A system and method for assessing the health of a medicament field soil

Abstract

The application discloses a kind of medicine field soil health assessment system and method, it is related to soil health assessment technical field;System includes: data acquisition module, the physical and chemical parameters of soil are monitored in real time based on sensor network, using wireless transmission technology, the data collected are sent to data processing center, and using remote sensing technology obtains large-area topography and geomorphology information and vegetation cover condition;Data processing module, the original data collected are washed, denoised and standardized, and abnormal values and error data points are removed, and missing data is filled using moving average method or interpolation method;According to the rules set in advance, compare the reference value in historical database with sensor real-time monitoring data.The application covers bulk density, porosity, organic matter, microbial activity and cold and drought resistance index and multiple dimensions, fully analyzes soil function characteristics, uses judgment matrix to calculate index weight, combines PCA to extract biological index principal component, and enhances the reliability of evaluation result.

Description

Technical Field

[0001] This invention relates to the field of soil health assessment technology, and in particular to a system and method for assessing the soil health of medicinal plant fields. Background Technology

[0002] Traditional soil health management in medicinal plant fields relies on manual sampling and laboratory analysis, which suffers from problems such as poor timeliness, low spatial resolution, and fragmented data. Especially in high-altitude areas (such as Tibet), extreme climates lead to complex dynamics in the soil environment, making it difficult for a single indicator to comprehensively reflect soil health. Existing technologies mostly employ isolated monitoring methods, lack multi-dimensional data fusion mechanisms, and do not fully consider the impact of geographical heterogeneity and biological activity on the growth of medicinal plants.

[0003] Furthermore, conventional evaluation methods, based on linear weighted models, cannot effectively handle fuzzy boundaries and nonlinear relationships between indicators, leading to significant biases in the evaluation results. With the development of precision agriculture, there is an urgent need for a support system integrating real-time sensing, intelligent analysis, and dynamic decision-making to achieve rapid diagnosis and scientific management of soil health in medicinal herb fields. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by proposing a soil health assessment system and method for medicinal herb fields.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A soil health assessment system for medicinal herb fields includes:

[0007] The data acquisition module monitors the physical and chemical parameters of the soil in real time based on a sensor network, uses wireless transmission technology to send the collected data to the data processing center, and uses remote sensing technology to obtain large-area topographic and geomorphological information and vegetation cover.

[0008] The data processing module cleans, denoises, and standardizes the collected raw data, removes outliers and erroneous data points, and fills in missing data using moving average or interpolation methods. According to pre-set rules, it compares the real-time monitoring data of the sensors with reference values ​​in the historical database to determine whether there are any sudden changes and issues early warning signals in a timely manner.

[0009] The storage module, based on the established medicinal herb field soil health database, stores monitoring data, experimental analysis results, and geospatial information, and provides query and management functions;

[0010] The evaluation system construction module integrates physical, chemical, biological, and environmental adaptability indicators to form an evaluation system.

[0011] The model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model. First, it determines the membership function and converts the actual values ​​of each index into corresponding membership values. Then, it constructs a fuzzy relation matrix and multiplies it with the weight vector to obtain the final comprehensive score vector. The soil health status level is determined according to the principle of maximum membership.

[0012] The visualization module is used to visually display system information.

[0013] Preferably, the evaluation system construction module selects the following physical parameters as evaluation factors based on the influence of soil structure on root growth, water retention, and aeration:

[0014] Bulk density ρb: reflects the compaction of the soil and affects the difficulty of plant rooting;

[0015] Total porosity Pt: determines the space in which air and water can coexist;

[0016] Capillary water holding capacity (FC): characterizes the effective water holding capacity;

[0017] Non-capillary porosity (NP): measures the residual aeration after gravity drainage;

[0018] A judgment matrix is ​​constructed using a scoring method, and the relative importance weights of each indicator are calculated, as follows:

[0019] Construct a judgment matrix: Compare the importance of each pair of indicators pairwise, assigning values ​​according to a 1-9 scale (e.g., "equally important = 1", "significantly important = 3"), forming an n×n matrix A = [a ij ];

[0020] Normalization: After summing the elements of each column, normalize to obtain the standardized matrix V'=[v' ij ]=A / ΣA j ;

[0021] Feature vector calculation: Take the average value of each row as the weight vector W=[W1,W2,…,W2]. n ] T ,in:

[0022]

[0023] Given the elements aᵢⱼ of the judgment matrix A, the weight of the i-th indicator is:

[0024]

[0025] Among them, the numerator term This is the sum of the scores for this indicator across all comparisons;

[0026] denominator This is the total score for the entire matrix, used for normalization.

