Soil micro-plastic pollution monitoring and analyzing method based on big data analysis

Abstract

The invention discloses a soil micro-plastic pollution monitoring analysis method based on big data analysis, and relates to the technical field of monitoring analysis. Comprising the following steps: arranging a sensor and sampling equipment, and collecting micro-plastic data; the method comprises the following steps: researching migration and diffusion laws of micro-plastic data in soil in different time periods by utilizing a time sequence analysis method, and constructing a dynamic migration model of micro-plastic in combination with meteorological conditions and geographical conditions; the method comprises the following steps: performing spatial analysis on micro-plastic concentration data of a monitoring area, identifying a high-risk area of micro-plastic pollution, and preliminarily determining a gathering area and a pollution source of pollutants; and comparing the position of the pollution source with a historical pollution source record, verifying the accuracy of the pollution source, and generating early warning information of a potential pollution source. According to the invention, meteorological and topographic factors are combined to identify the trend and path of pollutant diffusion, so that the positioning of the pollution risk area is more accurate, and comprehensive monitoring and deep analysis of micro-plastic pollution are realized.

Description

Technical Field

[0001] The present invention relates to the field of monitoring and analysis technology, and in particular to a soil microplastic pollution monitoring and analysis method based on big data analysis. Background Art

[0002] In recent years, the problem of soil microplastic pollution has gradually attracted widespread attention from the global academic community and society. Microplastics refer to plastic particles with a diameter of less than 5 mm, which are widely present in the environment, especially in soil, rivers and oceans. With the continuous increase in plastic production and consumption, the release and accumulation of microplastics are becoming increasingly serious, leading to the destruction of ecosystems and the reduction of biodiversity. In response to this environmental challenge, scientific research institutions and enterprises in various countries are actively exploring monitoring and analysis technologies for soil microplastics. Existing technologies mainly rely on traditional sampling and analysis methods, such as manual sampling and laboratory analysis, which have made certain progress in the quantitative detection and source identification of microplastics.

[0003] However, the limitations of these traditional methods are that the monitoring process is time-consuming and labor-intensive, and it is difficult to achieve large-scale, high-frequency data collection. At the same time, due to the limitations of sample representativeness and spatial coverage, it is often impossible to fully reflect the true distribution of soil microplastics. In addition, the existing monitoring methods are also relatively backward in data processing and analysis, lacking efficient algorithm support based on big data technology, making it difficult to achieve real-time monitoring and prediction of microplastic pollution dynamics. Summary of the invention

[0004] In view of the problems existing in the above background, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to use the pollution source reverse tracing algorithm, combined with the time series and spatial analysis results, to efficiently identify the pollution sources of microplastics and their potential impacts.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a soil microplastic pollution monitoring and analysis method based on big data analysis, which includes deploying sensors and sampling equipment, collecting microplastic data, combining remote sensing images or drone photography data to expand the spatial coverage of the data; using time series analysis methods to study the migration and diffusion laws of microplastic data in the soil in different time periods, and combining meteorological conditions and geographical conditions to construct a dynamic migration model of microplastics; through spatial analysis of microplastic concentration data in the monitoring area, high-risk areas of microplastic pollution are identified, and pollutant concentration areas and pollution sources are preliminarily determined; the location of the pollution source is compared with historical pollution source records to verify the accuracy of the pollution source, and generate early warning information for potential pollution sources.

[0007] As a preferred embodiment of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the construction of a dynamic migration model of microplastics includes the following steps: grouping the microplastic concentration time series data according to different meteorological conditions, generating multiple time series sequences respectively, and dividing the monitoring area into several sub-areas based on geographical conditions; for the microplastic time series data of each sub-area, the cumulative deviation analysis method is used, combined with meteorological factors, to analyze the cumulative deviation of the microplastic concentration changes in different time periods; by calculating the degree of deviation of the data, the trend and key turning points of the concentration fluctuation are identified, and combined with dynamic meteorological conditions, the concentration change range of microplastics in the future is predicted; based on the prediction results, the fluctuation period of the microplastic concentration in the time dimension is analyzed, the periodic migration behavior is identified, and the diffusion patterns in different time periods are compared to generate a time characteristic curve of microplastic diffusion; according to the generated time characteristic curve, combined with the geographical conditions of different sub-areas, a dynamic migration model of microplastics is constructed.

