Soil data analysis method and system

Abstract

The invention relates to the field of soil data analysis, in particular to a soil data analysis method and system. The method comprises the following steps: randomly dividing a plurality of soil areas by adopting a genetic algorithm; acquiring characteristic data of the soil internal environment and the soil external environment of the plurality of soil areas; carrying out optimization processing on the feature data; constructing a multi-dimensional analysis model; constructing a soil intelligent analysis model; and judging the health state of the soil through the soil intelligent analysis model. According to the method, the soil region is divided by using the genetic algorithm, so that subjectivity and uncertainty of a traditional method are overcome; through multi-dimensional analysis of soil internal and external environment data from the aspects of soil properties, crop growth, groundwater dynamics and the like, the data abnormal condition is judged step by step, the accuracy and practicability of data analysis are improved, and a scientific basis is provided for soil health assessment; by reasonably setting the weight coefficient, independent and comprehensive analysis of soil data characteristics in a single model is realized.

Description

Technical Field

[0001] The present invention relates to the field of soil data analysis, and particularly to a soil data analysis method and system. Background Art

[0002] Soil quality is crucial for agricultural production, and accurate analysis of soil data has become the key to improving production efficiency. Although existing soil data analysis methods based on big data provide certain support, there are still problems such as single analysis dimension and strong subjectivity. Most of these methods rely on traditional data processing methods and fail to comprehensively consider internal and external environmental factors of the soil, resulting in the lack of accuracy and comprehensiveness of the analysis results.

[0003] In the prior art, in terms of soil area division, it usually relies on on-site inspections and empirical judgments by experts, which are easily affected by personal subjective factors, resulting in inconsistent and inaccurate division results; in terms of soil data analysis, it is mainly limited to internal environmental data of the soil, such as moisture content, salt status, etc., and fails to fully consider the comprehensive influence of external environmental factors such as crop growth and groundwater dynamics, which weakens the practicality and comprehensiveness of the soil data analysis results to a certain extent; in terms of soil health status assessment, it mostly relies on single or simple index combinations, lacking a comprehensive assessment model that includes weight coefficients with significant discrimination degrees and can comprehensively reflect multi-dimensional characteristics, as well as scientific data analysis and judgment methods, resulting in insufficient accuracy and comprehensiveness of the assessment results.

[0004] At present, there is not much research work on soil data analysis considering multi-environment scenarios, multi-dimensional characteristics, and multi-weight considerations, and there is no specific soil data fusion analysis method that can comprehensively consider internal and external environmental factors of the soil. Summary of the Invention

[0005] In view of the defects in the prior art, the present invention provides a soil data analysis method and system.

[0006] In a first aspect, the present invention provides a method for soil data analysis, comprising the following steps: randomly dividing multiple soil regions by using a genetic algorithm; obtaining characteristic data of the internal and external environments of the soil in the multiple soil regions; performing optimization processing on the characteristic data to obtain multi-dimensional spatio-temporal characteristic data of the soil environment characteristics of the multiple soil regions; constructing a multi-dimensional analysis model for directly or indirectly analyzing soil data from the perspectives of basic soil properties, crop growth, and groundwater dynamics based on the multi-dimensional spatio-temporal characteristic data; constructing a soil intelligent analysis model for comprehensively analyzing soil data according to the multi-dimensional analysis model; and judging the health status of the soil through the soil intelligent analysis model. By randomly dividing multiple soil regions by using a genetic algorithm, the present invention ensures the diversity and representativeness of the soil region division, providing a solid foundation for the acquisition and analysis of characteristic data; by optimizing the characteristic data to obtain multi-dimensional spatio-temporal characteristic data, it realizes the comprehensive capture and in-depth analysis of internal and external environmental factors of the soil, overcomes the deficiency of traditional methods that are limited to internal environment data of the soil, makes soil data analysis more accurate and comprehensive, and enhances the practicality of soil data analysis; by constructing a multi-dimensional analysis model and a soil intelligent analysis model, it realizes the comprehensive analysis of soil data from multiple perspectives such as basic soil properties, crop growth, and groundwater dynamics, providing a strong scientific basis for soil management and protection.

[0007] Optionally, the obtaining of the characteristic data of the internal environment and the external environment of the soil in the multiple soil regions includes: obtaining the characteristic data of the water content, salt concentration, temperature, pH value, and sediment ratio at different depths in the soil of the multiple soil regions; obtaining the characteristic data of the crop growth cycle and yield of different crop types in the multiple soil regions; and obtaining the characteristic data of the groundwater level and flow rate at different monitoring points in the multiple soil regions. By obtaining the characteristic data of the water content, salt concentration, temperature, pH value, and sediment ratio at different depths in the soil, the present invention realizes the comprehensive analysis of the internal structure and properties of the soil; by obtaining the characteristic data of the growth cycle and yield of different crop types outside the soil, it reveals the close relationship between crop growth and the soil environment; by obtaining the characteristic data of the groundwater level and flow rate at different monitoring points outside the soil, it reveals the impact of groundwater dynamics on the soil environment, providing a scientific basis for the comprehensive analysis of soil data and helping to maintain the health and stability of the soil ecosystem.

