A data processing method and system for soil detection

Abstract

The present invention relates to the field of data processing technology, and discloses a data processing method and system for soil detection, wherein the system comprises: an acquisition module, comprising a sensor network and a node control unit arranged in a detection area; a preprocessing module, configured to determine whether there are missing values; a data completion module, configured to obtain the missing value position when it is determined that there are missing values, and determine the initial missing value according to the weighted average value of soil information on both sides of the missing value position; a data correction module, configured to correct the initial missing value; and a storage module, configured to respectively store humidity values, temperature values, precipitation data, plant coverage data, topography data, and the final missing values ​​after the correction and establish a corresponding database. The present invention improves the accuracy and reliability of soil detection data by improving the data processing flow and correction mechanism, and provides strong technical support for agricultural production and soil management.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data processing method and system for soil detection. Background Art

[0002] Soil moisture refers to the moisture content in the soil, specifically, whether the moisture content in the soil meets the needs of crop growth. Soil moisture is crucial to crop growth. It not only affects crop germination, growth, development and yield, but is also directly related to the rational use of water resources and the sustainability of agricultural production. Rationally mastering the laws of soil moisture changes and timely adjusting irrigation or drainage play an important role in improving crop yield and quality. Therefore, in agricultural production, detecting soil moisture is an important part of ensuring the healthy growth of crops.

[0003] However, in the process of soil testing, data missing is an unavoidable problem, which may be caused by sensor failure, communication interruption, environmental interference, etc. Missing data will affect the accuracy of soil testing results, thereby affecting agricultural management and decision-making. Therefore, how to effectively deal with missing values ​​in soil testing data to improve data quality has become an urgent problem to be solved. Summary of the invention

[0004] In view of this, the present invention proposes a data processing method and system for soil detection, aiming to solve the problem of data missing in the current soil detection process.

[0005] In one aspect, the present invention provides a data processing system for soil detection, comprising: a collection module, comprising a sensor network and a node control unit arranged in a detection area, wherein the sensor network is configured to collect soil information of the detection area over time, and the node control unit is configured to detect whether the sensor network is faulty. The soil information includes humidity value, temperature value and precipitation data of the detection area.

[0006] The preprocessing module is configured to calculate a soil information change rate threshold based on the soil information, determine whether to eliminate the soil information obtained by the sensor network based on the soil information change rate threshold, and determine whether there is a missing value based on the judgment result and the node control unit.

[0007] The data completion module is configured to obtain the missing value position when it is determined that there is a missing value, and determine the initial missing value based on the soil information on both sides of the missing value position.

[0008] The data correction module is configured to correct the initial missing value, and the correction includes: obtaining the initial missing value and precipitation data, and judging whether there is precipitation at the time corresponding to the initial missing value according to the precipitation data. If the judgment result is yes, the initial missing value is corrected for precipitation, and if the judgment result is no, no precipitation correction is performed.

[0009] Temperature correction, plant coverage correction and terrain correction are performed according to the temperature value, plant coverage data and terrain data respectively. After the correction is completed, the result is output and used as the final missing value.

[0010] The storage module is configured to store humidity values, temperature values, precipitation data, plant coverage data, topography data and the final missing values ​​after the correction respectively and establish a corresponding database.

[0011] Furthermore, the sensor network includes: a collection sensor and a redundant sensor, the collection sensor is used to obtain the humidity value, temperature value, and precipitation intensity of the detection area in real time, and the redundant sensor is used to replace the collection sensor.

[0012] The node control unit is specifically configured to: pre-set an inspection cycle, and whenever an inspection cycle is met, replace the currently working sensor and perform fault judgment.

[0013] When the first fault condition and / or the second fault condition is met, the node control unit determines that a fault has occurred and issues an instruction to replace the currently working sensor.

[0014] The first fault condition is to detect the communication status between the sensor network and the node control unit through the ACK / NACK signal of the communication protocol layer. If the communication attempt fails, it is determined to be a fault. The second fault condition is to set a timeout time. If the sensor network does not feedback within the timeout time, it is determined to be a fault.

[0015] Furthermore, when a sensor is replaced, the following judgment is performed: the values ​​of the acquisition sensor and the redundant sensor are compared, and when (BA) / B≥1.02%, it is judged that the acquisition sensor and / or the redundant sensor is faulty, wherein A is the smaller value between the acquisition sensor and the redundant sensor, and B is the larger value between the acquisition sensor and the redundant sensor.

[0016] A known standard signal is input into a sensor that is not currently working to determine whether the output signal of the sensor is the same as the standard signal.

[0017] If the judgment result is different, the sensor is replaced again and subsequent replacement is stopped.

[0018] If the judgment result is the same, no action is taken.

[0019] Furthermore, the preprocessing module is specifically configured as follows: the soil information change rate threshold includes a moisture change rate threshold and a temperature change rate threshold.

[0020] The change rates of any two adjacent humidity values ​​and temperature values ​​in the database are calculated respectively, and the maximum humidity value change rate is selected as the humidity change rate threshold, and the maximum temperature value change rate is selected as the temperature change rate threshold.

