Intelligent irrigation decision-making method and system based on artificial intelligence algorithm

Through intelligent irrigation decision-making methods based on artificial intelligence algorithms, using crop growth data and meteorological forecast data, the optimal irrigation strategy is formulated, which solves the problems of waste of water resources and uneven crop growth in traditional irrigation systems, and achieves precise irrigation and agricultural production efficiency promote.

CN119026932APending Publication Date: 2024-11-26CAMCE WHU DESIGN & RES CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202410872265.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-01
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

Traditional agricultural irrigation systems lack the ability to adjust according to actual environmental changes and crop needs, resulting in the problems of waste of water resources and uneven crop growth.

Method used

Using intelligent irrigation decision-making method based on artificial intelligence algorithms, we can obtain crop growth data, perform feature vector normalization processing, select important feature data to input machine learning models for training and deep neural network optimization, and combine weather forecast data to formulate optimal irrigation. Strategy, determine irrigation time, frequency, and water volume.

Benefits of technology

Accurate irrigation has been achieved, agricultural water use has been optimized, water resources have been avoided and unbalanced crop growth has been avoided, and agricultural production efficiency and crop quality have been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026932A_ABST
    Figure CN119026932A_ABST
Patent Text Reader

Abstract

The invention relates to an intelligent irrigation decision-making method based on an artificial intelligence algorithm, and the method comprises the steps: obtaining crop growth data which at least comprises the soil humidity, the environment temperature, the illumination intensity, the wind speed, the air humidity and the crop growth state; performing normalization processing on the feature vectors; selecting important feature data, and inputting the important feature data into a machine learning model to train the model so as to predict the instant moisture demand of the crop; inputting a prediction result of the machine learning model and the selected feature data into a deep neural network model for further optimization and prediction; introducing weather forecast data as additional input to formulate an optimal irrigation strategy, and determining irrigation time, frequency and water volume; and executing irrigation operation according to the optimal irrigation strategy. The agricultural irrigation system has the advantages that agricultural water can be optimized, accurate irrigation is achieved, the problems of water resource waste, crop growth imbalance and the like are solved, and therefore the agricultural production efficiency and the crop quality are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of modern agricultural technology, and in particular to an intelligent irrigation decision-making method and system based on an artificial intelligence algorithm. Background Art

[0002] Traditional agricultural irrigation systems usually rely on preset irrigation time and water volume, and lack the ability to adjust according to actual environmental changes and crop needs, resulting in problems such as water waste and uneven crop growth. With the development of artificial intelligence technology, the application of AI algorithms to agricultural irrigation decisions can achieve precise irrigation and improve agricultural production efficiency and crop quality. To this end, an intelligent irrigation decision-making method and system based on artificial intelligence algorithms is proposed to achieve scientific and efficient irrigation management. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an intelligent irrigation decision-making method and system based on artificial intelligence algorithm to overcome the deficiencies in the above-mentioned prior art.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: an intelligent irrigation decision-making method based on an artificial intelligence algorithm comprises the following steps:

[0005] Step 1. Obtain crop growth data, including at least: soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status;

[0006] Step 2, normalize the feature vector;

[0007] Step 3: Select important feature data and input them into the machine learning model to train the model to predict the immediate water demand of crops;

[0008] Step 4: Input the prediction results of the machine learning model and the selected feature data into the deep neural network model for further optimization and prediction;

[0009] Step 5: Introduce weather forecast data as additional input to develop the optimal irrigation strategy and determine the irrigation time, frequency and water volume;

[0010] Step 6. Perform irrigation operations according to the optimal irrigation strategy.

[0011] Based on the above technical solution, the present invention can also be improved as follows.

[0012] Furthermore, the feature vector formed in Step 1 is:

[0013]

[0014] Among them, X soilis soil moisture, X temp is the ambient temperature, X light is the light intensity, X wind is wind speed, X humidity is the air humidity, X crop The growth state of crops.

[0015] Furthermore, the formula for normalization in Step 2 is:

[0016]

[0017] Where μ and σ are the mean and standard deviation respectively.

[0018] Furthermore, the machine learning model used in Step 3 is the random forest model.

