A method and system for recommending a microbial culture scheme based on soil data analysis

Abstract

The application discloses a kind of microorganism culture scheme customization recommendation method and system based on soil data analysis, it is related to microorganism culture scheme technical field, this method includes: by collecting different positions and depth of soil sample, analysis soil characteristic data and carry out data processing;Through soil DNA extraction, PCR amplification and high-throughput sequencing obtain microbial community information, combine data preprocessing and diversity analysis, assess microorganism distribution and function;According to soil characteristics and microbial community analysis result, select suitable microorganism strain;Microorganism culture scheme is combined with agricultural management measure;Through real-time monitoring soil and microorganism condition, based on feedback mechanism dynamically adjusts microorganism culture scheme;Through field test and advanced performance evaluation index, the effect of microorganism culture scheme is verified for a long time.The application has strong adaptability and sustainability, and can provide customized microorganism management scheme in different agricultural environments.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of microbial culture scheme, in particular to a microbial culture scheme customization recommendation method and system based on soil data analysis. BACKGROUND

[0002] With the continuous development of agricultural production methods, soil health problems have become a key factor restricting the sustainable development of agriculture. Soil organic matter content, nutrient level, microbial community diversity and other soil characteristics have important influence on crop growth and agricultural yield. However, the traditional soil management method mainly depends on the application of chemical fertilizers and pesticides, which can improve soil fertility and crop yield in the short term, but long-term use will lead to soil degradation, environmental pollution and imbalance of microbial community. Therefore, finding a more sustainable soil management method has become a hot spot in current agricultural research.

[0003] Microbial culture technology as a green agricultural technology has been widely used in improving soil health, promoting plant growth and increasing crop yield. Microorganisms can improve soil structure and function through nitrogen fixation, organic matter decomposition, pathogenic bacteria inhibition and other ways, and play the role of synergistic and soil remediation. However, traditional microbial application is usually based on experience or fixed scheme, which fails to fully combine the characteristics and changes of soil for precise management. Therefore, how to customize microbial culture scheme according to soil type, crop demand and environmental change has become the key to improve the efficiency and effect of microbial application.

[0004] In view of the above problems, the present application provides a microbial culture scheme customization recommendation method and system based on soil data analysis, which can provide accurate microbial management scheme by real-time monitoring of soil and environmental parameters, analyzing the dynamic changes of microbial community, and combining data-driven decision support system, so as to realize the optimization and sustainable development of agricultural production. SUMMARY

[0005] The present application provides a microbial culture scheme customization recommendation method and system based on soil data analysis to solve the problem of inaccurate analysis of soil characteristics and dynamic changes of microbial community, low soil health and crop production efficiency in the prior art.

[0006] To solve the above technical problems, the present application provides the following technical scheme: a microbial culture scheme customization recommendation method based on soil data analysis, comprising the following steps:

[0007] Step S1, by collecting soil samples at different positions and depths, analyzing soil characteristic data, and preprocessing, format converting and normalizing the data;

[0008] In step S1, the following substeps are further included:

[0009] S1-1, by collecting soil samples at different depths and locations in the field to analyze soil characteristic data, including soil pH, soil moisture, soil texture, organic matter content, nutrient level, and microbial diversity;

[0010] S1-2, data preprocessing of soil data, including handling missing data, outlier detection and deletion, and consistency check; and format conversion to maintain data consistency, as follows:

[0011] Handling missing data: using mean interpolation technique to fill in missing values, using the average or median of observed values to estimate missing values for numerical data;

[0012] Outlier detection and deletion: using interquartile range (IQR) to identify and delete data points outside the range of the third quartile or below the first quartile plus or minus 1.5 times the IQR;

[0013] Data detection: using cross-validation to cross-check data from external sources;

[0014] Format conversion: organic matter content and microbial count often span several orders of magnitude, so use logarithmic transformation to normalize data and address skewness;

[0015] S1-3, create new features from existing soil properties, including soil health index and soil nutrient ratio;

[0016] Soil health index: combine multiple soil characteristics into an index score that reflects overall soil health, including pH, organic matter Y, and nutrient level YF;

[0017] Soil nutrient ratio is the nitrogen-phosphorus nutrient level;

[0018] S1-4, normalize data using min-max normalization to scale each feature within a fixed range, as shown in equation (1):

[0019] Equation (1)

[0020] where, is the normalized data, is the original data, is the minimum value of the original data, is the maximum value of the original data.

[0021] Step S2, obtain microbial community information by soil DNA extraction, PCR amplification and high-throughput sequencing, and combine data preprocessing and diversity analysis to evaluate the distribution and function of microorganisms in soil;

[0022] In step S2, the following sub-steps are also included:

[0023] S2-1, use soil DNA extraction kit to extract soil microbial DNA from soil samples, which includes homogenizing soil samples at different depths and locations, releasing DNA by cell lysis, purifying and quantifying the extracted DNA;

[0024] S2-2, use universal primers to amplify key genetic markers, select 16S rRNA for bacteria and ITS for fungi; PCR amplification process includes denaturation, primer annealing and extension of each marker under optimized conditions, and gel electrophoresis is used to check the quality and size of PCR products;

[0025] S2-3, use next-generation sequencing platform to perform high-throughput sequencing on PCR amplified DNA, sequence by adding adaptors to PCR products, obtain comprehensive microbial feature spectrum of soil samples, and ensure sufficient coverage of common and rare microbial species in samples;

[0026] S2-4, process raw sequencing data, use QIIME2 to remove low-quality reads, adapters and primers, classify by reference database, and align cleaned sequences to known species; microbial diversity assessment uses α diversity and β diversity indicators to assess microbial community diversity and differences of soil samples; weighted diversity index is used to further evaluate functional diversity of microorganisms, as shown in formula (2):

[0027] Formula (2)

[0028] Wherein, is the weighted diversity index, n is the index, is the weight of the i-th microorganism, is the abundance of the microorganism in the sample, is the total abundance of all microorganisms;

[0029] S2-5, combine microbial data with soil property data and environmental factors for time integration, spatial integration and environmental data integration;

[0030] Time integration: soil properties change over time, integrate time data to analyze seasonal changes, collect historical soil data or real-time measurements over a period of time, and use time series data to correlate soil changes with microbial activity trends over time;

[0031] Spatial integration: Geospatial information helps analyze the spatial variability of soil properties, using GIS data to map soil data for different fields, incorporating GPS coordinates into soil property data, and analyzing spatial trends and variability in the field;

[0032] Environmental data integration: Temperature, precipitation, and crop management practices affect soil properties and microbial activity. Integrating local environmental data from weather sources or sensors enhances the soil property data set.

