An artificial intelligence-based soil big data analysis method, device and storage medium

Abstract

The embodiment of the application relates to the field of artificial intelligence technology, and discloses a soil big data analysis method and device based on artificial intelligence and a storage medium, which realizes multi-dimensional soil data dynamic collection and analysis through integrated hardware equipment of a telescopic sampling module, a soil humidity detection module and a heavy metal content detection module. First, after triggering an instruction at different preset time periods, the telescopic sampling module is used to obtain soil samples layer by layer, then the humidity and heavy metal content data of each layer of soil are synchronously detected and input into a multi-modal model for analysis, and finally the dynamic correlation between soil humidity and heavy metal content and intensity evaluation are output. In this way, through multi-depth, multi-time point sampling and modalized data integration, the limitation of traditional single-point static analysis is broken through, the spatial heterogeneity and time evolution characteristics of soil pollution are accurately captured, and accurate data support is provided for soil pollution remediation strategy optimization and environmental policy making.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, specifically to a method, device, and storage medium for soil big data analysis based on artificial intelligence. Background Technology

[0002] Soil pollution includes heavy metal pollution and persistent organic pollutant pollution, so sampling and testing of polluted soil, pollution data analysis, and feedback on pollution status have become important issues to be studied.

[0003] With the development of technology, multimodal data fusion analysis is gradually becoming a trend. However, existing soil analysis equipment has shortcomings in sampling and data processing, resulting in insufficient accuracy in evaluating soil quality and failing to meet the needs of environmental risk assessment. Summary of the Invention

[0004] The main objective of this invention is to provide a soil big data analysis method, device, and storage medium based on artificial intelligence, aiming to solve the technical problem that the existing technology does not accurately evaluate soil quality and is difficult to meet the needs of environmental risk assessment.

[0005] To achieve the above objectives, in a first aspect, this application provides an artificial intelligence-based soil big data analysis method applied to a soil analysis device. The soil analysis device includes a retractable sampling module, a soil moisture detection module, and a heavy metal content detection module. The method includes: Obtain soil analysis commands triggered at different preset time periods, and control the telescopic sampling module to perform multimodal soil sampling according to the soil analysis commands to obtain first-mode soil and second-mode soil at different depths; The first mode soil moisture data and the second mode soil moisture data are obtained based on the detection data of the soil moisture detection module. The heavy metal content data of the first mode of soil and the heavy metal content data of the second mode of soil are obtained based on the detection data of the heavy metal content detection module. The soil moisture data of the first mode, the soil moisture data of the second mode, the soil heavy metal content data of the first mode, and the soil heavy metal content data of the second mode are input into the analysis model to obtain the evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed includes at least the correlation and correlation strength between soil moisture and soil heavy metal content.

[0006] In one possible implementation, the soil moisture detection module includes a soil moisture detection capacitor, which includes a first electrode plate and a second electrode plate. The controlled telescopic sampling module performs multimodal soil sampling to obtain first-mode and second-mode soil at different depths, including: The telescopic sampling module is controlled to penetrate into the first soil layer to collect soil samples and obtain the first mode of soil. The first modal soil is placed between the first electrode plate and the second electrode plate to form a first target capacitor, wherein the first modal soil serves as the dielectric material of the first target capacitor; and / or, The telescopic sampling module is controlled to penetrate into the second soil layer to collect soil samples and obtain the second soil modality, which is different from the first soil layer. The second modal soil is placed between the first electrode plate and the second electrode plate to form a second target capacitor, wherein the second modal soil serves as the dielectric material of the second target capacitor.

[0007] In one possible implementation, obtaining the first modal soil moisture data and the second modal soil moisture data based on the detection data from the soil moisture detection module includes: Based on the detection data of the first target capacitor, the initial soil moisture values ​​of the first mode at different preset time periods are obtained; The initial humidity value data of the first mode soil is corrected based on the ambient air humidity to obtain the target humidity value data of the first mode soil; Soil target moisture value data for the first mode are sorted chronologically to form soil moisture curve data for the first mode; and / or, Based on the detection data of the second target capacitor, the initial soil moisture values ​​of the second mode at different preset time periods are obtained; The initial soil humidity value data of the second mode is corrected based on the ambient air humidity to obtain the target soil humidity value data of the second mode; The soil target humidity value data of the second mode are sorted according to time sequence to form the soil humidity curve data of the second mode.

