A Multifactor Analysis-Based System for Preventing Continuous Cropping Obstacles in Konjac and Improving Soil

Abstract

This invention provides a multi-factor analysis-based system for preventing konjac continuous cropping obstacles and improving soil quality. Relating to the field of soil improvement technology, the system includes a nutrient intelligent optimization system, a microbial community dynamic adjustment system, a remote sensing and machine vision monitoring and evaluation system, an adaptive multi-energy management system, and a blockchain-traceable soil management system. Employing a comprehensive soil health assessment and intelligent optimization system, combined with remote sensing monitoring, microbial regulation, intelligent fertilization, energy management, and other technologies, it enables refined soil management and long-term maintenance of soil health during konjac continuous cropping. This avoids common continuous cropping obstacles such as soil nutrient depletion and disease accumulation, ensuring high-yield stability during konjac continuous cropping, maintaining the soil's continuous productivity, and effectively solving various soil-related problems in konjac continuous cropping. Through comprehensive prevention and dynamic management, it can effectively reduce the negative impacts of continuous cropping and improve overall yield and crop quality.

Description

Technical Field

[0001] This invention relates to the field of soil improvement technology, specifically to a system for preventing and improving konjac continuous cropping obstacles based on multi-factor analysis. Background Technology

[0002] According to a soil improvement method and dynamic monitoring system disclosed in Chinese Publication No. CN117829357A, the method includes the following steps: S1, collecting soil characteristic data and environmental data; S2, preprocessing the data to generate a dataset suitable for analysis; S3, processing the dataset using a machine learning model, wherein the machine learning model uses a random forest algorithm, and the algorithm predicts the effect of soil improvement measures by inputting feature vectors and model parameters; S4, outputting soil improvement suggestions based on the prediction. This invention provides farm managers with prediction-based soil improvement suggestions by collecting soil characteristic data and environmental data and using a machine learning model to predict the effect of soil improvement measures. By optimizing soil conditions and environmental factors, this method helps to improve crop yield and quality and provides support for sustainable agricultural development.

[0003] According to the Chinese patent application CN118071169A, an analytical decision-making method and system for engineering construction project approval, which relates to the field of Internet of Things technology, analyzes the soil condition of the construction land by obtaining information on the project land area and geographical location. This helps determine parameters such as soil permeability coefficient, heavy metal content, and soil density, providing basic data for subsequent soil condition assessment. This facilitates a better understanding of the soil conditions of the construction land, enabling the rational planning of soil improvement and treatment measures to meet project needs. By calculating the soil condition assessment coefficient for a specified engineering construction project and comprehensively considering the impact of factors such as soil permeability coefficient, heavy metal content, and soil density on the project, decision-makers can quickly understand the suitability of the soil and determine the importance and urgency of soil improvement and treatment work.

[0004] The aforementioned patent documents and prior art have the following technical problems when used:

[0005] Question 1: In the existing technologies mentioned above, the obstacles to continuous cropping of konjac involve multiple factors such as soil nutrient depletion and disease accumulation. Simple random forest models cannot capture these complex interrelationships and dynamic changes, so their predictive effect is not accurate enough and cannot provide sufficiently accurate soil improvement suggestions for continuous cropping.

[0006] Question 2: The soil monitoring in the aforementioned documents and existing technologies is limited to monitoring temperature, humidity and element content, failing to adequately monitor and manage the microbial community. This leads to the proliferation of harmful microorganisms, while the lack of beneficial microorganisms affects soil biodiversity, which in turn affects the growth and yield of konjac.

[0007] Question 3: In the above-mentioned documents and existing technologies, in the scenario of large-scale konjac cultivation, traditional soil sampling and data collection methods are too time-consuming and costly, making it difficult to achieve rapid response. Therefore, soil data collected solely by ground sensors cannot fully reflect the soil condition.

[0008] Question 4: The soil improvement measures mentioned above, which do not take into account environmental conditions, are too simplistic and difficult to adapt to complex climate changes. Furthermore, the lack of soil management records and traceability systems leads to opaque operations in the soil management process, making it impossible to accurately determine the historical state of soil health, which in turn affects long-term planting plans. Summary of the Invention

[0009] Technical problems to be solved

[0010] To address the shortcomings of existing technologies, this invention provides a multi-factor analysis-based system for preventing continuous cropping obstacles in konjac and for soil improvement, solving the following problems:

[0011] 1. Simple random forest models cannot capture these complex interrelationships and dynamic changes, thus their prediction performance is not accurate enough;

[0012] 2. Failure to adequately monitor and manage the microbial community led to the proliferation of harmful microorganisms, affecting crop yields;

[0013] 3. In large-scale konjac cultivation scenarios, traditional soil sampling and data collection methods are too time-consuming and costly, making it difficult to achieve rapid response.

[0014] 4. Soil improvement measures that do not take into account environmental conditions are too simplistic, making them difficult to adapt to complex climate changes and lacking soil management records and traceability systems.

[0015] Technical solution

[0016] To achieve the above objectives, this invention provides the following technical solution: a multi-factor analysis-based system for preventing continuous cropping obstacles in konjac and for soil improvement, comprising a nutrient intelligent optimization system, a microbial community dynamic adjustment system, a remote sensing and machine vision monitoring and evaluation system, an adaptive multi-functional management system, and a blockchain-based traceable soil management system, wherein:

[0017] The remote sensing and machine vision monitoring and evaluation system utilizes UAV and satellite remote sensing technology to analyze vegetation health through the NDVI vegetation index, while combining machine vision technology to monitor soil moisture, nutrient distribution, and signs of pests and diseases in real time, providing an accurate soil health assessment.

[0018] The nutrient intelligent optimization system receives macroscopic soil health data from remote sensing and machine vision monitoring and evaluation systems, monitors key nutrients such as nitrogen, phosphorus, and potassium in the soil in real time through sensors, and dynamically adjusts soil nutrients by combining deep learning algorithms.

