Soil Fertility Prediction Method Based on Data Mining

Abstract

This application relates to the field of data mining technology and provides a soil fertility prediction method based on data mining. The method includes: obtaining a target soil sample set and extracting a first soil sample; reading predetermined fertility characteristic indicators, detecting the fertility of the first soil sample to obtain first detection data; invoking a porosity plan to perform porosity detection and analysis on the first soil sample to obtain second detection data; using the first detection data and the second detection data as inputs to an integrated fusion fertility prediction model to obtain output information; taking the mean value of the first predicted fertility index in the output information to obtain a target fertility index. This application solves the technical problem in traditional soil fertility prediction methods that multi-source data cannot be fully utilized for comprehensive analysis, resulting in low fertility prediction accuracy and inability to adapt to changes in different soil characteristics, and realizes the technical effect of comprehensively analyzing various fertility characteristics through an integrated fusion model, improving the accuracy and applicability of soil fertility prediction.

Description

Technical Field

[0001] This application relates to the technical field of data mining, and specifically relates to a soil fertility prediction method based on data mining. Background Art

[0002] With the continuous development of agricultural production, the monitoring and prediction of soil fertility have become the key to improving soil utilization efficiency and crop yields. Traditional soil fertility assessment methods usually rely on manual sampling and laboratory analysis, which are not only time-consuming but also have certain limitations, making it difficult to comprehensively and accurately reflect the real-time changes in soil fertility. At the same time, with the increasing complexity of factors such as soil types, environmental factors, and fertilization management, traditional methods are difficult to handle the comprehensive analysis and accurate prediction of multi-dimensional data, resulting in inaccurate and lagging soil fertility assessment, and unable to provide timely and effective decision-making basis for agricultural production. In addition, many current soil fertility prediction methods lack comprehensive consideration of key features such as the spatial distribution and porosity of the soil, ignoring the interaction between various soil components and their impact on fertility. This makes the fertility prediction results unable to accurately reflect the actual fertility status of the soil, affecting the scientificity of fertilization strategies, soil improvement measures, and crop growth regulation in agricultural production. Summary of the Invention

[0003] This application provides a soil fertility prediction method based on data mining, aiming to solve the technical problem that traditional soil fertility prediction methods cannot fully utilize multi-source data for comprehensive analysis, resulting in low fertility prediction accuracy and inability to adapt to changes in different soil characteristics.

[0004] In view of the above problems, this application provides a soil fertility prediction method based on data mining. The method includes: introducing a partitioned and stratified sampling mechanism to obtain a soil sample set of the target soil, and extracting the first soil sample from the soil sample set; reading predetermined fertility characteristic indicators, and performing fertility detection on the first soil sample based on the predetermined fertility characteristic indicators to obtain first detection data; retrieving a porosity plan to perform porosity detection and analysis on the first soil sample to obtain second detection data; using the first detection data and the second detection data as input information for an integrated fusion fertility prediction model, and obtaining output information through the integrated fusion fertility prediction model; taking the mean of the first predicted fertility indices in the output information to obtain a target fertility index, where the target fertility index is used to characterize the fertility of the target soil.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0006] The above soil fertility prediction method based on data mining first obtains a soil sample set of the target soil and extracts the first soil sample from it. This sampling mechanism ensures the representativeness and diversity of the soil samples, helps improve the comprehensiveness of the data and the accuracy of the prediction. Subsequently, according to the predetermined fertility characteristic indicators, the first soil sample is subjected to fertility detection to obtain the first detection data. At the same time, the porosity plan is retrieved, and the first soil sample is subjected to porosity detection and analysis to obtain the second detection data. Then, these two sets of data are combined and input into the integrated fusion fertility prediction model as input information. This model can comprehensively analyze these multi-dimensional data, thereby improving the accuracy and reliability of soil fertility prediction. Finally, through the information output by the model, the mean value of the first predicted fertility index is extracted to obtain the target fertility index, which is used to characterize the fertility of the target soil. Through this method, the fertility level of the soil can be evaluated in real time and accurately, avoiding the errors caused by single data source or incomplete analysis in the traditional method. At the same time, this integrated fusion prediction model can flexibly adapt to the characteristics of different types of soil, improving the adaptability and practicality of soil fertility prediction, and providing a scientific basis for precise fertilization and soil improvement in agricultural production.

[0007] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically gives the specific implementation manners of the present application. Brief Description of the Drawings

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0009] Figure 1 It is a schematic flowchart of the soil fertility prediction method based on data mining in an embodiment.