[0008] In one possible implementation, the step of correcting the initial humidity value data of the first modal soil based on the ambient air humidity to obtain the target humidity value data of the first modal soil includes: The initial humidity value of the first mode soil is corrected based on the ambient air humidity value sensed by the air humidity sensor to obtain the target humidity value of the first mode soil; Specifically, when the ambient air humidity value is greater than the preset humidity value, the initial humidity value of the first modal soil is reversed; when the ambient air humidity value is less than the preset humidity value, the initial humidity value of the first modal soil is positively corrected.

[0009] In one possible implementation, obtaining the initial soil moisture values ​​for a first mode over preset time periods based on the detection data of the first target capacitor includes: Obtain the capacitance value of the first target capacitor; The capacitance value of the first target capacitor is input into a pre-trained humidity prediction model to obtain the initial soil humidity value for the first mode, wherein the humidity prediction model satisfies the following expression: (C≥16.4pF), where, Humidity is expressed as a percentage (%), and capacitance is expressed as a pF.

[0010] In one possible implementation, the heavy metal content detection module includes a fluorescence detection camera, and obtaining the first mode soil heavy metal content data and the second mode soil heavy metal content data based on the detection data from the heavy metal content detection module includes: The first target image is obtained by acquiring detection images of the first modality of soil captured by the fluorescence detection camera at different preset time periods; The second target image is obtained by acquiring detection images of the second modality of soil captured by the fluorescence detection camera at different preset time periods; The first target image and the second target image are respectively input into the soil heavy metal image analysis model to obtain the first mode soil heavy metal content data and the second mode soil heavy metal content data; The soil heavy metal content data of the first mode are sorted according to time sequence to obtain the soil heavy metal content curve data of the first mode; The heavy metal content data of the second mode soil were sorted according to time sequence to obtain the heavy metal content curve data of the second mode soil.

[0011] In one possible implementation, the step of inputting the first modal soil moisture data, the second modal soil moisture data, the first modal soil heavy metal content data, and the second modal soil heavy metal content data into the analysis model to obtain the evaluation information of the soil to be analyzed includes: By inputting the soil moisture curve data of the first mode, the soil moisture curve data of the second mode, the soil heavy metal content curve data of the first mode, and the soil heavy metal content curve data of the second mode into the analysis model, the correlation between soil moisture and soil heavy metal content and the correlation strength are obtained.

[0012] In one possible implementation, the step of inputting the first modal soil moisture curve data, the second modal soil moisture curve data, the first modal soil heavy metal content curve data, and the second modal soil heavy metal content curve data into the analysis model to obtain the correlation and correlation strength between soil moisture and soil heavy metal content includes: The curve is identified by image analysis technology, and the curve is divided into a first correlation part and a second correlation part according to the curve's trend. The first correlation part indicates that soil moisture and soil heavy metal content satisfy a first correlation relationship, and the second correlation part indicates that soil moisture and soil heavy metal content satisfy a second correlation relationship. The correlation strength between soil moisture and soil heavy metal content in different modes of soil in the first and second correlation components was calculated using the correlation coefficient formula, wherein the correlation coefficient formula satisfies the following expression: ; Where r represents the correlation coefficient, the closer the absolute value of r is to 1, the stronger the correlation between the two; the closer r is to 0, the weaker the correlation between the two; n is the sample size; xi represents the i-th soil moisture data. The average value of soil moisture data; yi represents the i-th soil heavy metal content data. This represents the average value of soil heavy metal content data.

[0013] Secondly, this application also provides a soil analysis device, including: a memory and a processor, wherein the memory is used to store program code; and the processor is used to call the program code to execute the method as described in the first aspect.

[0014] Thirdly, this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in the first aspect.

