Cultivated land quality monitoring system based on black land protection

Abstract

The invention relates to the technical field of black land protection, and discloses a cultivated land quality monitoring system based on black land protection. The system comprises a data acquisition module which is used for obtaining the position and time of a sampling point, the organic matter content and the soil layer thickness, and calculating quality evaluation indexes to generate an evaluation set; the feature extraction module is used for extracting quality evaluation indexes and positions, sorting adjacent point pairs according to spatial distances, and marking consistent and difference sections to obtain a feature consistency partition marking set; the state evaluation module is used for acquiring a pH value and water content time sequence of the sampling points in the section with consistent characteristics, and evaluating the degradation influence degree by combining the farming intensity to generate a comprehensive analysis result; the risk early warning module is used for identifying abnormal points with degradation response values greater than a reference value and located in a difference section to form an abnormal point set; and the result output module is used for acquiring abnormal points and information, marking deterioration risk point locations and generating monitoring and early warning results. The system can comprehensively monitor the quality of black land cultivated land and perform early warning in time.

Description

Technical Field

[0001] This invention relates to the field of black soil protection technology, specifically to a farmland quality monitoring system based on black soil protection. Background Technology

[0002] Black soil, as an extremely precious natural resource, plays a vital role in agricultural production. However, in recent years, due to factors such as over-cultivation, irrational land use, and environmental factors, black soil is facing serious quality degradation problems, such as declining soil organic matter content, thinning soil layer, pH imbalance, and abnormal water content. These problems not only lead to reduced arable land productivity but also pose a severe challenge to the sustainable development of agriculture.

[0003] Currently, there are many shortcomings in the monitoring of arable land quality in black soil regions. Most existing monitoring systems lack comprehensive collection and analysis of multi-dimensional indicators of arable land quality. For example, in terms of data collection, they may only focus on single soil factors, such as organic matter content or pH value, while ignoring other important indicators such as soil thickness and moisture content, thus failing to comprehensively reflect the quality status of arable land.

[0004] Traditional methods often fail to adequately consider the spatial relationships between sampling points during feature extraction and analysis. They cannot sort adjacent point pairs according to spatial distance, nor can they easily identify consistent and dissimilar segments within adjacent point pairs. This makes it impossible to accurately identify the spatial distribution characteristics and variation patterns of arable land quality.

[0005] In the soil condition assessment phase, existing technologies typically cannot combine tillage intensity to analyze the degree of degradation under soil evolution. They also cannot extract time series data on pH and water content for trend comparison, making it difficult to accurately assess the extent of soil degradation and thus failing to provide an effective basis for the protection and management of black soil.

[0006] In terms of risk warning, traditional systems lack comprehensive consideration of degradation response values, characteristic segments, and other relevant parameters. They cannot accurately identify sampling points with a risk of deterioration, resulting in the inability to issue timely warnings and hindering the implementation of effective prevention and control measures.

[0007] Furthermore, existing monitoring systems also have shortcomings in data processing and result output. The standardization of data collection is not perfect, and the result output is not intuitive or comprehensive enough, failing to meet the needs of practical applications for monitoring and managing the quality of black soil farmland.

[0008] Therefore, there is an urgent need for a system that can comprehensively and accurately monitor the quality of black soil farmland, promptly identify problems and issue early warnings, so as to achieve effective protection and sustainable utilization of black soil. Summary of the Invention

[0009] The purpose of this invention is to provide a farmland quality monitoring system based on black soil protection to solve the problems mentioned in the background art.

[0010] To achieve the above objectives, the present invention provides a farmland quality monitoring system based on black soil protection, the system comprising: The data acquisition module obtains the location and time of the farmland sampling points, collects the organic matter content and soil layer thickness at the corresponding locations, associates the sampling points and calculates the corresponding quality evaluation indicators, and generates a farmland quality evaluation set. The feature extraction module extracts the quality evaluation indicators and their corresponding locations from the cultivated land quality evaluation set, sorts adjacent point pairs by spatial distance, marks the consistent and different segments in the adjacent point pairs, and obtains the feature consistency partition label set. The state assessment module obtains the sampling points located in the feature-consistent segment of the feature consistency partition annotation set, extracts the pH value and water content time series, compares the changing trends with the tillage intensity, assesses the degree of degradation impact under soil evolution, and generates a comprehensive analysis result of degradation impact. The risk warning module identifies outliers in the comprehensive analysis results of degradation impacts, where the degradation response value is greater than the average response benchmark value and is located in the characteristic difference zone, forming a set of abnormal farmland quality points. The results output module obtains all locations and corresponding location information of the abnormal farmland quality points set, marks locations with a risk of deterioration, and generates farmland quality monitoring and risk warning results.

[0011] Preferably, the farmland quality evaluation set includes quality evaluation indicators, spatial coordinates of sampling points, and standardized soil factors. The feature consistency zoning label set specifically includes feature consistency section labeling, feature difference section labeling, and quality indicator difference rate of adjacent sampling points. The comprehensive analysis results of degradation impact include the degree of influence of pH value decrease rate on farmland, the degree of influence of water content increase rate on farmland, and the comparison of intensity degradation response under each soil evolution condition. The farmland quality anomaly point set includes the spatial location of anomaly points, the wind erosion amplitude characteristics of anomaly points, and the ratio of cultivated land to area change of anomaly points. The farmland quality monitoring and risk warning results include a list of monitored anomaly points and a joint judgment label of three indicators for anomaly points.

[0012] Preferably, the data acquisition module includes: The sampling information acquisition submodule acquires the location coordinates and sampling time of the farmland sampling point, collects the organic matter content data and soil layer thickness data corresponding to the coordinate location, and records the collection results as two soil factors: organic matter factor and thickness factor, and acquires the soil factor data set of the sampling point. The soil factor standardization submodule performs standardization processing on the organic matter factor and thickness factor data in the soil factor data set of the sampling points, establishes a correspondence between the standardized results and the location coordinates of the sampling points, calculates the average value of the standardized organic matter value and the standardized thickness value as the quality evaluation index, and generates a set of arable land quality evaluation data.

