Farmland irrigation management and control system based on Internet of Things

Abstract

The invention relates to the technical field of soil monitoring, in particular to a farmland irrigation management and control system based on the Internet of Things, and the system comprises a soil monitoring module, a crop water demand analysis module, an irrigation strategy making module, an irrigation execution control module, a water source management module, a fertilizer distribution module, an irrigation effect evaluation module and an adaptability adjustment module. According to the method, the crop water demand is analyzed by combining the decision tree, the water consumption is accurately calculated, the irrigation strategy optimizes the time and frequency based on the linear programming and simulated annealing method, the scheme adaptation degree is improved, the irrigation link adopts an automatic control and dynamic adjustment mechanism, the environment and crop demand changes are adapted in real time, and the irrigation efficiency is improved. Water source allocation ensures efficient distribution of multiple water sources on the basis of dynamic optimization, the type and quantity of fertilizer feeding are accurately controlled according to crop requirements, the irrigation effect is subjected to self-adaptive optimization of an irrigation plan after crop data evaluation, and accurate, flexible and efficient farmland resource management is integrally achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of soil monitoring, and in particular to a farmland irrigation control system based on the Internet of Things. Background Art

[0002] The field of soil monitoring technology includes the measurement and analysis of soil moisture, nutrients, temperature and other key parameters. The core content of this technical field is to provide a scientific basis for agricultural planting through the monitoring and data collection of soil physical and chemical properties. Soil monitoring technology usually includes soil parameter collection equipment, data transmission system and storage and analysis module of monitoring information. The systematic content of this technical field covers real-time monitoring of soil status, analysis of parameter change trends and provision of relevant decision support solutions, with the aim of improving agricultural management level and resource utilization efficiency.

[0003] Among them, the farmland irrigation control system refers to a technical device and method for optimizing the use of water resources by monitoring the state of farmland soil. The patent subject is aimed at technical matters such as farmland soil moisture monitoring, data collection, analysis and processing, and irrigation instruction execution. It collects data by configuring soil moisture sensors, transmits the monitoring data to the control system with wireless transmission equipment, and then controls the opening and closing operations of the irrigation equipment based on the soil moisture threshold. The system adopts a unified control process, from sensor data collection to the action control of the actuator, to achieve precise management of farmland irrigation water.

[0004] The existing technology has a single data monitoring model, usually focusing only on soil moisture and ignoring parameters such as temperature and pH value. This results in one-sided data and makes it difficult to fully support crop water demand analysis. Irrigation strategy formulation is mostly based on empirical formulas or fixed rules, lacking dynamic analysis and personalized adaptation, resulting in inflexible strategies. The irrigation execution process cannot be dynamically fed back and adjusted, resource utilization is unbalanced and prone to waste, water source management is mainly based on a single supply, and multiple water sources have not been allocated to meet complex needs. There is a lack of effect evaluation and improvement mechanism for crops and soil status after irrigation, and there are obvious limitations in system adaptability and management accuracy. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a farmland irrigation management and control system based on the Internet of Things.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a farmland irrigation control system based on the Internet of Things includes a soil monitoring module, a crop water demand analysis module, an irrigation strategy formulation module, an irrigation execution control module, a water source management module, a fertilizer distribution module, an irrigation effect evaluation module, and an adaptive adjustment module; The soil monitoring module is based on IoT devices and uses a sensor network to monitor soil moisture, pH value, and temperature indicators in real time, and uses a data aggregation algorithm to integrate data to generate soil status results; The crop water demand analysis module uses a decision tree analysis method based on the soil status results to analyze the water demand of crops, calculate the water demand, and generate a water demand analysis result; The irrigation strategy formulation module uses linear programming to formulate a comprehensive strategy for irrigation quantity, time and frequency based on the water demand analysis results, and uses simulated annealing algorithm to optimize the strategy and generate an irrigation strategy plan; The irrigation execution control module uses automatic control technology to irrigate based on the irrigation strategy plan, and uses a real-time feedback adjustment mechanism to monitor and adjust the irrigation execution and generate irrigation execution records; The water source management module manages and allocates water sources, including reservoirs, groundwater and recycled water, and uses a dynamic water source allocation algorithm to optimize allocation based on the irrigation execution record to generate a water source allocation plan; The fertilizer distribution module uses a decision support system to calculate the type and amount of fertilizers based on the water source allocation plan and crop growth requirements, and combines timing control to release fertilizers to generate a fertilizer distribution plan; The irrigation effect evaluation module collects crop growth data and soil conditions, and based on the fertilizer distribution plan, adopts an effect evaluation model to evaluate the irrigation effect and generate an irrigation effect evaluation result; The adaptive adjustment module adopts an adaptive adjustment algorithm based on the irrigation effect evaluation result to automatically adjust the irrigation strategy and execution plan to match the environmental changes and crop demand changes and generate an adjusted irrigation plan.

[0007] As a further scheme of the present invention, the soil status results include soil moisture index, pH, and temperature value; the water demand analysis results include average daily water demand and water demand during the growth stage; the irrigation strategy plan includes irrigation quantity parameters, irrigation schedule, and irrigation frequency plan; the irrigation execution record includes actual water volume, irrigation time, and irrigation effect evaluation; the water source allocation plan includes water source allocation ratio and deployment time schedule; the fertilizer distribution plan includes fertilizer type, fertilizer amount, and fertilization time; the irrigation effect evaluation results include crop growth rate, yield, and water resource utilization efficiency; the adjusted irrigation plan includes updated irrigation quantity, irrigation time, and irrigation frequency.

[0008] As a further solution of the present invention, the soil monitoring module includes a humidity detection submodule, a pH value detection submodule, and a temperature detection submodule; The humidity detection submodule is based on an IoT device and uses capacitive humidity sensing technology to monitor soil humidity changes by measuring the effect of soil on capacitance. It also performs data standardization processing, including denoising, standardization, and calibration, to generate soil humidity data. The pH value detection submodule is based on soil moisture data and adopts the potential difference method pH sensing technology to determine the soil pH value by measuring the activity of hydrogen ions in the soil solution, and performs data fusion processing, including data alignment, normalization and integration, to generate soil acidity and alkalinity data; The temperature detection submodule is based on soil pH data and adopts thermocouple temperature measurement technology to determine the soil temperature by measuring the junction temperature difference of two differentiated metals. At the same time, it adopts data aggregation algorithm for data integration, including temperature trend analysis and seasonal adjustment, to provide soil temperature information, and combine soil moisture data and soil pH data to generate soil status results.

[0009] As a further solution of the present invention, the crop water requirement analysis module includes a crop information analysis submodule, a water requirement calculation submodule, and a model adjustment submodule; The crop information analysis submodule uses a crop physiological growth model based on soil status results to analyze crop types, growth stages, and water requirements, and combines crop historical growth data and pattern matching to determine growth stages and estimate water requirements, thereby generating crop growth water requirement information. The water requirement calculation submodule calculates the water requirement of crops based on the water requirement information of crop growth, adopts the water balance calculation method, calculates the evaporation and transpiration of crops and the loss of soil water, and refers to precipitation and irrigation supply to calculate the water requirement of crops and generate the water requirement data of crops; The model adjustment submodule is based on crop water requirement data and adopts a machine learning time series analysis method. Through time series analysis, pattern recognition and predictive modeling, it dynamically predicts and adjusts the model of crop water demand, matches differentiated climate and soil conditions, and generates water demand analysis results.

[0010] As a further solution of the present invention, the irrigation strategy formulation module includes a water quantity strategy formulation submodule, a time frequency planning submodule, and a strategy optimization submodule; The water quantity strategy formulation submodule uses a linear programming algorithm to analyze and allocate irrigation water demand based on the water demand analysis results, establishes an objective function and constraints, iterates and solves to achieve the optimal allocation of water resources, and generates water quantity strategy data with reference to crop demand and soil conditions. The time-frequency planning submodule uses time series analysis methods based on water quantity strategy data to conduct comprehensive planning of irrigation time and frequency. It selects irrigation timing and frequency through historical irrigation data analysis and future trend prediction, and generates time-frequency planning data with reference to climate change and crop growth cycle. The strategy optimization submodule uses a simulated annealing algorithm based on time-frequency planning data to perform global optimization of the irrigation strategy. Through the simulated annealing process, it randomly captures and gradually reduces the system energy to achieve global optimality, optimizes the comprehensive strategy of irrigation amount, time and frequency, and generates an irrigation strategy plan.

