Intelligent irrigation control system and method based on intelligent crop growth model

Abstract

The invention relates to the technical field of agricultural irrigation, in particular to an intelligent irrigation control system and method based on an intelligent crop growth model. The method comprises the steps of collecting temperature, humidity, illumination and soil moisture data of a crop growth environment, and taking the data as input of a machine learning model; an LSTM machine learning algorithm is utilized to construct a crop growth model used for predicting the crop growth trend and calculating the irrigation water demand; in the crop growth process, crop image data are acquired in stages and compared with a standard growth image, similarity and a correction coefficient are calculated, and the predicted growth trend is corrected in real time; according to the corrected growth trend, the irrigation water demand is dynamically adjusted, and closed-loop feedback control is formed; according to the corrected irrigation water demand, the irrigation equipment is accurately controlled for irrigation, and intelligent monitoring of crop growth and efficient utilization of water resources are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural irrigation, and specifically to an intelligent irrigation control system and method based on an intelligent crop growth model. Background Art

[0002] Traditional irrigation methods usually rely on manual experience and fixed irrigation plans, and it is difficult to adapt to the dynamic changes of crop growth, resulting in waste of water resources and reduction of crop yields. Traditional technical solutions have proposed irrigation control methods based on environmental parameters. By collecting environmental parameters such as temperature, humidity, and light, the irrigation time and amount are determined according to preset thresholds or empirical formulas. However, these methods do not consider the dynamic change process of crop growth and cannot adjust the irrigation strategy according to the actual growth state of the crops.

[0003] The existing technologies have the following deficiencies in the field of crop irrigation: lack of accurate modeling and prediction of the dynamic process of crop growth, unable to make irrigation decisions according to the real-time growth state of crops; failure to fully consider the comprehensive influence of multiple factors such as environmental conditions and crop types, and it is difficult to meet the irrigation requirements under different crops and environmental conditions; mostly based on historical data for offline analysis and decision-making, lacking the ability of real-time response and adjustment to abnormal situations and environmental changes during the crop growth process; no closed-loop feedback mechanism for crop growth monitoring and irrigation control is established, and it is difficult to achieve dynamic optimization and intelligent control of the irrigation process.

[0004] In view of the deficiencies of the existing technologies, there is an urgent need for an intelligent irrigation control method based on a crop growth dynamic model, which can comprehensively consider multiple factors such as environmental conditions and crop types, accurately predict the crop growth trend and irrigation requirements, and correct and optimize the irrigation strategy in real time according to the crop growth monitoring results, so as to achieve precise and intelligent management of crop irrigation, improve water resource utilization efficiency and crop yields.

[0005] In view of this, the present invention proposes an intelligent irrigation control system and method based on an intelligent crop growth model. Summary of the Invention

[0006] To achieve the above object, the present invention provides an intelligent irrigation control system and method based on an intelligent crop growth model. The specific technical solutions are as follows: The intelligent irrigation control method based on an intelligent crop growth model includes:

[0007] Collect crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment;

[0008] Based on machine learning algorithms, construct a crop growth model according to the crop growth environment data, crop types, and growth time, and predict the crop growth trend;

[0009] Based on the constructed crop growth model and crop growth environment data, calculate the irrigation water requirement during the crop growth period;

[0010] Correct the crop growth trend. Periodically collect the image data of the crop growth process, compare the collected image data with the standard image data of the crop growth process, and correct the crop growth trend according to the comparison result;

[0011] Based on the corrected crop growth trend, correct the irrigation water requirement during the crop growth period, and perform irrigation according to the corrected crop irrigation water requirement.

[0012] Preferably, collect the temperature and humidity data of the crop growth environment, including temperature data T and relative humidity data H, collect the light data of the crop growth process, including light intensity L and light time D; collect the soil moisture data M during the crop growth process;

[0013] Integrate the collected temperature data T, relative humidity data H, light intensity L, light time D, and soil moisture data M into crop growth environment data E: E = {T, H, L, D, M}.

[0014] Preferably, combine the crop growth environment data and growth time into time series data; each time step includes crop growth environment data (T, H, L, D, M) and crop type C, and use the growth time t as the index of the time step; the crop growth environment data uses the actual value as the feature, and the crop type is represented by one-hot encoding; divide the time series data into subsequences of fixed length, each subsequence contains n time steps, and use the subsequence as the input of the LSTM model; the corresponding crop growth completion degree y is used as the target output of the subsequence;

[0015] Construct an LSTM model. The input layer is used to receive the crop growth environment data and crop type features, and the output layer predicts the crop growth completion degree; the architecture of the LSTM model includes an input layer, an LSTM layer, a fully connected layer, and an output layer;