[0013] Preferably, the feature extraction module includes: The quality index extraction submodule obtains the quality evaluation indexes and corresponding location data in the cultivated land quality evaluation set, identifies the spatial distribution relationship of all sampling points based on the location information, calls the sampling point location set, calculates and sorts the spatial sampling points based on the adjacent distance threshold, and generates a sorted sequence of adjacent sampling point distances. The difference rate calculation submodule calculates the quality index difference rate between two adjacent sampling points i and j based on the adjacent sampling point distance sorting sequence and uses a set rule to calculate the quality index difference rate sequence. The feature consistency recognition submodule extracts the direction of organic matter change and thickness change between adjacent sampling points based on the quality index difference rate sequence. It classifies and labels each pair of sampling points according to whether the change trends in the two directions are consistent. It records and groups the segments with consistent features and the segments with different features to obtain the feature consistency partition label set.

[0014] Preferably, the state assessment module includes: The environmental sequence acquisition submodule filters out segments marked with consistent features from the feature consistency partitioning label set, detects pH value data and relative water content data within the sampling time period of each sampling point, arranges them in chronological order to form pH value time series and water content time series, and generates a soil change time series set. Based on the soil change time series set, the state evolution analysis submodule calculates the rate of pH decrease and the rate of water content increase between consecutive time nodes in the time series of each sampling point. The rate of pH decrease and the rate of water content increase are compared side by side under the same tillage intensity conditions. By jointly analyzing the two types of rate indicators, the numerical relationship between the change trends under the intensity is identified. The influence value series of each sampling point is integrated to establish a comprehensive analysis result of degradation impact.

[0015] Preferably, the risk warning module includes: The recording and filtering submodule filters the sampling points whose degradation response value is greater than the average response benchmark value and the sampling points in the characteristic difference range according to the comprehensive analysis results of the degradation impact. It extracts the continuous sampling records of the sampling points in chronological order, collects the tillage intensity and tillage area data corresponding to each time node, and generates a continuous sampling record set. The parameter change ratio calculation submodule calls the continuous sampling record set to extract the intensity value and area of ​​the sampling point at two consecutive time nodes, calculates the intensity change ratio and cultivated area change ratio respectively, and integrates them into an intensity change ratio sequence and a cultivated area change ratio sequence to establish a cultivated land fluctuation change dataset. Based on the farmland fluctuation change dataset, the risk identification submodule extracts wind erosion amplitude data and water content fluctuation data for the corresponding time period, determines whether the intensity change ratio and area change ratio both exceed the set fluctuation identification threshold, determines whether wind erosion amplitude and water content fluctuation both exceed the risk judgment threshold, marks the time nodes that meet the conditions as anomalies, and generates a set of farmland quality anomaly points.

[0016] Preferably, the result output module includes: The comprehensive indicator judgment submodule obtains all locations and corresponding coordinates and identification information of the farmland quality anomaly point set, calculates the joint risk judgment value of the kth sampling point using set rules, and establishes a joint risk judgment value sequence. The abnormal results processing submodule, based on the joint risk judgment value sequence, filters out points whose degradation response value is greater than the degradation response risk threshold, whose quality evaluation index is lower than the quality benchmark value, and whose feature consistency label is a difference segment. It extracts the corresponding point number, location identifier and the partition to which it belongs, marks them as monitoring anomalies with a risk of deterioration, and outputs the points that meet the joint conditions in a structured format to generate farmland quality monitoring and risk warning results.

[0017] Preferably, the comprehensive indicator determination submodule includes: The benchmark value acquisition unit acquires the degradation response value and quality evaluation index of each point in the set of abnormal farmland quality points, retrieves the system's preset degradation response risk threshold, quality benchmark value and normalized scoring range, and establishes a benchmark value reference dataset. Based on the benchmark reference dataset, the judgment value calculation unit calculates the difference between the degradation response value and the degradation response risk threshold for each point, calculates the difference between the quality evaluation index and the quality benchmark value, integrates the two types of difference results and sums them according to the set weights to generate a joint risk judgment value for each point. The sequence construction unit arranges the joint risk assessment values ​​of all points in the order of sampling time to establish a joint risk assessment value sequence.

[0018] Preferably, the abnormal result processing submodule includes: Based on the joint risk judgment value sequence, the condition filtering unit traverses the degradation response value, quality evaluation index and feature consistency label of each point, and filters points that simultaneously meet the following conditions: degradation response value is greater than degradation response risk threshold, quality evaluation index is lower than quality benchmark value, and feature consistency label is a difference segment, and generates a candidate abnormal point list. The information extraction unit calls the candidate abnormal point list, extracts the number, location coordinates and partition identifier of each point, and organizes them into structured data entries; The output unit categorizes and summarizes the structured data entries by partition, generating farmland quality monitoring and risk warning results that include partition identifiers, anomaly point numbers, and location coordinates.

[0019] Preferably, the data acquisition module further includes: The spatial correction unit acquires the location coordinate data of the sampling point, calls the geographic information system to perform spatial correction on the coordinates, eliminates the position offset caused by the positioning error, and generates the corrected location coordinates of the sampling point. The time synchronization unit acquires the sampling time data of the sampling points, calls the standard time service to synchronize and calibrate the time, ensures the consistency of time data of different sampling points, and generates the synchronized sampling time of the sampling points. The data verification unit verifies the validity of the organic matter factor and thickness factor data, removes abnormal data that exceeds the reasonable range, and generates a verified soil factor data set for the sampling points.

[0020] Compared with the prior art, the beneficial effects of the present invention are: The farmland quality monitoring system based on black soil protection provided by this invention exhibits significant advantages in several aspects. The system's data acquisition module can obtain the location and time of farmland sampling points, collect the corresponding organic matter content and soil thickness, correlate the sampling points, calculate the corresponding quality evaluation indicators, and generate a farmland quality evaluation set. This process achieves comprehensive collection of multi-dimensional indicators of farmland quality, no longer limited to a single factor, enabling the collected data to more comprehensively and accurately reflect the actual quality status of farmland. By acquiring the location coordinates and sampling time of the sampling points, as well as the corresponding organic matter content and soil thickness data, and performing standardization processing, the quality evaluation indicators are calculated, providing a rich and reliable data foundation for subsequent analysis.

