Soil heavy metal pollution area anomaly identification and evaluation method based on multi-source data

Abstract

The invention discloses a soil heavy metal pollution area abnormity identification and evaluation method based on multi-source data, and relates to the technical field of pollution management, and the method comprises the following steps: 1, determining all soil heavy metal pollution areas; 2, regularly obtaining a regional anomaly identification value of each soil heavy metal pollution region, and judging whether the soil heavy metal pollution region is marked as a soil heavy metal anomaly region or not based on a comparison result of the regional anomaly identification value and a regional anomaly identification threshold value; and step 3, carrying out grading anomaly evaluation on the soil heavy metal anomaly regions, carrying out integration and deep processing on the multi-source data of each soil heavy metal pollution region through the step 1 and the step 2, and carrying out multi-dimensional analysis on the multi-source data in an independent and associated manner. Whether the soil heavy metal pollution area is abnormal or not is accurately and efficiently judged.

Description

Technical Field

[0001] The present invention relates to the field of pollution management technology, and more specifically, to a method for identifying and evaluating abnormalities in soil heavy metal pollution areas based on multi-source data. Background Art

[0002] In recent years, with the rapid development of information technology, big data technology and artificial intelligence technology, multi-source data fusion and processing technology has provided new ideas and methods for abnormal identification and evaluation of soil heavy metal pollution areas. By integrating soil heavy metal pollution data from different sources, different scales and different time resolutions, comprehensive and dynamic monitoring and accurate evaluation of soil heavy metal pollution areas can be achieved.

[0003] However, the existing multi-source data fusion and processing methods still have some shortcomings in the abnormal identification and evaluation of soil heavy metal pollution areas. For example, some methods rely too much on a single data source or simple statistical analysis, resulting in low accuracy and reliability of identification and evaluation results; although some methods consider the fusion of multi-source data, they lack in-depth processing and multi-dimensional analysis of the characteristics of soil heavy metal pollution, making it difficult to accurately identify and evaluate soil heavy metal pollution areas.

[0004] Therefore, there is an urgent need for a method for identifying and evaluating abnormalities in soil heavy metal pollution areas based on multi-source data. This method can integrate soil heavy metal pollution data from different sources and achieve accurate and efficient identification and evaluation of soil heavy metal pollution areas through deep processing and multi-dimensional analysis. Summary of the invention

[0005] In view of the shortcomings of the prior art, the purpose of the present invention is to provide a method for identifying and evaluating anomalies in soil heavy metal contaminated areas based on multi-source data.

[0006] To achieve the above object, the present invention provides the following technical solutions: The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data includes the following steps: Step 1: Identify all areas of soil heavy metal contamination; Step 2: Regularly obtain the regional anomaly identification value of each soil heavy metal pollution area, and determine whether to mark the soil heavy metal pollution area as a soil heavy metal abnormal area based on the comparison result between the regional anomaly identification value and the regional anomaly identification threshold value; Step 3: Conduct graded abnormal evaluation on areas with abnormal soil heavy metal content.

[0007] Furthermore, regional anomaly identification values ​​of each soil heavy metal pollution area are obtained regularly, specifically: an anomaly identification cycle is generated, and each time an anomaly identification cycle is completed, the regional anomaly identification value of each soil heavy metal pollution area is obtained.

[0008] Furthermore, the regional anomaly identification value of the soil heavy metal pollution area is obtained by the following steps: within the pollution identification evaluation period, j anomaly identification periods with equal intervals are divided, the period anomaly values ​​of the soil heavy metal pollution area in each anomaly identification period are obtained, the period anomaly total value DSm is obtained, all period anomaly values ​​are sorted according to the order of the anomaly identification period, the difference between the anomaly values ​​of the two adjacent period after sorting is calculated and the absolute value is taken to obtain the anomaly rise and fall value, all the anomaly rise and fall values ​​are summed and averaged to obtain the average anomaly rise and fall value HWq, and the formula is used The regional anomaly identification value AGPK of the soil heavy metal pollution area is obtained.