[0008] As a preferred embodiment of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the analysis of the cumulative deviation of the change in microplastic concentration in different time periods includes: calculating the mean of the microplastic concentration time series data of each sub-region as the baseline value of the microplastic concentration in the sub-region; using the cumulative deviation analysis method, by gradually accumulating the difference between the microplastic concentration time series data and its mean, a cumulative deviation curve is generated. , the formula is as follows: ; in, is the mean value of microplastic concentration in the sub-region, is the time series data of microplastic concentration in the sub-area, t is the time, is the cumulative deviation; the prediction of the concentration change range of microplastics in the future includes: using segmented regression to analyze the cumulative deviation curve in segments in combination with rainfall and wind speed, and identifying the impact of meteorological conditions on the change of microplastic concentration; according to the change trend of the cumulative deviation curve, identifying the key turning point of microplastic concentration; modeling the relationship between meteorological factors and concentration fluctuations, fitting the impact of meteorological conditions on microplastic concentration: ; in, and They represent the influence coefficients of rainfall and wind speed on the change of microplastic concentration, is the rainfall, is the wind speed; get the rainfall in the future time period and wind speed , predicting how microplastic concentrations will change in the future: ; ; in, For future time periods.

[0009] As a preferred embodiment of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the preliminary determination of the concentration areas and pollution sources of pollutants includes the following steps: gridding the microplastic data according to the spatial distribution of the monitoring area to construct spatial data sets of different areas; performing spatial interpolation processing on the gridded microplastic data; analyzing the distribution trend of spatial pollution data in combination with meteorological conditions and terrain information, and identifying the spatial gradient changes in microplastic concentrations; based on the results of spatial gradient analysis, applying hotspot analysis technology to identify the concentration areas of microplastic pollution, and determining the concentration intensity of pollutants through spatial autocorrelation methods; further refining the spatial analysis of high-risk areas, combining the time series migration model to infer the possible source areas of pollutants, and preliminarily locking the potential location of the pollution source through reverse speculation of spatial pollution concentrations and combining terrain and meteorological conditions.

[0010] As a preferred solution of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the spatial gradient change of identifying microplastic concentration includes: microplastic concentration Gradient in space Indicates the direction and magnitude of concentration change: ; According to the concentration gradient, pollutants diffuse from high-concentration areas to low-concentration areas, and the direction of their diffusion path is the negative direction of the gradient, that is, ; The method of determining the concentration intensity of pollutants by spatial autocorrelation includes: determining the concentration intensity of pollutants by Moran's index, that is, when the Moran's index is greater than 1, it indicates positive spatial autocorrelation, that is, areas with high concentrations tend to gather and are set as agglomeration areas; when the Moran's index is less than 1, it indicates negative spatial autocorrelation, that is, areas with low concentrations tend to disperse and are set as dispersed areas; the method of preliminarily locking the potential location of the pollution source by reverse inference of spatial pollution concentration and combining terrain and meteorological conditions includes: if the concentration gradient in the high-risk area is known , then the source direction is the direction of the concentration gradient; combined with the dynamic migration model, the potential source area can be further located by reversely tracing the migration path of microplastics: ; in, The initial geographic coordinates of the preliminarily determined microplastic pollution sources.

[0011] As a preferred embodiment of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the method of comparing the location of the pollution source with the historical pollution source records to verify the accuracy of the pollution source includes the following steps: collecting historical data related to the pollution source; comparing with the preliminary determined pollution source location to determine the relationship between the preliminary determined pollution source location and the historical pollution source.

