A jasmine soil moisture monitoring system and method

Abstract

The present invention discloses a jasmine soil moisture monitoring system and method, which belongs to the field of monitoring technology, and includes: distributed multi-type sensors: installed along the periphery of the soil to be monitored, and used to monitor the environmental parameters around the soil and the internal parameters of the soil in real time; data transmission module: collects the data of the distributed multi-type sensors. In the present invention, through this jasmine soil moisture monitoring system and method, through precise monitoring and intelligent control, the monitoring of multiple parameters such as soil temperature, electrical conductivity, pH value, etc. is increased, and comprehensive information is provided for agricultural production. The system can intelligently analyze data, predict changing trends, support irrigation decisions, and integrate multiple sensors to comprehensively monitor the ecological environment. It not only improves the intelligence level of the irrigation system, improves irrigation efficiency, but also reduces resource waste, and provides a precise and efficient irrigation plan for jasmine planting, thereby helping to improve the growth quality and yield of jasmine.

Description

Technical Field

[0001] The invention belongs to the technical field of monitoring, and in particular relates to a jasmine soil moisture monitoring system and method. Background Art

[0002] With the advancement of science and technology, people have higher and higher requirements for crop planting. Jasmine likes warm and humid environment and grows best in a well-ventilated and semi-shaded environment. The existing jasmine cannot detect the lack of water in the crop in time during the growth process, thereby reducing the crop yield. Therefore, there is an urgent need for a method that can monitor the moisture content of the soil during the growth of crops and replenish the moisture of the soil in time;

[0003] In the prior art, by calculating the difference between the soil moisture content and the preset moisture content, the preset difference range to which the difference belongs can be determined, and finally the opening time of the valve at the corresponding position can be controlled and irrigation can be performed according to actual needs. The prior art is limited to the soil moisture content, which limits the comprehensiveness of its functions in practical applications. Because the growth environment of jasmine is complex and changeable, and is affected by the joint action of multiple environmental factors, a single data monitoring is obviously not enough to cover the full range of its growth needs, which undoubtedly reduces the actual application scope and utility of the system.

[0004] Based on this, the present invention designs a jasmine soil moisture monitoring system and method to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to solve the problem that the prior art is limited to soil moisture content, which limits the comprehensiveness of its functions in practical applications. Because the growth environment of jasmine is complex and changeable, and is affected by the joint action of multiple environmental factors, a single data monitoring is obviously not enough to cover the full range of its growth needs, which undoubtedly reduces the practical application scope and effectiveness of the system, and a jasmine soil moisture monitoring system and method are proposed.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A jasmine soil moisture monitoring system, comprising:

[0008] Distributed multi-type sensors: installed along the periphery of the soil to be monitored, used to monitor the environmental parameters around the soil and the internal parameters of the soil in real time;

[0009] Data transmission module: collects data from distributed multi-type sensors;

[0010] Data preprocessing module: responsible for denoising and normalizing the original data;

[0011] Feature extraction module; responsible for extracting key features from preprocessed data;

[0012] Data storage module: responsible for storing the processed data in the database for subsequent analysis;

[0013] Control center: Receives data, analyzes and processes it by establishing a data prediction model, and issues irrigation instructions based on preset thresholds;

[0014] Irrigation execution system: used to perform automatic irrigation according to the instructions of the control center;

[0015] Power management system: provides stable power supply for the monitoring system;

[0016] Display and alarm system: used to display soil moisture data and issue alarms in abnormal situations.

[0017] As a further description of the above technical solution:

[0018] The distributed multi-type sensor can detect environmental parameters around the soil and internal parameters of the soil, the environmental parameters being such as light intensity, temperature, and carbon dioxide concentration, and the internal parameters of the soil being such as soil moisture, soil temperature, electrical conductivity, and pH value.

[0019] As a further description of the above technical solution:

[0020] The control center includes a database for storing historical data for long-term analysis and trend prediction. The irrigation execution system includes a water pump and a solenoid valve. The water pump can provide water with different pressures and flows as needed. The solenoid valve can control the on and off of the water flow and respond quickly. The power management system includes batteries, solar panels and AC adapters to ensure stable operation of the system in various environments. The display and alarm system is an LED display screen, and the alarm system can notify users of potential problems through sound, light or mobile applications.

[0021] As a further description of the above technical solution:

[0022] The establishment of the data prediction model includes the following steps:

[0023] Model construction, select the multivariate linear regression model for intelligent analysis of jasmine soil moisture, and configure hyperparameters to predict the trend of soil internal moisture;

[0024] Model training, using training set data to train the model, usually using the least squares method to estimate the parameter β;

[0025] Model evaluation, using the test set to evaluate the performance of the model;

[0026] Model prediction, using the trained model for prediction;

[0027] Model deployment, transferring the predicted results to the actual display screen.