[0027] Preferred method: The evaluation system construction module selects chemical indicators and performs standardization processing as follows:

[0028] The target components were determined, including the content of organic matter (OM), total nitrogen (TN), available phosphorus (AP), and available potassium (AK). TN was determined using standard methods such as the Kjeldahl method. The raw data were recorded as X. ij The measured value of the j-th indicator of the i-th sample;

[0029] Based on Z-score normalization:

[0030]

[0031] in, The arithmetic mean of the j-th indicator across all samples; The standard deviation reflects the degree of dispersion. After standardization, the mean is 0 and the standard deviation is 1.

[0032] Preferably, the evaluation system construction module selects the following biological indicators:

[0033] Microbial biomass carbon (MBC): determined by chloroform fumigation extraction;

[0034] Microbial entropy qMB: defined as the ratio of MBC to total organic matter qMB = MBC / OM, reflecting resource utilization efficiency;

[0035] Respiration intensity BR: CO2 release rate under closed culture conditions, representing the degree of metabolic activity;

[0036] PCA is used to extract independent principal components, and the original data matrix is ​​centered; the eigenvalues ​​and eigenvectors of the covariance matrix are calculated; the top k principal components with a cumulative contribution rate ≥ 85% are selected to replace the original variable set;

[0037] Let the selected principal component loading matrix be L kxn The standardized biological data matrix is ​​D nxm Then the score matrix S kxm =L·D T The total biological score for each sample is the score of the first principal component or a weighted sum.

[0038] Preferably, the evaluation system construction module defines environmental adaptability indicators as follows:

[0039] Based on the extreme climate characteristics of Tibet, the following adaptation indicators are defined:

[0040] Cold hardiness index CI: Based on the relationship between the lowest winter temperature and the depth of soil freezing, fitted by a regression model:

[0041]

[0042] in, This is a record low temperature in history. The maximum depth of permafrost. , , Determined by calibration experiments;

[0043] Drought Resistance Index (DI): Utilizing the ratio of soil field capacity (FC) to potential evaporation (PET).

[0044] DI = (FC / PET) × 100%

[0045] A higher DI value indicates that the individual is less susceptible to drought.

[0046] Preferably, the system normalizes the outputs of each module and inputs them into the fuzzy comprehensive evaluation model. The model is then mapped to a preset level range through a membership function, and finally generates a visual diagnostic report, which is output by the visualization module.

[0047] A method for assessing the health of medicinal plant field soil includes the following steps:

[0048] S1: Based on sensor networks, real-time monitoring of soil physicochemical parameters is conducted, and wireless transmission technology is used to send the collected data to the data processing center;

[0049] S2: Clean, denoise, and standardize the collected raw data;

[0050] S3: Evaluation system construction module, which constructs an evaluation system by combining physical indicators, chemical indicators, biological indicators and environmental adaptability indicators;

[0051] S4: Model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model;

[0052] S5: Normalize the outputs of each module and input them into the fuzzy comprehensive evaluation model, and map them to the preset level interval through the membership function;

[0053] S6: Generates a visual diagnostic report, output by the visualization module.

[0054] The beneficial effects of this invention are as follows:

[0055] 1. This invention covers multiple dimensions such as bulk density, porosity, organic matter, microbial activity, and cold and drought resistance index, comprehensively analyzes soil functional characteristics, uses judgment matrix to calculate index weights, and combines PCA to extract principal components of biological indicators, thereby enhancing the reliability of evaluation results.

[0056] 2. This invention maps continuous values ​​to discrete level intervals through membership functions, solving the problem of rigid boundaries in traditional threshold methods. It also customizes cold resistance and drought resistance index models for extreme climate zones such as Tibet, incorporates geographical calibration parameters, and significantly improves the assessment accuracy of special regions. Attached Figure Description

[0057] Figure 1 This is a flowchart of a method for assessing the health of medicinal plant field soil proposed in this invention;

[0058] Figure 2 This is a framework diagram of a soil health assessment system for medicinal plant fields proposed in this invention. Detailed Implementation

[0059] The technical solution of the present invention will be further described in detail below with reference to specific embodiments.