[0015] Unlike existing technologies, this application provides an artificial intelligence-based soil big data analysis method. By integrating a retractable sampling module, a soil moisture detection module, and a heavy metal content detection module, it achieves dynamic acquisition and analysis of multi-dimensional soil data. First, after triggering commands at different preset time periods, the retractable sampling module acquires soil samples layer by layer (first and second modal soils). Then, the moisture and heavy metal content data of each soil layer are simultaneously detected and input into a multimodal DBM model for analysis. Finally, the dynamic correlation and intensity evaluation between soil moisture and heavy metal content are output. Thus, through multi-depth, multi-time-point sampling and modal data integration, the limitations of traditional single-point static analysis are overcome, accurately capturing the spatial heterogeneity and temporal evolution characteristics of soil pollution, providing accurate data support for optimizing soil pollution remediation strategies and formulating environmental policies. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the structure of the soil analysis device in some embodiments of this application; Figure 2 This is a flowchart illustrating an artificial intelligence-based soil big data analysis method in some embodiments of this application; Figure 3 This is a flowchart illustrating step S600 of the artificial intelligence-based soil big data analysis method in some embodiments of this application; Figure 4 This is a schematic diagram of soil data curves in some embodiments of this application; Figure 5 This is a schematic diagram of the hardware structure of the soil analysis device in some embodiments of this application.

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0021] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the term "and / or" throughout the text includes three solutions; taking A and / or B as an example, it includes technical solution A, technical solution B, and a technical solution that simultaneously satisfies A and B. Furthermore, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of a person skilled in the art to implement them. When the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0022] Soil pollution includes heavy metal pollution and persistent organic pollutant pollution, so sampling and testing of polluted soil, pollution data analysis, and feedback on pollution status have become important issues to be studied.

[0023] With the development of technology, multimodal data fusion analysis is gradually becoming a trend. However, existing soil analysis equipment has shortcomings in sampling and data processing, resulting in insufficient accuracy in evaluating soil quality and failing to meet the needs of environmental risk assessment.

[0024] To solve the above problems, such as Figure 1 As shown in the figure, this application embodiment provides a soil analysis device 100. The device includes a telescopic sampling module (not shown), a soil moisture detection module 110, and a heavy metal content detection module 120.

[0025] The soil moisture detection module 110 uses a capacitive sensor. Its working principle is that when soil is placed in the capacitive sensor as a dielectric material, the sensor can detect the corresponding capacitance value, and then deduce the soil moisture value based on the relationship between the capacitance value and the moisture content.

[0026] The heavy metal content testing module 120 uses fluorescence detection technology to determine the heavy metal content in soil. Specifically, it takes images of the soil using a fluorescence camera, then analyzes and processes the images to obtain the heavy metal content data.

[0027] Specifically, the soil moisture detection module 110 includes an upper electrode plate 111 and a lower electrode plate 112. The upper electrode plate 111, the soil 130, and the lower electrode plate 112 together constitute a target capacitor for detecting soil moisture.

[0028] like Figures 1-4As shown, the following explanation uses a soil analysis device to perform this AI-based soil big data analysis method. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order. Please refer to the appendix. Figure 2 The method includes the following steps S200-S800: Step S200: Obtain soil analysis instructions triggered at different preset time periods, and control the telescopic sampling module to perform multimodal soil sampling according to the soil analysis instructions to obtain first-mode soil and second-mode soil at different depths; Specifically, the soil analysis equipment is placed on the soil to be analyzed. Soil sampling and analysis commands are then triggered at preset times (e.g., every 20 minutes or every day). Upon receiving the command, the equipment controls a telescopic sampling module to perform multimodal soil sampling, obtaining first and second modal soil samples at different depths. That is, after each analysis command is triggered, the telescopic sampling module performs two soil samplings, collecting soil samples at the first depth (e.g., the top 2cm depth) and the second depth (e.g., the bottom 20cm depth).

[0029] In one embodiment, the step of controlling the telescopic sampling module to perform multimodal soil sampling to obtain first modal soil and second modal soil at different depths includes: controlling the telescopic sampling module to penetrate into a first depth soil layer to obtain first modal soil; placing the first modal soil between a first electrode plate and a second electrode plate to form a first target capacitor, wherein the first modal soil serves as the dielectric material of the first target capacitor; and / or, controlling the telescopic sampling module to penetrate into a second depth soil layer to obtain second modal soil, wherein the second depth soil layer is different from the first depth soil layer; placing the second modal soil between the first electrode plate and the second electrode plate to form a second target capacitor, wherein the second modal soil serves as the dielectric material of the second target capacitor.

