Soil monitoring method and system based on digital twinborn technology

Abstract

The invention relates to the technical field of computer software, and particularly discloses a soil monitoring method and system based on a digital twinning technology, and the method comprises the steps: obtaining the real-time detection information and real-time environment information of soil; obtaining feature classification information according to the real-time environment information, and obtaining a soil influence degree value according to the classification type of the feature information; obtaining physical feature information and chemical feature information according to the real-time detection information; acquiring a soil water diversion change degree according to the soil influence degree value and the physical characteristic information, and acquiring a first abnormal area of the soil according to the soil change degree based on a digital twinborn technology; according to the method, the influence of environmental factors such as meteorology, landform and biocenosis on the soil and the change of physical and chemical characteristics of the soil are comprehensively considered, so that the soil change trend can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of computer software, and in particular to a soil monitoring method and system based on digital twin technology. Background Art

[0002] With the growth of the global population and economic development, the rational utilization and protection of soil resources have become increasingly important. The demand for accurate monitoring and scientific management of soil conditions in fields such as precision agriculture, ecological environment protection, and land planning is becoming increasingly urgent. As an emerging technology, digital twin technology has achieved remarkable results in fields such as engineering and manufacturing. By constructing a virtual model of a physical entity, it realizes real-time monitoring, simulation analysis, and optimal control of physical objects, providing new ideas and methods for solving complex system problems. Introducing digital twin technology into the field of soil monitoring is expected to improve the accuracy, timeliness, and comprehensiveness of soil monitoring and achieve the sustainable utilization of soil resources.

[0003] When evaluating the impact of environmental factors such as meteorology, topography, and biological communities on soil, the existing technology mostly uses single-factor analysis or simple superposition methods, and cannot accurately simulate the complex coupling relationship between environmental factors. For example, when studying the problem of soil erosion in mountainous areas, only considering a single factor such as precipitation or slope cannot truly reflect the actual situation, because the interaction between precipitation and slope will exacerbate soil erosion, and the existing technology is difficult to accurately quantify this coupling effect, resulting in inaccurate assessment of soil erosion risk and affecting the formulation of soil and water conservation measures. Summary of the Invention

[0004] The purpose of the present invention is to provide a soil monitoring method and system based on digital twin technology to solve the technical problems proposed in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solutions:

[0006] A soil monitoring method based on digital twin technology, comprising:

[0007] Obtaining real-time detection information and real-time environmental information of the soil;

[0008] Obtaining characteristic classification information according to the real-time environmental information, and obtaining a soil influence degree value according to the type of the characteristic information classification;

[0009] Obtaining physical characteristic information and chemical characteristic information according to the real-time detection information;

[0010] Obtaining a soil water conductivity change degree according to the soil influence degree value and the physical characteristic information, and obtaining a first abnormal area of the soil based on the digital twin technology according to the soil change degree;

[0011] Obtain the soil chemical change degree based on the soil impact degree value and chemical characteristic information, and obtain the second abnormal area of the soil based on the digital twin technology according to the soil chemical change degree;

[0012] Obtain the proportion of the soil abnormal area based on multiple first abnormal areas of the soil and multiple second abnormal areas of the soil, and determine whether the proportion of the soil abnormal area exceeds a preset value;

[0013] If it does not exceed, determine that the soil here is abnormal, and continuously obtain the real-time detection information and real-time environmental information of the soil;

[0014] If it exceeds, determine that the soil here is abnormal, and generate a soil warning message.

[0015] Preferably, the step of obtaining the characteristic classification information according to the real-time environmental information and obtaining the soil impact degree value according to the type classified by the characteristic information includes:

[0016] Extract features from the real-time environmental information to obtain characteristic classification information, where the characteristic classification information includes meteorological characteristic information, topographic and geomorphic characteristic information, and biological community characteristic information;

[0017] Obtain historical meteorological characteristic information, historical topographic and geomorphic characteristic information, and historical biological community characteristic information;

[0018] Obtain environmental temperature change characteristic information, precipitation change characteristic information, and light change characteristic information according to the historical meteorological characteristic information and meteorological characteristic information;

[0019] Obtain a meteorological change value according to the environmental temperature change characteristic information, precipitation change characteristic information, and light change characteristic information;

[0020] Obtain a first weight coefficient according to the meteorological change value;

[0021] Obtain real-time slope change characteristic information and altitude change characteristic information according to the historical topographic and geomorphic characteristic information and topographic and geomorphic characteristic information;

[0022] Obtain a terrain change value according to the real-time slope change characteristic information and altitude change characteristic information;

[0023] Obtain a second weight coefficient according to the terrain change value;

[0024] Obtain vegetation change characteristic information and animal activity change characteristic information according to the historical biological community characteristic information and biological community characteristic information;

[0025] Obtain a biological community impact value according to the vegetation change characteristic information and animal activity change characteristic information;

[0026] Obtain the third weight coefficient according to the biotic community influence value;

[0027] Obtain the soil influence degree value according to the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biotic community influence value and the third weight coefficient, where the calculation formula is:

[0028]

[0029] Among them, K represents the soil influence degree value, A represents the meteorological change value, B represents the terrain change value, C represents the biotic community influence value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

[0030] Preferably, the step of obtaining the physical characteristic information and the chemical characteristic information according to the real-time detection information includes:

[0031] Obtain the soil particle characteristic information according to the real-time detection information;

[0032] Obtain the proportions of sand, silt and clay based on the soil particle characteristic information, and obtain the soil texture classification based on the proportions of sand, silt and clay;

[0033] Obtain the soil aggregate information based on the soil texture classification;

[0034] Obtain the soil stability according to the soil aggregate information;

[0035] Obtain the soil porosity based on the soil stability;

[0036] Obtain the soil pH characteristic, the soil nitrogen characteristic and the soil salinity characteristic according to the chemical characteristic information.

[0037] Preferably, the step of obtaining the soil water conductivity change degree according to the soil influence degree value and the physical characteristic information, and obtaining the first abnormal area of the soil based on the digital twin technology includes:

[0038] Obtain the soil texture classification, the soil stability and the soil porosity according to the physical characteristic information;

[0039] Obtain the soil water holding capacity according to the soil stability;

[0040] Obtain the water holding capacity coefficient according to the soil water holding capacity;

[0041] According to the soil texture classification and the soil hydraulic conductivity;

[0042] Obtain the hydraulic conductivity coefficient according to the soil hydraulic conductivity;

[0043] Obtain the flow rate according to the soil porosity;

[0044] Obtain the flow rate coefficient according to the flow rate;

[0045] Obtain the moisture content of the soil;

[0046] Obtain the initial porosity and water holding coefficient of the soil;

[0047] Calculate the soil hydraulic conductivity change degree according to the soil water holding capacity, water holding capacity coefficient, soil hydraulic conductivity, hydraulic conductivity coefficient, hydraulic conductivity coefficient, flow rate coefficient, moisture content, initial porosity and water holding coefficient, where the calculation formula is:

[0048]

[0049] Among them, P represents the soil hydraulic conductivity change degree, I m represents the soil water holding capacity, α represents the water holding capacity coefficient, I n represents the soil hydraulic conductivity, β represents the hydraulic conductivity coefficient, I h represents the hydraulic conductivity coefficient, γ represents the flow rate coefficient, W represents the moisture content, S represents the initial porosity and D represents the water holding coefficient;

[0050] Construct the soil water movement in the digital twin body according to the soil hydraulic conductivity change degree;

[0051] Obtain the digital twin body to simulate multiple soil moisture regions according to the soil water movement;

[0052] Obtain the physical change degree of soil moisture in each of the moisture regions;

[0053] Judge whether the physical change degree of soil moisture in each of the regions exceeds a preset value;

[0054] If it exceeds, determine that the moisture region is the first abnormal region of the soil;

[0055] If it does not exceed, determine that the moisture region is normal.

[0056] Preferably, the step of obtaining the soil chemical change degree according to the soil influence degree value and chemical characteristic information and obtaining the second abnormal region of the soil based on digital twin technology includes:

[0057] Obtain the real-time soil pH according to the soil pH characteristics;

[0058] Obtain the historical soil pH, and obtain the real-time soil pH difference value according to the historical soil pH and the real-time soil pH;

[0059] Obtain the acid-base weight coefficient according to the real-time soil pH difference value;

[0060] Obtain the real-time nitrogen content according to the soil nitrogen characteristics;

[0061] Obtain the historical nitrogen content of the soil, and obtain the soil nitrogen loss value according to the historical nitrogen content of the soil and the real-time nitrogen content;

[0062] Obtain the nitrogen weight coefficient according to the soil nitrogen loss value;

[0063] Obtain the real-time soil salt content according to the soil salt characteristics;

[0064] Obtain the historical soil salt content, and obtain the soil salt change value according to the historical soil salt content and the real-time soil salt content;

[0065] Obtain the salt weight coefficient according to the soil salt change value;

[0066] Obtain the soil chemical change degree according to the real-time soil acidity-base difference value, acidity-base weight coefficient, soil nitrogen loss value, nitrogen weight coefficient, soil salt change value, and salt weight coefficient;

[0067] Construct the soil chemical change in the digital twin body according to the soil chemical change degree;

[0068] Obtain multiple chemical change regions of the simulated soil in the digital twin body according to the soil chemical change;

[0069] Obtain the soil chemical change degree of each chemical change region;

[0070] Judge whether the soil chemical change degree of each one exceeds the preset value;

[0071] If it exceeds, determine that the chemical change region is the second abnormal region of the soil;

[0072] If it does not exceed, determine that the chemical change region is normal.