[0021] The real-time humidity value and the adjacent humidity values ​​collected by the sensor network are respectively obtained, the real-time humidity value change rate is calculated, and the real-time humidity value change rate is judged with the humidity value change rate threshold.

[0022] When the real-time humidity value change rate is greater than or equal to the humidity value change rate threshold, the humidity values ​​collected in real time by the sensor network are discarded and the missing value positions are recorded according to the collection time.

[0023] Furthermore, when the node control unit determines that there are missing values, it also includes: determining whether there is corresponding soil information at each collected time point, and if not, recording the missing value position according to the collection time.

[0024] Further, the data completion module is specifically configured to: when determining the initial missing value according to the weighted average of the soil information on both sides of the missing value position, obtain the number of the initial missing values, and the initial missing value is obtained according to the following relationship:

[0025] .

[0026] Where Hi is the i-th initial missing value counted from the collection time. i is an integer, and 1≤i≤the number of initial missing values. It is the soil information adjacent to the left. is the soil information adjacent to the right. N is the initial missing value.

[0027] Furthermore, the data correction module is specifically configured as follows: the precipitation data includes precipitation intensity and precipitation duration, the precipitation intensity is obtained according to the collection time corresponding to the initial missing value, the precipitation intensity is compared with a pre-set precipitation threshold, and when the precipitation intensity is greater than or equal to the precipitation threshold, it is determined that precipitation exists.

[0028] The precipitation correction includes: obtaining the precipitation intensity and precipitation duration, and calculating the precipitation adjustment coefficient according to the precipitation intensity and precipitation duration:

[0029] .

[0030] Among them, C is the precipitation adjustment coefficient. is the precipitation intensity in mm / hour. is the precipitation duration in hours. x is the precipitation intensity index, and 1.2≤x≤2. y is the precipitation duration index, and 0.5≤y≤1.5.

[0031] Further, the temperature correction includes:

[0032] .

[0033] The plant cover amendments include:

[0034] .

[0035] The terrain correction includes:

[0036] .

[0037] Where, T is the temperature correction coefficient, t is the real-time temperature corresponding to the collection time, t0 is the reference temperature, and t0 is 20°C. z is the temperature correction index, and 0.1≤z≤0.3. Q is the plant cover correction coefficient, f is the plant cover index, and 0.1≤f≤0.5. P is the plant coverage, 0≤P≤1. B is the terrain correction system. θ is the ground slope. g is the terrain index, and 1≤g≤2. S is the soil type coefficient.

[0038] Furthermore, the final missing value HI is calculated in the following way: .

[0039] On the other hand, the present invention also proposes a method applied to the above-mentioned data processing system for soil detection, the method comprising: deploying a sensor network and a node control unit in a detection area, collecting soil information of the detection area over time and detecting whether the sensor network is faulty. The soil information includes humidity value, temperature value and precipitation data of the detection area.

[0040] The soil information change rate threshold is calculated based on the soil information, and whether to discard the acquired soil information is determined based on the soil information change rate threshold. The presence of missing values ​​and the location of the missing values ​​are determined based on the judgment result and the node control unit.

[0041] When it is determined that there is a missing value, the missing value position is obtained, and the initial missing value is determined based on the weighted average of the soil information on both sides of the missing value position.

[0042] The initial missing value is corrected, and the correction includes: obtaining the initial missing value and precipitation data, and judging whether there is precipitation at the time corresponding to the initial missing value according to the precipitation data. If the judgment result is yes, the initial missing value is corrected for precipitation, and if the judgment result is no, no precipitation correction is performed.

[0043] Temperature correction, soil structure correction, plant cover correction and terrain correction are performed according to the temperature value, plant cover data and terrain data respectively. After the correction is completed, the result is output and used as the final missing value.

[0044] Humidity values, temperature values, precipitation data, plant coverage data, topography data and the final missing values ​​after the correction are stored separately and a corresponding database is established.

[0045] Compared with the prior art, the beneficial effects of the present invention are: by accurately detecting missing values ​​and their positions, and filling in the initial missing values ​​based on the weighted average of adjacent soil information, the influence of missing data on the accuracy of soil detection results is reduced, and the data correction module performs multi-dimensional correction on the initial missing values ​​by comprehensively considering factors such as precipitation data, temperature values, plant coverage data, and topography. At the same time, the present invention can more accurately reflect the actual soil moisture situation and improve the reliability and practicality of the data. The storage module not only stores core information such as soil moisture values, temperature values, and precipitation data, but also includes plant coverage data and topography data. By establishing a comprehensive database, soil detection data can be effectively managed and analyzed to support subsequent decision-making and research work. Integrating data acquisition, preprocessing, completion, correction and storage on a single platform realizes automation and efficiency of data processing, reduces human intervention and operational errors, and improves the efficiency of data processing. Taking into account a variety of factors affecting soil moisture (such as precipitation, temperature, plant coverage and topography), the system has strong adaptability, can process soil detection data under various complex environments, and provide more accurate analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] By reading the detailed description of the preferred embodiment below, various other advantages and benefits will become clear to those of ordinary skill in the art. The accompanying drawings are only used for the purpose of illustrating the preferred embodiment and are not considered to be limitations of the present invention. In addition, the same reference symbols are used to represent the same components throughout the accompanying drawings.