[0012] As a preferred solution of the soil microplastic pollution monitoring and analysis method based on big data analysis described in the present invention, the dynamic migration model of the microplastics is expressed using the convection-diffusion equation.

[0013] In a second aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the soil microplastic pollution monitoring and analysis method based on big data analysis as described in the first aspect of the present invention are implemented.

[0014] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the soil microplastic pollution monitoring and analysis method based on big data analysis as described in the first aspect of the present invention are implemented.

[0015] The beneficial effects of the present invention are as follows: the present invention analyzes the changes in microplastic concentration over time, identifies the key turning points of its migration, and analyzes its impact on concentration fluctuations in combination with meteorological factors, thereby constructing an effective dynamic migration model, revealing the diffusion path and deposition pattern of microplastics in the soil; combining meteorological and topographic factors to identify the trend and path of pollutant diffusion, making the positioning of pollution risk areas more accurate, and facilitating more detailed environmental monitoring and governance work in high-risk areas of microplastic pollution, thereby effectively reducing the impact of microplastics on the ecological environment and ensuring soil health; the present invention realizes comprehensive monitoring and in-depth analysis of microplastic pollution. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a flow chart of the soil microplastic pollution monitoring and analysis method based on big data analysis.

[0018] Figure 2 FIG. 1 is a schematic diagram of the structure of a terminal in the first embodiment of the present invention.

[0019] Figure 3 It is a schematic diagram of the structure of a computer device in the first embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments. Embodiment 1:

[0023] Reference Figure 1~Figure 3 , which is the first embodiment of the present invention, and provides a soil microplastic pollution monitoring and analysis method based on big data analysis, such as Figure 1 As shown, including, S1: Deploy sensors and sampling equipment in the soil monitoring area and collect data, combining remote sensing images or drone photography data to expand the spatial coverage of the data.

[0024] Specifically, appropriate monitoring points are selected according to the topographical characteristics of the soil monitoring area and the purpose of the research. Various sensors and sampling equipment are deployed at these monitoring points, such as microplastic detection sensors, humidity sensors, temperature sensors, anemometers, and rain gauges.

[0025] Among them, the layout of sensors should cover representative areas to ensure that data can be obtained for different soil types (such as sandy soil, clay soil, etc.) and different climatic conditions (dry areas, humid areas, etc.).

[0026] At the same time, remote sensing technology, such as satellite images or drone aerial photography, can be combined to expand the coverage of the monitoring area and obtain large-scale soil condition data. The flight path of the drone should be planned reasonably to ensure the comprehensiveness of the image data.

[0027] The collected data are preliminarily processed, including data cleaning, outlier removal and formatting, to ensure data quality.

[0028] S2: Use time series analysis methods to process microplastic data in the soil, study their migration and diffusion patterns in different time periods, and combine meteorological conditions (such as rainfall, wind speed) and geographical conditions to construct a dynamic migration model of microplastics to reveal their diffusion paths and deposition patterns in the soil.

[0029] S2.1: Group the microplastic concentration time series data according to different meteorological conditions, generate multiple time series respectively, and divide the monitoring area into several sub-areas based on geographical conditions (such as terrain and soil type), and analyze the data of different sub-areas independently.

[0030] Among them, meteorological conditions can be divided into different intervals: such as low, medium and high rainfall, low, medium and high wind speeds, etc., to generate multiple time series data sets, which respectively represent the changes in microplastic concentration under different meteorological conditions.

[0031] According to the geographical conditions of the monitoring area, such as terrain height and soil type, the entire monitoring area is divided into multiple sub-areas. The geographical characteristics within each sub-area can affect the migration and deposition process of microplastics.

[0032] S2.2: For the microplastic time series data of each sub-region, the cumulative deviation analysis method (CDA) is used to analyze the cumulative deviation of microplastic concentration changes in different time periods in combination with meteorological factors such as rainfall and wind speed. By calculating the degree of deviation of the data, the trend and key turning points of concentration fluctuations are identified, and combined with dynamic meteorological conditions, the future range of microplastic concentration changes is inferred.