[0011] As a further solution of the present invention, the irrigation execution control module includes an automatic irrigation submodule, an execution monitoring submodule, and a real-time adjustment submodule; The automatic irrigation submodule uses a fuzzy logic control algorithm based on the irrigation strategy to automatically adjust the water flow and irrigation time. The fuzzy logic control algorithm is used to construct a set of fuzzy rules and fuzzy sets to handle uncertainty and approximate reasoning, optimize the configuration of irrigation parameters, and use soil moisture sensing technology for real-time monitoring to generate irrigation task execution results. The execution monitoring submodule uses an event-driven monitoring algorithm based on the irrigation task execution results to perform real-time monitoring of the irrigation process. The event-driven monitoring algorithm identifies key events in the irrigation system and adjusts the monitoring strategy in real time in response to the events. At the same time, it analyzes the irrigation process in combination with anomaly detection technology to generate irrigation process monitoring records; The real-time adjustment submodule adopts an adaptive control method based on the irrigation process monitoring record to dynamically adjust the irrigation parameters. The adaptive control method analyzes the irrigation data in real time and adjusts the irrigation parameters according to the difference between the current and expected irrigation effects to generate an irrigation effect optimization record.

[0012] As a further solution of the present invention, the water source management module includes a water source investigation submodule, a water volume allocation submodule, and a water source optimization submodule; The water source investigation submodule uses the information of reservoirs, groundwater and recycled water, adopts the geographic information system analysis method, investigates the water source through spatial data analysis and remote sensing image interpretation, applies hydrological data modeling technology, including watershed simulation and groundwater dynamic analysis, comprehensively evaluates the water source status, and generates water source status results; The water allocation submodule is based on the water source status results, uses genetic algorithm optimization, allocates water through population initialization, fitness function calculation and genetic operation, combines the water demand prediction model, conducts time series analysis and consumption pattern evaluation, and formulates a water allocation plan; The water source optimization submodule is based on the water allocation plan, adopts a neural network optimization algorithm, optimizes the water source configuration through a feedforward neural network and a back propagation algorithm, combines the resource allocation decision support system, performs system simulation and optimization plan generation, optimizes the water source configuration, and generates a water source optimization plan.

[0013] As a further solution of the present invention, the fertilizer distribution module includes a fertilizer demand analysis submodule, a distribution plan formulation submodule, and an intelligent delivery submodule; The fertilizer demand analysis submodule uses a crop growth model based on the water source optimization plan and crop growth requirements to perform fertilizer demand analysis through photosynthesis simulation and soil-plant-atmosphere continuum model, and also applies a fertilizer demand prediction algorithm to perform linear regression analysis and demand calculation, analyze crop demand for fertilizer, and generate fertilizer demand prediction results; The distribution plan formulation submodule is based on the fertilizer demand forecast results, adopts the logistics network optimization model, plans the fertilizer distribution through supply chain network design and transportation route optimization, combines the cost-benefit analysis method, conducts cost minimization strategy and benefit maximization evaluation, and generates a fertilizer distribution plan; The intelligent delivery submodule is based on the fertilizer distribution plan, adopts an adaptive control algorithm, and performs fertilizer delivery through PID controller and fuzzy logic control. At the same time, it uses environmental sensing technology, including soil moisture sensors and crop growth monitors, to monitor environmental conditions to control fertilizer delivery and generate an intelligent fertilizer delivery plan.

[0014] As a further solution of the present invention, the irrigation effect evaluation module includes a crop growth evaluation submodule, a soil condition evaluation submodule, and a resource utilization evaluation submodule; The crop growth assessment submodule is based on the fertilizer distribution plan and adopts the decision tree analysis method to analyze the crop growth data by building a decision tree model, including selecting the best segmentation point from the data to create a tree node, branching the node, avoiding overfitting through pruning operations, assessing the impact of irrigation on crop growth, and generating a crop growth impact analysis; The soil condition assessment submodule is based on crop growth impact analysis, adopts principal component analysis, calculates the covariance matrix of soil sample data, extracts key components, performs dimensionality reduction processing on key components, analyzes and evaluates the impact of irrigation on soil conditions, and generates soil condition impact analysis; The resource utilization assessment submodule is based on soil condition impact analysis, adopts a linear programming model, defines the objective function and constraints of water and fertilizer use, uses the simplex algorithm to solve the optimal solution, evaluates the efficiency of water and fertilizer use, and generates an irrigation resource efficiency analysis.

[0015] As a further solution of the present invention, the adaptive adjustment module includes a strategy adjustment submodule, an execution plan update submodule, and an environment adaptation submodule; The strategy adjustment submodule is based on irrigation resource efficiency analysis and adopts a simulated annealing algorithm. By randomly selecting points in the solution space as initial solutions, the system temperature is gradually reduced to search for the global optimal solution, which is used to adjust the irrigation strategy to match the changes in the environment and crop needs, and generate an irrigation strategy optimization plan; The execution plan update submodule is based on the irrigation strategy optimization scheme and adopts a dynamic programming method to decompose the problem into overlapping sub-problems, recursively solve the sub-problems, construct a global optimal irrigation execution plan, and generate an updated irrigation execution plan; The environmental adaptation submodule uses a genetic algorithm based on the updated irrigation execution plan, including population initialization, fitness evaluation, and finding the optimal solution through gene crossover and mutation operations, to ensure that the irrigation plan continues to adapt to environmental changes and crop needs and generate an adaptive irrigation plan.

[0016] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, comprehensive soil assessment results are generated through multi-indicator soil status monitoring and data aggregation to ensure information integrity and accuracy. The crop water demand is analyzed and the water consumption is accurately calculated in combination with the decision tree. The irrigation strategy is based on linear programming and simulated annealing methods to optimize time and frequency and improve the adaptability of the scheme. The irrigation link adopts automatic control and dynamic adjustment mechanisms to adapt to changes in the environment and crop demand in real time. Water source allocation is based on dynamic optimization to ensure efficient distribution of multiple water sources. Fertilizer placement is accurately controlled in type and amount according to crop demand. The irrigation effect is adaptively optimized through crop data evaluation and irrigation plan, thus achieving accurate, flexible and efficient farmland resource management as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a system flow chart of the present invention; Figure 2 It is a schematic diagram of the system framework of the present invention; Figure 3 It is a flow chart of the soil monitoring module of the present invention; Figure 4 This is a flow chart of the crop water requirement analysis module of the present invention; Figure 5 Develop a module flow chart for the irrigation strategy of the present invention; Figure 6 It is a flow chart of the irrigation execution control module of the present invention; Figure 7 This is a flow chart of the water source management module of the present invention; Figure 8 This is a flow chart of the fertilizer distribution module of the present invention; Fig. 9 It is a flow chart of the irrigation effect evaluation module of the present invention; Fig.10 It is a flow chart of the adaptive adjustment module of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0019] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0020] Embodiment 1

[0021] See also Figure 1 to Figure 2 ,A farmland irrigation control system based on the Internet of Things includes a soil monitoring module, a crop water demand analysis module, an irrigation strategy formulation module, an irrigation execution control module, a water source management module, a fertilizer distribution module, an irrigation effect evaluation module, and an adaptive adjustment module; The soil monitoring module is based on IoT devices and uses a sensor network to monitor soil moisture, pH value, and temperature indicators in real time. It also uses a data aggregation algorithm to integrate data and generate soil status results. The crop water demand analysis module uses the decision tree analysis method based on the soil status results to analyze the water demand of crops, calculate the water demand, and generate water demand analysis results; The irrigation strategy formulation module uses linear programming to formulate a comprehensive strategy for irrigation quantity, time and frequency based on the water demand analysis results, and uses simulated annealing algorithm to optimize the strategy and generate an irrigation strategy plan; The irrigation execution control module uses automatic control technology to irrigate based on the irrigation strategy plan, monitors and adjusts the irrigation execution using a real-time feedback adjustment mechanism, and generates irrigation execution records; The water source management module manages and allocates water sources, including reservoirs, groundwater and recycled water. Based on irrigation execution records, it uses a dynamic water source allocation algorithm to optimize allocation and generate a water source allocation plan; The fertilizer distribution module uses a decision support system to calculate the type and amount of fertilizers based on the water distribution plan and crop growth needs, and combines timing control to release fertilizers and generate a fertilizer distribution plan; The irrigation effect evaluation module collects crop growth data and soil conditions, uses an effect evaluation model based on the fertilizer distribution plan, evaluates the irrigation effect, and generates irrigation effect evaluation results; Based on the irrigation effect evaluation results, the adaptive adjustment module uses an adaptive adjustment algorithm to automatically adjust the irrigation strategy and execution plan to match environmental changes and crop demand changes and generate an adjusted irrigation plan.

