Multi-source soil environment data detection processing method and system based on sensor network

Abstract

This invention relates to the field of soil monitoring technology, specifically to a method and system for detecting and processing multi-source soil environmental data based on sensor networks. After acquiring soil environmental data, the method performs consistency verification through a validation mechanism, identifies and removes suspicious data within a preset time window to form a valid dataset; identifies soil hazard parameters and generates hypothetical soil quality; compares the hypothetical soil quality with the actual soil quality, and identifies soil hazard parameters whose difference exceeds a preset allowable error threshold as anomalous hazard parameters; outputs all normal hazard parameters along with the identified anomalous hazard parameters to avoid interference from anomalous hazard parameters. This invention filters out suspicious data caused by sensor malfunctions or transmission interference before core analysis, ensuring the reliability of soil environmental data, identifying and isolating anomalous hazard parameters, avoiding distortion of global soil quality assessment by local extreme values, and improving the accuracy and reliability of soil quality assessment results.

Description

Technical Field

[0001] This invention belongs to the field of soil monitoring technology, specifically relating to a method and system for detecting and processing multi-source soil environmental data based on sensor networks. Background Technology

[0002] The environmental quality and health of soil are directly related to food security, ecological stability and sustainable social development. In order to achieve precision agriculture, environmental risk early warning and scientific soil management, with the development of Internet of Things and sensor technology, real-time and continuous online monitoring of soil environmental factors can be carried out through sensor networks to obtain soil environmental data, providing a data foundation for soil improvement and remediation.

[0003] Because sensors are deployed in complex underground environments for extended periods, they are susceptible to interference from factors such as physical damage, chemical corrosion, signal drift, and communication link interruptions. This makes it difficult to guarantee the intrinsic quality of the data source, leading to problems such as abnormal fluctuations, missing data, or trend deviations in the collected data. Furthermore, it is difficult to distinguish between drastic parameter changes caused by sudden pollution or extreme drought, and it is also difficult to differentiate between false anomalies caused by sensor malfunctions or signal interference. This can easily lead to missed or false alarms in environmental events, weakening the early warning and decision support capabilities of the monitoring system and interfering with soil remediation.

[0004] In view of this, the present invention provides a method and system for detecting and processing multi-source soil environmental data based on sensor networks. Summary of the Invention

[0005] The purpose of this invention is to provide a method and system for detecting and processing multi-source soil environmental data based on sensor networks, which can promptly correct the impact of abnormal soil parameters on soil quality and obtain accurate soil quality assessment results.

[0006] The specific technical solution adopted by this invention is as follows: A multi-source soil environmental data detection and processing method based on sensor networks includes the following steps: Based on valid datasets obtained from sensor networks, soil hazard parameters are identified. Based on soil hazard parameters, hypothetical soil quality is generated to serve as a comparison benchmark; Calculate the actual soil quality based on the valid dataset; When the difference between the assumed soil quality and the actual soil quality exceeds the preset allowable error threshold, the following steps are taken: the soil hazard parameters used to generate the assumed soil quality are identified as anomalous hazard parameters; based on the soil hazard parameters that are not identified as anomalous hazard parameters, the soil quality is recalculated, and the recalculated soil quality is output as the soil quality assessment result. The effective dataset obtained from the sensor network includes: acquiring soil environmental data output by soil sensor nodes deployed in multiple different areas and the timestamps corresponding to the soil environmental data to form a dataset to be processed; performing consistency verification on the soil environmental data in the dataset to be processed based on a preset verification mechanism, and removing data items identified as suspicious data from the dataset to be processed to form an effective dataset.

[0007] Preferably, the consistency verification of the soil environmental data in the dataset to be processed, based on a preset verification mechanism, includes: For any data in the dataset to be processed, a time window is set with its corresponding timestamp as the center. Within the time window, other soil environmental data of the same type as the data to be verified are retrieved. The data to be verified is compared with the retrieved other soil environmental data. If the difference is not within the preset allowable range, the number of times the data to be verified fails is accumulated. If the accumulated number of times the data to be verified fails is greater than the preset failure threshold, the data to be verified is marked as suspicious data.

[0008] Preferably, the soil environmental data output by the soil sensor nodes deployed in multiple different areas includes: Temperature, humidity, pH value, electrical conductivity, and organic matter content.

[0009] Preferably, generating the hypothetical soil quality used as a comparison benchmark based on soil hazard parameters includes: Based on the allocation model, allocation formulas are matched for soil hazard parameters; based on the attribute information of soil hazard parameters, the corresponding calculation weights are determined; the allocation formulas and calculation weights are input into the soil quality calculation model to generate hypothetical soil quality.