[0019] Further, Step 3 is as follows:

[0020] Step 31. Select feature data based on correlation analysis and input it into the machine learning model:

[0021]

[0022] Step 32: Train the machine learning model:

[0023]

[0024] in is the target variable (crop water demand), i.e., the predicted value of the random forest model, f RF is the trained random forest model, X selected,norm is the selected feature data after normalization, T i represents the i-th decision tree, and N is the total number of decision trees;

[0025] Step 33: Predict the crop's immediate water demand based on the trained model:

[0026]

[0027] in is the current predicted crop water demand, X selected,norm,current It is the feature data selected after normalization at the current moment.

[0028] Furthermore, in Step 33, for each new input sample X selected,norm,current , each decision tree T i A prediction value will be given, and the final prediction value is the average of all decision tree prediction values.

[0029] Further, Step 4 is as follows:

[0030] Step 41. Build and train the model

[0031] A deep neural network model is constructed, where the input layer is the normalized selected feature data and the prediction results of the machine learning model, and the output layer is the predicted value of crop water demand:

[0032]

[0033] in, is the predicted value of the deep neural network, f DNN is a trained deep neural network model;

[0034] Step 42: Model Optimization

[0035] The loss function is optimized using gradient descent to minimize the error between the predicted value and the actual value:

[0036]

[0037] Where n is the number of samples, and i are the predicted value and the actual value respectively.

[0038] 8. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 7 is characterized in that Step 5 is specifically:

[0039] Step 51: Combined with weather forecast

[0040] Introduce weather forecast data as additional input:

[0041] X aug =[X selected,norm ,X weather ]

[0042] Among them, X weather For future forecast data, at least including: temperature and rainfall;

[0043] Step 52: Optimize irrigation strategy

[0044] Given that the goal is to minimize irrigation prediction error and cost, the optimization objective function is expressed as:

[0045]

[0046] in, is the predicted water demand in the ith time period, WaterSupple(t i ,f i ,W i ) is the actual water supply in the i-th time period, which depends on the irrigation time t i, irrigation frequency f i and water volume W i , λ is a hyperparameter used to balance irrigation accuracy and cost, and Cost(t,f,W) is the total irrigation cost function;

[0047] The sum of squared prediction errors is:

[0048]

[0049] Irrigation costs:

[0050] λ·Cost(t,f,W)

[0051] WaterSupple(t i ,f i ,W i ) is defined as:

[0052] WaterSupple(t i ,f i ,W i ) = f i ·W i ·t i

[0053] Cost(t,f,W) is defined as:

[0054]

[0055] Among them, α t , α f , α W are the cost coefficients for irrigation time, frequency, and water volume, respectively;

[0056] During the optimization process, the constraints defined are:

[0057] Irrigation time per day i Cannot exceed a certain maximum value T max :

[0058] 0≤t i ≤T max

[0059] Irrigation frequency per day i Cannot exceed a certain maximum value F max :

[0060] 0≤f i ≤F max

[0061] Water volume per irrigation i Cannot exceed a certain maximum value W max :

[0062] 0≤W i ≤W max

[0063] Then, the linear programming optimization model is used to solve the optimal irrigation time, frequency and water volume according to the predicted water demand, and confirm whether the optimized irrigation time, frequency and water volume meet the actual operation requirements and constraints. If not, the optimization model or parameters need to be adjusted and optimized again. If they meet, proceed to the next step;

[0064] Step 53: Final decision

[0065] Based on the optimization results, the final irrigation strategy is generated, including specific irrigation time, frequency and water volume:

[0066] IrrigationStrategy={t,f,W}.

[0067] Based on the above technical solution, the present invention also provides an intelligent irrigation decision system based on artificial intelligence algorithm, which runs the above intelligent irrigation decision method based on artificial intelligence algorithm, including:

[0068] Sensor unit, used to detect crop growth data, including: soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status;

[0069] A data preprocessing unit, used to obtain the crop growth data detected by the sensor unit, form it into a feature vector, and then perform normalization processing;

[0070] An artificial intelligence algorithm module is used to select important feature data after normalization and use it to train a machine learning model to predict the immediate water demand of crops. The prediction results of the machine learning model and the selected feature data are then input into a deep neural network model for further optimization and prediction;

[0071] An integrated decision-making unit that uses weather forecast data as additional input to develop optimal irrigation strategies and determine irrigation time, frequency, and water volume;

[0072] A communication unit, used to transmit the crop growth data acquired by the sensor unit and the optimal irrigation strategy formulated by the comprehensive decision-making unit to a remote server;

[0073] A remote server, used for sending the obtained optimal irrigation strategy to the execution unit;

[0074] An execution unit executes irrigation operations according to an optimal irrigation strategy.

