Coastal saline-alkali soil water level adjusting system based on real-time monitoring and intelligent regulation and control

Abstract

According to the coastal saline-alkali land underground water level adjusting system based on real-time monitoring and intelligent regulation and control, the system integrates the soil salinity sensor, the underground water level sensor and the central processing unit, future trend prediction is carried out by monitoring key parameters such as soil salinity and underground water level in real time in combination with a deep learning model, and the real-time monitoring and intelligent regulation and control are achieved. And precise intelligent regulation and control are realized. The system can effectively reduce soil salinization, prevent seawater from flowing backwards, improve the utilization efficiency of water resources and reduce the labor management cost at the same time. The method is characterized in that the application of multi-parameter comprehensive monitoring, a deep learning prediction model and a self-adaptive intelligent regulation and control algorithm provides a new technical solution for coastal saline-alkali land treatment.

Description

Technical Field

[0001] The present invention relates to technological innovation in the field of soil salinization control and groundwater resource management, and specifically to a comprehensive system that integrates modules such as multi-source environmental monitoring, data acquisition and preprocessing, deep learning prediction, intelligent control algorithm, user interaction and system maintenance. Background Art

[0002] As a special type of land resource, coastal saline-alkali land has high soil salt content and large fluctuations in groundwater levels, which poses a severe challenge to the growth of crops. Traditional methods for managing coastal saline-alkali land mainly rely on manual monitoring and empirical regulation, which is not only inefficient, but also difficult to accurately grasp the real-time changes in soil salinity and groundwater levels, resulting in regulatory measures often lagging behind actual needs and making it difficult to effectively respond to complex and changing environmental conditions.

[0003] With the rapid development of the Internet of Things, big data and artificial intelligence technologies, new ideas and means have been provided for the management of coastal saline-alkali land. By integrating a variety of sensors, real-time monitoring of key parameters such as soil salinity, groundwater level, soil moisture, temperature and meteorological conditions can be achieved, providing rich data support for precise regulation. At the same time, the introduction of deep learning technology enables the system to establish a dynamic prediction model based on historical data and real-time monitoring data, accurately predict the future trend of soil salinity and groundwater level, and provide a scientific basis for intelligent regulation.

[0004] At present, there is still a lack of a comprehensive system on the market that can fully integrate multi-source environmental monitoring, deep learning prediction, intelligent control algorithms and user interaction functions to achieve accurate, real-time and intelligent control of groundwater levels in coastal saline-alkali land. Therefore, the development of a coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent control has important practical significance and application value. Summary of the invention

[0005] The present invention aims to solve the problems of low efficiency, slow response and difficulty in real-time adaptation to environmental changes in the existing coastal saline-alkali land management. By integrating multi-source environmental monitoring, intelligent data processing and prediction, and adaptive control algorithms, an innovative coastal saline-alkali land groundwater level intelligent control system is proposed. The system can not only realize real-time monitoring of soil salinity, groundwater level and meteorological conditions, but also predict future change trends based on deep learning models, and automatically adjust irrigation, drainage and other operations through intelligent control algorithms to maintain soil salinity within an appropriate range, effectively prevent soil salinization and seawater backflow, and improve water resource utilization efficiency.

[0006] The coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent control includes ten or more key modules to ensure accurate and efficient water level control. Specifically, the system is equipped with a multi-source soil monitoring module, which contains a soil salinity sensor array, humidity and temperature sensors to monitor soil conditions in real time; the groundwater level monitoring module uses high-precision sensors to accurately capture water level changes; the meteorological monitoring module integrates a variety of sensors to monitor external environmental conditions such as wind speed, wind direction, temperature, humidity and rainfall. The data acquisition and preprocessing module is responsible for comprehensively collecting and processing these data, and improving data quality through verification, cleaning, compression and encryption steps. The real-time data transmission module uses advanced wireless communication technology to ensure that the preprocessed data can be delivered to the central processing unit in real time. The deep learning prediction module relies on powerful algorithms to accurately predict the future trend of soil salinity and groundwater level based on historical and real-time data. The intelligent control algorithm module intelligently generates irrigation and drainage control strategies based on the prediction results and preset parameters. The execution control module responds quickly and accurately controls the operation of related equipment. The user interaction interface module provides an intuitive operation interface that supports real-time data display, historical record query, personalized system parameter settings and alarm notification functions. Finally, the system maintenance and optimization module ensures the long-term stable operation of the system and regularly performs system maintenance, sensor calibration, and optimization and update of deep learning models.