[0033] Preferably, the mean value of the microplastic concentration time series data of each sub-region is calculated as the baseline value of the microplastic concentration in the region; The cumulative deviation analysis (CDA) method was used to generate a cumulative deviation curve by gradually accumulating the difference between the microplastic concentration time series data and its mean. , the specific formula is as follows: ; in, is the mean value of microplastic concentration in the sub-region, is the time series data of microplastic concentration in the sub-area, t is the time, The cumulative deviation curve can intuitively reflect the long-term change trend of microplastic concentration.

[0034] The cumulative deviation curve was analyzed segmentally using segmented regression based on rainfall and wind speed to identify the impact of meteorological conditions on the change in microplastic concentration. The focus was on analyzing the inflection points of the cumulative deviation curve before and after rainfall and when the wind speed changed significantly.

[0035] Furthermore, based on the changing trend of the cumulative deviation curve, key turning points in microplastic concentrations were identified, which may represent concentration changes caused by significant environmental events (such as rainfall and strong winds).

[0036] Based on the changes in the cumulative deviation curve and key turning points, combined with future meteorological conditions (rainfall and wind speed), the future range of changes in microplastic concentrations is predicted.

[0037] Specifically, before the critical turning point, the change in microplastic concentration was mainly affected by current and historical meteorological conditions. Therefore, we need to model the relationship between meteorological factors and concentration fluctuations, that is, use linear regression to fit the impact of meteorological conditions on microplastic concentration: ; in, and They represent the influence coefficients of rainfall and wind speed on the change of microplastic concentration, is the rainfall, is the wind speed.

[0038] Obtain rainfall for future time periods by using weather forecast data and wind speed , it is possible to predict how microplastic concentrations will change in the future: ; ; in, For future time periods.

[0039] It can be seen that the cumulative deviation analysis gradually accumulates the deviations between the actual observed values ​​and their mean values, and intuitively presents the long-term change trend of the data with the cumulative deviation curve. Combined with external meteorological factors such as rainfall and wind speed in each sub-region, the impact of these factors on the deviation curve is analyzed, and the change points of microplastic concentration before and after rainfall are identified, which can infer possible concentration changes in the future.

[0040] S2.3: Based on the prediction results, analyze the fluctuation period of microplastic concentration in the time dimension, identify periodic migration behaviors (such as seasonal deposition and diffusion after heavy rain), and compare the diffusion patterns in different time periods to generate the time characteristic curve of microplastic diffusion.

[0041] First, the cumulative deviation curve is processed using periodic analysis methods (such as Fourier transform or autocorrelation analysis) to identify significant periodic behaviors, focusing on the impact of seasonal factors (such as spring snowmelt and heavy rain periods) on the migration of microplastics.

[0042] Based on the identified period, a time characteristic curve of microplastic concentration is generated to show the periodic change behavior of microplastic migration. Combined with the previous cumulative deviation curve analysis, a complete time characteristic description is formed; The temporal characteristic curves of different sub-regions are compared to analyze the migration differences of each sub-region under different seasons or meteorological conditions. Through comparison, significant migration behaviors within a specific time period can be identified (such as diffusion after heavy rain and deposition in the dry season).

[0043] S2.4: Construct a dynamic migration model of microplastics based on the geographical conditions of different sub-regions.

[0044] Specifically, the diffusion of microplastics in soil can be expressed by the convection-diffusion equation, which combines the convective transport and diffusion processes of microplastics: ; in, Describe the convective transport of microplastics in soil, which is affected by the diffusion rate The impact of speed Depends on meteorological conditions and topographical influences; Describe the diffusion process of microplastics in soil by the diffusion coefficient and concentration gradient Decide, The input or deposition of external microplastics (such as microplastic deposition caused by human activities or natural processes) is the spatial coordinate at time t The concentration of microplastics in the

[0045] S3: Through spatial analysis of microplastic concentration data in the monitoring area, high-risk areas of microplastic pollution are identified, and the concentration areas and sources of pollutants are preliminarily determined.