[0010] Figure 2 It is a schematic flowchart of obtaining the second detection data of the soil fertility prediction method based on data mining in an embodiment. Detailed Description of the Embodiments

[0011] By providing a soil fertility prediction method based on data mining in the embodiments of the present application, the technical problem that in the traditional soil fertility prediction method, multi-source data cannot be fully utilized for comprehensive analysis, resulting in low fertility prediction accuracy and inability to adapt to the changes of different soil characteristics, is solved.

[0012] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0013] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0014] An embodiment is as Figure 1 shown. The present application provides a soil fertility prediction method based on data mining. The method includes:

[0015] Introduce a partitioned and stratified sampling mechanism to obtain a soil sample set of the target soil, and extract a first soil sample from the soil sample set.

[0016] In the embodiments of the present application, first, a partitioned and stratified sampling mechanism is adopted to obtain a soil sample set of the target soil. The core of this partitioned and stratified sampling mechanism lies in dividing the target area into several small blocks or levels according to different characteristics of the soil (such as soil type, terrain, climate, etc.). Each block or level represents a certain specific type or condition of the soil (such as soils with different soil acid-base degrees, soil organic matter contents, or soils with different terrain elevations). This method can ensure that different characteristic areas of the soil are covered during sample collection, thereby obtaining more comprehensive and representative soil samples. After obtaining the soil sample set of the target soil, a soil sample is randomly extracted from the soil sample set of the target soil as the first soil sample. This sample will serve as the basis for preliminary analysis and provide key data for subsequent soil fertility detection. Through this partitioned and stratified sampling, the deviation that may be brought by single sampling can be effectively reduced, ensuring that the samples are more representative, and thus providing a more reliable basis for accurately predicting soil fertility.

[0017] Read the predetermined fertility characteristic indicators, and perform fertility detection on the first soil sample based on the predetermined fertility characteristic indicators to obtain first detection data.

[0018] In one embodiment, a set of predetermined fertility characteristic indicators are first read. These indicators include parameters in aspects such as the chemical composition and physical characteristics of the soil. For example, the fertility characteristic indicators may include the organic matter content in the soil, the concentrations of nitrogen, phosphorus, and potassium, the soil pH value, the water content, etc. These indicators are important bases for judging the soil fertility status. Subsequently, based on these predetermined fertility characteristic indicators, a fertility detection is performed on the first soil sample. The process of fertility detection involves a series of experimental methods, such as chemical analysis, spectral analysis, or other modern detection techniques. By measuring and analyzing various fertility characteristics in the soil sample, a set of specific detection data, namely the first detection data, is obtained. This first detection data contains the specific parameter values corresponding to the fertility characteristic indicators, and these parameter values reflect the soil fertility level, providing quantitative basic data for subsequent analysis and prediction.

[0019] Furthermore, the present application provides that the predetermined fertility characteristic indicators include fertility characteristic indicators in the soil composition dimension and the soil characteristic dimension. Among them, the soil composition dimension includes various organic matter content indicators and various mineral content indicators, and the soil characteristic dimension includes at least the soil pH value, soil water content, and soil temperature.

[0020] Preferably, the predetermined fertility characteristic indicators include two main dimensions, namely the soil composition dimension and the soil characteristic dimension. Among them, the soil composition dimension focuses on the chemical composition of the soil, mainly including various organic matter content indicators and various mineral content indicators in the soil. Various organic matter content indicators reflect the abundance of organic substances (such as plant residues, humus, etc.) in the soil, and various mineral content indicators include the concentrations of important elements (such as nitrogen, phosphorus, potassium, etc.) in the soil. These components directly affect the soil fertility and nutrient supply capacity. The soil characteristic dimension focuses on the physical properties of the soil, mainly including the soil pH value (pH), soil water content, and soil temperature. The soil pH value affects the plant's ability to absorb nutrients, and overly acidic or alkaline soil may limit plant growth. Soil water content is an important factor in soil fertility, and the water content in the soil affects the plant growth environment. Excessive or insufficient water will affect the fertility performance. Soil temperature affects the activity of soil microorganisms and the growth of plant roots, thus indirectly affecting soil fertility. Through the fertility characteristic indicators of these two dimensions, the soil fertility status can be comprehensively evaluated, providing a more accurate basis for soil fertility prediction and agricultural management.

[0021] Retrieve the porosity plan to perform porosity detection and analysis on the first soil sample to obtain the second detection data.