[0022] Soil status results include soil moisture index, pH, and temperature values. Water demand analysis results include average daily water demand and water demand during the growth stage. Irrigation strategy plans include irrigation quantity parameters, irrigation schedule, and irrigation frequency plan. Irrigation execution records include actual water volume, irrigation time, and irrigation effect evaluation. Water source allocation plan includes water source allocation ratio and deployment schedule. Fertilizer distribution plan includes fertilizer type, fertilizer amount, and fertilization time. Irrigation effect evaluation results include crop growth rate, yield, and water resource utilization efficiency. The adjusted irrigation plan includes updated irrigation volume, irrigation time, and irrigation frequency.

[0023] In the soil monitoring module, real-time monitoring of soil status is achieved through IoT devices and sensor networks. These sensors regularly collect soil moisture, pH and temperature data. The collected data is integrated through a data aggregation algorithm to eliminate the impact of single point failures or outliers and ensure the accuracy and reliability of the data. The algorithm first performs a preliminary screening of the sensor data to exclude data points that are significantly deviated from the normal range. Subsequently, the readings of each sensor are combined using a weighted average method to balance the differences between different sensors. Ultimately, the soil status results generated by the system include a comprehensive soil moisture index, pH and temperature values. These results are critical for assessing the health of the soil and formulating irrigation strategies.

[0024] In the crop water requirement analysis module, based on the above soil status results, the decision tree analysis method is applied to calculate the water requirements of crops. The decision tree is constructed through parameters such as soil moisture, pH and temperature, and comprehensively considers the growth stage and environmental factors of the crop to accurately estimate the average daily water requirement and growth stage water requirement of the crop. This process involves analyzing the sensitivity of crops to water and their adaptability to different soil conditions. Algorithm refinement operations include setting different branch conditions according to crop type and growth stage, and adjusting the estimation of water requirements according to soil status. The generated water demand analysis results are crucial for formulating effective irrigation strategies.

[0025] In the irrigation strategy formulation module, linear programming and simulated annealing algorithms are used to comprehensively formulate irrigation strategies. Linear programming is used to determine the optimal irrigation amount, time, and frequency to meet the water requirements of crops while considering resource utilization efficiency. During the operation of linear programming, the algorithm sets a series of constraints and objective functions based on the results of crop water requirement analysis and soil conditions. The simulated annealing algorithm is used to optimize these strategies and find the global optimal solution in the solution space by simulating the metal annealing process. This process involves randomly selecting solutions, evaluating their quality, and accepting or rejecting the solution based on a certain probability, so as to achieve a balance between search efficiency and solution quality. The generated irrigation strategy plan is an irrigation plan that comprehensively considers crop needs and resource sustainability.

[0026] In the irrigation execution control module, automatic control technology is used to execute irrigation strategies. This module uses a real-time feedback adjustment mechanism to continuously monitor various parameters in the irrigation process, such as actual water consumption and irrigation time. The control system automatically adjusts irrigation equipment according to the preset irrigation strategy, such as switching valves and adjusting flow. At the same time, the system collects irrigation process data in real time and compares it with the preset strategy. If necessary, it automatically adjusts irrigation parameters to optimize the irrigation effect. The process ensures the accuracy and efficiency of irrigation execution and reduces the waste of water resources. The generated irrigation execution record records the specific situation of each irrigation in detail, providing a basis for future irrigation strategy adjustments.

[0027] The water source management module is responsible for the management and allocation of water sources. This module uses a dynamic water source allocation algorithm to optimize the allocation of water sources such as reservoirs, groundwater and recycled water based on irrigation execution records and water resource conditions. The algorithm first analyzes the current water resource conditions, including the available amount and location of each water source. Then, based on irrigation needs and geographical location, the optimal water source allocation plan is calculated to reduce water transmission costs and ensure sustainable use of water sources. In this process, the algorithm also takes into account weather forecasts and seasonal water source changes to cope with potential water shortages or surpluses. The generated water source allocation plan ensures efficient and rational use of water resources.

[0028] In the fertilizer distribution module, the decision support system calculates the type and amount of fertilizers, combining the water distribution plan and crop growth needs. The module first analyzes the crop's needs for different nutrients, and then determines the most appropriate type and amount of fertilizer based on the water distribution plan and soil conditions. During operation, the algorithm considers the crop growth stage, soil nutrient status and moisture status to determine the best fertilization plan. The fertilization plan also incorporates timing control to ensure that fertilizers are delivered at the most appropriate time to improve fertilizer utilization. The generated fertilizer distribution plan aims to maximize crop growth and efficient use of resources.

[0029] In the irrigation effect evaluation module, the irrigation effect is evaluated by collecting crop growth data and soil conditions. The evaluation model combines the fertilizer distribution plan and irrigation execution records to comprehensively consider crop growth rate, yield and water resource utilization efficiency. During the evaluation process, the algorithm analyzes the collected data to identify key factors affecting crop growth, such as water, nutrients and soil conditions. By comparing the effects of different irrigation strategies and fertilization plans, the algorithm can evaluate the effectiveness of various management measures. The generated irrigation effect evaluation results provide an important basis for further optimizing irrigation and fertilizer distribution strategies.

[0030] In the adaptive adjustment module, irrigation strategies and execution plans are automatically adjusted based on the irrigation effect evaluation results. This module uses an adaptive adjustment algorithm to optimize irrigation strategies based on environmental changes and dynamic changes in crop demand. During operation, the algorithm analyzes the irrigation effect evaluation results, identifies potential problems and room for improvement, and then adjusts the irrigation amount, irrigation time, and frequency. This process ensures that the irrigation plan can quickly adapt to environmental changes, improve irrigation efficiency and crop yields. The resulting adjusted irrigation plan is an optimization and update of the original strategy to ensure continued crop growth and efficient use of water resources.

[0031] See also Figure 3 ,The soil monitoring module includes a humidity detection submodule, a pH value detection submodule, and a temperature detection submodule; The humidity detection submodule is based on IoT devices and uses capacitive humidity sensing technology to monitor soil humidity changes by measuring the impact of soil on capacitance. It also performs data standardization processing, including denoising, standardization, and calibration, to generate soil humidity data. The pH value detection submodule is based on soil moisture data and uses the potential difference method pH sensing technology to determine the soil pH value by measuring the activity of hydrogen ions in the soil solution. It performs data fusion processing, including data alignment, normalization and integration, to generate soil acidity and alkalinity data. The temperature detection submodule is based on soil pH data and adopts thermocouple temperature measurement technology to determine the soil temperature by measuring the junction temperature difference between two differentiated metals. At the same time, it uses data aggregation algorithm for data integration, including temperature trend analysis and seasonal adjustment, to provide soil temperature information, and combine soil moisture data and soil pH data to generate soil status results.

[0032] In the humidity detection submodule, soil moisture is monitored by capacitive humidity sensing technology. This technology is based on the principle of capacitors, where soil is used as a dielectric and changes in its humidity will result in changes in the capacitance value. First, the sensor periodically measures the soil capacitance to obtain raw humidity data. These data are direct measurements of the capacitance value and are usually measured in farads (F). Next, data standardization is performed, which includes three main steps: denoising, standardization, and calibration. The denoising process removes random noise from the data through filtering algorithms (such as Kalman filters) and retains useful signals. Standardization converts the data into a standard format to adapt it to different analyses and comparisons. Calibration is the regular calibration of the sensor to ensure the accuracy of the data. These steps ensure that the collected humidity data is both accurate and reliable. Finally, the generated soil moisture data is expressed in percentage form, reflecting the moisture status of the soil. This data is essential for formulating irrigation strategies, assessing crop water requirements, and adjusting irrigation plans.

[0033] In the pH detection submodule, the potential difference method pH sensing technology is used to determine the soil pH. This technology is based on the principle of measuring the activity of hydrogen ions in the soil solution. The sensor first obtains the potential difference data of the soil solution, which directly reflects the changes in the hydrogen ion concentration. Then, data fusion processing is performed to ensure the consistency and accuracy of the data. The data alignment step ensures that the data collected from different sensors are aligned in time to facilitate comprehensive analysis. The normalization process converts the data into a standardized numerical range, such as 0 to 14, representing the standard range of pH values. The integration step combines the data from different sensors to improve the accuracy and reliability of the overall measurement. The generated soil pH data is expressed in pH values, which is very important for understanding the chemical properties of the soil and adjusting crop planting strategies.