[0030] Specifically, through remote control or a preset program, a telescopic sampling module is inserted into a designated first soil depth to obtain a soil sample from that depth, representing the first modality of soil. The obtained first modality of soil is then placed between a first electrode plate and a second electrode plate, thus becoming the dielectric material of the first target capacitor. After the analysis of the first modality of soil is completed, the position of the telescopic sampling module is adjusted to insert into a second soil depth to obtain a soil sample from that depth, representing the second modality of soil. The obtained second modality of soil is then placed between the first electrode plate and the second electrode plate, thus becoming the dielectric material of the second target capacitor. In other words, different modalities of soil analysis are performed by using two capacitive sensors.

[0031] Based on this, embodiments of this application control a telescopic sampling module to perform multimodal (i.e., different depth) sampling of the soil, and place the obtained soil samples between electrode plates to form a capacitor, using the soil as the dielectric material of the capacitor. This allows the analysis of soil moisture values ​​using the characteristics of the capacitor.

[0032] Step S400: Obtain the first mode soil moisture data and the second mode soil moisture data based on the detection data of the soil moisture detection module; It's important to note that the capacitance sensor outputs a capacitance value, while the humidity value of the dielectric material and the capacitance value sensed by the sensor are correlated. Specifically, when the soil moisture content is sufficiently high and increases, the gaps between soil particles are filled with water. The polarity of water molecules enhances the soil's polarization ability in an electric field, leading to an increase in the dielectric constant. Furthermore, with other parameters constant, the higher the dielectric constant of the soil, the greater the capacitance value. In other words, when the soil moisture content exceeds a certain threshold, the capacitance value output by the capacitance sensor is positively correlated with the soil moisture content.

[0033] It is understandable that, since the space between the two electrode plates of the capacitor is filled not only with soil but also with air, and the air humidity also has a certain impact on the soil's moisture content and other properties. Therefore, in one embodiment, step S400: obtaining the first modal soil moisture data and the second modal soil moisture data based on the detection data from the soil moisture detection module includes: Based on the detection data of the first target capacitor, the initial soil moisture values ​​of the first mode at different preset time periods are obtained; The initial humidity value data of the first mode soil is corrected based on the ambient air humidity to obtain the target humidity value data of the first mode soil; Soil target moisture value data for the first mode are sorted chronologically to form soil moisture curve data for the first mode; and / or, Based on the detection data of the second target capacitor, the initial soil moisture values ​​of the second mode at different preset time periods are obtained; The initial soil humidity value data of the second mode is corrected based on the ambient air humidity to obtain the target soil humidity value data of the second mode; The soil target humidity value data of the second mode are sorted according to time sequence to form the soil humidity curve data of the second mode.

[0034] Specifically, for the first target capacitor, its detection data is used to obtain the initial soil moisture values ​​for the first mode at different preset time periods. That is, at each preset time point, the capacitance value is recorded and converted into a moisture value. Since there is not only soil but also air between the capacitor plates, and air humidity affects the capacitance value (and thus the moisture value calculation), the initial moisture value data for the first mode needs to be corrected. The corrected first-mode soil target moisture value data is then sorted chronologically to form the first-mode soil moisture curve data. This ensures accurate soil moisture data while facilitating the analysis model's analysis of moisture trends over time. The data processing method for the second target capacitor is the same as that for the first target capacitor, and will not be repeated here. Figure 4 As shown, curve S1 represents the soil moisture curve data for the first mode, and curve S2 represents the soil moisture curve data for the second mode. It can be seen that the soil moisture in the first mode is higher than that in the second mode.

[0035] In one specific embodiment, obtaining initial soil moisture values ​​for a first mode at different preset time periods based on the detection data of the first target capacitor includes: acquiring the capacitance detection value of the first target capacitor; inputting the capacitance detection value of the first target capacitor into a pre-trained moisture prediction model to obtain the initial soil moisture value for the first mode, wherein the moisture prediction model satisfies the following expression: (C≥16.4pF), where, Humidity is expressed as a percentage (%), and capacitance is expressed as a pF.