[0075] Furthermore, the intelligent irrigation decision-making system based on artificial intelligence algorithm also includes:

[0076] The user terminal establishes communication with the remote server via the communication unit, displays the crop growth data detected by the sensor unit, the predicted instantaneous water demand of the crop and the generated optimal irrigation strategy, and allows the user to manually adjust the system parameters.

[0077] Further, the sensor unit includes: a soil moisture sensor, an ambient temperature sensor, a light intensity sensor, a wind speed sensor, an air humidity sensor, and a crop growth sensor;

[0078] The communication unit adopts NB-I oT wireless communication module;

[0079] The execution unit includes: a solenoid valve and a pump.

[0080] The beneficial effects of the present invention are: it can optimize agricultural water use and achieve precise irrigation to avoid problems such as water resource waste and uneven crop growth, thereby improving agricultural production efficiency and crop quality, and is suitable for farmlands, greenhouses and orchards that require efficient water resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a flow chart of the intelligent irrigation decision-making method based on artificial intelligence algorithm in the present invention;

[0082] Figure 2 It is a structural diagram of the intelligent irrigation decision-making system based on artificial intelligence algorithm in the present invention.

[0083] In the accompanying drawings, the components represented by the reference numerals are listed as follows:

[0084] 1. Sensor unit, 2. Data preprocessing unit, 3. Artificial intelligence algorithm module, 4. Comprehensive decision-making unit, 5. Communication unit, 6. Remote server, 7. Execution unit, 8. User terminal. DETAILED DESCRIPTION

[0085] The principles and features of the present invention are described below in conjunction with the accompanying drawings. The examples given are only used to explain the present invention and are not used to limit the scope of the present invention.

[0086] Example 1

[0087] like Figure 1 As shown, the intelligent irrigation decision-making method based on artificial intelligence algorithm includes the following steps:

[0088] Step 1. Obtain crop growth data, including at least soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status, and transform it into a feature vector;

[0089] Step 2: Normalize the feature vector to ensure the stability of subsequent machine learning model training;

[0090] Step 3: Select important feature data and input them into the machine learning model to train the model to predict the immediate water demand of crops;

[0091] Step 4: Input the prediction results of the machine learning model and the selected feature data into the deep neural network model for further optimization and prediction;

[0092] Step 5: Introduce weather forecast data as additional input to develop the optimal irrigation strategy and determine the irrigation time, frequency and water volume;

[0093] Step 6. Perform irrigation operations according to the optimal irrigation strategy.

[0094] Example 2

[0095] like Figure 1 As shown, this embodiment is a further improvement on the basis of embodiment 1, and the details are as follows:

[0096] The feature vector formed in Step 1 is:

[0097]

[0098] Among them, X soil is soil moisture, X temp is the ambient temperature, X light is the light intensity, X wind is wind speed, X humidity is the air humidity, X crop The growth state of crops.

[0099] The normalization formula in Step 2 is:

[0100]

[0101] Where μ and σ are the mean and standard deviation respectively.

[0102] Example 3

[0103] like Figure 1 As shown, this embodiment is a further improvement on the basis of embodiment 2, and the details are as follows:

[0104] The machine learning model used in Step 3 is the random forest model.

[0105] Among them, Step 3 is specifically as follows:

[0106] Step 31. Select feature data based on correlation analysis and input it into the machine learning model:

[0107]

[0108] That is, the selected characteristic data is: X soil is soil moisture, X temp is the ambient temperature, X light is the light intensity, X humidity is the air humidity;

[0109] Step 32: Train the machine learning model:

[0110]

[0111] in is the target variable (crop water demand), i.e., the predicted value of the random forest model, f RF is the trained random forest model, X selected,norm is the selected feature data after normalization, T i represents the i-th decision tree, and N is the total number of decision trees;

[0112] Step 33: Predict the crop's immediate water demand based on the trained model:

[0113]

[0114] in is the current predicted crop water demand, X selected,norm,current It is the feature data selected after normalization at the current moment;

[0115] For each new input sample X selected,norm,current , each decision tree T i A prediction value will be given, and the final prediction value is the average of all decision tree prediction values.