[0073] Preferably, the step of obtaining the ratio of the soil abnormal region according to the multiple first abnormal regions of the soil and the multiple second abnormal regions of the soil includes:

[0074] Obtain the first abnormal quantity of the first abnormal region of the soil;

[0075] Obtain the second abnormal quantity of the second abnormal region of the soil;

[0076] Obtain the total quantity of the first abnormal region and the second abnormal region of the soil;

[0077] Obtain the ratio of the soil abnormal region according to the first abnormal quantity, the second abnormal quantity and the total quantity.

[0078] The present invention also discloses a soil monitoring system based on digital twin technology, which is characterized by including:

[0079] A first acquisition module, configured to acquire real-time detection information and real-time environmental information of soil;

[0080] A second acquisition module, configured to acquire feature classification information according to the real-time environmental information, and acquire a soil influence degree value according to the type of the classified feature information;

[0081] A third acquisition module, configured to acquire physical feature information and chemical feature information according to the real-time detection information;

[0082] A fourth acquisition module, configured to acquire a soil water conductivity change degree according to the soil influence degree value and the physical feature information, and acquire a first soil abnormal area according to the soil change degree based on digital twin technology;

[0083] A fifth acquisition module, configured to acquire a soil chemical change degree according to the soil influence degree value and the chemical feature information, and acquire a second soil abnormal area according to the soil chemical change degree based on digital twin technology;

[0084] A judgment module, configured to acquire a ratio of the soil abnormal area according to multiple first soil abnormal areas and multiple second soil abnormal areas, and judge whether the ratio of the soil abnormal area exceeds a preset value;

[0085] If not exceeding, judge that the soil here is abnormal, and continuously acquire real-time detection information and real-time environmental information of the soil;

[0086] If exceeding, judge that the soil here is abnormal, and generate a soil warning message.

[0087] Preferably, the second acquisition module includes:

[0088] A first acquisition unit, configured to perform feature extraction on the real-time environmental information to obtain feature classification information, where the feature classification information includes meteorological feature information, topographic and geomorphic feature information, and biological community feature information;

[0089] A second acquisition unit, configured to acquire historical meteorological feature information, historical topographic and geomorphic feature information, and historical biological community feature information;

[0090] A third acquisition unit, configured to acquire environmental temperature change feature information, precipitation change feature information, and light change feature information according to the historical meteorological feature information and the meteorological feature information;

[0091] A fourth acquisition unit, configured to acquire a meteorological change value according to the environmental temperature change feature information, the precipitation change feature information, and the light change feature information;

[0092] A fifth acquisition unit, configured to acquire a first weight coefficient according to the meteorological change value;

[0093] A sixth acquisition unit, configured to acquire real-time slope change feature information and altitude change feature information according to the historical terrain and landform feature information and the terrain and landform feature information;

[0094] A seventh acquisition unit, configured to acquire a terrain change value according to the real-time slope change feature information and the altitude change feature information;

[0095] An eighth acquisition unit, configured to acquire a second weight coefficient according to the terrain change value;

[0096] A ninth acquisition unit, configured to acquire vegetation change feature information and animal activity change feature information according to the historical biological community feature information and the biological community feature information;

[0097] A tenth acquisition unit, configured to acquire a biological community influence value according to the vegetation change feature information and the animal activity change feature information;

[0098] An eleventh acquisition unit, configured to acquire a third weight coefficient according to the biological community influence value;

[0099] A calculation unit, configured to acquire a soil influence degree value according to the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biological community influence value, and the third weight coefficient, where the calculation formula is:

[0100]

[0101] Wherein, K represents the soil influence degree value, A represents the meteorological change value, B represents the terrain change value, C represents the biological community influence value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

[0102] The present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0103] The present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0104] The beneficial effects of this application are as follows: By comprehensively considering the impacts of environmental factors such as meteorology, topography, and biological communities on the soil, as well as the changes in soil physical and chemical characteristics, the present invention can accurately evaluate the soil change trend. Based on digital twin technology, it precisely simulates soil physical and chemical processes, enabling more scientific determination of soil abnormal areas and hierarchical management. In soil remediation projects, it can accurately locate polluted areas, formulate targeted remediation plans according to the pollution degree, improve remediation efficiency, reduce costs, and achieve the efficient utilization of soil resources and the effective protection of the ecological environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0105] Figure 1 It is a schematic flowchart of the method according to an embodiment of this application.

[0106] Figure 2 It is a schematic structural diagram of the system according to an embodiment of this application.

[0107] Figure 3 It is a schematic internal structure diagram of a computer device according to an embodiment of this application.

[0108] The realization of the purpose of this application, functional features, and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0109] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0110] As Figure 1 shown, this application provides a soil monitoring method based on digital twin technology, including:

[0111] S1. Obtain real-time detection information and real-time environmental information of the soil;

[0112] S2. Obtain feature classification information according to the real-time environmental information, and obtain the soil influence degree value according to the type of the feature information classification;

[0113] S3. Obtain physical feature information and chemical feature information according to the real-time detection information;

[0114] S4. Obtain the soil water conductivity change degree according to the soil influence degree value and the physical feature information, and obtain the first soil abnormal area based on the digital twin technology according to the soil change degree;

[0115] S5. Obtain the soil chemical change degree according to the soil influence degree value and the chemical feature information, and obtain the second soil abnormal area based on the digital twin technology according to the soil chemical change degree;

[0116] S6. Obtain the ratio of the soil abnormal area based on the multiple first soil abnormal areas and the multiple second soil abnormal areas, and determine whether the ratio of the soil abnormal area exceeds a preset value;

[0117] If it does not exceed, determine that the soil here is abnormal, and continuously obtain the real-time detection information and real-time environmental information of the soil;

[0118] If it exceeds, determine that the soil here is abnormal, and generate a soil warning message.

[0119] As described in the above steps S1 - S6, when analyzing the influence of environmental factors on soil, existing digital twins often have difficulty accurately simulating the complex coupling relationship between multiple environmental factors. For example, meteorological factors (such as precipitation, temperature) interact with topography (such as slope, aspect) to jointly affect soil water movement and erosion processes, but current models may not fully consider this interaction, resulting in inaccurate calculation of the degree of influence on soil. In actual situations, for the same precipitation amount on terrains with different slopes and aspects, the soil erosion amount will vary greatly, but digital twins may not be able to accurately simulate this difference, affecting the accurate assessment and decision-making of soil conditions.

[0120] Through the real-time detection of information, the present invention can directly present the current physical and chemical states of the soil. The real-time environmental information covers external influencing factors. For example, meteorological data can assist in analyzing soil water evaporation and infiltration. In agricultural production, for instance, the traditional method of periodically collecting soil samples manually for analysis has a long interval and cannot timely reflect dynamic changes, which may lead to improper fertilization and affect crop growth. However, obtaining information in real time can enable precise decision-making during the critical period when crops need fertilizers. After heavy rain, by combining real-time precipitation and soil moisture detection data, the risk of waterlogging can be timely judged and drainage measures can be taken to avoid damage to crop roots caused by overly wet soil. Then, through step S2 (obtaining characteristic classification information according to real-time environmental information and obtaining the soil influence degree value according to the type of characteristic information classification), it is conducive to deeply understanding the soil change mechanism for accurate characteristic classification and influence degree assessment. After classifying the environmental information, the influence of each factor can be analyzed specifically. For example, calculating the meteorological change value can quantify the influence of meteorological factors on soil moisture and temperature, providing key parameters for model construction and improving the accuracy of soil prediction. It solves the problem of being unable to quantify the influence degree of environmental factors on the soil. For example, in mountainous areas, it was previously difficult to determine the relationship between meteorology and soil erosion. Now, through this step, the relationship between factors such as precipitation intensity and slope and the erosion amount can be clarified. When predicting heavy precipitation, combined with the topography and landform, the erosion risk of different regions can be evaluated, and protective measures can be taken in advance to reduce soil loss and protect the ecological environment. After that, through step S3 (obtaining physical characteristic information and chemical characteristic information according to real-time detection information), obtaining physical and chemical characteristics provides rich basis for soil quality assessment. Physical characteristics reflect the conditions of soil aeration, water permeability, and water retention, etc., and chemical characteristics can judge soil fertility, providing data for the construction of the digital twin model and simulating the internal processes of the soil. It solves the problem of lacking comprehensive and accurate data for soil quality assessment. In agriculture, soil texture affects crop growth. If the texture is not understood, the wrong crops may be selected, resulting in low yields. Obtaining physical characteristics such as texture can optimize the planting plan. For chemical characteristics, soil pH affects the availability of nutrients. For example, phosphorus is easily fixed in acidic soil. Real-time detection of pH can adjust fertilization measures to improve the availability of nutrients and promote crop growth. Then, through step S4 (obtaining the soil water conductivity change degree according to the soil influence degree value and physical characteristic information, and obtaining the first abnormal area of the soil based on the digital twin technology according to the soil change degree), the digital twin technology is used to analyze the soil water conductivity change degree to achieve precise monitoring and abnormal early warning. Considering multiple factors comprehensively to calculate the water conductivity change degree can grasp the law of water movement, construct a model to simulate the change trend, and discover problems in advance. This solves the problem of being unable to predict and accurately locate the abnormal area of soil moisture in advance. In large-scale farmland irrigation, it is difficult to determine uneven water distribution or waterlogging areas in the traditional way. Through this step, the irrigation process can be simulated, and areas can be divided and compared according to the water conductivity change degree. After determining the abnormal area, the irrigation strategy can be adjusted to ensure that the soil moisture is suitable for crop growth and avoid problems such as reduced yields and soil secondary salinization.Next, through step S5 (obtaining the soil chemical change degree based on the soil influence degree value and chemical characteristic information, and obtaining the second abnormal area of the soil based on the soil chemical change degree by means of digital twin technology), in-depth analysis of the chemical change degree and determination of the abnormal area contribute to fertility management and pollution prevention and control. Integrating information to calculate the change degree can track the evolution of chemical properties, construct a model to simulate chemical processes, predict the change trend, which is of great significance for reasonable fertilization and pollution prevention and control. It solves the problems of untimely monitoring of soil chemical properties and difficult effective treatment of pollution. In agriculture, excessive fertilization can lead to soil nutrient imbalance and environmental pollution. For example, excessive application of nitrogen fertilizer causes water eutrophication. Through this step, the change of nitrogen can be monitored in real time, the loss situation can be simulated by combining environmental factors, and fertilization can be adjusted after determining the abnormal area to protect the soil and water environment. For pollution monitoring, such as the soil around industrial pollution areas, the chemical abnormal area can be located through this step for timely repair to prevent pollution diffusion. Finally, through step S6 (obtaining the ratio of the soil abnormal area based on multiple first abnormal areas and multiple second abnormal areas of the soil, and determining whether the ratio of the soil abnormal area exceeds a preset value), overall evaluation of the soil abnormal area provides a basis for management decision-making. Calculating the ratio can grasp the soil health status, comprehensively consider physical and chemical abnormal areas, avoid the limitation of single-factor evaluation, and clarify the overall state of the soil after comparison with the preset value, providing a quantitative reference for improvement and planning. It solves the problems of lack of overall evaluation criteria for soil management and blindness in decision-making. In regional soil monitoring, in the past, individual problem points were concerned without overall judgment. For example, in a certain area, both industrial pollution caused chemical anomalies and topographic factors caused physical structure damage. By calculating the ratio through this step, if it exceeds the preset value, a comprehensive repair plan will be launched.