[0036] In this embodiment, the above expression is first obtained by training a humidity prediction model based on a large amount of data. Then, the capacitance detection value of the first target capacitor is input into the pre-trained humidity prediction model to obtain the initial soil humidity value for the first mode. That is, each input of a capacitance detection value for a preset time period yields a corresponding initial soil humidity value for the first mode. The calculation process for the initial soil humidity value of the second mode is similar to that of the first mode, and will not be described in detail here.

[0037] The correction of the initial soil humidity value data of the first mode can be obtained by correcting the initial soil humidity value data of the first mode based on the ambient air humidity value sensed by the air humidity sensor; similarly, the correction of the initial soil humidity value data of the second mode can be obtained by correcting the initial soil humidity value data of the second mode based on the ambient air humidity value sensed by the air humidity sensor.

[0038] Specifically, when the ambient air humidity is higher than the preset humidity value, it indicates that there is more moisture in the air, which may increase the capacitance value of the capacitor, resulting in an overestimation of the soil moisture value calculated from the capacitance value. Therefore, a reverse correction is needed for the initial soil moisture value of the first mode, i.e., decreasing the humidity value, to obtain a more accurate target humidity value. When the ambient air humidity is lower than the preset humidity value, it indicates that there is less moisture in the air, which may decrease the capacitance value of the capacitor, resulting in an underestimation of the soil moisture value calculated from the capacitance value. Therefore, a forward correction is needed for the initial soil moisture value of the first mode, i.e., increasing the humidity value, to obtain a more accurate target humidity value. The specific forward and reverse correction ranges can be determined based on actual conditions (such as soil type, capacitor characteristics, environmental conditions, etc.).

[0039] Step S600: Obtain the heavy metal content data of the first mode soil and the heavy metal content data of the second mode soil based on the detection data of the heavy metal content detection module; In one embodiment, step S600, obtaining heavy metal content data of the first mode of soil and heavy metal content data of the second mode of soil based on the detection data of the heavy metal content detection module, includes: S610. Obtain the detection images of the first modality of soil captured by the fluorescence detection camera at different preset time periods to obtain the first target image; S620. Obtain the detection images of the second modality soil captured by the fluorescence detection camera at different preset time periods to obtain the second target image; S630. Input the first target image and the second target image into the soil heavy metal image analysis model to obtain the first mode soil heavy metal content data and the second mode soil heavy metal content data, respectively. S640. Soil heavy metal content data of the first mode is sorted according to time sequence to obtain soil heavy metal content curve data of the first mode; S650. Soil heavy metal content data of the second mode are sorted according to time sequence to obtain soil heavy metal content curve data of the second mode.

[0040] Specifically, a fluorescence detection camera is used to photograph the first mode of soil at different preset time periods. Image data of the first mode of soil at different time points is acquired for subsequent analysis. A series of detection images of the first mode of soil are obtained, serving as the first target image. Similarly, a fluorescence detection camera is used to photograph the second mode of soil at the same or different preset time periods. Image data of the second mode of soil at different time points is acquired. A series of detection images of the second mode of soil are obtained, serving as the second target image. Then, the first and second target images are respectively input into a soil heavy metal image analysis model. This model can analyze the fluorescence signals in the images and convert them into heavy metal content values. The soil heavy metal content values ​​are extracted from the image data, thus obtaining the heavy metal content data of the first and second modes of soil. Finally, the heavy metal content data of the first and second modes of soil are sorted in chronological order to obtain the heavy metal content curve data of the first and second modes of soil. Figure 4 As shown, curve H1 represents the heavy metal content data of the first soil mode, and curve H2 represents the heavy metal content data of the second soil mode. It can be seen that the heavy metal content of the first soil mode is lower than that of the second soil mode.

[0041] Step S800: Input the first modal soil moisture data, the second modal soil moisture data, the first modal soil heavy metal content data, and the second modal soil heavy metal content data into the analysis model to obtain the evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed includes at least the correlation and correlation strength between soil moisture and soil heavy metal content.

[0042] After obtaining the soil moisture data for the first mode, the soil moisture data for the second mode, the soil heavy metal content data for the first mode, and the soil heavy metal content data for the second mode, the relationship between the two variables of moisture and heavy metal content can be evaluated and analyzed based on the data.