[0010] Preferably, the method for matching soil hazard parameters with the allocation formula based on the allocation model includes: For soil hazard parameters, a matching rule base is searched to obtain preliminary matching content; based on the preliminary matching content, the field information to be compared is determined and sorted; according to the matching order, keyword matching is performed on the sorted field information in turn to determine the adjustment formula.

[0011] Preferably, the method of matching soil hazard parameters with the allocation formula based on the allocation model further includes: If the allocation model fails to determine an allocation formula for any of the soil hazard parameters, the parameter for which no allocation formula was determined is removed from the soil hazard parameters to form a reconstructed parameter list; the backup algorithm is invoked to generate a new hypothetical soil quality based on the reconstructed parameter list, and the new hypothetical soil quality is used to compare with the actual soil quality.

[0012] Preferably, it further includes: Along with the soil quality assessment results, the system outputs soil hazard parameters that are identified as normal hazard parameters and soil hazard parameters that are identified as abnormal hazard parameters.

[0013] A multi-source soil environmental data detection and processing system based on sensor networks includes the following modules: The data acquisition and verification module is used to acquire soil environmental data output by soil sensor nodes and perform consistency verification on the soil environmental data based on a preset verification mechanism to generate a valid dataset. The quality assessment and parameter diagnosis module is used to perform the following actions in response to a valid dataset: identify soil hazard parameters; generate hypothetical soil quality based on the soil hazard parameters and calculate the actual soil quality based on the valid dataset; when the difference between the hypothetical soil quality and the actual soil quality exceeds a preset allowable error threshold, the soil hazard parameters used to generate the hypothetical soil quality are identified as anomalous hazard parameters; and the soil quality is recalculated based on the soil hazard parameters that are not identified as anomalous hazard parameters, so as to output the soil quality assessment results.

[0014] Preferably, the process of performing consistency verification on soil environmental data based on a preset verification mechanism to generate a valid dataset includes: acquiring soil environmental data output by soil sensor nodes deployed in multiple different areas and the timestamps corresponding to the soil environmental data to form a dataset to be processed; performing consistency verification on the soil environmental data in the dataset to be processed based on the preset verification mechanism, and removing data items identified as suspicious data from the dataset to be processed to form a valid dataset.

[0015] Preferably, the step of generating hypothetical soil quality based on soil hazard parameters includes: Based on the allocation model, allocation formulas are matched for soil hazard parameters; based on the attribute information of soil hazard parameters, the corresponding calculation weights are determined; the allocation formulas and calculation weights are input into the soil quality calculation model to generate hypothetical soil quality.

[0016] Beneficial effects This invention performs consistency verification through a preset verification mechanism. Based on the timestamp of the data point, it compares the data with similar data within a preset time window. Suspicious data is identified and removed based on the number of failures, forming a valid dataset. Suspicious data caused by sensor failure or transmission interference is filtered out before core analysis, ensuring the reliability of soil environmental data.

[0017] This invention identifies soil hazard parameters and generates hypothetical soil quality. It then compares the hypothetical soil quality with the actual soil quality. When the difference exceeds a preset allowable error threshold, the corresponding soil hazard parameter is identified as an abnormal hazard parameter. By identifying and isolating abnormal hazard parameters, the soil quality assessment results are calculated based solely on normal hazard parameters, avoiding the impact of local extreme values ​​on the overall soil quality assessment and improving the accuracy and reliability of the soil quality assessment results.

[0018] This invention recalculates soil quality based on parameters identified as normal hazards to output soil quality assessment results. It outputs all normal hazards along with the identified abnormal hazards to avoid interference from abnormal hazards, providing data support for data calibration and analysis optimization. It uses normal hazards to iteratively optimize the soil quality calculation model, enhancing the long-term stability and applicability of the calculation model. Attached Figure Description

[0019] Figure 1 This is a flowchart of the method of the present invention; Figure 2 This is a flowchart of the method for obtaining effective datasets from sensor networks according to the present invention; Figure 3 This is a flowchart of the method for generating hypothetical soil quality according to the present invention; Figure 4 This is a system module diagram of the present invention. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments. It should be understood that the specific embodiments described herein are merely for explaining the invention and are not intended to limit the scope of protection of the invention.