[0121] In one embodiment, the step of obtaining the characteristic classification information according to the real-time environmental information and obtaining the soil influence degree value according to the type of the classified characteristic information includes:

[0122] S201. Extract features from the real-time environmental information to obtain characteristic classification information, where the characteristic classification information includes meteorological characteristic information, topographic and geomorphic characteristic information, and biological community characteristic information;

[0123] S202. Obtain historical meteorological characteristic information, historical topographic and geomorphic characteristic information, and historical biological community characteristic information;

[0124] S203. Obtain environmental temperature change characteristic information, precipitation change characteristic information, and light change characteristic information according to the historical meteorological characteristic information and the meteorological characteristic information;

[0125] S204. Obtain a meteorological change value according to the environmental temperature change characteristic information, the precipitation change characteristic information, and the light change characteristic information;

[0126] S205. Obtain the first weight coefficient according to the meteorological change value;

[0127] S206. Obtain the real-time slope change feature information and altitude change feature information according to the historical topographic and geomorphic feature information and the topographic and geomorphic feature information;

[0128] S207. Obtain the terrain change value according to the real-time slope change feature information and altitude change feature information;

[0129] S208. Obtain the second weight coefficient according to the terrain change value;

[0130] S209. Obtain the vegetation change feature information and animal activity change feature information according to the historical biological community feature information and the biological community feature information;

[0131] S210. Obtain the biological community influence value according to the vegetation change feature information and animal activity change feature information;

[0132] S211. Obtain the third weight coefficient according to the biological community influence value;

[0133] S212. Obtain the soil influence degree value according to the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biological community influence value and the third weight coefficient, where the calculation formula is:

[0134]

[0135] Among them, K represents the soil influence degree value, A represents the meteorological change value, B represents the terrain change value, C represents the biological community influence value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

[0136] As described in the above steps S201 - S212, the present invention obtains feature classification information by extracting features from real - time environmental information. Its beneficial effect lies in achieving an orderly classification of information, making complex environmental information more organized. This solves the problem that environmental information is messy and difficult to analyze. For example, during mountain soil monitoring, numerous real - time environmental information can be clearly distinguished into categories such as meteorology, topography, and biological communities through this step, avoiding information confusion. Then, in step S202, historical meteorological feature information, historical topographical feature information, and historical biological community feature information are obtained, which provides historical reference data for soil monitoring and helps enhance the understanding of the changing trend of the soil environment. Taking farmland soil as an example, it is difficult to grasp the changing trend of soil moisture content relying solely on current meteorology. The introduction of historical meteorological feature information such as historical precipitation and temperature can better assist in arranging irrigation and farming activities, preventing the impact of drought or flood on soil quality, effectively solving the problem that the long - term changing law of soil cannot be grasped only by real - time data. Then, through step S203, according to historical and real - time meteorological feature information, environmental temperature, precipitation, and light change feature information are obtained. Its advantage lies in accurately capturing the changes in key meteorological elements and providing dynamic parameters for the soil monitoring model. In the digital twin soil model, accurate information on these changes can update modules such as soil water evaporation and crop growth simulation in real - time, making the model more in line with the actual soil environment changes, thereby improving the soil state prediction ability and well solving the problem that it is difficult to quantify the impact of meteorological factors on soil. For example, in greenhouse soil monitoring, accurate temperature change feature information can timely adjust temperature control equipment to maintain an appropriate soil temperature for promoting crop root growth; precipitation change feature information can guide irrigation strategies to avoid over - wet or dry soil and ensure stable soil fertility. Based on this, in step S204, a meteorological change value is obtained according to the above - mentioned meteorological change feature information, and a single quantitative index is obtained by synthesizing meteorological element changes, which is convenient for uniformly evaluating the comprehensive impact of meteorology on soil. In the soil digital twin system, the meteorological change value can be directly input into the model to quickly calculate the impact degree of meteorological factors on soil physical and chemical processes (such as soil erosion and nutrient transformation), simplifying the calculation process and improving soil analysis efficiency, solving the problem that it is difficult to comprehensively evaluate the impact of multiple meteorological factors. For example, in mountain soil monitoring, under complex terrain, temperature, precipitation, and light changes are complex. Through the meteorological change value, the impact degree of meteorology on soil in different regions can be intuitively compared, providing a basis for soil protection and vegetation restoration. After that, through step S205, a first weight coefficient is obtained according to the meteorological change value. This operation highlights the relative importance of meteorological changes among soil influencing factors and optimizes the calculation of soil impact degree. In the soil digital twin model, a reasonable first weight coefficient enables meteorological factors to play an accurate role in multi - factor comprehensive analysis, more accurately simulating the impact of meteorological changes on processes such as soil water balance and heat transfer, improving the model accuracy, and solving the problem of unreasonable weights of meteorological factors in soil impact assessment.In the soil monitoring of arid regions, precipitation changes have a great impact on the soil. Accurately determining the first weight coefficient can highlight its importance and provide a scientific basis for the rational planning of water resource utilization. Step S206 obtains real-time slope change and elevation change characteristic information based on historical and real-time topographic and geomorphic characteristic information. Monitoring the dynamic changes of topography and geomorphology provides key data for research such as soil erosion and water distribution. In the digital twin soil monitoring, real-time slope changes affect the speed and direction of soil runoff, and elevation changes affect temperature and vegetation distribution, which in turn affect soil formation and properties. These data help to deeply analyze the mechanism of soil environmental changes and solve the problem of being difficult to grasp the dynamic impact of topography and geomorphology on the soil in real time. In mountain road construction projects, real-time slope change characteristic information can timely evaluate the impact of construction on the stability of surrounding soil and prevent landslides; elevation change characteristic information helps to analyze the impact of changes in vertical vegetation distribution on soil nutrient cycling and provides guidance for ecological protection. Furthermore, step S207 obtains the terrain change value according to the slope and elevation change characteristic information, quantifies the key characteristics of topography and geomorphology, and facilitates the unified analysis of its impact on the soil. In the soil digital twin model, the terrain change value is input as an important parameter and acts together with other factors on modules such as soil water movement and soil erosion simulation, enabling the model to more accurately reflect the impact of topography and geomorphology changes on soil physical processes, improving the accuracy of soil state prediction, and solving the problem of being difficult to quantitatively input topographic and geomorphic factors into the soil model. In the soil monitoring of river basins, the slope and elevation changes in different regions are complex. The terrain change value can visually compare the impact degrees of topography on soil erosion and water convergence in different sections and provide a quantitative basis for the soil and water conservation planning of river basins. Then, through step S208, the second weight coefficient is obtained according to the terrain change value, determining the relative importance of topographic and geomorphic factors in soil impact and improving the evaluation of soil impact degree. In the soil monitoring system, a reasonable second weight coefficient enables topographic and geomorphic factors to be accurately reflected in the multi-factor comprehensive analysis, more accurately simulates the impact of terrain changes on soil physical structure, water distribution, etc., optimizes the soil analysis results, and solves the problem of unscientific weights of topographic and geomorphic factors in soil impact evaluation. In agricultural production in hilly areas, the slope has a significant impact on soil water retention and agricultural machinery operation. Accurately obtaining the second weight coefficient can highlight its importance and provide a basis for the rational planning of farmland irrigation and tillage methods. Step S209 obtains vegetation and animal activity change characteristic information based on historical and real-time biotic community characteristic information, tracks the dynamics of the biotic community, and reveals the interaction relationship between organisms and the soil. In the digital twin soil monitoring, vegetation changes affect soil water conservation and nutrient cycling, and animal activities change the soil structure. These change characteristic information helps to comprehensively understand the impact mechanism of the ecosystem on the soil and provides a reference for soil ecological restoration, solving the problem of being difficult to monitor the dynamic impact of the biotic community on the soil.In the grassland ecosystem, the information on the characteristics of vegetation changes can promptly detect the impact of vegetation degradation caused by overgrazing on soil erosion and adjust the grazing strategy; the information on the characteristics of animal activity changes can help understand the improvement effect of soil animals on soil aeration and protect soil biodiversity. Subsequently, in step S210, the biological community impact value is obtained based on the information on the characteristics of vegetation and animal activity changes, quantifying the comprehensive impact of the biological community on the soil and providing a basis for soil ecological assessment. In the soil monitoring model, the biological community impact value is input as an important indicator and jointly affects the simulation of the soil ecosystem with factors such as meteorology and topography, helping to accurately evaluate the impact of biological community changes on soil fertility, structural stability, etc., guiding ecological protection and restoration practices, and solving the problem of difficult quantitative assessment of the impact of the biological community on the soil. In the forest ecosystem, the biological community impact value can quantitatively analyze the contribution of the forest ecosystem to the soil carbon cycle and provide a scientific basis for forest management strategies to address climate change. In step S211, the third weight coefficient is obtained based on the biological community impact value, clarifying the relative importance of the biological community factor in soil impact and optimizing the calculation of the soil impact degree. In the soil digital twin system, a reasonable third weight coefficient enables the biological community factor to play an accurate role in multi-factor comprehensive analysis, more accurately simulating the impact of biological activities on soil chemical processes (such as nutrient transformation) and physical structures (such as aggregate formation), improving the model accuracy and solving the problem of unreasonable weight of the biological community factor in soil impact assessment. In the wetland ecosystem, biological communities such as microorganisms and plant roots play a key role in soil nutrient transformation and water purification. Accurately determining the third weight coefficient can highlight its importance and provide scientific guidance for wetland ecological restoration and protection. Finally, in step S212, the soil impact degree value is obtained based on the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biological community impact value, and the third weight coefficient, comprehensively evaluating the degree of soil impact by environmental factors and providing a scientific basis for soil management. In digital twin soil monitoring, the soil impact degree value intuitively reflects the soil health status, helping managers promptly discover problem areas and formulate precise soil improvement, protection, and land use planning schemes to achieve sustainable utilization of soil resources and solve the problem of incomplete assessment of soil impact by a single factor. In soil monitoring in urban expansion areas, the soil impact degree value obtained by comprehensively considering various factors can accurately evaluate the comprehensive impact of construction activities on the soil.