[0016] The input layer includes: each time step includes crop growth environment data (T, H, L, D, M) and the one-hot encoding of crop type C; the LSTM layer includes: using a multi-layer LSTM structure, each layer has h hidden units; the fully connected layer includes: converting the output of the LSTM layer into a predicted value of the crop growth completion degree through the fully connected layer; the output layer includes: using the sigmoid activation function to output the predicted value of the crop growth completion degree The value range is [0, 1];

[0017] Use the mean square error as the loss function, and the optimization goal is to minimize the loss function: Among them, A is the number of subsequences, and y a is the true crop growth completion degree of the a-th subsequence, and is the crop growth completion degree of the a-th subsequence predicted by the model;

[0018] The LSTM model is trained using the backpropagation algorithm and an optimizer, and the model parameters are updated to minimize the loss function; the performance of the LSTM model is evaluated using the cross-validation method, and the LSTM model with the optimal performance is selected as the final crop growth model.

[0019] Preferably, the trained LSTM model is deployed to the production environment, and the crop growth trend is predicted based on the real-time collected crop growth environment data and crop type; given the input sequence: X new =[(T1, H1, L1, D1, M1, C1), (T2, H2, L2, D2, M2, C2),...,(T n , H n , L n , D n , M n , C n )], the LSTM model outputs the predicted values of the crop growth completion degree for the next k time steps Based on the predicted growth trend, combined with the crop growth model and the crop growth environment data, the irrigation water requirement during the crop growth period is predicted.

[0020] Preferably, according to the crop growth completion degree predicted by the LSTM model, the water consumption of the crop at different growth stages is calculated; let the crop growth completion degree be G(k), where k is the time step, then the water consumption W(k) of the crop at the k-th time step is expressed as: Among them, η is the crop water consumption coefficient; represents the derivative of the crop growth completion degree with respect to the time step, that is, the crop growth rate;

[0021] Considering the influence of the crop growth environment data on the water consumption, the temperature coefficient α(T), humidity coefficient β(H), and light coefficient γ(L) are introduced to correct the calculation of the crop water consumption: W'(k)=W(k)·α(T)·β(H)·γ(L); where W'(k) is the corrected crop water consumption, and T, H, and L are the temperature, relative humidity, and light intensity at the k-th time step, respectively;

[0022] According to the soil moisture data, the soil moisture deficit is calculated. Let the soil moisture content at the k-th time step be θ(k), and the field water holding capacity be θ f , then the soil moisture deficit Δθ(k) is: Δθ(k)=θ f -θ(k);

[0023] Introduce the formula for the dynamic change of soil moisture, and calculate the dynamic change of soil moisture content θ(k): θ(k) = θ(k - 1) - W'(k) + I(k), where θ(k - 1) is the soil moisture content at the (k - 1)-th time step;

[0024] Integrate the crop water consumption and soil moisture deficit to calculate the irrigation water requirement I(k) at the k-th time step: I(k) = max(W'(k) - Δθ(k), 0); when W'(k) > Δθ(k), irrigation is needed to supplement water; otherwise, no irrigation is required; Calculate the irrigation water requirement for the entire crop growth period to obtain the total irrigation water requirement I during crop growth total : where K0 is the total number of time steps in the crop growth period.

[0025] Preferably, during the crop growth process, crop growth image data is collected at predetermined time intervals; Suppose a total of Q time steps of image data are collected, and the image data collected at the i-th time step is I i ; For each time step i, i > k, select the standard image corresponding to the growth stage from the standard crop growth image dataset

[0026] Calculate the similarity between the collected image data I i and the standard image ; Use SSIM to calculate the similarity, that is: where represents the SSIM value of the image data I i and the labeled image , and the value range is [0, 1]. The larger the value, the more similar the two images are;

[0027] According to the similarity value, calculate the growth trend correction coefficient λ at the i-th time step i : The correction coefficient λ i reflects the degree of difference between the actual growth image and the standard growth image; The larger λ i , the greater the deviation between the actual growth trend and the expected growth trend, and a greater degree of correction is required;

[0028] Use the correction coefficient λ i to correct the predicted value of crop growth completion degree at the i-th time step to obtain the corrected predicted value of growth completion degree

[0029]

[0030] Among them, G(i - 1) is the actual growth completion degree at the (i - 1)-th time step; through calibration, the predicted growth completion degree is adjusted towards the actual growth completion degree;

[0031] After calibrating the predicted values of the growth completion degree for all time steps, the corrected crop growth trend is obtained Among them, K0 is the total number of time steps in the crop growth cycle.