[0021] Example 1 Please refer to Figures 1-3 This embodiment provides a method for detecting and processing multi-source soil environmental data based on sensor networks, including the following steps: The system acquires soil environmental data and corresponding timestamps from soil sensor nodes deployed in multiple different areas; it then aggregates the acquired soil environmental data and timestamps to form a dataset to be processed; it initializes multiple soil sensor nodes deployed in the monitoring area, which are responsible for collecting multi-dimensional soil environmental data; the soil environmental data may include key indicators such as soil temperature, humidity, pH value, electrical conductivity, and organic matter content. After completing the measurement, each soil sensor node packages its output soil environmental data and corresponding timestamp into an independent data unit; data units are continuously collected from all soil sensor nodes and then aggregated to form a structured dataset to be processed; each record in the dataset to be processed is clearly associated with the data value, timestamp, sensor source, and data type, thus providing raw input for consistency verification and analysis.

[0022] Furthermore, based on a preset verification mechanism, consistency verification is performed on each soil environmental data in the dataset to be processed, and statistical outliers are identified and filtered out. Based on the results of the consistency verification, suspicious data is identified; all data identified as suspicious data is removed from the dataset to be processed to form a valid dataset; through a preset verification mechanism, suspicious data that deviates from the normal fluctuation range due to instantaneous sensor failure or sudden environmental changes is filtered out. The verification mechanism includes: for any soil environmental data to be verified in the dataset to be processed, its corresponding timestamp is determined as the time reference point to establish the context of the data point in the time series; a time window is set as the evaluation interval with the time reference point as the center, wherein the time window can be five minutes before and after the time reference point; Within the assessment period, all other soil environmental data of the same type as the data being verified are retrieved as reference data; if the data being verified is pH value, then all pH value data reported by other soil sensor nodes or the same soil sensor node at different times within the time window are retrieved. A reference baseline value is calculated based on all retrieved reference data. Specifically, the mean or median of these reference data can be calculated. Then, the difference between the data being verified and the reference baseline value is calculated, and it is determined whether the difference is within a preset tolerance range. The preset tolerance range is a reasonable fluctuation range set based on historical data statistical analysis or the experience of domain experts. If the difference is within the preset tolerance range, the data being verified is determined to have passed the verification; if the difference exceeds the preset tolerance range, the data point is recorded as having failed the verification. To prevent potentially reasonable drastic fluctuations from being incorrectly rejected, a fault-tolerant processing logic is introduced to continuously track the cumulative number of failures for each soil sensor node. When the cumulative number of failures for a soil sensor node exceeds a preset failure threshold within a continuous evaluation period, the verified data output by that soil sensor node near that time point is marked as suspicious data. The preset failure threshold can be three cumulative failures. All data identified as suspicious will be removed from the dataset to be processed, and the remaining data will constitute the valid dataset.

[0023] Furthermore, the effective dataset is analyzed to identify soil hazard parameters; the identified soil hazard parameters are then substituted into the soil quality calculation process to generate hypothetical soil quality for comparison. After obtaining a valid dataset, the dataset is analyzed based on the built-in soil parameter safety threshold or the user-defined soil parameter safety threshold to identify soil hazard parameters that exceed the preset normal range. Specifically, when a pH value below 5.5 or an electrical conductivity above 2.5 mS / cm is detected, the corresponding parameters and their values ​​are identified as soil hazard parameters. To assess the combined impact of multiple soil hazard parameters on soil quality, hypothetical soil quality is generated through a pre-defined selection and matching procedure. Based on the specific combination of the identified multiple soil hazard parameters, the most suitable adjustment formula is selected from a pre-stored parameter library. The formulation includes calculation steps and logical combinations. Each formulation corresponds to one or more specific soil problem scenarios, including soil acidification, salinization, or organic matter deficiency. To improve the accuracy of the assessment, the corresponding calculation weights are determined based on the attribute information of multiple soil hazard parameters. The attribute information includes not only the parameter values, but also the rate of change, duration, and historical sensitivity of the region. The specific steps of the selection and matching procedure include: for the identified multiple soil hazard parameters, searching for keywords in the matching rule base to obtain the primary matching content corresponding to the multiple soil hazard parameters; among them, the keywords can be low pH value and low organic matter content, and the corresponding primary matching content can point to the risk of soil acidification. Based on the initial matching content, determine the field information that needs to be compared, and sort the field information according to the preset matching order; the preset matching order may specifically include, first matching parameter type, and then matching its exceedance range. According to the matching order, keyword matching is performed on the sorted field information in turn until a unique applicable allocation formula is determined from the parameter library; when determining the calculation weight, a scoring item is assigned to each parameter according to the attribute information of each of the multiple soil hazard parameters, wherein the greater the deviation of the parameter, the higher its scoring item score. Based on the results of the scoring items for each parameter, the calculation weight of each parameter is determined through numerical normalization. The selected blending formula and the determined calculation weight are used as input to execute the soil quality calculation process, thereby generating the hypothetical soil quality used as a comparison benchmark. If the selected matching procedure fails to determine a formulation for at least one of the multiple soil hazard parameters, the exception handling procedure is executed. Specifically, if an unpredictable combination of parameters occurs, the parameter for which no formulation can be determined is removed from the multiple soil hazard parameters, forming a reconstructed parameter list. An alternative algorithm is invoked, specifically through a general weighted average calculation process, based on the reconstructed parameter list, to generate a new hypothetical soil quality. The new hypothetical soil quality will be used for comparison in subsequent steps, thereby ensuring that the assessment process is not interrupted due to matching failure.