[0008] Optionally, optimize the feature data to obtain multi-dimensional spatio-temporal data of soil environmental characteristics in multiple soil regions, including: preprocessing the feature data; performing spatio-temporal matching processing on the feature data; performing spatio-temporal interpolation processing on the feature data; performing spatio-temporal fusion processing on the feature data; through the preprocessing, the spatio-temporal matching processing, the spatio-temporal interpolation processing and the spatio-temporal fusion processing, obtain multi-dimensional spatio-temporal data of soil internal and external environmental characteristics in multiple soil regions, and the multi-dimensional spatio-temporal data includes spatio-temporal correlation data of soil internal environmental characteristics, spatio-temporal correlation data of soil external environmental characteristics, and spatio-temporal fusion data of soil internal and external environmental characteristics. By preprocessing the feature data, the present invention effectively improves the accuracy and reliability of the data, providing a high-quality data basis for subsequent analysis; through spatio-temporal matching, interpolation and fusion processing, spatio-temporal correlation and fusion data of soil internal and external environmental characteristics are successfully constructed, realizing a comprehensive capture and in-depth analysis of soil characteristics in time and space, providing a scientific basis for revealing the dynamic laws and trends of soil environmental changes; by obtaining multi-dimensional spatio-temporal data, the dimension and depth of soil data analysis are enriched, which helps to improve the intelligent and refined level of soil management and protection, and provides strong support for the sustainable development of agriculture.

[0009] Optionally, based on the multi-dimensional spatio-temporal feature data, construct a multi-dimensional analysis model for directly or indirectly analyzing soil data from the perspectives of soil basic properties, crop growth and groundwater dynamics, including: based on the multi-dimensional spatio-temporal feature data, construct an internal environment analysis model for directly analyzing soil data; based on the multi-dimensional spatio-temporal feature data, construct an indirect analysis model for indirectly analyzing soil data, and the indirect analysis model includes a crop growth analysis model and a groundwater dynamics analysis model. By constructing the internal environment analysis model, the present invention directly uses multi-dimensional spatio-temporal feature data to deeply analyze soil basic properties, realizes accurate capture and quantitative evaluation of changes in the soil internal environment, and provides a scientific basis for soil improvement and fertility management; by constructing the indirect analysis model, indirectly reflects the soil conditions from the two perspectives of crop growth and groundwater dynamics, reveals the complex relationship between the soil environment and crop growth and groundwater dynamics, and thus is conducive to indirectly analyzing the state of soil data; by constructing a multi-dimensional analysis model, the accuracy and comprehensiveness of soil data analysis are improved, promoting the in-depth development of soil science research.

[0010] Optionally, the internal environment analysis model for directly analyzing soil data satisfies the following expression: Where is the soil internal environment analysis value at time is at time The soil moisture content at the soil depth of a certain area is at the time for the th area at the soil depth of ; the soil salinity concentration at the soil depth of a certain area is at the time for the th area at the soil depth of ; the soil temperature at the soil depth of a certain area is at the time for the th area at the soil depth of ; the soil pH value at the soil depth of a certain area is at the time for the th area at the soil depth of ; the soil sediment ratio at the soil depth of a certain area 、 、 、 are the weight coefficients of the soil moisture content, soil salinity concentration, soil temperature, soil pH value and soil sediment ratio at the soil depth of the th area respectively; is the total number of soil areas, is the initial soil depth, is the total soil depth of the th area; the crop growth analysis model for indirectly analyzing soil data satisfies the following expression: wherein, is the crop growth analysis value of the soil external environment at the time, is the reciprocal of the growth cycle of the th crop in the th area at the time, is the yield of the th crop in the th area at the 、 are the weight coefficients of the growth cycle and yield of the th crop in the th area respectively; is the total number of soil areas, is the total number of crop types in the th area; the groundwater dynamics analysis model for indirectly analyzing soil data satisfies the following expression: Among them, is the groundwater dynamic analysis value of the soil external environment at time is the groundwater level of the th monitoring point in the th area at time th area, is the total number of soil areas, is the total number of monitoring points in the , are respectively th the weight coefficients of the groundwater level and groundwater flow of the monitoring point in the

[0011] Optionally, the direct analysis includes: setting the weight coefficients of the soil moisture content, the soil salt concentration, the soil temperature, the soil pH value, and the soil sediment ratio, and the weight coefficients satisfy the following conditions: According to the weight coefficients, set the fluctuation amplitude threshold of the soil internal environment analysis value, and the fluctuation amplitude threshold is set as: , , , and ; Compare and analyze the absolute value of the fluctuation amplitude of the soil internal environment analysis value with the fluctuation amplitude threshold to obtain a comparative analysis result, and the comparative analysis result is as follows: when , the soil moisture content data is abnormal; when , the soil salt concentration data is abnormal; when , the soil temperature data is abnormal; when When the soil pH data is abnormal; when When the soil sediment ratio data is abnormal; when When the internal environment data of the soil is normal. By reasonably setting the weight coefficients, the present invention accurately reflects the differences of various factors in the internal environment of the soil, providing a scientific basis for setting the fluctuation amplitude threshold; by comparing and analyzing the absolute value of the fluctuation amplitude of the internal environment analysis value of the soil with the fluctuation amplitude threshold, the abnormal conditions of data such as soil temperature, pH, moisture, salt concentration and sediment ratio can be quickly identified, improving the efficiency and accuracy of the internal environment data analysis of the soil.

[0012] Optionally, the indirect analysis includes: setting a maximum threshold and a minimum threshold for the indirect analysis value, where the indirect analysis value includes the crop growth analysis value and the groundwater dynamic analysis value; comparing the indirect analysis value with the maximum threshold and the minimum threshold to obtain a comparison result, where the comparison result includes: when the indirect analysis value is greater than or equal to the maximum threshold, the soil data quality is relatively good; when the indirect analysis value is less than the maximum threshold and greater than the minimum threshold, the soil data quality is average; when the indirect analysis value is less than the minimum threshold, the soil data quality is poor. By setting the maximum threshold and the minimum threshold for the indirect analysis value, the present invention provides a clear standard for evaluating the soil data quality; by comparing the indirect analysis value with the threshold, the analysis result of the soil data quality can be quickly obtained, including three cases of relatively good, average and poor soil data quality; by combining two dimensions of the crop growth analysis value and the groundwater dynamic analysis value, the soil data quality is comprehensively evaluated from multiple angles, more comprehensively reflecting the actual situation of the soil, and improving the accuracy and reliability of the soil data quality evaluation.