[0019] The microbial community dynamic adjustment system is based on soil assessment data from the remote sensing and machine vision monitoring and evaluation system and real-time monitoring data from the nutrient intelligent optimization system. It analyzes the composition of the microbial community in the soil, uses the Lotka-Volterra competition model to describe the interaction between harmful and beneficial microorganisms, and monitors the structure of the microbial community in the soil in real time.

[0020] The adaptive multi-energy management system integrates and utilizes various renewable energy sources, and dynamically adjusts the soil environment, including temperature, humidity, light, and irrigation, based on feedback from remote sensing and machine vision monitoring and evaluation systems, thereby performing functional and control regulation of the soil environment.

[0021] The blockchain-based traceable soil management system utilizes blockchain technology to build a traceable system for soil management and crop production, recording each soil treatment and crop health monitoring on the blockchain for transparent management.

[0022] Preferably, in the remote sensing and machine vision monitoring and evaluation system, UAVs and satellite remote sensing are used for regional scanning to collect vegetation and soil information. In the remote sensing image analysis, the Normalized Difference Vegetation Index (NDVI) is used to assess vegetation health, as shown in the following formula:

[0023]

[0024] in:

[0025] NIR is the reflectance value in the near-infrared band;

[0026] RED is the reflectance value in the red light band;

[0027] NDVI is a vegetation assessment index. The closer the NDVI is to 1, the healthier the vegetation.

[0028] For soil moisture calculation, the modified Soil Modification Index (MADI) is used for assessment, as shown in the following formula:

[0029]

[0030] in:

[0031] NIR is the reflectance value in the near-infrared band;

[0032] SWIR is the reflectance value in the shortwave infrared band, used to distinguish between wet and dry soil;

[0033] Soil_Moisture_Sensor is the soil moisture measurement value of the ground sensor;

[0034] α and β are weighting coefficients used to adjust the ratio of remote sensing data to ground data.

[0035] Preferably, in the nutrient intelligent optimization system, soil health status is obtained from a remote sensing and machine vision monitoring and evaluation system, and nitrogen, phosphorus, and potassium in the soil are monitored in real time by sensors. The optimization objective is set to maintain the balance of nutrients in the soil, and nutrient optimization is performed using the Lagrange optimization formula.

[0036] L(N, P, K, λ)

[0037] =U(N, P, K) - λ(N) target -N)-λ(P target -P)-λ(K target -K)

[0038] in:

[0039] L(N, P, K, λ) is the Lagrangian function used to solve the nutrient optimization problem;

[0040] U(N, P, K) is the utility function for nutrient optimization, representing the effective utilization rate of nitrogen, phosphorus, and potassium in the soil;

[0041] λ is the Lagrange multiplier, used to solve nutrient optimization problems;

[0042] N, P, K represent the current nitrogen, phosphorus, and potassium content in the soil;

[0043] N target , P target K target This indicates the target content of each nutrient.

[0044] Preferably, in the aforementioned microbial community dynamic adjustment system, due to the dynamic evolution of the soil microbial community, the Lotka-Volterra competition model is used to describe the interaction between harmful and beneficial microorganisms, as shown in the following formula:

[0045]

[0046] in:

[0047] N1 represents the number of beneficial microorganisms;

[0048] N2 represents the number of harmful microorganisms;

[0049] r1 and r2 are the growth rates of beneficial and harmful microorganisms, representing the rate at which microorganisms reproduce in the current environment;

[0050] K1 and K2 represent the environmental carrying capacity of beneficial and harmful microorganisms, respectively, indicating the upper limit of the number of microbial communities that the soil can support;

[0051] α and β represent the competitive intensity between different microbial communities, reflecting the inhibition and competition relationships between them.

[0052] Preferably, the adaptive multi-energy management system adjusts soil moisture, temperature, and light intensity based on soil assessment data and environmental information, and optimizes energy allocation through a linear programming model, as shown in the following formula:

[0053] And 0≤P i ≤P i，max

[0054] And 0≤P i ≤P i，max

[0055] in:

[0056] C represents the total energy consumption of the system, indicating the cost of energy use;

[0057] P i Let i be the output power of the i-th energy source;

[0058] c i The unit energy cost for each type of energy source;

[0059] E demand Total energy demand for agricultural facilities;

[0060] P i , max This represents the maximum power output for each energy source.

[0061] Preferably, the blockchain-based traceable soil management system records each soil management operation on the blockchain as a transaction. In the blockchain, each soil management operation can be considered as a transaction, as shown in the following formula:

[0062] T i =ID i Time i Operation i Status i Data i

[0063] in:

[0064] T i This refers to the transaction information for the i-th soil management operation.

[0065] ID iIt serves as a unique identifier for operations, ensuring its immutability within the blockchain;

[0066] Time i Use the timestamp of the operation to record the execution time.

[0067] Operation i Specify the specific type of operation, indicating whether this management is fertilization, irrigation, or other operations;

[0068] Status i The status of the operation, including completed and incomplete;

[0069] Data i Detailed data related to the operation, including soil moisture and nutrient concentration.

[0070] Preferably, the system operation flow is as follows:

[0071] Sp1: Data Acquisition and Multi-Dimensional Monitoring: The remote sensing and machine vision monitoring and evaluation system uses drones or satellites to remotely monitor soil health and crop growth, and combines machine vision technology to evaluate soil surface conditions, vegetation growth, and early signs of pests and diseases to obtain data A.

[0072] Sp2: Dynamic monitoring and optimization of soil nutrients. The intelligent nutrient optimization system relies on soil nutrient information provided by remote sensing and real-time sensors, and dynamically adjusts the fertilization strategy through optimization formulas to obtain data B.

[0073] Sp3: Dynamic monitoring and adjustment of soil microbial community: The microbial community dynamic adjustment system acquires macroscopic assessment data and real-time nutrient data of the soil, analyzes the composition of the microbial community in the soil, and obtains data C;

[0074] Sp4: Soil health status assessment, the remote sensing and machine vision monitoring and assessment system generates a control plan based on the monitoring and analysis of data A, data B and data C using NDVI assessment of remote sensing image analysis;

[0075] Sp5: Multi-energy control and management of soil environment. The adaptive multi-energy management system allocates various renewable energy sources according to the control scheme obtained in Sp4 and the current energy demand and environmental status. It drives each energy source to automatically adjust fertilization, microbial adjustment and facility control strategies according to the analysis results, so as to carry out multi-energy control and management of soil environment.