[0032] Preferably, according to the corrected crop growth trend, the crop water consumption W'(i) at the i-th time step is corrected to obtain the corrected crop water consumption W”(i):

[0033]

[0034] Among them, is the predicted value of the corrected crop growth completion degree at the i-th time step, is the predicted value of the crop growth completion degree before correction at the i-th time step; ∈ is a non-zero constant, and the water consumption is adjusted accordingly by comparing the growth rates before and after correction;

[0035] According to the corrected crop water consumption W”(i), calculate the soil water deficit Δθ'(i) at the i-th time step: Δθ'(i) = θ f - θ(i) + W”(i) Among them, θ f is the field water holding capacity, and θ(i) is the soil water content at the i-th time step;

[0036] Calculate the corrected irrigation water requirement I'(i) at the i-th time step: I'(i) = max(Δθ'(i), 0); when Δθ'(i) > 0, irrigation is needed to supplement water; otherwise, no irrigation is required; correct the irrigation water requirement for the entire crop growth cycle to obtain the corrected total irrigation water requirement I' total : Among them, K0 is the total number of time steps in the crop growth cycle;

[0037] According to the corrected irrigation water requirement I'(i), formulate an irrigation plan; for the i-th time step, if I'(i) > 0, then irrigate according to the irrigation water requirement I'(i); if I'(i) = 0, then do not irrigate; during actual irrigation, by controlling the irrigation equipment, supply water precisely according to the corrected irrigation water requirement I'(i).

[0038] The intelligent irrigation control system based on the intelligent crop growth model, which is used to implement the intelligent irrigation control method based on the intelligent crop growth model, includes: a data acquisition module, a growth trend prediction module, an irrigation water requirement calculation module, a growth trend correction module, and an irrigation water requirement correction module;

[0039] The data acquisition module is used to acquire crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment;

[0040] The growth trend prediction module constructs a crop growth model based on machine learning algorithms according to crop growth environment data, crop types, and growth time to predict the crop growth trend;

[0041] The irrigation water requirement calculation module calculates the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data;

[0042] The growth trend correction module corrects the crop growth trend, periodically acquires image data of the crop growth process, compares the acquired image data with the standard image data of the crop growth process, and corrects the crop growth trend according to the comparison results;

[0043] The irrigation water requirement correction module corrects the irrigation water requirement during the crop growth period based on the corrected crop growth trend and performs irrigation according to the corrected crop irrigation water requirement.

[0044] An electronic device includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory; the processor executes the intelligent irrigation control method based on the intelligent crop growth model by calling the computer program stored in the memory.

[0045] A computer-readable storage medium stores instructions that, when run on a computer, cause the computer to execute the intelligent irrigation control method based on the intelligent crop growth model.

[0046] The beneficial effects of the present invention: By comprehensively collecting key parameters of the crop growth environment, the present invention provides a rich data basis for constructing a crop growth model, helps to improve the accuracy and applicability of the model, and lays a data support for subsequent intelligent irrigation decision-making.

[0047] The present invention uses machine learning algorithms, comprehensively considers multiple factors such as environmental conditions, crop characteristics, and growth time, and establishes a model that can dynamically predict the crop growth trend, providing a scientific basis for accurately grasping the crop growth status and irrigation requirements.

[0048] According to the prediction results of the crop growth model and real-time environmental parameters, the present invention quantitatively calculates the irrigation water requirement of the crop at different growth stages, realizes the quantification and refinement of irrigation decision-making, and helps to improve the water resource utilization efficiency and irrigation accuracy.

[0049] The present invention collects crop growth image data in stages, compares it with standard growth images, establishes a feedback correction mechanism for crop growth monitoring and model prediction, dynamically adjusts the model prediction results, and improves the accuracy and real-time performance of crop growth trend prediction.

[0050] Based on the corrected crop growth trend, the present invention dynamically adjusts the irrigation water demand, forms a closed-loop feedback control, realizes real-time optimization and dynamic regulation of irrigation decision-making, ensures appropriate water supply for crops throughout the growth cycle, and improves crop yield and quality. Brief Description of the Drawings

[0051] Figure 1 It is a flowchart of an intelligent irrigation control method based on an intelligent crop growth model provided by the present invention;

[0052] Figure 2 It is a structural diagram of an intelligent irrigation control system based on an intelligent crop growth model provided by the present invention. Detailed Description of the Embodiments

[0053] To better understand the present invention, more detailed descriptions of various aspects of the present invention will be made with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present invention and do not limit the scope of the present invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0054] In the accompanying drawings, for ease of illustration, the sizes, dimensions, and shapes of the elements have been slightly adjusted. The drawings are only examples and are not drawn strictly to scale. As used herein, terms such as "substantially", "about", and similar terms are used as terms indicating approximation and not as terms indicating degree, and are intended to illustrate the inherent deviations in measured or calculated values that would be recognized by those of ordinary skill in the art. Additionally, in the present invention, the order of description of each step process does not necessarily represent the order in which these processes occur in actual operation, unless otherwise clearly defined or derivable from the context.