[0013] Optionally, the soil intelligent analysis model satisfies the following expression: Where is the fluctuation analysis value of the soil data at time is the internal environment analysis value of the soil at time is the crop growth analysis value of the external environment of the soil at time is the groundwater dynamic analysis value of the external environment of the soil at time , , is the weight coefficient. By integrating the analysis values of the internal soil environment, the crop growth analysis values of the external soil environment, and the groundwater dynamic analysis values, the present invention realizes a comprehensive and integrated evaluation of soil data, which is more accurate and comprehensive than the existing single-index evaluation, and helps to reveal the true fluctuation of soil data; by introducing the weight coefficient, the weights of each analysis value can be flexibly adjusted according to the actual situation, so as to more accurately reflect the fluctuation characteristics of soil data, improve the flexibility and applicability of the model, and make it applicable to soil data analysis under different soil types and different environmental conditions; by calculating the fluctuation analysis value of soil data, it provides a scientific basis for the dynamic monitoring and early warning of soil data.

[0014] Optionally, the determination of the health status of the soil by the soil intelligent analysis model includes: setting the maximum threshold, the minimum threshold, and the maximum stable state value of the fluctuation analysis value of the soil data by the soil intelligent analysis model; comparing the fluctuation analysis value with the maximum threshold, the minimum threshold, and the maximum stable state value to obtain a comparison result, and the comparison result includes: when the fluctuation analysis value is greater than the maximum threshold, there are obvious fluctuations in the internal soil environment data, then it is determined that the soil is in an unhealthy state; when the fluctuation analysis value is less than the maximum threshold and greater than the minimum threshold, if there is an obvious increasing fluctuation in the crop growth data in the external soil environment data, then it is determined that the soil is in a sub-healthy state, and if there is an obvious decreasing fluctuation, then it is determined that the soil is in a healthy state; when the fluctuation analysis value is less than the minimum threshold and greater than the maximum stable state value, if there is a fluctuation in the groundwater dynamic data in the external soil environment that deviates from the maximum stable state value, then it is determined that the soil is in a sub-healthy state, and if there is a fluctuation close to the maximum stable state value, then it is determined that the soil is in a healthy state; when the fluctuation analysis value is less than the maximum stable state value, the data of the internal and external soil environments are both stable, then it is determined that the soil is in an extremely healthy state. By combining historical data and setting the maximum threshold, the minimum threshold, and the maximum stable state value of the fluctuation analysis value, the present invention provides a clear standard for the evaluation of the soil health status, making the evaluation result more objective and accurate, and helping to timely discover soil health problems; by comprehensively considering the fluctuation conditions of the internal soil environment data and the external soil environment data, the soil health status is comprehensively evaluated from multiple angles, improving the comprehensiveness and accuracy of the evaluation; according to the comparison result of the fluctuation analysis value and the threshold, the soil health status is divided into four levels: unhealthy, sub-healthy, healthy, and extremely healthy, providing more refined decision-making support for soil management and protection.

[0015] Second aspect, a soil data analysis system provided by the present invention includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. Among them, the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the system uses the soil data analysis method described above. The system has the following creative effects: First, it realizes the comprehensive collection, efficient processing, and intuitive display of soil data, greatly improving the automation and intelligence level of soil data analysis; second, it can accurately evaluate the soil health status, timely discover potential problems, provide a scientific basis for soil management and protection, and enhance the accuracy and practicality of soil data analysis; third, it has good scalability and compatibility, can flexibly adapt to the data analysis needs under different soil types and different environmental conditions, and at the same time supports seamless docking with other soil management systems, realizing the sharing and collaborative analysis of soil data. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the soil data analysis method according to an embodiment of the present invention; Figure 2 It is a flowchart of the genetic algorithm according to an embodiment of the present invention; Figure 3 It is a dynamic schematic diagram of groundwater according to an embodiment of the present invention; Figure 4 It is a schematic structural diagram of the soil data analysis system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Specific embodiments of the present invention will be described in detail below. It should be noted that the embodiments described here are only for illustrative purposes and are not used to limit the present invention. In the following description, in order to provide a thorough understanding of the present invention, a large number of specific details are set forth. However, it is obvious to those of ordinary skill in the art that the present invention does not have to employ these specific details. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the present invention.

[0018] Throughout the specification, references to "an embodiment", "embodiments", "an example", or "examples" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in at least one embodiment of the present invention. Thus, the phrases "in an embodiment", "in embodiments", "an example", or "examples" that appear throughout the specification do not necessarily all refer to the same embodiment or example. In addition, the particular features, structures, or characteristics may be combined in any suitable combination and / or sub-combination in one or more embodiments or examples. Further, those of ordinary skill in the art should understand that the diagrams provided herein are for illustrative purposes only and are not necessarily drawn to scale.

[0019] Please refer to Figure 1 , an embodiment of the present invention provides a soil data analysis method, and the method includes the following steps: S1. Randomly divide multiple soil regions using a genetic algorithm.

[0020] Please refer to Figure 2 , in an embodiment, first initialize the population, that is, initially divide the soil regions.

[0021] Specifically, first, the number of initially divided soil regions or the number of individuals.

[0022] Further, randomly generate the initial population, where each individual represents a division scheme of the soil regions, and binary coding or other suitable coding methods can be used to represent it. In this embodiment, for each soil sample, a bit vector is used to represent the region to which it belongs, and each bit of the vector corresponds to a region, 1 indicating that the sample belongs to the region, and 0 indicating that it does not belong to the region.

[0023] Further, calculate the fitness value of each individual through a fitness function. The fitness function is designed based on factors such as the similarity of soil properties and spatial continuity to evaluate the quality of the division scheme.