[0028] As a further description of the above technical solution:

[0029] The data prediction model is specifically expressed by the multivariate linear regression formula as follows:

[0030] SW=β0+β1×Time+β2×Rainfall+β3×SoilType+…+ε;

[0031] SW(Soil Moisture):

[0032] This is the dependent or response variable that we want to predict and it represents the amount of water in the soil.

[0033] β0 (intercept term):

[0034] This is the constant term in the model, also known as the intercept. It represents the soil moisture content when all independent (explanatory) variables are zero. In real-world applications, this may not have practical significance, but it is part of the model formula.

[0035] β1:

[0036] This is the coefficient of the time variable. It indicates the average change in soil moisture content for each unit increase in time (such as one day), with other conditions remaining constant.

[0037] β2:

[0038] This is the coefficient of the rainfall variable. It indicates how much, on average, the soil moisture content changes for each unit increase in rainfall (e.g., one millimeter), other things remaining the same.

[0039] β3:

[0040] This is the coefficient for the soil type variable. Since soil type is a categorical variable, it is usually necessary to convert it into a dummy variable or use one-hot encoding. The coefficient β3 represents the effect of a particular soil type on soil moisture content compared to other soil types.

[0041] …:

[0042] This ellipsis indicates that there may be other independent variables in the model. These independent variables can be other factors that affect soil moisture, such as temperature, humidity, wind speed, etc.

[0043] ε (error term):

[0044] This is the error term of the model, also called the residual. It represents the difference between the soil moisture content predicted by the model and the actual observed value. The error term reflects the unobserved randomness in the model and the imperfections of the model.

[0045] The whole formula means that the soil moisture content (SW) is determined by multiple independent variables, an intercept term (β0), and an error term (ε). The goal of the model is to estimate these coefficients (β0, β1, β2, β3, etc.) by analyzing the data so that the soil moisture content can be predicted for a given value of the independent variable. By minimizing the error term ε, the model attempts to find the parameter estimate that best describes the variation of the soil moisture content in the data.

[0046] As a further description of the above technical solution:

[0047] The hyperparameters include soil moisture, soil temperature, electrical conductivity, and pH value.

[0048] As a further description of the above technical solution:

[0049] The processing of categorical variables includes the following steps:

[0050] Identify categorical variables: Determine which variables in the dataset are categorical;

[0051] Transform data: Convert categorical variables into multiple binary columns using one-hot encoding;

[0052] Integrate data: merge the transformed columns with the rest of the original dataset;

[0053] Model training: Use the transformed data to train a machine learning model.

[0054] As a further description of the above technical solution:

[0055] The one-hot encoding can be implemented using the get_dummies function of the pandas library. The specific steps are as follows:

[0056] 1. import pandas as pd

[0057] 2. Load data into DataFrame

[0058] 3. #Assume df is a DataFrame containing a soil type column

[0059] 4. df_encoded=pd.get_dummies(df, columns=['SoilType']).

[0060] As a further description of the above technical solution:

[0061] The data transmission is performed in a wireless transmission manner.

[0062] A method for monitoring soil moisture of jasmine flowers, comprising the following steps:

[0063] The various parameter data of jasmine soil are collected in real time through distributed multi-type sensors;

[0064] Transmit the collected soil parameter data to the data preprocessing module;

[0065] Then, after extracting features from the feature extraction module, the data is stored in the data storage module;

[0066] The control center receives the data and performs real-time analysis on the soil data to determine whether the soil environment is within a range suitable for jasmine growth;

[0067] Based on the soil data analysis results, the control center then issues irrigation instructions;

[0068] Use the multivariate linear regression formula to establish a data prediction model to predict the changes in multiple parameters;

[0069] The irrigation execution system irrigates the jasmine flowers according to the instructions of the control center;

[0070] The monitoring system displays real-time soil parameter data and irrigation status on the display screen, and issues an alarm in abnormal situations;

[0071] According to the growth stage of jasmine, climatic conditions and other factors, the parameters of the soil moisture monitoring system are adjusted in time to adapt to different growth needs.