[0137] In one embodiment, the step of obtaining the physical characteristic information and the chemical characteristic information according to the real-time detection information includes:

[0138] S301. Obtain the soil particle characteristic information according to the real-time detection information;

[0139] S302. Obtain the proportions of sand, silt, and clay based on the soil particle characteristic information, and obtain the soil texture classification based on the proportions of sand, silt, and clay;

[0140] S303. Obtain the soil aggregate information based on the soil texture classification;

[0141] S304. Obtain the soil stability according to the soil aggregate information;

[0142] S305. Obtain the soil porosity based on the soil stability;

[0143] S306. Obtain the soil pH characteristic, soil nitrogen characteristic, and soil salt characteristic according to the chemical characteristic information.

[0144] As described in the above steps S301 - S306, the present invention lays a solid foundation for soil physical property analysis by obtaining soil particle characteristic information based on real - time detection information. In the digital twin soil monitoring system, these basic data are like the cornerstones of a building, providing initial parameters for constructing an accurate soil physical model, enabling the model to more realistically simulate the movement trajectories of water and gas in the soil. At the same time, this step also solves the problem of insufficient understanding of the soil physical structure in the past. Taking sandy soil areas as an example, in the past, due to the lack of detailed understanding of soil particle characteristics, irrigation and fertilization were often carried out blindly, resulting in the rapid loss of nutrients through the large pores between sand grains, and the rapid evaporation of water due to poor water retention. Then, through step S302, the proportions of sand, silt, and clay particles are obtained based on the soil particle characteristic information, and further soil texture classification is obtained. This operation realizes the accurate discrimination of soil texture, which is of great significance. Soils with different textures (such as sandy soil, loam, and clay) are like building materials with unique characteristics, having significant differences in physical and chemical properties, and also having very different abilities in crop growth, water retention, and nutrient supply. The soil texture classification based on this provides a key basis for soil fertility evaluation, just like a compass guiding agricultural production, helping farmers select suitable crop varieties and planting methods. In the field of digital twin soil monitoring, soil texture classification information, together with data such as meteorology and topography, collaborates to draw a scientific blueprint for regional agricultural planning and ecological protection, greatly improving the utilization efficiency of land resources. For example, in agricultural production, if the soil texture cannot be accurately judged, it is like groping in the dark, and it is very easy to make wrong decisions. For example, planting crops with shallow roots and high oxygen demand on clay - textured soil, due to poor soil aeration and poor drainage, the crops often grow poorly or even die. With accurate soil texture classification, farmers can be like experienced helmsmen, choosing suitable crops according to soil characteristics. Growing a variety of crops on loam can yield good harvests. Then, through step S303, soil aggregate information is obtained based on soil texture classification, which helps to deeply understand the soil aggregate situation and plays a crucial role in soil structure stability and fertility maintenance. Soil aggregate information is just like a barometer of the soil structure, reflecting the bonding mode and stability between soil particles. A good aggregate structure is like a "sponge" in the soil, which can not only allow air and water to freely shuttle in the soil, but also provide a comfortable environment for root growth and microbial activities. In the digital twin soil monitoring system, soil aggregate information is like a key to open the door to simulate the dynamic changes of soil structure, predict the structural stability of the soil under different external conditions (such as rainfall, tillage), provide a scientific basis for formulating soil protection and improvement measures, and ensure the normal operation of the soil ecosystem function. In agricultural production, past unreasonable tillage methods (such as excessive deep tillage, frequent plowing) are like a ruthless storm, wantonly destroying the soil aggregate structure, resulting in soil compaction and a serious decline in aeration and water permeability.Through step S304, the soil stability is obtained based on the soil aggregate information, realizing the quantification of the soil structure stability, which provides an indispensable key parameter for soil erosion prediction and prevention. Soil stability is like the "resistance" of the soil, directly determining the soil's erosion resistance under external forces such as hydraulic and wind forces. In the digital twin soil monitoring system, the soil stability data is like an accurate weather forecast. After being input into the soil erosion model, it can accurately predict the soil erosion risk, enabling us to make preventive preparations in advance, such as building terraced fields and planting trees, effectively reducing soil loss and protecting precious land resources and fragile ecological environments. At the same time, the soil stability information also has important reference value for evaluating the soil bearing capacity (such as the stability of building foundations), just as important as a construction engineer must understand the bearing capacity of the foundation before design. In step S305, the soil porosity is obtained based on the soil stability, successfully establishing a close connection between soil stability and porosity, further improving the analysis of soil physical properties. Soil porosity is like the "breathing channel" and "water storage space" of the soil, and is an important indicator of soil aeration, water permeability and water retention, complementing soil stability. A stable soil structure usually has a reasonable porosity distribution, just like a well-designed building with a proper ventilation and drainage system, which is conducive to the exchange of water and air in the soil, promoting the free breathing of plant roots and efficient absorption of nutrients. In digital twin soil monitoring, the soil porosity information and soil stability data complement each other, enabling more accurate simulation of soil water movement and nutrient cycling processes, providing strong support for optimizing irrigation and fertilization management strategies, and thus improving the utilization efficiency of soil resources. In agricultural irrigation, in the past, if the relationship between soil porosity and soil stability was not understood, it was like a doctor prescribing medicine blindly without understanding the patient's physical condition, which might lead to unreasonable irrigation. In step S306, the soil pH characteristics, soil nitrogen characteristics and soil salt characteristics are obtained based on the chemical characteristic information, enabling us to comprehensively grasp the soil chemical fertility status and illuminating the way forward for precise fertilization and soil improvement. Soil pH is like the "pH regulator" of the soil chemical environment, directly affecting the availability of nutrients and microbial activity in the soil. Nitrogen is the "energy source" for plant growth and is an essential macronutrient, while too high a salt content is like a "double-edged sword" that can cause salt damage to plants. By obtaining this chemical characteristic information, we are like mastering the password of soil chemical fertility, able to formulate a scientific and reasonable fertilization plan according to the actual chemical condition of the soil, accurately adjust the soil pH, strictly control salt accumulation, effectively improve soil fertility, and help crops grow vigorously. In digital twin soil monitoring, the chemical characteristic information works together with meteorological and physical characteristic information to jointly simulate the dynamic changes of soil chemical processes and predict the evolution trend of soil chemical properties, providing far-sighted decision-making support for long-term soil management. In agricultural production, in the past, due to the lack of understanding of soil pH, fertilization was like groping in the dark, and the effect was greatly reduced.For example, in acidic soil, phosphorus is like a trapped spirit and is easily fixed. If fertilizers are blindly applied without adjusting the soil pH, it is like blindly delivering letters in front of a closed door, and the utilization rate of phosphorus is extremely low, resulting in a great waste of fertilizer resources. Regarding the characteristics of soil nitrogen, unreasonable fertilization is like a faucet out of control, which may lead to nitrogen loss and further pollute the environment. For example, in farmland with excessive application of nitrogen fertilizer, nitrogen enters the water body with rainwater runoff and causes eutrophication of the water body like a tumor. Nowadays, by obtaining information on soil chemical characteristics, we can take targeted measures, such as applying lime in acidic soil to increase the pH, and reasonably controlling the application rate of nitrogen fertilizer to avoid deterioration of soil chemical properties.