[0043] In one embodiment, the soil moisture curve data of the first mode, the soil moisture curve data of the second mode, the soil heavy metal content curve data of the first mode, and the soil heavy metal content curve data of the second mode can be input into the analysis model to obtain the correlation and correlation strength between soil moisture and soil heavy metal content.

[0044] by Figure 5 The obtained soil moisture curve data of the first mode, soil moisture curve data of the second mode, soil heavy metal content curve data of the first mode, and soil heavy metal content curve data of the second mode are used as basic analysis data.

[0045] Specifically, the pre-trained analysis model in this application first identifies the trend of the curve using image analysis technology, and then divides the curve into a first correlation part B1 and a second correlation part B2 based on the trend. The trend shows that the first correlation part B1 indicates that the soil heavy metal content increases with increasing soil moisture (first correlation), while the second correlation part B2 indicates that the soil heavy metal content decreases with increasing soil moisture (second correlation). Finally, the correlation strength between soil moisture and soil heavy metal content in different modes of soil in the first and second correlation parts can be calculated using the correlation coefficient formula, wherein the correlation coefficient formula satisfies the following expression: ; Where r represents the correlation coefficient, the closer the absolute value of r is to 1, the stronger the correlation between the two; the closer r is to 0, the weaker the correlation between the two; n is the sample size; xi represents the i-th soil moisture data. The average value of soil moisture data; yi represents the i-th soil heavy metal content data. This represents the average value of soil heavy metal content data.

[0046] Therefore, the correlation and quantitative strength between soil moisture and heavy metal content can serve as a basis for soil environmental remediation and improvement. For example, when analysis shows a significant negative correlation between soil moisture and heavy metal content (e.g., r = -0.75), a targeted control strategy can be adopted: increasing soil moisture content to 60%-70% of field capacity via drip irrigation to trigger the water-seeking response mechanism of plant roots. Basic knowledge indicates that when soil moisture reaches a certain value, continued moderate humidity can increase the surface area of ​​plant roots by 23%-35%, while simultaneously promoting the secretion of organic acids (such as citric acid and malic acid), increasing their concentration by 1.8-2.5 times. These secretions, through chelation, convert insoluble heavy metals in the soil into bioavailable forms. Combined with transpiration-driven mass transport, this leads to a decrease in the content of heavy metals such as cadmium in the topsoil (0-20cm), meeting the standards for agricultural land soil pollution risk management. The quantitative correlation between soil moisture and heavy metal content derived from the above model analysis can be combined with theoretical knowledge to carry out other soil environmental management and improvement, which will not be illustrated here.

[0047] Based on this, this application provides an artificial intelligence-based soil big data analysis method. By integrating a hardware device with a scalable sampling module, a soil moisture detection module, and a heavy metal content detection module, it achieves dynamic acquisition and analysis of multi-dimensional soil data. First, after triggering commands at different preset time periods, the scalable sampling module acquires soil samples layer by layer (first and second modal soils). Then, the moisture and heavy metal content data of each soil layer are simultaneously detected and input into a multimodal DBM model for analysis. Finally, the dynamic correlation and intensity evaluation between soil moisture and heavy metal content are output. Thus, through multi-depth, multi-time-point sampling and modal data integration, the limitations of traditional single-point static analysis are overcome, accurately capturing the spatial heterogeneity and temporal evolution characteristics of soil pollution, providing high-resolution and accurate data support for optimizing soil pollution remediation strategies and formulating environmental policies.

[0048] like Figure 5 As shown, Figure 5 The diagram below shows the hardware structure of a soil analysis device in some embodiments of this application. The soil analysis device provided in the embodiments of this application also includes a memory 1000 and a processor 2000. The memory 1000 is used to store computer-readable instructions, and the processor 2000 is used to call the computer-readable instructions to execute the artificial intelligence-based soil big data analysis method as described above.