[0055] It should also be understood that expressions such as "comprises", "including", "having", "includes" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present invention, "may" is used to mean "one or more embodiments of the present invention". And, the term "exemplary" is intended to refer to an example or illustration.

[0056] Unless otherwise defined, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which the present invention belongs. It should also be understood that unless there is a clear explanation in the present invention, the words defined in the commonly used dictionary should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0057] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present invention can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0058] Example 1

[0059] Reference Figure 1 , which is the first embodiment of the present invention, provides an intelligent irrigation control method based on an intelligent crop growth model.

[0060] S1: Collect crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment.

[0061] Collect temperature and humidity data of the crop growth environment, including temperature data T and relative humidity data H; collect light data during the crop growth process, including light intensity L and light time D; collect soil moisture data M during the crop growth process.

[0062] The collected temperature data T, relative humidity data H, light intensity L, light duration D and soil moisture data M are integrated into the crop growth environment data E: E = {T, H, L, D, M};

[0063] The collected crop growth environment data are cleaned to remove outliers and fill in missing values.

[0064] In step S1, collecting crop growth environment data provides a comprehensive and accurate data basis for constructing a crop growth model, which helps to improve the prediction accuracy and applicability of the model; through data cleaning and integration, the data quality is further improved, laying a solid data support for subsequent model training and optimization.

[0065] S2: Based on machine learning algorithms, construct a crop growth model according to crop growth environment data, crop types, and growth time to predict the crop growth trend.

[0066] Combine the crop growth environment data and growth time into time series data; each time step includes crop growth environment data (T, H, L, D, M) and crop type C, and use the growth time t as the index of the time step; the crop growth environment data uses actual values as features, and the crop type is represented by one-hot encoding; divide the time series data into subsequences of fixed length, each subsequence contains n time steps, and use the subsequences as the input of the LSTM model; the corresponding crop growth completion degree y is used as the target output of the subsequence.

[0067] Construct an LSTM model. The input layer is used to receive crop growth environment data and crop type features, and the output layer predicts the crop growth completion degree; the architecture of the LSTM model includes an input layer, an LSTM layer, a fully connected layer, and an output layer.

[0068] The input layer includes: each time step includes crop growth environment data (T, H, L, D, M) and the one-hot encoding of crop type C; the LSTM layer includes: using a multi-layer LSTM structure, each layer has h hidden units; the fully connected layer includes: converting the output of the LSTM layer into a predicted value of the crop growth completion degree through the fully connected layer; the output layer includes: using a sigmoid activation function to output the predicted value of the crop growth completion degree The value range is [0, 1].

[0069] Use the mean squared error (MSE) as the loss function, and the optimization goal is to minimize the loss function: where A is the number of subsequences, y a is the true crop growth completion degree of the a-th subsequence, is the crop growth completion degree of the a-th subsequence predicted by the model.

[0070] Use the backpropagation algorithm and an optimizer (such as Adam) to train the LSTM model, and update the model parameters to minimize the loss function; use the cross-validation method to evaluate the performance of the LSTM model, such as 5-fold cross-validation.

[0071] Adjust the hyperparameters of the LSTM model, such as the number of hidden units, the number of layers, the sequence length, the batch size, etc., to improve the prediction accuracy of the model; use the Early Stopping strategy to prevent overfitting and stop training when the performance on the validation set no longer improves; select the LSTM model with the best performance as the final crop growth model.

[0072] Deploy the trained LSTM model to the production environment. According to the real-time collected crop growth environment data and crop types, predict the crop growth trend; given the input sequence X new =[(T1, H1, L1, D1, M1, C1), (T2, H2, L2, D2, M2, C2),...,(T n , H n , L n , D n , M n , C n )], the LSTM model outputs the predicted values of the crop growth completion degree for the next k time steps According to the predicted growth trend, combined with the crop growth model and crop growth environment data, predict the irrigation water requirement during the crop growth period.

[0073] In step S2, an LSTM model is used to comprehensively consider environmental factors, crop characteristics, and growth time, and a machine learning model that can dynamically predict crop growth trends is established. Through the optimization and parameter adjustment of the model, the prediction accuracy and generalization ability are improved, providing a reliable decision-making basis for accurately grasping the crop growth status and irrigation requirements.

[0074] S3: Based on the constructed crop growth model and crop growth environment data, calculate the irrigation water requirement during the crop growth period.