[0007] Preferably, in the interconnection design between the modules of the coastal saline-alkali land groundwater level regulation system for real-time monitoring and intelligent regulation, a standardized interface protocol is adopted to ensure seamless data transmission between the modules. This design not only simplifies the system integration process, but also greatly improves the efficiency and stability of data transmission. At the same time, the standardized interface also gives the system a high degree of flexibility, allowing each module to be flexibly replaced or upgraded according to actual needs. For example, when it is necessary to introduce more advanced sensors or optimize data processing algorithms, only the corresponding modules need to be replaced without large-scale changes to the entire system, thereby reducing the maintenance cost of the system and extending its service life. This feature enables the system to better adapt to the complexity and dynamics of coastal saline-alkali land management, and provides strong support for the sustainable development of agricultural production.

[0008] Preferably, the data acquisition and preprocessing module integrates advanced edge computing technology. When the front-end devices such as the multi-source soil monitoring module, the groundwater level monitoring module and the meteorological monitoring module collect the raw data, the data is first transmitted to the edge computing node deployed in the data acquisition and preprocessing module. At these nodes, the edge computing technology quickly performs preliminary processing on the data, including data verification, outlier removal, data compression and other steps. Through intelligent data compression algorithms, such as LZ4 or Snappy, the module can reduce the volume of raw data to 20%-30% of the original while ensuring data quality, thereby greatly reducing the bandwidth requirements and delays during data transmission. Subsequently, the preprocessed streamlined data is efficiently transmitted to the central processing unit through a standardized interface for further analysis and processing. This process not only significantly improves the data processing speed, but also reduces the load on the central processing unit, ensuring the overall high performance and real-time response capabilities of the system.

[0009] Preferably, the deep learning prediction module has built-in advanced deep learning frameworks (such as TensorFlow or PyTorch), which can continuously draw knowledge from multiple information such as soil salinity, humidity, temperature, groundwater level, and meteorological data collected in real time. During the training phase, the module uses large-scale historical data sets to automatically adjust the network weights through the back-propagation algorithm, and continuously optimizes the internal structure of the prediction model to capture the complex laws of dynamic changes in soil water and salt. As the system runs longer, the module can also perform incremental learning based on newly acquired real-time data, further refine the model parameters, and improve the prediction accuracy of future soil salinity and groundwater level changes. In addition, the deep learning prediction module also has excellent generalization capabilities, which can effectively cope with the challenges of different environmental conditions and soil characteristics, and ensure the stability and reliability of the prediction results. This series of automatic learning and optimization mechanisms enables the system to continuously provide high-quality prediction services and provide solid data support for subsequent intelligent control decisions.

[0010] Preferably, the intelligent control algorithm module dynamically adjusts the irrigation strategy according to the growth cycle characteristics of crop types (such as rice, wheat, etc.), such as different requirements for water and nutrients at different growth stages. Specifically, the module first determines the irrigation threshold of each crop at different growth stages based on the crop growth model and historical planting data. Subsequently, the real-time data of the current soil salinity sensor (monitoring accuracy ±0.1% dS / m), soil moisture sensor (accuracy ±2%) and meteorological monitoring module (such as wind speed ±0.3m / s, wind direction resolution 1°, temperature ±0.5℃, etc.) are combined to analyze the soil environmental state and external environmental conditions. Based on these analyses, the algorithm module calculates the optimal irrigation amount and irrigation timing, and automatically generates irrigation instructions. For drainage strategies, the module also considers the water holding characteristics of soil types (such as clay, sand, etc.) and the changing trend of groundwater levels to ensure that drainage operations can effectively prevent seawater backflow and maintain a suitable soil moisture state. This dynamic adjustment process ensures the accuracy and timeliness of irrigation and drainage strategies, and helps to improve soil quality, crop yields and water resource utilization efficiency.

[0011] Preferably, the user interaction interface module shows a high degree of flexibility and convenience, and fully supports the access of multiple devices such as smart phones, tablets and traditional computers. Users can access the system interface anytime and anywhere through a standard Web browser or a dedicated APP, and enjoy the convenience of remote monitoring and management. The interface design is intuitive and friendly, integrating core functions such as real-time data display, historical data query, system settings and alarm notifications. In the real-time data display area, users can clearly see the dynamic changes of key parameters such as current soil salinity, groundwater level, soil moisture and temperature, and the data update frequency can reach once per second to ensure the real-time nature of information. The historical data query function allows users to trace back monitoring records within any time period as needed, providing strong support for scientific research analysis or management decisions. The system setting module provides flexible configuration options, and users can adjust parameters such as soil salinity thresholds, irrigation and drainage strategies according to their own needs to achieve personalized management. At the same time, once the system detects an abnormal situation, such as excessive soil salinity, abnormal fluctuations in groundwater levels, etc., the user interaction interface will immediately pop up a striking alarm notification, and send reminders to preset managers through SMS, emails and other methods to ensure that the problem is handled in a timely manner. This combination of multi-device access and remote management not only improves the operability and ease of use of the system, but also greatly enhances the flexibility and responsiveness of system management.