[0145] In one embodiment, the step of obtaining the soil water conductivity change degree according to the soil influence degree value and physical characteristic information, and obtaining the first abnormal area of the soil based on the digital twin technology according to the soil change degree includes:

[0146] S401. Obtain the soil texture classification, soil stability, and soil porosity according to the physical characteristic information;

[0147] S402. Obtain the soil water holding capacity according to the soil stability;

[0148] S403. Obtain the water holding capacity coefficient according to the soil water holding capacity;

[0149] S404. According to the soil texture classification and soil hydraulic conductivity;

[0150] S405. Obtain the hydraulic conductivity coefficient according to the soil hydraulic conductivity;

[0151] S406. Obtain the flow rate according to the soil porosity;

[0152] S407. Obtain the flow rate coefficient according to the flow rate;

[0153] S408. Obtain the water content of the soil;

[0154] S409. Obtain the initial porosity and water holding coefficient of the soil;

[0155] S410. Calculate the soil water conductivity change degree according to the soil water holding capacity, water holding capacity coefficient, soil hydraulic conductivity, hydraulic conductivity coefficient, hydraulic conductivity coefficient, flow rate coefficient, water content, initial porosity, and water holding coefficient, where the calculation formula is:

[0156]

[0157] Among them, P represents the soil water conductivity change degree, I m represents the soil water holding capacity, α represents the water holding capacity coefficient, I nk represents the soil hydraulic conductivity, β represents the hydraulic conductivity coefficient, and I h represents the hydraulic conductivity coefficient, γ represents the flow rate coefficient, W represents the water content, S represents the initial porosity, and D represents the water holding coefficient;

[0158] S411. Construct the soil water movement in the digital twin body according to the soil hydraulic conductivity change degree;

[0159] S412. Obtain the digital twin body to simulate multiple soil water regions according to the soil water movement;

[0160] S413. Obtain the physical change degree of soil water in each of the water regions;

[0161] S414. Determine whether the physical change degree of soil water in each of the water regions exceeds a preset value;

[0162] If it exceeds, determine that the water region is the first abnormal region of the soil;

[0163] If it does not exceed, determine that the water region is normal.

[0164] As described in the above steps S401 - S414, the present invention comprehensively integrates physical characteristic information by obtaining soil texture classification, soil stability, and soil porosity based on the physical characteristic information, thereby constructing a solid basic framework for the study of soil water movement. Soil texture classification, stability, and porosity, as key indicators of soil physical properties, their systematic sorting helps to deeply analyze the internal relationship between soil structure and water retention and conduction. In the field of digital twin soil monitoring, these data, as basic parameters, can make the constructed soil physical model more accurate and make the simulated soil water movement more in line with the actual situation. For example, soils with different texture classifications (sand, loam, clay) have significant differences in porosity and stability, and thus have very different effects on the distribution and flow path of water in the soil. Accurately obtaining this information can provide a key basis for subsequent in - depth analysis and help optimize the design of irrigation systems and water resource management strategies. By obtaining the soil water - holding capacity based on soil stability, a quantitative relationship between soil stability and water - holding capacity is successfully established, further deepening the understanding of the soil water - retaining ability. Soil stability has an important impact on the arrangement and aggregation state of soil particles, and thus determines the size and continuity of soil pores, which is closely related to the water - holding capacity. Clarifying this relationship helps to accurately evaluate the water - retaining performance of the soil under different conditions. In digital twin soil monitoring, it provides more accurate parameters for predicting soil water changes, optimizes soil water management. By obtaining the water - holding coefficient based on the soil water - holding capacity, the standardization of the description of soil water - holding capacity is achieved, which greatly facilitates the comparison between different soils and model calculations. The water - holding coefficient converts the relatively complex water - holding capacity characteristics into a quantifiable index, making it easier to perform comprehensive operations with other parameters (such as meteorology, topography, etc.) in multi - factor analysis. In the digital twin soil monitoring model, as a key parameter input, the water - holding coefficient can make the model more accurately simulate the soil water balance process and improve the accuracy of soil water dynamic prediction. Based on soil texture classification and soil hydraulic conductivity, the relationship between soil texture and hydraulic conductivity is effectively correlated, clearly revealing the influence mechanism of soil physical structure on water conduction. Soil texture directly determines the size, shape, and arrangement of soil particles, and thus has a fundamental impact on soil hydraulic conductivity. Clarifying this relationship helps to deeply understand the conduction speed and path of soil water in soils with different textures. In digital twin soil monitoring, it helps to optimize the soil water movement simulation model. For example, sandy soil has a loose texture, high hydraulic conductivity, and fast water conduction speed; clay soil has a fine texture, low hydraulic conductivity, and slow water conduction. After understanding these characteristics, appropriate engineering parameters can be selected according to soil texture in water conservancy project design (such as drainage systems, irrigation channels), improving engineering efficiency. By obtaining the hydraulic conductivity coefficient based on soil hydraulic conductivity, the quantification of soil hydraulic conductivity is achieved, significantly enhancing its application effect in soil water models. The hydraulic conductivity coefficient standardizes soil hydraulic conductivity, making it more widely applicable under different soil conditions and model calculations.In digital twin soil monitoring, the hydraulic conductivity coefficient can be combined with other physical and chemical parameters to more accurately simulate the process of soil water movement. For example, in the simulation of processes such as soil water infiltration, evaporation, and runoff, it effectively improves the accuracy of model prediction. The flow rate is obtained based on soil porosity, and the characteristics of soil water flow are successfully determined based on porosity, providing key data for the study of soil water dynamics. Soil porosity, as an important channel for soil water flow, directly determines the flow rate and direction of water in the soil. By obtaining the flow rate in this step, it is possible to more intuitively understand the water transmission capacity of the soil, providing a basis for simulating the movement of soil water in soils with different pore structures in digital twin soil monitoring, and helping to optimize soil water management strategies. For example, in arid regions, after clarifying the relationship between soil porosity and flow rate, appropriate irrigation methods can be selected according to soil characteristics. For example, drip irrigation is suitable for soils with smaller porosity and low flow rate, which can effectively avoid rapid water loss. Obtaining the hydraulic conductivity coefficient based on the flow rate standardizes the soil water flow rate, facilitating the comparison of flow characteristics between different soils and model integration. The hydraulic conductivity coefficient converts the flow rate into a unified quantitative index, which is convenient for collaborative calculation with other parameters (such as meteorology, topography, etc.) in multi-factor analysis. In the digital twin soil monitoring model, the hydraulic conductivity coefficient can act together with other physical and chemical parameters to more accurately simulate the process of soil water movement and improve the accuracy of soil water dynamics prediction. For example, in regional soil water monitoring, with the help of the hydraulic conductivity coefficient, it is possible to quickly compare the water flow differences in soils of different plots, providing data support for water resource allocation and land use planning. Obtaining the soil water content enables real-time monitoring of the soil water status, providing direct data support for soil water dynamics monitoring and management. Soil water content, as a key indicator of soil water balance, directly affects plant growth, soil microbial activities, and soil physical and chemical processes. By obtaining the soil water content in real time, in digital twin soil monitoring, it is possible to update the soil water model in a timely manner, accurately simulate the process of soil water change, and provide a basis for decision-making such as precise irrigation, flood control, and drought resistance. For example, in agricultural production, adjusting the irrigation volume in a timely manner according to the soil water content can effectively avoid crop drought or waterlogging; in ecological restoration projects, monitoring the soil water content helps to evaluate the impact of vegetation restoration on soil water. In the past, traditional soil water monitoring methods had problems such as time lag or large measurement errors. Obtaining the initial soil porosity and water holding coefficient provides the initial state parameters of the soil and improves the construction of the soil water movement model. The initial porosity and water holding coefficient are important initial conditions for the soil water movement model, which reflect the physical characteristics of the soil when it is not affected by external interference. In digital twin soil monitoring, accurate initial parameters can enable the model to more accurately simulate the initial state of soil water movement and improve the accuracy of model prediction.For example, during the study of soil water infiltration, the initial porosity determines the ease of water entry into the soil, and the water holding coefficient affects the initial water retention capacity of the soil. These parameters are crucial for accurately simulating the infiltration process. In the past, when constructing a soil water model, the initial porosity and water holding coefficient might have been inaccurately estimated, leading to a large deviation in the model prediction results. Calculating the soil hydraulic conductivity variability comprehensively quantifies the changes in soil hydraulic conductivity by considering multiple factors, enabling a comprehensive assessment of the soil water movement trend. The soil hydraulic conductivity variability comprehensively considers multiple physical characteristic factors such as soil water holding capacity, hydraulic conductivity, porosity, water content, and their correlation coefficients, and can accurately reflect the conduction and changes of soil water under different conditions. In digital twin soil monitoring, the soil hydraulic conductivity variability, as a key indicator, can be used to monitor and predict the soil water movement trend in real time, providing a scientific basis for water resource management, agricultural irrigation, soil erosion prevention, etc. For example, during heavy rain, the runoff and infiltration of soil water can be predicted through the soil hydraulic conductivity variability, and flood prevention measures can be taken in advance to protect farmland and the ecological environment. In the past, relying solely on a single factor to evaluate soil water conduction changes had limitations. Based on the soil hydraulic conductivity variability, the soil water movement was constructed within the digital twin, and a dynamic soil water movement model was built based on actual data, realizing the visualization and simulation of the soil water process. Through this key indicator of the soil hydraulic conductivity variability, the soil water movement model constructed within the digital twin can truly reflect the dynamic change process of soil water under different conditions, and can intuitively display the conduction, distribution, and transformation of water in the soil. This helps to deeply study the mechanism of soil water movement and provides strong technical support for soil water resource management, agricultural irrigation optimization, ecological environment assessment, etc. For example, in agricultural research, the movement process of soil water under different irrigation methods can be simulated through this model, comparing the advantages and disadvantages of various irrigation schemes, and selecting the optimal irrigation strategy to improve crop yield and water resource utilization efficiency. Previously, it was difficult for traditional methods to dynamically and visually simulate and accurately predict soil water movement. Based on the soil water movement, multiple water regions of the digital twin soil were obtained, refining the study of soil water distribution and effectively revealing the spatial heterogeneity of soil water. By dividing the soil water movement simulation into multiple water regions, the distribution differences and change laws of soil water in different regions can be analyzed more meticulously, helping to deeply understand the spatial heterogeneity of soil water and its influencing factors. In digital twin soil monitoring, this provides more detailed information for precision agriculture, ecological protection, and water resource management. For example, in farmland, factors such as soil texture and terrain in different regions may lead to uneven water distribution. By dividing the water regions, targeted irrigation and fertilization management can be carried out to improve agricultural production efficiency; in wetland ecosystems, understanding the water distribution in different regions helps to protect wetland ecological functions. In the past, the assessment of soil water distribution was often overall, making it difficult to reflect the water differences in local areas.For example, in an orchard, the overall soil moisture content may be within the appropriate range, but there may be waterlogging in local low-lying areas, which affects the growth of fruit trees. By dividing the orchard into multiple moisture regions, these local problems can be detected in a timely manner, and corresponding measures can be taken, such as setting up drainage facilities in the waterlogged areas to improve the soil moisture condition and promote the healthy growth of fruit trees.