[0009] Furthermore, the total time period anomaly value DSm is obtained through the following steps: a rectangular coordinate system is constructed with the pollution identification evaluation period as the X-axis and the time period anomaly value as the Y-axis, the time period anomaly value of each anomaly identification time period is marked in the rectangular coordinate system in the form of a point, adjacent points in the rectangular coordinate system are connected to draw a time period anomaly curve, the two end points of the time period anomaly curve are perpendicular to the X-axis, and two time period start-end lines are obtained after the two perpendicular lines intersect the X-axis, and the total area of ​​the closed figure formed by the time period anomaly curve, the two time period start-end lines and the X-axis is marked as the total time period anomaly value DSm.

[0010] Furthermore, the time period abnormal value of the abnormal identification period is obtained by the following steps: collecting various types of core impact data of the soil heavy metal pollution area within the abnormal identification period, and then obtaining the core impact value of each type of core impact data, setting the core impact demarcation value, when the core impact value is greater than or equal to the core impact demarcation value, marking the type of core impact data as core abnormal data, when the core impact value is less than the core impact demarcation value, marking the type of core impact data as core normal data, marking the number of core normal data as kzr, and grouping all the core abnormal data into a core abnormal group in pairs, and grouping the core abnormal data in a core abnormal group into a core abnormal group. The core impact values ​​of the two core abnormal data are summed and averaged to obtain the core impact group value, and the core impact group threshold is set. When the core impact group value is greater than or equal to the core impact group threshold, the core abnormal group is marked as a core diffusion abnormal group, and the number of core diffusion abnormal groups is marked as acg. The core impact values ​​of the two core abnormal data in a core abnormal group are calculated by difference and the absolute value is taken to obtain the core impact deviation value, and the core impact threshold deviation value is set. When the core impact deviation value is less than the core impact threshold deviation value, the core abnormal group is marked as a core synchronization abnormal group, and the number of core synchronization abnormal groups is marked as byt. Using the formula The time period abnormal value Shp of the abnormal identification period is obtained, where wa is the core normal coefficient, wb is the core diffusion coefficient, and wc is the core synchronization coefficient.

[0011] Furthermore, the core influence value of each type of core influence data is obtained through the following steps: obtaining the core influence model corresponding to each type of core influence data, preprocessing each type of core influence data, and inputting the preprocessed core influence data of each type into the corresponding core influence model, thereby obtaining the core influence value of each type of core influence data.

[0012] Furthermore, a graded abnormality evaluation is performed on the soil heavy metal abnormal area, specifically: a graded abnormality evaluation value MZg of the soil heavy metal abnormal area is obtained, and a range of each graded abnormality evaluation value is set to correspond to an abnormality evaluation grade, wherein the range of the graded abnormality evaluation value includes (0, MZ1], (MZ1, MZ2], …, (MZg-1, MZg], MZ1<MZ2<…<MZg-1<MZg, and the abnormality evaluation grades include abnormality evaluation grade 1, abnormality evaluation grade 2, …, abnormality evaluation grade g-1, abnormality evaluation grade g, and the higher the abnormality evaluation grade, the more abnormal the soil heavy metal pollution in the soil heavy metal abnormal area is.

[0013] Furthermore, the graded abnormal evaluation value of the soil heavy metal abnormal area is obtained by the following steps: determine the regional abnormal distance according to the regional abnormal identification value AGPk of the soil heavy metal abnormal area, mark the remaining soil heavy metal abnormal areas as abnormal evaluation influence areas, obtain the distance between the soil heavy metal abnormal area and each abnormal evaluation influence area, and when the distance between the soil heavy metal abnormal area and the abnormal evaluation influence area is less than the regional abnormal distance, increase the regional abnormal spread number by one, mark the regional abnormal spread number as HBCe, and use the formula The graded anomaly evaluation value MZg of the soil heavy metal abnormal area is obtained, where fa is the regional anomaly coefficient and fb is the regional anomaly propagation coefficient.