[0022] In one embodiment, first, a porosity plan is retrieved, and porosity detection and analysis are performed on the first soil sample. Porosity is an index of the proportion of voids (such as air pores and water pores) in the soil, which reflects the soil's ventilation, water permeability, and water retention capacity. By analyzing the porosity of the soil sample, the performance of the soil in terms of water and air flow can be understood, which is crucial for judging soil fertility. When performing porosity detection and analysis, direct volume detection is carried out through the volume detection plan in the porosity plan, and then liquid penetration detection is carried out through the liquid penetration detection plan in the porosity plan. Based on the results of these two detections, important indicators such as the soil's ventilation coefficient and water permeability coefficient can be calculated, and these indicators will be used as the second detection data for subsequent soil fertility assessment. Porosity detection provides more detailed physical property data for soil fertility prediction, helping to comprehensively evaluate the state of the soil.

[0023] Further, as Figure 2 shown, the present application provides retrieving a porosity plan to perform porosity detection and analysis on the first soil sample to obtain second detection data, including:

[0024] Extracting the volume detection plan in the porosity plan; performing direct volume detection on the first soil sample according to the volume detection plan to obtain a first detection result; extracting the liquid penetration detection plan in the porosity plan; performing liquid penetration detection on the first soil sample according to the liquid penetration detection plan to obtain a second detection result; and forming the second detection data based on the first ventilation coefficient obtained by analyzing the first detection result, the first water permeability coefficient, and the first water retention coefficient obtained by analyzing the second detection result.

[0025] Preferably, before porosity detection, first extract the volume detection plan related to soil volume detection from the porosity plan. This volume detection plan usually contains technical details such as how to measure the volume of soil, how to calculate the ratio of pore volume to solid volume, etc. This plan provides operation guidance for subsequent direct volume detection; subsequently, according to the extracted volume detection plan, conduct direct volume detection. This step obtains the total volume of the soil by measuring the mass and volume of the first soil sample. Usually, the first soil sample is placed in a container with a known volume, its mass is measured, and then the solid volume of the soil is measured through drying treatment. By summarizing these data, the first test result can be obtained; in addition, extract the plan content related to liquid penetration detection from the porosity plan. The purpose of liquid penetration detection is to evaluate the water permeability of the soil. This process usually involves the penetration rate of a liquid (such as water or a specific solution) through the first soil sample. The plan will include the liquid type, the time period of the penetration test, the penetration path, etc. According to the liquid penetration detection plan, conduct permeability detection on the dried first soil sample. This process usually involves injecting a certain amount of liquid on the soil surface and observing the penetration process of the liquid in the soil. During the detection process, it is necessary to record the mass of the dry soil sample, the volume of water that penetrates through the soil sample, the cross-sectional area of the soil sample, the penetration time, the mass of the soil sample after penetration, etc., to obtain the data on the penetration ability of the liquid through the soil, thereby obtaining the second test result; after obtaining the results of volume detection and liquid penetration detection, calculate the difference between the total volume of the soil in the first test result and the solid volume of the dry soil to obtain the pore volume, and then calculate the ratio of the pore volume to the total volume of the soil to obtain the first aeration coefficient of the soil, that is, the proportion of the space available for gas flow in the soil pores. Calculate the ratio of the volume of water that penetrates through the soil sample in the second test result to the product of the cross-sectional area of the soil sample and the penetration time to obtain the first permeability coefficient, that is, the water flow ability of the soil. At the same time, calculate the difference between the mass of the soil sample after penetration and the mass of the dry soil sample, and then calculate the ratio of the calculation result to the mass of the dry soil sample to obtain the first water retention coefficient of the soil sample, that is, the ability of the soil to retain water; finally, summarize the first aeration coefficient, the first permeability coefficient, and the first water retention coefficient obtained through analysis to form the second test data. These data reflect the performance of the soil in terms of air and water flow and are important physical characteristics for evaluating soil fertility, providing key inputs for subsequent fertility prediction models.

[0026] Use the first test data and the second test data as input information for the integrated fusion fertility prediction model, and obtain output information through the integrated fusion fertility prediction model.

[0027] In one embodiment, first, the first detection data and the second detection data are used as input information and fed into a pre-constructed integrated fusion fertility prediction model. Specifically, the first detection data includes the fertility characteristics of the soil (such as organic matter content, mineral content, pH value, etc.), while the second detection data reflects the physical properties of the soil (such as porosity, air permeability, water permeability, etc.). These two types of data analyze the fertility status of the soil from different perspectives, so they need to be integrated. After inputting these two types of data into the integrated fusion fertility prediction model, the model will conduct in-depth analysis and integration of each data item according to the internal first-level prediction layer and second-level prediction layer, generating a more accurate fertility prediction result. Through the integrated fusion model, multiple fertility characteristics and soil physical properties can be comprehensively considered, thus obtaining a more comprehensive and accurate soil fertility prediction result. Finally, the model outputs the soil fertility prediction result as output information, which usually manifests as a predicted fertility index reflecting the fertility level of the target soil. This output information can provide a scientific basis for agricultural decision-making, helping to select suitable fertilization strategies, soil improvement methods, etc.