[0024] Further, enter the iterative process. Set a genetic algebra counter and set a maximum genetic algebra stop condition. The iterative process is as follows: According to the fitness values of the individuals, select a part of the excellent individuals as the parents for subsequent crossover and mutation operations; pair the selected parent individuals and apply the crossover operator to generate new offspring individuals; apply the mutation operator to the offspring individuals to introduce new genetic information. It should be noted that the crossover operator can be single-point crossover, multi-point crossover, uniform crossover, etc. During the crossover process, it is necessary to ensure that the offspring individuals still meet the requirements of the belonging regions of the soil samples, that is, each soil sample can only belong to one region. The mutation operation can be randomly flipping the value of a certain gene bit, or a more complex mutation strategy.

[0025] Further, for each individual in the newly generated offspring population, recalculate its fitness value.

[0026] Further, check whether the maximum genetic generation stop condition is reached. If it is reached, stop the iterative process; otherwise, continue the iteration.

[0027] Further, after the iterative process ends, output the optimal solution, that is, the soil area division scheme represented by the individual with the highest fitness value. This scheme should be the most reasonable soil area division result, based on the designed fitness function and the optimization process of the genetic algorithm.

[0028] S2. Obtain the characteristic data of the internal and external environments of the soil in the multiple soil areas.

[0029] In one embodiment, based on the soil area division result of step S1, obtain the characteristic data of the inside and outside of these soil areas. The specific steps are as follows: S21. Obtain the characteristic data of water content, salt concentration, temperature, pH value, and sediment ratio at different depths inside the soil in the multiple areas.

[0030] In this embodiment, within each divided soil area, determine the sampling points at different depths according to research requirements and soil characteristics.

[0031] Further, use professional tools such as soil drills and samplers for soil sampling to ensure the accuracy and representativeness of the sampling.

[0032] Further, mark each sampling point and record information such as sampling depth, time, and location. Properly store the obtained soil samples to avoid water loss and contamination.

[0033] Further, by detecting the soil samples, obtain the characteristic data of water content, salt concentration, temperature, pH value, and sediment ratio. The specific steps are as follows: S211. Obtain the data of water content at different depths in multiple soil areas.

[0034] In this embodiment, weigh the obtained soil samples and record the initial weight.

[0035] Further, put the soil samples into an oven and dry them at high temperature until a constant weight is reached.

[0036] Further, weigh again and calculate the soil water content.

[0037] S212. Obtain the data of salt concentration at different depths in multiple soil areas.

[0038] In this embodiment, insert the electrodes of the salinity meter into the soil sample, and wait for stability before reading the data.

[0039] Further, calculate the soil salinity concentration according to the relationship between the reading and the soil salinity concentration.

[0040] S213. Obtain data on the temperature at different depths in multiple soil regions.

[0041] In this embodiment, insert the soil thermometer into the soil sample, wait for a period of time before reading the data, and directly obtain the temperature value of the soil sample.

[0042] S214. Obtain data on the pH value at different depths in multiple soil regions.

[0043] In this embodiment, insert the soil pH detection instrument into the soil sample, wait for stability before reading the data, and directly obtain the pH value of the soil sample.

[0044] S215. Obtain data on the sediment-sand ratio at different depths in multiple soil regions.

[0045] In this embodiment, disperse the soil sample into a suspension, and use a hydrometer to measure the sedimentation velocity of soil particles in the suspension.

[0046] Further, infer the particle size distribution of soil particles based on the sedimentation velocity, so as to judge the sediment-sand ratio of the soil.

[0047] S22. Obtain characteristic data on the growth of crops outside the soil and the dynamics of groundwater in the multiple regions.

[0048] Among them, S22 further includes the following steps: S221. Obtain characteristic data on the growth of crops outside the soil in the multiple regions.

[0049] In one embodiment, in the selected soil regions, deploy temperature sensors, humidity sensors, and light sensors to monitor the environmental parameters outside the soil in real time. The deployment positions of the involved sensors are reasonable and can accurately reflect the real situation of the crop growth environment.

[0050] Further, observe the crops regularly, record the growth status of the crops, such as plant height, leaf area, flowering situation, fruit development, etc. When the crop growth reaches a specific state, it is recorded as a growth cycle.

[0051] Further, within a specific time, obtain the yield data of these crops, and analyze the situation of their growth cycles according to the yield data.

[0052] Further, organize the above growth cycle data and yield data to form characteristic data on crop growth.

[0053] S222. Obtain the data of the dynamic groundwater outside the soil in the multiple regions.

[0054] Please refer to Figure 3 , in one embodiment, an observation drainage ditch is excavated at the selected soil area location to ensure that the ditch depth reaches the target aquifer. Among them, it is necessary to carry out ditch reinforcement treatment on the observation ditch to ensure the stability of the ditch wall and prevent groundwater pollution.

[0055] Furthermore, different monitoring points are set in the observation ditch, and water level sensors are installed at these monitoring points respectively, and are connected to the data collector to ensure that the water level changes can be recorded in real time or regularly.

[0056] Furthermore, install water flow monitoring equipment to monitor the water flow index.

[0057] S3. Optimize the characteristic data to obtain the multi-dimensional spatio-temporal characteristic data of the soil environment characteristics in multiple soil regions.

[0058] Among them, S3 further includes the following steps: S31. Preprocess the characteristic data.

[0059] In one embodiment, preprocess the characteristic data inside and outside the soil obtained in step S2.

[0060] Specifically, it includes the following steps: S311. Data cleaning.

[0061] In this embodiment, first, delete the duplicate, invalid or abnormal data records.

[0062] Furthermore, correct the obvious error data, such as unreasonable temperature, salt concentration, etc.