[0014] Furthermore, the regional anomaly distance is determined according to the regional anomaly identification value AGPk of soil heavy metals, specifically: a range of each regional anomaly identification value is set to correspond to a regional anomaly distance, wherein the range of the regional anomaly identification value includes (0, AGP1], (AGP1, AGP2], …, (AGPk-1, AGPk], AGP1<AGP2<…<AGPk-1<AGPk, the regional anomaly distance includes regional anomaly distance 1, regional anomaly distance 2, …, regional anomaly distance k-1, regional anomaly distance k, the length of regional anomaly distance 1<the length of regional anomaly distance 2<…<the length of regional anomaly distance k-1<the length of regional anomaly distance k.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The method of the present invention integrates and deeply processes the multi-source data of each soil heavy metal pollution area through steps one and two, and accurately and efficiently determines whether there is an abnormality in the soil heavy metal pollution area by performing multi-dimensional analysis of the multi-source data in independent and related ways. Through step three, an in-depth and comprehensive analysis of the abnormal soil heavy metal pollution area is performed, and an accurate and detailed evaluation of the abnormalities in the soil heavy metal pollution area is performed, which helps regional managers understand the degree of abnormality in the area. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of the abnormal identification and evaluation method of soil heavy metal pollution areas based on multi-source data; Figure 2 Flowchart for obtaining regional anomaly identification values ​​for areas contaminated by heavy metals in soil. DETAILED DESCRIPTION

[0017] Reference Figure 1-Figure 2 ,The abnormal identification and evaluation method of soil heavy metal pollution area based on multi-source data includes the following steps: Step 1: Identify all soil heavy metal pollution areas (i.e., determine the soil heavy metal pollution areas targeted by this application method. Normally, this method usually requires research on multiple soil heavy metal pollution areas).

[0018] Step 2: Generate an anomaly identification cycle. After each anomaly identification cycle, obtain the regional anomaly identification value of each soil heavy metal pollution area, set the regional anomaly identification threshold value (the regional anomaly identification threshold value is a preset value, and the preset value value is set according to demand). When the regional anomaly identification value is greater than or equal to the regional anomaly identification threshold value, mark the soil heavy metal pollution area as a soil heavy metal abnormal area. When the regional anomaly identification value is less than the regional anomaly identification threshold value, no processing is performed.

[0019] The regional anomaly identification value of the soil heavy metal pollution area is obtained by the following steps: j anomaly identification periods with equal intervals are divided within the pollution identification evaluation cycle, and the period anomaly values ​​of the soil heavy metal pollution area in each anomaly identification period are obtained. A rectangular coordinate system is constructed with the pollution identification evaluation cycle as the X-axis and the period anomaly value as the Y-axis. The period anomaly value of each anomaly identification period is marked in the rectangular coordinate system in the form of a point. Adjacent points in the rectangular coordinate system are connected to draw a period anomaly curve. The two end points of the period anomaly curve are perpendicular to the X-axis. After the two perpendicular lines intersect the X-axis, two period start-end lines are obtained. The total area of ​​the closed figure formed by the period anomaly curve, the two period start-end lines and the X-axis is marked as the total period anomaly value DSm. All period anomaly values ​​are sorted according to the order of the anomaly identification periods. The difference between the two adjacent period anomaly values ​​after sorting is calculated and the absolute value is taken to obtain the anomaly rise and fall value. All anomaly rise and fall values ​​are summed and averaged to obtain the average anomaly rise and fall value HWq. The formula is used The regional anomaly identification value AGPK of the soil heavy metal pollution area is obtained.

[0020] The time period anomaly value of the anomaly identification period is obtained through the following steps: collect various types of core impact data in the soil heavy metal pollution area within the anomaly identification period, and then obtain the core impact value of each type of core impact data, set the core impact demarcation value (the core impact demarcation value is a preset value, and the preset value value is set according to demand), when the core impact value is greater than or equal to the core impact demarcation value, mark this type of core impact data as core abnormal data, when the core impact value is less than the core impact demarcation value, mark this type of core impact data as core normal data, mark the number of core normal data as kzr, group all core abnormal data into a core abnormal group in pairs, sum and average the core impact values ​​of two core abnormal data in a core abnormal group, obtain the core impact group value, and set the core impact. Group threshold (the core impact group threshold is a preset value, and the preset value is set according to demand). When the core impact group value is greater than or equal to the core impact group threshold, the core abnormal group is marked as a core diffusion abnormal group. When the core impact group value is less than the core impact group threshold, no processing is performed. The number of core diffusion abnormal groups is marked as acg. The core impact values ​​of two core abnormal data in a core abnormal group are calculated by difference and the absolute value is taken to obtain the core impact distance value. The core impact threshold distance value is set (the core impact threshold distance value is a preset value, and the preset value is set according to demand). When the core impact distance value is greater than or equal to the core impact threshold distance value, no processing is performed. When the core impact distance value is less than the core impact threshold distance value, the core abnormal group is marked as a core synchronization abnormal group, and the number of core synchronization abnormal groups is marked as byt. The formula is used. The period anomaly value Shp of the anomaly identification period is obtained, where wa is the core normal coefficient, wb is the core diffusion coefficient, wc is the core synchronization coefficient, the value of wa is 0.92, the value of wb is 1.29, and the value of wc is 1.08.