[0021] The feature extraction module extracts quality evaluation indicators and their corresponding locations from the farmland quality evaluation set, sorts adjacent point pairs by spatial distance, and marks consistent and differing segments within adjacent point pairs, resulting in a feature consistency partitioning label set. This module fully considers the spatial relationships between sampling points. By calculating and sorting the distances between adjacent point pairs and calculating the difference rate of quality indicators, it can accurately identify spatially consistent and differing segments of farmland quality. This helps to gain a deeper understanding of the spatial distribution patterns of farmland quality, providing important spatial basis for subsequent status assessment and risk warning.

[0022] The state assessment module acquires sampling points located in characteristic-consistent zones from the feature-consistent zoning set, extracts pH and water content time series, and compares the changing trends in conjunction with tillage intensity to assess the degree of degradation impact under soil evolution, generating a comprehensive analysis result of degradation impact. This module combines the time series changes of soil factors with tillage intensity for analysis, rather than viewing changes in soil factors in isolation. By calculating the rate of pH decrease and the rate of water content increase and comparing them under the same tillage intensity conditions, it can more accurately assess the degree of degradation impact of soil evolution on arable land quality, providing a scientific basis for the protection and management of black soil.

[0023] The risk warning module identifies outliers in the comprehensive analysis of degradation impacts—sampling points whose degradation response values ​​exceed the average baseline and are located in characteristic difference zones—forming a set of abnormal farmland quality points. This module comprehensively considers multiple factors, including degradation response values ​​and characteristic zones, enabling accurate identification of sampling points with a risk of deterioration. By analyzing continuous sampling records, calculating the intensity change ratio and cultivated area change ratio, and combining this with wind erosion amplitude data and water content fluctuation data, the module can more comprehensively assess the risk status of sampling points, issue timely warnings, and provide strong support for taking effective prevention and control measures.

[0024] The results output module acquires all locations and corresponding location information of the farmland quality anomaly point set, marks locations with a risk of deterioration, and generates farmland quality monitoring and risk warning results. This module accurately marks locations with a risk of deterioration by calculating and filtering joint risk assessment values, and outputs the results in a structured format, making the monitoring and warning results more intuitive and clear, facilitating relevant personnel to understand the farmland quality status and take timely appropriate measures.

[0025] In addition, the data acquisition module includes a spatial correction unit, a time synchronization unit, and a data verification unit, which can correct and synchronize the location coordinates and sampling time of sampling points, and verify the validity of soil factor data, thereby improving the accuracy and reliability of the data. The feature extraction module, state assessment module, risk warning module, and result output module work together to form a complete monitoring system, enabling comprehensive and accurate monitoring and timely early warning of black soil farmland quality, providing effective technical support for the protection and sustainable utilization of black soil. Attached Figure Description

[0026] Figure 1 This is a schematic diagram illustrating the working principle of the farmland quality monitoring system based on black soil protection as described in this invention. Figure 2 A flowchart detailing the system characteristics; Figure 3 This is a flowchart of the feature extraction module; Figure 4 This is a flowchart of the risk warning module; Figure 5 This is a flowchart of the indicator comprehensive judgment submodule. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Please see Figures 1-5 This invention provides a farmland quality monitoring system based on black soil protection. The system includes: a data acquisition module, a feature extraction module, a status assessment module, a risk early warning module, and a result output module. The specific implementation steps are as follows: The data acquisition module obtains the location and time of farmland sampling points, collects the organic matter content and soil thickness at the corresponding locations, associates the sampling points, calculates the corresponding quality evaluation indicators, and generates a farmland quality evaluation set. The feature extraction module extracts the quality evaluation indicators and corresponding locations from the farmland quality evaluation set, sorts adjacent point pairs by spatial distance, and marks consistent and differing sections within adjacent point pairs, obtaining a feature consistency partitioning annotation set. The state assessment module obtains sampling points located in the consistent sections of the feature consistency partitioning annotation set, extracts pH and water content time series, compares the changing trends with tillage intensity, assesses the degree of degradation impact under soil evolution, and generates a comprehensive analysis result of degradation impact. The risk warning module identifies abnormal points in the comprehensive analysis result of degradation impact where the degradation response value is greater than the average response benchmark value and is located in the characteristic difference section, forming a farmland quality anomaly point set. The results output module obtains all points in the farmland quality anomaly point set and their corresponding point information, marks points with deterioration risk, and generates farmland quality monitoring and risk warning results.

[0029] Example 1: The data acquisition module is used to acquire and process relevant data from farmland sampling points to generate a farmland quality evaluation set. It includes a sampling information acquisition submodule, a soil factor standardization submodule, a spatial correction unit, a time synchronization unit, and a data verification unit.

[0030] The operation of the sampling information acquisition submodule is as follows: The location coordinates of the farmland sampling points are acquired using relevant equipment and technologies. These coordinates can be determined using satellite positioning systems to accurately identify the sampling points' locations in geographic space. Simultaneously, the sampling time is acquired and precisely recorded for subsequent temporal analysis. Next, organic matter content data corresponding to the coordinate location is collected. Chemical analysis methods can be used to determine the organic matter content in the soil, yielding specific values. Soil thickness data is also collected, determined through field measurements. Then, the collected organic matter content and soil thickness data are recorded as two soil factors: organic matter factor and soil thickness factor. These factors are integrated with the corresponding sampling point information to obtain a soil factor data set for each sampling point. This data set includes the location, time, and corresponding soil factor information for each sampling point.

[0031] The soil factor standardization submodule operates based on organic matter and soil thickness data from the soil factor dataset of the sampling points. Since different soil factors may have different dimensions and numerical ranges, standardization is required for both organic matter and soil thickness factors to facilitate subsequent analysis and comparison. Common standardization methods, such as Z-score standardization, can be used to convert the data to a uniform scale. After standardization, the results are correlated with the coordinates of the sampling points, ensuring that each standardized soil factor corresponds to a specific geographical location. Then, the average of the standardized organic matter and standardized soil thickness values ​​is calculated and used as a quality evaluation index, comprehensively reflecting the soil quality status of the sampling points. Finally, the quality evaluation index, sampling point coordinates, and other information are integrated to generate a farmland quality evaluation set, which provides the foundational data for subsequent feature extraction and other operations.