[0024] Furthermore, based on the valid dataset, the actual soil quality representing the true quality status of the soil in the same period is calculated; the assumed soil quality is compared with the actual soil quality to obtain the difference; and it is determined whether the difference exceeds the preset allowable error threshold. If the preset allowable error threshold is exceeded, the soil hazard parameters used to generate the hypothetical soil quality will be identified as abnormal hazard parameters. While generating the hypothetical soil quality, the actual soil quality will be calculated through the benchmark calculation process based on the complete and valid dataset, or the actual soil quality data of the same period will be obtained from authoritative third-party data sources such as agricultural monitoring stations. The generated hypothetical soil quality is compared with the actual soil quality to obtain the difference between the two. This difference is then compared with a preset tolerance error threshold, which represents the upper limit of the acceptable deviation between the prediction and the actual situation. If the difference is higher than the preset allowable error threshold, it indicates that the assumed soil quality derived from this set of soil hazard parameters deviates from the actual situation beyond the allowable range. There may be data artifacts or deviations caused by unconventional factors. All soil hazard parameters used to generate this assumed soil quality are identified as abnormal hazard parameters. Among them, data artifacts caused by unconventional factors are distorted data introduced by the measurement or processing process that cannot reflect the true physical condition. Conversely, if the difference is not higher than the preset allowable error threshold, it indicates that the set of soil hazard parameters can effectively reflect the current soil quality status.

[0025] Furthermore, soil hazard parameters that were not identified as abnormal hazard parameters are identified as normal hazard parameters; and soil quality is recalculated based on normal hazard parameters, with the recalculated soil quality being output as the soil quality assessment result. After verification, all soil hazard parameters that are identified as normal hazard parameters are considered to be effective indicators that truly reflect the current risk status of the soil. Based solely on these normal hazard parameters, the determined allocation formula and calculation weights are reused to re-execute the soil quality calculation. The recalculated soil quality eliminates potential interference from abnormal hazard parameters, and the result is output as the final soil quality assessment result. The output soil quality assessment result includes not only the final quality score or grade, but also a detailed parameter report. Along with the output soil quality assessment result, all normal hazard parameters and all abnormal hazard parameters are also output. The output normal and abnormal hazard parameters can be used for subsequent data calibration and analysis optimization. Maintenance personnel can determine whether a soil sensor node needs to be calibrated or replaced based on records that have been identified as abnormal hazard parameters for a long time. Researchers can also discover new soil environmental change patterns that have not yet been fully understood by analyzing the occurrence patterns of abnormal hazard parameters, thereby providing a basis for the verification mechanism and soil quality calculation process in optimization.

[0026] To further enhance practicality and applicability, optimization processes are implemented. For suspicious data that has been removed, interpolation can be performed by setting time gradients and weight values ​​based on valid data at the time points before and after it to ensure the integrity of the data sequence. For identified soil hazard parameters, external meteorological data can be accessed to determine whether they are caused by drastic weather fluctuations such as short-term heavy rain or drought, thereby increasing the accuracy of the judgment. For the determination of soil hazard levels, the relevant safety thresholds can be dynamically adjusted according to the different growth stages of the monitored objects, such as the seedling stage or maturity stage of the crop. It also includes a self-optimization process, which analyzes a large amount of historical data records, adjusts the matching rules used to select the allocation formula and determines the specific values ​​of the calculation weights, thereby continuously improving the accuracy of the assessment and enhancing the responsiveness and early warning accuracy to real-time soil changes.