[0021] The core impact value of each type of core impact data is obtained through the following steps: obtaining the core impact model corresponding to each type of core impact data, preprocessing each type of core impact data (the preprocessing steps include but are not limited to data cleaning, missing value processing, and data normalization), and inputting the preprocessed core impact data of each type into the corresponding core impact model, thereby obtaining the core impact value of each type of core impact data.

[0022] The core influencing data types of soil heavy metal pollution areas include but are not limited to soil heavy metal content data, soil physical and chemical properties data, air pollution data, pollution source emission data, climate and meteorological data, and ecological data. Soil heavy metal content data include various heavy metal content data and distribution data. Soil physical and chemical properties data include soil pH data, soil organic matter content data, soil cation exchange capacity, etc. Air pollution data include various heavy metal content data, heavy metal form and distribution data, particulate matter concentration data, etc. Pollution source emission data include industrial emission data, agricultural emission data, transportation data, etc. Climate and meteorological data include wind speed data, wind direction data, temperature data, humidity data, etc. Ecological data include plant growth data, animal health data, etc.

[0023] Each type of core impact data corresponds to a core impact model, and the only difference between the constructions of each core impact model is the difference in training data. This embodiment discloses the steps for constructing a core impact model for soil heavy metal content data: collecting multiple groups of soil heavy metal content data, preprocessing each group of soil heavy metal content data, constructing a deep learning model, using the preprocessed soil heavy metal content data as training data for the deep learning model, assigning a core impact value to each training data, and the core impact value range is (0.01~1.99). The larger the core impact value, the more abnormal the soil heavy metal content data, and the smaller the core impact value, the more normal the soil heavy metal content data. The training data is divided into a 55% training set and a 45% validation set, and the training set and validation set in the deep learning model are trained. After the training is completed, the core impact model for soil heavy metal content data is constructed.

[0024] Step 3: Conduct graded abnormal evaluation on areas with abnormal soil heavy metal content.

[0025] The soil heavy metal abnormal area is graded for abnormal evaluation, specifically: obtaining the graded abnormal evaluation value MZg of the soil heavy metal abnormal area, setting the range of each graded abnormal evaluation value to correspond to an abnormal evaluation grade, wherein the range of the graded abnormal evaluation value includes (0, MZ1], (MZ1, MZ2], …, (MZg-1, MZg], MZ1<MZ2<…<MZg-1<MZg, the abnormal evaluation grade includes abnormal evaluation grade 1, abnormal evaluation grade 2, …, abnormal evaluation grade g-1, abnormal evaluation grade g, when MZg∈(MZ1, MZ2], the abnormal evaluation grade is abnormal evaluation grade 2, wherein the higher the abnormal evaluation grade (the abnormal evaluation grade g is higher than the abnormal evaluation grade g-1), the more abnormal the soil heavy metal pollution in the soil heavy metal abnormal area is.