[0047] Figure 1 The figure is a functional block diagram of a data processing system for soil detection according to an embodiment of the present invention.

[0048] Figure 2 The figure is a flow chart of a data processing method for soil detection according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0050] See also Figure 1 As shown, an embodiment of the present invention provides a data processing system for soil detection, including: a collection module, including a sensor network and a node control unit arranged in a detection area, the sensor network is configured to collect soil information of the detection area over time, and the node control unit is configured to detect whether the sensor network is faulty. The soil information includes humidity value, temperature value and precipitation data of the detection area.

[0051] The preprocessing module is configured to calculate a soil information change rate threshold based on the soil information, determine whether to eliminate the soil information obtained by the sensor network based on the soil information change rate threshold, and determine whether there is a missing value based on the judgment result and the node control unit.

[0052] The data completion module is configured to obtain the missing value position when it is determined that there is a missing value, and determine the initial missing value based on the soil information on both sides of the missing value position.

[0053] The data correction module is configured to correct the initial missing values, and the correction includes: obtaining the initial missing values ​​and precipitation data, and judging whether there is precipitation at the time corresponding to the initial missing values ​​according to the precipitation data. If the judgment result is yes, the initial missing values ​​are corrected for precipitation, and if the judgment result is no, no precipitation correction is performed.

[0054] Temperature correction, plant coverage correction and terrain correction are performed according to the temperature value, plant coverage data and terrain data respectively. After the correction is completed, the result is output and used as the final missing value.

[0055] The storage module is configured to store humidity values, temperature values, precipitation data, plant coverage data, topography data and corrected final missing values ​​respectively and establish a corresponding database.

[0056] It can be explained that, through the sensor network and node control unit deployed in the detection area, soil information can be monitored in real time and sensor failures can be detected. This real-time monitoring and fault detection mechanism can detect and handle data anomalies in a timely manner, ensuring that the acquired data is more accurate and reliable. The change rate threshold of soil information is calculated to determine whether to remove abnormal data. This method helps to filter out abnormal data caused by sensor failure or environmental changes, thereby improving the validity and accuracy of the data. The initial missing value is determined by the weighted average of the soil information on both sides. This method can provide a relatively accurate initial missing value when the surrounding data of the missing value position is sufficiently stable, thereby reducing the error in the completion process. The data correction module corrects the initial missing value by combining multiple factors such as precipitation, temperature, plant cover data and topography. This mechanism can comprehensively adjust the missing value according to different environments and conditions, so that the corrected data is closer to the actual situation. By correcting the initial missing value by judging whether it is precipitation, the direct impact of precipitation on soil moisture can be effectively considered, thereby improving the accuracy of the correction. By comprehensively considering these factors for correction, the actual soil situation can be more comprehensively reflected and adapted to the data processing needs under different environmental conditions. The storage module not only stores core information such as soil moisture, temperature, and precipitation data, but also includes plant cover data and terrain data. By establishing a comprehensive database, data can be systematically managed and analyzed to support in-depth research and decision-making. Systematic storage and processing can effectively integrate various data types, making data analysis and query more convenient and efficient, and providing a good foundation for subsequent agricultural management and soil monitoring. Through the integration of modules such as preprocessing, data completion, and correction, data processing is automated. This reduces manual intervention and operational errors, and improves the efficiency and accuracy of data processing.

[0057] In some embodiments of the present application, the sensor network includes: a collection sensor and a redundant sensor, the collection sensor is used to obtain the humidity value, temperature value, and precipitation intensity of the detection area in real time, and the redundant sensor is used to replace the collection sensor.

[0058] The node control unit is specifically configured to: pre-set an inspection cycle, and whenever an inspection cycle is met, replace the currently working sensor and perform a fault judgment.

[0059] When the first fault condition and / or the second fault condition is met, the node control unit determines that a fault has occurred and issues an instruction to replace the currently working sensor.

[0060] The first fault condition is to detect the communication status between the sensor network and the node control unit through the ACK / NACK signal of the communication protocol layer. If the communication attempt fails, it is determined to be a fault. The second fault condition is to set a timeout period. If the sensor network does not feedback within the timeout period, it is determined to be a fault.