[0076] SP6: The system's blockchain traceability and management, the blockchain-traceable soil management system records every operation such as fertilization, microbial adjustment, and environmental control on the blockchain, and the historical data in the blockchain provides a basis for AI nutrient optimization, dynamic microbial adjustment and facility management.

[0077] Preferably, the renewable energy in the adaptive multi-energy management system includes wind energy and solar energy, and wind energy and solar energy are generated through solar panels and wind turbines, respectively.

[0078] Preferably, the soil data collection in the intelligent nutrient optimization system includes soil sensors and a weather station, and the soil sensors include sensors for measuring nitrogen, phosphorus, and potassium content, while the weather station provides information on ambient temperature, humidity, and precipitation.

[0079] Beneficial effects

[0080] This invention provides a system for preventing continuous cropping obstacles in konjac and for soil improvement based on multi-factor analysis. It has the following beneficial effects:

[0081] 1. This invention employs UAV remote sensing, micro remote sensing technology, and machine vision technology in the remote sensing and machine vision monitoring and evaluation system. By using the NDVI vegetation index and MADI soil moisture index, combined with high-precision soil sensors, it monitors soil health in real time. It can accurately obtain data on soil moisture, nutrient distribution, and early signs of pests and diseases, enabling timely detection and intervention of soil degradation, excessive moisture, or nutrient imbalance during continuous cropping. Konjac has high requirements for soil, and this system can accurately determine the health status of the soil, helping to prevent yield decline caused by continuous cropping obstacles.

[0082] 2. This invention utilizes deep learning algorithms and Lagrange optimization models in the system, along with soil sensors and an intelligent nutrient optimization system, to monitor key nutrients such as nitrogen, phosphorus, and potassium in the soil in real time and dynamically adjust fertilization plans. This yields accurate data on soil nutrients and reasonable nutrient replenishment strategies, achieving a balanced supply of nutrients in the soil, avoiding over-fertilization or nutrient loss, maintaining long-term soil productivity, and ensuring stable soil nutrients during konjac cultivation, thus preventing nutrient imbalances caused by continuous cropping obstacles.

[0083] 3. This invention utilizes the Lotka-Volterra competition model and microbial community dynamic adjustment technology to analyze the dynamic balance of soil microorganisms, promote the growth of beneficial microorganisms, inhibit harmful microorganisms, and form a healthy microbial community structure within the soil. This reduces the proliferation of harmful pathogens and achieves effective prevention of diseases during continuous cropping. It also reduces disease outbreaks caused by the accumulation of pathogens in the soil. Since konjac is susceptible to diseases due to continuous cropping obstacles, optimizing the microbial structure can effectively prevent the accumulation of pathogens in the soil.

[0084] 4. This invention adopts an adaptive multi-energy management system and renewable energy technologies such as solar and wind power. Through linear programming optimization algorithms, it dynamically adjusts the temperature, humidity, light, and irrigation in the soil environment, so as to rationally allocate various energy sources, reduce the energy consumption of soil management, improve the controllability of the soil environment, save energy, and improve resource utilization. Since konjac continuous cropping requires stable environmental conditions, the system can automatically adjust according to demand to maintain suitable soil temperature and humidity levels and promote the healthy growth of konjac.

[0085] 5. This invention uses blockchain technology and a smart contract system to record each soil management operation on the blockchain, including the time, status, and related data of operations such as fertilization and irrigation. This makes the entire system's soil management and processing operations transparent and tamper-proof, ensuring the traceability of each soil management operation and guaranteeing transparency and security in the soil improvement and planting management process. Since long-term soil management is crucial for konjac cultivation, blockchain technology provides a reliable traceability mechanism for soil management, helping farmers track the soil's health history and reducing human error.

[0086] 6. This invention employs a comprehensive soil health assessment system and intelligent optimization system, combined with remote sensing monitoring, microbial regulation, intelligent fertilization, energy management, and other technologies to conduct refined soil management and long-term maintenance of soil health during konjac continuous cropping. This avoids common continuous cropping obstacles such as soil nutrient depletion and disease accumulation, ensuring high-yield stability during konjac continuous cropping, maintaining the soil's continuous production capacity, and effectively solving various soil-related problems in konjac continuous cropping. Through comprehensive prevention and dynamic management, it can effectively reduce the negative impacts of continuous cropping and improve overall yield and crop quality. Attached Figure Description

[0087] Figure 1 This is a system structure diagram of the present invention;

[0088] Figure 2 This is a flowchart illustrating the system operation of the present invention.

[0089] Figure 3 This is a comparison diagram of NDVI experiments in specific embodiment four of the present invention;

[0090] Figure 4 This is a comparison chart of yield experiments in a specific embodiment four of the present invention;

[0091] Figure 5 This is a comparison chart of energy consumption experiments in specific embodiment four of the present invention;

[0092] Figure 6A visualization of NDVI and MADI for the remote sensing and machine vision monitoring and evaluation system of the present invention;

[0093] Figure 7 A visualization chart of nutrient optimization calculations in the intelligent nutrient optimization system of the present invention;

[0094] Figure 8 A visualization of the Lotka-Volterra model of the microbial community dynamic adjustment system of the present invention;

[0095] Figure 9 This is a visualization chart of energy allocation in the adaptive multi-energy management system of the present invention;

[0096] Figure 10 This is a visualization chart of transaction records for the blockchain-based traceable soil management system of the present invention. Detailed Implementation

[0097] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. Specific Implementation Example 1:

[0099] like Figure 1-2 As shown, the konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis includes a nutrient intelligent optimization system, a microbial community dynamic adjustment system, a remote sensing and machine vision monitoring and evaluation system, an adaptive multi-functional management system, and a blockchain-based traceable soil management system.