[0012] The method of the coastal saline-alkali land groundwater level regulation system has the following detailed process:

[0013] S1. Initialize the system: fully configure the entire system, including setting the initial parameters of soil salinity sensors, groundwater level sensors, and meteorological monitoring equipment (such as anemometers, thermometers, etc.). Check the hardware connection and software configuration of each module (sensor array, data collector, central processing unit, user interface, etc.) to ensure that all equipment is in normal working condition. Set initial control parameters such as soil salinity threshold, crop growth cycle parameters, and irrigation and drainage strategies.

[0014] S2. The multi-source soil monitoring module, groundwater level monitoring module and meteorological monitoring module start real-time monitoring and data collection: the soil salt sensor monitors the salt content and soil moisture in the soil in real time with an accuracy of ±0.1% dS / m (accuracy ±2%). The groundwater level sensor accurately monitors the changes in the groundwater level. The meteorological monitoring module collects meteorological data such as wind speed (accuracy of ±0.3m / s), wind direction (resolution 1°), and temperature (accuracy of ±0.5℃).

[0015] S3. Data acquisition and preprocessing module receives data: The data collector receives data from each sensor through wireless communication. The received data is preliminarily processed, including data cleaning (removing outliers), data compression (reducing transmission burden) and data formatting (unifying data format).

[0016] S4. Real-time data transmission module sends data to the central processing unit: The pre-processed data is transmitted to the central processing unit via a high-speed network to ensure the real-time and accuracy of the data.

[0017] S5. The deep learning prediction module uses historical data and real-time data for prediction analysis: The deep learning model loads historical data and combines it with real-time monitoring data to predict the future trend of soil salinity and groundwater level. The prediction results include the trend of soil salinity change and groundwater level fluctuation in the future.

[0018] S6. The intelligent control algorithm module formulates control strategies based on the prediction results and preset parameters: Based on the prediction results of the deep learning model, combined with the preset soil salinity threshold, crop growth cycle, soil type and climate conditions, the intelligent control algorithm calculates the best irrigation and drainage strategy. The control strategy includes specific parameters such as irrigation amount, irrigation timing, and drainage amount.

[0019] S7. The execution control module receives the control instructions and controls the operation of the irrigation system, drainage system and other equipment: The execution control module receives the control instructions from the intelligent control algorithm module. According to the instructions, the operation status of the irrigation system (such as water pumps, sprinkler irrigation equipment, etc.) and the drainage system (such as drainage pumps, drainage ditches, etc.) is automatically adjusted to achieve precise irrigation and drainage.

[0020] S8. The user interface module displays the system status and control effects in real time and receives user instructions: The user interface displays the monitoring results of key parameters such as soil salinity, groundwater level, and meteorological data in real time. It displays the irrigation and drainage strategies formulated by the intelligent control algorithm and the execution effects. It allows users to remotely view the system status, set soil salinity thresholds, and receive alarm notifications through devices such as smartphones, tablets, or computers.

[0021] S9. System maintenance and optimization module regularly performs system maintenance tasks: regularly calibrates sensors to ensure the accuracy of monitoring data. Updates deep learning models to improve prediction accuracy. Checks system hardware and software status to identify and address potential problems in a timely manner.

[0022] S10. Repeat steps S2 to S9 to achieve continuous monitoring and intelligent regulation of groundwater levels in coastal saline-alkali land: The system enters a continuous operation state and continuously repeats the above steps to achieve real-time monitoring and intelligent regulation of groundwater levels in coastal saline-alkali land. Through continuous optimization and adjustment, the system is ensured to always maintain the best working state, effectively reduce soil salinization, and improve water resource utilization efficiency.

[0023] Preferably, during the real-time data monitoring process of the system, the integrated anomaly detection module is combined with the data processing process. When it is found that the soil salinity, groundwater level or meteorological monitoring data deviates from the preset normal threshold range, or when internal system problems such as sensor communication failure and data collection anomaly are detected, the system immediately triggers the alarm mechanism. At this time, the anomaly detection module transmits the abnormal information to the user interface in real time, and displays or sends an alarm notification to the preset manager's mobile phone with high priority. The notification content contains a specific description of the abnormality, the time of occurrence and preliminary processing suggestions. The user or system administrator responds quickly and initiates corresponding processing measures based on the received alarm information, such as immediate on-site inspection, replacement of faulty sensors, adjustment of control strategies, etc., to ensure the continuous stable operation and efficient control efficiency of the system. This process greatly improves the system's fault response capability and control accuracy through intelligent automatic monitoring and timely human-computer interaction.