[0032] The spatial correction unit ensures the accuracy of the sampling point coordinates. After acquiring the sampling point coordinate data, a Geographic Information System (GIS) is invoked, and its spatial correction function is used to process the coordinates. During actual sampling, positioning errors may occur due to factors such as the accuracy of the positioning equipment and environmental conditions, resulting in positional shifts. GIS correction eliminates these positional shifts caused by positioning errors, making the sampling point coordinates more accurate and generating corrected sampling point coordinates. This provides reliable location information for subsequent location-based analysis.

[0033] The time synchronization unit ensures the consistency of time data across different sampling points. After acquiring the sampling time data, it calls the standard time service to synchronize and calibrate the sampling time with the standard time. Because sampling times at multiple points may deviate due to inconsistent device time settings, synchronization with the standard time guarantees the consistency of time data from different sampling points, generating synchronized sampling times. This is crucial for subsequent time series analysis and other operations, ensuring comparability and accuracy of the data across the time dimension.

[0034] The data validation unit verifies the validity of organic matter and soil thickness data. During data acquisition, some abnormal data may occur, such as data exceeding reasonable ranges due to measurement errors or equipment malfunctions. The data validation unit examines these data, sets reasonable range thresholds, removes abnormal data exceeding these thresholds, retains valid data, and generates a validated set of soil factor data for the sampling points. Validated data is more reliable and improves the accuracy and credibility of subsequent analysis results.

[0035] Example 2: The feature extraction module is used to extract feature information from the farmland quality evaluation set and form a feature consistency partition label set. It includes a quality index extraction submodule, a difference rate calculation submodule, and a feature consistency recognition submodule.

[0036] The workflow of the quality indicator extraction submodule is as follows: First, it acquires the quality evaluation indicators and corresponding location data from the cultivated land quality evaluation set. This data includes the comprehensive quality evaluation results of each sampling point and its coordinate information in geographic space. Then, based on the location information, it identifies the spatial distribution relationship of all sampling points. By analyzing the coordinates of the sampling points, it understands their distribution within the region, such as whether they are densely packed or exhibit a regular distribution. Next, it calls the sampling point location set and calculates the distance between the sampling points in space based on the adjacent distance threshold. The adjacent distance threshold can be set according to the actual geographical characteristics and sampling needs. For example, a smaller threshold may be needed in areas with complex terrain, while a larger threshold can be set in areas with flat terrain. By calculating the spatial distance between every two sampling points and sorting them according to the distance, it generates a sequence of adjacent sampling point distances. This sequence reflects the spatial proximity of the sampling points, providing a basis for subsequent analysis of the characteristic differences between adjacent sampling points.

[0037] The difference rate calculation submodule operates based on the sorted sequence of distances between adjacent sampling points. For the i-th and j-th adjacent sampling points in the sorted sequence, a set rule is used to calculate the difference rate of quality indicators between them. This set rule can be based on the specific values ​​of the quality evaluation indicators, using a specific calculation method to measure the degree of difference between the quality indicators of two adjacent sampling points. For example, the difference rate can be represented by the ratio of the absolute value of the difference between the two indicators to one of the indicators. During the calculation process, this calculation needs to be performed for each pair of adjacent sampling points. Then, all the calculated difference rates of quality indicators are integrated to generate a quality indicator difference rate sequence. This sequence shows the differences in quality indicators between adjacent sampling points and is an important data basis for subsequent feature consistency identification.

[0038] The feature consistency identification submodule operates based on the quality index difference rate sequence. First, it extracts the direction of organic matter change and the direction of thickness change between adjacent sampling points from this sequence. The direction of organic matter change refers to the increasing or decreasing trend of organic matter factors between two adjacent sampling points, while the direction of thickness change refers to the increasing or decreasing trend of soil layer thickness factors. Then, it classifies and labels each pair of sampling points based on whether their trends in these two directions are consistent. Specifically, if the directions of organic matter change and thickness change of two adjacent sampling points are the same, such as both showing an increasing trend or both showing a decreasing trend, then the segment containing this pair of sampling points is marked as a feature-consistent segment; if the trends in the two directions are different, such as organic matter showing an increasing trend while thickness shows a decreasing trend, or vice versa, then the segment containing this pair of sampling points is marked as a feature-difference segment. During the labeling process, feature-consistent and feature-difference segments need to be recorded and grouped separately. Segments belonging to the same feature type are grouped together, and relevant information for each segment is recorded, such as the corresponding sampling point location and the segment's range, ultimately obtaining a feature consistency partition label set.

[0039] The feature extraction module, through the sequential operation of these three sub-modules, starts from the original farmland quality assessment dataset. After steps such as spatial distance sorting, quality index difference rate calculation, and feature consistency identification, it divides the area where the sampling points are located into different feature segments, clarifying which segments show consistent soil quality characteristic trends and which segments exhibit differences. This information is crucial for the subsequent state assessment module, helping it to more effectively select sampling points for analysis and improve the accuracy and effectiveness of the assessment.

[0040] Example 3: The state assessment module is used to evaluate the degree of degradation impact under soil evolution and generate comprehensive analysis results of degradation impact. It includes an environmental sequence acquisition submodule and a state evolution analysis submodule.

[0041] The environmental sequence acquisition submodule works as follows: First, based on the characteristic consistency partitioning annotation set, segments marked as having consistent characteristics are selected. The characteristic consistency partitioning annotation set records the characteristic types of each sampling point segment. By filtering, it can be determined which segments have consistent trends in soil quality characteristic changes. In these characteristic-consistent segments, each sampling point has its corresponding sampling time period and related data. Next, the pH value and relative moisture content data of each sampling point within the sampling time period are detected. pH value data can be measured using tools such as pH test strips and pH meters, while relative moisture content data can be obtained using methods such as drying method and time domain reflectance method. After acquiring these data, they are arranged in chronological order to form pH value time series and moisture content time series. The arrangement of the time series must strictly follow the chronological order of sampling time to ensure the continuity and logic of the data in the time dimension. Finally, these time series are integrated to generate a soil change time series set. This set contains pH value and moisture content data of each sampling point within the characteristic-consistent segments at different time points, providing rich time series data for subsequent analysis of soil state evolution.