[0033] Step S3, based on the analysis of soil properties and microbial community, select appropriate microbial strains, and optimize microbial culture environment and inoculation strategy;

[0034] In step S3, it also includes the following sub-steps:

[0035] S3-1, according to the comprehensive analysis of soil properties and existing microbial community, select suitable microbial strains, as follows:

[0036] The soil data and microbial community data are analyzed through multi-level analysis and optimization algorithm to obtain the optimal microbial culture scheme, the soil data includes nutrient level, pH value and microbial diversity, a large amount of soil data and microbial activity data are trained by using machine learning algorithm, a relationship model between microbial growth and soil properties is established, the growth state of microorganisms and soil health indicators under different soil conditions are predicted, and a series of possible microbial inoculation schemes are output; Using multi-objective optimization algorithm, the scheme is optimized when considering multiple objectives, each candidate scheme will be evaluated through the following process:

[0037] Microbial performance evaluation, based on the demand of soil properties and microbial community, evaluate the ability of microorganisms to fix nutrients and inhibit diseases;

[0038] Environmental adaptability evaluation, analyze the growth stability and effect of microorganisms in different environments;

[0039] Soil health impact evaluation: evaluate the effect of microbial culture scheme on soil improvement through soil health index;

[0040] According to the analysis results, identify the defects or imbalances in the soil, select strains that can make up for these gaps, consider the compatibility of selected strains with existing microbial communities, avoid competition and ensure synergy;

[0041] S3-2, determine the optimal growth conditions according to the needs of the selected strain, including temperature, humidity, oxygen availability and pH value; through standardized microbial culture conditions method, combined with real-time monitoring data for dynamic adjustment, through sensors to monitor soil moisture, temperature and nutrient levels in real time, realize environmental adaptability adjustment, ensure that the microbial growth conditions are always in the best state;

[0042] S3-3, determine the appropriate inoculation strategy, including inoculation density, inoculation time and application frequency, ensure that the microorganisms are applied at a fixed rate and interval; real-time monitoring of microbial population density and health status, determine whether additional inoculation or adjustment of inoculation dose is needed, ensure that the microbial population maintains balance throughout the culture process;

[0043] S3-4, microbial culture scheme combined with other agricultural management measures, management measures including fertilization, irrigation and crop management; according to the real-time performance of microbial inoculant, adjust the fertilization plan to ensure that the nutrient supply is synchronized with the microbial demand; adjust the irrigation strategy according to the soil moisture and microbial activity level to maintain the optimal moisture conditions required for microbial growth; microbial culture scheme and crop rotation or cover crop agricultural practice complement each other, adjust the microbial culture effect according to seasonal changes and crop growth cycle;

[0044] S3-5, adjust the microbial culture scheme based on the real-time changes of soil and microbial data, feedback mechanism makes necessary adjustments to the microbial culture scheme in the process, apply machine learning algorithm to analyze real-time data and predict future soil and microbial state, actively adjust the culture strategy to improve the efficiency of microbial inoculant, use reinforcement learning algorithm, reward function as shown in equation (3):

[0045] Equation (3)

[0046] Where, is the reward at time t, is the weighting coefficient, reflecting the influence of each soil and microbial index on the overall health, is the state of the i-th soil or microbial index at time t.

[0047] Step S4, combine microbial culture scheme with fertilization, irrigation, crop rotation and agricultural management measures, dynamically adjust soil health and crop productivity;

[0048] In step S4, the following sub-steps are also included:

[0049] S4-1, the microbial inoculation scheme is combined with the fertilization plan, the amount of fertilizer input is automatically adjusted by monitoring the microbial population and nutrient availability, the microbial efficiency is optimized, the nutrient circulation is improved, and the demand for excessive chemical fertilizer is reduced, and optimization is performed through the comprehensive target of microbial efficiency and the amount of fertilizer used, as shown in formula (4):

[0050] Formula (4)

[0051] wherein, is a target function, represents the efficiency of the i-th microorganism, is the weight of the microorganism under specific soil and crop management conditions, is the input amount of the i-th fertilizer;

[0052] S4-2, the irrigation scheme is adapted to the microbial growth demand, the irrigation amount is adjusted according to the real-time soil moisture data and microbial demand, the irrigation scheme is customized in combination with the microbial growth data and the soil moisture level, the water condition is ensured to be suitable for microbial growth, and the negative effects of excessive saturation or drought stress on microorganisms are avoided;

[0053] S4-3, the microbial inoculation scheme is integrated with crop rotation and cover planting practices, the microbial inoculation scheme is dynamically adjusted according to the types of rotation crops and the existence of cover crops, as follows:

[0054] Nitrogen-fixing microorganisms are suitable for legume crops, and other microorganisms are suitable for non-legume crops, and this integration method improves soil health by providing appropriate microorganisms at the right time.

[0055] Step S5, by monitoring the soil and microbial conditions in real time, the microbial culture scheme is dynamically adjusted based on the feedback mechanism, and the growth conditions and culture effect of microorganisms are adjusted;

[0056] In step S5, the following sub-steps are further included:

[0057] S5-1, the soil and microbial conditions are continuously monitored by a sensor network and a real-time data collection system, the key soil characteristics and microbial activity are monitored in real time by integrating Internet of Things-based sensors, the changes in soil or microbial conditions are detected in real time, and dynamic environmental factors are ensured to be responded in time;

[0058] S5-2, an adaptive feedback system is used to adjust the microbial culture scheme according to real-time data, real-time data of soil and microorganisms are continuously analyzed, and inoculation rate, nutrient delivery and environmental conditions are automatically adjusted;

[0059] When the soil humidity decreases or the microbial population reaches a set threshold, irrigation or inoculation rate is automatically adjusted to maintain optimal growth conditions;

[0060] S5-3, integrate data from soil sensors, microbial activity monitoring, and environmental factors, build predictive models, analyze comprehensive data using machine learning algorithms and predict future conditions, proactively adjust the program according to upcoming weather changes or seasonal changes, use long short-term memory network for time series prediction, as shown in equation (5):

[0061] Equation (5)

[0062] where, represents the predicted value of soil or microorganisms at time t, is the input data at historical time, is the model parameter, is the LSTM model;

[0063] S5-4, use long-term data collection to improve microbial management strategies, track soil and microbial health conditions over multiple growing seasons, adjust the program according to long-term trends, periodically retrain machine learning models by continuously learning from historical data, reflect changes in soil and microbial conditions, and ensure long-term effectiveness.