[0028] Furthermore, before providing the first detection data and the second detection data as input information to the integrated fusion fertility prediction model and obtaining output information through the integrated fusion fertility prediction model, the present application further includes:

[0029] Obtain the soil fertility detection log and extract the first fertility detection record from the soil fertility detection log; form a first training data set based on the first fertility characteristic information and the first fertility index in the first fertility detection record, and perform supervised learning on the first training data set to obtain a first prediction model; form a second training data set based on the first porosity characteristic information and the first fertility index in the first fertility detection record, and perform supervised learning on the second training data set to obtain a second prediction model; the first prediction model and the second prediction model constitute the first-level prediction layer; obtain a second-level prediction layer, which is used for normalizing and weighting the prediction results of the first prediction model and the second prediction model; the first-level prediction layer and the second-level prediction layer are built into the integrated fusion fertility prediction model.

[0030] Preferably, first obtain all the detection records from the stored soil fertility detection log, which records the detailed data and results of each soil fertility detection; subsequently, extract the first fertility detection record from the soil fertility detection log, which contains the fertility characteristic information of a specific soil sample (such as the organic matter content, mineral composition, pH value, etc. of the soil) and the corresponding fertility index. According to the extracted first fertility detection record, combine the first fertility characteristic information with the first fertility index group to construct the first training data group, which will be used to train a supervised learning model aiming to predict the soil fertility level. Specifically, taking the fully connected neural network as an example, other machine learning models can also be used. Build an initial first prediction model through the fully connected neural network, including an input layer, a hidden layer, an output layer, etc., and then use a random initialization method (such as Xavier initialization or He initialization) to assign initial values to the weights of each neuron to ensure that the initial first prediction model does not generate too large or too small gradients at the beginning of training; then, take the first fertility characteristic information in the first training data group as the input feature and input it layer by layer into the initial first prediction model. After the layer-by-layer calculation of the input layer and the hidden layer, the predicted fertility index is output. The calculation of each layer includes the linear weighting of the input and the weights, adding a bias, and performing a non-linear transformation through an activation function. Then, use the mean square error (MSE) as the loss function to calculate the error between the predicted fertility index and the first fertility index. Through the backpropagation algorithm, the error is transmitted backward from the output layer to the input layer, calculate the gradients layer by layer, and determine the contribution of each weight and bias to the loss. Use the Adam optimizer (or other optimizers such as SGD) to update the weights in the initial first prediction model. The Adam optimizer combines momentum and an adaptive learning rate, which can effectively accelerate convergence and avoid overfitting. Through the above steps, perform multiple iterations until the loss function of the first training data group converges or reaches the set maximum number of iterations to generate the first prediction model. In each round of training, the weights and biases will be adjusted to minimize the loss function, thereby improving the prediction accuracy; in the first fertility detection record, in addition to the fertility characteristic information, it also contains the first porosity characteristic information (such as the physical properties of soil aeration and water permeability), and these characteristics also have an important impact on soil fertility. Therefore, based on the porosity characteristic information and the fertility index, construct the second training data group. Similarly, the second training data group is also trained in a supervised learning manner, with the input feature being the first porosity characteristic information and the label being the first fertility index, and the second prediction model obtained through the same steps as above;Then, the first prediction model (based on fertility characteristics) and the second prediction model (based on porosity characteristics) obtained through training are combined into a primary prediction layer. The role of this primary prediction layer is to predict soil fertility based on two different input characteristics respectively, obtaining two sets of independent prediction results. In the primary prediction layer, each model processes the input data separately to generate prediction results, but does not directly perform the final output. Instead, it is handed over to the secondary prediction layer for further processing. In the secondary prediction layer, normalization weighting is performed on the two sets of prediction results of the primary prediction layer. Normalization weighting means performing standardization processing (such as the maximum-minimum method) on the prediction results of the first prediction model and the second prediction model, adjusting them to the same scale or range for comparison. Then, different weights are determined for each model according to the accuracy rate of each model on the data not used for training, and the determined weights are built into the secondary prediction layer. The secondary prediction layer weights the prediction results of the two models through these two weights, thereby obtaining a fused prediction result, that is, the first predicted fertility index. This first predicted fertility index is more comprehensive and accurate, and can better reflect the true fertility status of the soil; finally, the primary prediction layer and the secondary prediction layer are built into an integrated fusion fertility prediction model in an integrated manner. This integrated model combines the prediction results of fertility characteristics and porosity characteristics, and through weighted fusion, obtains a more accurate and stable soil fertility prediction, providing a scientific basis for soil management and fertilizer application in agricultural production.;

[0031] Take the mean of the first predicted fertility index in the output information to obtain the target fertility index, where the target fertility index is used to characterize the fertility situation of the target soil.