[0072] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0073] In the present invention, through the jasmine soil moisture monitoring system and method, through precise monitoring and intelligent control, the monitoring of multiple parameters such as soil temperature, conductivity, pH value, etc. is increased, providing comprehensive information for agricultural production. The system can intelligently analyze data, predict changing trends, support irrigation decisions, and integrate multiple sensors to comprehensively monitor the ecological environment. Not only does it improve the intelligence level of the irrigation system, improve irrigation efficiency, but it also reduces resource waste, and provides a precise and efficient irrigation plan for jasmine planting, thereby helping to improve the growth quality and yield of jasmine. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 A schematic diagram of the system composition of a jasmine soil moisture monitoring system proposed by the present invention;

[0075] Figure 2 A schematic diagram of a model establishment process of a jasmine soil moisture monitoring system proposed by the present invention;

[0076] Figure 3 This is a schematic diagram of the steps for processing classification variables of a jasmine soil moisture monitoring system proposed by the present invention. DETAILED DESCRIPTION

[0077] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0078] Please refer to the attached Figure 1 -Attached Figure 3 The present invention provides a technical solution: a jasmine soil moisture monitoring system, comprising:

[0079] Distributed multi-type sensors: installed along the periphery of the soil to be monitored, used to monitor the environmental parameters around the soil and the internal parameters of the soil in real time;

[0080] Data transmission module: collects data from distributed multi-type sensors;

[0081] Data preprocessing module: responsible for denoising and normalizing the original data;

[0082] Feature extraction module; responsible for extracting key features from preprocessed data;

[0083] Data storage module: responsible for storing the processed data in the database for subsequent analysis;

[0084] Control center: Receives data, analyzes and processes it by establishing a data prediction model, and issues irrigation instructions based on preset thresholds;

[0085] Irrigation execution system: used to perform automatic irrigation according to the instructions of the control center;

[0086] Power management system: provides stable power supply for the monitoring system;

[0087] Display and alarm system: used to display soil moisture data and issue alarms in abnormal situations.

[0088] Distributed multi-type sensors can detect environmental parameters around the soil and internal parameters of the soil, such as light intensity, temperature, and carbon dioxide concentration, while internal parameters of the soil include soil moisture, soil temperature, conductivity, and pH value. The control center includes a database for storing historical data for long-term analysis and trend prediction. The irrigation execution system includes a water pump and a solenoid valve. The water pump can provide water with different pressures and flows as needed. The solenoid valve can control the switch of the water flow and respond quickly. The power management system includes batteries, solar panels, and AC adapters to ensure stable operation of the system in various environments. The display and alarm system is an LED display, and the alarm system can notify users of potential problems through sound, light, or mobile applications.

[0089] The establishment of the data prediction model includes the following steps:

[0090] Model construction, select the multivariate linear regression model for intelligent analysis of jasmine soil moisture, and configure hyperparameters to predict the trend of soil internal moisture;

[0091] Model training, using training set data to train the model, usually using the least squares method to estimate the parameter β;

[0092] Model evaluation, using the test set to evaluate the performance of the model;

[0093] Model prediction, using the trained model for prediction;

[0094] Model deployment, transferring the predicted results to the actual display screen.

[0095] The data prediction model is specifically expressed by the multivariate linear regression formula:

[0096] SW=β0+β1×Time+β2×Rainfall+β3×SoilType+…+ε;

[0097] SW(Soil Moisture):

[0098] This is the dependent or response variable that we want to predict and it represents the amount of water in the soil.

[0099] β0 (intercept term):

[0100] This is the constant term in the model, also known as the intercept. It represents the soil moisture content when all independent (explanatory) variables are zero. In real-world applications, this may not have practical significance, but it is part of the model formula.

[0101] Beta:

[0102] This is the coefficient of the time variable. It indicates the average change in soil moisture content for each unit increase in time (such as one day), with other conditions remaining constant.

[0103] β2:

[0104] This is the coefficient of the rainfall variable. It indicates how much, on average, the soil moisture content changes for each unit increase in rainfall (e.g., one millimeter), other things remaining the same.

[0105] β3:

[0106] This is the coefficient for the soil type variable. Since soil type is a categorical variable, it is usually necessary to convert it into a dummy variable or use one-hot encoding. The coefficient β3 represents the effect of a particular soil type on soil moisture content compared to other soil types.

[0107] …:

[0108] This ellipsis indicates that there may be other independent variables in the model. These independent variables can be other factors that affect soil moisture, such as temperature, humidity, wind speed, etc.

[0109] ε (error term):

[0110] This is the error term of the model, also called the residual. It represents the difference between the soil moisture content predicted by the model and the actual observed value. The error term reflects the unobserved randomness in the model and the imperfections of the model.

[0111] The whole formula means that the soil moisture content (SW) is determined by multiple independent variables, an intercept term (β0), and an error term (ε). The goal of the model is to estimate these coefficients (β0, β1, β2, β3, etc.) by analyzing the data so that the soil moisture content can be predicted for a given value of the independent variable. By minimizing the error term ε, the model attempts to find the parameter estimate that best describes the variation of the soil moisture content in the data. Hyperparameters include soil moisture, soil temperature, conductivity, and pH.