[0060] Example 1:

[0061] A soil health assessment system for medicinal herb fields includes:

[0062] The data acquisition module monitors the physical and chemical parameters of the soil in real time based on a sensor network, uses wireless transmission technology to send the collected data to the data processing center, and uses remote sensing technology to obtain large-area topographic and geomorphological information and vegetation cover.

[0063] The data processing module cleans, denoises, and standardizes the collected raw data, removes outliers and erroneous data points, and fills in missing data using moving average or interpolation methods. According to pre-set rules, it compares the real-time monitoring data of the sensors with reference values ​​in the historical database to determine whether there are any sudden changes and issues early warning signals in a timely manner.

[0064] The storage module, based on the established medicinal herb field soil health database, stores monitoring data, experimental analysis results, and geospatial information, and provides query and management functions;

[0065] The evaluation system construction module integrates physical, chemical, biological, and environmental adaptability indicators to form an evaluation system.

[0066] The model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model. First, it determines the membership function and converts the actual values ​​of each index into corresponding membership values. Then, it constructs a fuzzy relation matrix and multiplies it with the weight vector to obtain the final comprehensive score vector. The soil health status level is determined according to the principle of maximum membership.

[0067] The visualization module is used to visually display system information.

[0068] The evaluation system construction module, when selecting physical indicators, chooses the following physical parameters as evaluation factors based on the influence of soil structure on root growth, water retention, and aeration:

[0069] Bulk density (ρb): reflects the compaction of the soil and affects the difficulty of plant rooting;

[0070] Total porosity (Pt): determines the space in which air and water can coexist;

[0071] Capillary water holding capacity (FC): Characterizes the effective water holding capacity;

[0072] Non-capillary porosity (NP): measures the residual aeration after gravity drainage;

[0073] A judgment matrix is ​​constructed using a scoring method, and the relative importance weights of each indicator are calculated, as follows:

[0074] Construct a judgment matrix: Compare the importance of each pair of indicators pairwise, assigning values ​​according to a 1-9 scale (e.g., "equally important = 1", "significantly important = 3"), forming an n×n matrix A = [a ij ];

[0075] Normalization: After summing the elements of each column, normalize to obtain the standardized matrix V'=[v' ij ]=A / ΣA j ;

[0076] Feature vector calculation: Take the average value of each row as the weight vector W=[W1,W2,…,W2]. n ] T ,in:

[0077]

[0078] Given the elements aᵢⱼ of the judgment matrix A, the weight of the i-th indicator is:

[0079]

[0080] Among them, the numerator term This is the sum of the scores for this indicator across all comparisons;

[0081] denominator This is the total score for the entire matrix, used for normalization.

[0082] The evaluation system construction module selects chemical indicators and performs standardization as follows:

[0083] The target components were determined, including the content of organic matter (OM), total nitrogen (TN), available phosphorus (AP), and available potassium (AK). Standard methods (such as the Kjeldahl method for TN determination) were used, and the raw data were recorded as X. ij (Measured value of the j-th indicator for the i-th sample);

[0084] Based on Z-score normalization:

[0085]

[0086] in, The arithmetic mean of the j-th indicator across all samples; The standard deviation reflects the degree of dispersion. After standardization, the mean is 0 and the standard deviation is 1.

[0087] The evaluation system construction module selects the following specific biological indicators:

[0088] Microbial biomass carbon (MBC): determined by chloroform fumigation extraction;

[0089] Microbial entropy (qMB): defined as the ratio of MBC to total organic matter (qMB = MBC / OM), reflecting resource utilization efficiency;

[0090] Respiration intensity (BR): CO2 release rate under closed culture conditions, representing the degree of metabolic activity;

[0091] PCA is used to extract independent principal components and center the original data matrix; the eigenvalues ​​and eigenvectors of the covariance matrix are calculated; the top k principal components with a cumulative contribution rate of ≥85% are selected to replace the original variable set; for example, if the first two principal components explain 87% of the variance, then only these two comprehensive indicators are used in the subsequent scoring.

[0092] Let the selected principal component loading matrix be L kxn The standardized biological data matrix is ​​D nxm Then the score matrix S kxm =L·D T The total biological score for each sample is the score of the first principal component or a weighted sum.