[0032] In one embodiment, after obtaining the output information of each soil sample in the soil sample set, the mean of the first predicted fertility index in these output information is calculated to obtain the target fertility index of the target soil. This target fertility index is used to describe the overall fertility status of the target soil, enabling users to understand the overall fertility status of the soil, and thus formulate reasonable fertilization plans and improvement measures.

[0033] Furthermore, the present application provides using the first detection data and the second detection data as input information of the integrated fusion fertility prediction model, and obtaining output information through the integrated fusion fertility prediction model. After that, it further includes:

[0034] Extract the second fertility detection record in the soil fertility detection log; generate a soil fertility time series based on the first fertility index and the second fertility index in the second fertility detection record; activate the prediction support rate function to analyze the soil fertility time series, and obtain the first prediction support rate of the first predicted fertility index; when the first prediction support rate does not reach the predetermined support rate threshold, conduct a retest analysis on the first predicted fertility index.

[0035] Optionally, first, obtain the second soil fertility detection record from the stored soil fertility detection log. This second soil fertility detection record is the data after the first fertility detection record and contains the soil fertility data at another moment, including the second fertility index and related fertility characteristic data, etc. These data provide a reference for the soil fertility at another time point for subsequent analysis. Subsequently, according to the previously extracted first fertility index and the second fertility index, generate a soil fertility time series in the order of time. The fertility time series reflects the change trend of soil fertility at different time points. After obtaining the soil fertility time series, use the prediction support rate function to analyze the time series data. The role of the prediction support rate function is to measure the reliability and accuracy of the model prediction result. Usually, the first prediction support rate of the first predicted fertility index is calculated based on the trend of the time series data. If the first prediction support rate does not reach the predetermined support rate threshold, it means that the prediction of the model may have a large error and the reliability of the prediction result is low. At this time, in order to improve the prediction accuracy, a retest analysis needs to be conducted on the first predicted fertility index. During the retest analysis, first, judge the input first detection data and the second detection data to identify whether there are incorrect data in the first detection data and the second detection data, such as missing values and outliers. If there are errors, the fertility detection and porosity detection will be carried out again, the first detection data and the second detection data will be updated, and the prediction process will be executed again. If there are no errors, it means that the setting of the hyperparameters of the model itself does not conform to the current scenario. At this time, using the current first detection data and the second detection data as the retrieval target, obtain the records in the soil fertility detection log whose deviation from the first detection data and the second detection data is within the tolerance range (determined according to business requirements and expert decisions), and use these records to conduct secondary training on the current integrated fusion fertility prediction model. The training process is the same as the foregoing. Through further data collection and model optimization, ensure that the predicted fertility index is more accurate and reliable, so as to provide more scientific data support for precise fertilization and soil management in agricultural production.

[0036] Furthermore, the present application provides activating the prediction support rate function to analyze the soil fertility time series and obtaining the first prediction support rate of the first predicted fertility index, including:

[0037] Perform a trend analysis on the soil fertility time series according to the predicted support rate function to obtain a soil fertility trend line; obtain the first distance from the first predicted fertility index to the soil fertility trend line; use the normalized first distance as the first predicted support rate.