[0061] It can be explained that the system includes acquisition sensors and redundant sensors. The acquisition sensors are used to obtain soil moisture, temperature and precipitation intensity data in real time, while the redundant sensors are used to replace the acquisition sensors when they fail. The main function of the redundant design is to improve the fault tolerance of the system and ensure that the system can still operate normally when a sensor fails, avoiding data loss or quality degradation. Inspection cycle: The node control unit pre-sets the inspection cycle to regularly evaluate the status of the sensor. This mechanism helps the system to perform maintenance and monitoring at predetermined time intervals and detect potential problems in a timely manner. Periodic inspection can ensure the normal working state of the sensor and reduce data loss or errors caused by failures. The first fault condition: The communication status between the sensor network and the node control unit is detected through the ACK / NACK signal of the communication protocol layer. When the system attempts to communicate with the sensor, if the confirmation signal (ACK) is not received but the negative signal (NACK) is received or the communication fails, the node control unit will determine it as a fault. This mechanism can detect communication failures in a timely manner and prevent the system from continuing to work when the sensor fails. The second fault condition: Set a timeout to monitor the response of the sensor network. If no feedback is received from the sensor network within the set timeout, the node control unit will determine it as a fault. This timeout mechanism can handle response problems caused by communication delays or sensor failure, improving the stability and reliability of the system. Replacement of sensors: When the fault conditions are met, the node control unit will issue a command to replace the currently working sensor. The redundant sensor will immediately take over to ensure that the system continues to work normally. This automatic replacement mechanism ensures the continuity and stability of data collection and reduces the risk of system downtime or data interruption. Improve system reliability: Through this redundant design and periodic inspection, the system can continuously monitor and maintain the status of sensors, significantly improving the reliability of the system. Even if some sensors fail, the system can quickly switch to backup sensors to ensure that data collection is not affected. Reduce maintenance costs: Automatic fault detection and sensor replacement mechanisms reduce the need for manual intervention and reduce the maintenance cost of the system. The system can automatically handle faults, reducing the frequency of manual inspection and replacement of sensors. Optimize data quality: Timely detection and handling of faults ensure the accuracy and consistency of sensor data, thereby improving data quality. This is crucial for subsequent data analysis and decision support. Enhance the intelligence of the system: The intelligent node control unit and automatic fault handling mechanism improve the intelligence level of the system, enabling it to manage and maintain itself more autonomously and reduce dependence on manual operations.

[0062] In some embodiments of the present application, when a sensor is replaced, the following judgment is performed: the values ​​of the acquisition sensor and the redundant sensor are compared, and when (BA) / B≥1.02%, it is judged that the acquisition sensor and / or the redundant sensor is faulty, where A is the smaller value between the acquisition sensor and the redundant sensor, and B is the larger value between the acquisition sensor and the redundant sensor.

[0063] A known standard signal is input into a sensor that is not currently working to determine whether the output signal of the sensor is the same as the standard signal.

[0064] If the judgment result is different, the sensor is replaced again and subsequent replacement is stopped.

[0065] If the judgment result is the same, no action is taken.

[0066] It can be explained that the setting of the humidity change rate threshold and the temperature change rate threshold has the following functions: Ensure data stability: By setting the humidity change rate threshold and the temperature change rate threshold, erroneous data caused by sudden changes or abnormal fluctuations in sensor data can be avoided. This helps to maintain the stability and accuracy of soil information.

[0067] Calculate the change rate: Get historical soil data from the database and calculate the change rate between two consecutive data collections. Select the maximum value from the calculated humidity change rate as the humidity change rate threshold. Select the maximum value from the calculated temperature change rate as the temperature change rate threshold.

[0068] Detect abnormal data: By calculating the rate of change of humidity values ​​in real time, it is possible to detect whether the data exceeds the normal range of change. If the rate of change exceeds the threshold, it means that the data may be abnormal and needs to be eliminated.

[0069] Specifically, the humidity value and the adjacent humidity values ​​are collected from the sensor network in real time. The change rate is calculated: the calculated real-time humidity change rate is compared with the set humidity change rate threshold. If the real-time humidity change rate is greater than or equal to the humidity change rate threshold, it means that the data may be abnormal.

[0070] The role of eliminating abnormal data: By eliminating abnormal data, it is possible to prevent erroneous data from affecting subsequent data processing and analysis. This helps to improve data quality and ensure the accuracy of soil test results.

[0071] Data elimination: When the real-time humidity change rate is greater than or equal to the humidity change rate threshold, the humidity value collected by the sensor network in real time is eliminated. The position of the missing value is recorded according to the collection time for subsequent data completion and correction.

[0072] By setting and calculating the change rate threshold, abnormal data can be effectively detected and eliminated. This method can prevent erroneous analysis and decision-making caused by abnormal data and ensure the authenticity of soil test results.

[0073] Abnormal data processing: Real-time calculation of the rate of change and comparison with the threshold can detect data anomalies in time to avoid their impact on subsequent processing. Recording the location of missing values ​​provides a basis for subsequent data completion.

[0074] Comprehensive judgment mechanism: Through comprehensive judgment of humidity and temperature change rate, abnormal data can be identified more accurately, ensuring the comprehensiveness and accuracy of the data processing process. This method improves the robustness and data processing capabilities of the system.

[0075] Through the above steps and methods, a reliable data preprocessing system is established to ensure the quality and accuracy of soil testing data, thereby providing support for subsequent data analysis.

[0076] In some embodiments of the present application, the preprocessing module is specifically configured as follows: the soil information change rate threshold includes a moisture change rate threshold and a temperature change rate threshold.

[0077] Calculate the change rates of any two adjacent humidity values ​​and temperature values ​​in the database respectively, select the maximum humidity value change rate as the humidity change rate threshold, and select the maximum temperature value change rate as the temperature change rate threshold.

[0078] The real-time humidity value collected by the sensor network and the adjacent humidity values ​​are respectively obtained, the real-time humidity value change rate is calculated, and the real-time humidity value change rate is judged with the humidity value change rate threshold.