[0064] Step S6, long-term verification of the effect of microbial cultivation program through field tests and advanced performance evaluation indicators, and continuous adjustment of the program according to feedback data.

[0065] In step S6, the following sub-steps are also included:

[0066] S6-1, field test to verify the effectiveness of customized microbial cultivation program under actual agricultural conditions, implement multi-zone field tests in different soil types and environmental conditions, evaluate the growth effect of microorganisms, and the long-term impact of different growing seasons on soil health, microbial diversity and crop yield, assess the adaptability of microbial cultivation program in diverse environments through these data, and provide comprehensive verification;

[0067] S6-2, use advanced performance indicators to evaluate the impact of microbial cultivation program, include functional microbial activity and soil resilience in key performance indicators, as shown in equation (6):

[0068] Equation (6)

[0069] where, is the total soil health index, is the i-th soil or microbial property, is the weight coefficient, reflecting the contribution of each property to soil health;

[0070] Functional microorganism activity includes nutrient cycling efficiency and disease suppression, soil resilience includes water retention capacity and erosion resistance;

[0071] S6-3, according to field test and real-time monitoring data, continuously adjust the microbial culture scheme, adopt continuous learning mechanism, real-time feedback from field test and monitoring data, and accordingly fine-tune the microbial protocol in future growing season; machine learning model re-trains the system according to past performance, ensuring that the protocol continuously adapts to changing soil health, microbial behavior and climate conditions.

[0072] A microbial culture scheme customization recommendation system based on soil data analysis, comprising:

[0073] Data collection module, data processing and analysis module, microbial culture scheme recommendation module, monitoring and feedback module;

[0074] The data collection module collects soil property data, microbial data and environmental data; the data sources mainly include two parts: sensor data and microbial diversity analysis;

[0075] The sensor data includes environmental data sensor data and soil sensor data, the soil sensor data includes pH, humidity, temperature, texture and nutrient soil properties, and the environmental data sensor data includes environmental parameters obtained by weather station and crop growth monitoring instruments;

[0076] The microbial diversity analysis analyzes the microbial community in the soil through soil DNA extraction, PCR amplification and high-throughput sequencing technology;

[0077] The data processing and analysis module cleans, preprocesses, analyzes and extracts features of the collected soil data, microbial data and environmental data; the soil and microbial data are automatically analyzed by machine learning algorithm, and the potential law is mined to provide recommendation basis for microbial culture scheme;

[0078] The microbial culture scheme recommendation module provides customized microbial culture scheme according to soil analysis results, combines historical data and real-time data; by analyzing the defects or imbalance of the soil, it automatically recommends appropriate microbial strains, considers the soil microbial diversity, avoids selecting strains that conflict with existing flora, and ensures the synergistic effect between strains;

[0079] The monitoring and feedback module monitors the soil and microbial state in real time, and optimizes the microbial culture scheme through adaptive feedback mechanism; soil and microbial data are collected by sensors and uploaded to cloud platform for real-time processing; according to real-time data, automatically adjust microbial inoculation strategy, fertilizer use and irrigation strategy, ensure that the microorganisms are in the best growth environment.

[0080] Compared with the prior art, the present application has the beneficial effects that:

[0081] The present application combines real-time soil data collection with microbial community analysis, customizes personalized microbial cultivation schemes based on soil characteristics and microbial diversity, automatically selects suitable microbial strains and adjusts cultivation conditions by analyzing soil pH, humidity, and nutrient level information, accurately matches the specific needs of the soil, and significantly improves the effectiveness of microbial applications.

[0082] The present application continuously collects real-time data of soil humidity, temperature, and nutrients through Internet of Things sensors and real-time monitoring systems, and combines with the changes of microbial populations to build a self-adaptive feedback mechanism. This mechanism can dynamically adjust the microbial inoculation density, inoculation time, fertilization, and irrigation strategies according to real-time data, so as to ensure that the growth environment of microorganisms always remains in the best state.

[0083] The present application integrates multiple data sources and uses advanced data analysis and machine learning techniques to establish a comprehensive evaluation model, which can perform in-depth analysis on multi-dimensional data and generate personalized microbial cultivation schemes. Through machine learning algorithms and prediction models, not only can the soil change trend be predicted according to historical data, but also the microbial management strategy can be actively adjusted to cope with future environmental changes, thereby realizing the intelligentization and precision of agricultural management.

[0084] The present application reduces the dependence on chemical fertilizers and pesticides through precise microbial inoculation strategies and dynamic adjustment measures. The microbial inoculation scheme is optimized according to the specific needs of the soil, avoiding the problem of excessive use of fertilizers and pesticides in traditional agriculture, thereby reducing environmental pollution and soil degradation risks. At the same time, by optimizing irrigation, fertilization, and microbial inoculation amount, the resource utilization efficiency is improved, not only reducing the input cost of farmers, but also improving the sustainability of agricultural production.

[0085] The present application can promote crop growth and yield while optimizing soil health by introducing microorganisms with specific functions. Microorganisms not only improve soil structure, but also enhance soil nutrient cycling efficiency, increase soil drought resistance and disease resistance. Through long-term microbial management and soil health monitoring, it helps to realize sustainable use of soil, thereby improving the long-term yield and quality of crops.