[0038] Optionally, when calculating the support rate of the first predicted fertility index using the predicted support rate function, it is first necessary to perform a trend analysis on the soil fertility time series. Specifically, from the existing soil fertility time series, extract the paired data of time and fertility index to construct a time series data set. These data will serve as the basis for regression analysis to reveal the change trend of soil fertility; subsequently, select a suitable regression model to fit these data. In the soil fertility time series data, the fertility usually shows certain non-linear characteristics over time, which means that polynomial regression can better capture the change pattern of the fertility index. To avoid overfitting and maintain the accuracy of the model, we can start with a quadratic regression model. Quadratic regression can effectively fit the fertility data with a single change curve. For example, the fertility rises or falls in some periods and remains stable or slightly fluctuates in other periods. Using the quadratic regression model, it can be expressed as y = β0 + β1t + β2t 2, where β0 is the intercept, β1 and β2 are regression coefficients, representing the linear part and quadratic part of the fertility change over time, t is the time variable, and y is the soil fertility index; then, the data is fitted by the least squares method to solve the best regression coefficient, so that the fitted trend line can reduce the error between the predicted value and the actual data as much as possible, thereby obtaining a trend line describing the change in soil fertility. After completing the trend line fitting, it is necessary to evaluate the fitting effect, and use the determination coefficient to evaluate the goodness of fit of the model. The closer the determination coefficient is to 1, the better the model fits the data, and the more accurately it can reflect the long-term change trend of fertility. If the determination coefficient value is low, it means that quadratic regression may not be sufficient to fit the data, and you may need to consider increasing the order of the model (such as cubic regression) or trying other nonlinear regression methods. At the same time, you also need to evaluate the residual The residuals are analyzed to check the error distribution of the fitted data. If the residuals show a random distribution, it means that the model fits well. On the contrary, if the residuals show systematic deviations, the model should be adjusted or other methods should be selected. Once it is confirmed that the trend line fits well, the soil fertility trend line can be drawn based on the regression coefficient obtained by fitting. This trend line can not only accurately reflect the change pattern of soil fertility over time, but also provide a reliable basis for subsequent fertility prediction. After obtaining the soil fertility trend line, the absolute difference between the first predicted fertility index and the soil fertility index at that moment in the soil fertility trend line is calculated to obtain the first distance from the first predicted fertility index to the soil fertility trend line. The first distance is then ratio-calculated with the historical maximum distance to complete the normalization of the first distance, thereby obtaining the first prediction support rate, which provides a basis for subsequent retesting or optimization.

[0039] The above process of calculating the first predicted support rate is the specific calculation process of the predicted support rate function. Therefore, the specific expression of the predicted support rate function is: Among them, S is the normalized first prediction support rate, is the first predicted fertility index predicted by the model, y trend is the value of the soil fertility trend line at the corresponding time point, D max is the maximum distance between the forecast value and the trend line in the historical data.

[0040] Further, the present application provides taking the mean of the first predicted fertility index in the output information to obtain a target fertility index, including:

[0041] Reading a predetermined human impact index; analyzing human activity records based on the predetermined human impact index to obtain human impact index parameters; performing normalized weighted analysis on the human impact index parameters to obtain a human impact coefficient; and calibrating and adjusting the first predicted fertility index based on the human impact coefficient.

[0042] Preferably, in soil fertility prediction, it is crucial to consider the impact of human factors, because soil fertility is not only affected by natural factors, but also significantly affected by human activities (such as tillage, fertilization, irrigation, etc.). Therefore, it is necessary to calibrate the first predicted fertility index according to the human impact indicators. Specifically, first obtain the predetermined human impact indicators, which usually include various human activity data related to soil fertility changes. For example, crop rotation, fertilization records, tillage, pollution, etc.; Subsequently, obtain human activity records through survey records, agricultural management systems or other data sources, and quantify the impact degree of these human impact indicators by combining the knowledge of domain experts and existing agricultural research literature to obtain human impact indicator parameters; After that, since the impact intensity of different human activities on soil fertility varies greatly, it is necessary to normalize the extracted human impact indicator parameters (such as the maximum-minimum method). The purpose of normalization is to convert data with different units and dimensions into the same scale (usually between 0 and 1) for easy comparison and weighting; After normalization, it is also necessary to weight each indicator. Different human impact indicators may have different impact intensities on soil fertility, and these differences need to be reflected through weighting. For example, the impact of fertilization on fertility may be stronger than that of tillage, so the weight of fertilization can be set larger. The weight of each human impact indicator is also determined based on business needs and expert decisions. By summing up the weighted human impact indicator parameters obtained through these weights, a human impact coefficient can be obtained. By adding this human impact coefficient to the first predicted fertility index, the calibration adjustment of the first predicted fertility index is completed. This adjusted first predicted fertility index combines the impacts of natural and human factors and provides a more accurate and comprehensive fertility prediction.

[0043] Furthermore, the present application provides that the predetermined human impact indicators include impact indicators in the crop rotation dimension, fertilization management dimension, and social activity dimension. Among them, the crop rotation dimension refers to the rotation records with crop type identifiers, the fertilization management dimension refers to the fertilization records with fertilization type and dosage identifiers, and the social activity dimension at least includes tillage, desertification, and pollution.