[0046] S3.1: The microplastic data collected and processed in steps S1 and S2 are gridded according to the spatial distribution of the monitoring area to construct spatial data sets for different regions.

[0047] The gridding resolution is dynamically adjusted according to the sensor distribution density and terrain complexity to ensure that each grid cell contains pollution data with sufficient accuracy. The division process is as follows: Divide the monitoring area A into multiple grid cells , the side length of each grid cell is ,in, Based on the distribution density of sensors and terrain complexity Adjustment: ; in, is the sensor density.

[0048] S3.2: Perform spatial interpolation on the gridded microplastic data and use the Kriging interpolation method or the inverse distance weighted (IDW) method to fill in the blank areas between monitoring points and generate a continuous pollution distribution map. This can eliminate data gaps between sensors and improve the spatial integrity and continuity of pollution data.

[0049] Furthermore, when the data sampling points in the monitoring area are relatively evenly distributed and there is no significant spatial correlation or trend, IDW can be preferred to reduce the computational complexity and obtain fast results.

[0050] When the data points in the monitoring area are unevenly distributed or there is significant spatial correlation, you can switch to Kriging to improve the accuracy and reliability of the interpolation results.

[0051] In some areas, the data distribution may be sparse and there are complex terrain features. In this case, Kriging can be used to capture local changes in microplastic concentrations. In other areas, when the sampling points are densely distributed or the data changes slowly, IDW can be used for fast interpolation.

[0052] S3.3: Combine meteorological conditions (such as wind speed and rainfall) and terrain information to analyze the distribution trend of spatial pollution data and identify the spatial gradient changes in microplastic concentrations. Gradient in space Indicates the direction and magnitude of concentration change: ; According to the concentration gradient, pollutants may diffuse from high-concentration areas to low-concentration areas, and the direction of the diffusion path is the negative direction of the gradient, that is, .

[0053] Through gradient change analysis, we can preliminarily identify high-risk areas for microplastic pollution and determine the paths through which pollutants may spread from high-concentration areas to low-concentration areas.

[0054] S3.4: Based on the results of spatial gradient analysis, hotspot analysis technology is applied to identify the concentrated areas of microplastic pollution, and the concentration intensity of pollutants is determined through spatial autocorrelation methods (such as the Moran's index). That is, when the Moran's index is greater than 1, it indicates positive spatial autocorrelation, that is, areas with high concentrations tend to aggregate; when the Moran's index is less than 1, it indicates negative spatial autocorrelation, that is, areas with low concentrations tend to disperse.

[0055] S3.5: Conduct a more detailed spatial analysis of high-risk areas, and combine the time-series migration model in step S2 to infer the possible source areas of pollutants. Through reverse inference of spatial pollution concentrations, combined with terrain and meteorological conditions, preliminarily identify the potential location of the pollution source.

[0056] If the concentration gradient in the high-risk area is known , then the source direction is the direction of the concentration gradient.

[0057] Furthermore, combined with the dynamic migration model in step S2, the potential source area can be further located by reversely tracing the migration path of microplastics: ; in, The initial geographic coordinates of the preliminarily determined microplastic pollution sources.

[0058] Starting from the preliminary source position, the displacement of the pollutant in the time period t is considered and the preliminary source position is adjusted to more accurately infer the potential pollution source position.

[0059] S4: Compare the location of pollution sources with historical pollution source records (such as industrial activities, landfill locations, etc.) to verify the accuracy of the pollution sources and generate early warning information for potential pollution sources.

[0060] First, collect historical data related to pollution sources, including: records of industrial activities (such as factory, industrial area, production line information), locations of garbage dumps and landfills and their historical operating data, records of other potential pollution sources (such as traffic arteries, construction sites, etc.), organize and store these data to ensure the accuracy and accessibility of the information.