[0024] Preferably, the storage medium uses a highly reliable non-volatile memory, such as an SSD or NAND flash memory, to ensure the stability and durability of the stored data. The computer program stored thereon is carefully designed and rigorously tested, and is explicitly configured to automatically execute the method steps described in detail in claim 7 or 8. After the program is started, the initialization parameters are first loaded, including the soil salinity threshold, the groundwater level monitoring accuracy, the anomaly detection threshold, etc., to ensure that the system operates according to the preset standards. Subsequently, the program enters the real-time monitoring mode, receives data from the sensor through an efficient data processing algorithm, and performs data preprocessing, anomaly detection and other processes. Once an abnormality is found or the preset alarm condition is reached, the program will immediately trigger the alarm mechanism and generate detailed alarm information, notifying the management personnel through the user interface or SMS. At the same time, the program also integrates deep learning models and intelligent control algorithms, which can predict the future trend of soil salinity and groundwater level based on real-time and historical data, and formulate and implement precise irrigation and drainage strategies accordingly. The entire execution process is clear and the steps are specific, which ensures the intelligent and precise control of the groundwater level in coastal saline-alkali land, and achieves effective mitigation of soil salinization and significant improvement of water resource utilization.

[0025] Preferably, the system integration service covers the entire process from the initial planning of the system to the final delivery, including detailed demand analysis, system design, equipment selection and procurement, on-site installation and wiring, system debugging and optimization, user operation training and other key links. We have a professional technical team that can ensure that the system is designed, implemented and maintained according to the highest standards. In addition, we also provide long-term after-sales service support, including regular system inspection and maintenance, technical upgrades, troubleshooting and user consultation, etc., to ensure that customers can fully enjoy the convenience and benefits brought by the intelligent control system, realize the precise management of groundwater levels in coastal saline-alkali land, reduce soil salinization, and improve water resource utilization efficiency.

[0026] The above technical solution can bring the following significant technical effects:

[0027] 1. Precision control and soil quality improvement: By real-time monitoring of soil salinity, groundwater level and meteorological conditions, combined with deep learning prediction models and intelligent control algorithms, this system can achieve precise control of groundwater levels in coastal saline-alkali land. This can not only effectively reduce the degree of soil salinization and maintain soil salinity within the appropriate range for crop growth, but also significantly improve soil quality and provide strong guarantees for the healthy growth of crops. The improvement of soil quality will directly lead to an increase in crop yields and improve agricultural production efficiency.

[0028] 2. Intelligent management and cost reduction: This system introduces the concept of intelligent management, which greatly reduces the need for human intervention through automated monitoring, prediction and regulation. This not only reduces labor costs, but also avoids regulation errors and delays caused by human factors. At the same time, the intelligent regulation algorithm can dynamically adjust irrigation and drainage strategies according to actual environmental conditions and crop needs, realize the rational use and conservation of water resources, and further reduce the cost of agricultural production.

[0029] 3. Strong environmental adaptability and convenient operation: This system has good environmental adaptability and flexibility, and can cope with soil characteristics and environmental conditions in different regions. Through the user-friendly interactive interface and remote monitoring function, users can easily set soil salinity thresholds, view system status and receive abnormal alarm information. This highly integrated intelligent system makes the governance and management of coastal saline-alkali land more convenient and efficient, and provides strong technical support and guarantee for agricultural production. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 The block diagram of the regulation system of the present invention is

[0031] Figure 2 This is the flow chart of the intelligent control algorithm of the present invention

[0032] Figure 3 Flow chart of the method for using the regulating system of the present invention DETAILED DESCRIPTION