[0044] Optionally, the predefined anthropogenic impact indicators involve multiple aspects, mainly including dimensions such as crop rotation, fertilization management, and social activities. These dimensions directly or indirectly affect the soil fertility level. The crop rotation dimension refers to the records related to crop rotation. Crop rotation means planting different crops in a specific order on the same piece of land. Crop rotation can effectively improve the fertility and health of the soil, avoiding the excessive consumption of soil nutrients. The crop rotation dimension usually includes the identification of crop types and the planting order of crops within each cycle, helping to analyze the long-term impact of different crop plantings on soil fertility. For example, certain crops (such as legumes) can fix nitrogen, contributing to an increase in the nitrogen content in the soil, while certain crops (such as grains) may consume more nitrogen. Therefore, the records of crop rotation are crucial for understanding changes in soil fertility. The fertilization management dimension covers detailed records of fertilization, including information such as the type of fertilizer, the amount used, and the fertilization method. Fertilization management is an important factor affecting soil fertility. By applying fertilizers rationally, the nutrients lacking in the soil can be supplemented, enhancing the soil fertility. The fertilization management dimension records the type of fertilizer used (such as organic fertilizer, chemical fertilizer, compound fertilizer, etc.) each time fertilization is carried out, the amount of fertilizer applied (usually measured in kilograms per hectare or tons per hectare), and the fertilization method (such as broadcasting, band application, drip fertilization, etc.). Different fertilization methods and amounts have different effects on soil fertility. Rational fertilization can maintain or improve soil fertility, while excessive fertilization may lead to nutrient imbalance or soil pollution. The social activities dimension includes the direct or indirect impact of human activities on soil fertility, especially activities that may cause soil degradation or pollution during agricultural production processes, mainly including tillage, desertification, and pollution. Among them, tillage refers to the tillage methods adopted during plowing, such as deep plowing, shallow plowing, and rotary tillage. Different tillage methods will affect the soil structure, air permeability, and water retention capacity. For example, excessive tillage may lead to soil compaction, affecting the water permeability of the soil and reducing the accumulation of organic matter, thereby reducing soil fertility. Desertification refers to the process in which the surface layer of the soil loses its soil-fixing ability due to factors such as overgrazing, over-tillage, or vegetation damage, resulting in wind erosion or water erosion and forming sandy land. Desertification will exacerbate the decline in soil fertility, especially in arid regions, affecting the cultivability of the land and agricultural productivity. Pollution is usually caused by chemical substances (such as pesticides, heavy metals, excessive fertilizers, etc.). Pollution will reduce the ecological function of the soil, damage the soil structure, and affect the activities of microorganisms, thereby affecting soil fertility. Industrial emissions, improper waste disposal, agricultural pollution, etc. in social activities may all lead to soil pollution; these anthropogenic impact indicators comprehensively evaluate soil fertility from different perspectives, helping to more comprehensively understand the changing rules of soil fertility and providing a basis for precise soil management and fertilization decisions.

[0045] In summary, the embodiments of the present application have at least the following technical effects:

[0046] The embodiments of this application aim to accurately predict soil fertility by comprehensively considering the fertility characteristics, porosity characteristics of soil samples, and the influence of human activities. This application includes introducing a partitioned and stratified sampling mechanism to obtain a sample set of the target soil and conduct fertility detection, combining the porosity plan to detect and analyze the porosity of soil samples, and using an integrated and fused fertility prediction model. Taking the fertility detection data and porosity data as inputs to obtain a prediction result; further analyzing the time-series data of soil fertility, activating the prediction support rate function, conducting trend analysis to obtain the prediction support rate of soil fertility, and optimizing the model based on this; to ensure the accuracy of the prediction result, human influence factors such as crop rotation, fertilization management, and social activities are also considered. By performing normalized weighted analysis on the parameters of these human factors, a human influence coefficient is obtained, and the predicted fertility index is calibrated and adjusted, thereby providing a more accurate prediction of soil fertility. These technical effects together solve the technical problems in traditional soil fertility prediction methods that multi-source data cannot be fully utilized for comprehensive analysis, resulting in low fertility prediction accuracy and inability to adapt to changes in different soil characteristics. It realizes the technical effect of comprehensively analyzing various fertility characteristics through an integrated and fused model, improving the accuracy and applicability of soil fertility prediction.

[0047] It should be noted that the above order of the embodiments of this application is only for description and does not represent the superiority or inferiority of the embodiments. And the above description of specific embodiments of this specification has been made. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-tasking and parallel processing are also possible or may be advantageous.