[0042] The state evolution analysis submodule performs in-depth analysis based on a soil change time series dataset. First, for each sampling point's time series, it calculates the rate of pH decrease and the rate of water content increase between consecutive time nodes. For example, for a sampling point's pH time series, at two adjacent time nodes t1 and t2, the corresponding pH values ​​are pH1 and pH2, respectively. The rate of pH decrease can be calculated using (pH1-pH2) / (t2-t1). The time interval needs to be converted based on the actual sampling time interval to obtain the rate of decrease per unit time. Similarly, the rate of water content increase can be calculated using a similar method, determined by the ratio of the difference in water content data between adjacent time nodes to the time interval.

[0043] After calculating the rates of pH decrease and water content increase, these two rates need to be compared side-by-side under the same tillage intensity. Tillage intensity is a crucial factor influencing soil condition changes; different tillage intensities may lead to different trends in soil pH and water content changes. Therefore, comparing these two rates under the same tillage intensity allows for a more accurate analysis of soil evolution at that intensity. By jointly analyzing the trends of these two rate indicators in relation to tillage intensity, numerical relationships can be identified. For example, observing how the rates of pH decrease and water content increase change as tillage intensity gradually increases, and whether there is any correlation between them, such as a positive or negative correlation.

[0044] After analyzing the rate of pH decrease, the rate of water content increase, and their relationship with tillage intensity at each sampling point, the impact value sequence for each sampling point was integrated. This impact value sequence comprehensively considers the effects of both the rate of pH decrease and the rate of water content increase on soil degradation. Through a specific calculation method, these two indicators are integrated into a single comprehensive impact value, with each time point corresponding to an impact value, thus forming the impact value sequence. Finally, based on these integrated impact value sequences, a comprehensive analysis of degradation impacts was established. This result includes information such as the degree of impact of the rate of pH decrease on cultivated land, the degree of impact of the rate of water content increase on cultivated land, and a comparison of the intensity degradation response under each soil evolution condition, comprehensively and systematically reflecting the degradation impacts on soil during the evolution process.

[0045] The soil condition assessment module, through the collaborative work of the environmental sequence acquisition submodule and the soil condition evolution analysis submodule, extracts time-series data on pH and water content from sampling points in areas with consistent characteristics. Through steps such as rate calculation, comparative analysis, and impact value integration, it thoroughly assesses the degree of degradation impact under soil evolution. These assessment results provide crucial analytical basis for the subsequent risk warning module, enabling it to more accurately identify sampling points at risk of degradation. The soil condition assessment module plays a vital role in the entire farmland quality monitoring system. It conducts detailed analysis and assessment of soil condition evolution, providing strong support for the system to achieve comprehensive monitoring and risk warning of farmland quality. This helps to promptly detect farmland degradation issues and provides decision-making references for the protection and management of black soil.

[0046] Example 4: The risk warning module is used to identify abnormal points in arable land quality and form a set of abnormal points in arable land quality. It includes a record screening submodule, a parameter change ratio calculation submodule, and a risk identification submodule.

[0047] The workflow of the record screening submodule is as follows: First, based on the comprehensive analysis results of degradation impact, sampling points with degradation response values ​​greater than the average response benchmark value are selected. The degradation response value is an indicator that comprehensively reflects the degree of soil degradation, while the average response benchmark value is a reference value set based on a large amount of historical data or industry standards, used to determine whether the degradation response of the sampling point is abnormal. Simultaneously, sampling points located in characteristic difference zones are selected. Characteristic difference zones refer to areas where the trends of soil quality characteristics change inconsistently; soils in these areas are more prone to degradation and other problems. Then, continuous sampling records of these sampling points are extracted in chronological order. Each sampling point has corresponding sampling data at different time points, and continuous sampling records can reflect the changes of the sampling point over time. During the extraction of continuous sampling records, data on tillage intensity and cultivated area corresponding to each time point are collected. Tillage intensity can be represented by indicators such as tillage frequency and depth, while cultivated area is the actual area of ​​land cultivated. These data are integrated to generate a continuous sampling record set. This set contains information such as tillage intensity and cultivated area of ​​the selected sampling points at different time points, providing a data foundation for subsequent parameter change ratio calculations.

[0048] The parameter change ratio calculation submodule calls the continuous sampling record set and processes each sampling point. For each sampling point, it extracts the intensity value and area at two consecutive time nodes. For example, for time nodes t and t+1, the corresponding intensity values ​​are respectively... and The areas are respectively and Then, calculate the intensity change ratio and the cultivated area change ratio separately. The formula for calculating the intensity change ratio is:

[0049] in, Indicates the ratio of intensity change. This represents the intensity value at the next time point. This represents the intensity value at the previous time point. This formula is used to measure the magnitude of change in tillage intensity between two time points. By taking the absolute value and comparing it to the intensity value at the previous time point, a relative change is obtained, which can more intuitively reflect the degree of change in intensity.

[0050] The formula for calculating the change ratio of cultivated area is:

[0051] in, This indicates the percentage change in cultivated area. This indicates the cultivated area at the next point in time. This represents the cultivated area at the previous time point. The purpose of this formula is to calculate the relative change in cultivated area between two time points. Through a similar calculation method, the ratio of area change can be obtained to analyze the changes in cultivated area.

[0052] After calculating the intensity change ratio and cultivated area change ratio for each sampling point at consecutive time points, these ratios are integrated into an intensity change ratio sequence and a cultivated area change ratio sequence, and then a cultivated land fluctuation change dataset is established. This dataset contains the intensity change ratio and cultivated area change ratio for each sampling point at different time points, reflecting the fluctuation of cultivated land in terms of cultivation intensity and area.

