Soil microorganism analysis method based on digital twinning

Abstract

The invention relates to the field of soil microbiological analysis, in particular to a soil microbiological analysis method based on digital twinning. Comprising the following steps: acquiring soil environment data and data of different microbial populations in soil in real time, inputting the soil environment data and the microbial population data into a soil microbial virtual model constructed by a digital twin technology, simulating an evolution process of a microbial community through a dynamic equation, and dynamically predicting the number of microbial populations; on the basis of the soil environment data and the predicted microbial population number, a microbial health index is calculated through a microbial health index calculation algorithm; and based on the microbial health index, selecting an optimal microbial management operation scheme through an adaptive evolution optimal operation selection model. The technical problem that an existing soil microorganism analysis method neglects the mutual relation between microorganism populations and possibly causes inaccurate prediction of the change trend of the microorganism populations is solved.

Description

Technical Field

[0001] The present invention relates to the field of soil microorganism analysis, and particularly to a soil microorganism analysis method based on digital twin. Background Art

[0002] Soil microorganisms, as an important part of the soil ecosystem, play a crucial role in crop growth, soil health, and ecological balance. However, traditional soil microorganism analysis methods have various limitations, such as difficult sample acquisition, long detection time, and weak data dynamics, making it difficult to meet the needs of the rapid development of modern agriculture.

[0003] Digital twin, as an advanced technology that combines physical entities and virtual models, provides a new approach for the monitoring, simulation, and optimization of complex systems through the transmission and two-way interaction of real-time data. Introducing digital twin technology into the field of soil microorganism analysis, the soil microorganism analysis method based on digital twin can not only provide more accurate decision-making support for agricultural producers but also offer new technical means for scientific research institutions to conduct ecosystem research and soil health assessment. In precision agriculture, the digital twin model can monitor the activity level of soil microorganisms in real time, guiding the timing and dosage of farmland fertilization, irrigation, and other operations, thereby improving the yield and quality of crops; in the field of ecological protection, the digital twin model can monitor the impact of soil pollution on microbial communities and evaluate the effectiveness of treatment measures; in environmental climate change research, the digital twin model can dynamically record the response of soil microorganisms to climate variables, providing fine data support for global carbon cycle and greenhouse gas emission models.

[0004] The soil microorganism analysis method based on digital twin provides a new technical approach for the dynamic monitoring, function prediction, and management optimization of soil microbial communities by closely integrating the virtual and the real. Compared with traditional methods, it not only greatly improves the efficiency of data collection and analysis but also can capture the complex dynamic changes of soil microorganisms in real time, providing strong support for the sustainable development of modern agriculture and ecological environment protection.

[0005] However, the existing soil microorganism analysis methods have the following technical problems: Traditional soil microorganism population analysis often relies on static data or intermittent sampling, lacking dynamics and being unable to predict the changes in soil microorganism populations in real time, resulting in the inability to respond promptly to the impact of environmental changes on microbial communities; Most existing soil microorganism analysis methods ignore the mutual relationships (such as competition and symbiosis) between microorganism populations, which may lead to inaccurate prediction of the change trends of microorganism populations; The dynamic impact of the soil environment on the growth of microorganisms is ignored, and it is impossible to effectively quantify the effects of soil environmental factors (such as soil temperature, humidity, and pH) on the growth rate of microorganism populations, resulting in the inability to dynamically adjust microorganism analysis according to soil conditions. Summary of the Invention

[0006] The present invention provides a method for soil microorganism analysis based on digital twin to solve the problems that traditional soil microorganism population analysis often relies on static data or intermittent sampling, lacks dynamics, and cannot predict the changes in soil microorganism populations in real time, resulting in the inability to respond in a timely manner to the impact of environmental changes on the microbial community; most existing soil microorganism analysis methods ignore the interactions (such as competition and symbiosis) between microorganism populations, which may lead to inaccurate prediction of the changing trends of microorganism populations; and the dynamic impact of the soil environment on the growth of microorganisms is ignored, and the effects of soil environmental factors (such as soil temperature, humidity, and pH) on the growth rate of microorganism populations cannot be effectively quantified, resulting in the inability to dynamically adjust microorganism analysis according to soil conditions.