[0061] Compare the locations of identified potential pollution sources to determine their relationship with historical pollution sources: Determine the coordinates of the pollution source location; Use distance thresholds (e.g., 500 meters, 1 kilometer, etc.) to determine whether newly identified pollution sources overlap with historical pollution sources; For overlapping pollution sources, record their specific relationship with historical pollution sources (such as distance, type, etc.).

[0062] Furthermore, different risk levels for pollution sources are set based on their historical pollution event records, environmental monitoring data (such as changes in water quality and air quality), and the impact of surrounding industrial and residential activities. Based on the risk levels of different pollution sources, specific governance suggestions are put forward, including source control, pollution remediation and other measures.

[0063] This embodiment also provides a computer device, which is suitable for the soil microplastic pollution monitoring and analysis method based on big data analysis, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the soil microplastic pollution monitoring and analysis method based on big data analysis as proposed in the above embodiment.

[0064] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0065] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for monitoring and analyzing soil microplastic pollution based on big data analysis proposed in the above embodiment is implemented.

[0066] In summary, the present invention analyzes the changes in microplastic concentration over time, identifies the key turning points of its migration, and analyzes its impact on concentration fluctuations in combination with meteorological factors, constructs an effective dynamic migration model, and reveals the diffusion path and deposition pattern of microplastics in the soil; combines meteorological and topographic factors to identify the trend and path of pollutant diffusion, making the positioning of pollution risk areas more accurate, and facilitating more detailed environmental monitoring and governance work in high-risk areas of microplastic pollution, thereby effectively reducing the impact of microplastics on the ecological environment and ensuring soil health; the present invention achieves comprehensive monitoring and in-depth analysis of microplastic pollution. Embodiment 2:

[0067] Referring to Table 1 and Table 2, which is the second embodiment of the present invention, this embodiment provides a soil microplastic pollution monitoring and analysis method based on big data analysis. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0068] In order to verify the innovation and effectiveness of the soil microplastic pollution monitoring and analysis method based on big data analysis, a microplastic pollution monitoring experiment was conducted in a humid climate area. The experimental area has a complex terrain, covering flat areas and mountains. According to the terrain characteristics and different soil types (sandy soil, clay soil, etc.), 10 monitoring points were set up in the area, and each monitoring point was equipped with a variety of sensors, including microplastic detection sensors, humidity sensors, temperature sensors, anemometers and rain gauges. The layout of sensors ensures that representative areas are covered in order to obtain microplastic pollution data with different geographical conditions and climate characteristics.

[0069] In order to expand the spatial coverage of the data, drones were used for regional aerial photography to obtain high-definition remote sensing images. The aerial photography path was planned according to the terrain to ensure the comprehensiveness of the image data. The drone flight altitude was set to 150 meters, covering the entire monitoring area, and obtaining image data within 500 meters around each monitoring point.

[0070] The data collected included the concentration of microplastics in the soil, rainfall, wind speed, humidity and temperature. To ensure the quality of the data, data cleaning and outlier removal were carried out, such as removing extreme values ​​that were obviously beyond the normal range, and formatting the data collected by different devices to make them consistent.

[0071] After data collection, the migration pattern of microplastic concentration over time was studied based on the time series analysis method. The data was grouped according to rainfall (divided into low rainfall, medium rainfall and high rainfall) and wind speed (divided into low wind speed, medium wind speed and high wind speed). The monitoring area was also divided into three sub-areas according to terrain height and soil type, namely flat area, hilly area and mountainous area. Under different meteorological conditions, the temporal changes of microplastic concentration in each area were calculated separately to generate multiple time series data sets.

[0072] Next, the cumulative deviation analysis (CDA) method was used to analyze the changes in microplastic concentrations in different time periods. By calculating the cumulative deviation between the mean of microplastic concentrations and the actual data, a cumulative deviation curve for each sub-region was generated. According to the changes in rainfall and wind speed, segmented regression was used to identify the key inflection points of concentration changes. Finally, by predicting future meteorological conditions (rainfall and wind speed in the next 24 hours), the future trend of microplastic concentration changes was predicted.