[0033] The following will be combined with the attached embodiment of the present invention Figures 1 to 3 , the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] A coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent regulation. Its highly integrated design integrates ten key modules to achieve accurate and efficient water level regulation. The system adopts a multi-source soil monitoring module, equipped with a soil salinity sensor array (monitoring accuracy of ±0.1% dS / m), a soil moisture sensor (accuracy ±2%), and a soil temperature sensor (accuracy ±0.5℃) to ensure comprehensive and accurate monitoring of the soil environment. The groundwater level monitoring module is equipped with a high-precision groundwater level sensor (measurement error does not exceed ±1cm) to monitor groundwater level changes in real time. The meteorological monitoring module integrates sensors such as wind speed (measurement range 0-40m / s, accuracy ±0.3m / s), wind direction (resolution 1°), temperature (±0.5℃), humidity (±3%RH) and rainfall (measurement range 0-400mm / h, accuracy ±4%) to fully capture external environmental conditions. The data acquisition and preprocessing module works at a data acquisition frequency of 1000 times per second, strictly verifies, cleans and compresses the data to less than 50% of the original data, and uses AES-256 encryption technology to ensure data security. The real-time data transmission module transmits data to the central processing unit in real time at a rate of 10 data packets per second through low-power LoRa wireless communication technology. The deep learning prediction module uses advanced LSTM neural network algorithms to predict the trend of soil salinity and groundwater level in the next 7 days based on historical data and real-time data in the past two years, with an error rate of less than 5%. The intelligent control algorithm module automatically formulates and executes irrigation (accuracy to per cubic meter), drainage and other control strategies based on the prediction results and preset soil salinity thresholds (for example, ≤4dS / m), crop types and current environmental conditions. The execution control module responds quickly to control instructions and accurately controls the flow of the irrigation system and drainage system (adjustment range 0-100L / min, accuracy ±2%). The user interface module provides clear real-time data chart display, quick historical record query, system parameter setting (including soil salinity threshold adjustment), and abnormal alarm notification functions. The system maintenance and optimization module regularly performs system self-checks, sensor calibration (once every quarter) and deep learning model optimization updates (once every six months) to ensure long-term stable operation of the system. This series of high-precision and high-efficiency modules together constitute an advanced coastal saline-alkali land groundwater level intelligent control system.

[0035] The characteristics of the coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent regulation are further refined as follows: the modules in the system are closely connected through interface protocols that comply with international standards such as RS-485 or CAN 2.0B, ensuring a data transmission rate of up to 10Mbps and a delay of less than 1 millisecond, thus achieving seamless data transmission. Specifically, the front-end acquisition devices such as the multi-source soil monitoring module, the groundwater level monitoring module, and the meteorological monitoring module accurately transmit the collected data to the data acquisition and preprocessing module at a speed of 10 data packets per second through a preset standardized interface. Subsequently, the preprocessed data also follows this standardized interface specification and flows seamlessly to the real-time data transmission module, and then is sent to the central processing unit through wireless communication technologies such as LoRa at a speed of at least 1 data packet per second. After the intelligent control algorithm module formulates the control strategy based on the prediction results, the execution control module also receives instructions through standardized electrical and data interfaces to control the irrigation system (response time ≤ 1 second), drainage system (flow regulation accuracy ± 2%) and other equipment to perform corresponding operations. In addition, the standardized interface design also gives the system powerful modular upgrade capabilities. For example, users can replace it with a higher-precision soil salinity sensor (monitoring accuracy increased to ±0.05% dS / m) or update the deep learning prediction model to the latest version as needed without interrupting the overall operation of the system to adapt to changing environmental conditions and ensure that the system always maintains optimal performance. According to the coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent regulation as described in claim 1 or 2, its data acquisition and preprocessing module ingeniously incorporates efficient edge computing technology. Specifically, when front-end devices such as soil salinity sensor arrays (accuracy ±0.1% dS / m), soil moisture sensors (accuracy ±2%), and soil temperature sensors (accuracy ±0.5°C) generate about 1,000 raw data per second, these data are first sent to the edge computing nodes deployed in the data acquisition and preprocessing modules. On these high-performance edge computing devices, using advanced data compression algorithms such as LZ4 or Snappy, the system can complete data verification, cleaning and compression within milliseconds, reducing the amount of data transmission to about 25% of the original data (i.e., a compression ratio of 4:1), while ensuring that data quality is not affected. Subsequently, these optimized data are transmitted to the central processing unit in real time through a standardized RS-485 or CAN 2.0B interface at a speed of at least 500 data packets per second (compared to one-tenth of the original data). In this process, the application of edge computing technology not only reduces the amount of data transmission by about 75%, but also greatly shortens the data processing time, which increases the response speed of the entire system to the millisecond level, thereby ensuring that the system can achieve real-time monitoring and intelligent regulation of groundwater levels in coastal saline-alkali land with high efficiency.

[0036] The deep learning prediction module of the coastal saline-alkali groundwater level regulation system based on real-time monitoring and intelligent regulation integrates high-precision and high-generalization automatic learning and optimization mechanisms. Specifically, the module is built on mainstream deep learning frameworks such as TensorFlow or PyTorch, and has the ability to process large-scale data sets (such as daily soil salinity, humidity, temperature, groundwater level and meteorological data in the past five years, with a total data volume of more than 1TB). During the training process, the module uses the back propagation algorithm to automatically adjust millions of parameters in the neural network based on historical data. After hundreds of rounds of iterative training, the model prediction error drops below 5% (at least 20% higher than the traditional statistical model). As the system continues to run, the deep learning prediction module can also receive new data samples in real time, conduct incremental learning, and automatically update the model every two weeks to adapt to complex situations such as seasonal changes and extreme weather. At the same time, the module also has excellent generalization capabilities, which can cope with the differences brought by different soil types (such as clay, sand, etc.) and crop types (such as rice, wheat, etc.), ensuring the accuracy and reliability of prediction results under different environmental conditions. These parameterized details demonstrate the power of the deep learning prediction module in improving prediction accuracy and generalization ability.