[0075] According to the crop growth completion degree predicted by the LSTM model, calculate the water consumption of the crop at different growth stages; assume that the crop growth completion degree is G(k), where k is the time step, then the water consumption W(k) of the crop at the k-th time step is expressed as: where η is the crop water consumption coefficient, which reflects the relationship between the crop growth rate and water consumption; represents the derivative of the crop growth completion degree with respect to the time step, that is, the crop growth rate.

[0076] Considering the influence of crop growth environment data on water consumption, introduce the temperature coefficient α(T), humidity coefficient β(H), and light coefficient γ(L), and the corrected formula for calculating crop water consumption is:

[0077] W'(k)=W(k)·α(T)·β(H)·γ(L)

[0078] Among them, W'(k) is the corrected crop water consumption, and T, H, and L are the temperature, relative humidity, and light intensity at the k-th time step respectively; the temperature coefficient, humidity coefficient, and light coefficient can be obtained by fitting historical data.

[0079] According to the soil moisture data, calculate the soil moisture deficit. Let the soil moisture content at the k-th time step be θ(k), and the field capacity be θ f , then the soil moisture deficit Δθ(k) is: Δθ(k) = θ f - θ(k).

[0080] Introduce the soil moisture dynamic change formula to calculate the dynamic change of the soil moisture content θ(k), θ(k) = θ(k - 1) - W'(k) + I(k), where θ(k - 1) is the soil moisture content at the (k - 1)-th time step.

[0081] Integrate the crop water consumption and the soil moisture deficit to calculate the irrigation water requirement I(k) at the k-th time step:

[0082] I(k) = max(W'(k) - Δθ(k), 0)

[0083] When W'(k) > Δθ(k), irrigation is needed to supplement water; otherwise, irrigation is not needed; calculate the irrigation water requirement for the entire crop growth period to obtain the total irrigation water requirement I totoal : Among them, K0 is the total number of time steps in the crop growth period.

[0084] Step S3 quantifies and calculates the irrigation water requirements of crops at different growth stages based on the prediction results of the crop growth model, combined with environmental parameters and soil moisture data. By comprehensively considering various influencing factors, the refinement and dynamicization of irrigation decision-making are realized, which helps to improve the water resource utilization efficiency and crop growth quality.

[0085] S4: Correct the crop growth trend, collect image data of the crop growth process at regular intervals, compare the collected image data with the standard image data of the crop growth process, and correct the crop growth trend according to the comparison results.

[0086] During the crop growth process, collect crop growth image data at regular intervals; assume that a total of Q time steps of image data are collected, and the image data collected at the i-th time step is I i ; for each time step i, where k < i < K0, select the standard image corresponding to the growth stage from the standard crop growth image dataset The standard crop growth image dataset is constructed based on a large amount of historical data and expert experience, and contains typical images of each stage of crop growth;

[0087] Calculate the acquired image data I i and the standard image to obtain the similarity The similarity can be calculated using various image similarity measurement methods, such as the Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), etc.; when calculating the similarity using SSIM, there is: where represents the SSIM value of the image data I i and the standard image The value ranges from [0, 1], and the larger the value, the more similar the two images are.

[0088] According to the similarity value, calculate the growth trend correction coefficient λ at the i-th time step: λ = 1 - The correction coefficient λ reflects the degree of difference between the actual growth image and the standard growth image; the larger λ is, the greater the deviation between the actual growth trend and the expected growth trend, and a greater degree of correction is required.

[0089] Use the correction coefficient λ to correct the predicted value of the crop growth completion degree at the i-th time step to obtain the corrected predicted value of the growth completion degree

[0090]

[0091] where G(i - 1) is the actual growth completion degree at the (i - 1)-th time step; through correction, the predicted growth completion degree is adjusted towards the actual growth completion degree to make it closer to the real growth trend.

[0092] After correcting the predicted values of the growth completion degree for all time steps, the corrected crop growth trend is obtained, where K0 is the total number of time steps in the crop growth cycle.

[0093] In step S4, by periodically collecting crop growth image data and comparing it with the standard image, a real-time correction mechanism for crop growth monitoring and model prediction is established. According to the correction coefficient, the prediction result is dynamically adjusted, improving the accuracy and real-time performance of crop growth trend prediction, and providing a reliable feedback basis for optimizing irrigation decisions.

[0094] S5: Based on the corrected crop growth trend, correct the irrigation water requirement during the crop growth period, and irrigate according to the corrected crop irrigation water requirement.

[0095] According to the corrected crop growth trend, correct the crop water consumption W'(i) at the i-th time step to obtain the corrected crop water consumption W”(i):

[0096]

[0097] Among them, is the predicted value of the crop growth completion degree after correction at the i-th time step, is the predicted value of the crop growth completion degree before correction at the i-th time step, and ∈ is a non-zero constant to prevent the denominator from being zero; by comparing the growth rates before and after correction, the water consumption is adjusted accordingly.