[0079] When the real-time humidity value change rate is greater than or equal to the humidity value change rate threshold, the humidity values ​​collected in real time by the sensor network are eliminated and the missing value positions are recorded according to the collection time.

[0080] In some embodiments of the present application, when the node control unit determines that there are missing values, it also includes: determining whether there is corresponding soil information at each collection time point, and if not, recording the missing value position according to the collection time.

[0081] In some embodiments of the present application, the data completion module is specifically configured to: when determining the initial missing value according to the weighted average of the soil information on both sides of the missing value position, obtain the initial number of missing values, and the initial missing value is obtained according to the following relationship:

[0082] .

[0083] Where Hi is the i-th initial missing value counted from the collection time. i is an integer, and 1≤i≤the number of initial missing values. It is the soil information adjacent to the left. is the soil information adjacent to the right. N is the initial missing value.

[0084] Specifically, data collection and recording: the sensor network collects soil information at specified time intervals, including moisture values, temperature values, and precipitation data. These data will be recorded in the data storage system to form time series data.

[0085] Missing value detection: The node control unit will check whether there is corresponding soil information at each acquisition time point. The specific operations are as follows: Get a list of time points: Get a list of all recorded acquisition time points. Check data integrity: For each time point, check whether there is corresponding soil information (humidity value, temperature value, precipitation data). This can be done by searching the data records.

[0086] Determine missing values: If one or more soil information (such as moisture value, temperature value, precipitation data) at a certain time point is missing, it is determined that there are missing values ​​at that time point.

[0087] Record the location of missing values: Record the time point of the missing value and the specific information missing (for example, humidity, temperature, or precipitation data) to form a log of the location of missing values.

[0088] Time series storage: All collected time points and corresponding soil information should be stored in a time series database for quick query and analysis. Missing value record: Establish a missing value record table to record each missing time point and its specific missing data items. Detection process: Traverse time points: Traverse all recorded time points. Verify data: For each time point, verify whether there are complete data items (humidity values, temperature values, precipitation data). Missing value confirmation: If one or more data items at a time point are missing, confirm that the time point is a missing value location. Record log: Record these missing time points and their missing data items in the missing value record table.

[0089] In some embodiments of the present application, the data correction module is specifically configured as follows: precipitation data includes precipitation intensity and precipitation duration, the precipitation intensity is obtained according to the collection time corresponding to the initial missing value, the precipitation intensity is compared with a pre-set precipitation threshold, and when the precipitation intensity is greater than or equal to the precipitation threshold, it is determined that precipitation exists.

[0090] Precipitation correction includes: obtaining precipitation intensity and precipitation duration, and calculating the precipitation adjustment coefficient based on the precipitation intensity and precipitation duration:

[0091] .

[0092] Among them, C is the precipitation adjustment coefficient. is the precipitation intensity in mm / hour. is the precipitation duration in hours. x is the precipitation intensity index, and 1.2≤x≤2. y is the precipitation duration index, and 0.5≤y≤1.5.

[0093] It should be noted that the accuracy of data correction is enhanced: by using precipitation intensity and precipitation duration to calculate the precipitation adjustment coefficient, the initial missing value can be corrected more accurately. This ensures that when the precipitation is large, the corrected value can reflect the actual precipitation impact, thereby improving the accuracy of the corrected data. Considering precipitation amount and duration: using precipitation intensity and precipitation duration as correction parameters can comprehensively consider the impact of precipitation amount and time on soil moisture, avoiding the correction error that may be caused by a single factor. Index adjustment mechanism: by setting the precipitation intensity index and precipitation duration index, the system can dynamically adjust the correction coefficient according to different precipitation intensities and durations. This enables the correction mechanism to adapt to various precipitation conditions and improves the flexibility and adaptability of the system. Adaptive correction: dynamically adjusting the correction coefficient according to precipitation intensity and duration can enable the system to make adaptive corrections to different precipitation events (such as short-term heavy precipitation and long-term weak precipitation), thereby improving the accuracy of data correction.

[0094] Reduce correction errors: Through accurate precipitation correction, data errors caused by precipitation factors can be effectively reduced. Ensure that data such as soil moisture can more truly reflect the actual situation and improve data quality. Reliable data correction: Considering the impact of precipitation intensity and duration on the correction coefficient, appropriate corrections can be made under different precipitation conditions, avoiding interference with soil data due to precipitation changes and improving data reliability.

[0095] Improve the intelligence level of the system: Use precipitation intensity and precipitation duration to calculate the precipitation adjustment coefficient, so that the system has a certain intelligent adjustment ability. It can automatically correct according to the actual precipitation situation, which improves the intelligence level of the system. Dynamic adjustment ability: Dynamically adjust the correction coefficient according to different precipitation conditions, which reflects the adaptive ability of the system and makes the correction process more in line with the actual situation.

[0096] By calculating the precipitation adjustment coefficient and making corrections based on precipitation intensity and precipitation duration, the precipitation correction module of the present invention can provide accurate soil data correction under variable precipitation conditions. This not only improves the accuracy of the data and the intelligence level of the system, but also optimizes the data quality and decision support capabilities, thereby enhancing the overall performance and reliability of the soil detection system.