[0165] Step S413 obtains the physical change degree of soil moisture in each moisture region, quantifies the physical change of soil moisture in each moisture region, and realizes the accurate assessment of the dynamic soil moisture in the region. The physical change degree of soil moisture can accurately reflect the change degree of soil moisture in each moisture region during physical processes (such as evaporation, infiltration, runoff, etc.), providing detailed data for the accurate monitoring and management of soil moisture. In the digital twin soil monitoring, irrigation, drainage and other measures in each region can be adjusted in a timely manner according to the physical change degree of soil moisture to achieve the refined management of soil water resources. For example, in hillside terrace agriculture, the physical change degrees of soil moisture in different terraces may be different, and irrigation plans can be formulated separately according to their change situations to avoid water resource waste and the impact of insufficient or excessive soil moisture on crops. By judging whether each physical change degree of soil moisture exceeds the preset value, the abnormal soil moisture regions can be detected in a timely manner, providing a basis for soil moisture problem warning and decision-making. By comparing with the preset value, the regions with abnormal physical changes of soil moisture can be quickly identified, such as the regions with too fast water loss or excessive accumulation, so as to issue warning signals in a timely manner and take corresponding adjustment measures (such as increasing irrigation, improving drainage, etc.). In the digital twin soil monitoring, this helps to maintain the soil moisture balance and ensure the stability of agricultural production and ecological environment. For example, in urban green space management, if the physical change degree of soil moisture in a certain region exceeds the preset value, it may indicate that there are problems such as water leakage or waterlogging in this region, and timely treatment can avoid problems such as lawn withering or soil compaction. In the past, traditional soil monitoring methods may not be able to detect the abnormal changes of soil moisture in a timely manner, resulting in the accumulation of problems.

[0166] In one embodiment, the step of obtaining the soil chemical change degree according to the soil influence degree value and chemical characteristic information, and obtaining the second soil abnormal region based on the digital twin technology according to the soil chemical change degree includes:

[0167] S501. Obtain the real-time soil pH according to the soil pH characteristic;

[0168] S502. Obtain the historical soil pH, and obtain the real-time soil pH difference value according to the historical soil pH and the real-time soil pH;

[0169] S503. Obtain the acid-base weight coefficient according to the real-time soil pH difference value;

[0170] S504. Obtain the real-time nitrogen content according to the soil nitrogen characteristic;

[0171] S505. Obtain the historical nitrogen content of the soil, and obtain the soil nitrogen loss value according to the historical nitrogen content of the soil and the real-time nitrogen content.

[0172] S506. Obtain the nitrogen weight coefficient according to the soil nitrogen loss value.

[0173] S507. Obtain the real-time soil salt content according to the soil salt characteristics.

[0174] S508. Obtain the historical soil salt content, and obtain the soil salt change value according to the historical soil salt content and the real-time soil salt content.

[0175] S509. Obtain the salt weight coefficient according to the soil salt change value.

[0176] S510. Obtain the soil chemical change degree according to the real-time soil acidity-basicity difference value, the acidity-basicity weight coefficient, the soil nitrogen loss value, the nitrogen weight coefficient, the soil salt change value, and the salt weight coefficient.

[0177] S511. Construct the soil chemical change in the digital twin body according to the soil chemical change degree.

[0178] S512. Obtain multiple chemical change regions of the simulated soil in the digital twin body according to the soil chemical change.

[0179] S513. Obtain the soil chemical change degree of each chemical change region.

[0180] Judge whether the soil chemical change degree of each one exceeds a preset value.

[0181] If it exceeds, determine that the chemical change region is the second abnormal region of the soil.

[0182] If it does not exceed, determine that the chemical change region is normal.

[0183] As described in the above steps S501 - S513, the present invention obtains the real - time soil pH according to the soil pH characteristics, providing instant status information for soil chemical property monitoring. This measure is of great significance because soil pH has a profound impact on nutrient availability, microbial activity, and plant growth. Obtaining the pH in real - time can promptly reflect the dynamic changes in the soil chemical environment. In the digital twin soil monitoring, as basic data input, it enables the real - time update of the soil chemical model, accurately simulating chemical reactions such as nutrient transformation and heavy metal dissolution processes, providing a key basis for precision agriculture and ecological restoration. By obtaining the historical soil pH and calculating the real - time pH difference value, the degree of soil pH change is effectively quantified. The pH difference value obtained by comparing historical and real - time data visually shows the change trend and rate of soil chemical properties. In the digital twin soil monitoring system, this data helps to analyze the process of soil acidification or alkalization, predict the future change direction, plan countermeasures in advance, and maintain soil ecological stability. By obtaining the pH weight coefficient based on the real - time soil pH difference value, the relative importance of pH change in the assessment of soil chemical changes is highlighted. This coefficient is determined based on the pH difference value and can accurately reflect the impact degree of pH change on the overall chemical properties. In the digital twin soil monitoring model, a reasonable pH weight coefficient enables the pH factor to play an appropriate role in the comprehensive analysis of multiple factors, optimizing the assessment model and improving the accuracy of predicting soil chemical environment changes. By obtaining the real - time nitrogen content according to the soil nitrogen characteristics, the real - time monitoring of a key indicator of soil fertility is achieved. Nitrogen is an essential macronutrient for plant growth, and its real - time content is directly related to crop growth and yield. By obtaining the historical soil nitrogen content and calculating the nitrogen loss value, the soil nitrogen loss situation is successfully quantified. The loss value obtained by comparing historical and real - time nitrogen contents accurately reveals the degree and rate of nitrogen loss, providing an important basis for evaluating the soil fertility maintenance ability and environmental risks. By obtaining the nitrogen weight coefficient based on the soil nitrogen loss value, the importance of nitrogen loss in the assessment of soil chemical changes is clarified. This coefficient is determined based on the nitrogen loss value and can accurately reflect the impact degree of nitrogen loss on the overall chemical properties and fertility. By obtaining the real - time soil salt content according to the soil salt characteristics, the risk of soil salinization is effectively monitored. Excessive salt inhibits plant growth, and real - time monitoring of the salt content can promptly detect potential salinization risks. By obtaining the historical soil salt content and calculating the salt change value, the dynamic changes in soil salinity are accurately evaluated. The change value obtained by comparing historical and real - time salt contents clearly presents the process of soil salinization or desalinization, providing a key reference for salinization control and ecological restoration. By obtaining the salt weight coefficient based on the soil salt change value, the relative importance of salt change in the assessment of soil chemical changes is highlighted. This coefficient is determined based on the salt change value and can accurately reflect the impact degree of salt change on the overall chemical properties and ecological functions. By comprehensively considering multiple factors to obtain the soil chemical change degree, a comprehensive assessment of soil chemical property changes is achieved.This degree of change comprehensively considers the changes in key chemical factors such as acidity / alkalinity, nitrogen, and salinity, as well as their weights, and can accurately reflect the overall change trend and degree of the soil chemical environment. In digital twin soil monitoring, as a key indicator, it can monitor and predict the evolution of soil chemical properties in real time, providing a basis for fertility management and environmental protection. Based on the soil chemical change degree, soil chemical changes are constructed in the digital twin, realizing the dynamic simulation of soil chemical processes. The model built based on the chemical change degree can truly reproduce the dynamics of soil chemical reactions, such as acid-base neutralization and nutrient transformation, helping to deeply study the chemical mechanism and providing technical support for improvement and pollution control. Multiple chemical change regions are obtained according to the soil chemical changes, refining the study of the spatial distribution of soil chemical properties. Dividing the chemical change regions reveals the spatial heterogeneity of soil chemical properties, providing detailed information for precision agriculture and ecological restoration. For example, in farmland, different regions have different chemical properties due to differences in fertilization, irrigation, and texture. Dividing the regions can enable targeted fertilization improvement, increase efficiency, and obtain the soil chemical change degree of each chemical change region, accurately monitoring the regional soil chemical dynamics. By comprehensively mastering the chemical change degree of each region, precise data can be provided for regional soil management. In digital twin soil monitoring, management measures can be adjusted accordingly to achieve refined utilization. For example, in hillside terrace agriculture, different terraces have different chemical change degrees due to differences in terrain, irrigation, and fertilization. Based on this, separate plans can be formulated to improve soil quality and crop yields. In the past, it was difficult to understand local chemical changes in real time during large-scale management. For example, in large irrigation areas, if the chemical change degree of each field cannot be obtained, fertilization improvement measures lack pertinence. Now, by obtaining this indicator, for example, a flower planting base can adjust the flower layout according to the chemical change degree of different regions, improving quality and efficiency.