[0037] The core feature of the intelligent control system for groundwater levels in coastal saline-alkali land is the high customization and dynamic adaptability of the intelligent control algorithm module. Specifically, the module performs well in crop growth cycle management. It can finely divide the growth stages (such as germination, growth, heading, maturity, etc.) according to the specific needs of different crops (such as rice, whose growth cycle is about 120-150 days; wheat, about 220-270 days), and set unique irrigation thresholds for each stage (such as the daily water requirement of rice during the growth period is about 5-8mm, and wheat needs more during the heading period). At the same time, the module is tightly integrated with soil salinity sensors (accuracy up to ±0.1% dS / m), soil moisture sensors (accuracy ±2%), and high-precision meteorological stations (wind speed monitoring error ±0.3m / s, wind direction accuracy to 1°, temperature error ±0.5℃), to capture subtle changes in soil and climate environment in real time. By analyzing these real-time data and combining them with the preset soil salinity threshold (such as setting a safety range of 0.3%-0.6% dS / m), the algorithm module can dynamically calculate the irrigation and drainage strategies that best suit the current conditions. For example, when the soil salinity approaches the upper limit, the system automatically increases the drainage and reduces the irrigation to prevent salt accumulation; in dry weather, the irrigation system is started in advance to ensure the water supply for crops. This series of parameterized and refined operations not only improves the accuracy of irrigation and drainage, but also significantly enhances the system's adaptability to different soil types (such as clay with strong water retention and sandy soil with fast drainage) and climatic conditions, thereby effectively promoting soil health, increasing crop yields, and optimizing the utilization efficiency of water resources.

[0038] The user interface module of the coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent control demonstrates excellent compatibility and practicality, and supports access from devices including but not limited to iOS / Android smartphones, iPad series tablets, and computers with Windows / macOS operating systems. Users can easily remotely monitor and manage the system through the web browser on these devices (supporting HTML5 standards to ensure cross-platform compatibility) or dedicated APP (such as .ipa on iOS or .apk files on Android, with version updates once a quarter). The interface design follows modern UI / UX principles and provides a data update frequency of up to 1 per second, ensuring that users can view the dynamic changes of key parameters such as soil salinity (accurate to ±0.1% dS / m), groundwater level (accuracy depends on the sensor), soil moisture (±2% accuracy) and temperature (±0.5℃ accuracy) in real time. The historical data query function supports any selection of time ranges from the last hour to the past year, and is presented in a variety of forms such as charts and tables, which facilitates users to conduct in-depth analysis. The system settings module provides detailed parameter configuration options. Users can freely set soil salinity thresholds (such as between 0.3%-0.6% dS / m), irrigation and drainage strategies (considering crop growth cycles, soil types and climatic conditions), etc., to achieve personalized and precise management. When the system detects an abnormal situation, such as soil salinity exceeding the preset threshold or abnormal fluctuations in groundwater levels, the user interaction interface will immediately display an alarm message in the form of a pop-up window, and send instant notifications to the preset list of managers through SMS (supports major global operators) and email (supports SMTP / IMAP protocols) and other communication methods to ensure that the problem is responded to and handled quickly. This series of functional designs not only improves the convenience of user operation and the manageability of the system, but also greatly enhances the overall flexibility and intelligence of the system.

[0039] The method of the coastal saline-alkali land groundwater level regulation system has the following detailed process:

[0040] S1. Initialize the system: Configure the soil salinity sensor and set its measurement accuracy to ±0.1% dS / m to ensure accurate monitoring of the salt content in the soil. Set the measurement accuracy of the groundwater level sensor to ±1cm to meet the monitoring needs of subtle changes in the groundwater level. In the meteorological monitoring equipment, the anemometer accuracy is set to ±0.3m / s and the thermometer accuracy is set to ±0.5℃ to accurately capture changes in meteorological conditions. Set the soil salinity threshold to between 0.3% dS / m and 0.6% dS / m as a reference for intelligent control. Check and confirm that all hardware connections are stable, the software configuration is correct, and the system is in standby mode.

[0041] S2. Real-time monitoring and data collection: The soil salt sensor collects data every 5 minutes to record the current soil salt content and soil moisture (accuracy ±2%). The groundwater level sensor collects data once an hour to monitor the real-time changes in the groundwater level. The meteorological monitoring equipment records wind speed, wind direction and temperature data every 10 minutes to ensure the timeliness of the data.

