node uses a consortium chain architecture, includes more than 3 consensus nodes, is respectively deployed at a meteorological station, a soil monitoring terminal and a crop growth monitoring terminal, uses a practical Byzantine fault tolerance algorithm for the consensus mechanism, is used for real-time hash checking of original data and intermediate results in the calculation process by the blockchain node, realizes consensus verification when the water demand calculation results are tamper-proof, and the block generation interval is ≤30 s.

5. The method for dynamically calculating the crop water requirement according to claim 1, characterized in that, In step S1, the collected soil moisture data is temperature compensated based on the temperature sensitivity of quantum dot fluorescent probes, and the compensation formula is: where W t is the compensated moisture content, W0 is the original measured value, γ is the temperature coefficient, T is the real-time temperature, and T0 is the calibration temperature.

6. A dynamic intelligent irrigation system for crop water requirement, applying the dynamic calculation method of crop water requirement according to any one of claims 1-5, characterized in that, The system comprises: a data acquisition layer including a quantum dot fluorescence probe array, a terahertz time-domain spectroscopy system and an environmental field monitoring module of a millimeter wave radar; an edge computing gateway for receiving original data of the data acquisition layer and executing a multi-modal fusion calculation model; an irrigation control hub for receiving dynamic water demand values output by the edge computing gateway, generating a pulse width modulation signal based on a preset crop growth stage water demand threshold value; a magneto-rheological irrigation execution mechanism for responding to the pulse width modulation signal, adjusting irrigation flow and pressure by changing the yield stress of magneto-rheological fluid, and the magneto-rheological irrigation execution mechanism being internally provided with a nanoscale flow sensor.

7. The dynamic smart irrigation system for crop water requirement according to claim 6, wherein, The edge computing gateway adopts a heterogeneous computing architecture, integrates an FPGA and a RISC-V processor, the FPGA is used for real-time Fourier transform of terahertz spectrum data, and the RISC-V processor runs a multi-modal fusion computing model, and data processing delay is less than or equal to 10 ms.

8. The dynamic smart irrigation system for crop water requirement as claimed in claim 6 wherein, The magneto-rheological irrigation actuator comprises a ring-shaped electromagnetic coil and a deformable valve core, the coil current regulation range is 0-2 A, the corresponding irrigation flow regulation range is 0-50 L / h, and the flow control accuracy is less than or equal to ± 2 % FS.

9. The dynamic smart crop water requirement irrigation system according to claim 6, wherein, The unmanned aerial vehicle inspection module is also included, the unmanned aerial vehicle inspection module is equipped with a terahertz imager, a crop canopy is scanned in a large range, scanning results are fused with measurement results of a ground terahertz time-domain spectrum system, and the spatial distribution accuracy of a crop physiological water demand signal is optimized.

Images