[0097] In some embodiments of the present application, temperature correction includes:

[0098] .

[0099] Vegetation cover modifications include:

[0100] .

[0101] Terrain corrections include:

[0102] .

[0103] Where, T is the temperature correction coefficient, t is the real-time temperature corresponding to the collection time, t0 is the reference temperature, and t0 is 20°C. z is the temperature correction index, and 0.1≤z≤0.3. Q is the plant cover correction coefficient, f is the plant cover index, and 0.1≤f≤0.5. P is the plant coverage, 0≤P≤1. B is the terrain correction system. θ is the ground slope. g is the terrain index, and 1≤g≤2. S is the soil type coefficient.

[0104] In some embodiments of the present application, the final missing value HI is calculated in the following manner.

[0105] .

[0106] It should be noted that 0≤HI≤1, when HI>1, HI takes the value of 1.

[0107] Specifically, the process of obtaining the temperature correction index (z) is as follows: Data collection, soil moisture and temperature data: Soil moisture and corresponding temperature data are collected under different environments and seasons.

[0108] Experimental conditions: Set different temperature conditions and record the changes in soil moisture. This may need to be done in a laboratory or in a real environment.

[0109] Data analysis: Use statistical software (such as R, Python's pandas, scikit-learn, etc.) to perform regression analysis on the collected data to find the relationship between temperature and soil moisture. Based on the analysis results, a temperature correction model is established to determine the degree of impact of temperature changes on soil moisture.

[0110] Determine the index range: Extract the temperature correction factor from the experimental data and calculate its change at different temperatures.

[0111] Index adjustment: Set the range of temperature correction index (0.1 to 0.3) according to experimental results and actual application requirements.

[0112] Field verification: Verify the effect of the correction index in actual application scenarios to ensure that it can effectively adjust soil moisture data.

[0113] The process of obtaining the plant cover index (f) is as follows: Remote sensing data: The plant cover data of the area is obtained through remote sensing technology, using satellite images or drone photography.

[0114] Ground survey: Conduct a ground survey at the sample site to measure plant cover, using tools such as handheld devices or rulers.

[0115] Calculate plant coverage: Image processing: Use remote sensing image processing software (such as ENVI, ERDAS IMAGINE, etc.) to calculate plant coverage. Use image classification technology to distinguish between vegetation and non-vegetation areas.

[0116] Sample analysis: Calculate plant coverage based on ground survey data and obtain coverage ratio.

[0117] Calculate the plant cover index: Data analysis: Analyze the effect of plant cover on soil moisture. You can use regression analysis and other methods to find out the relationship between plant cover and soil moisture.

[0118] Set the index: Based on the data analysis results, set the range of the plant cover index (0.1 to 0.5) and calculate the actual correction factor.

[0119] Verification and adjustment: Apply the plant cover correction factor in the actual environment to verify its effect on soil moisture data.

[0120] The process of obtaining the topographic relief index (g) is as follows: Digital elevation model (DEM): Obtain digital elevation model (DEM) data, which can be obtained through satellite measurement, aerial photography or ground measurement.

[0121] Terrain features: including information such as altitude, slope, and terrain type.

[0122] Data analysis, terrain analysis: Use geographic information system (GIS) software (such as ArcGIS, QGIS, etc.) to analyze terrain feature data and calculate the impact of terrain slope and altitude on soil moisture.

[0123] Model building: A mathematical model was established to describe the effect of terrain characteristics on soil moisture and determine the calculation method of the topographic relief index.

[0124] Calculate the topographic relief index: Index calculation: Substitute the topographic feature data into the model to calculate the topographic relief index. The index is usually in the range of 1 to 2, and the specific value is determined based on the actual analysis results.

[0125] Verification and adjustment, field testing: Test the correction factors under different terrain conditions, verify their effectiveness and make adjustments.

[0126] The process of obtaining the soil type coefficient (S) is as follows: Soil sample collection: Collect different types of soil samples in the test area. Use a soil drilling tool to obtain samples.

[0127] Laboratory analysis: Soil samples are analyzed in the laboratory for physical and chemical properties, including soil texture, porosity, water holding capacity, etc.

[0128] Data Analysis: Classification and Grouping: Classify the soils based on the characteristics of the soil samples and identify different soil types.

[0129] Establish coefficient: Based on the relationship between soil type and soil moisture, calculate the soil type coefficient. This coefficient represents the correction effect of different soil types on soil moisture.

[0130] See also Figure 2 As shown, the embodiment of the present invention also provides a data processing method for soil detection, and the data processing system for the above soil detection includes: S1, deploying a sensor network and a node control unit in the detection area, collecting soil information of the detection area over time and detecting whether the sensor network is faulty. The soil information includes humidity value, temperature value and precipitation data of the detection area.

[0131] S2, calculate the soil information change rate threshold according to the soil information, determine whether to discard the acquired soil information according to the soil information change rate threshold, and determine whether there are missing values ​​and the missing value positions according to the judgment result and the node control unit.

[0132] S3, when it is determined that there is a missing value, the missing value position is obtained, and the initial missing value is determined according to the weighted average of the soil information on both sides of the missing value position.