[0100] Remote sensing and machine vision monitoring and assessment system: Utilizing UAV and satellite remote sensing technology, this system analyzes vegetation health using the NDVI vegetation index. Simultaneously, it combines machine vision technology to monitor soil moisture, nutrient distribution, and signs of pests and diseases in real time, providing an accurate soil health assessment. The system uses UAVs and satellite remote sensing for regional scanning to collect vegetation and soil information. In remote sensing image analysis, the Normalized Difference Vegetation Index (NDVI) is used to assess vegetation health, as shown in the following formula:

[0101]

[0102] in:

[0103] NIR is the reflectance value in the near-infrared band;

[0104] RED is the reflectance value in the red light band;

[0105] NDVI is a vegetation assessment index. The closer the NDVI is to 1, the healthier the vegetation.

[0106] For soil moisture calculation, the modified Soil Modification Index (MADI) is used for assessment, as shown in the following formula:

[0107]

[0108] in:

[0109] NIR is the reflectance value in the near-infrared band;

[0110] SWIR is the reflectance value in the shortwave infrared band, used to distinguish between wet and dry soil;

[0111] Soil_Moisture_Sensor is the soil moisture measurement value of the ground sensor;

[0112] α and β are weighting coefficients used to adjust the ratio of remote sensing data to ground data;

[0113] The intelligent nutrient optimization system receives macroscopic soil health data from remote sensing and machine vision monitoring and assessment systems. It monitors key nutrients like nitrogen, phosphorus, and potassium in the soil in real-time using sensors, and dynamically adjusts soil nutrients using deep learning algorithms. The system obtains soil health status data from remote sensing and machine vision monitoring and assessment systems, combines real-time sensor monitoring of nitrogen, phosphorus, and potassium, sets an optimization objective of maintaining nutrient balance in the soil, and optimizes nutrients using the Lagrange optimization formula.

[0114] L(N, P, K, λ)

[0115] =U(N, P, K) - λ(N) target -N)-λ(P target -P)-λ(K target -K)

[0116] in:

[0117] L(N, P, K, λ) is the Lagrangian function used to solve the nutrient optimization problem;

[0118] U(N, P, K) is the utility function for nutrient optimization, representing the effective utilization rate of nitrogen, phosphorus, and potassium in the soil;

[0119] λ is the Lagrange multiplier, used to solve nutrient optimization problems;

[0120] N, P, K represent the current nitrogen, phosphorus, and potassium content in the soil;

[0121] N target , P target K targetTo indicate the target content of each nutrient;

[0122] Microbial Community Dynamic Adjustment System: Based on soil assessment data from remote sensing and machine vision monitoring and evaluation systems and real-time monitoring data from intelligent nutrient optimization systems, this system analyzes the composition of soil microbial communities and employs the Lotka-Volterra competition model to describe the interaction between harmful and beneficial microorganisms. It monitors the structure of the soil microbial community in real time. Due to the dynamic evolution of the soil microbial community, the Lotka-Volterra competition model is used to describe the interaction between harmful and beneficial microorganisms, as shown in the following formula:

[0123]

[0124] in:

[0125] N1 represents the number of beneficial microorganisms;

[0126] N2 represents the number of harmful microorganisms;

[0127] r1 and r2 are the growth rates of beneficial and harmful microorganisms, representing the rate at which microorganisms reproduce in the current environment;

[0128] K1 and K2 represent the environmental carrying capacity of beneficial and harmful microorganisms, respectively, indicating the upper limit of the number of microbial communities that the soil can support;

[0129] α and β represent the intensity of competition between different microbial communities, reflecting the inhibitory and competitive relationships between them.

[0130] Adaptive Multi-Energy Management System: This system integrates and utilizes various renewable energy sources, combining feedback from remote sensing and machine vision monitoring and evaluation systems to dynamically adjust the soil environment, including temperature, humidity, light, and irrigation, thereby functionally controlling and regulating the soil environment.

[0131] The adaptive multi-energy management system, based on soil assessment data and environmental information, regulates soil moisture, temperature, and light intensity, and optimizes energy allocation through a linear programming model, as shown in the following formula:

[0132] And 0≤P i ≤P i，max

[0133] And 0≤P i ≤P i，max

[0134] in:

[0135] C represents the total energy consumption of the system, indicating the cost of energy use;

[0136] P i Let i be the output power of the i-th energy source;

[0137] c i The unit energy cost for each type of energy source;

[0138] E demand Total energy demand for agricultural facilities;

[0139] P i , max The power limit for each energy source;

[0140] Blockchain-based Traceable Soil Management System: This system utilizes blockchain technology to build a traceable system for soil management and crop production. Every soil treatment and crop health monitoring is recorded on the blockchain for transparent management. The system records each soil management operation as a transaction on the blockchain; each soil management operation can be considered a transaction, as shown in the following formula:

[0141] T i =ID i Time i Operation i Status i Data i

[0142] in:

[0143] T i This refers to the transaction information for the i-th soil management operation.

[0144] ID i It serves as a unique identifier for operations, ensuring its immutability within the blockchain;

[0145] Time i Use the timestamp of the operation to record the execution time.

[0146] Operation i Specify the specific type of operation, indicating whether this management is fertilization, irrigation, or other operations;

[0147] Status i The status of the operation, including completed and incomplete;

[0148] Data i Detailed data related to the operation, including soil moisture and nutrient concentration.

[0149] The aforementioned system integrates advanced sensors, AI algorithms, IoT, blockchain and other technologies to achieve comprehensive monitoring and management of soil during konjac cultivation. From preventing continuous cropping obstacles to dynamically optimizing soil health, the various systems work together to form an intelligent closed-loop management system. Specific Implementation Example 2:

[0151] like Figure 1-2 As shown, based on the content of the above specific embodiments, the following technical contents are further disclosed:

[0152] In remote sensing and machine vision monitoring and evaluation systems, equipment control is achieved through drones, satellite remote sensing devices, and ground sensors. Drones are equipped with multispectral or hyperspectral cameras for near-infrared (NIR), red (RED), and short-wave infrared (SWIR) data acquisition. Satellite remote sensing devices acquire macroscopic images of the area from satellites for long-term soil and vegetation health monitoring. Ground sensors, such as soil moisture sensors, collect humidity data in real time and upload it to a data center. Utilizing drone and satellite remote sensing technologies, multispectral images of the field surface are periodically captured, and the acquired images are uploaded to a central processing system. The system uses the NDVI formula to assess vegetation health, and then calculates soil moisture distribution by combining the improved Soil Conditioning Index (MDVI) with sensor data. Ground sensor data is transmitted to the system via the Internet of Things (IoT) to provide accurate moisture monitoring. Combined with machine vision technology, the system takes real-time pictures of crop leaves and stems, and analyzes the images using AI algorithms to detect early signs of pests and diseases. This enables timely detection and intervention of soil degradation, excessive moisture, or nutrient imbalance during continuous cropping. Konjac has high soil requirements, and this system can accurately determine the soil health status, helping to prevent yield decline caused by continuous cropping obstacles.