[0007] The method for soil microorganism analysis based on digital twin of the present invention specifically includes the following technical solutions:

[0008] The method for soil microorganism analysis based on digital twin includes the following steps:

[0009] S1: Real-time obtain soil environmental data and data of different microorganism populations in the soil, input the soil environmental data and microorganism population data into a soil microorganism virtual model constructed by digital twin technology, simulate the evolution process of the microbial community through dynamic equations, and dynamically predict the number of microorganism populations.

[0010] S2: Based on the soil environmental data and the predicted number of microorganism populations, calculate the microorganism health index through a microorganism health index calculation algorithm.

[0011] S3: Based on the microorganism health index, select the best microorganism management operation plan through an adaptive evolution optimal operation selection model.

[0012] Preferably, S1 specifically includes:

[0013] The soil microorganism virtual model constructed by digital twin technology combines the self-growth of microorganism populations and the interactions between different microorganism populations. The self-growth of microorganism populations means that each microorganism reproduces according to its growth rate without external interference.

[0014] Preferably, S1 specifically includes:

[0015] Introduce the interactions between microorganism populations, including competition and symbiosis. There is a symbiotic relationship between different microorganism populations, and their growth can be accelerated with mutual help; at the same time, there is also a competitive relationship. Under the condition of insufficient resources, different types of microorganisms will compete, and the competition for resources will inhibit the growth of microorganisms.

[0016] Preferably, the S1 specifically includes:

[0017] The calculation formula for predicting the microbial population quantity is:

[0018]

[0019] where, M i (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; M i (t) represents the quantity of the i-th microbial population at time t; Δt represents the predicted time step, that is, the time difference from time t to t + Δt; α represents the adjustment coefficient; ∑ k represents the summation of the impacts of all soil environmental data; S k (t) represents the k-th soil environmental data at time t; represents the maximum value of the k-th soil environmental data at time t; represents the change rate of the i-th microbial population quantity at time t, that is, the change trend of the microbial population.

[0020] Preferably, the S2 specifically includes:

[0021] The calculation algorithm of the microbial health index adjusts the impact on the microbial health index by introducing the basic coefficient of the microbial population on the microbial health index and the weighted index of the microbial population on the microbial health index, and obtains the microbial health index.

[0022] Preferably, the S2 specifically includes:

[0023] The calculation formula of the microbial health index is:

[0024]

[0025] where, Q(t + Δt) represents the microbial health index at time t + Δt; ∑ i represents the summation of the contributions of all microbial populations to the microbial health index; M i (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; γ i represents the basic coefficient of the i-th microbial population on the microbial health index; θ i represents the weighted index of the i-th microbial population on the microbial health index; represents the exponential decay factor of the impact of soil environmental data on microorganisms; S k (t) represents the k-th soil environmental data at time t; δ i represents the sensitivity coefficient of the i-th microbial population to the soil environment.

[0026] Preferably, the S3 specifically includes:

[0027] The adaptive evolutionary optimal operation selection model obtains new microbial health index information and makes real-time optimization adjustments to the microbial management operation plan. When the microbial health index is extremely low, fertilization will be increased to improve the soil condition; when the health index is too high, the corresponding operation amount will be reduced.

[0028] Preferably, S3 specifically includes:

[0029] The adaptive evolutionary optimal operation selection model introduces a feedback mechanism and combines a feedback adjustment factor to obtain the optimized best microbial management operation plan. The specific implementation formula is:

[0030]

[0031] Among them, O opt represents the optimized best microbial management operation plan; O l represents the l-th microbial management operation; Q(t + Δt) represents the microbial health index at time t + Δt; μ represents the feedback adjustment factor; ρ kl represents the response degree of the k-th soil environmental data to the l-th microbial management operation; C l represents the cost of the l-th microbial management operation; λ represents the cost adjustment coefficient.

[0032] The beneficial effects of the technical solution of the present invention are:

[0033] 1. By using sensors and high-throughput sequencing technology to obtain soil environmental data and microbial population data in real time, and combining digital twin technology to construct a soil microbial virtual model, the dynamic prediction of the microbial community is realized. By simulating the competition and symbiosis of microbial populations through dynamic equations, the change of microbial population quantity over time can be accurately predicted, providing accurate data support for the real-time monitoring of soil health and microbial management, and promoting scientific soil microbial analysis and management.