[0042] S3. Data preprocessing: The received data is first tested for outliers to remove data points that are beyond a reasonable range. The data is compressed to reduce the amount of data during transmission while retaining key information. The data is formatted to a unified standard for subsequent processing and analysis.

[0043] S4. Real-time data transmission: Through wireless communication technology (such as 4G / 5G, Wi-Fi, etc.), ensure that the pre-processed data is transmitted to the central processing unit within 3 seconds.

[0044] S5. Deep learning prediction: The deep learning model loads historical data from the past week and analyzes it in combination with the real-time monitoring data from the last hour. It predicts the changing trend of soil salinity in the next 24 hours, including the highest and lowest values ​​and fluctuation range. It also predicts the expected changes in groundwater levels in the next 24 hours to ensure the accuracy and timeliness of the prediction.

[0045] S6. Intelligent control strategy formulation: Based on the prediction results of the deep learning model, combined with the preset soil salinity threshold, crop growth cycle (such as the stage of rice growth cycle with high water demand), soil type (such as the difference in irrigation strategy between clay soil and sandy soil) and current meteorological conditions (such as the need to increase irrigation volume during high temperature and dryness), formulate detailed irrigation and drainage strategies. Determine the exact amount of water for each irrigation (such as 30-50 cubic meters per mu of land), irrigation frequency (such as once a day or every other day), and drainage (if necessary) and other specific parameters.

[0046] S7. Execution control: After receiving the intelligent control strategy, the execution control module immediately starts the irrigation system (such as starting the water pump, setting the spraying range and intensity of the sprinkler equipment) and the drainage system (such as turning on the drainage pump and adjusting the flow of the drainage ditch) to ensure that the irrigation and drainage operations are completed on time.

[0047] S8. User interaction and feedback: The user interface displays key parameters such as soil salinity, groundwater level, meteorological data, and current irrigation and drainage status in real time. It allows users to remotely set soil salinity thresholds, adjust irrigation and drainage strategies, and receive system alarm notifications (such as excessive soil salinity, equipment failure, etc.).

[0048] S9. System maintenance and optimization: Calibrate sensors weekly to ensure measurement accuracy. Use newly collected data monthly to train and optimize deep learning models to improve prediction accuracy. Regularly check system hardware and software status to prevent potential problems.

[0049] S10. Continuous monitoring and regulation: The system maintains a continuous operation state, and continuously repeats steps S2 to S9 to form a closed-loop coastal saline-alkali land groundwater level intelligent regulation system. Through continuous optimization and adjustment, ensure that the system can adapt to different environmental conditions and soil characteristics, effectively reduce soil salinization, and improve water resource utilization efficiency.

[0050] When the system monitors data in real time, the anomaly detection module will accurately analyze soil salinity (±0.05% dS / m outside the set threshold is considered abnormal), groundwater level (deviation of ±0.5cm is considered abnormal) and meteorological monitoring data (such as wind speed ±0.1m / s, temperature ±0.2℃ changes are considered abnormal). Once data anomalies or sensor communication failures, data collection anomalies (such as missing data or continuous abnormal values ​​for more than 3 times) and other system internal problems are found, the alarm mechanism will be activated immediately. The alarm information will be transmitted to the user interface at the fastest speed (no more than 5 seconds) and will be immediately notified to the preset management personnel through highlighting or SMS. The alarm content includes the type of anomaly, specific numerical deviation, occurrence time (accurate to seconds) and preliminary processing instructions (such as recommendations to immediately go to the site for inspection or replace the faulty sensor). Based on the detailed alarm information, the management personnel can quickly make judgments and take effective treatment measures to ensure the efficient and stable operation of the system and maintain the precise control of the groundwater level in the coastal saline-alkali land.

[0051] The computer-readable storage medium adopts high-performance SSD storage technology to ensure the reliability and fast access of data storage. The computer program stored thereon accurately configures the detailed steps of executing the method in claim 7 or 8. After the program is started, the initial settings are first loaded, including the soil salinity threshold (set to 0.3% dS / m to 0.6% dS / m), the groundwater level monitoring accuracy (±1cm), and the abnormal detection parameters (such as soil salinity deviation ±0.05% dS / m, groundwater level deviation ±0.5cm, meteorological data deviation such as wind speed ±0.1m / s, temperature ±0.2℃, etc.). Subsequently, the program automatically enters the real-time monitoring state, receives accurate data from multiple sensors every second, executes efficient data preprocessing algorithms, and performs abnormal detection in real time. If any data anomaly or system failure exceeding the preset threshold is detected, the program immediately generates detailed alarm information, including the type of anomaly, specific numerical deviation (such as soil salinity exceeding 0.05% dS / m), and the time of occurrence (accurate to seconds), and sends the alarm information to the management personnel within 5 seconds through the user interface and the preset SMS notification method. In addition, the program also integrates deep learning models and intelligent control algorithms, which can accurately predict future changes in soil salinity and groundwater levels based on real-time monitoring and historical data, and automatically adjust irrigation and drainage strategies to ensure precise control of groundwater levels in coastal saline-alkali land, effectively reduce soil salinization, and significantly improve the utilization efficiency of water resources.