[0153] The equipment used in the remote sensing and machine vision monitoring and evaluation system further includes the following:

[0154] Unmanned aerial vehicle (UAV) multispectral camera: used for data acquisition in multiple bands such as near-infrared and red light;

[0155] Satellite image processing system: used for macroscopic assessment;

[0156] Internet of Things (IoT) sensor networks: monitoring key parameters such as soil moisture and temperature;

[0157] AI vision algorithms: used for early identification of pests and diseases;

[0158] Cloud computing platforms: centrally process and store massive amounts of data.

[0159] The nutrient intelligent optimization system collects soil data through soil sensors and a weather station. The soil sensors measure nitrogen, phosphorus, and potassium content, while the weather station provides information on ambient temperature, humidity, and precipitation. The soil sensors measure nitrogen, phosphorus, and potassium content and upload the data to an intelligent analysis platform in real time. The system obtains the overall health status of the soil from remote sensing and machine vision monitoring systems. Using the Lagrange optimization algorithm, the system calculates the soil nutrient balance based on the N, P, and K data collected by the sensors. The deep learning model predicts future nutrient requirements based on historical data and current soil conditions, optimizes fertilization plans, connects to automated fertilization equipment, and applies fertilizer precisely according to the optimized nutrient requirements.

[0160] The microbial community dynamic adjustment system uses soil sampling equipment to collect soil samples regularly, analyzes the microbial community, uses high-throughput sequencers to analyze the genetic information of microorganisms in the soil to determine the microbial community structure, obtains physical and chemical state data of the soil from remote sensing and machine vision monitoring systems and nutrient optimization systems, uses the Lotka-Volterra competition model to describe the interactions between microorganisms, calculates the dynamic balance between beneficial and harmful microorganisms, and promotes the growth of beneficial microorganisms and inhibits harmful microorganisms by controlling soil nutrient supply, humidity, temperature and other parameters.

[0161] The adaptive multi-energy management system incorporates renewable energy sources including wind and solar power. Wind and solar power are generated through solar panels and wind turbines, respectively. Intelligent controllers regulate soil moisture, temperature, and irrigation conditions. Remote sensing and machine vision systems monitor soil moisture, temperature, and light conditions in real time. Current energy consumption and environmental parameters are obtained from a sensor network. Linear programming algorithms are used to calculate the optimal allocation of various energy sources. Temperature control equipment and irrigation systems are adjusted based on real-time soil parameters to ensure the stability of the soil environment.

[0162] The blockchain-based traceable soil management system uses blockchain node devices to record soil management operations and data. Encryption modules ensure the security of data during transmission and storage. Each soil operation, such as fertilization or irrigation, is recorded as a transaction. Operation data, such as soil moisture and nutrient concentration, are uploaded in real time via sensors. All operation records are stored in the blockchain network and can be viewed and audited by relevant parties. Specific Implementation Example 3:

[0164] like Figure 1-2 As shown, based on the content of the above specific embodiments, the following technical contents are further disclosed:

[0165] The system's operation process is as follows:

[0166] Sp1: Data Acquisition and Multi-Dimensional Monitoring: The remote sensing and machine vision monitoring and evaluation system uses drones or satellites to remotely monitor soil health and crop growth, combined with machine vision technology to assess soil surface conditions, vegetation growth, and early signs of pests and diseases, obtaining data A.

[0167] Sp2: Dynamic monitoring and optimization of soil nutrients. The intelligent nutrient optimization system relies on soil nutrient information provided by remote sensing and real-time sensors. It dynamically adjusts the fertilization strategy through optimization formulas to obtain data B. Based on the collected data such as soil nutrients, humidity, and temperature, artificial intelligence algorithms analyze the current needs of crops and adjust the amount and frequency of nutrient application. Its core goal is to ensure the nutrient balance in the soil and avoid excessive consumption or accumulation of nutrients, thereby reducing continuous cropping obstacles. Nutrient application affects the activity of the microbial community. The system will adjust the fertilization strategy based on the feedback of the microorganisms to avoid microbial ecological imbalance. The soil health status monitored by remote sensing and machine vision serves as the basis for AI to adjust the amount of fertilizer.

[0168] Sp3: Dynamic monitoring and adjustment of soil microbial community: The microbial community dynamic adjustment system acquires macroscopic assessment data and real-time nutrient data of the soil, analyzes the composition of the microbial community in the soil, and obtains data C;

[0169] Sp4: Soil health assessment. The remote sensing and machine vision monitoring and assessment system uses NDVI assessment based on the monitoring and analysis of data A, B, and C to generate control plans. The NDVI remote sensing index reflects the crop growth status and determines whether there is poor growth due to soil problems. Machine vision is used to detect changes in soil surface structure, color, and moisture to predict potential soil degradation or nutrient loss. The remote sensing data is provided to the AI ​​nutrient optimization system and microbial adjustment system as feedback information to adjust nutrient application and microbial regulation strategies.

[0170] Sp5: Multi-energy control and management of soil environment. The adaptive multi-energy management system allocates various renewable energy sources based on the control scheme obtained in Sp4 and the current energy demand and environmental conditions. It drives each energy source to automatically adjust fertilization, microbial adjustment and facility control strategies according to the analysis results, and conducts multi-energy control and management of soil environment. It adjusts light, temperature, humidity and irrigation according to real-time data to provide suitable crop growth conditions. Environmental control will indirectly affect the microbial community in the soil. Suitable temperature and humidity conditions will promote the reproduction of beneficial microorganisms and inhibit the spread of harmful microorganisms. By adaptively adjusting energy consumption, it maximizes the use of natural resources and ensures the efficient and low-carbon operation of agricultural equipment.