[0184] In one embodiment, the step of obtaining the ratio of the soil abnormal region according to the multiple soil first abnormal regions and the multiple soil second abnormal regions includes:

[0185] S601. Obtain the first abnormal quantity of the soil first abnormal region;

[0186] S602. Obtain the second abnormal quantity of the soil second abnormal region;

[0187] S603. Obtain the total quantity of the soil first abnormal region and the soil second abnormal region;

[0188] S604. Obtain the ratio of the soil abnormal region according to the first abnormal quantity, the second abnormal quantity, and the total quantity.

[0189] As described in the above steps S601 - S604, the present invention obtains the first abnormal quantity of the first abnormal area of the soil, and its beneficial effect is that it lays a quantitative foundation for the evaluation of the soil physical state. Accurately grasping the quantity of the first abnormal area (mainly involving abnormal soil physical properties, such as the water - conducting abnormal area) can clearly present the scale and distribution range of soil physical problems. In the digital twin soil monitoring system, this data is a key basis for subsequent in - depth analysis of the soil physical health status, and helps to accurately understand the stability and uniformity of the soil physical structure. Obtaining the second abnormal quantity of the second abnormal area of the soil is beneficial in that it realizes the quantification of the degree of abnormal soil chemical properties. The second abnormal quantity of the second abnormal area of the soil (mainly involving abnormal chemical properties, such as acid - base imbalance and nutrient abnormal area) can accurately reflect the severity and distribution breadth of soil chemical problems. In digital twin soil monitoring, this is of great benefit to evaluating the soil chemical fertility status and pollution risk. For example, in the field of agricultural production, by counting the second abnormal quantity of the soil nutrient abnormal area, it is possible to deeply understand the area range where a certain nutrient in the soil is lacking or excessive, so as to timely adjust the fertilization plan and avoid adverse effects on crop yield and quality caused by nutrient imbalance; in pollution monitoring, the degree of pollution diffusion can be accurately judged based on the quantity of the chemical pollution abnormal area, providing a scientific decision - making basis for pollution control. This step successfully solves the problem that it is difficult to determine the scope of the soil chemical abnormal area. In the soil monitoring around industrial polluted sites, traditional detection methods can often only find that the soil is chemically polluted, but cannot accurately grasp the specific scope of the polluted area. Obtaining the total quantity of the first abnormal area and the second abnormal area of the soil has the positive significance that it can comprehensively evaluate the overall abnormal situation of the soil from a macroscopic level. Adding the quantities of the soil physical and chemical abnormal areas to obtain the total quantity helps to grasp the health status of the soil from an overall perspective. In digital twin soil monitoring, this data provides a comprehensive and key reference basis for soil comprehensive management, which is conducive to formulating scientific and reasonable soil improvement, protection and utilization plans. For example, in the process of urban construction planning, understanding the total abnormal quantity of the soil in the area to be developed can effectively evaluate the impact of soil quality on construction projects. If the total abnormal quantity is too high, it may be necessary to pre - conduct soil remediation or adjust the land use method to avoid adverse consequences such as building settlement and environmental pollution caused by soil problems. This step properly solves the problem that there is a lack of quantitative indicators for the comprehensive evaluation of soil physical and chemical abnormalities. In the past, when evaluating soil quality, physical and chemical properties were usually considered separately, but there was a lack of quantitative indicators for organically combining the two. Taking the reclaimed land in mining areas as an example, the soil may suffer from dual problems of physical structure damage (such as subsidence and compaction) and chemical pollution (such as excessive heavy metals).By obtaining the total number of anomalies, the severity of soil problems can be comprehensively evaluated, and then a practical reclamation plan can be formulated based on the total number of anomalies, covering measures such as physical remediation (such as land leveling and soil improvement) and chemical remediation (such as heavy metal fixation and vegetation restoration), effectively improving the reclamation effect. The proportion of soil anomaly areas is obtained based on the first anomaly number, the second anomaly number, and the total number. Its significant advantage is that it can intuitively present the proportion of soil anomalies, greatly facilitating soil quality grading and decision-making. The proportion of soil anomaly areas shows the degree of soil anomaly conditions clearly in the form of a percentage by comparing the number of anomaly areas with the total number of areas. In digital twin soil monitoring, this indicator can be used to quickly grade soil quality. For example, by setting different threshold ranges, the soil can be divided into different grades such as excellent, good, medium, poor, and inferior, providing an intuitive and clear basis for soil management decisions. For example, in agricultural planting planning, the crop planting areas can be reasonably selected according to the proportion of soil anomaly areas. For areas with a lower proportion, crops with higher requirements for soil conditions are suitable for planting; while for areas with a higher proportion, soil improvement work should be carried out first or crop varieties with strong adaptability should be selected to improve agricultural production efficiency.

[0190] The present invention also discloses a soil monitoring system based on digital twin technology, which is characterized by comprising:

[0191] The first acquisition module 1 is used to acquire the real-time detection information and real-time environment information of the soil;

[0192] The second acquisition module 2 is used to acquire the characteristic classification information according to the real-time environment information, and acquire the soil influence degree value according to the type of the characteristic information classification;

[0193] The third acquisition module 3 is used to acquire the physical characteristic information and chemical characteristic information according to the real-time detection information;

[0194] The fourth acquisition module 4 is used to acquire the soil water conductivity change degree according to the soil influence degree value and the physical characteristic information, and acquire the first soil anomaly area based on the digital twin technology according to the soil change degree;

[0195] The fifth acquisition module 5 is used to acquire the soil chemical change degree according to the soil influence degree value and the chemical characteristic information, and acquire the second soil anomaly area based on the digital twin technology according to the soil chemical change degree;

[0196] The judgment module 6 is used to acquire the proportion of soil anomaly areas according to the multiple first soil anomaly areas and the multiple second soil anomaly areas, and judge whether the proportion of soil anomaly areas exceeds a preset value;

[0197] If it does not exceed, determine that the soil here is abnormal, and continuously obtain the real-time detection information and real-time environmental information of the soil;

[0198] If it exceeds, determine that the soil here is abnormal, and generate a soil warning message.

[0199] In one embodiment, the second acquisition module 2 includes:

[0200] The first acquisition unit is used to extract features from the real-time environmental information to obtain feature classification information, where the feature classification information includes meteorological feature information, topographic and geomorphic feature information, and biological community feature information;

[0201] The second acquisition unit is used to obtain historical meteorological feature information, historical topographic and geomorphic feature information, and historical biological community feature information;

[0202] The third acquisition unit is used to obtain environmental temperature change feature information, precipitation change feature information, and light change feature information according to the historical meteorological feature information and meteorological feature information;

[0203] The fourth acquisition unit is used to obtain a meteorological change value according to the environmental temperature change feature information, precipitation change feature information, and light change feature information;

[0204] The fifth acquisition unit is used to obtain a first weight coefficient according to the meteorological change value;

[0205] The sixth acquisition unit is used to obtain real-time slope change feature information and altitude change feature information according to the historical topographic and geomorphic feature information and topographic and geomorphic feature information;

[0206] The seventh acquisition unit is used to obtain a terrain change value according to the real-time slope change feature information and altitude change feature information;

[0207] The eighth acquisition unit is used to obtain a second weight coefficient according to the terrain change value;

[0208] The ninth acquisition unit is used to obtain vegetation change feature information and animal activity change feature information according to the historical biological community feature information and biological community feature information;

[0209] The tenth acquisition unit is used to obtain a biological community influence value according to the vegetation change feature information and animal activity change feature information;

[0210] The eleventh acquisition unit is used to obtain a third weight coefficient according to the biological community influence value;

[0211] A calculation unit, configured to obtain a soil impact degree value according to the meteorological change value, a first weight coefficient, a terrain change value, a second weight coefficient, a biotic community impact value, and a third weight coefficient, where the calculation formula is:

[0212]

[0213] wherein, K represents the soil impact degree value, A represents the meteorological change value, B represents the terrain change value, C represents the biotic community impact value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

[0214] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, value library, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0215] It should be noted that in this article, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusively, so that a process, apparatus, article, or method including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, apparatus, article, or method including that element.

[0216] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent results or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are similarly included in the patent protection scope of the present invention.

Claims

1. A soil monitoring method based on digital twin technology, characterized in that: include: Obtain real-time soil detection information and real-time environmental information; Acquire characteristic classification information according to the real-time environmental information, and acquire a soil impact degree value according to the type of the characteristic information classification; Acquire physical characteristic information and chemical characteristic information according to the real-time detection information; Acquire the soil water conductivity change degree according to the soil impact degree value and the physical characteristic information, and acquire the first abnormal area of ​​soil according to the soil change degree based on the digital twin technology; Acquire the soil chemical change degree according to the soil impact degree value and the chemical characteristic information, and acquire the second abnormal area of ​​the soil according to the soil chemical change degree based on the digital twin technology; Obtaining a soil abnormality area ratio value according to the plurality of first soil abnormality areas and the plurality of second soil abnormality areas, and determining whether the soil abnormality area ratio value exceeds a preset value; If not, the soil is judged to be abnormal, and real-time soil detection information and real-time environmental information are continuously obtained; If it exceeds, the soil here is judged to be abnormal and a soil warning message is generated.