[0098] According to the corrected crop water consumption W”(i), calculate the soil water deficit Δθ'(i) at the i-th time step: Δθ'(i) = θ f - θ(i) + W”(i) Among them, θ f is the field capacity, and θ(i) is the soil water content at the i-th time step.

[0099] Calculate the corrected irrigation water requirement I'(i) at the i-th time step: I'(i) = max(Δθ'(i), 0); when Δθ'(i) > 0, irrigation is needed to supplement water; otherwise, no irrigation is required; correct the irrigation water requirement for the entire crop growth period to obtain the corrected total irrigation water requirement I' total : Among them, K0 is the total number of time steps in the crop growth period.

[0100] According to the corrected irrigation water requirement I'(i), formulate an irrigation plan; for the i-th time step, if I'(i) > 0, then irrigate according to the irrigation water requirement I'(i); if I'(i) = 0, then do not irrigate; during the actual irrigation process, by controlling the irrigation equipment, supply water precisely according to the corrected irrigation water requirement I'(i).

[0101] In step S5, according to the corrected crop growth trend, the irrigation water requirement is dynamically adjusted, forming a closed-loop feedback control. By optimizing the irrigation decision in real time, it ensures that the crop obtains appropriate water supply throughout the growth period, improves the crop yield and quality, and realizes the precise management and efficient utilization of water resources.

[0102] Example 2

[0103] Referring to Figure 2 , this is the second embodiment of the present invention, which provides an intelligent irrigation control system based on an intelligent crop growth model.

[0104] The system includes: a data acquisition module, a growth trend prediction module, an irrigation water requirement calculation module, a growth trend correction module, and an irrigation water requirement correction module.

[0105] The data acquisition module is used to acquire crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment.

[0106] The growth trend prediction module constructs a crop growth model based on machine learning algorithms according to crop growth environment data, crop types, and growth time to predict the crop growth trend.

[0107] The irrigation water requirement calculation module calculates the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data.

[0108] The growth trend correction module corrects the crop growth trend by periodically collecting image data of the crop growth process, comparing the collected image data with the standard image data of the crop growth process, and correcting the crop growth trend according to the comparison results.

[0109] The irrigation water requirement correction module corrects the irrigation water requirement during the crop growth period based on the corrected crop growth trend and irrigates according to the corrected crop irrigation water requirement.

[0110] Example 3

[0111] The present invention also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the intelligent irrigation control method based on the intelligent crop growth model as described above.

[0112] The method or system according to the embodiment of the present invention can also be implemented by means of the architecture of the electronic device of the present invention.

[0113] The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, input / output components, a hard disk, etc.

[0114] The storage device in the electronic device, such as ROM or a hard disk, can store the intelligent irrigation control method provided by the present invention.

[0115] Intelligent irrigation control method based on an intelligent crop growth model, including collecting crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment; based on a machine learning algorithm, constructing a crop growth model according to the crop growth environment data, crop type, and growth time to predict the crop growth trend; calculating the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data; correcting the crop growth trend by periodically collecting image data of the crop growth process, comparing the collected image data with the standard image data of the crop growth process, and correcting the crop growth trend according to the comparison result; based on the corrected crop growth trend, correcting the irrigation water requirement during the crop growth period, and performing irrigation according to the corrected crop irrigation water requirement.

[0116] Furthermore, the electronic device may further include a user interface. Of course, the architecture of the present invention is only exemplary. When implementing different devices, one or more components of the electronic device disclosed in the present invention may be omitted according to actual needs.

[0117] Embodiment 4

[0118] The present invention also discloses a computer-readable storage medium.

[0119] Computer-readable instructions are stored on the computer-readable storage medium.

[0120] When the computer-readable instructions are run by a processor, the intelligent irrigation control method based on the intelligent crop growth model according to the embodiments of the present invention described with reference to the above drawings can be executed.

[0121] The storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. Additionally, according to the embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs.

[0122] For example, the present invention provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present invention. For example: collecting crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment; based on a machine learning algorithm, constructing a crop growth model according to the crop growth environment data, crop type, and growth time to predict the crop growth trend; calculating the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data; correcting the crop growth trend by periodically collecting image data of the crop growth process, comparing the collected image data with the standard image data of the crop growth process, and correcting the crop growth trend according to the comparison result; based on the corrected crop growth trend, correcting the irrigation water requirement during the crop growth period and performing irrigation according to the corrected crop irrigation water requirement.

[0123] When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present invention are executed. There may be many ways to implement the method, device, and equipment of the present invention. For example, the method, device, and equipment of the present invention can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0124] The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the specific order described above, unless otherwise specifically stated.