[0049] The processor 2000 provides computing and control capabilities to control the soil analysis equipment to perform corresponding tasks. For example, it controls the soil analysis equipment to perform the artificial intelligence-based soil big data analysis method in any of the above method embodiments. The method includes: acquiring soil analysis instructions triggered at preset time periods, and controlling a telescopic sampling module to perform multimodal soil sampling to obtain first-mode soil and second-mode soil at different depths according to the soil analysis instructions; obtaining first-mode soil moisture data and second-mode soil moisture data according to the detection data of the soil moisture detection module; obtaining first-mode soil heavy metal content data and second-mode soil heavy metal content data according to the detection data of the heavy metal content detection module; inputting the first-mode soil moisture data, second-mode soil moisture data, first-mode soil heavy metal content data, and second-mode soil heavy metal content data into an analysis model to obtain evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed includes at least the correlation and correlation strength between soil moisture and soil heavy metal content.

[0050] The processor 2000 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The aforementioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0051] The memory 1000, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the artificial intelligence-based soil big data analysis method in the embodiments of this application. The processor 2000 can implement the artificial intelligence-based soil big data analysis method in any of the above method embodiments by running the non-transitory software programs, instructions, and modules stored in the memory 1000.

[0052] Specifically, memory 1000 may include volatile memory (VM), such as random access memory (RAM); memory 1000 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), solid-state drive (SSD), or other non-transitory solid-state storage devices; memory 1000 may also include combinations of the above types of memory.

[0053] In summary, the soil analysis device of this application adopts the technical solution of any of the above-mentioned embodiments of the artificial intelligence-based soil big data analysis method. Therefore, it has at least the beneficial effects brought about by the technical solutions of the above embodiments, which will not be elaborated here.

[0054] This application also provides a computer-readable storage medium, such as a memory including program code, which can be executed by a processor to complete the artificial intelligence-based soil big data analysis method described in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), magnetic tape, floppy disk, or optical data storage device, etc.

[0055] This application also provides a computer program product comprising one or more lines of program code stored in a computer-readable storage medium. The processor of the early warning system reads the program code from the computer-readable storage medium and executes the program code to complete the steps of the artificial intelligence-based soil big data analysis method provided in the above embodiments.

[0056] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware, or by a program or program code related to hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0057] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0058] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software and a general-purpose hardware platform, or of course, using hardware. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0059] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural transformations made using the contents of the present invention's specification and drawings under the inventive concept of the present invention, or direct / indirect applications in other related technical fields, are included within the patent protection scope of the present invention.

Claims

1. A soil big data analysis method based on artificial intelligence, characterized in that, The method is applied to soil analysis equipment, which includes a telescopic sampling module, a soil moisture detection module, and a heavy metal content detection module. Obtain soil analysis commands triggered at different preset time periods, and control the telescopic sampling module to perform multimodal soil sampling according to the soil analysis commands to obtain first-mode soil and second-mode soil at different depths; The first mode soil moisture data and the second mode soil moisture data are obtained based on the detection data of the soil moisture detection module. The heavy metal content data of the first mode of soil and the heavy metal content data of the second mode of soil are obtained based on the detection data of the heavy metal content detection module. The soil moisture data of the first mode, the soil moisture data of the second mode, the soil heavy metal content data of the first mode, and the soil heavy metal content data of the second mode are input into the analysis model to obtain the evaluation information of the soil to be analyzed. The evaluation information of the soil to be analyzed includes at least the correlation and correlation strength between soil moisture and soil heavy metal content. The soil moisture detection module includes a soil moisture detection capacitor, which includes a first electrode plate and a second electrode plate. The controlled telescopic sampling module performs multimodal soil sampling to obtain first-mode and second-mode soil samples at different depths, including: The telescopic sampling module is controlled to penetrate into the first soil layer to collect soil samples and obtain the first mode of soil. The first modal soil is placed between the first electrode plate and the second electrode plate to form a first target capacitor, wherein the first modal soil serves as the dielectric material of the first target capacitor; and / or, The telescopic sampling module is controlled to penetrate into the second soil layer to collect soil samples and obtain the second soil modality, which is different from the first soil layer. The second modal soil is placed between the first electrode plate and the second electrode plate to form a second target capacitor, wherein the second modal soil serves as the dielectric material of the second target capacitor; The process of obtaining the first modal soil moisture data and the second modal soil moisture data based on the detection data from the soil moisture detection module includes: Based on the detection data of the first target capacitor, the initial soil moisture values ​​of the first mode at different preset time periods are obtained; The initial humidity value data of the first mode soil is corrected based on the ambient air humidity to obtain the target humidity value data of the first mode soil; Soil target moisture value data for the first mode are sorted chronologically to form soil moisture curve data for the first mode; and / or, Based on the detection data of the second target capacitor, the initial soil moisture values ​​of the second mode at different preset time periods are obtained; The initial soil humidity value data of the second mode is corrected based on the ambient air humidity to obtain the target soil humidity value data of the second mode; The soil target moisture value data of the second mode are sorted according to time sequence to form the soil moisture curve data of the second mode; The step of obtaining the initial soil moisture values ​​for the first mode at different time periods based on the detection data of the first target capacitor includes: Obtain the capacitance value of the first target capacitor; The capacitance value of the first target capacitor is input into a pre-trained humidity prediction model to obtain the initial soil humidity value for the first mode, wherein the humidity prediction model satisfies the following expression: (C≥16.4pF), where, Humidity is expressed as a percentage (%), and capacitance is expressed as a pF.