[0034] In the temperature detection submodule, thermocouple temperature measurement technology is used to monitor soil temperature. Thermocouples determine temperature by measuring the thermoelectric potential generated at the junction of two different metals. After data collection, it is processed by a data aggregation algorithm to ensure the accuracy and continuity of temperature readings. Temperature trend analysis is a time series analysis of the collected temperature data to identify long-term and short-term temperature change trends. Seasonal adjustment adjusts temperature readings based on historical data patterns, taking into account the impact of seasonal changes on soil temperature. The final soil temperature information is displayed in degrees Celsius (℃), providing important information about the thermal condition of the soil. Combined with soil moisture data and soil pH data, the final soil status results provide comprehensive soil environmental information for the soil monitoring system, which helps to make more accurate irrigation decisions.

[0035] Assume that in a certain monitoring cycle, the raw capacitance data collected by the humidity detection submodule is [0.1F, 0.15F, 0.1F]. After denoising and standardization, the data is converted into humidity percentage, such as [30%, 45%, 30%]. The potential difference data collected by the pH detection submodule in the same cycle is [0.7V, 0.75V, 0.72V], which is converted into pH value after processing, such as [6.5, 6.7, 6.6]. The thermoelectric potential data collected by the temperature detection submodule is [2.5mV, 2.6mV, 2.55mV], which is converted into degrees Celsius after processing, such as [22℃, 23℃, 22.5℃]. Finally, these data are processed comprehensively, and the generated soil status results include the average soil humidity (35%), average pH value (6.6) and average temperature (22.5℃). These data provide comprehensive soil environmental information for the soil monitoring system and help guide soil monitoring in farmland.

[0036] See also Figure 4 ,The crop water demand analysis module includes a crop information analysis submodule, a water demand calculation submodule, and a model adjustment submodule; The crop information analysis submodule uses crop physiological growth models based on soil status results to analyze crop types, growth stages, and water requirements. It combines crop historical growth data and pattern matching to determine growth stages and estimate water requirements, and generates crop growth water requirement information. The water demand calculation submodule is based on the water demand information of crop growth. It uses the water balance calculation method to calculate the crop evaporation and transpiration and soil moisture loss, and refers to precipitation and irrigation supply to calculate the crop water demand and generate crop water demand data; The model adjustment submodule is based on crop water requirement data and adopts machine learning time series analysis methods. Through time series analysis, pattern recognition and predictive modeling, it dynamically predicts and adjusts the model of crop water demand, matches differentiated climate and soil conditions, and generates water demand analysis results.

[0037] In the crop information analysis submodule, the crop type, growth stage and water requirement are analyzed through the crop physiological growth model. The model first receives the soil status results from the soil monitoring module, such as humidity, pH value and temperature data, which are presented in digital form, such as humidity expressed in percentage, pH value expressed in numerical range, and temperature expressed in degrees Celsius. Subsequently, the model analyzes the historical growth data of the crop, which includes the planting date, growth cycle, and previous water requirements of the crop, which are usually stored in the form of a database table. The model uses a pattern matching algorithm to compare the current soil status with historical data to identify the current growth stage of the crop. The steps involve a large amount of data comparison and pattern recognition, such as determining the growth stage of the crop based on soil conditions and historical data through a decision tree algorithm. Next, the model estimates the water requirement of the crop. This process is carried out through regression analysis or similar statistical methods, taking into account the growth stage, soil status and historical water requirement of the crop. The final crop growth water requirement information is presented in the form of a table or report, providing a scientific basis for farmland irrigation.

[0038] In the water demand calculation submodule, the water balance calculation method is used to calculate the water demand of crops. The submodule first receives the water demand information of crop growth, which includes the evapotranspiration rate of crops, historical water demand, etc. Next, the submodule calculates the crop evapotranspiration and soil water loss through the water balance equation. The calculation of evapotranspiration takes into account the crop type, growth stage, and environmental factors such as temperature and humidity. The calculation of soil water loss includes soil infiltration and evaporation losses. At the same time, the submodule also considers the impact of precipitation and irrigation replenishment, which are usually derived from records of meteorological departments or irrigation systems. During the calculation process, the submodule uses a linear or nonlinear water balance model to solve the equation group to obtain the water demand of crops. The generated crop water demand data is in cubic meters or liters, providing accurate irrigation guidance.

[0039] In the model adjustment submodule, based on the crop water demand data, the machine learning time series analysis method is used to dynamically predict the crop water demand and adjust the model. The submodule first uses time series analysis techniques, such as the autoregressive moving average (ARMA) model, to analyze the historical water demand data and identify the trend and periodic changes in water demand. Then, through pattern recognition techniques, such as support vector machines (SVM) or random forests, the water demand patterns of different crops under different environmental conditions are classified and identified. On this basis, the submodule uses predictive modeling techniques, such as neural networks or deep learning, to predict future crop water demand. During the process, the model will adjust its own parameters according to the actual irrigation effect and environmental changes to improve the accuracy of the prediction. The generated water demand analysis results are presented in the form of reports or data tables, providing a scientific basis with strong adaptability and high reliability for irrigation decisions.

[0040] Assume that in a growing season, the soil status data received by the crop information analysis submodule is 60% humidity, 6.5 pH value, and 25°C temperature. Historical data show that under such soil conditions, the crop is in the middle of growth and the average daily water demand is 5 liters. The water demand calculation submodule then calculates the crop evaporation and transpiration as 3 liters, the soil water loss as 1 liter, and the precipitation replenishment of 1 liter, and finally calculates that the crop daily water demand is 4 liters. The model adjustment submodule finds through time series analysis that the crop water demand is gradually increasing, and predicts that the next water demand will rise to 5.5 liters, and adjusts the irrigation model accordingly. The final generated water demand analysis results show that the average daily water demand of crops should be adjusted to 5.5 liters in the current growth stage, providing accurate guidance for soil monitoring.

[0041] See also Figure 5 ,The irrigation strategy formulation module includes a water quantity strategy formulation submodule, a time and frequency planning submodule, and a strategy optimization submodule; The water strategy formulation submodule uses a linear programming algorithm to analyze and allocate irrigation water demand based on the water demand analysis results. It establishes an objective function and constraints, iterates and solves to achieve the optimal allocation of water resources, and generates water strategy data by referring to crop demand and soil conditions. The time-frequency planning submodule uses time series analysis methods based on water quantity strategy data to conduct comprehensive planning of irrigation time and frequency. It selects irrigation timing and frequency through historical irrigation data analysis and future trend forecasting, and generates time-frequency planning data with reference to climate change and crop growth cycle. The strategy optimization submodule uses the simulated annealing algorithm to perform global optimization of the irrigation strategy based on the time-frequency planning data. Through the simulated annealing process, it randomly captures and gradually reduces the system energy to achieve the global optimum, optimizes the comprehensive strategy of irrigation amount, time and frequency, and generates an irrigation strategy plan.

[0042] In the water strategy formulation submodule, the demand analysis and allocation of irrigation water are carried out through a linear programming algorithm. The starting point of the process is the water demand analysis results, including the average daily water demand of crops, seasonal water demand changes, etc. These data are usually presented in the form of digital tables. The linear programming algorithm first establishes the objective function, which aims to minimize the total irrigation cost or maximize the efficiency of water resource use while ensuring that the water demand of crops is met. Next, constraints are set, including the amount of available water resources, the water absorption capacity of the soil, and the efficiency of crop water absorption. These conditions are expressed in the form of inequalities, which limit the upper and lower bounds of the irrigation amount. The algorithm gradually approaches the optimal solution through iterative solution. At each iteration, the algorithm adjusts the allocation of irrigation until the optimal allocation scheme that meets all constraints is found. The generated water strategy data includes information such as the irrigation amount and irrigation priority of each crop block. These data are presented in the form of spreadsheets or visual charts to guide the specific operation of the irrigation system.

[0043] In the time-frequency planning submodule, time series analysis methods are used to plan irrigation time and frequency. The submodule receives water strategy data, including the irrigation amount for each crop block, and information on the growth stage of the crop. Time series analysis methods include autoregressive models (AR), moving average models (MA), etc., which are used to analyze the temporal patterns and trends of historical irrigation data. Through these models, the algorithm can identify the best time and frequency of irrigation, such as increasing the irrigation frequency during critical stages of crop growth or adjusting the irrigation time to avoid high temperature periods. In addition, the submodule also considers the impact of climate change and crop growth cycles, such as adjusting the irrigation frequency according to seasonal changes. The generated time-frequency planning data includes the specific time, interval and duration of irrigation, which are presented in the form of a schedule or timeline to ensure that irrigation activities match crop needs and climatic conditions.