[0112] Processing categorical variables involves the following steps:

[0113] Identify categorical variables: This includes data review, data type check, and business logic understanding. First, review the metadata of the dataset or use data exploration techniques (such as descriptive statistics) to identify which variables are categorical. Usually, categorical variables appear as strings or categories in the dataset. Understand the business context and model requirements to determine which variables should be considered categorical variables.

[0114] Transform the data: One-hot encoding, label encoding, and binary encoding can be used. Use a one-hot encoder to transform each categorical variable into a series of binary columns (also called dummy variables), where each column represents a possible category.

[0115] For example, if there is a categorical variable called "color" with three possible values ​​"red", "green", and "blue", one-hot encoding will convert it into three binary columns: "color_red", "color_green", and "color_blue";

[0116] Label encoding:

[0117] Another approach is to convert categorical variables into integers, which works well for ordered categorical variables;

[0118] Binary encoding:

[0119] For categorical variables with a large number of categories, binary encoding can be used to reduce the number of generated columns.

[0120] Integrate data: This includes merging data and aligning data. New columns that have been one-hot encoded are added to the rest of the original dataset to form a complete feature set, ensuring that the transformed data is aligned with other variables in the original dataset.

[0121] Model training: including data segmentation, feature selection, model training and model evaluation;

[0122] Data splitting: Split the integrated dataset into training and testing sets.

[0123] Feature selection: Select appropriate features based on the model requirements and feature importance.

[0124] Model training: Use the training set data to train the machine learning model. Ensure that the model can learn useful patterns from the converted categorical features.

[0125] Model evaluation: Use the test set to evaluate the performance of the model and ensure that the model has good generalization ability.

[0126] One-hot encoding can be implemented using the get_dummies function of the pandas library. The specific steps are as follows:

[0127] 1. import pandas as pd

[0128] 2. Load data into DataFrame

[0129] 3. #Assume df is a DataFrame containing a soil type column

[0130] 4. df_encoded=pd.get_dummies(df, columns=['SoilType']).

[0131] Data transmission is carried out by wireless transmission.

[0132] A jasmine soil moisture monitoring method comprises the following steps:

[0133] The various parameter data of jasmine soil are collected in real time through distributed multi-type sensors;

[0134] Transmit the collected soil parameter data to the data preprocessing module;

[0135] Then, after extracting features from the feature extraction module, the data is stored in the data storage module;

[0136] The control center receives the data and performs real-time analysis on the soil data to determine whether the soil environment is within a range suitable for jasmine growth;

[0137] Based on the soil data analysis results, the control center then issues irrigation instructions;

[0138] Use the multivariate linear regression formula to establish a data prediction model to predict the changes in multiple parameters;

[0139] The irrigation execution system irrigates the jasmine flowers according to the instructions of the control center;

[0140] The monitoring system displays real-time soil parameter data and irrigation status on the display screen, and issues an alarm in abnormal situations;

[0141] According to the growth stage of jasmine, climatic conditions and other factors, the parameters of the soil moisture monitoring system are adjusted in time to adapt to different growth needs.

[0142] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A jasmine soil moisture monitoring system, characterized in that: include: Distributed multi-type sensors: installed along the periphery of the soil to be monitored, used to monitor the environmental parameters around the soil and the internal parameters of the soil in real time; Data transmission module: collects data from distributed multi-type sensors; Data preprocessing module: responsible for denoising and normalizing the original data; Feature extraction module; Responsible for extracting key features from preprocessed data; Data storage module: responsible for storing the processed data in the database for subsequent analysis; Control center: Receives data, analyzes and processes it by establishing a data prediction model, and issues irrigation instructions based on preset thresholds; Irrigation execution system: used to perform automatic irrigation according to the instructions of the control center; Power management system: provides stable power supply for the monitoring system; Display and alarm system: used to display soil moisture data and issue alarms in abnormal situations.

2. A jasmine soil moisture monitoring system according to claim 1, characterized in that, The distributed multi-type sensor can detect environmental parameters around the soil and internal parameters of the soil, the environmental parameters being such as light intensity, temperature, and carbon dioxide concentration, and the internal parameters of the soil being such as soil moisture, soil temperature, electrical conductivity, and pH value.