[0034] 2. Using the real-time obtained soil environmental data and microbial population quantity, through the microbial health index calculation algorithm, the microbial health index can be dynamically calculated. The microbial health index takes into account the comprehensive influence of the quantity, characteristics of the microbial population and soil environmental factors. Especially through the design of weighted sum and exponential decay factor, the calculation of the microbial health index is accurate, which can reflect the actual health status of the soil microbial community, providing an effective basis for formulating reasonable measures to optimize the soil microbial environment.

[0035] 3. Based on the microbial health index, through the adaptive evolution optimal operation selection model, the operation plan can be dynamically adjusted according to the change of the microbial health index. When the microbial health index is low, fertilization and irrigation operations can be adjusted in real time. When the microbial health index is too high, the corresponding operations can be reduced to avoid over-intervention, optimizing the microbial analysis and management effect, improving the flexibility and accuracy of operations, and saving resources and costs.

[0036] 4. With the real-time calculation and feedback mechanism of digital twin technology, by continuously updating the microbial health index and the number of microbial populations, automated microbial health assessment and operation optimization can be achieved, thus reducing manual intervention. The data-driven automated decision-making method improves the efficiency and accuracy of decision-making, avoiding human errors and lag in traditional methods.

[0037] 5. The combination of digital twin technology and the analysis method of microbial communities provides accurate data support for intelligent agriculture. Through the real-time monitoring and prediction of soil microorganisms, decision-making support can be provided for agricultural production, promoting the development of precision agriculture, and maintaining the stability of soil microbial health under changing environmental conditions, thereby improving the yield and quality of crops. Brief Description of the Drawings

[0038] Figure 1 It is a flowchart of the method for analyzing soil microorganisms based on digital twin according to the present invention. Detailed Embodiments

[0039] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0041] The following specifically describes the specific solution of the method for analyzing soil microorganisms based on digital twin provided by the present invention with reference to the accompanying drawings.

[0042] Refer to the attached Figure 1 , which shows a flowchart of the method for analyzing soil microorganisms based on digital twin provided by an embodiment of the present invention. The method includes the following steps:

[0043] S1. Obtain soil environmental data and data on different microbial populations in the soil in real time, input the soil environmental data and microbial population data into a soil microbial virtual model constructed by digital twin technology, simulate the evolution process of the microbial community through dynamic equations, and dynamically predict the number of microbial populations;

[0044] Obtain soil environmental data in real time through sensors, such as soil temperature, soil humidity, and soil pH; obtain data on different microbial populations in the soil in real time through high-throughput sequencing technology, such as the number of microbial populations; input the soil environmental data and microbial population data into a soil microbial virtual model constructed by digital twin technology, and calculate the change trend of the microbial population in real time, thereby dynamically predicting the number of microbial populations;

[0045] The soil microbial virtual model constructed by digital twin technology not only considers the self-growth of microbial populations, but also considers the interactions between different microbial populations, including competition and symbiosis;

[0046] The self-growth of the microbial population means that each microorganism reproduces according to a specific growth rate without external interference. However, when the number of the microbial population approaches the carrying capacity of the environment, the growth rate of the microbial population will gradually slow down;

[0047] Introduce the interactions between microbial populations, such as competition and symbiosis. There is a symbiotic relationship between different microbial populations, and they can grow faster with each other's help; at the same time, there is also a competitive relationship. Under limited resource conditions, different types of microorganisms will compete, and the competition for resources will inhibit the growth of microorganisms;

[0048] Simulate the evolution process of the microbial community through dynamic equations, consider the competition and symbiosis between microbial populations, calculate the changes of each microbial population, and dynamically update over time, so as to dynamically predict the number of microbial populations;

[0049] To improve the prediction accuracy, the influence of the soil environment is considered, and an adjustment coefficient is used to quantify the influence of the soil environment on microbial growth. The change of the soil environment will directly affect the growth rate of microorganisms, and thus affect the change of the number of microbial populations; to avoid the excessive influence of single soil environmental data on predicting the number of microbial populations, a standardized maximum value is introduced to standardize the soil environmental data, which can make different soil environmental data comparable on the same scale and make the prediction accurate;