[0044] In the strategy optimization submodule, the simulated annealing algorithm is used to perform global optimization of the irrigation strategy. The submodule receives time-frequency plan data, including the initial set irrigation time and frequency. When the simulated annealing algorithm is started, a high "temperature" is first set, which represents the randomness of the solution space search. As the algorithm proceeds, the "temperature" gradually decreases and the search process tends to stabilize. At each step, the algorithm randomly selects a solution, such as changing the time or frequency of a certain irrigation, and calculates the "energy" of the solution, that is, the impact of the solution on irrigation efficiency and crop growth. If the energy of the new solution is lower than the current solution, or although the energy is high but accepted according to a certain probability, the algorithm will accept the new solution. This process is repeated until the solution with the lowest energy is found, that is, the optimal irrigation strategy. The generated irrigation strategy plan includes the finalized irrigation amount, time and frequency, which are presented in the form of a comprehensive report or decision chart to provide the best solution for soil monitoring.

[0045] Assume that the water demand analysis results show that the average daily water demand of a crop block is 5,000 liters. The water quantity strategy formulation submodule sets the objective function and constraints through a linear programming algorithm, and after solving it, it is determined that the block should be irrigated with 5,000 liters per day. The time frequency planning submodule then analyzes the historical irrigation data and determines that the best time for the block is 2,500 liters each in the morning and evening. The strategy optimization submodule uses the simulated annealing algorithm for optimization and finally determines that irrigation should be carried out at 5 am and 6 pm, with each irrigation lasting 1 hour. The generated irrigation strategy plan details the specific time, duration and amount of irrigation, providing precise guidance for irrigation operations.

[0046] See also Figure 6 ,The irrigation execution control module includes an automatic irrigation submodule, an execution monitoring submodule, and a real-time adjustment submodule; The automatic irrigation submodule uses fuzzy logic control algorithm to automatically adjust water flow and irrigation time based on the irrigation strategy scheme. It uses fuzzy logic control algorithm to handle uncertainty and approximate reasoning by constructing a set of fuzzy rules and fuzzy sets to optimize the configuration of irrigation parameters, and uses soil moisture sensing technology for real-time monitoring to generate irrigation task execution results. The execution monitoring submodule uses an event-driven monitoring algorithm based on the irrigation task execution results to perform real-time monitoring of the irrigation process. The event-driven monitoring algorithm identifies key events in the irrigation system and adjusts the monitoring strategy in real time in response to the events. At the same time, it analyzes the irrigation process in combination with anomaly detection technology to generate irrigation process monitoring records. The real-time adjustment submodule uses an adaptive control method based on the irrigation process monitoring records to dynamically adjust the irrigation parameters. The adaptive control method analyzes the irrigation data in real time and adjusts the irrigation parameters according to the difference between the current and expected irrigation effects to generate irrigation effect optimization records.

[0047] In the automatic irrigation submodule, the irrigation parameters are optimized by the fuzzy logic control algorithm. The submodule first receives the irrigation strategy plan, including the predetermined irrigation amount, time and frequency, which is usually in the form of a spreadsheet or data stream. The fuzzy logic control algorithm simulates and processes various situations that occur during the irrigation process with its ability to handle uncertainty and approximate reasoning. The algorithm first constructs a set of fuzzy rules and fuzzy sets. For example, factors such as soil moisture and temperature are used as input variables, and fuzzy sets such as "low", "medium" and "high" are defined according to actual values. Then, according to the defined rules, such as "if the soil moisture is low and the temperature is high, increase the irrigation amount", the algorithm processes these fuzzy inputs and obtains specific irrigation parameters. In addition, the submodule uses soil moisture sensing technology for real-time monitoring and adjusts the irrigation parameters according to the real-time data of soil moisture. The generated irrigation task execution results include the actual execution time, water volume and soil moisture changes of each irrigation. These data are recorded in the form of logs or reports to provide actual data support for irrigation effect evaluation.

[0048] In the execution monitoring submodule, an event-driven monitoring algorithm is used to monitor the irrigation process in real time. This submodule receives the irrigation task execution results generated by the automatic irrigation submodule, such as the timestamps of the start and end of irrigation, the actual irrigation amount, and other information, which are usually presented in the form of a real-time data stream. The event-driven monitoring algorithm identifies key events in the irrigation system, such as irrigation start, end, or parameter adjustment, and adjusts the monitoring strategy in real time based on these events. For example, if it is detected that an irrigation is not executed as planned, the algorithm will trigger an alarm and record the abnormal situation. In addition, the submodule combines anomaly detection techniques, such as statistical analysis or machine learning methods, to analyze the irrigation process and identify equipment failures or operational errors. The generated irrigation process monitoring record includes detailed information on each irrigation and any abnormalities, which are presented in the form of logs or real-time monitoring panels, which are crucial to ensuring the normal operation of the irrigation system.

[0049] In the real-time adjustment submodule, an adaptive control method is used to dynamically adjust the irrigation parameters. This submodule receives the irrigation process monitoring records generated by the execution monitoring submodule, including information such as irrigation amount, time, and effect. The adaptive control method analyzes these irrigation data in real time and adjusts the irrigation parameters according to the difference between the current and expected irrigation effects. For example, if the actual soil moisture is monitored to be lower than expected, the algorithm will increase the next irrigation amount or frequency. During the process, the algorithm continuously learns and adjusts to adapt to different environmental conditions and crop needs. The generated irrigation effect optimization record includes the adjusted irrigation parameters and the actual irrigation effect, which is stored in the form of reports or database records to provide a basis for continuous optimization of irrigation strategies.

[0050] Assume that in an irrigation task, the scheduled irrigation volume is 1000 liters at 6 am. The automatic irrigation submodule detects that the soil moisture is lower than expected based on the soil moisture sensing technology, and the fuzzy logic control algorithm decides to increase the irrigation volume to 1200 liters. The execution monitoring submodule records the actual irrigation start time, end time and irrigation volume, and records the event when the irrigation volume exceeds the predetermined value. The real-time adjustment submodule analyzes the monitoring records and finds that the increase in irrigation volume is due to the soil moisture being lower than expected, confirming that the adjustment is reasonable. The generated irrigation effect optimization record includes the adjusted irrigation parameters and the actual irrigation effect, which guides future irrigation tasks.

[0051] See also Figure 7 ,The water source management module includes a water source investigation submodule, a water allocation submodule, and a water source optimization submodule; The water source investigation submodule uses the information of reservoirs, groundwater and recycled water, adopts the GIS analysis method, investigates water sources through spatial data analysis and remote sensing image interpretation, applies hydrological data modeling technology, including watershed simulation and groundwater dynamic analysis, comprehensively evaluates water source conditions, and generates water source status results; The water allocation submodule uses genetic algorithm optimization based on the water source status results to allocate water through population initialization, fitness function calculation and genetic operation. It combines the water demand forecasting model, conducts time series analysis and consumption pattern evaluation, and formulates a water allocation plan; The water source optimization submodule is based on the water allocation plan and adopts a neural network optimization algorithm. It optimizes the water source configuration through a feedforward neural network and a back propagation algorithm. It combines the resource allocation decision support system to perform system simulation and optimization plan generation, optimize the water source configuration, and generate a water source optimization plan.

[0052] In the water source survey submodule, a comprehensive survey of water sources is conducted through geographic information system (GIS) analysis methods. This process involves spatial data analysis and remote sensing image interpretation to collect and analyze information on reservoirs, groundwater and recycled water. Water source information includes the location, size, water volume and quality of water bodies, usually in the form of GIS maps and remote sensing images. Spatial data analysis involves map layer overlay, regional analysis and buffer zone analysis to identify the geographical location and surrounding environmental characteristics of water sources. Remote sensing image interpretation uses image processing techniques such as normalized difference water index (NDWI) to identify and quantify water bodies. In addition, the submodule also applies hydrological data modeling techniques such as watershed simulation, analysis of water cycle processes such as rainfall, evaporation and runoff, and groundwater dynamic analysis to assess the changes and sustainability of groundwater levels. The generated water source status results are presented in the form of reports or data tables, providing detailed information and status assessment of water sources, providing a scientific basis for water allocation and management.