[0086] The present application can be customized according to the soil and crop needs of different regions, and can adapt to different soil types, climate conditions, and crop planting patterns, supporting large-scale agricultural production. Through continuous data accumulation and updating of machine learning models, the microbial management scheme can be continuously optimized to maintain high production efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0087] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments, and understand that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0088] Fig. 1 is a method flowchart of the present application;

[0089] Fig. 2 is a system architecture diagram of the present application. DETAILED DESCRIPTION

[0090] In order to make the purposes, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only for selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0091] Please refer to Figs. 1-2 is a method and system schematic diagram of a microbial culture scheme customization recommendation method based on soil data analysis provided by the embodiments of the present application, including the following steps:

[0092] Step S1, by collecting soil samples at different positions and depths, analyzing soil property data, and pre-processing, format conversion and normalization of the data;

[0093] In step S1, the following sub-steps are further included:

[0094] S1-1, by collecting soil samples at different depths and positions in the field to analyze soil property data, the soil property data includes: soil pH value, soil moisture, soil texture, organic matter content, nutrient level, microbial diversity;

[0095] S1-2, data preprocessing is performed on the soil data, including: processing missing data, detecting and deleting outliers, and consistency checking; and format conversion is performed to maintain data consistency, which is specifically as follows:

[0096] Handling missing data: Fill in missing values using mean imputation technique, estimate missing values using the mean or median of observations for numerical data;

[0097] Outlier detection and removal: Use interquartile range (IQR) method to identify and remove data points that are more than 1.5 times the IQR above the third quartile or below the first quartile;

[0098] Data detection: Use cross-validation to cross-check data from external sources;

[0099] Format conversion: Organic matter content and microbial count often span multiple orders of magnitude, use logarithmic transformation for data normalization to address skewness;

[0100] S1-3, create new features from existing soil properties, including soil health index and soil nutrient ratio;

[0101] Soil health index: Combine multiple soil characteristics T (pH, Y, YF) including pH, organic matter Y, and nutrient level YF into an index score reflecting overall soil health;

[0102] Soil nutrient ratio is the nitrogen-phosphorus ratio of nutrient levels;

[0103] S1-4, normalize data by using min-max normalization to scale each feature to a fixed range, as shown in equation (1):

[0104] Equation (1)

[0105] where, is the normalized data, is the original data, is the minimum value of the original data, is the maximum value of the original data.

[0106] It should be noted that soil pH is used to determine the acidity or alkalinity of the soil, affecting microbial activity and nutrient availability, and microorganisms have different pH preferences; soil moisture content affects microbial growth, and excessive watering and insufficient watering can put pressure on microbial communities; the relative amounts of sand, silt, and clay in the soil determine the soil's water retention, drainage, and aeration; high organic matter content provides nutrients for microbial populations and is the energy source for microbial growth; nitrogen, phosphorus, and potassium are essential for plant and microbial growth and help identify nutrient deficiencies; microbial diversity is a basic analysis of existing microbial community structure that can reveal the types of microorganisms present and their relative abundance.

[0107] Crop management practices belong to environmental factors because they directly affect the soil environment and microbial activities in the soil, as follows: tillage, crop rotation or the use of cover crops can change soil structure, nutrient availability and organic matter content, which in turn affect the microbial community in the soil; fertilization methods affect the nutrient balance in the soil, and different microorganisms require different nutrient conditions to survive and grow, thus affecting the prosperity of different microbial species.

[0108] Step S2, obtain microbial community information by soil DNA extraction, PCR amplification and high-throughput sequencing, and combine data preprocessing and diversity analysis to evaluate the distribution and function of microorganisms in the soil;

[0109] In step S2, the following sub-steps are further included:

[0110] S2-1, use a soil DNA extraction kit to extract soil microbial DNA from soil samples, which includes homogenizing soil samples at different depths and locations, releasing DNA by cell lysis, purifying and quantifying the extracted DNA;

[0111] S2-2, use universal primers to amplify key genetic markers, select 16S rRNA for bacteria and ITS for fungi; the PCR amplification process includes denaturation, primer annealing and extension of each marker under optimized conditions, and the quality and size of the PCR product are checked by gel electrophoresis;

[0112] S2-3, use next-generation sequencing platforms to perform high-throughput sequencing on PCR-amplified DNA, sequence by adding adaptors to PCR products, obtain comprehensive microbial feature spectrum of soil samples, and ensure sufficient coverage of common and rare microbial species in the sample;

[0113] S2-4, process the raw sequencing data, use QIIME2 to remove low-quality reads, adapters and primers, classify by reference database, and align the cleaned sequences to known species; microbial diversity assessment uses α diversity and β diversity indicators to assess the diversity and difference of microbial communities in soil samples; weighted diversity index is used to further evaluate the functional diversity of microorganisms, as shown in equation (2):

[0114] Equation (2)

[0115] wherein, is the weighted diversity index, n is the index, is the weight of the i-th microorganism, is the abundance of the microorganism in the sample, is the total abundance of all microorganisms;

[0116] S2-5, combining microbial data with soil property data and environmental factors for temporal integration, spatial integration, and environmental data integration;

[0117] Temporal integration: soil properties change over time, integrating temporal data to analyze seasonal changes, collecting historical soil data or real-time measurements over a period of time, using time series data to correlate soil changes with microbial activity trends over time;

[0118] Spatial integration: geospatial information helps analyze spatial variability of soil properties, using GIS data to map soil data for different fields, incorporating GPS coordinates into soil property data, analyzing spatial trends and variability in the field;

[0119] Environmental data integration: temperature, precipitation, and crop management practices affect soil properties and microbial activity, integrating local environmental data from weather sources or sensors to enhance the soil property data set.

[0120] It should be noted that by integrating soil properties, microbial diversity data and environmental data, machine learning algorithms are used for data analysis to automatically generate microbial cultivation schemes adapted to different soil and climate conditions. The system can identify the most suitable microbial strains based on historical and real-time data, and provide personalized fertilization, irrigation and inoculation recommendations for users.