[0053] The risk identification submodule performs risk identification based on the farmland fluctuation change dataset. First, it extracts wind erosion amplitude data and moisture content fluctuation data for the corresponding time period. Wind erosion amplitude can be determined by measuring the degree of wind erosion on the soil over a certain period, while moisture content fluctuation data records the changes in soil moisture content during that time period. Then, it determines whether both the intensity change ratio and the area change ratio exceed a set fluctuation identification threshold. This threshold is a standard value set based on actual conditions and experience, used to determine whether changes in tillage intensity and area constitute abnormal fluctuations. If both the intensity change ratio and the area change ratio exceed this threshold, it indicates that the changes in tillage intensity and area are significant and may affect farmland quality.

[0054] Simultaneously, it is determined whether the amplitude of wind erosion and the fluctuation of water content both exceed the risk assessment threshold. The risk assessment threshold is also set based on relevant standards and actual conditions, and is used to determine whether wind erosion and water content fluctuations have reached a level that could lead to degradation of arable land quality. If both the amplitude of wind erosion and the fluctuation of water content exceed this threshold, it indicates that the arable land is significantly affected by wind erosion and changes in water content, and there is a risk of degradation.

[0055] When both the intensity change ratio and the area change ratio exceed the fluctuation identification threshold, and the wind erosion amplitude and water content fluctuation simultaneously exceed the risk assessment threshold, the time points meeting these conditions are marked as anomalies. Each anomaly corresponds to a specific time point and sampling point, recording the changes in various indicators of cultivated land at that time point. Finally, all marked anomalies are integrated to generate a set of cultivated land quality anomalies. This set contains information such as the spatial location of the anomalies, wind erosion amplitude characteristics, and the ratio of cultivation to area change, accurately identifying points with a risk of cultivated land quality anomalies and providing crucial anomaly data for subsequent output modules.

[0056] The risk early warning module, through the sequential operation of the recording and screening submodule, the parameter change ratio calculation submodule, and the risk identification submodule, filters suspicious sampling points from the comprehensive analysis results of degradation impacts. After steps such as parameter change ratio calculation and risk indicator judgment, it ultimately identifies anomalies in arable land quality. The identification of these anomalies plays a crucial role in the timely detection of arable land quality problems and the implementation of corresponding protective measures. It helps relevant personnel to monitor and manage anomalies in a targeted manner, effectively protecting the arable land quality of black soil. The risk early warning module plays a warning role in the entire arable land quality monitoring system. It can detect potential risks to arable land quality in advance, providing strong support for the system to achieve comprehensive monitoring and protection of arable land quality, and contributing to ensuring the sustainable use of black soil and the healthy development of agriculture.

[0057] Example 5: The results output module is used to generate farmland quality monitoring and risk warning results. It includes an indicator comprehensive judgment submodule and an abnormal results processing submodule.

[0058] The operation flow of the comprehensive indicator judgment submodule is as follows: First, all locations and their corresponding coordinates and identification information from the farmland quality anomaly point set are acquired. The farmland quality anomaly point set includes relevant data for all anomalies identified by the risk warning module, such as the spatial location of the anomalies and wind erosion amplitude characteristics. After acquiring this point information, the joint risk judgment value for the k-th sampling point is calculated using predefined rules. These rules can comprehensively consider factors such as degradation response values ​​and quality evaluation indicators, and obtain a value that reflects the comprehensive risk level of the sampling point through a certain calculation method.

[0059] This submodule includes a baseline value acquisition unit, a judgment value calculation unit, and a sequence construction unit. The baseline value acquisition unit obtains the degradation response values ​​and quality evaluation indicators for each point in the farmland quality anomaly point set, while simultaneously retrieving the system's preset degradation response risk threshold, quality baseline value, and normalized scoring range. The degradation response risk threshold is the standard for determining whether a degradation response reaches a risk level; the quality baseline value is the basic standard for measuring farmland quality; and the normalized scoring range is used to convert data of different dimensions into a unified scoring scale. These data are integrated to establish a baseline value reference dataset, providing a reference basis for subsequent judgment value calculations.

[0060] The judgment value calculation unit operates based on the benchmark reference dataset. For each location, the difference between its degradation response value and the degradation response risk threshold is calculated to obtain the degree of deviation of the degradation response; simultaneously, the difference between the quality evaluation index and the quality benchmark value is calculated to obtain the degree of deviation of the quality evaluation index. Then, these two types of difference results are integrated and weighted according to set weights to generate the joint risk judgment value for each location. For example, assuming that the degradation response value of a certain location is R, the degradation response risk threshold is R0, the quality evaluation index is Q, the quality benchmark value is Q0, the weight of the degradation response is w1, and the weight of the quality evaluation index is w2, then the joint risk judgment value can be expressed as (w1*(R-R0)+w2*(Q-Q0)). This is only an illustrative calculation method; in actual calculations, the weights and calculation methods are determined by the system's preset rules.

[0061] The sequence construction unit arranges the joint risk assessment values ​​of all locations in chronological order according to sampling time, establishing a joint risk assessment value sequence. By arranging them in chronological order, the changes in the joint risk assessment values ​​of each location at different time points can be clearly seen, providing an ordered data sequence for subsequent anomaly point screening.

[0062] The anomaly result processing submodule operates based on the joint risk assessment value sequence to screen out locations with a risk of deterioration and generate the final monitoring and early warning results. This submodule includes a condition filtering unit, an information extraction unit, and a result output unit.

[0063] The conditional filtering unit, based on the joint risk assessment value sequence, traverses the degradation response value, quality evaluation index, and feature consistency label for each location. The feature consistency label identifies whether the segment in which the location is located is a feature-consistent segment or a feature-discrepancy segment. Locations that simultaneously meet the following criteria are filtered: degradation response value greater than the degradation response risk threshold, quality evaluation index lower than the quality benchmark value, and feature consistency label indicating a discrepancy segment. For example, suppose there is a location A with a degradation response value of 12, a degradation response risk threshold of 10, a quality evaluation index of 65, a quality benchmark value of 70, and a feature consistency label indicating a discrepancy segment. Therefore, location A meets the filtering criteria, its degradation response value is greater than the risk threshold, its quality evaluation index is lower than the benchmark value, and it is located in a feature-discrepancy segment, thus meeting the filtering conditions and being selected to generate a candidate list of abnormal locations.