2. The soil big data analysis method based on artificial intelligence as described in claim 1, wherein correcting the initial humidity value data of the first modal soil according to the ambient air humidity to obtain the target humidity value data of the first modal soil includes: The initial humidity value of the first mode soil is corrected based on the ambient air humidity value sensed by the air humidity sensor to obtain the target humidity value of the first mode soil; Specifically, when the ambient air humidity value is greater than the preset humidity value, the initial humidity value of the first modal soil is reversed; when the ambient air humidity value is less than the preset humidity value, the initial humidity value of the first modal soil is positively corrected.

3. The soil big data analysis method based on artificial intelligence as described in claim 1, wherein the heavy metal content detection module includes a fluorescence detection camera, and the step of obtaining the first mode soil heavy metal content data and the second mode soil heavy metal content data based on the detection data of the heavy metal content detection module includes: The first target image is obtained by acquiring detection images of the first modality of soil captured by the fluorescence detection camera at different preset time periods; The second target image is obtained by acquiring detection images of the second modality of soil taken by the fluorescence detection camera at different preset time periods; The first target image and the second target image are respectively input into the soil heavy metal image analysis model to obtain the first mode soil heavy metal content data and the second mode soil heavy metal content data; The soil heavy metal content data of the first mode are sorted according to time sequence to obtain the soil heavy metal content curve data of the first mode; The heavy metal content data of the second mode soil were sorted according to time sequence to obtain the heavy metal content curve data of the second mode soil.

4. The soil big data analysis method based on artificial intelligence as described in claim 3, wherein inputting the first modal soil moisture data, the second modal soil moisture data, the first modal soil heavy metal content data, and the second modal soil heavy metal content data into the analysis model to obtain the evaluation information of the soil to be analyzed includes: By inputting the soil moisture curve data of the first mode, the soil moisture curve data of the second mode, the soil heavy metal content curve data of the first mode, and the soil heavy metal content curve data of the second mode into the analysis model, the correlation between soil moisture and soil heavy metal content and the correlation strength are obtained.

5. The soil big data analysis method based on artificial intelligence as described in claim 4, wherein inputting the first modal soil moisture curve data, the second modal soil moisture curve data, the first modal soil heavy metal content curve data, and the second modal soil heavy metal content curve data into the analysis model to obtain the correlation relationship and correlation strength between soil moisture and soil heavy metal content includes: The curve is identified by image analysis technology, and the curve is divided into a first correlation part and a second correlation part according to the curve's trend. The first correlation part indicates that soil moisture and soil heavy metal content satisfy a first correlation relationship, and the second correlation part indicates that soil moisture and soil heavy metal content satisfy a second correlation relationship. The correlation strength between soil moisture and soil heavy metal content in different modes of soil in the first and second correlation components was calculated using the correlation coefficient formula, wherein the correlation coefficient formula satisfies the following expression: Where r represents the correlation coefficient, the closer the absolute value of r is to 1, the stronger the correlation between the two; the closer r is to 0, the weaker the correlation between the two; n is the sample size; x i Represents the i-th soil moisture data. y represents the average soil moisture data; i This represents the i-th soil heavy metal content data. This represents the average value of soil heavy metal content data.

6. A soil analysis device, characterized in that, Also includes: Memory and processor, wherein the memory is used to store program code; The processor is used to call the program code to perform the method as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images