[0052] System integration services cover the entire process from initial system planning to final delivery, including detailed demand analysis, system design, equipment selection and procurement, on-site installation and wiring, system debugging and optimization, user operation training and other key links. We have a professional technical team that can ensure that the system is designed, implemented and maintained in accordance with the highest standards. In addition, we also provide long-term after-sales service support, including regular system inspection and maintenance, technical upgrades, troubleshooting and user consultation, to ensure that customers can fully enjoy the convenience and benefits brought by the intelligent control system, achieve accurate management of groundwater levels in coastal saline-alkali land, reduce soil salinization, and improve water resource utilization efficiency.

[0053] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A coastal saline-alkali land groundwater level regulation system based on real-time monitoring and intelligent regulation, characterized in that: The system includes the following ten or more modules: a multi-source soil monitoring module, including a soil salt sensor array, a soil moisture sensor, and a soil temperature sensor, which are used to monitor the salt, moisture, and temperature in the soil in real time; a groundwater level monitoring module, equipped with a high-precision groundwater level sensor, which monitors groundwater level changes in real time; a meteorological monitoring module, which integrates meteorological sensors such as wind speed, wind direction, temperature, humidity, and rainfall to monitor external environmental conditions; The data acquisition and preprocessing module is responsible for collecting data from various sensors and performing verification, cleaning, compression and encryption processing; the real-time data transmission module uses wireless communication technology to transmit preprocessed data to the central processing unit in real time; the deep learning prediction module uses deep learning algorithms to predict the future trends of soil salinity and groundwater levels based on historical data and real-time data; The intelligent control algorithm module formulates irrigation, drainage and other control strategies based on the prediction results and preset parameters; the execution control module receives control instructions and controls the operation of irrigation systems, drainage systems and other equipment; the user interaction interface module provides real-time data display, historical record query, system parameter setting, alarm notification and other functions; the system maintenance and optimization module is responsible for tasks such as regular system maintenance, sensor calibration, and deep learning model updates.

2. The system according to claim 1, characterized in that The modules are connected through standardized interfaces to achieve seamless data transmission and flexible module replacement.

3. The system according to claim 1 or 2, characterized in that: The data acquisition and preprocessing module uses edge computing technology to reduce data transmission volume and improve data processing efficiency.

4. The system according to any one of claims 1 to 3, characterized in that: The deep learning prediction module can automatically learn and optimize the prediction model to improve prediction accuracy and generalization ability.

5. The system according to any one of claims 1 to 4, characterized in that: The intelligent control algorithm module can dynamically adjust irrigation and drainage strategies according to the growth cycle, soil type and climatic conditions of different crops.

6. The system according to any one of claims 1 to 5, characterized in that: The user interface module supports access from a variety of devices, including smartphones, tablets and computers, providing convenient remote monitoring and management functions.

7. A method for operating the coastal saline-alkali land groundwater level regulation system according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: a. Initialize the system, configure and check each module; b. The multi-source soil monitoring module, groundwater level monitoring module and meteorological monitoring module start real-time monitoring and data collection; c. The data acquisition and preprocessing module receives the data, performs preprocessing and transmits it to the real-time data transmission module; d. The real-time data transmission module sends data to the central processing unit; e. The deep learning prediction module uses historical data and real-time data for predictive analysis; f. The intelligent control algorithm module formulates control strategies based on the prediction results and preset parameters; g. The execution control module receives control instructions and controls the operation of irrigation systems, drainage systems and other equipment; h. The user interaction interface module displays the system status and control effects in real time and receives user instructions; i. The system maintenance and optimization module regularly performs system maintenance tasks, including sensor calibration, model update, etc.; j. Repeat steps b to i to achieve continuous monitoring and intelligent regulation of groundwater levels in coastal saline-alkali land.

8. The method according to claim 7, characterized in that It also includes abnormal detection and alarm steps. When abnormal data or system failure is monitored, the user is notified in time and appropriate processing measures are taken.

9. A computer-readable storage medium having a computer program stored thereon, the program being configured to execute the method steps of claim 7 or 8.

10. A system integration service based on the system or method according to any one of claims 1 to 9, including all-round support such as system planning, design, installation, debugging, training and after-sales service.

Images