[0064] The information extraction unit retrieves the candidate anomaly point list and extracts the point's ID, location coordinates, and zone identifier for each point. The point ID uniquely identifies each point, the location coordinates specify its geographic spatial location, and the zone identifier indicates the region / zone to which the point belongs. This information is organized into structured data entries, each containing the point ID, location coordinates, and zone identifier, making the data clearer, more standardized, and easier for subsequent processing and output.

[0065] The output unit categorizes and summarizes structured data entries by partition. Based on the partition identifier, data points within the same partition are grouped together, and then farmland quality monitoring and risk warning results are generated, including the partition identifier, anomaly point numbers, and location coordinates. For example, partition 1 contains anomaly point 1 and point 2, partition 2 contains anomaly point 3, and so on. The output results will list the identifier of each partition, as well as the anomaly point numbers and location coordinates within that partition, using a structured format for partitioned output, making the results more intuitive and easier to understand.

[0066] The operation of Example 5 is illustrated with a specific example: Assume that in a certain farmland monitoring area, the set of farmland quality anomaly points generated by the risk warning module contains 10 points, namely point 1 to point 10. The index comprehensive judgment submodule obtains information such as the coordinates, degradation response values, and quality evaluation indicators of these points. The benchmark value acquisition unit retrieves the system's preset degradation response risk threshold of 10, the quality benchmark value of 70, and the normalized score range of 0-100. The judgment value calculation unit calculates for each point. For example, if the degradation response value of point 1 is 15, the quality evaluation indicator is 60, the degradation response weight is 0.6, and the quality evaluation indicator weight is 0.4, then its joint risk judgment value is 0.6*(15-10)+0.4*(60-70)=3-4=-1 (this is only an illustrative calculation; the actual calculation method follows the system rules). The joint risk judgment values ​​of all points are arranged into a sequence in chronological order.

[0067] The anomaly result processing submodule's condition filtering unit iterates through the 10 locations, filtering out those that simultaneously meet the criteria of a degradation response value greater than 10, a quality evaluation index lower than 70, and a feature consistency label indicating a difference segment. Assuming locations 1, 3, and 5 meet these conditions, they are included in the candidate anomaly location list. The information extraction unit extracts the location numbers, coordinates (e.g., location 1's coordinates are 123.45°E, 45.67°N), and partition identifiers (e.g., partition A) of these three locations, organizing them into structured data entries. The result output unit categorizes these entries by partition. If locations 1 and 3 belong to partition A, and location 5 belongs to partition B, the output results will list the locations numbers and coordinates of locations 1 and 3 under partition A, and the location number and coordinates of location 5 under partition B, generating complete farmland quality monitoring and risk warning results. This provides relevant personnel with clear information on anomaly locations, enabling timely and targeted protective measures.

[0068] The results output module, through the collaborative work of the indicator comprehensive judgment submodule and the abnormal results processing submodule, filters out locations with a risk of deterioration from the centralized collection of abnormal farmland quality points, and compiles and outputs monitoring and early warning results. These results can intuitively display the abnormal conditions of farmland quality and the distribution of risk points, providing specific reference for the protection and management of black soil, helping relevant departments and personnel to understand the farmland quality status in a timely manner, formulate corresponding protection strategies, effectively prevent and control farmland quality degradation, and ensure the sustainable use of black soil.

[0069] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0070] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A farmland quality monitoring system based on black soil protection, characterized in that, The system includes: The data acquisition module obtains the location and time of the farmland sampling points, collects the organic matter content and soil layer thickness at the corresponding locations, associates the sampling points and calculates the corresponding quality evaluation indicators, and generates a farmland quality evaluation set. The feature extraction module extracts the quality evaluation indicators and their corresponding locations from the cultivated land quality evaluation set, sorts adjacent point pairs by spatial distance, marks the consistent and different segments in the adjacent point pairs, and obtains the feature consistency partition label set. The state assessment module obtains the sampling points located in the feature-consistent segment of the feature consistency partition annotation set, extracts the pH value and water content time series, compares the changing trends with the tillage intensity, assesses the degree of degradation impact under soil evolution, and generates a comprehensive analysis result of degradation impact. The risk warning module identifies outliers in the comprehensive analysis results of degradation impacts, where the degradation response value is greater than the average response benchmark value and is located in the characteristic difference zone, forming a set of abnormal farmland quality points. The results output module obtains all locations and corresponding location information of the abnormal farmland quality points set, marks locations with a risk of deterioration, and generates farmland quality monitoring and risk warning results.

2. The farmland quality monitoring system based on black soil protection according to claim 1, characterized in that, The farmland quality evaluation set includes quality evaluation indicators, spatial coordinates of sampling points, and standardized soil factors. The feature consistency zoning label set specifically includes feature consistency section labeling, feature difference section labeling, and quality indicator difference rate of adjacent sampling points. The comprehensive analysis results of degradation impact include the degree of impact of pH value decrease rate on farmland, the degree of impact of water content increase rate on farmland, and the comparison of intensity degradation response under each soil evolution condition. The farmland quality anomaly point set includes the spatial location of anomalies, the wind erosion amplitude characteristics of anomalies, and the ratio of cultivated land to area change of anomalies. The farmland quality monitoring and risk warning results include a list of monitored anomaly points and a joint judgment label of three indicators for anomalies.

3. The farmland quality monitoring system based on black soil protection according to claim 1, characterized in that, The data acquisition module includes: The sampling information acquisition submodule acquires the location coordinates and sampling time of the farmland sampling point, collects the organic matter content data and soil layer thickness data corresponding to the coordinate location, and records the collection results as two soil factors: organic matter factor and thickness factor, and acquires the soil factor data set of the sampling point. The soil factor standardization submodule performs standardization processing on the organic matter factor and thickness factor data in the soil factor data set of the sampling points, establishes a correspondence between the standardized results and the location coordinates of the sampling points, calculates the average value of the standardized organic matter value and the standardized thickness value as the quality evaluation index, and generates a set of arable land quality evaluation data.