[0171] SP6: The system's blockchain traceability and management. The blockchain-traceable soil management system records every operation such as fertilization, microbial adjustment, and environmental control on the blockchain. The historical data in the blockchain provides a basis for AI nutrient optimization, dynamic microbial adjustment, and facility management. The system records all details about soil improvement, energy allocation, and nutrient application, making it convenient to track changes in soil health and the effects of each operation in the future.

[0172] By employing a comprehensive soil health assessment system and intelligent optimization system, combined with remote sensing monitoring, microbial regulation, intelligent fertilization, energy management and other technologies, the soil is managed in a refined manner. This ensures long-term maintenance of soil health during konjac continuous cropping, avoiding common problems such as soil nutrient depletion and disease accumulation. It guarantees high-yield stability during konjac continuous cropping, maintains the soil's continuous production capacity, and effectively solves various soil-related problems in konjac continuous cropping. Through comprehensive prevention and dynamic management, the negative impacts of continuous cropping can be effectively reduced, and overall yield and crop quality can be improved. Specific Implementation Example 4:

[0174] like Figure 1-5 As shown, based on the content of the above specific embodiments, the following technical contents are further disclosed:

[0175] Based on the above embodiments, the system's soil improvement effect during konjac continuous cropping was demonstrated, verifying the application effect of the core technology of this system model in konjac continuous cropping. This system will be referred to as the new system below. Experimental data are as follows:

[0176] 1. Experimental objective: To verify the effectiveness of the new system in preventing continuous cropping obstacles and soil improvement, and to compare its differences with existing traditional soil improvement systems;

[0177] 2. Experimental comparison system:

[0178] The new system includes a remote sensing and machine vision monitoring and evaluation system, a nutrient intelligent optimization system, a microbial community dynamic adjustment system, an adaptive multi-functional management system, and a blockchain-based traceable soil management system.

[0179] Traditional systems are based on conventional soil management and monitoring technologies, mainly including basic soil testing and improvement methods such as fertilization, irrigation, and physical remediation techniques, without the intervention of IoT and machine learning optimization algorithms;

[0180] 3. Experimental location: Select farmland where konjac has been continuously planted, as long-term planting may lead to the risk of continuous cropping obstacles, and the experimental results will be more significant;

[0181] 4. Experimental Samples: The experimental fields were divided into two groups, managed using the new system and the traditional system respectively. The soil properties of each group of fields, such as nutrient content, pH value, and moisture, were basically the same, and they were randomly assigned to avoid human interference.

[0182] 5. Experimental steps:

[0183] Data collection: Before the experiment began, initial soil data of the experimental field was collected using drones, satellite remote sensing technology and ground sensors, including information on humidity, nutrient distribution, microbial community structure, signs of pests and diseases, etc.

[0184] Traditional system group: Remediation and improvement are carried out according to traditional soil management practices, including regular fertilization and irrigation, without further monitoring and dynamic adjustments;

[0185] New System Group: Using the new system for comprehensive soil monitoring and optimization, specific steps include:

[0186] Sp1: Remote sensing and machine vision monitoring: Collect information on soil moisture, nutrient distribution, vegetation health and pests and diseases weekly, and analyze soil health status;

[0187] Sp2: Intelligent Nutrient Optimization: Combining deep learning algorithms, it adjusts key nutrients such as nitrogen, phosphorus, and potassium in the soil in real time based on monitoring data;

[0188] Sp3: Dynamic adjustment of microbial community: Real-time monitoring of beneficial and harmful microorganisms in the soil, and dynamic balance of the microbial community through the Lotka-Volterra model;

[0189] Sp4: Adaptive Multi-functional Management: Optimizes irrigation and environmental conditions such as soil moisture and temperature based on monitoring data;

[0190] SP5: Blockchain Management: Records each soil management operation and its results.

[0191] Experimental period: The entire experimental period was set for two growing seasons, totaling 18 months. Soil health status, konjac growth, yield, and disease status were recorded for each period.

[0192] 6. Experimental Results and Analysis:

[0193] 1) Soil health

[0194] New system group: Remote sensing monitoring shows that the NDVI value remains between 0.8 and 0.9 throughout the growing season, indicating good vegetation health. The combination of MADI index and ground sensor data shows that soil moisture is maintained within the optimal range of 20%-25%, nutrients are evenly distributed, the microbial community structure tends to be stable, and soil health is significantly improved.

[0195] Traditional system group: NDVI values ​​fluctuate greatly, between 0.6 and 0.7, indicating that the vegetation health in some areas is poor, soil moisture is sometimes too high or too low, fertilization and irrigation lack precise control, and the microbial community is prone to adverse changes.

[0196] 2) Nutrient utilization rate

[0197] New system group: Through Lagrange optimization, the utilization rate of nitrogen, phosphorus and potassium in the soil is significantly improved, the nutrient balance is maintained and unnecessary fertilization costs are reduced;

[0198] Traditional system group: Due to the lack of intelligent optimization, soil nutrients are often insufficient or excessive, resulting in low nutrient utilization efficiency;

[0199] 3) Microbial community structure

[0200] The new system group: real-time monitoring and dynamic adjustment effectively inhibited the excessive reproduction of harmful microorganisms, promoted the growth of beneficial microbial communities, and made the soil ecosystem more stable;

[0201] Traditional systems: The structure of the microbial community is greatly affected by seasonal and environmental changes, and the problem of harmful microorganisms often occurs.