[0073] During the experiment, a dynamic model of microplastic diffusion under different meteorological conditions was used to identify the significant impact of seasonal factors (such as rainstorms) on the diffusion of microplastics. Combined with the time characteristic curve, the periodic diffusion behavior of microplastics in different regions was demonstrated. Some experimental data are as follows. The data in the table represent the microplastic concentrations and related meteorological parameters in different regions at different time periods: Table 1 Soil microplastic concentration and meteorological data records

[0074] Table 2 Cumulative deviation analysis of soil microplastic concentrations

[0075] Through the analysis of the above table data, it can be seen that in Table 1, monitoring points A, B and C are in areas with relatively high rainfall, and the concentration of microplastics is significantly higher than that in areas with low rainfall (such as monitoring points E and F). This shows that rainfall has a significant impact on the migration and deposition of microplastics. Combined with the changes in wind speed, temperature and humidity, the impact of meteorological conditions on the change of microplastic concentration can be further inferred.

[0076] The cumulative deviation curve in Table 2 shows the gradual deviation trend of microplastic concentration over time. For example, at monitoring point B, the cumulative deviation increased from 0.7 to 2.7, indicating that this point was significantly deposited with microplastics at multiple times. The key turning points of the cumulative deviation were identified through segmented regression, and a clear upward trend in microplastic concentration after rainfall was found.

[0077] Compared with the existing technology, the method of the present invention can monitor the dynamic migration behavior of microplastics in real time through multi-source data fusion (sensors, drones and meteorological data). In particular, based on the cumulative deviation analysis method, it can accurately identify the key periods and turning points of concentration fluctuations, and predict future concentration changes in combination with meteorological factors. The existing technology often lacks comprehensive analysis of time series and spatial gradients, and cannot effectively identify the diffusion path and key turning points of microplastics. Therefore, in terms of environmental pollution prevention and control, the present invention has obvious creativity and practical application value.

[0078] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A soil microplastic pollution monitoring and analysis method based on big data analysis, characterized in that: include, Deploy sensors and sampling equipment to collect soil microplastic data, and combine remote sensing images or drone footage to expand the spatial coverage of the data; Using time series analysis methods, we studied the migration and diffusion patterns of microplastics in soil in different time periods, and combined meteorological and geographical conditions to build a dynamic migration model of microplastics. Through spatial analysis of microplastic concentration data in the monitoring area, high-risk areas of microplastic pollution are identified, and the concentration areas and pollution sources of pollutants are preliminarily determined; Compare the location of pollution sources with historical pollution source records to verify the accuracy of the pollution sources and generate early warning information for potential pollution sources.

2. The soil microplastic pollution monitoring and analysis method based on big data analysis as claimed in claim 1, characterized in that: The construction of the dynamic migration model of microplastics comprises the following steps: The microplastic concentration time series data were grouped according to different meteorological conditions to generate multiple time series, and the monitoring area was divided into several sub-areas based on geographical conditions; For the microplastic time series data of each sub-region, the cumulative deviation analysis method is used, combined with meteorological factors, to analyze the cumulative deviation of microplastic concentration changes in different time periods; by calculating the degree of deviation of the data, the trend and key turning points of concentration fluctuations are identified, and combined with dynamic meteorological conditions, the concentration change range of microplastics in the future is predicted; Based on the prediction results, the fluctuation period of microplastic concentration in the time dimension is analyzed, the periodic migration behavior is identified, and the diffusion patterns in different time periods are compared to generate the time characteristic curve of microplastic diffusion; Combining the geographical conditions of different sub-regions, a dynamic migration model of microplastics is constructed.