[0063] Furthermore, deal with the missing values, which can be carried out by methods such as interpolation, mean substitution or deletion of missing values.

[0064] S312. Data conversion and standardization.

[0065] In this embodiment, convert the data with different units into a unified unit, such as converting the temperature to degrees Celsius and the salt concentration to grams per kilogram.

[0066] Furthermore, perform standardization processing on the data to eliminate the influence of different dimensions on data analysis.

[0067] S313. Data integration.

[0068] In this embodiment, integrate the characteristic data inside and outside the soil to form a complete data set.

[0069] S32. Perform spatio-temporal matching processing on the feature data.

[0070] Among them, S32 further includes the following steps: S321. Perform time series analysis on the feature data.

[0071] In this embodiment, time series analysis is performed on the feature data inside and outside the soil respectively to reveal the changing trend of the data over time. For example, analyze the changing rules of feature data such as soil moisture content, salt concentration, temperature, pH value, sediment ratio, crop growth, and groundwater dynamics in different seasons or different years.

[0072] S322. Perform spatial distribution analysis on the feature data.

[0073] In this embodiment, a geographic information system (GIS) or other spatial analysis techniques are used to draw the spatial distribution maps of the feature data inside and outside the soil. The spatial distribution maps are used to reveal the spatial distribution characteristics and differences of the feature data at different regions and different soil depths.

[0074] S323. Based on the time series analysis and the spatial distribution analysis, perform spatio-temporal matching processing on the feature data.

[0075] In this embodiment, the results of the time series analysis and the spatial distribution analysis are matched to reveal the spatio-temporal correlation and changing trend between the feature data inside the soil and the feature data outside the soil. For example, analyze the relationship between soil moisture content, salt concentration, temperature, pH value, and sediment ratio, or analyze the relationship between crop growth cycle and groundwater dynamics.

[0076] S33. Perform spatio-temporal interpolation processing on the feature data.

[0077] Among them, S33 further includes the following steps: S331. Perform spatial interpolation processing on the feature data.

[0078] In this embodiment, according to the characteristics of the data and research requirements, the inverse distance weighted interpolation method is selected to perform spatial interpolation processing on the feature data.

[0079] S332. Perform time interpolation processing on the feature data.

[0080] In this embodiment, according to the characteristics of the data and research requirements, a method combining linear interpolation and non-linear interpolation is used to perform time interpolation processing on the feature data.

[0081] S333. Based on the spatial interpolation processing and the time interpolation processing, perform spatio-temporal interpolation processing.

[0082] In this embodiment, the spatial interpolation result and the temporal interpolation result are integrated to form a complete spatio-temporal data set.

[0083] Further, according to the characteristics of the spatio-temporal data and the research requirements, a spatio-temporal interpolation model is constructed.

[0084] Further, the constructed spatio-temporal interpolation model is used to interpolate the soil characteristic data at unknown spatio-temporal points.

[0085] S34. Perform spatio-temporal fusion processing on the characteristic data.

[0086] In this embodiment, a spatio-temporal fusion model is used to process the characteristic data. The effect of the spatio-temporal fusion model is to fuse the characteristic data inside the soil and the characteristic data outside the soil. After the spatio-temporal fusion processing, fusion data is obtained in which the characteristic data of soil moisture content, salt concentration, temperature, pH value, sediment ratio and the characteristic data of crop growth cycle and groundwater dynamics are in one-to-one correspondence according to the time series and spatial relationship.

[0087] S35. Through the preprocessing, the spatio-temporal matching processing, the spatio-temporal interpolation processing and the spatio-temporal fusion processing, multi-dimensional spatio-temporal data of the soil internal and external environment characteristics of multiple soil regions are obtained.

[0088] In this embodiment, the processing results of steps S31, S32, S33 and S34 are integrated to obtain multi-dimensional spatio-temporal data of the soil internal and external characteristics of multiple soil regions.

[0089] It should be noted that the multi-dimensional spatio-temporal data includes spatio-temporal correlation data of soil internal environment characteristics, spatio-temporal correlation data of soil external environment characteristics, and spatio-temporal fusion data of soil internal and external characteristics.

[0090] S4. Based on the multi-dimensional spatio-temporal characteristic data, construct a multi-dimensional analysis model for directly or indirectly analyzing soil data from the perspectives of soil basic properties, crop growth and groundwater dynamics.

[0091] Among them, S4 further includes the following steps: S41. Based on the multi-dimensional spatio-temporal characteristic data, construct a soil internal environment analysis model for directly analyzing soil data from the perspective of soil basic properties.

[0092] In one embodiment, based on step S3, a soil internal environment analysis model for directly analyzing soil data from the perspective of soil basic properties is constructed. The soil internal environment analysis model satisfies the following expression: Among them, is the soil internal environment analysis value at time is the soil moisture content at soil depth for the is the soil salinity concentration at soil depth for the is the soil temperature at soil depth for the is the soil pH value at soil depth for the is the soil sediment ratio at soil depth for the 、 、 、 、 are respectively the weight coefficients of the soil moisture content, soil salinity concentration, soil temperature, soil pH value and soil sediment ratio at soil depth for the ; is the total number of soil regions, is the initial soil depth, is the total soil depth of the

[0093] It should be noted that one of the innovations of the present invention is that by judging the fluctuation value, the precise search for the fluctuation conditions of soil temperature, soil pH value, soil moisture, soil salinity concentration and soil sediment ratio is realized, and then the direct analysis of soil data conditions is realized. The direct analysis is only a preliminary analysis of soil data.

[0094] Specifically, first, by reasonably setting the weight coefficients, the following conditions are satisfied: Furthermore, five groups of fluctuation amplitude thresholds of soil internal environment analysis values are set, which are respectively 、 、 、 and ; Furthermore, the absolute value of the fluctuation amplitude of the soil internal environment analysis value is compared with the fluctuation amplitude threshold to obtain a comparison result. The absolute value of the fluctuation amplitude Satisfy the following expression: Wherein, represents the real-time change data of the soil internal environment analysis value, represents the initial fixed data of the soil internal environment analysis value.