[0133] S4, correcting the initial missing values, the correction includes: obtaining the initial missing values ​​and precipitation data, and judging whether there is precipitation at the time corresponding to the initial missing values ​​according to the precipitation data. If the judgment result is yes, the initial missing values ​​are corrected for precipitation, and if the judgment result is no, no precipitation correction is performed.

[0134] S5, perform temperature correction, soil structure correction, plant cover correction and terrain correction according to the temperature value, plant cover data and terrain data respectively, and output the result after the correction is completed as the final missing value.

[0135] Humidity values, temperature values, precipitation data, plant cover data, topography data and corrected final missing values ​​are stored separately and a corresponding database is established.

[0136] It can be understood that by calculating the soil information change rate threshold, inaccurate data can be eliminated, data quality can be improved, and subsequent analysis and decision-making can be ensured to be based on reliable information.

[0137] The weighted average is used to determine the initial missing values, making data completion more reasonable and reducing the analysis bias caused by missing data.

[0138] Correcting the precipitation data and adjusting the missing values ​​according to the actual precipitation intensity and duration can effectively reflect the actual impact of precipitation on soil moisture and provide more accurate soil information.

[0139] Comprehensive corrections are made based on multiple factors such as temperature, plant coverage, topography, etc., ensuring that the correction results can take into account the influence of various environmental factors, thereby improving the practicality and accuracy of the data.

[0140] The information such as humidity values, temperature values, precipitation data, plant cover data and topographic data are systematically stored, and a database is established with corrected missing values, providing a comprehensive data management platform to facilitate subsequent data query and analysis.

[0141] The establishment of the database will help to track and monitor the changing trends of soil information in the long term and provide historical data support for agricultural decision-making.

[0142] By monitoring and correcting sensor failures in the system, the robustness of the system is improved, ensuring that the system can still provide accurate data when sensor problems occur.

[0143] The real-time correction mechanism enables the system to adapt to changes in environmental conditions, thereby providing real-time and reliable data support.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A data processing system for soil detection, characterized in that: include: A collection module, comprising a sensor network and a node control unit arranged in a detection area, wherein the sensor network is configured to collect soil information of the detection area over time, and the node control unit is configured to detect whether the sensor network is faulty; the soil information includes humidity value, temperature value and precipitation data of the detection area; a preprocessing module configured to calculate a soil information change rate threshold according to the soil information, determine whether to remove the soil information obtained by the sensor network according to the soil information change rate threshold, and determine whether there is a missing value according to the determination result and the node control unit; The data completion module is configured to obtain the missing value position when it is determined that there is a missing value, and determine the initial missing value according to the soil information on both sides of the missing value position; The data correction module is configured to correct the initial missing values, and the correction includes: The initial missing value and precipitation data are obtained, and whether there is precipitation at the time corresponding to the initial missing value is determined according to the precipitation data; if the judgment result is yes, the initial missing value is corrected for precipitation, and if the judgment result is no, no precipitation correction is performed; the data correction module is specifically configured as follows: The precipitation data includes precipitation intensity and precipitation duration. The precipitation intensity is obtained according to the collection time corresponding to the initial missing value. The precipitation intensity is compared with a preset precipitation threshold. When the precipitation intensity is greater than or equal to the precipitation threshold, it is determined that precipitation exists. The precipitation correction includes: obtaining the precipitation intensity and precipitation duration, and calculating the precipitation adjustment coefficient according to the precipitation intensity and precipitation duration: ； Where, C is the precipitation adjustment coefficient; ra is the precipitation intensity, in millimeters per hour; rb is the precipitation duration, in hours; x is the precipitation intensity index, and 1.2≤x≤2; y is the precipitation duration index, and 0.5≤y≤1.5; Temperature correction, plant coverage correction and terrain correction are performed according to the temperature value, plant coverage data and terrain data respectively, and the result is output as the final missing value after the correction is completed; the temperature correction includes: ； The plant cover amendments include: ； The terrain correction includes: ； Wherein, T is the temperature correction coefficient, t is the real-time temperature corresponding to the collection time, t0 is the reference temperature, t0 is 20°C; z is the temperature correction index, and 0.1≤z≤0.3; Q is the plant cover correction coefficient, f is the plant cover index, and 0.1≤f≤0.5; P is the plant coverage, 0≤P≤1; B is the terrain correction system; θ is the ground slope; g is the terrain index, and 1≤g≤2; S is the soil type coefficient; The final missing value HI is calculated in the following way: ； The storage module is configured to respectively store humidity values, temperature values, precipitation data, plant coverage data, topographic data and the final missing values ​​after the correction and establish a corresponding database.

2. The data processing system for soil detection according to claim 1, characterized in that: The sensor network includes: a collection sensor and a redundant sensor, wherein the collection sensor is used to obtain the humidity value, temperature value, and precipitation intensity of the detection area in real time, and the redundant sensor is used to replace the collection sensor; The node control unit is specifically configured to: pre-set an inspection cycle, and whenever an inspection cycle is met, replace the currently working sensor and perform fault judgment; When the first fault condition and / or the second fault condition is met, the node control unit determines that a fault has occurred and issues an instruction to replace the currently working sensor; The first fault condition is to detect the communication status between the sensor network and the node control unit through the ACK / NACK signal of the communication protocol layer. If the communication attempt fails, it is determined to be a fault; the second fault condition is to set a timeout period. If the sensor network does not provide feedback within the timeout period, it is determined to be a fault.