[0116] Example 4

[0117] like Figure 1 As shown, this embodiment is a further improvement on the basis of embodiment 3, and the details are as follows:

[0118] Step 4 is as follows:

[0119] Step 41. Build and train the model

[0120] A deep neural network (DNN) model is constructed. The input layer is the normalized selected feature data and the prediction results of the machine learning model, and the output layer is the predicted value of crop water demand:

[0121]

[0122] in, is the predicted value of the deep neural network, f DNNis a trained deep neural network model;

[0123] Step 42: Model Optimization

[0124] The loss function is optimized using gradient descent to minimize the error between the predicted value and the actual value:

[0125]

[0126] Where n is the number of samples, and i are the predicted value and the actual value respectively.

[0127] Example 5

[0128] like Figure 1 As shown, this embodiment is a further improvement on the basis of embodiment 4, and the details are as follows:

[0129] Step 5 is as follows:

[0130] Step 51: Combined with weather forecast

[0131] Introducing weather forecast data as additional input to improve the accuracy of the forecast:

[0132] X aug =[X selected,norm ,X weather ]

[0133] Among them, X weather For future forecast data, at least including: temperature and rainfall;

[0134] Step 52: Optimize irrigation strategy

[0135] Given that the goal is to minimize irrigation prediction error and cost, the optimization objective function is expressed as:

[0136]

[0137] in, is the predicted water demand in the ith time period, WaterSupple(t i ,f i ,W i ) is the actual water supply in the i-th time period, which depends on the irrigation time t i , irrigation frequency f i and water volume W i , λ is a hyperparameter used to balance irrigation accuracy and cost, and Cost(t,f,W) is the total irrigation cost function;

[0138] The variable to be optimized is the irrigation time t i , irrigation frequency fi and irrigation water volume W i , the above objective function consists of the following two parts: the sum of squares of the prediction error and the irrigation cost:

[0139] The sum of squared prediction errors is:

[0140]

[0141] Irrigation costs:

[0142] λ·Cost(t,f,W)

[0143] WaterSupple(t i ,f i ,W i ) is defined as:

[0144] WaterSupple(t i ,f i ,W i ) = f i ·W i ·t i

[0145] Cost(t,f,W) is defined as:

[0146]

[0147] Among them, α t , α f , α W are the cost coefficients for irrigation time, frequency, and water volume, respectively;

[0148] During the optimization process, first define the constraints:

[0149] Irrigation time per day i Cannot exceed a certain maximum value T max :

[0150] 0≤t i ≤T max

[0151] Irrigation frequency per day i Cannot exceed a certain maximum value F max :

[0152] 0≤f i ≤F max

[0153] Water volume per irrigation i Cannot exceed a certain maximum value W max :

[0154] 0≤W i ≤Wmax

[0155] Then, the linear programming optimization model is used to solve the optimal irrigation time, frequency and water volume according to the predicted water demand, and confirm whether the optimized irrigation time, frequency and water volume meet the actual operation requirements and constraints. If not, the optimization model or parameters need to be adjusted and optimized again. If they meet, proceed to the next step;

[0156] Step 53: Final decision

[0157] Based on the optimization results, the final irrigation strategy is generated, including specific irrigation time, frequency and water volume:

[0158] IrrigationStrategy={t,f,W}.