4. The farmland quality monitoring system based on black soil protection according to claim 3, characterized in that, The feature extraction module includes: The quality index extraction submodule obtains the quality evaluation indexes and corresponding location data in the cultivated land quality evaluation set, identifies the spatial distribution relationship of all sampling points based on the location information, calls the sampling point location set, calculates and sorts the spatial sampling points based on the adjacent distance threshold, and generates a sorted sequence of adjacent sampling point distances. The difference rate calculation submodule calculates the quality index difference rate between two adjacent sampling points i and j based on the adjacent sampling point distance sorting sequence and uses a set rule to calculate the quality index difference rate sequence. The feature consistency recognition submodule extracts the direction of organic matter change and thickness change between adjacent sampling points based on the quality index difference rate sequence. It classifies and labels each pair of sampling points according to whether the change trends in the two directions are consistent. It records and groups the segments with consistent features and the segments with different features to obtain the feature consistency partition label set.

5. The farmland quality monitoring system based on black soil protection according to claim 4, characterized in that, The status assessment module includes: The environmental sequence acquisition submodule filters out segments marked with consistent features from the feature consistency partitioning label set, detects pH value data and relative water content data within the sampling time period of each sampling point, arranges them in chronological order to form pH value time series and water content time series, and generates a soil change time series set. Based on the soil change time series set, the state evolution analysis submodule calculates the rate of pH decrease and the rate of water content increase between consecutive time nodes in the time series of each sampling point. The rate of pH decrease and the rate of water content increase are compared side by side under the same tillage intensity conditions. By jointly analyzing the two types of rate indicators, the numerical relationship between the change trends under the intensity is identified. The influence value series of each sampling point is integrated to establish a comprehensive analysis result of degradation impact.

6. The farmland quality monitoring system based on black soil protection according to claim 5, characterized in that, The risk warning module includes: The recording and filtering submodule filters the sampling points whose degradation response value is greater than the average response benchmark value and the sampling points in the characteristic difference range according to the comprehensive analysis results of the degradation impact. It extracts the continuous sampling records of the sampling points in chronological order, collects the tillage intensity and tillage area data corresponding to each time node, and generates a continuous sampling record set. The parameter change ratio calculation submodule calls the continuous sampling record set to extract the intensity value and area of ​​the sampling point at two consecutive time nodes, calculates the intensity change ratio and cultivated area change ratio respectively, and integrates them into an intensity change ratio sequence and a cultivated area change ratio sequence to establish a cultivated land fluctuation change dataset. Based on the farmland fluctuation change dataset, the risk identification submodule extracts wind erosion amplitude data and water content fluctuation data for the corresponding time period, determines whether the intensity change ratio and area change ratio both exceed the set fluctuation identification threshold, determines whether wind erosion amplitude and water content fluctuation both exceed the risk judgment threshold, marks the time nodes that meet the conditions as anomalies, and generates a set of farmland quality anomaly points.

7. The farmland quality monitoring system based on black soil protection according to claim 6, characterized in that, The result output module includes: The comprehensive indicator judgment submodule obtains all locations and corresponding coordinates and identification information of the farmland quality anomaly point set, calculates the joint risk judgment value of the kth sampling point using set rules, and establishes a joint risk judgment value sequence. The abnormal results processing submodule, based on the joint risk judgment value sequence, filters out points whose degradation response value is greater than the degradation response risk threshold, whose quality evaluation index is lower than the quality benchmark value, and whose feature consistency label is a difference segment. It extracts the corresponding point number, location identifier and the partition to which it belongs, marks them as monitoring anomalies with a risk of deterioration, and outputs the points that meet the joint conditions in a structured format to generate farmland quality monitoring and risk warning results.

8. The farmland quality monitoring system based on black soil protection according to claim 7, characterized in that, The comprehensive indicator judgment submodule includes: The benchmark value acquisition unit acquires the degradation response value and quality evaluation index of each point in the set of abnormal farmland quality points, retrieves the system's preset degradation response risk threshold, quality benchmark value and normalized scoring range, and establishes a benchmark value reference dataset. Based on the benchmark reference dataset, the judgment value calculation unit calculates the difference between the degradation response value and the degradation response risk threshold for each point, calculates the difference between the quality evaluation index and the quality benchmark value, integrates the two types of difference results and sums them according to the set weights to generate a joint risk judgment value for each point. The sequence construction unit arranges the joint risk assessment values ​​of all points in the order of sampling time to establish a joint risk assessment value sequence.

9. The farmland quality monitoring system based on black soil protection according to claim 8, characterized in that, The abnormal result processing submodule includes: Based on the joint risk judgment value sequence, the condition filtering unit traverses the degradation response value, quality evaluation index and feature consistency label of each point, and filters points that simultaneously meet the following conditions: degradation response value is greater than degradation response risk threshold, quality evaluation index is lower than quality benchmark value, and feature consistency label is a difference segment, and generates a candidate abnormal point list. The information extraction unit calls the candidate abnormal point list, extracts the number, location coordinates and partition identifier of each point, and organizes them into structured data entries; The output unit categorizes and summarizes the structured data entries by partition, generating farmland quality monitoring and risk warning results that include partition identifiers, anomaly point numbers, and location coordinates.

10. The farmland quality monitoring system based on black soil protection according to claim 9, characterized in that, The data acquisition module also includes: The spatial correction unit acquires the location coordinate data of the sampling point, calls the geographic information system to perform spatial correction on the coordinates, eliminates the position offset caused by the positioning error, and generates the corrected location coordinates of the sampling point. The time synchronization unit acquires the sampling time data of the sampling points, calls the standard time service to synchronize and calibrate the time, ensures the consistency of time data of different sampling points, and generates the synchronized sampling time of the sampling points. The data verification unit verifies the validity of the organic matter factor and thickness factor data, removes abnormal data that exceeds the reasonable range, and generates a verified soil factor data set for the sampling points.

Images