[0121] Step S3, according to the analysis results of soil properties and microbial community, select appropriate microbial strains, and optimize microbial culture environment and inoculation strategy;

[0122] In step S3, the following sub-steps are included:

[0123] S3-1, according to the comprehensive analysis of soil properties and existing microbial community, select appropriate microbial strains, as follows:

[0124] The optimal microbial cultivation scheme is obtained by multi-level analysis and optimization algorithm based on soil data including nutrient level, pH value and microbial diversity, and a large amount of soil data and microbial activity data are trained by machine learning algorithm to establish a relationship model between microbial growth and soil properties, predict the growth state of microorganisms and soil health indicators under different soil conditions, and output a series of possible microbial inoculation schemes; multi-objective optimization algorithm is used to optimize the scheme considering multiple objectives, and each candidate scheme is evaluated by the following process:

[0125] Microbial performance evaluation, based on soil properties and microbial community needs, evaluate the microbial ability to fix nutrients and inhibit diseases;

[0126] Environmental adaptability assessment, analyzing the growth stability and effects of microorganisms in different environments;

[0127] Soil health impact assessment: evaluating the effects of microbial cultivation programs on soil improvement through soil health index;

[0128] Identify soil deficiencies or imbalances based on analysis results, select strains that can make up for these gaps, consider compatibility of selected strains with existing microbial communities to avoid competition and ensure synergy;

[0129] S3-2, determine optimal growth conditions for selected strains, including temperature, humidity, oxygen availability and pH; through standardized microbial cultivation conditions method, combined with real-time monitoring data for dynamic adjustment, real-time monitoring of soil moisture, temperature and nutrient levels through sensors to achieve environmental adaptability adjustment, ensuring that microbial growth conditions are always in the best state;

[0130] S3-3, determine appropriate inoculation strategies, including inoculation density, inoculation time and application frequency, ensure that microorganisms are applied at a fixed rate and interval; monitor microbial population density and health status in real time to determine whether additional inoculation or adjustment of inoculation dose is needed to ensure that the microbial population maintains balance throughout the cultivation process;

[0131] S3-4, combine microbial cultivation programs with other agricultural management measures, including fertilization, irrigation and crop management; adjust fertilization plan according to real-time performance of microbial inoculant to ensure synchronization of nutrient supply and microbial demand; adjust irrigation strategy according to soil moisture and microbial activity level to maintain optimal moisture conditions for microbial growth; microbial cultivation programs complement crop rotation or cover crop agricultural practices, adjust microbial cultivation effects according to seasonal changes and crop growth cycles;

[0132] S3-5, adjust microbial cultivation programs based on real-time changes in soil and microbial data, feedback mechanism makes necessary adjustments to microbial cultivation programs during the process, apply machine learning algorithms to analyze real-time data and predict future soil and microbial states, actively adjust cultivation strategies to improve the effectiveness of microbial inoculants, use reinforcement learning algorithm, reward function as shown in equation (3):

[0133] Equation (3)

[0134] where, is the reward at time t, is the weighting coefficient, reflecting the influence of each soil and microbial index on overall health, is the state of the i-th soil or microbial index at time t.

[0135] It should be noted that in the process of selecting microbial strains, real-time soil data and microbial community changes are used to dynamically adjust strain recommendations, such as automatically recommending appropriate microbial strains, such as nitrogen-fixing bacteria and phosphorus-dissolving bacteria, according to certain deficiencies in the soil, such as nitrogen deficiency and phosphorus deficiency, so as to automatically optimize the microbial inoculation scheme under different environmental conditions.

[0136] Step S4, combining microbial culture schemes with fertilization, irrigation, crop rotation and agricultural management measures, dynamically adjusting soil health and crop productivity;

[0137] In step S4, the following sub-steps are further included:

[0138] S4-1, the microbial inoculation scheme is combined with the fertilization plan, and the amount of fertilizer input is automatically adjusted by monitoring the microbial population and nutrient availability, so as to optimize the microbial efficiency, improve the nutrient cycle, and reduce the demand for excessive chemical fertilizers, and the optimization is carried out through the comprehensive target of microbial efficiency and fertilizer usage, as shown in formula (4):

[0139] Formula (4)

[0140] wherein, is the target function, represents the efficiency of the i-th microorganism, is the weight of the microorganism under specific soil and crop management conditions, is the input amount of the i-th fertilizer;

[0141] S4-2, the irrigation scheme is adapted to the growth needs of the microorganisms, and the irrigation amount is adjusted according to real-time soil moisture data and microbial needs, and the irrigation scheme is customized by combining microbial growth data with soil moisture levels, so as to ensure that the water conditions are suitable for microbial growth and avoid the negative effects of excessive saturation or drought stress on microorganisms;

[0142] S4-3, the microbial inoculation scheme is integrated with crop rotation and mulching practices, and the microbial inoculation scheme is dynamically adjusted according to the types of crops in rotation and the presence of mulching crops, as follows:

[0143] Nitrogen-fixing microorganisms are suitable for leguminous crops, and other microorganisms are suitable for non-leguminous crops, and this integration method improves soil health by providing appropriate microbial support at the right time.

[0144] It should be noted that through the synergistic effect of microorganisms and fertilizers, the amount of fertilizer used is optimized, and the amount of fertilizer applied is automatically adjusted according to the activity level of the microorganisms, and when the microbial community can effectively fix nitrogen, the system will reduce the use of nitrogen fertilizer to avoid excessive fertilization; through this synergistic effect, not only is the waste of chemical fertilizers reduced, but also the soil health and crop yield are improved.