2. A soil monitoring method based on digital twin technology according to claim 1, characterized in that: The step of acquiring characteristic classification information according to the real-time environmental information, and acquiring the soil impact degree value according to the type of the characteristic information classification includes: Extracting features from the real-time environmental information to obtain feature classification information, wherein the feature classification information includes meteorological feature information, topographic feature information, and biological community feature information; Obtain historical meteorological characteristics information, historical topographic and geomorphic characteristics information, and historical biological community characteristics information; Acquire ambient temperature change characteristic information, precipitation change characteristic information, and light change characteristic information according to the historical meteorological characteristic information and the meteorological characteristic information; Acquire a meteorological change value according to the ambient temperature change characteristic information, the precipitation change characteristic information, and the illumination change characteristic information; Acquire a first weight coefficient according to the meteorological change value; Acquire real-time slope change characteristic information and altitude change characteristic information according to the historical topographic and geomorphic characteristic information and the topographic and geomorphic characteristic information; Acquire a terrain change value according to the real-time slope change characteristic information and altitude change characteristic information; Acquire a second weight coefficient according to the terrain change value; Obtaining vegetation change characteristic information and animal activity change characteristic information based on the historical biome characteristic information and the biome characteristic information; Obtaining a biome impact value based on the vegetation change characteristic information and the animal activity change characteristic information; Obtaining a third weight coefficient according to the biome impact value; The soil impact degree value is obtained according to the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biological community impact value and the third weight coefficient, wherein the calculation formula is: Among them, K represents the soil impact value, A represents the meteorological change value, B represents the terrain change value, C represents the biological community impact value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

3. According to claim 1, a soil monitoring system based on digital twin technology is characterized in that: The step of acquiring physical characteristic information and chemical characteristic information according to the real-time detection information comprises: Acquire soil particle characteristic information according to the real-time detection information; Obtaining the ratio of sand, silt and clay particles according to the soil particle characteristic information, and obtaining the soil texture classification based on the ratio of sand, silt and clay particles; Obtain soil aggregation information based on soil texture classification; obtaining soil stability according to the soil aggregation information; obtaining soil porosity based on the soil stability; The soil pH characteristics, soil nitrogen characteristics and soil salinity characteristics are obtained according to the chemical characteristic information.

4. A soil monitoring system based on digital twin technology according to claim 3, characterized in that: The step of obtaining the soil water conductivity change degree according to the soil impact degree value and the physical characteristic information, and obtaining the first abnormal soil area according to the soil change degree based on the digital twin technology includes: Obtaining soil texture classification, soil stability, and soil porosity based on the physical characteristic information; obtaining soil water holding capacity based on the soil stability; obtaining a water holding capacity coefficient according to the soil water holding capacity; Based on said soil texture classification and soil hydraulic conductivity; Obtaining a hydraulic conductivity coefficient according to the soil hydraulic conductivity; obtaining a flow rate based on the soil porosity; Obtaining a mobility coefficient according to the mobility; Get the moisture content of the soil; Obtain the initial porosity and water holding coefficient of the soil; The soil water conductivity change degree is calculated according to the soil water holding capacity, water holding capacity coefficient, soil water conductivity, water conductivity coefficient, water conductivity coefficient, flow rate coefficient, water content, initial porosity and water holding coefficient, wherein the calculation formula is: Where P represents the soil water conductivity change, I m represents soil water holding capacity, α represents water holding capacity coefficient, I n represents soil hydraulic conductivity, β represents hydraulic conductivity coefficient, I h represents the hydraulic conductivity coefficient, γ represents the fluidity coefficient, W represents the water content, S represents the initial porosity and D represents the water holding coefficient; constructing soil moisture movement in the digital twin according to the soil water conductivity variation; Acquire a digital twin to simulate multiple soil moisture areas according to the soil moisture movement; Obtaining the physical change degree of soil moisture in each of the moisture areas; Determining whether each of the soil moisture physical change degrees exceeds a preset value; If it exceeds, the moisture area is determined to be the first abnormal soil area; If it does not exceed, the moisture range is determined to be normal.

5. The soil monitoring system based on digital twin technology according to claim 1 is characterized in that: The step of obtaining the soil chemical change degree according to the soil impact degree value and the chemical characteristic information, and obtaining the second abnormal soil area according to the soil chemical change degree based on the digital twin technology includes: Acquire the real-time soil pH according to the soil pH characteristics; Obtaining the historical pH value of the soil, and obtaining the real-time pH difference value of the soil according to the historical pH value of the soil and the real-time pH value of the soil; Obtaining an acid-base weight coefficient according to the real-time soil acid-base difference value; Obtaining real-time nitrogen content according to the soil nitrogen characteristics; Obtaining the historical nitrogen content of the soil, and obtaining the soil nitrogen loss value according to the historical nitrogen content of the soil and the real-time nitrogen content; Obtaining a nitrogen weight coefficient according to the soil nitrogen loss value; Obtaining real-time soil salt content according to the soil salt characteristics; Acquire the historical soil salt content, and acquire the soil salt change value according to the historical soil salt content and the real-time soil salt content; Obtaining a salt weight coefficient according to the soil salt change value; Obtaining the degree of soil chemical change according to the real-time soil pH difference value, the pH weight coefficient, the soil nitrogen loss value, the nitrogen weight coefficient, the soil salinity change value, and the salinity weight coefficient; constructing soil chemical changes in the digital twin according to the soil chemical change degree; Acquire a digital twin to simulate multiple chemical change areas of the soil according to the soil chemical changes; Obtaining the degree of soil chemical change in each of the chemical change areas; Determining whether each degree of soil chemical change exceeds a preset value; If it exceeds, the chemical change area is determined to be the second abnormal soil area; If it does not exceed, the chemical change area is judged to be normal.

6. The soil monitoring system based on digital twin technology according to claim 1 is characterized in that: The step of obtaining a soil abnormality area ratio value according to the plurality of first soil abnormality areas and the plurality of second soil abnormality areas comprises: Obtaining a first abnormal quantity of the first abnormal area of ​​the soil; Obtaining a second abnormal quantity of the second abnormal area of ​​the soil; Obtaining the total number of the first soil abnormality areas and the second soil abnormality areas; The soil abnormality area ratio value is obtained according to the first abnormality number, the second abnormality number and the total number.

7. A soil monitoring system based on digital twin technology, characterized in that: include: A first acquisition module is used to acquire real-time soil detection information and real-time environmental information; A second acquisition module is used to acquire characteristic classification information according to the real-time environmental information, and acquire a soil impact degree value according to the type of the characteristic information classification; A third acquisition module, used to acquire physical characteristic information and chemical characteristic information according to the real-time detection information; a fourth acquisition module, configured to acquire a soil water conductivity change degree according to the soil impact degree value and the physical characteristic information, and acquire a first abnormal soil area according to the soil change degree based on the digital twin technology; a fifth acquisition module, configured to acquire the soil chemical change degree according to the soil impact degree value and the chemical characteristic information, and acquire the second abnormal soil area according to the soil chemical change degree based on the digital twin technology; A judgment module, used for obtaining a soil abnormality area ratio value according to the plurality of first soil abnormality areas and the plurality of second soil abnormality areas, and judging whether the soil abnormality area ratio value exceeds a preset value; If not, the soil is judged to be abnormal, and real-time soil detection information and real-time environmental information are continuously obtained; If it exceeds, the soil here is judged to be abnormal and a soil warning message is generated.

8. A soil monitoring system based on digital twin technology, characterized in that: The second acquisition module includes: A first acquisition unit is used to extract features from the real-time environmental information to obtain feature classification information, wherein the feature classification information includes meteorological feature information, topographic feature information and biological community feature information; The second acquisition unit is used to acquire historical meteorological characteristic information, historical topographical characteristic information and historical biological community characteristic information; A third acquisition unit is used to acquire ambient temperature change characteristic information, precipitation change characteristic information, and light change characteristic information according to the historical meteorological characteristic information and the meteorological characteristic information; A fourth acquisition unit, configured to acquire a meteorological change value according to the ambient temperature change characteristic information, the precipitation change characteristic information, and the illumination change characteristic information; a fifth acquisition unit, configured to acquire a first weight coefficient according to the meteorological change value; A sixth acquisition unit, configured to acquire real-time slope change characteristic information and altitude change characteristic information according to the historical topographic and geomorphic characteristic information and the topographic and geomorphic characteristic information; a seventh acquisition unit, configured to acquire a terrain change value according to the real-time slope change characteristic information and the altitude change characteristic information; an eighth acquiring unit, configured to acquire a second weight coefficient according to the terrain change value; a ninth acquisition unit, configured to acquire vegetation change characteristic information and animal activity change characteristic information according to the historical biological community characteristic information and the biological community characteristic information; a tenth acquisition unit, configured to acquire a biome impact value according to the vegetation change characteristic information and the animal activity change characteristic information; an eleventh obtaining unit, configured to obtain a third weight coefficient according to the biome impact value; A calculation unit is used to obtain a soil impact degree value according to the meteorological change value, the first weight coefficient, the terrain change value, the second weight coefficient, the biological community impact value and the third weight coefficient, wherein the calculation formula is: Among them, K represents the soil impact value, A represents the meteorological change value, B represents the terrain change value, C represents the biological community impact value, X represents the first weight coefficient, Y represents the second weight coefficient, and Z represents the third weight coefficient.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images