[0027] Example 2 Please refer to Figure 4 This embodiment provides a multi-source soil environmental data detection and processing system based on sensor networks, including the following modules: The data acquisition and verification module is used to collect soil environmental data from the sensor network and generate a valid dataset for subsequent analysis. It continuously receives soil environmental data sent from multiple soil sensor nodes through a communication interface. Soil environmental data includes, but is not limited to, soil temperature, humidity, pH value, electrical conductivity and organic matter content. Each data point is accompanied by a timestamp of its collection time. All received soil environmental data are collected to form a dataset to be processed. The preset verification mechanism is activated to perform consistency verification on each soil environmental data in the dataset to be processed. For any data to be verified in the dataset to be processed, a time window of 30 minutes before and after its corresponding timestamp is set. Within the time window, other soil environmental data of the same type as the data to be verified are retrieved from other sensor nodes. If the data to be verified is pH value, pH value data from other nodes can be retrieved. The data to be verified is compared with each other soil environmental data retrieved, and the difference is calculated. If the difference is not within the preset allowable range, the cumulative number of times the data to be verified fails is accumulated. After comparing the data with all comparable data within the time window, if the cumulative number of failures of the verified data exceeds the preset failure threshold, the module will mark the verified data as suspicious data. All data identified as suspicious is removed from the dataset to be processed, and the remaining data constitutes the valid dataset; the valid dataset is considered to be a dataset that has undergone preliminary cleaning and has high credibility.

[0028] The quality assessment and parameter diagnosis module, upon receiving a valid dataset, performs soil quality assessment and diagnosis of abnormal parameters; based on preset rules or models, it identifies soil hazard parameters that have a key impact on soil quality assessment from the valid dataset; and executes a dual-path calculation process to generate hypothetical soil quality and calculate actual soil quality. The process of generating hypotheses about soil quality includes: initiating the selection and matching procedure, matching a formula for each soil hazard parameter, and the formula matching process includes: for a certain soil hazard parameter, searching the internal matching rule base to obtain the initial matching content; and based on the initial matching content, determining and sorting the field information that needs to be compared. According to the matching order, keyword matching is performed on the field information to determine its unique corresponding allocation formula; and based on the parameter type, impact level, regional characteristics and other attribute information of each soil hazard parameter, the corresponding calculation weight is determined; the determined allocation formula and calculation weight are input into the soil quality calculation process to generate the hypothetical soil quality. Calculating actual soil quality includes: directly calculating the actual soil quality using a benchmark calculation process based on all or part of the relevant data in the valid dataset; After obtaining the assumed soil quality and the actual soil quality, the difference between the two is calculated and compared with the preset allowable error threshold. If the difference does not exceed the threshold, it indicates that the assumption based on the soil hazard parameters is basically consistent with the actual situation, and the calculated actual soil quality can be directly output as the final soil quality assessment result. If the difference exceeds the threshold, the anomaly diagnosis and recalculation process is triggered, and all soil hazard parameters used to generate the assumed soil quality are initially identified as anomalous hazard parameters; this indicates that at least one or more of the anomalous hazard parameters have significant deviations, leading to the distortion of the assumed model. Based on other soil hazard parameters that were not identified as abnormal hazard parameters, i.e. normal hazard parameters, the soil quality calculation process is called again to calculate and obtain a more reliable corrected soil quality. The recalculated soil quality is then output as the final soil quality assessment result. To provide more comprehensive diagnostic information, a parameter status report is output along with the soil quality assessment results, clearly listing which soil hazard parameters are identified as normal hazard parameters and which are identified as abnormal hazard parameters. It also executes fault tolerance logic. If the selection and matching procedure fails to find a corresponding formula for any of the soil hazard parameters when matching and adjusting formulas, the parameter whose formula cannot be determined is removed from the multiple soil hazard parameters to form a reconstructed parameter list. The backup algorithm is called to generate a new hypothetical soil quality based on the reconstructed parameter list and to continue the subsequent comparison process with the actual soil quality, ensuring robustness in the case of an incomplete rule base.