[0095] Furthermore, the comparison result is as follows: When the soil moisture content data is abnormal and deviates from the healthy state; When the soil salt concentration data is abnormal and deviates from the healthy state; When the soil temperature data is abnormal and deviates from the healthy state; When the soil pH data is abnormal and deviates from the healthy state; When the soil silt ratio data is abnormal and deviates from the healthy state.

[0096] When the overall soil internal environment data is stable and relatively healthy.

[0097] It should be noted that for the situation where the specific soil internal environment data leads to deviation from the healthy state, the order of checking one by one from large to small is followed. For example, in this embodiment, when the absolute value of the fluctuation range of the soil internal environment analysis value is greater than or equal to , it is determined that the temperature data is abnormal. At this time, the soil temperature is adjusted by using the temperature adjustment device to change the value until is less than . Further, the abnormal judgment and adjustment improvement are carried out on the soil pH data, moisture data, salt concentration data and silt ratio data according to this method.

[0098] S42. Based on the multi-dimensional spatio-temporal feature data, construct a crop growth analysis model for indirectly analyzing soil data from the perspective of the crop growth cycle.

[0099] In one embodiment, based on step S3, construct a crop growth analysis model for indirectly analyzing soil data from the perspective of the crop growth cycle. The crop growth analysis model satisfies the following expression: Wherein, is the analysis value of the crop growth cycle outside the soil at time is at time The reciprocal of the growth cycle of the th crop in a region, is At time the yield of the th crop in a region, , are respectively the weight coefficients of the growth cycle and yield of the th crop in a region, where is the total number of soil regions, is the th region's total number of crop types.

[0100] It should be noted that , and values hardly change significantly in the short term. Through the crop growth analysis model, soil data can be indirectly analyzed. Specifically as follows: First, set the maximum threshold and minimum threshold : Furthermore, compare with and in terms of magnitude; When , it indicates that the crop has a short growth cycle and a large yield. At this time, the soil data is optimal data and is very suitable for crop growth.

[0101] When , it indicates that the crop has a long growth cycle and a large yield. At this time, the soil data is relatively optimal data and is suitable for crop growth.

[0102] When , it indicates that the crop has a short growth cycle and a small yield or a long growth cycle and a small yield. At this time, the soil data is poor data and is not very suitable or very unsuitable for crop growth.

[0103] It should be noted that the length of the crop growth cycle can reflect certain characteristics of the soil. For example, sufficient soil fertility, proper water management, and good soil structure usually enable crops to grow rapidly, thus shortening the growth cycle. On the contrary, poor soil, salinization, acidification, or improper management may lead to slow crop growth and an extended growth cycle. Crop yield is a direct manifestation of the soil's production capacity. High yields usually mean sufficient soil nutrients and suitable soil conditions for crop growth. Low yields, on the other hand, may reflect insufficient soil nutrients, poor soil structure, or other limiting factors.

[0104] S43. Based on the multi-dimensional spatio-temporal feature data, construct a groundwater dynamics analysis model for indirectly analyzing soil data from the perspective of groundwater dynamics.

[0105] In one embodiment, based on step S3, construct a groundwater dynamics analysis model for indirectly analyzing soil data from the perspective of groundwater dynamics. The groundwater dynamics analysis model satisfies the following expression: Where, is the multi-dimensional analysis value of the groundwater dynamics outside the soil at time is the groundwater level of the th monitoring point in the th area at time is the groundwater flow rate of the th monitoring point in the th area at time is the total number of soil areas, is the total number of monitoring points in the , are respectively the weight coefficients of the groundwater level and groundwater flow rate of the th monitoring point in the th area.

[0106] Through the groundwater dynamics analysis model, soil data can be indirectly analyzed. Specifically as follows: First, set the maximum threshold and the minimum threshold : Furthermore, compare and as well as ; When , it indicates that the soil is wet, dilutes salts, accelerates mass transfer and chemical reactions, and affects nutrient distribution and pH. Therefore, the soil data obtained under this condition is relatively good.

[0107] When , it indicates that the soil is prone to saturation, has poor aeration, salts and nutrients tend to accumulate on the surface layer, and slows down mass cycling and biological activities. The soil may exhibit a wet-dry alternating state, and deep or distant groundwater recharge is abundant. The specific impact on the soil needs to consider the interaction between water movement and soil properties. Therefore, the soil data obtained under this condition is relatively poor.

[0108] When When it is in this state, it indicates that the soil is dry, prone to drought and salinization, which is not conducive to microbial activities and plant growth. The organic matter content decreases and the biological activity reduces. Therefore, the soil data obtained under this condition is poor.

[0109] S5. According to the multi-dimensional analysis model, construct a soil intelligent analysis model for comprehensively analyzing soil data.

[0110] In one embodiment, according to the soil internal environment analysis model, the crop growth analysis model, and the groundwater dynamic analysis model, construct a soil intelligent analysis model for comprehensively analyzing soil data. The soil intelligent analysis model satisfies the following expression: Wherein, is the fluctuation analysis value of the soil data at time is the fluctuation analysis value of the soil internal environment at time is the fluctuation analysis value of the external crop growth cycle of the soil at time is the fluctuation analysis value of the external groundwater dynamics of the soil at time 、 、 are weight coefficients.

[0111] S6. According to the soil intelligent analysis model, obtain the comprehensive analysis result of the soil data.

[0112] In one embodiment, a method for setting weight coefficients with great creativity is proposed.

[0113] Specifically, based on step S5, first, obtain a large amount of historical data of 、 and with the same time series correspondence.