[0050] The calculation formula for predicting the number of microbial populations is:

[0051]

[0052] Where Mi (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; M i (t) represents the quantity of the i-th microbial population at time t; Δt represents the predicted time step, that is, the time difference from time t to t + Δt, which can be specifically set according to the specific implementation scenario and is not limited here; α represents the adjustment coefficient, used to describe the regulation intensity of soil environmental data on microbial growth, which can be specifically set according to the specific implementation scenario and is not limited here; represents the comprehensive impact of all soil environmental data on microbial growth. The impact of each soil environmental data on microbial growth is standardized to ensure the integration of the impacts of soil environments with different units on microbial growth, so that the change rate of the microbial population can reflect the actual impact of soil environmental data; ∑ k represents the summation of the impacts of all soil environmental data; S k (t) represents the k-th soil environmental data at time t; represents the maximum value of the k-th soil environmental data at time t, which can be specifically set according to the specific implementation scenario and is not limited here; represents the change rate of the i-th microbial population quantity at time t, that is, the change trend of the microbial population. The calculation formula is:

[0053]

[0054] Among them, represents the change rate of the i-th microbial population quantity at time t, that is, the change trend of the microbial population; r i represents the growth rate of the i-th microbial population, obtained from the literature, which can be specifically set according to the specific implementation scenario and is not limited here; M i (t) represents the quantity of the i-th microbial population at time t; represents the environmental carrying capacity limiting factor, reflecting the limiting effect of the environmental carrying capacity on the growth of the microbial population. When the microbial population quantity approaches the environmental carrying capacity of the microorganism, the growth rate of the microbial population approaches zero, indicating that the soil environment cannot support too many microorganisms, reflecting the impact of the growth of microorganisms being restricted by resources; K i represents the environmental carrying capacity of the i-th microbial population, which is the upper limit of the growth of the microbial population and limits the expansion of the microbial population, which can be specifically set according to the specific implementation scenario and is not limited here; ∑ j≠i represents the summation symbol, summing over all microbial populations other than the i-th microbial population; B ij ·M i (t)·M j(t) represents the symbiotic effect between the i-th microbial population and the j-th microbial population, that is, the i-th microbial population and the j-th microbial population jointly promote the growth of each other; M j (t) represents the quantity of the j-th microbial population at time t; B ij represents the symbiotic effect coefficient, which describes the cooperation intensity between different microbial populations and can be specifically set according to the specific implementation scenario and is not limited here; A ij ·M i (t)·M j (t) represents the competitive effect between the i-th microbial population and the j-th microbial population, that is, the i-th microbial population and the j-th microbial population compete for soil resources such as water and nutrients, and the competitive relationship will inhibit the growth of the microbial population; A ij represents the competition coefficient between the i-th microbial population and the j-th microbial population, which is used to control the competitive effect between different microbial populations and can be specifically set according to the specific implementation scenario and is not limited here;

[0055] By inputting soil environmental data and microbial population data into a soil microbial virtual model constructed by digital twin technology, and calculating the change trend of the microbial population in real time, as well as accurately predicting the growth trend of the microbial population, it can provide strong technical support for intelligent optimization and decision-making;

[0056] S2. Based on the soil environmental data and the predicted microbial population quantity, calculate the microbial health index through the microbial health index calculation algorithm;

[0057] Based on the soil environmental data and the predicted microbial population quantity, calculate the microbial health index through the microbial health index calculation algorithm;

[0058] The microbial health index calculation algorithm takes into account the contribution of the microbial population quantity to the microbial health index. The influence degree of each microorganism is determined according to the microbial population quantity and characteristics. Specifically, the relationship between the microbial population quantity and the contribution of the microorganism to the microbial health index is not a simple linear relationship, and it is necessary to introduce the basic coefficient of the microbial population to the microbial health index and the weighted index of the microbial population to the microbial health index to adjust the influence of the microorganism;