[0159] Example 6

[0160] like Figure 2 As shown, the intelligent irrigation decision system based on artificial intelligence algorithm runs the intelligent irrigation decision method based on artificial intelligence algorithm as described in any one of embodiments 1 to 5, including:

[0161] The sensor unit 1, the data preprocessing unit 2, the artificial intelligence algorithm module 3, the comprehensive decision unit 4, the remote server 6 and the execution unit 7 are electrically connected in sequence;

[0162] The sensor unit 1 is used to detect crop growth data, including: soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status;

[0163] The data preprocessing unit 2 is used to obtain the crop growth data detected by the sensor unit 1, form it into a feature vector, and then perform normalization processing;

[0164] The artificial intelligence algorithm module 3 is used to select the important feature data after normalization, and use it to train the machine learning model to predict the immediate water demand of crops, and then input the prediction results of the machine learning model and the selected feature data into the deep neural network model for further optimization and prediction;

[0165] The integrated decision-making unit 4 takes the weather forecast data as additional input to formulate the optimal irrigation strategy and determine the irrigation time, frequency and water volume;

[0166] The communication unit 5 is used to transmit the crop growth data acquired by the sensor unit 1 and the optimal irrigation strategy formulated by the comprehensive decision-making unit 4 to the remote server 6;

[0167] The remote server 6 is used to send the acquired optimal irrigation strategy to the execution unit 7;

[0168] The execution unit 7 executes the irrigation operation according to the optimal irrigation strategy.

[0169] Going a step further: The intelligent irrigation decision-making system based on artificial intelligence algorithms also includes:

[0170] The user terminal 8 establishes communication with the remote server 6 via the communication unit 5, and displays the crop growth data detected by the sensor unit 1, the predicted instantaneous water demand of the crop and the generated optimal irrigation strategy, and allows the user to manually adjust the system parameters.

[0171] The sensor unit 1 includes: a soil moisture sensor, an ambient temperature sensor, a light intensity sensor, a wind speed sensor, an air humidity sensor and a crop growth sensor; wherein the soil moisture sensor is used to detect soil moisture; the ambient temperature sensor is used to monitor ambient temperature; the light intensity sensor is used to detect light intensity; the wind speed sensor is used to monitor wind speed; the air humidity sensor is used to detect air humidity; and the crop growth sensor is used to monitor crop growth status.

[0172] The communication unit 5 adopts a NB-I oT wireless communication module, that is, the comprehensive decision unit 4 is wirelessly connected to the remote server 6 via the communication unit 5, and the remote server 6 is wirelessly connected to the user terminal 8 via the communication unit 5;

[0173] The data preprocessing unit 2 includes a high-performance computing chip and a data storage module, and is used to receive and process sensor data.

[0174] The execution unit 7 includes: electromagnetic valves, pumps and other equipment, which are used to perform precise irrigation operations according to the optimal irrigation strategy.

[0175] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent irrigation decision-making method based on artificial intelligence algorithm, characterized in that: The following steps are involved: Step 1. Obtain crop growth data, including at least: soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status; Step 2, normalize the feature vector; Step 3: Select important feature data and input them into the machine learning model to train the model to predict the immediate water demand of crops; Step 4: Input the prediction results of the machine learning model and the selected feature data into the deep neural network model for further optimization and prediction; Step 5: Introduce weather forecast data as additional input to develop the optimal irrigation strategy and determine the irrigation time, frequency and water volume; Step 6. Perform irrigation operations according to the optimal irrigation strategy.

2. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 1 is characterized in that: The feature vector formed in Step 1 is: Among them, X soil is soil moisture, X temp is the ambient temperature, X light is the light intensity, X wind is wind speed, X humidity is the air humidity, X crop The growth state of crops.

3. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 1 or 2, characterized in that: The formula for normalization in Step 2 is: Where μ and σ are the mean and standard deviation respectively.

4. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 1, 2 or 3, characterized in that: The machine learning model used in Step 3 is the random forest model.

5. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 4 is characterized in that: Step 3 is as follows: Step 31. Select feature data based on correlation analysis and input it into the machine learning model: Step 32: Train the machine learning model: in is the target variable (crop water demand), i.e., the predicted value of the random forest model, f RF is the trained random forest model, X selected,norm is the selected feature data after normalization, T i represents the i-th decision tree, and N is the total number of decision trees; Step 33: Predict the crop's immediate water demand based on the trained model: in is the current predicted crop water demand, X selected,norm,current It is the feature data selected after normalization at the current moment.

6. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 5 is characterized in that: In Step 33, for each new input sample X selected,norm,current , each decision tree T i A prediction value will be given, and the final prediction value is the average of all decision tree prediction values.

7. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to any one of claims 1 to 6, characterized in that: Step 4 is as follows: Step 41. Build and train the model A deep neural network model is constructed, where the input layer is the normalized selected feature data and the prediction results of the machine learning model, and the output layer is the predicted value of crop water demand: in, is the predicted value of the deep neural network, f DNN is a trained deep neural network model; Step 42: Model Optimization The loss function is optimized using gradient descent to minimize the error between the predicted value and the actual value: Where n is the number of samples, and i are the predicted value and the actual value respectively.

8. The intelligent irrigation decision-making method based on artificial intelligence algorithm according to claim 7 is characterized in that: Step 5 is as follows: Step 51: Combined with weather forecast Introduce weather forecast data as additional input: Among them, X weather For future forecast data, at least including: temperature and rainfall; Step 52: Optimize irrigation strategy Given that the goal is to minimize irrigation prediction error and cost, the optimization objective function is expressed as: in, is the predicted water demand in the i-th time period, WaterSupple(t i ,f i ,W i ) is the actual water supply in the i-th time period, which depends on the irrigation time t i , irrigation frequency f i and water volume W i , λ is a hyperparameter used to balance irrigation accuracy and cost, and Cost(t,f,W) is the total irrigation cost function; The sum of squared prediction errors is: Irrigation costs: λ·Cost(t,f,W) WaterSupple(t i ,f i ,W i ) is defined as: WaterSupple(t i ,f i ,W i )=f i ·W i ·t i Cost(t,f,W) is defined as: Among them, α t , α f , α W are the cost coefficients for irrigation time, frequency, and water volume, respectively; During the optimization process, the constraints defined are: Irrigation time per day i Cannot exceed a certain maximum value T max : 0≤t i ≤T max Irrigation frequency per day i Cannot exceed a certain maximum value F max : 0≤f i ≤F max Water volume per irrigation i Cannot exceed a certain maximum value W max : 0≤W i ≤W max Then, the linear programming optimization model is used to solve the optimal irrigation time, frequency and water volume according to the predicted water demand, and confirm whether the optimized irrigation time, frequency and water volume meet the actual operation requirements and constraints. If not, the optimization model or parameters need to be adjusted and optimized again. If they meet, proceed to the next step; Step 53: Final decision Based on the optimization results, the final irrigation strategy is generated, including specific irrigation time, frequency and water volume: IrrigationStrategy={t,f,W}.

9. Intelligent irrigation decision-making system based on artificial intelligence algorithm, characterized by: Running the intelligent irrigation decision-making method based on artificial intelligence algorithm as claimed in any one of claims 1 to 8 comprises: A sensor unit (1) is used to detect crop growth data, including soil moisture, ambient temperature, light intensity, wind speed, air humidity and crop growth status; A data preprocessing unit (2) is used to obtain the crop growth data detected by the sensor unit (1), form a feature vector, and then perform normalization processing; An artificial intelligence algorithm module (3) is used to select important feature data after normalization and use it to train a machine learning model to predict the immediate water demand of crops, and then input the prediction results of the machine learning model and the selected feature data into a deep neural network model for further optimization and prediction; The integrated decision-making unit (4) uses weather forecast data as additional input to develop the optimal irrigation strategy and determine the irrigation time, frequency, and water volume; A communication unit (5) for transmitting the crop growth data acquired by the sensor unit (1) and the optimal irrigation strategy formulated by the comprehensive decision-making unit (4) to a remote server (6); A remote server (6) is used to send the obtained optimal irrigation strategy to an execution unit (7); An execution unit (7) executes irrigation operations according to the optimal irrigation strategy.

10. The intelligent irrigation decision-making system based on artificial intelligence algorithm according to claim 9, characterized in that: Also includes: The user terminal (8) establishes communication with the remote server (6) via the communication unit (5), displays the crop growth data detected by the sensor unit (1), the predicted instantaneous water demand of the crop and the generated optimal irrigation strategy, and allows the user to manually adjust the system parameters.

Citation Information

Cited By

  • Intelligent agriculture method and system based on Internet of Things and artificial intelligence

    CN119444477A

  • Intelligent irrigation method for crops

    CN119629204A

  • Intelligent greenhouse temperature control method based on multi-source sensor

    CN120066169A

  • Artificial intelligence decision system for unmanned agricultural operation

    CN120611992A