[0093] The evaluation system construction module defines environmental adaptability indicators as follows:

[0094] Based on the extreme climate characteristics of Tibet, the following adaptation indicators are defined:

[0095] Cold hardiness index (CI): Based on the relationship between the lowest winter temperature and the depth of soil freezing, fitted by a regression model:

[0096]

[0097] in, This is a record low temperature in history. The maximum depth of permafrost. , , Determined by calibration experiments;

[0098] Drought Resistance Index (DI): Utilizing the ratio of soil field capacity (FC) to potential evaporation (PET):

[0099] DI = (FC / PET) × 100%

[0100] A higher DI value indicates that the individual is less susceptible to drought.

[0101] The system normalizes the outputs of each module and inputs them into the fuzzy comprehensive evaluation model. The model is then mapped to the [Excellent / Good / Medium / Poor] grade range through the membership function, and finally generates a visual diagnostic report, which is output by the visualization module.

[0102] Specific examples are as follows:

[0103] Input data:

[0104] Physical layer: ρb = 1.4 g / cm 3 (0.72 after normalization), Pt=45%(0.81), FC=22%(0.65), NP=18%(0.59);

[0105] Chemical layer: OM=3.2% (0.89), TN=0.15% (0.76), AP=12mg / kg (0.68), AK=180mg / kg (0.92);

[0106] Biolayer: MBC = 350 μg / g (0.82), qMB = 2.1 (0.73), BR = 0.5 μmol CO2 / h (0.64);

[0107] Environmental layer: CI=0.65 (corrected for altitude 4500m), DI=0.48;

[0108] Fuzzy reasoning process:

[0109] Weighted score of the physical subsystem: 0.72×0.3+0.81×0.25+0.65×0.2+0.59×0.25=0.713

[0110] After fuzzing at each level, the final comprehensive membership vector is [0.32, 0.45, 0.18, 0.05].

[0111] It is judged as "good" based on the principle of maximum membership, but there is room for improvement to "excellent" (mainly limited by non-capillary porosity).

[0112] Visual output:

[0113] The main interface displays a 3D topographic map overlaid with colored contour lines, which intuitively reflects the differences in hydrothermal conditions on different slope aspects; the drilling-style interaction supports layer-by-layer exploration, and clicking on an abnormal area can expand the monitoring data curves of that location over the years.

[0114] Example 2:

[0115] A method for assessing the health of medicinal plant field soil, based on the system implementation of Example 1, includes the following steps:

[0116] S1: Based on sensor networks, real-time monitoring of soil physicochemical parameters is conducted, and wireless transmission technology is used to send the collected data to the data processing center;

[0117] S2: Clean, denoise, and standardize the collected raw data;

[0118] S3: Evaluation system construction module, which constructs an evaluation system by combining physical indicators, chemical indicators, biological indicators and environmental adaptability indicators;

[0119] S4: Model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model;

[0120] S5: Normalize the outputs of each module and input them into the fuzzy comprehensive evaluation model, and map them to the preset level interval through the membership function;

[0121] S6: Generates a visual diagnostic report, output by the visualization module.

[0122] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A soil health assessment system for medicinal herb fields, characterized in that, include: The data acquisition module monitors the physicochemical parameters of the soil in real time based on a sensor network; The data processing module cleans, denoises, and standardizes the collected raw data, removing outliers and erroneous data points. The evaluation system construction module integrates physical, chemical, biological, and environmental adaptability indicators to form an evaluation system. The model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model. First, it determines the membership function and converts the actual values ​​of each index into corresponding membership values. Then, it constructs a fuzzy relation matrix and multiplies it with the weight vector to obtain the final comprehensive score vector. The soil health status level is determined according to the principle of maximum membership. The visualization module is used to visually display system information.

2. The medicinal herb field soil health assessment system according to claim 1, characterized in that, The data acquisition module uses wireless transmission technology to send the acquired data to the data processing center and uses remote sensing technology to obtain large-area topographic information and vegetation cover.

3. The soil health assessment system for medicinal herb fields according to claim 1, characterized in that, The data processing module uses a moving average method or interpolation method to fill in missing data; according to pre-set rules, it compares the real-time monitoring data of the sensor with the reference values ​​in the historical database to determine whether there are any sudden changes and issues an early warning signal in a timely manner.

4. The medicinal herb field soil health assessment system according to claim 1, characterized in that, The system also includes a storage module, which stores monitoring data, experimental analysis results, and geospatial information based on the established medicinal herb field soil health database, and provides query and management functions.