3. A jasmine soil moisture monitoring system according to claim 1, characterized in that: The control center includes a database for storing historical data for long-term analysis and trend prediction. The irrigation execution system includes a water pump and a solenoid valve. The water pump can provide water with different pressures and flows as needed. The solenoid valve can control the on and off of the water flow and respond quickly. The power management system includes batteries, solar panels and AC adapters to ensure stable operation of the system in various environments. The display and alarm system is an LED display screen, and the alarm system can notify users of potential problems through sound, light or mobile applications.

4. A jasmine soil moisture monitoring system according to claim 1, characterized in that: The establishment of the data prediction model includes the following steps: Model construction, select the multivariate linear regression model for intelligent analysis of jasmine soil moisture, and configure hyperparameters to predict the trend of soil internal moisture; Model training, using training set data to train the model, usually using the least squares method to estimate the parameter β; Model evaluation, using the test set to evaluate the performance of the model; Model prediction, using the trained model for prediction; Model deployment, transferring the predicted results to the actual display screen.

5. A jasmine soil moisture monitoring system according to claim 4, characterized in that: The data prediction model is specifically expressed by a multiple linear regression formula as follows: SW=β0+β1×Time+β2×Rainfall+β3×SoilType+…+ε; SW(Soil Moisture): This is the dependent or response variable that we want to predict and it represents the amount of water in the soil. β0 (intercept term): This is the constant term in the model, also known as the intercept. It represents the soil moisture content when all independent (explanatory) variables are zero. In real-world applications, this may not have practical significance, but it is part of the model formula. β1： This is the coefficient of the time variable. It indicates the average change in soil moisture content for each unit increase in time (such as one day), with other conditions remaining constant. β2： This is the coefficient of the rainfall variable. It indicates how much, on average, the soil moisture content changes for each unit increase in rainfall (e.g., one millimeter), other things remaining the same. β3： This is the coefficient for the soil type variable. Since soil type is a categorical variable, it is usually necessary to convert it into a dummy variable or use one-hot encoding. The coefficient β3 represents the effect of a particular soil type on soil moisture content compared to other soil types. …： This ellipsis indicates that there may be other independent variables in the model. These independent variables can be other factors that affect soil moisture, such as temperature, humidity, wind speed, etc. ε (error term): This is the error term of the model, also called the residual. It represents the difference between the soil moisture content predicted by the model and the actual observed value. The error term reflects the unobserved randomness in the model and the imperfections of the model. The whole formula means that the soil moisture content (SW) is determined by multiple independent variables, an intercept term (β0), and an error term (ε). The goal of the model is to estimate these coefficients (β0, β1, β2, β3, etc.) by analyzing the data so that the soil moisture content can be predicted for a given value of the independent variable. By minimizing the error term ε, the model attempts to find the parameter estimate that best describes the variation of the soil moisture content in the data.

6. A jasmine soil moisture monitoring system according to claim 4, characterized in that: The hyperparameters include soil moisture, soil temperature, electrical conductivity, and pH value.

7. A jasmine soil moisture monitoring system according to claim 3, characterized in that: The processing of categorical variables includes the following steps: Identify categorical variables: Determine which variables in the dataset are categorical; Transform data: Convert categorical variables into multiple binary columns using one-hot encoding; Integrate data: merge the transformed columns with the rest of the original dataset; Model training: Use the transformed data to train a machine learning model.

8. A jasmine soil moisture monitoring system according to claim 7, characterized in that: The one-hot encoding can be implemented using the get_dummies function of the pandas library. The specific steps are as follows:

1. import pandas as pd 2. Load data into DataFrame 3. #Assume df is a DataFrame containing a soil type column 4. df_encoded=pd.get_dummies(df, columns=['SoilType']).

9. A jasmine soil moisture monitoring system according to claim 1, characterized in that: The data transmission is performed in a wireless transmission manner.

10. A method for monitoring soil moisture of jasmine, according to a jasmine soil moisture monitoring system according to any one of claims 1 to 9, characterized in that: The jasmine soil moisture monitoring method comprises the following steps: The various parameter data of jasmine soil are collected in real time through distributed multi-type sensors; Transmit the collected soil parameter data to the data preprocessing module; Then, after extracting features from the feature extraction module, the data is stored in the data storage module; The control center receives the data and performs real-time analysis on the soil data to determine whether the soil environment is within a range suitable for jasmine growth; Based on the soil data analysis results, the control center then issues irrigation instructions; Use the multivariate linear regression formula to establish a data prediction model to predict the changes in multiple parameters; The irrigation execution system irrigates the jasmine flowers according to the instructions of the control center; The monitoring system displays real-time soil parameter data and irrigation status on the display screen, and issues an alarm in abnormal situations; According to the growth stage of jasmine, climatic conditions and other factors, the parameters of the soil moisture monitoring system are adjusted in time to adapt to different growth needs.

Images