3. The soil microplastic pollution monitoring and analysis method based on big data analysis as claimed in claim 2, characterized in that: The cumulative deviations of the analysis of changes in microplastic concentrations over different time periods include: Calculate the mean of the microplastic concentration time series data of each sub-region as the baseline value of the microplastic concentration in the sub-region; The cumulative deviation analysis method was used to generate a cumulative deviation curve by gradually accumulating the difference between the microplastic concentration time series data and its mean. , the formula is as follows: ； in, is the mean value of microplastic concentration in the sub-region, is the time series data of microplastic concentration in the sub-area, t is the time, is the cumulative deviation; The predicted range of future microplastic concentration changes includes: The cumulative deviation curve was segmented by segmented regression combined with rainfall and wind speed to identify the impact of meteorological conditions on the changes in microplastic concentrations. According to the changing trend of the cumulative deviation curve, the key turning points of microplastic concentration were identified; Model the relationship between meteorological factors and concentration fluctuations, and fit the impact of meteorological conditions on microplastic concentrations: ； in, and Respectively represent the influence coefficients of rainfall and wind speed on the change of microplastic concentration, is the rainfall, is the wind speed; Get the rainfall for a future time period and wind speed , predicting how microplastic concentrations will change in the future: ； ； in, For future time periods.

4. The soil microplastic pollution monitoring and analysis method based on big data analysis as claimed in claim 3, characterized in that: The preliminary determination of the concentration areas and pollution sources of pollutants comprises the following steps: The microplastic data were gridded according to the spatial distribution of the monitoring area to construct spatial data sets for different regions; Perform spatial interpolation on the gridded microplastic data; Combine meteorological conditions and terrain information to analyze the distribution trend of spatial pollution data and identify the spatial gradient changes in microplastic concentrations; Based on the results of spatial gradient analysis, hot spot analysis techniques were applied to identify the concentrated areas of microplastic pollution, and the concentration intensity of pollutants was determined through spatial autocorrelation methods. Further detailed spatial analysis of high-risk areas is carried out, and the possible source areas of pollutants are deduced in combination with time-series migration models. The potential locations of pollution sources are preliminarily identified through reverse inference of spatial pollution concentrations and combined with terrain and meteorological conditions.

5. The soil microplastic pollution monitoring and analysis method based on big data analysis as claimed in claim 4, characterized in that: The identification of spatial gradient changes in microplastic concentrations includes: Microplastic concentration Gradient in space Indicates the direction and magnitude of concentration change: ； According to the concentration gradient, pollutants diffuse from high-concentration areas to low-concentration areas, and the direction of their diffusion path is the negative direction of the gradient, that is, ; The method of determining the concentration intensity of pollutants by using the spatial autocorrelation method includes: The concentration intensity of pollutants is determined by the Moran index. When the Moran index is greater than 1, it indicates positive spatial autocorrelation, that is, areas with high concentrations tend to aggregate and are set as agglomerated areas; when the Moran index is less than 1, it indicates negative spatial autocorrelation, that is, areas with low concentrations tend to disperse and are set as dispersed areas. The potential locations of pollution sources are initially identified through reverse inference of spatial pollution concentrations and combined with terrain and meteorological conditions, including: If the concentration gradient in the high-risk area is known , then the source direction is the direction of the concentration gradient; Combined with the dynamic migration model, the migration path of microplastics is traced in reverse to further locate potential source areas: ； in, The initial geographic coordinates of the preliminarily determined microplastic pollution sources.

6. The soil microplastic pollution monitoring and analysis method based on big data analysis as claimed in claim 5, characterized in that: Comparing the pollution source location with the historical pollution source records to verify the accuracy of the pollution source includes the following steps: Collect historical data related to pollution sources; Compare with the preliminary determined pollution source location to determine the relationship between the preliminary determined pollution source location and the historical pollution source.

7. The soil microplastic pollution monitoring and analysis method based on big data analysis according to claim 6, characterized in that: The dynamic migration model of microplastics is expressed using the convection-diffusion equation.

Images