[0029] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for detecting and processing multi-source soil environmental data based on sensor networks, characterized in that, Includes the following steps: Based on valid datasets obtained from sensor networks, soil hazard parameters are identified. Based on soil hazard parameters, hypothetical soil quality is generated to serve as a comparison benchmark; Calculate the actual soil quality based on the valid dataset; When the difference between the assumed soil quality and the actual soil quality exceeds the preset allowable error threshold, the following action is taken: the soil hazard parameter used to generate the assumed soil quality is identified as an abnormal hazard parameter. Based on the soil hazard parameters that were not identified as abnormal hazard parameters, the soil quality was recalculated, and the recalculated soil quality was output as the soil quality assessment result. The effective dataset obtained from the sensor network includes: acquiring soil environmental data output by soil sensor nodes deployed in multiple different areas and the timestamps corresponding to the soil environmental data to form a dataset to be processed; performing consistency verification on the soil environmental data in the dataset to be processed based on a preset verification mechanism, and removing data items identified as suspicious data from the dataset to be processed to form an effective dataset.

2. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 1, characterized in that, The consistency verification of soil environmental data in the dataset to be processed, based on a preset verification mechanism, includes: For any data in the dataset to be processed, a time window is set with its corresponding timestamp as the center. Within the time window, other soil environmental data of the same type as the data to be verified are retrieved. The data to be verified is compared with the retrieved other soil environmental data. If the difference is not within the preset allowable range, the number of times the data to be verified fails is accumulated. If the accumulated number of times the data to be verified fails is greater than the preset failure threshold, the data to be verified is marked as suspicious data.

3. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 1, characterized in that, The soil environmental data output by soil sensor nodes deployed in multiple different areas includes: Temperature, humidity, pH value, electrical conductivity, and organic matter content.

4. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 1, characterized in that, The hypothetical soil quality used as a comparison benchmark, generated based on soil hazard parameters, includes: Based on the allocation model, allocation formulas are matched for soil hazard parameters; based on the attribute information of soil hazard parameters, the corresponding calculation weights are determined; the allocation formulas and calculation weights are input into the soil quality calculation model to generate hypothetical soil quality.

5. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 4, characterized in that, The formula for matching soil hazard parameters based on the allocation model includes: For soil hazard parameters, a matching rule base is searched to obtain preliminary matching content; based on the preliminary matching content, the field information to be compared is determined and sorted; according to the matching order, keyword matching is performed on the sorted field information in turn to determine the adjustment formula.

6. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 4, characterized in that, The formula for matching soil hazard parameters based on the allocation model also includes: If the allocation model fails to determine an allocation formula for any of the soil hazard parameters, the parameter for which no allocation formula was determined is removed from the soil hazard parameters to form a reconstructed parameter list; the backup algorithm is invoked to generate a new hypothetical soil quality based on the reconstructed parameter list, and the new hypothetical soil quality is used to compare with the actual soil quality.

7. The method for detecting and processing multi-source soil environmental data based on sensor networks according to claim 1, characterized in that, Also includes: Along with the soil quality assessment results, the system outputs soil hazard parameters that are identified as normal hazard parameters and soil hazard parameters that are identified as abnormal hazard parameters.

8. A multi-source soil environmental data detection and processing system based on sensor networks, characterized in that, Includes the following modules: The data acquisition and verification module is used to acquire soil environmental data output by soil sensor nodes and perform consistency verification on the soil environmental data based on a preset verification mechanism to generate a valid dataset. The quality assessment and parameter diagnosis module is used to perform the following in response to a valid dataset: identify soil hazard parameters; generate hypothetical soil quality based on the soil hazard parameters and calculate the actual soil quality based on the valid dataset; when the difference between the hypothetical soil quality and the actual soil quality exceeds a preset allowable error threshold, the soil hazard parameters used to generate the hypothetical soil quality are identified as abnormal hazard parameters. Soil quality is recalculated based on soil hazard parameters that were not identified as anomalous hazard parameters, in order to output soil quality assessment results.

9. The multi-source soil environmental data detection and processing system based on sensor networks according to claim 8, characterized in that, The process of performing consistency verification on soil environmental data based on a preset verification mechanism to generate a valid dataset includes: acquiring soil environmental data output by soil sensor nodes deployed in multiple different areas and the timestamps corresponding to the soil environmental data to form a dataset to be processed; performing consistency verification on the soil environmental data in the dataset to be processed based on the preset verification mechanism, and removing data items identified as suspicious data from the dataset to be processed to form a valid dataset.

10. The multi-source soil environmental data detection and processing system based on sensor networks according to claim 8, characterized in that, The soil quality assumed based on soil hazard parameters includes: Based on the allocation model, allocation formulas are matched for soil hazard parameters; based on the attribute information of soil hazard parameters, the corresponding calculation weights are determined; the allocation formulas and calculation weights are input into the soil quality calculation model to generate hypothetical soil quality.

Images