[0145] Step S5, dynamically adjust the microbial culture scheme based on the feedback mechanism by real-time monitoring of soil and microbial conditions, adjust the growth conditions and culture effect of microorganisms;

[0146] Among them, in step S5, the following sub-steps are included:

[0147] S5-1, continuously monitor the soil and microbial conditions through the sensor network and real-time data collection system, monitor the key soil characteristics and microbial activity in real time through the integration of Internet of Things based sensors, detect the changes of soil or microbial conditions in real time, and ensure timely response to dynamic environmental factors;

[0148] S5-2, adopt adaptive feedback system, adjust microbial culture scheme according to real-time data, continuously analyze real-time data of soil and microorganisms, and automatically adjust inoculation rate, nutrient delivery and environmental conditions;

[0149] When the soil humidity decreases or the microbial population reaches the set threshold, automatically adjust irrigation or inoculation rate to maintain the best growth conditions;

[0150] S5-3, integrate data from soil sensors, microbial activity monitoring and environmental factors, establish prediction model, use machine learning algorithm to analyze comprehensive data and predict future conditions, actively adjust scheme according to upcoming weather changes or seasonal changes, use long short-term memory network for time series prediction, as shown in formula (5):

[0151] Formula (5)

[0152] Among them, represents the predicted value of soil or microorganisms at time t, is the input data at historical time, is the model parameter, is the LSTM model;

[0153] S5-4, use long-term data collection to improve microbial management strategy, track soil and microbial health conditions in multiple growth seasons, adjust scheme according to long-term trend, periodically retrain machine learning model by continuously learning from historical data, reflect the changes of soil and microbial conditions, and ensure long-term effectiveness.

[0154] It should be noted that the adaptive adjustment of microbial inoculation scheme is realized through reinforcement learning algorithm and real-time feedback mechanism, according to the changes of soil conditions and microbial community, the density, time and frequency of microbial inoculation are continuously optimized, when the soil humidity is too low or the microbial activity is low, the system will automatically increase the inoculation frequency or adjust the inoculation amount, to ensure that the microorganisms can play a role in the most suitable conditions.

[0155] Step S6, the effectiveness of the microbial cultivation scheme is verified through field tests and advanced performance evaluation indicators, and the scheme is continuously adjusted according to feedback data.

[0156] In step S6, the following sub-steps are also included:

[0157] S6-1, field tests are conducted to verify the effectiveness of the customized microbial cultivation scheme under actual agricultural conditions, multi-zone field tests are conducted under different soil types and environmental conditions, the growth effect of the microorganisms is evaluated, and the long-term impact of different growth seasons on soil health, microbial diversity and crop yield is evaluated. Through these data, the adaptability of the microbial cultivation scheme in various environments is evaluated, and comprehensive verification is provided.

[0158] S6-2, the impact of the microbial cultivation scheme is evaluated using advanced performance indicators, and functional microbial activity and soil resilience are included in the key performance indicators, as shown in formula (6):

[0159] Formula (6)

[0160] Wherein, is the total soil health index, is the i-th soil or microbial characteristic, is the weight coefficient reflecting the contribution of each characteristic to soil health;

[0161] Functional microbial activity includes nutrient cycling efficiency and disease inhibition, and soil resilience includes water retention capacity and erosion resistance.

[0162] S6-3, continuously adjust the microbial cultivation scheme according to field tests and real-time monitoring data, adopt a continuous learning mechanism, real-time feedback from field tests and monitoring data, and accordingly fine-tune the microbial protocol for future growth seasons; machine learning model re-trains the system according to past performance to ensure that the protocol continuously adapts to changing soil health, microbial behavior and climate conditions.

[0163] It should be noted that the microorganisms not only improve the nutrient cycling of the soil, but also enhance the soil's resistance to diseases and pests through biological control. It is recommended to use microbial strains with antibacterial and insecticidal effects to help reduce pesticide use in farmland; for example, Trichoderma, Bacillus and other microorganisms can inhibit pathogenic bacteria and pests in the soil, reduce the frequency of pesticide use, and further improve soil health and the natural resistance of crops.

[0164] A microbial cultivation scheme customization recommendation system based on soil data analysis, comprising:

[0165] Data collection module, data processing and analysis module, microbial cultivation scheme recommendation module, monitoring and feedback module;

[0166] The data collection module collects soil property data, microbial data and environmental data; the data sources mainly include two parts: sensor data and microbial diversity analysis;

[0167] The sensor data includes environmental data sensor data and soil sensor data, the soil sensor data includes pH, humidity, temperature, texture and nutrient soil properties, and the environmental data sensor data includes environmental parameters obtained by weather stations and crop growth monitoring instruments;

[0168] The microbial diversity analysis analyzes the microbial community in the soil through soil DNA extraction, PCR amplification and high-throughput sequencing technology;

[0169] The data processing and analysis module cleans, preprocesses, analyzes and extracts features from the collected soil data, microbial data and environmental data; through machine learning algorithm, the soil and microbial data are automatically analyzed to mine potential rules and provide recommendation basis for microbial cultivation scheme;

[0170] The microbial cultivation scheme recommendation module provides customized microbial cultivation scheme according to the soil analysis results, combines historical data and real-time data, analyzes the defects or imbalance of the soil, automatically recommends suitable microbial strains, considers the soil microbial diversity, avoids selecting strains that conflict with existing flora, and ensures the synergistic effect between strains;

[0171] The monitoring and feedback module monitors the soil and microbial state in real time, and optimizes the microbial cultivation scheme through adaptive feedback mechanism; through the sensor, the soil and microbial data are collected, the data is uploaded to the cloud platform for real-time processing; according to the real-time data, the microbial inoculation strategy, fertilizer use and irrigation strategy are automatically adjusted to ensure that the microorganisms are in the best growth environment.

[0172] The above only describes the preferred embodiments of the present application and is not used to limit the present application. For those skilled in the art, the present application has various changes and variations. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for customizing and recommending microbial culture protocols based on soil data analysis, characterized in that, Includes the following steps: Step S1: Collect soil samples from different locations and depths, analyze soil characteristic data, and preprocess, convert, and normalize the data. Step S2 involves obtaining microbial community information through soil DNA extraction, PCR amplification, and high-throughput sequencing, and then combining data preprocessing and diversity analysis to assess the distribution and function of microorganisms in the soil. Step S3: Based on the soil characteristics and microbial community analysis results, select suitable microbial strains and optimize the microbial culture environment and inoculation strategy; Step S4 involves integrating the microbial culture program with agricultural management practices such as fertilization, irrigation, and crop rotation, by dynamically adjusting soil health and crop productivity. Step S5: By monitoring the soil and microbial conditions in real time, the microbial culture program is dynamically adjusted based on the feedback mechanism to adjust the growth conditions and culture effect of the microorganisms. Step S6 involves long-term validation of the effectiveness of the microbial culture program through field trials and advanced performance evaluation indicators, and continuous adjustment of the program based on feedback data.

2. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S1 further includes the following sub-steps: S1-1, soil characteristic data were analyzed by collecting soil samples at different depths and locations in the field. The soil characteristic data included: soil pH, soil moisture, soil texture, organic matter content, nutrient level, and microbial diversity. S1-2, Data preprocessing of soil data, including: handling missing data, outlier detection and deletion, and consistency checks; and format conversion to maintain data consistency, as detailed below: Handling missing data: Use mean imputation to fill in missing values. For numerical data, use the mean or median of the observations to estimate missing values. Outlier detection and removal: Using the interquartile range (IQR), identify and remove data points that are above the third quartile or below 1.5 times the IQR of the first quartile; Data inspection: Use cross-validation to cross-check the data against external sources; Format conversion: Organic matter content and microbial counts often span multiple orders of magnitude. Logarithmic transformation is used to normalize the data and solve the problem of skewed distribution. S1-3, Create new features by means of existing soil properties, the new features including soil health index and soil nutrient ratio; Soil Health Index: A score that combines multiple soil properties into an index that reflects the overall health of the soil, including pH, organic matter Y, and nutrient levels YF; Soil nutrient ratio is the nitrogen-phosphorus ratio nutrient level; S1-4, by normalizing the data using min-max normalization, each feature is scaled to fit within a fixed range, as shown in equation (1): Equation (1) in, For the normalized data, This is the original data. The minimum value of the original data. This represents the maximum value of the original data.

3. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S2 further includes the following sub-steps: S2-1, Soil DNA Extraction Kit is used to extract soil microbial DNA from soil samples. This process includes homogenizing soil samples from different depths and locations, releasing DNA through cell lysis, and purifying and quantifying the extracted DNA. S2-2, using universal primers to directionally amplify key genetic markers, selecting bacterial 16S rRNA and fungal ITS; The PCR amplification process includes denaturation, primer annealing, and expansion of each label under optimized conditions, followed by gel electrophoresis to check the quality and size of the PCR products. S2-3: High-throughput sequencing of PCR-amplified DNA was performed using a next-generation sequencing platform. By adding aptamers to the PCR product for sequencing, a comprehensive microbial characterization profile of the soil sample was obtained to prepare a sequencing library, ensuring full coverage of common and rare microbial species in the sample. S2-4, the raw sequencing data were processed, and low-quality reads, adapters, and primers were removed using QIIME2. The data were then classified using a reference database, and the cleaned sequences were compared with those of known species. Microbial diversity was assessed using α-diversity and β-diversity indices to evaluate the diversity and variability of the microbial community in the soil samples. The functional diversity of the microorganisms was further assessed using a weighted diversity index, as shown in Equation (2). Equation (2) in, This is a weighted diversity index, where n is the index. Let i be the weight of the i-th microorganism. The abundance of this microorganism in the sample. The total abundance of all microorganisms; S2-5, Microbial data is combined with soil property data and environmental factors to achieve temporal integration, spatial integration, and environmental data integration; Temporal integration: Soil properties change over time. Integrating temporal data to analyze seasonal changes involves collecting historical soil data or real-time measurements over a period of time and using time series data to correlate soil changes with changes in microbial activity trends over time. Spatial integration: Geospatial information helps to analyze the spatial variability of soil properties. By using GIS data to map soil data in different fields and incorporating GPS coordinates into soil property data, spatial trends and variability in the fields can be analyzed. Environmental data integration: Environmental factors such as temperature, precipitation, and crop management practices can affect soil properties and microbial activity. Integrating local environmental data from meteorological sources or sensors can enhance soil property datasets.

4. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S3 further includes the following sub-steps: S3-1. Based on a comprehensive analysis of soil characteristics and existing microbial communities, suitable microbial strains were selected, as follows: The optimal microbial culture scheme is derived by using multi-level analysis and optimization algorithms on soil data and microbial community data. The soil data includes nutrient levels, pH value, and microbial diversity. Machine learning algorithms are used to train a model on a large amount of soil and microbial activity data to establish the relationship between microbial growth and soil properties, predicting the growth status of microorganisms and soil health indicators under different soil conditions, and outputting a series of possible microbial inoculation schemes. A multi-objective optimization algorithm is used to optimize the scheme while considering multiple objectives. Each candidate scheme is evaluated through the following process: Microbial efficacy assessment, based on soil characteristics and the needs of the microbial community, evaluates the ability of microorganisms to fix nutrients and suppress diseases. Environmental adaptability assessment, analyzing the growth stability and effects of microorganisms under different environments; Soil health impact assessment: The effectiveness of microbial culture programs on soil improvement is evaluated using the soil health index; Based on the analysis results, identify defects or imbalances in the soil, select strains that can fill these gaps, consider the compatibility of selected strains with the existing microbial community, avoid competition and ensure synergy. S3-2 determines the optimal growth conditions based on the needs of the selected strains, including temperature, humidity, oxygen availability, and pH. It uses standardized microbial culture conditions and real-time monitoring data for dynamic adjustments. Sensors monitor soil moisture, temperature, and nutrient levels in real time to achieve environmental adaptive adjustments and ensure that the microbial growth conditions are always in the optimal state. S3-3, Determine an appropriate inoculation strategy, including inoculation density, inoculation time, and application frequency, to ensure that the microorganisms are applied at a fixed rate and interval; monitor the microbial population density and health status in real time to determine whether additional inoculation or adjustment of the inoculation dose is needed, and ensure that the microbial population remains in balance throughout the culture process; S3-4, Microbial culture programs are integrated with other agricultural management practices, including fertilization, irrigation, and crop management; fertilization plans are adjusted based on the real-time performance of microbial inoculants to ensure nutrient supply is synchronized with microbial needs; irrigation strategies are adjusted based on soil moisture and microbial activity levels to maintain optimal water conditions for microbial growth; microbial culture programs complement crop rotation or cover crop practices, adjusting the effectiveness of microbial culture according to seasonal changes and crop growth cycles; S3-5, the microbial culture program is adjusted based on real-time changes in soil and microbial data. The feedback mechanism adjusts the microbial culture program during the process. Machine learning algorithms are applied to analyze real-time data and predict future soil and microbial states. The culture strategy is actively adjusted to improve the effectiveness of the microbial inoculant. The reinforcement learning algorithm is used, and the reward function is shown in equation (3): Equation (3) in, The reward at time t. These are weighted coefficients, reflecting the impact of various soil and microbial indicators on overall health. Let represent the state of the i-th soil or microbial indicator at time t.

5. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S4 further includes the following sub-steps: S4-1, the microbial inoculation program is combined with the fertilization plan. By monitoring the microbial population and nutrient availability, the fertilizer input is automatically adjusted to optimize microbial efficiency, improve nutrient cycling, and reduce the demand for excessive fertilizer. The optimization is achieved through a comprehensive objective of microbial efficiency and fertilizer usage, as shown in Equation (4): Equation (4) in, Let be the objective function. This represents the efficiency of the i-th microorganism. The weight of the microorganism under specific soil and crop management conditions. Let i be the input amount of the i-th type of fertilizer; S4-2, the irrigation scheme is adapted to the growth needs of microorganisms. The irrigation amount is adjusted according to real-time soil moisture data and microbial needs. The irrigation scheme is customized by combining microbial growth data and soil moisture level to ensure that the water conditions are suitable for microbial growth and avoid the negative impact of oversaturation or drought stress on microorganisms. S4-3, the microbial inoculation program is integrated with crop rotation and mulch planting practices, and the microbial inoculation program is dynamically adjusted according to the type of rotation crop and the presence of mulch crop, as detailed below: Nitrogen-fixing microorganisms are suitable for legume crops, while other microorganisms are suitable for non-legume crops. This integration approach improves soil health by providing the right microbial support at the right time.

6. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S5 further includes the following sub-steps: S5-1 continuously monitors soil and microbial conditions through a sensor network and a real-time data collection system. By integrating IoT-based sensors, it monitors key soil characteristics and microbial activity in real time, instantly detects changes in soil or microbial conditions, and ensures timely response to dynamic environmental factors. S5-2 employs an adaptive feedback system to adjust the microbial culture program based on real-time data, continuously analyzes real-time data on soil and microorganisms, and automatically adjusts the inoculation rate, nutrient delivery, and environmental conditions. When soil moisture decreases or the microbial population reaches a set threshold, the irrigation or inoculation rate is automatically adjusted to maintain optimal growth conditions. S5-3 integrates data from soil sensors, microbial activity monitoring, and environmental factors to establish a predictive model. Machine learning algorithms are used to analyze the comprehensive data and predict future conditions. The plan is proactively adjusted based on upcoming weather or seasonal changes. Long Short-Term Memory (LSTM) networks are used for time series forecasting, as shown in Equation (5). Equation (5) in, This represents the predicted value of soil or microorganisms at time t. Input data for historical moments, For model parameters, It is an LSTM model; S5-4 utilizes long-term data collection to improve microbial management strategies, tracks soil and microbial health across multiple growing seasons, adjusts programs based on long-term trends, and continuously learns from historical data, periodically retraining machine learning models to reflect changes in soil and microbial conditions, ensuring long-term effectiveness.

7. The method for customizing and recommending microbial culture programs based on soil data analysis according to claim 1, characterized in that: Step S6 further includes the following sub-steps: S6-1, conduct field trials to verify the effectiveness of customized microbial culture programs under actual agricultural conditions, implement multi-zone field trials under different soil types and environmental conditions, evaluate the growth effects of microorganisms, and the long-term impact of different growing seasons on soil health, microbial diversity and crop yield, and use these data to evaluate the adaptability of microbial culture programs in diverse environments, providing comprehensive validation; S6-2, using advanced performance indicators to evaluate the impact of microbial culture programs, incorporating functional microbial activity and soil resilience into key performance indicators, as shown in Equation (6): Equation (6) in, The total soil health index, For the i-th soil or microbial characteristic, These are weighting coefficients, reflecting the contribution of each characteristic to soil health; Functional microbial activity includes nutrient cycling efficiency and disease inhibition, while soil resilience includes water retention capacity and erosion resistance. S6-3 continuously adjusts the microbial culture program based on field trials and real-time monitoring data. It adopts a continuous learning mechanism to provide real-time feedback from field trials and monitoring data, and fine-tunes the microbial protocol for future growing seasons accordingly. The machine learning model retrains the system based on past performance to ensure that the protocol continuously adapts to changing soil health, microbial behavior, and climatic conditions.

8. A microbial culture protocol customization and recommendation system based on soil data analysis, applied to the microbial culture protocol customization and recommendation method based on soil data analysis as described in any one of claims 1-7, characterized in that: Data collection module, data processing and analysis module, microbial culture protocol recommendation module, monitoring and feedback module; The data collection module collects soil characteristic data, microbial data, and environmental data; the data sources are mainly two parts: sensor data and microbial diversity analysis. The sensor data includes environmental sensor data and soil sensor data. The soil sensor data includes soil properties such as pH, humidity, temperature, texture, and nutrients. The environmental sensor data includes environmental parameters obtained from weather stations and crop growth monitoring instruments. The microbial diversity analysis was conducted by analyzing the microbial community in the soil using soil DNA extraction, PCR amplification, and high-throughput sequencing technologies. The data processing and analysis module cleans, preprocesses, analyzes, and extracts features from the collected soil data, microbial data, and environmental data. Automated analysis of soil and microbial data using machine learning algorithms uncovers potential patterns and provides recommendations for microbial culture programs; The microbial culture program recommendation module provides customized microbial culture programs based on soil analysis results, combined with historical and real-time data. By analyzing soil defects or imbalances, it automatically recommends suitable microbial strains, taking into account soil microbial diversity, avoiding the selection of strains that conflict with existing microbial communities, and ensuring synergistic effects between strains. The monitoring and feedback module monitors the soil and microbial status in real time and optimizes the microbial cultivation program through an adaptive feedback mechanism; it collects soil and microbial data through sensors and uploads the data to the cloud platform for real-time processing; it automatically adjusts the microbial inoculation strategy, fertilizer application, and irrigation strategy based on real-time data to ensure that the microorganisms are in the optimal growth environment.

Images