[0059] In addition to the microbial population quantity, soil environmental data, such as soil temperature, soil humidity, and soil pH value, also have a significant impact on the microbial health index. The influence degrees of different soil environmental data on different microbial populations are different. It may be beneficial to the growth of microorganisms, but it may also inhibit the growth of microorganisms. The influence of soil environmental data needs to be adjusted and weighted according to the characteristics of microbial populations; introducing an exponential decay factor for the influence of soil environmental data on microorganisms, as the soil environmental data increases, the growth rate of microorganisms will slow down exponentially. When the exponential decay factor is close to 1, it reflects that the soil environment has almost no influence on the growth of microorganisms. When the exponential decay factor approaches 0, it reflects that the growth of microorganisms is almost completely inhibited; through the sensitivity coefficient of microbial populations to the soil environment, the response degrees of different microbial populations to soil environmental changes are reflected;

[0060] The calculation formula for the microbial health index is:

[0061]

[0062] Among them, Q(t + Δt) represents the microbial health index at time t + Δt; ∑ i represents the summation of the contributions of all microbial populations to the microbial health index; M i (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; γ i represents the basic coefficient of the i-th microbial population for the microbial health index, which can be specifically set according to specific implementation scenarios and is not limited here; θ i represents the weighting index of the i-th microbial population for the microbial health index, which can be specifically set according to specific implementation scenarios and is not limited here; represents the exponential decay factor for the influence of soil environmental data on microorganisms. As the soil environmental data increases, the growth rate of microorganisms will slow down exponentially. When the exponential decay factor is close to 1, it reflects that the soil environment has almost no influence on the growth of microorganisms. When the exponential decay factor approaches 0, it reflects that the growth of microorganisms is almost completely inhibited; S k (t) represents the k-th soil environmental data at time t; δ i represents the sensitivity coefficient of the i-th microbial population to the soil environment, which reflects the response degrees of different microbial populations to soil environmental changes and can be specifically set according to specific implementation scenarios and is not limited here;

[0063] S3. Based on the microbial health index, select the best microbial management operation plan through the adaptive evolution optimal operation selection model;

[0064] Based on the microbial health index, select the best microbial management operation plan through the adaptive evolution optimal operation selection model;

[0065] The adaptive evolution optimal operation selection model makes decisions by optimizing the microbial health index and balancing cost - effectiveness;

[0066] By continuously obtaining new microbial health index information, it can optimize and adjust the microbial management operation plan in real - time. When the microbial health index is extremely low, it will improve the soil condition by increasing fertilization. On the contrary, when the microbial health index is too high, it will reduce the corresponding operation amount to avoid over - intervention;

[0067] It realizes the optimal effect of soil management by optimizing the microbial health index. By adjusting different management measures, such as fertilizer type and fertilization amount, it maximizes the microbial health index and minimizes the operation cost;

[0068] To adapt to the changes of microorganisms and the dynamic changes of the soil environment, it is updated in real - time through a feedback mechanism, so that each microbial management operation selection can meet the actual needs of current microorganisms. The formula is as follows:

[0069]

[0070] Among them, O opt represents the best microbial management operation plan selected after optimization; O l represents the l - th microbial management operation, such as fertilization; Q(t + Δt) represents the microbial health index at time t+Δt; μ represents the feedback adjustment factor, which is used to introduce the fitness of soil microorganisms to microbial management operations and will adjust the effect of microbial management operations according to the changes of microorganisms. It can be specifically set according to the specific implementation scenario and is not limited here; ρ kl represents the responsiveness of the k - th soil environmental data to the l - th microbial management operation, which can be specifically set according to the specific implementation scenario and is not limited here; C l represents the cost of the l - th microbial management operation, such as material cost (such as the purchase cost of fertilizers) or execution cost (such as labor, equipment usage cost); λ represents the cost adjustment coefficient, which is used to control the balance between the cost and benefit of microbial management operations. It can be specifically set according to the specific implementation scenario and is not limited here;

[0071] By combining the adaptive evolution optimal operation selection model with digital twin technology, intelligent and real - time microbial management decisions can be realized. Digital twin technology provides a dynamic virtual environment, enabling the adaptive evolution optimal operation selection model to foresee the long - term effects of different operation plans and achieve fine microbial analysis and management.