[0125] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0126] In addition, parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0127] As described above in the specific embodiments, the purpose, technical solutions, and beneficial effects of the present invention are further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent irrigation control method based on an intelligent crop growth model, characterized in that, Including: Collecting crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment; Based on machine learning algorithms, constructing a crop growth model according to the crop growth environment data, crop type, and growth time to predict the crop growth trend; Calculating the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data; Correcting the crop growth trend, collecting image data of the crop growth process at stages, comparing the collected image data with the standard image data of the crop growth process, and correcting the crop growth trend according to the comparison results; Based on the corrected crop growth trend, correcting the irrigation water requirement during the crop growth period and irrigating according to the corrected crop irrigation water requirement.

2. The intelligent irrigation control method based on the intelligent crop growth model according to claim 1, wherein, Collecting the temperature and humidity data of the crop growth environment, including temperature data T and relative humidity data H, collecting the light data of the crop growth process, including light intensity L and light time D; collecting the soil moisture data M during the crop growth process; Integrating the collected temperature data T, relative humidity data H, light intensity L, light time D, and soil moisture data M into crop growth environment data E: E = {T, H, L, D, M}.

3. The intelligent irrigation control method based on the intelligent crop growth model according to claim 2, wherein, Combining the crop growth environment data and growth time into time series data; each time step includes crop generation environment data (T, H, L, D, M) and crop type C, using the growth time t as the index of the time step; the crop growth environment data uses actual values as features, and the crop type is represented by one-hot encoding; dividing the time series data into subsequences of fixed length, each subsequence contains n time steps, and using the subsequence as the input of the LSTM model; the corresponding crop growth completion degree y is used as the target output of the subsequence; Constructing an LSTM model, where the input layer is used to receive the crop growth environment data and crop type features, and the output layer predicts the crop growth completion degree; the architecture of the LSTM model includes an input layer, an LSTM layer, a fully connected layer, and an output layer; The input layer includes: at each time step, it includes the crop growth environment data (T, H, L, D, M) and the one-hot encoding of the crop type C; the LSTM layer includes: using a multi-layer LSTM structure, with h hidden units in each layer; the fully connected layer includes: converting the output of the LSTM layer into a predicted value of the crop growth completion degree through the fully connected layer; the output layer includes: using the sigmoid activation function to output the predicted value of the crop growth completion degree The value range is [0, 1]; Using the mean squared error as the loss function, the optimization objective is to minimize the loss function: where A is the number of subsequences, and y a is the true crop growth completion degree of the a-th subsequence, and is the crop growth completion degree of the a-th subsequence predicted by the model; Training the LSTM model using the backpropagation algorithm and optimizer, updating the model parameters to minimize the loss function; using the cross-validation method to evaluate the performance of the LSTM model, and selecting the LSTM model with the optimal performance as the final crop growth model.

4. The intelligent irrigation control method based on the intelligent crop growth model according to claim 3, characterized in that Deploy the trained LSTM model to the production environment, and predict the crop growth trend based on the real-time collected crop growth environment data and crop types; given the input sequence: X new =[(T1, H1, L1, D1, M1, C1), (T2, H2, L2, D2, M2, C2),...,(T n , H n , L n , C n , M n , C n ), the LSTM model outputs the predicted values of the crop growth completion degree for the next k time steps Based on the predicted growth trend, combined with the crop growth model and crop growth environment data, predict the irrigation water requirement during the crop growth period.

5. The intelligent irrigation control method based on the intelligent crop growth model according to claim 4, characterized in that, According to the crop growth completion degree predicted by the LSTM model, calculate the water consumption of the crop at different growth stages; let the crop growth completion degree be G(k), where k is the time step, then the water consumption W(k) of the crop at the k-th time step is expressed as: where η is the crop water consumption coefficient; represents the derivative of the crop growth completion degree with respect to the time step, that is, the crop growth rate; Considering the influence of crop growth environment data on water consumption, introducing a temperature coefficient α(T), a humidity coefficient β(H), and a light coefficient γ(L) to correct the calculation of crop water consumption: W'(k) = W(k)·α(T)·β(H)γ(L); where, W'(k) is the corrected crop water consumption, and T, H, and L are the temperature, relative humidity, and light intensity at the kth time step respectively; According to the soil moisture data, calculate the soil moisture deficit. Let the soil moisture content at the k-th time step be θ(k), and the field capacity be θ f , then the soil moisture deficit Δθ(k) is: Δθ(k) = θ f - θ(k); Introducing the soil moisture dynamic change formula to calculate the dynamic change of soil moisture content θ(k), θ(k) = θ(k - 1) - W'(k) + I(k), where θ(k - 1) is the soil moisture content at the (k - 1)th time step; Integrate the crop water consumption and the soil water deficit to calculate the irrigation water requirement I(k) at the k-th time step: I(k) = max(W'(k) - Δθ(k), 0); when W'(k) > Δθ(k), irrigation is needed to supplement water; otherwise, irrigation is not needed; calculate the irrigation water requirement for the entire crop growth period to obtain the total irrigation water requirement I during the crop growth period total : where K0 is the total number of time steps in the crop growth period.