5. The soil health assessment system for medicinal herb fields according to claim 1, characterized in that, The evaluation system construction module, when selecting physical indicators, chooses the following physical parameters as evaluation factors based on the influence of soil structure on root growth, water retention, and aeration: Bulk density ρb: reflects the compaction of the soil and affects the difficulty of plant rooting; Total porosity Pt: determines the space in which air and water can coexist; Capillary water holding capacity (FC): characterizes the effective water holding capacity; Non-capillary porosity (NP): measures the residual aeration after gravity drainage; A judgment matrix is ​​constructed using a scoring method, and the relative importance weights of each indicator are calculated, as follows: Constructing the judgment matrix: For each pair of indicators, compare their importance pairwise, assign values ​​using a 1-9 scale, and form an n×n matrix A=[a ij ]; Normalization: After summing the elements of each column, normalize to obtain the standardized matrix V'=[v' ij ]=A / ΣA j ; Feature vector calculation: Take the average value of each row as the weight vector W=[W1,W2,…,W2]. n ] T ,in: Given the elements aᵢⱼ of the judgment matrix A, the weight of the i-th indicator is: Among them, the numerator term This is the sum of the scores for this indicator across all comparisons; denominator This is the total score for the entire matrix, used for normalization.

6. The soil health assessment system for medicinal herb fields according to claim 5, characterized in that, The evaluation system construction module selects chemical indicators and performs standardization as follows: The target components were determined, including the content of organic matter (OM), total nitrogen (TN), available phosphorus (AP), and available potassium (AK). TN was determined using standard methods such as the Kjeldahl method. The raw data were recorded as X. ij The measured value of the j-th indicator of the i-th sample; Based on Z-score normalization: in, The arithmetic mean of the j-th indicator across all samples; The standard deviation reflects the degree of dispersion. After standardization, the mean is 0 and the standard deviation is 1.

7. The medicinal herb field soil health assessment system according to claim 6, characterized in that, The evaluation system construction module selects the following specific biological indicators: Microbial biomass carbon (MBC): determined by chloroform fumigation extraction; Microbial entropy qMB: defined as the ratio of MBC to total organic matter qMB = MBC / OM, reflecting resource utilization efficiency; Respiration intensity BR: CO2 release rate under closed culture conditions, representing the degree of metabolic activity; PCA was used to extract independent principal components, and the original data matrix was then centered. Calculate the eigenvalues ​​and eigenvectors of the covariance matrix; select the top k principal components with a cumulative contribution rate ≥ 85% to replace the original variable set; Let the selected principal component loading matrix be L kxn The standardized biological data matrix is ​​D nxm Then the score matrix S kxm =L·D T The total biological score for each sample is the score of the first principal component or a weighted sum.

8. The medicinal herb field soil health assessment system according to claim 7, characterized in that, The evaluation system construction module defines environmental adaptability indicators as follows: Based on the extreme climate characteristics of Tibet, the following adaptation indicators are defined: Cold hardiness index CI: Based on the relationship between the lowest winter temperature and the depth of soil freezing, fitted by a regression model: in, This is a record low temperature in history. The maximum depth of permafrost. , , Determined by calibration experiments; Drought Resistance Index (DI): Utilizing the ratio of soil field capacity (FC) to potential evaporation (PET): DI = (FC / PET) × 100%.

9. A soil health assessment system for medicinal herb fields according to claim 8, characterized in that, The system normalizes the outputs of each module and inputs them into the fuzzy comprehensive evaluation model. The model maps the outputs to a preset level range through a membership function, and finally generates a visual diagnostic report, which is output by the visualization module.

10. A method for assessing the health of medicinal herb field soil, characterized in that, The system implementation based on any one of claims 1-9 includes the following steps: S1: Based on sensor networks, real-time monitoring of soil physicochemical parameters is conducted, and wireless transmission technology is used to send the collected data to the data processing center; S2: Clean, denoise, and standardize the collected raw data; S3: Evaluation system construction module, which constructs an evaluation system by combining physical indicators, chemical indicators, biological indicators and environmental adaptability indicators; S4: Model evaluation module, based on the constructed evaluation index system, uses fuzzy mathematics theory to establish a comprehensive evaluation model; S5: Normalize the outputs of each module and input them into the fuzzy comprehensive evaluation model, and map them to the preset level interval through the membership function; S6: Generates a visual diagnostic report, output by the visualization module.

Images