[0114] Furthermore, using statistical analysis methods, respectively obtain the minimum value of , the maximum and minimum values of , and the maximum value of .

[0115] Furthermore, by setting a value to change the size of , such that the size of is always greater than ; by setting a value to change the size of , such that the size of is always between and between; by setting a value change of the size, such that the size of is always less than .

[0116] Furthermore, according to the size of, set the maximum threshold and the minimum threshold .

[0117] Furthermore, compare and analyze the actual value with the maximum threshold and the minimum threshold , and the results are as follows: When , there are obvious fluctuations in the soil internal environment data.

[0118] When , there are no obvious fluctuations in the soil internal environment data, and there are obvious fluctuations in the crop growth data in the soil external environment data. When , it means that the crop growth data shows a decreasing fluctuation; when , it means that the crop growth data shows an increasing fluctuation.

[0119] When , there are no obvious fluctuations in both the soil internal environment data and the crop growth data in the soil external environment data, and there are obvious fluctuations in the groundwater dynamic data in the soil external environment data. Among them, represents the maximum value when both the soil internal and external environment data are in a stable state.

[0120] When , both the soil internal and external environment data are in a stable state.

[0121] S7. Based on the above fluctuation analysis results, judge the health status of the soil.

[0122] In one embodiment, based on the fluctuation analysis results in step S6, judge the health status of the soil.

[0123] Specifically, the judgment results are as follows: When there are obvious fluctuations in the soil internal environment data, it means that among the characteristic data such as soil moisture content, salt concentration, temperature, pH value, and sediment ratio, the data with obvious fluctuations deviate seriously from the normal state. Therefore, the soil is in an unhealthy state.

[0124] When there are no obvious fluctuations in the soil internal environment data and there is an increasing fluctuation in the crop growth cycle data in the soil external environment data, the soil is in a sub-healthy state; when there is a decreasing fluctuation, the soil is in a healthy state.

[0125] When there are no obvious fluctuations in the crop growth cycle data in both the soil internal environment data and the soil external environment data, and the groundwater dynamic data in the soil external environment data fluctuates away from the stable state, the soil is in a sub-healthy state; when it fluctuates closer to the stable state, the soil is in a healthy state.

[0126] When both the soil internal environment data and the external environment data are in a stable state, the soil is in an extremely healthy state.

[0127] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of the soil data analysis system in the embodiment of the present invention. The system includes an input device, a processor, an output device, and a memory. The input device, the processor, the output device, and the memory are interconnected. Among them, the memory is used to store computer programs, and the computer programs include program instructions. The processor is configured to call the program instructions, and the system uses the soil data analysis method described above.

[0128] In this embodiment, the input device is the front end of the soil data analysis system, responsible for inputting the original data of the soil sample into the system, including high-precision soil sensors, scanners, and user interfaces.

[0129] The processor is the core of the soil data analysis system, responsible for executing the computer programs stored in the memory, especially those program instructions related to soil data analysis, including high-performance computing units.

[0130] The output device is the back end of the soil data analysis system, responsible for presenting the processed data and analysis results in a user-friendly manner, including a display screen and a printer.

[0131] The memory uses a high-speed solid-state drive, which has the characteristics of fast read and write speed, large capacity, and high reliability. It is mainly used to store the data input by the input device and the result data processed by the processor, and can meet the needs of storing a large amount of data.

[0132] In summary, the present invention breaks through the subjectivity and uncertainty of traditional methods by introducing a genetic algorithm for random division of soil regions, realizing the intelligentization and automation of soil region division; by comprehensively considering the data of the internal and external environments of the soil, it realizes the multi-dimensional comprehensive analysis of soil data, comprehensively reflects the true state of the soil, and improves the accuracy and practicality of the analysis; by directly or indirectly analyzing soil data from three perspectives of the basic properties of the soil, crop growth, and groundwater dynamics, it can accurately judge the abnormal conditions of soil data step by step, providing a scientific basis for the evaluation of soil health status; by reasonably setting the weight coefficients of soil characteristics in different regions, it realizes the individual analysis and comprehensive analysis of multiple soil characteristics in a single comprehensive analysis model of soil data.

[0133] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A soil data analysis method, characterized in that: The method comprises the following steps: Genetic algorithm was used to randomly divide multiple soil regions; Acquire characteristic data of the soil internal environment and external environment of the plurality of soil regions; Optimizing the characteristic data to obtain multi-dimensional spatiotemporal characteristic data of soil environmental characteristics of multiple soil regions; Based on the multidimensional spatiotemporal characteristic data, a multidimensional analysis model is constructed for directly or indirectly analyzing soil data from the perspectives of basic soil properties, crop growth, and groundwater dynamics; Based on the multi-dimensional analysis model, a soil intelligence analysis model for comprehensive analysis of soil data is constructed; The soil health status is judged by the soil intelligent analysis model.

2. A soil data analysis method according to claim 1, characterized in that: The step of acquiring characteristic data of the soil internal environment and the external environment of the plurality of soil regions comprises: Acquire characteristic data of water content, salt concentration, temperature, pH and mud-sand ratio at different depths in the soil of the plurality of soil regions; Acquire characteristic data of crop growth cycle and yield of different crop types in the plurality of soil regions; Characteristic data of groundwater level and flow rate at different monitoring points in the plurality of soil regions are obtained.