6. The intelligent irrigation control method based on the intelligent crop growth model according to claim 5, wherein, During the growth process of the crop, crop growth image data is collected stage by stage at predetermined time intervals; suppose a total of Q time steps of image data are collected, and the image data collected at the i-th time step is I i ; for each time step i, where i > k, a standard image corresponding to the growth stage is selected from the standard crop growth image dataset Calculate the acquired image data I i and the standard image to calculate the similarity Use SSIM to calculate the similarity, that is: where represents the SSIM value of the image data I i and the standard image The value range is [0, 1], and the larger the value, the more similar the two images are; Calculate the growth trend correction coefficient λ at the i-th time step according to the similarity value i : λ i = 1 - The correction coefficient λ i reflects the degree of difference between the actual growth image and the standard growth image; λ i The larger it is, the greater the deviation between the actual growth trend and the expected growth trend Using the correction coefficient λ i Predict the crop growth completion value for the i-th time step Perform correction to obtain the corrected predicted growth completion value Among them, G(i - 1) is the actual growth completion degree at the (i - 1)th time step; through correction, adjusting the predicted growth completion degree towards the actual growth completion degree; After correcting the predicted values of the growth completion degree for all time steps, the corrected crop growth trend is obtained. Where K0 is the total number of time steps in the crop growth cycle.

7. The intelligent irrigation control method based on the intelligent crop growth model according to claim 6, characterized in that According to the corrected crop growth trend, the crop water consumption W'(i) at the i-th time step is corrected to obtain the corrected crop water consumption W”(i): Among them, is the predicted value of the crop growth completion degree after correction at the i-th time step, is the predicted value of the crop growth completion degree before correction at the i-th time step; ∈ is a non-zero constant, and the water consumption is adjusted accordingly by comparing the growth rates before and after correction; Calculate the soil water deficit Δθ'(i) at the i-th time step according to the corrected crop water consumption W”(i): Δθ'(i) = θ f - θ(i) + W”(i), where θ f is the field capacity, and θ(i) is the soil water content at the i-th time step; Calculate the corrected irrigation water requirement I'(i) at the i-th time step: I'(i) = max(Δθ'(i), 0); when Δθ'(i) > 0, irrigation is needed to supplement water; otherwise, no irrigation is required; correct the irrigation water requirement for the entire crop growth period to obtain the corrected total irrigation water requirement I' total : where K0 is the total number of time steps in the crop growth period; Based on the corrected irrigation water requirement I'(i), an irrigation plan is formulated; for the i-th time step, if I'(i)>0, irrigation is carried out according to the irrigation water requirement I'(i); if I'(i) = 0, no irrigation is carried out; during the actual irrigation process, by controlling the irrigation equipment, water is supplied precisely according to the corrected irrigation water requirement I'(i).

8. An intelligent irrigation control system based on an intelligent crop growth model, which is used to implement the intelligent irrigation control method based on the intelligent crop growth model according to any one of claims 1 to 7, characterized in that, Including: A data acquisition module, a growth trend prediction module, an irrigation water requirement calculation module, a growth trend correction module, and an irrigation water requirement correction module; The data acquisition module is used to collect crop growth environment data, including temperature and humidity data, light data, and soil moisture data of the crop growth environment; The growth trend prediction module, based on a machine learning algorithm, constructs a crop growth model according to the crop growth environment data, crop type, and growth time to predict the crop growth trend; The irrigation water requirement calculation module calculates the irrigation water requirement during the crop growth period based on the constructed crop growth model and crop growth environment data; The growth trend correction module corrects the crop growth trend, periodically collects image data of the crop growth process, compares the collected image data with the standard image data of the crop growth process, and corrects the crop growth trend according to the comparison result; The irrigation water requirement correction module corrects the irrigation water requirement during the crop growth period based on the corrected crop growth trend and conducts irrigation according to the corrected crop irrigation water requirement.

9. An electronic device, characterized in that, Including: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the intelligent irrigation control method based on the intelligent crop growth model according to any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Stores instructions that, when run on a computer, cause the computer to execute the intelligent irrigation control method based on the intelligent crop growth model according to any one of claims 1 to 7.

Images