[0048] The above are only the preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included within the protection scope of this application.

[0049] This specification and the drawings are only exemplary descriptions of this application and are considered to have covered any and all modifications, changes, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application is intended to include these modifications and variations.

Claims

1. A soil fertility prediction method based on data mining, characterized in that Including: Introduce a partitioned and stratified sampling mechanism to obtain a soil sample set of the target soil, and extract the first soil sample from the soil sample set; Read the predetermined fertility characteristic indicators, and perform fertility detection on the first soil sample based on the predetermined fertility characteristic indicators to obtain the first detection data; Retrieve the porosity plan to perform porosity detection and analysis on the first soil sample to obtain the second detection data; Use the first detection data and the second detection data as input information for the integrated fusion fertility prediction model, and obtain output information through the integrated fusion fertility prediction model; Take the mean of the first predicted fertility indices in the output information to obtain the target fertility index, where the target fertility index is used to characterize the fertility of the target soil; Using the first detection data and the second detection data as input information for the integrated fusion fertility prediction model, and obtaining output information through the integrated fusion fertility prediction model, and then further including: Extract the second fertility detection record from the soil fertility detection log; Generate a soil fertility time series based on the first fertility index and the second fertility index in the second fertility detection record; Activate the prediction support rate function to analyze the soil fertility time series to obtain the first prediction support rate of the first predicted fertility index; When the first prediction support rate does not reach the predetermined support rate threshold, perform a retest analysis on the first predicted fertility index; Activating the prediction support rate function to analyze the soil fertility time series to obtain the first prediction support rate of the first predicted fertility index, including: Perform a trend analysis on the soil fertility time series according to the prediction support rate function to obtain a soil fertility trend line; Obtain the first distance from the first predicted fertility index to the soil fertility trend line; Use the normalized first distance as the first prediction support rate.

2. The soil fertility prediction method based on data mining according to claim 1, wherein The predetermined fertility characteristic indicators include fertility characteristic indicators in the soil composition dimension and the soil characteristic dimension, where the soil composition dimension includes various organic matter content indicators and various mineral content indicators, and the soil characteristic dimension includes at least soil pH, soil moisture, and soil temperature.

3. The soil fertility prediction method based on data mining according to claim 1, wherein Retrieving the porosity plan to perform porosity detection and analysis on the first soil sample to obtain the second detection data, including: Extract the volume detection plan in the porosity plan; Perform a direct volume detection on the first soil sample according to the volume detection plan to obtain the first detection result; Extract the liquid penetration detection plan in the porosity plan; Perform a liquid penetration detection on the first soil sample according to the liquid penetration detection plan to obtain the second detection result; Based on the first ventilation coefficient obtained by analyzing the first detection result and the first water permeability coefficient and the first water retention coefficient obtained by analyzing the second detection result, form the second detection data.

4. The soil fertility prediction method based on data mining according to claim 1, characterized in that Before using the first detection data and the second detection data as input information for the integrated fusion fertility prediction model and obtaining output information through the integrated fusion fertility prediction model, it further includes: Obtain the soil fertility detection log and extract the first fertility detection record from the soil fertility detection log; A first training data set is formed based on the first fertility characteristic information and the first fertility index in the first fertility detection record, and a first prediction model is obtained through supervised learning of the first training data set; A second training data set is formed based on the first porosity characteristic information and the first fertility index in the first fertility detection record, and a second prediction model is obtained through supervised learning of the second training data set; The first prediction model and the second prediction model form a first-level prediction layer; A second-level prediction layer is obtained, and the second-level prediction layer is used for normalized weighted output of the prediction results of the first prediction model and the second prediction model; The first-level prediction layer and the second-level prediction layer are constructed into the integrated fusion fertility prediction model.

5. The soil fertility prediction method based on data mining according to claim 1, characterized in that Taking the mean of the first predicted fertility indices in the output information to obtain the target fertility index, including: Reading a predetermined human influence index; Analyzing the human activity record based on the predetermined human influence index to obtain a human influence index parameter; Performing normalized weighted analysis on the human influence index parameter to obtain a human influence coefficient; Calibrating and adjusting the first predicted fertility index based on the human influence coefficient.

6. The soil fertility prediction method based on data mining according to claim 5, wherein, The predetermined human influence index includes influence indices in the crop rotation dimension, fertilization management dimension, and social activity dimension. Among them, the crop rotation dimension refers to the rotation record with crop type identification, the fertilization management dimension refers to the fertilization record with fertilization type and dosage identification, and the social activity dimension at least includes tillage, desertification, and pollution.

Images