[0072] In summary, a soil microbial analysis method based on digital twin is completed.

[0073] The sequence of the invention embodiments is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or consecutive order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0074] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

[0075] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for analyzing soil microorganisms based on digital twins, characterized in that, It includes the following steps: S1: Obtain soil environmental data and data on different microbial populations in the soil in real time. Input the soil environmental data and microbial population data into a soil microbial virtual model constructed by digital twin technology, simulate the evolution process of the microbial community through dynamic equations, and dynamically predict the number of microbial populations; S2: Calculate the microbial health index based on the soil environmental data and the predicted number of microbial populations through a microbial health index calculation algorithm; S3: Select the best microbial management operation plan through an adaptive evolution optimal operation selection model based on the microbial health index.

2. The method for soil microorganism analysis based on digital twin according to claim 1, wherein The S1 specifically includes: The soil microbial virtual model constructed by digital twin technology combines the self-growth of microbial populations and the interactions between different microbial populations. The self-growth of microbial populations means that each microorganism reproduces according to its growth rate without external interference.

3. The method for analyzing soil microorganisms based on digital twin according to claim 2, wherein The S1 specifically includes: Introduce the interactions between microbial populations, including competition and symbiosis. There is a symbiotic relationship between different microbial populations, and they can accelerate growth when helping each other; at the same time, there is also a competitive relationship. Under the condition of insufficient resources, different types of microorganisms will compete, and the competition for resources will inhibit the growth of microorganisms.

4. The method for soil microorganism analysis based on digital twin according to claim 1, characterized in that, The S1 specifically includes: The calculation formula for predicting the number of microbial populations is: Among them, M i (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; M i (t) represents the quantity of the i-th microbial population at time t; Δt represents the predicted time step, that is, the time difference from time t to t + Δt; α represents the adjustment coefficient; ∑ k represents the summation of the impacts on all soil environmental data; S k (t) represents the k-th soil environmental data at time t; represents the maximum value of the k-th soil environmental data at time t; represents the change rate of the i-th microbial population quantity at time t, that is, the change trend of the microbial population.

5. The method for analyzing soil microorganisms based on digital twins according to claim 1, characterized in that The S2 specifically includes: The microbial health index calculation algorithm adjusts the impact on the microbial health index by introducing the basic coefficient of the microbial population on the microbial health index and the weighted index of the microbial population on the microbial health index to obtain the microbial health index.

6. The method for analyzing soil microorganisms based on digital twin according to claim 5, wherein The S2 specifically includes: The calculation formula for the microbial health index is: Among them, Q(t + Δt) represents the microbial health index at time t + Δt; ∑ i represents the summation of the contributions of all microbial populations to the microbial health index; M i (t + Δt) represents the quantity of the i-th microbial population at time t + Δt; γ i represents the basic coefficient of the i-th microbial population to the microbial health index; θ i represents the weighting index of the i-th microbial population to the microbial health index; represents the exponential decay factor of the influence of soil environmental data on microorganisms; S k (t) represents the k-th soil environmental data at time t; δ i represents the sensitivity coefficient of the i-th microbial population to the soil environment.

7. The method for soil microorganism analysis based on digital twin according to claim 1, characterized in that, The S3 specifically includes: The adaptive evolution optimal operation selection model obtains new microbial health index information and makes real-time optimization adjustments to the microbial management operation plan. When the microbial health index is extremely low, it will improve the soil condition by increasing fertilization; when the health index is too high, the corresponding operation amount will be reduced.

8. The method for soil microorganism analysis based on digital twin according to claim 7, wherein The S3 specifically includes: The adaptive evolution optimal operation selection model obtains the best microbial management operation plan selected after optimization by introducing a feedback mechanism and combining a feedback adjustment factor. The specific implementation formula is: Among them, O opt represents the best microbial management operation plan selected after optimization; O l represents the l-th microbial management operation; Q(t + Δt) represents the microbial health index at time t + Δt; μ represents the feedback regulation factor; ρ kl represents the responsiveness of the k-th soil environmental data to the l-th microbial management operation; C l represents the cost of the l-th microbial management operation; λ represents the cost regulation coefficient.

Images