[0053] In the water allocation submodule, a genetic algorithm is used to optimize water allocation. The submodule first receives the water source status results, including the available water volume and quality data of each water source. The first step of the genetic algorithm is to initialize the population and create a series of water allocation plans. Then, the fitness of each plan is calculated through the fitness function, that is, the degree to which the plan meets water demand and resource sustainability. Genetic operations include selection, crossover and mutation, which are used to generate new allocation plans. The selection operation retains the plans with high fitness, while crossover and mutation introduce new plans to increase the diversity of the solution space. Combined with the water demand forecasting model, the submodule performs time series analysis and consumption pattern evaluation to predict future water demand trends. The final generated water allocation plan is presented in the form of tables or charts to guide the actual allocation and deployment of water resources.

[0054] In the water source optimization submodule, a neural network optimization algorithm is used to optimize the water source configuration. The submodule receives the water allocation plan, including the allocation ratio and schedule of various water sources. Using a feedforward neural network and a back propagation algorithm, the submodule trains the model to identify the optimal water source configuration. The feedforward network predicts the effect of water source utilization, such as the degree of meeting water demand and sustainable use of resources, by inputting water source data and current configuration. The back propagation algorithm is used to adjust network parameters based on the prediction results to improve the accuracy of the prediction. Combined with the resource allocation decision support system, the submodule performs system simulation to simulate the effects of different configuration schemes. The generated water source optimization plan is presented in the form of a report or optimization plan, providing the optimal solution for water source configuration to improve the efficiency and sustainability of water resources.

[0055] Assume that the water source survey submodule collects 1 million cubic meters of water from a certain reservoir, 500,000 cubic meters of groundwater, and 300,000 cubic meters of recycled water. The water allocation submodule generates multiple allocation plans through genetic algorithms, such as plan 1, which is 70% for reservoirs, 20% for groundwater, and 10% for recycled water. The neural network optimization algorithm analyzes these plans, predicts their effectiveness in meeting future water needs, and adjusts parameters through back propagation. The optimal plan is finally determined to be 65% for reservoirs, 25% for groundwater, and 10% for recycled water. The generated water source optimization plan details the allocation ratio and schedule for each water source, providing precise guidance for actual water source management.

[0056] See also Figure 8 ,The fertilizer distribution module includes a fertilizer demand analysis submodule, a distribution plan formulation submodule, and an intelligent delivery submodule; The fertilizer demand analysis submodule uses the crop growth model to analyze fertilizer demand based on the water source optimization plan and crop growth demand, through photosynthesis simulation and soil-plant-atmosphere continuum model. At the same time, it applies the fertilizer demand prediction algorithm, performs linear regression analysis and demand calculation, analyzes the fertilizer demand of crops, and generates fertilizer demand prediction results; The distribution plan formulation submodule is based on the fertilizer demand forecast results, adopts the logistics network optimization model, plans fertilizer distribution through supply chain network design and transportation route optimization, combines cost-benefit analysis methods, conducts cost minimization strategies and benefit maximization evaluations, and generates fertilizer distribution plans; The intelligent delivery submodule is based on the fertilizer distribution plan and adopts an adaptive control algorithm to deliver fertilizers through PID controller and fuzzy logic control. It also uses environmental sensing technology, including soil moisture sensors and crop growth monitors, to monitor environmental conditions to control fertilizer delivery and generate an intelligent fertilizer delivery plan.

[0057] In the fertilizer demand analysis submodule, fertilizer demand analysis is performed through crop growth models to analyze data based on water source optimization plans and crop growth needs, including crop types, growth stages, historical growth data, and water source conditions. Crop growth models usually use photosynthesis simulations and soil-plant-atmosphere continuum (SPAC) models, which can simulate the physiological processes of crops and their interactions with the environment. Photosynthesis simulation analyzes the photosynthetic efficiency of crops under different environmental conditions and predicts the nutrient needs of crops. The SPAC model simulates the movement and changes of water and nutrients between soil, plants, and the atmosphere. Next, fertilizer demand prediction algorithms, such as linear regression analysis, are applied to calculate fertilizer requirements based on crop type, growth stage, and environmental conditions. The generated fertilizer demand forecast results are presented in the form of reports or data tables, providing detailed forecasts of the demand for various types of fertilizers to guide the procurement and distribution of fertilizers.

[0058] In the distribution planning submodule, the logistics network optimization model is used to plan the fertilizer distribution. The planning is based on the fertilizer demand forecast results, including the fertilizer type and demand for different crops. The logistics network optimization model considers the design of the supply chain network and the optimization of the transportation route. By analyzing the location, storage capacity and transportation cost of fertilizer suppliers, the model designs the most efficient fertilizer distribution network. At the same time, the transportation route optimization considers the route length, traffic conditions and transportation costs to minimize the delivery time and cost. Combined with the cost-benefit analysis method, the model evaluates the economy and efficiency of different distribution schemes. The final fertilizer distribution plan is presented in the form of a chart or roadmap, detailing the fertilizer distribution route, schedule and cost, providing an efficient plan for the actual fertilizer distribution.

[0059] In the smart delivery submodule, adaptive control algorithms and environmental sensing technologies are used for intelligent fertilizer delivery. The submodule receives fertilizer delivery plans, including fertilizer type, quantity, and delivery time. The adaptive control algorithm combines PID controller and fuzzy logic control to accurately adjust the fertilizer delivery amount and time. The PID controller adjusts the speed and amount of fertilizer delivery through proportional, integral, and differential operations, while the fuzzy logic control handles the uncertainty of soil and climate conditions. In addition, the submodule uses environmental sensing technologies such as soil moisture sensors and crop growth monitors to monitor environmental conditions and crop needs in real time. Based on the monitoring results, the algorithm automatically adjusts the fertilizer delivery strategy. The generated intelligent fertilizer delivery plan is presented in the form of a dashboard or report, providing a detailed plan and monitoring data for fertilizer delivery, ensuring the accuracy and efficiency of fertilizer delivery.

[0060] Assume that the fertilizer demand analysis submodule predicts that wheat needs 80 kg / ha of nitrogen fertilizer during the growth period. The distribution plan formulation submodule plans the transportation of nitrogen fertilizer from the nearest supplier through the logistics network optimization model and formulates the transportation route with the lowest cost. After receiving the distribution plan, the intelligent delivery submodule adjusts the amount and time of nitrogen fertilizer delivery through the PID controller and soil moisture sensor. For example, if the soil moisture is below the threshold, the amount of nitrogen fertilizer delivery is increased. The generated intelligent delivery plan records the time, amount and soil moisture data of each fertilizer delivery in detail to guide future fertilizer management activities.

[0061] See also Fig. 9 ,The irrigation effect evaluation module includes a crop growth evaluation submodule, a soil condition evaluation submodule, and a resource utilization evaluation submodule; The crop growth assessment submodule is based on the fertilizer distribution plan and uses decision tree analysis to analyze crop growth data by building a decision tree model, including selecting the best split point from the data to create tree nodes, branching the nodes, avoiding overfitting through pruning operations, evaluating the impact of irrigation on crop growth, and generating crop growth impact analysis; The soil condition assessment submodule is based on crop growth impact analysis and uses principal component analysis to calculate the covariance matrix of soil sample data, extract key components, perform dimensionality reduction on key components, analyze and evaluate the impact of irrigation on soil conditions, and generate soil condition impact analysis; The resource utilization assessment submodule is based on soil condition impact analysis and adopts a linear programming model. By defining the objective function and constraints of water and fertilizer use, the simplex algorithm is used to solve the optimal solution, evaluate the efficiency of water and fertilizer use, and generate an irrigation resource efficiency analysis.

[0062] In the crop growth assessment submodule, the crop growth data is analyzed in depth through decision tree analysis. This process is based on data from the fertilizer distribution plan, including fertilizer type, application amount, and crop response. Crop growth data is usually stored in a table format, recording the growth rate, yield, and health of crops. Decision tree analysis first selects the best split points from the data to create tree nodes, which involves calculating indicators such as information gain or Gini impurity to determine which factors have the greatest impact on crop growth. These nodes are then branched to form the structure of the decision tree. To avoid the risk of overfitting, pruning operations are used to remove unnecessary branches. In this way, the specific impact of fertilizer type and application amount on crop growth can be clarified. The generated crop growth impact analysis is presented in the form of visual charts or detailed reports, providing agricultural management with in-depth insights into crop growth status and fertilizer effects.