3. The data processing system for soil detection according to claim 2, characterized in that: When the sensor is replaced, the following judgment is made: The values ​​of the acquisition sensor and the redundant sensor are compared. When (BA) / B≥1.02%, it is determined that the acquisition sensor and / or the redundant sensor is faulty, wherein A is the smaller value between the acquisition sensor and the redundant sensor, and B is the larger value between the acquisition sensor and the redundant sensor; Input a known standard signal to the sensor that is not currently working, and determine whether the output signal of the sensor is the same as the standard signal; If the judgment result is different, the sensor is replaced again and subsequent replacement is stopped; If the judgment result is the same, no action is taken.

4. The data processing system for soil detection according to claim 3, characterized in that: The preprocessing module is specifically configured as follows: The soil information change rate threshold includes a humidity change rate threshold and a temperature change rate threshold; Calculate the change rates of any two adjacent humidity values ​​and temperature values ​​in the database respectively, select the maximum humidity value change rate as the humidity change rate threshold, and select the maximum temperature value change rate as the temperature change rate threshold; Respectively obtain the real-time collected humidity value and adjacent humidity values ​​of the sensor network, calculate the real-time humidity value change rate, and compare the real-time humidity value change rate with the humidity value change rate threshold; When the real-time humidity value change rate is greater than or equal to the humidity value change rate threshold, the humidity values ​​collected in real time by the sensor network are discarded and the missing value positions are recorded according to the collection time.

5. The data processing system for soil detection according to claim 4, characterized in that: When the node control unit determines that there is a missing value, it also includes: Determine whether there is corresponding soil information at each collection time point. If not, record the missing value position according to the collection time.

6. The data processing system for soil detection according to claim 5, characterized in that: The data completion module is specifically configured as follows: When the initial missing value is determined according to the weighted average of the soil information on both sides of the missing value position, the number of the initial missing values ​​is obtained, and the initial missing value is obtained according to the following relationship: ； Where Hi is the i-th initial missing value counted from the collection time; i is an integer, and 1≤i≤the number of initial missing values; It is the soil information adjacent to the left; is the soil information adjacent to the right; N is the initial missing value.

7. A data processing method for soil detection, applied to the data processing system for soil detection according to any one of claims 1 to 6, characterized in that: The method comprises: A sensor network and a node control unit are deployed in the detection area to collect soil information of the detection area over time and detect whether the sensor network is faulty; the soil information includes humidity value, temperature value and precipitation data of the detection area; Calculate a soil information change rate threshold according to the soil information, determine whether to remove the acquired soil information according to the soil information change rate threshold, and determine whether there are missing values ​​and the position of the missing values ​​according to the determination result and the node control unit; When it is determined that there is a missing value, the missing value position is obtained, and the initial missing value is determined according to the weighted average of the soil information on both sides of the missing value position; The initial missing values ​​are corrected, and the correction includes: The initial missing value and precipitation data are obtained, and whether there is precipitation at the time corresponding to the initial missing value is determined according to the precipitation data; if the judgment result is yes, the initial missing value is corrected for precipitation, and if the judgment result is no, no precipitation correction is performed; the data correction module is specifically configured as follows: The precipitation data includes precipitation intensity and precipitation duration. The precipitation intensity is obtained according to the collection time corresponding to the initial missing value. The precipitation intensity is compared with a preset precipitation threshold. When the precipitation intensity is greater than or equal to the precipitation threshold, it is determined that precipitation exists. The precipitation correction includes: obtaining the precipitation intensity and precipitation duration, and calculating the precipitation adjustment coefficient according to the precipitation intensity and precipitation duration: ； Among them, C is the precipitation adjustment coefficient; is the precipitation intensity, in mm / h; is the duration of precipitation, in hours; x is the precipitation intensity index, and 1.2≤x≤2; y is the precipitation duration index, and 0.5≤y≤1.5; Temperature correction, soil structure correction, plant cover correction and terrain correction are performed according to the temperature value, plant cover data and terrain data respectively. After the correction is completed, the result is output as the final missing value; the temperature correction includes: ； The plant cover amendments include: ； The terrain correction includes: ； Wherein, T is the temperature correction coefficient, t is the real-time temperature corresponding to the collection time, t0 is the reference temperature, t0 is 20°C; z is the temperature correction index, and 0.1≤z≤0.3; Q is the plant cover correction coefficient, f is the plant cover index, and 0.1≤f≤0.5; P is the plant coverage, 0≤P≤1; B is the terrain correction system; θ is the ground slope; g is the terrain index, and 1≤g≤2; S is the soil type coefficient; The final missing value HI is calculated in the following way: ； Humidity values, temperature values, precipitation data, plant coverage data, topography data and the final missing values ​​after the correction are stored separately and a corresponding database is established.

Images