[0202] 4) Konjac yield

[0203] New system group: The average yield of konjac per hectare increased by 15%-20%, pests and diseases decreased, and crop quality also improved;

[0204] Traditional system group: Konjac yield fluctuates greatly, is susceptible to pests and diseases, and has a lower overall yield than the new system;

[0205] 5) Disease control

[0206] The new system group: uses machine vision and remote sensing technology to identify signs of pests and diseases at an early stage, and takes timely and targeted measures to effectively prevent the large-scale spread of diseases;

[0207] Traditional system group: Disease and pest monitoring is lagging behind, and treatment is often only carried out when diseases appear, resulting in crop damage in some areas;

[0208] 6) Resource utilization efficiency

[0209] New system group: The adaptive multi-energy management system optimizes the use of water, fertilizer and energy, reduces resource waste, and optimizes energy allocation through a linear programming model, reducing overall energy consumption costs by about 10%-15%.

[0210] Traditional systems often lack optimized resource utilization, resulting in over- or under-irrigation, leading to resource waste and increased energy consumption.

[0211] The experimental results are as follows Figure 3-5 As shown:

[0212] against Figure 3 An NDVI comparison was conducted, i.e., a health index comparison was prepared. As shown in the chart, the NDVI value of the traditional system was between 0.64 and 0.70, showing a relatively stable but low level of vegetation health. The NDVI value of the new system was significantly higher, maintained between 0.85 and 0.90, indicating a significant improvement in vegetation health.

[0213] against Figure 4 A comparison of yields per hectare was conducted. As shown in the chart, the yield of the traditional system fluctuated between approximately 3300 and 3600 kg / ha, while the yield under the new system was significantly improved and stabilized between 4000 and 4250 kg / ha. This indicates that the new improved system helps to increase the yield of konjac cultivation.

[0214] against Figure 5 A comparison of energy consumption was conducted, with the unit being kWh. As shown in the chart, the energy consumption of the traditional system fluctuated between 195 and 215 kWh, while the energy consumption of the new system was significantly reduced, remaining between 170 and 190 kWh, demonstrating higher energy utilization efficiency.

[0215] 7. Summary and Analysis:

[0216] Comparative experiments show that the konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis exhibits significant technical advantages in the following aspects:

[0217] 1) Intelligentization and Automation: The new system achieves real-time and accurate soil monitoring and management through technologies such as drones, sensors, and deep learning, which greatly reduces manual intervention and improves efficiency;

[0218] 2) Nutrient optimization: Through the intelligent nutrient optimization system, the new system can maintain the dynamic balance of soil nutrients, significantly improve nutrient utilization, and reduce fertilizer waste and environmental pollution;

[0219] 3) Microbial balance: The dynamic adjustment system of the microbial community effectively regulates the competition between beneficial and harmful microorganisms, maintains the health of the soil ecosystem, and reduces the occurrence of diseases;

[0220] 4) Energy consumption and resource efficiency: The adaptive multi-energy management system optimizes the use of energy and water resources and reduces operating costs by intelligently regulating temperature, humidity and irrigation;

[0221] 5) Early warning of pests and diseases: Machine vision technology can detect signs of pests and diseases in a timely manner. Combined with the traceability function of blockchain, the new system improves the transparency and traceability of pest and disease management.

[0222] 6) Sustainability: The new system integrates multiple advanced technologies to provide a sustainable soil management solution for konjac intercropping, extending the lifespan of the soil and increasing the sustainability of the planting.

[0223] These technical features and experimental results fully demonstrate that the new system, through the integration of multiple technologies such as remote sensing, AI optimization, and microbial adjustment, effectively improves the vegetation health index, increases crop yield, and significantly reduces energy consumption. This indicates that the new system has significant advantages in preventing konjac continuous cropping obstacles and improving soil, especially in terms of environmental sustainability and production efficiency. The new system has significant advantages in preventing konjac continuous cropping obstacles and improving soil health, and can provide strong support for the sustainable development of konjac cultivation. Specific Implementation Example 5:

[0225] like Figure 1-10 As shown, based on the content of the above specific embodiments, the following technical contents are further disclosed:

[0226] like Figure 6 As shown, NDVI and MADI are simulated and calculated for the remote sensing and machine vision monitoring and evaluation system. The health status of vegetation is calculated by the reflectance values ​​of the near-infrared band and the red light band. The closer the NDVI value is to 1, the healthier the vegetation is. Combined with the humidity data of the near-infrared band, the short-wave infrared band and the ground sensor, the soil moisture is comprehensively evaluated. This index is used to more accurately reflect the degree of soil moisture.

[0227] like Figure 7 As shown, the nutrient optimization calculation of the intelligent nutrient optimization system is visualized. Through Lagrange optimization, the nitrogen, phosphorus, and potassium in the soil are optimized. Based on the difference between the current nutrient content and the target content, it is determined whether the nutrient distribution needs to be adjusted to maintain the balance of soil nutrients.

[0228] like Figure 8As shown, the Lotka-Volterra model of the microbial community dynamic adjustment system is visualized. The Lotka-Volterra model is used to describe the competitive relationship between beneficial and harmful microorganisms. Through dynamic simulation, the changing trend of the microbial community can be understood and corresponding adjustments can be made.

[0229] like Figure 9 As shown, the energy allocation optimization of the adaptive multi-energy management system is visualized. A linear programming model is used to optimize the allocation of various renewable energy sources to ensure that agricultural facilities achieve the minimum energy cost while meeting energy needs.

[0230] like Figure 10 As shown, a visualization of the transaction record simulation of the blockchain-traceable soil management system is presented. By simulating the transaction structure of the blockchain, each soil management operation is recorded as a transaction, including timestamp, operation type and operation data, thus enabling transparent tracking of soil management.