[0063] In the soil condition assessment submodule, principal component analysis (PCA) is used to assess the impact of irrigation on soil condition. This submodule is based on the results of the crop growth impact analysis, especially soil sample data, such as soil chemical composition, structure and microbial activity. PCA extracts key components by calculating the covariance matrix of soil sample data, revealing the main associations between soil properties. Then, dimensionality reduction is performed to merge multiple highly correlated variables into a few main components, simplifying the complexity of the data while retaining the most critical information. This method can provide an in-depth understanding of the long-term and short-term effects of irrigation on soil chemical composition, structure and microbial activity. The generated soil condition impact analysis is presented in the form of reports or charts, providing a comprehensive assessment of soil health and fertility, which is of great guiding significance for soil management and adjustment of irrigation strategies.

[0064] In the resource utilization assessment submodule, a linear programming model is used to evaluate the efficiency of water and fertilizer use. Based on the results of the soil condition impact analysis, the submodule defines the objective function and constraints for water and fertilizer use. The objective function may include maximizing yield, minimizing water and fertilizer costs, or optimizing crop growth quality. The constraints involve the amount of available water resources, fertilizer supply limitations, and crop growth requirements. Using the simplex algorithm, the submodule solves the linear programming problem and finds the optimal solution that meets all constraints. This approach can identify the best way to use water and fertilizer at different crop growth stages and optimize resource allocation. The generated irrigation resource efficiency analysis is presented in the form of a report or data table, which provides cost-effective guidance for irrigation and fertilizer management and helps to improve the sustainability of agricultural production.

[0065] Assume that the data analyzed by the crop growth assessment submodule show that increasing a certain proportion of nitrogen fertilizer can significantly increase the yield of a certain crop. The PCA analysis of the soil condition assessment submodule reveals that long-term excessive application of nitrogen fertilizer leads to soil acidification. The linear programming model of the resource utilization assessment submodule further shows that moderately increasing the amount of nitrogen fertilizer can effectively improve the utilization efficiency of water resources and fertilizers without causing soil acidification. The generated irrigation resource efficiency analysis report proposes the optimal irrigation and fertilizer use strategy for the crop, helping farmers achieve yield improvement and rational use of resources.

[0066] See also Fig.10 ,The adaptive adjustment module includes a strategy adjustment submodule, an execution plan update submodule, and an environment adaptation submodule; The strategy adjustment submodule is based on the analysis of irrigation resource efficiency and adopts the simulated annealing algorithm. By randomly selecting points in the solution space as the initial solution, the system temperature is gradually reduced to search for the global optimal solution, which is used to adjust the irrigation strategy to match the changes in the environment and crop demand and generate an irrigation strategy optimization plan. The execution plan update submodule is based on the irrigation strategy optimization scheme and adopts the dynamic programming method to decompose the problem into overlapping sub-problems, recursively solve the sub-problems, construct the global optimal irrigation execution plan, and generate the updated irrigation execution plan; The environmental adaptation submodule uses a genetic algorithm based on the updated irrigation execution plan, including population initialization, fitness evaluation, and finding the optimal solution through gene crossover and mutation operations to ensure that the irrigation plan continues to adapt to environmental changes and crop needs and generate an adaptive irrigation plan.

[0067] In the strategy adjustment submodule, the irrigation strategy is optimized and adjusted by the simulated annealing algorithm. This process is based on the results of the irrigation resource efficiency analysis, including the current status and efficiency of water resources and fertilizer use. The simulated annealing algorithm first randomly selects a point in the solution space as the initial solution, which represents an irrigation strategy, including irrigation amount, time and frequency. The core of the algorithm is to gradually reduce the "temperature" of the system and try new solutions at each step. In the early stage, the system "temperature" is high, and the algorithm is more inclined to explore the solution space and accept solutions even if they increase the cost. As the "temperature" decreases, the algorithm gradually reduces the acceptance of new solutions and tends to refine and optimize the current solution. In this way, the algorithm can effectively avoid local optimal solutions and find the global optimal irrigation strategy. The generated irrigation strategy optimization plan includes the adjusted irrigation amount, time and frequency, which is presented in the form of data tables or charts, providing a more efficient and adaptable soil monitoring strategy.

[0068] In the execution plan update submodule, the dynamic programming method is used to update the irrigation execution plan based on the irrigation strategy optimization solution generated by the strategy adjustment submodule. The dynamic programming method breaks down the irrigation plan formulation problem into several overlapping subproblems, solves these subproblems one by one, and stores their solutions to avoid repeated calculations. These subproblems are irrigation arrangements within a specific time period, water allocation to specific crop areas, etc. By recursively solving these subproblems, the submodule is able to construct a globally optimal irrigation execution plan. This plan takes into account the availability of various irrigation resources, the water requirements of crops, and changes in environmental conditions. The generated updated irrigation execution plan is presented in the form of a detailed schedule or execution guide to ensure the efficiency and timeliness of irrigation activities.

[0069] In the environmental adaptation submodule, a genetic algorithm is used to ensure that the irrigation plan continues to adapt to environmental changes and crop needs. The process is based on the updated irrigation execution plan, taking into account future environmental changes such as climate variability and changes in precipitation patterns. The genetic algorithm population initialization creates a series of irrigation plans that take into account the needs of different environmental conditions and crop growth stages. Fitness evaluation scores the plans based on their efficiency and effectiveness. Through gene crossover and mutation operations, the algorithm explores new irrigation plans in the solution space to find the optimal solution that adapts to environmental changes. This approach ensures the flexibility and responsiveness of the irrigation plan to adapt to the changing environment and crop needs. The generated adaptive irrigation plan is presented in the form of a strategy report or an operation guide, providing a highly adaptable guidance scheme for soil monitoring.

[0070] Specific implementation example: Assume that the policy adjustment submodule analyzes the current irrigation policy and finds that the irrigation amount is insufficient in hot weather. Through the simulated annealing algorithm, a new irrigation policy is found, which is to increase the frequency and amount of irrigation in hot weather. The execution plan update submodule creates a detailed irrigation schedule based on the policy, including an increase in the number of irrigations per day during heat waves. The environmental adaptation submodule further optimizes the plan through a genetic algorithm, taking into account possible extreme heat waves in the future, and generates an irrigation plan that can adapt to hotter weather. This adaptive irrigation plan provides detailed guidance for irrigation operations under different weather conditions, ensuring that crops can get enough water even in extreme weather conditions.

[0071] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A farmland irrigation control system based on the Internet of Things, characterized by: The system includes a soil monitoring module, a crop water demand analysis module, an irrigation strategy formulation module, an irrigation execution control module, a water source management module, a fertilizer distribution module, an irrigation effect evaluation module, and an adaptive adjustment module; The soil monitoring module is based on IoT devices and uses a sensor network to monitor soil moisture, pH value, and temperature indicators in real time, and uses a data aggregation algorithm to integrate data to generate soil status results; The crop water demand analysis module uses a decision tree analysis method based on the soil status results to analyze the water demand of crops, calculate the water demand, and generate a water demand analysis result; The irrigation strategy formulation module uses linear programming to formulate a comprehensive strategy for irrigation quantity, time and frequency based on the water demand analysis results, and uses simulated annealing algorithm to optimize the strategy and generate an irrigation strategy plan; The irrigation execution control module uses automatic control technology to irrigate based on the irrigation strategy plan, and uses a real-time feedback adjustment mechanism to monitor and adjust the irrigation execution and generate irrigation execution records; The water source management module manages and allocates water sources, including reservoirs, groundwater and recycled water, and uses a dynamic water source allocation algorithm to optimize allocation based on the irrigation execution record to generate a water source allocation plan; The fertilizer distribution module uses a decision support system to calculate the type and amount of fertilizers based on the water source allocation plan and crop growth requirements, and combines timing control to release fertilizers to generate a fertilizer distribution plan; The irrigation effect evaluation module collects crop growth data and soil conditions, and based on the fertilizer distribution plan, adopts an effect evaluation model to evaluate the irrigation effect and generate an irrigation effect evaluation result; The adaptive adjustment module adopts an adaptive adjustment algorithm based on the irrigation effect evaluation result to automatically adjust the irrigation strategy and execution plan to match the environmental changes and crop demand changes and generate an adjusted irrigation plan.

2. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The soil status results include soil moisture index, pH, and temperature value; the water demand analysis results include average daily water demand and water demand during the growth stage; the irrigation strategy plan includes irrigation quantity parameters, irrigation schedule, and irrigation frequency plan; the irrigation execution record includes actual water volume, irrigation time, and irrigation effect evaluation; the water source allocation plan includes water source allocation ratio and deployment schedule; the fertilizer distribution plan includes fertilizer type, fertilizer amount, and fertilization time; the irrigation effect evaluation results include crop growth rate, yield, and water resource utilization efficiency; the adjusted irrigation plan includes updated irrigation quantity, irrigation time, and irrigation frequency.

3. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The soil monitoring module includes a humidity detection submodule, a pH value detection submodule, and a temperature detection submodule; The humidity detection submodule is based on an IoT device and uses capacitive humidity sensing technology to monitor soil humidity changes by measuring the effect of soil on capacitance. It also performs data standardization processing, including denoising, standardization, and calibration, to generate soil humidity data. The pH value detection submodule is based on soil moisture data and adopts the potential difference method pH sensing technology to determine the soil pH value by measuring the activity of hydrogen ions in the soil solution, and performs data fusion processing, including data alignment, normalization and integration, to generate soil acidity and alkalinity data; The temperature detection submodule is based on soil pH data and adopts thermocouple temperature measurement technology to determine the soil temperature by measuring the junction temperature difference of two differentiated metals. At the same time, it adopts data aggregation algorithm for data integration, including temperature trend analysis and seasonal adjustment, to provide soil temperature information, and combine soil moisture data and soil pH data to generate soil status results.

4. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The crop water demand analysis module includes a crop information analysis submodule, a water demand calculation submodule, and a model adjustment submodule; The crop information analysis submodule uses a crop physiological growth model based on soil status results to analyze crop types, growth stages, and water requirements, and combines crop historical growth data and pattern matching to determine growth stages and estimate water requirements, thereby generating crop growth water requirement information. The water requirement calculation submodule calculates the water requirement of crops based on the water requirement information of crop growth, adopts the water balance calculation method, calculates the evaporation and transpiration of crops and the loss of soil water, and refers to precipitation and irrigation supply to calculate the water requirement of crops and generate the water requirement data of crops; The model adjustment submodule is based on crop water requirement data and adopts a machine learning time series analysis method. Through time series analysis, pattern recognition and predictive modeling, it dynamically predicts and adjusts the model of crop water demand, matches differentiated climate and soil conditions, and generates water demand analysis results.

5. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The irrigation strategy formulation module includes a water quantity strategy formulation submodule, a time frequency planning submodule, and a strategy optimization submodule; The water quantity strategy formulation submodule uses a linear programming algorithm to analyze and allocate irrigation water demand based on the water demand analysis results, establishes an objective function and constraints, iterates and solves to achieve the optimal allocation of water resources, and generates water quantity strategy data with reference to crop demand and soil conditions. The time-frequency planning submodule uses time series analysis methods based on water quantity strategy data to conduct comprehensive planning of irrigation time and frequency. It selects irrigation timing and frequency through historical irrigation data analysis and future trend prediction, and generates time-frequency planning data with reference to climate change and crop growth cycle. The strategy optimization submodule uses a simulated annealing algorithm based on time-frequency planning data to perform global optimization of the irrigation strategy. Through the simulated annealing process, it randomly captures and gradually reduces the system energy to achieve global optimality, optimizes the comprehensive strategy of irrigation amount, time and frequency, and generates an irrigation strategy plan.

6. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The irrigation execution control module includes an automatic irrigation submodule, an execution monitoring submodule, and a real-time adjustment submodule; The automatic irrigation submodule uses a fuzzy logic control algorithm based on the irrigation strategy to automatically adjust the water flow and irrigation time. The fuzzy logic control algorithm is used to construct a set of fuzzy rules and fuzzy sets to handle uncertainty and approximate reasoning, optimize the configuration of irrigation parameters, and use soil moisture sensing technology for real-time monitoring to generate irrigation task execution results. The execution monitoring submodule uses an event-driven monitoring algorithm based on the irrigation task execution results to perform real-time monitoring of the irrigation process. The event-driven monitoring algorithm identifies key events in the irrigation system and adjusts the monitoring strategy in real time in response to the events. At the same time, it analyzes the irrigation process in combination with anomaly detection technology to generate irrigation process monitoring records; The real-time adjustment submodule adopts an adaptive control method based on the irrigation process monitoring record to dynamically adjust the irrigation parameters. The adaptive control method analyzes the irrigation data in real time and adjusts the irrigation parameters according to the difference between the current and expected irrigation effects to generate an irrigation effect optimization record.

7. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The water source management module includes a water source investigation submodule, a water volume allocation submodule, and a water source optimization submodule; The water source investigation submodule uses the information of reservoirs, groundwater and recycled water, adopts the geographic information system analysis method, investigates the water source through spatial data analysis and remote sensing image interpretation, applies hydrological data modeling technology, including watershed simulation and groundwater dynamic analysis, comprehensively evaluates the water source status, and generates water source status results; The water allocation submodule is based on the water source status results, uses genetic algorithm optimization, allocates water through population initialization, fitness function calculation and genetic operation, combines the water demand prediction model, conducts time series analysis and consumption pattern evaluation, and formulates a water allocation plan; The water source optimization submodule is based on the water allocation plan, adopts a neural network optimization algorithm, optimizes the water source configuration through a feedforward neural network and a back propagation algorithm, combines the resource allocation decision support system, performs system simulation and optimization plan generation, optimizes the water source configuration, and generates a water source optimization plan.

8. The farmland irrigation control system based on the Internet of Things according to claim 1 is characterized in that: The fertilizer distribution module includes a fertilizer demand analysis submodule, a distribution plan formulation submodule, and an intelligent delivery submodule; The fertilizer demand analysis submodule uses a crop growth model based on the water source optimization plan and crop growth requirements to perform fertilizer demand analysis through photosynthesis simulation and soil-plant-atmosphere continuum model, and also applies a fertilizer demand prediction algorithm to perform linear regression analysis and demand calculation, analyze crop demand for fertilizer, and generate fertilizer demand prediction results; The distribution plan formulation submodule is based on the fertilizer demand forecast results, adopts the logistics network optimization model, plans the fertilizer distribution through supply chain network design and transportation route optimization, combines the cost-benefit analysis method, conducts cost minimization strategy and benefit maximization evaluation, and generates a fertilizer distribution plan; The intelligent delivery submodule is based on the fertilizer distribution plan, adopts an adaptive control algorithm, and performs fertilizer delivery through PID controller and fuzzy logic control. At the same time, it uses environmental sensing technology, including soil moisture sensors and crop growth monitors, to monitor environmental conditions to control fertilizer delivery and generate an intelligent fertilizer delivery plan.

9. The farmland irrigation control system based on the Internet of Things according to claim 1, characterized in that: The irrigation effect evaluation module includes a crop growth evaluation submodule, a soil condition evaluation submodule, and a resource utilization evaluation submodule; The crop growth assessment submodule is based on the fertilizer distribution plan and adopts the decision tree analysis method to analyze the crop growth data by building a decision tree model, including selecting the best segmentation point from the data to create a tree node, branching the node, avoiding overfitting through pruning operations, assessing the impact of irrigation on crop growth, and generating a crop growth impact analysis; The soil condition assessment submodule is based on crop growth impact analysis, adopts principal component analysis, calculates the covariance matrix of soil sample data, extracts key components, performs dimensionality reduction processing on key components, analyzes and evaluates the impact of irrigation on soil conditions, and generates soil condition impact analysis; The resource utilization assessment submodule is based on soil condition impact analysis, adopts a linear programming model, defines the objective function and constraints of water and fertilizer use, uses the simplex algorithm to solve the optimal solution, evaluates the efficiency of water and fertilizer use, and generates an irrigation resource efficiency analysis.

10. The farmland irrigation control system based on the Internet of Things according to claim 1, characterized in that: The adaptive adjustment module includes a strategy adjustment submodule, an execution plan update submodule, and an environment adaptation submodule; The strategy adjustment submodule is based on irrigation resource efficiency analysis and adopts a simulated annealing algorithm. By randomly selecting points in the solution space as initial solutions, the system temperature is gradually reduced to search for the global optimal solution, which is used to adjust the irrigation strategy to match the changes in the environment and crop needs, and generate an irrigation strategy optimization plan; The execution plan update submodule is based on the irrigation strategy optimization scheme and adopts a dynamic programming method to decompose the problem into overlapping sub-problems, recursively solve the sub-problems, construct a global optimal irrigation execution plan, and generate an updated irrigation execution plan; The environmental adaptation submodule uses a genetic algorithm based on the updated irrigation execution plan, including population initialization, fitness evaluation, and finding the optimal solution through gene crossover and mutation operations, to ensure that the irrigation plan continues to adapt to environmental changes and crop needs and generate an adaptive irrigation plan.

Images