3. A soil data analysis method according to claim 1, characterized in that: The optimizing process of the characteristic data to obtain multi-dimensional spatiotemporal data of soil environmental characteristics of multiple soil regions includes: Preprocessing the feature data; Performing spatiotemporal matching processing on the feature data; Performing spatiotemporal interpolation processing on the feature data; Performing spatiotemporal fusion processing on the feature data; Through the preprocessing, the spatiotemporal matching processing, the spatiotemporal interpolation processing and the spatiotemporal fusion processing, multidimensional spatiotemporal data of the internal and external environmental characteristics of soil in multiple soil areas are obtained, and the multidimensional spatiotemporal data include the spatiotemporal correlation data of the internal environmental characteristics of the soil, the spatiotemporal correlation data of the external environmental characteristics of the soil, and the spatiotemporal fusion data of the internal and external environmental characteristics of the soil.

4. A soil data analysis method according to claim 1, characterized in that: The multidimensional analysis model constructed based on the multidimensional spatiotemporal characteristic data for directly or indirectly analyzing soil data from the perspectives of basic soil properties, crop growth and groundwater dynamics includes: Based on the multi-dimensional spatiotemporal characteristic data, an internal environment analysis model for directly analyzing soil data is constructed; Based on the multi-dimensional spatiotemporal characteristic data, an indirect analysis model for indirectly analyzing soil data is constructed, and the indirect analysis model includes a crop growth analysis model and a groundwater dynamic analysis model.

5. A soil data analysis method according to claim 4, characterized in that: The internal environment analysis model for directly analyzing soil data satisfies the following expression: in, for The soil environment analysis value at the moment, for Moment Areas at soil depth The soil moisture content at for Moment Areas at soil depth The soil salt concentration at for Moment Areas at soil depth The soil temperature at for Moment Areas at soil depth The soil pH at for Moment Areas at soil depth The soil-sand ratio at , , , , Respectively Areas at soil depth The weight coefficients of soil moisture content, soil salt concentration, soil temperature, soil pH and soil mud-sand ratio are is the total number of soil areas, is the initial soil depth, For the The total soil depth of the region; the crop growth analysis model for indirect analysis of soil data satisfies the following expression: in, for Crop growth analysis value of the soil environment at all times, for Moment Region The inverse of the growth cycle of a crop. for Moment Region The yield of crops, , Respectively Region The weight coefficient of the growth cycle and yield of each crop, is the total number of soil areas, For the The total number of crop types in a region; the groundwater dynamic analysis model for indirect analysis of soil data satisfies the following expression: in, for Dynamic analysis value of groundwater in the soil environment at all times, for Moment Region The groundwater level at each monitoring point, for Moment Region The groundwater flow at each monitoring point is is the total number of soil areas, For the The total number of monitoring points in each region, , Respectively Region The weight coefficients of groundwater level and groundwater flow at each monitoring point.

6. A soil data analysis method according to claim 5, characterized in that: The direct analysis includes: The weight coefficients of the soil moisture content, the soil salt concentration, the soil temperature, the soil pH and the soil mud-sand ratio are set, and the weight coefficients meet the following conditions: According to the weight coefficient, a fluctuation amplitude threshold of the soil internal environment analysis value is set, and the fluctuation amplitude threshold is set as: , , , and ; The absolute value of the fluctuation range of the soil internal environment analysis value A comparative analysis is performed with the fluctuation amplitude threshold to obtain a comparative analysis result, which is as follows: when When, the soil moisture content data is abnormal; when When , the soil salt concentration data is abnormal; when When, the soil temperature data is abnormal; when When the soil pH data is abnormal; when When the soil mud-sand ratio data is abnormal; when The soil environment data are normal.

7. A soil data analysis method according to claim 5, characterized in that: The indirect analysis includes: Setting a maximum threshold and a minimum threshold of indirect analysis values, wherein the indirect analysis values ​​include the crop growth analysis value and the groundwater dynamic analysis value; The indirect analysis value is compared with the maximum threshold and the minimum threshold to obtain a comparison result, which includes: when the indirect analysis value is greater than or equal to the maximum threshold, the soil data quality is better; when the indirect analysis value is less than the maximum threshold and greater than the minimum threshold, the soil data quality is average; when the indirect analysis value is less than the minimum threshold, the soil data quality is poor.

8. A soil data analysis method according to claim 1, characterized in that: The soil intelligence analysis model satisfies the following expression: in, for Fluctuation analysis value of soil data at each moment, for The soil environment analysis value at the moment, for Crop growth analysis value of the soil environment at all times, for Dynamic analysis value of groundwater in the soil environment at all times, , , is the weight coefficient.

9. A soil data analysis method according to claim 1, characterized in that: The method of judging the health status of the soil by using the soil intelligence analysis model includes: By using the soil intelligent analysis model, the maximum threshold, minimum threshold and maximum stable state value of the fluctuation analysis value of the soil data are set; The fluctuation analysis value is compared with the maximum threshold, the minimum threshold and the maximum stable state value to obtain a comparison result, wherein the comparison result includes: When the fluctuation analysis value is greater than the maximum threshold value, the soil internal environment data has obvious fluctuations, and the soil is judged to be in an unhealthy state; When the fluctuation analysis value is less than the maximum threshold and greater than the minimum threshold, if the crop growth data in the soil external environment data has a significantly increased fluctuation, the soil is judged to be in a sub-healthy state; if the crop growth data in the soil external environment data has a significantly reduced fluctuation, the soil is judged to be in a healthy state; When the fluctuation analysis value is less than the minimum threshold and greater than the maximum stable state value, if the groundwater dynamic data in the extra-soil environment has fluctuations that deviate from the maximum stable state value, the soil is judged to be in a sub-healthy state; if there is a fluctuation close to the maximum stable state value, the soil is judged to be in a healthy state; When the fluctuation analysis value is less than the maximum stable state value, the data of the internal and external environments of the soil are stable, and the soil is judged to be in an extremely healthy state.

10. A soil data analysis system, the system using a soil data analysis method according to any one of claims 1 to 9, characterized in that: The system includes an input device, a processor, an output device and a memory, wherein the input device, the processor, the output device and the memory are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions.

Images