[0231] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a reference structure" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0232] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A system for preventing continuous cropping obstacles of konjac and improving soil based on multi-factor analysis, characterized in that: The system includes a nutrient intelligent optimization system, a microbial community dynamic adjustment system, a remote sensing and machine vision monitoring and evaluation system, an adaptive multi-functional management system, and a blockchain-based traceable soil management system, wherein: The remote sensing and machine vision monitoring and evaluation system utilizes UAV and satellite remote sensing technology to analyze vegetation health through the NDVI vegetation index. Simultaneously, it combines machine vision technology to monitor soil moisture, nutrient distribution, and signs of pests and diseases in real time, providing an accurate soil health assessment. In this system, UAVs and satellite remote sensing are used for regional scanning to collect vegetation and soil information. In the remote sensing image analysis, the Normalized Difference Vegetation Index (NDVI) is used to assess vegetation health, as shown in the following formula: ； in: This refers to the reflectance value in the near-infrared band. This represents the reflectance value in the red light band. For vegetation assessment index, The closer to 1, the healthier the vegetation. For soil moisture calculation, the modified Soil Modification Index (MADI) is used for assessment, as shown in the following formula: ； in: This refers to the reflectance value in the near-infrared band. This is the reflectance value in the shortwave infrared band, used to distinguish between wet and dry soil; This refers to the soil moisture measurement value from the ground sensor; These are weighting coefficients used to adjust the ratio of remote sensing data to ground data. The intelligent nutrient optimization system receives macroscopic soil health status data from a remote sensing and machine vision monitoring and evaluation system. It monitors key nutrients (nitrogen, phosphorus, and potassium) in the soil in real-time using sensors and dynamically adjusts soil nutrients using deep learning algorithms. Specifically, the system acquires soil health status data from the remote sensing and machine vision monitoring and evaluation system, combines real-time sensor monitoring of nitrogen, phosphorus, and potassium levels, sets an optimization objective of maintaining nutrient balance in the soil, and optimizes nutrients using the Lagrange optimization formula. ； in: is the Lagrangian function used to solve nutrient optimization problems; The utility function for nutrient optimization represents the effective utilization rate of nitrogen, phosphorus, and potassium in the soil; where is the Lagrange multiplier, used to solve nutrient optimization problems; This represents the current nitrogen, phosphorus, and potassium content in the soil; To indicate the target content of each nutrient; The microbial community dynamic adjustment system is based on soil assessment data from the remote sensing and machine vision monitoring and evaluation system and real-time monitoring data from the nutrient intelligent optimization system. It analyzes the composition of the microbial community in the soil, uses the Lotka-Volterra competition model to describe the interaction between harmful and beneficial microorganisms, and monitors the structure of the microbial community in the soil in real time. The adaptive multi-energy management system integrates and utilizes various renewable energy sources, and dynamically adjusts the soil environment, including temperature, humidity, light, and irrigation, based on feedback from remote sensing and machine vision monitoring and evaluation systems, thereby performing functional and control regulation of the soil environment. The blockchain-based traceable soil management system utilizes blockchain technology to build a traceable system for soil management and crop production, recording each soil treatment and crop health monitoring on the blockchain for transparent management.

2. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: In the aforementioned microbial community dynamic adjustment system, due to the dynamic evolution of the soil microbial community, the Lotka-Volterra competition model is used to describe the interaction between harmful and beneficial microorganisms, as shown in the following formula: ； ； in: The number of beneficial microorganisms; The number of harmful microorganisms; The growth rate of beneficial and harmful microorganisms represents the rate at which microorganisms reproduce in the current environment; These represent the environmental carrying capacity for beneficial and harmful microorganisms, respectively, indicating the upper limit of the number of microbial communities that the soil can support; The intensity of competition among different microbial communities reflects the inhibitory and competitive relationships between them.

3. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: The adaptive multi-energy management system, based on soil assessment data and environmental information, regulates soil moisture, temperature, and light intensity, and optimizes energy allocation through a linear programming model, as shown in the following formula: ； ； in: The total energy consumption of the system represents the cost of energy use; For the first The output power of this energy source; The unit energy cost for each type of energy source; Total energy demand for agricultural facilities; This represents the maximum power output for each energy source.

4. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: The blockchain-based traceable soil management system records each soil management operation as a transaction on the blockchain. Each soil management operation can be considered a transaction on the blockchain, as shown in the following formula: ； in: For the first Transaction information for soil management operations; It serves as a unique identifier for operations, ensuring its immutability within the blockchain; Use the timestamp of the operation to record the execution time. Specify the specific type of operation, indicating whether this management is fertilization, irrigation, or other operations; The status of the operation, including completed and incomplete; Detailed data related to the operation, including soil moisture and nutrient concentration.

5. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: The system's operation flow is as follows: Sp1: Data Acquisition and Multi-Dimensional Monitoring: The remote sensing and machine vision monitoring and evaluation system uses drones or satellites to remotely monitor soil health and crop growth, and combines machine vision technology to evaluate soil surface conditions, vegetation growth, and early signs of pests and diseases to obtain data A. Sp2: Dynamic monitoring and optimization of soil nutrients. The intelligent nutrient optimization system relies on soil nutrient information provided by remote sensing and real-time sensors, and dynamically adjusts the fertilization strategy through optimization formulas to obtain data B. Sp3: Dynamic monitoring and adjustment of soil microbial community: The microbial community dynamic adjustment system acquires macroscopic assessment data and real-time nutrient data of the soil, analyzes the composition of the microbial community in the soil, and obtains data C; Sp4: Soil health status assessment, the remote sensing and machine vision monitoring and assessment system generates a control plan based on the monitoring and analysis of data A, data B and data C using NDVI assessment of remote sensing image analysis; Sp5: Multi-energy control and management of soil environment. The adaptive multi-energy management system allocates various renewable energy sources according to the control scheme obtained in Sp4 and the current energy demand and environmental status. It drives each energy source to automatically adjust fertilization, microbial adjustment and facility control strategies according to the analysis results, so as to carry out multi-energy control and management of soil environment. SP6: The system's blockchain traceability and management, the blockchain-traceable soil management system records every fertilization, microbial adjustment, and environmental control operation on the blockchain, and the historical data in the blockchain provides a basis for AI nutrient optimization, dynamic microbial adjustment and facility management.

6. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: The adaptive multi-energy management system includes renewable energy sources such as wind and solar energy, which are generated through solar panels and wind turbines, respectively.

7. The konjac continuous cropping obstacle prevention and soil improvement system based on multi-factor analysis according to claim 1, characterized in that: The soil data collection in the intelligent nutrient optimization system includes soil sensors and a weather station. The soil sensors include sensors that measure the content of nitrogen, phosphorus, and potassium, and the weather station provides information on ambient temperature, humidity, and precipitation.

Images