[0026] The graded abnormal evaluation value of the soil heavy metal abnormal area is obtained by the following steps: determine the regional abnormal distance according to the regional abnormal identification value AGPk of the soil heavy metal abnormal area, mark the remaining soil heavy metal abnormal areas as abnormal evaluation influence areas (the soil heavy metal abnormal areas except the soil heavy metal abnormal area are all abnormal evaluation influence areas), obtain the distance between the soil heavy metal abnormal area and each abnormal evaluation influence area (if the soil heavy metal abnormal area is the soil heavy metal abnormal area A, there are 2 abnormal evaluation influence areas, namely abnormal evaluation influence area B and abnormal evaluation influence area C, then obtain the distance between the soil heavy metal abnormal area A and the abnormal evaluation influence area B, and obtain the soil heavy metal abnormal area A The distance from the abnormal evaluation affected area C, the distance between two soil heavy metal abnormal areas is usually measured by map measurement. First, obtain a map containing two soil heavy metal abnormal areas, which can be a paper map or a digital map, such as a GIS map. Mark the boundaries of the two soil heavy metal pollution areas on the map, and use the measurement tools on the map to measure the shortest distance between the two soil heavy metal pollution areas). When the distance between the soil heavy metal abnormal area and the abnormal evaluation affected area is greater than or equal to the regional abnormal distance, no processing is performed. When the distance between the soil heavy metal abnormal area and the abnormal evaluation affected area is less than the regional abnormal distance, the regional abnormal spread number is increased by one, and the regional abnormal spread number is marked as HBCe. Using the formula The graded anomaly evaluation value MZg of the soil heavy metal abnormal area is obtained, where fa is the regional anomaly coefficient, fb is the regional anomaly propagation coefficient, the value of fa is 1.63, and the value of fb is 1.04.

[0027] The regional anomaly distance is determined according to the regional anomaly identification value AGPk of soil heavy metals, specifically: the range of each regional anomaly identification value is set to correspond to a regional anomaly distance, wherein the range of the regional anomaly identification value includes (0, AGP1], (AGP1, AGP2], …, (AGPk-1, AGPk], AGP1<AGP2<…<AGPk-1<AGPk, the regional anomaly distance includes regional anomaly distance 1, regional anomaly distance 2, …, regional anomaly distance k-1, regional anomaly distance k, the length of regional anomaly distance 1<the length of regional anomaly distance 2<…<the length of regional anomaly distance k-1<the length of regional anomaly distance k, when AGPk∈(AGP1, AGP2], the regional anomaly distance is regional anomaly distance 2.

[0028] Through steps one and two, the multi-source data of each soil heavy metal pollution area are integrated and deeply processed. Through multi-dimensional analysis of the multi-source data in independent and related ways, it is accurately and efficiently determined whether there are abnormalities in the soil heavy metal pollution area. Through step three, the abnormal soil heavy metal pollution area is deeply and comprehensively analyzed, and the abnormalities in the soil heavy metal pollution area are accurately and detailedly evaluated, which helps regional managers understand the degree of abnormality in the area.

[0029] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0030] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0031] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0032] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0033] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0034] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0035] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0036] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data, characterized in that: The steps include: Step 1: Identify all areas of soil heavy metal contamination; Step 2: Regularly obtain the regional anomaly identification value of each soil heavy metal pollution area, and determine whether to mark the soil heavy metal pollution area as a soil heavy metal abnormal area based on the comparison result between the regional anomaly identification value and the regional anomaly identification threshold value; Step 3: Conduct graded abnormal evaluation on areas with abnormal soil heavy metal content.

2. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 1 is characterized in that: The regional anomaly identification value of each soil heavy metal pollution area is obtained regularly, specifically: an anomaly identification cycle is generated, and each time an anomaly identification cycle is completed, the regional anomaly identification value of each soil heavy metal pollution area is obtained.

3. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 2 is characterized in that: The regional anomaly identification value of the soil heavy metal pollution area is obtained by the following steps: divide the pollution identification evaluation period into j equally spaced anomaly identification periods, obtain the period anomaly value of the soil heavy metal pollution area in each anomaly identification period, obtain the period anomaly total value DSm, sort all period anomaly values ​​according to the order of the anomaly identification period, calculate the difference between the anomaly values ​​of the two adjacent period after sorting and take the absolute value to obtain the anomaly rise and fall value, sum up all the anomaly rise and fall values ​​and take the average to obtain the average anomaly rise and fall value HWq, and use the formula The regional anomaly identification value AGPK of the soil heavy metal pollution area is obtained.

4. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 3 is characterized in that: The total time period anomaly value DSm is obtained through the following steps: a rectangular coordinate system is constructed with the pollution identification and evaluation period as the X-axis and the time period anomaly value as the Y-axis, the time period anomaly value of each anomaly identification time period is marked in the rectangular coordinate system in the form of a point, adjacent points in the rectangular coordinate system are connected to draw a time period anomaly curve, the two end points of the time period anomaly curve are perpendicular to the X-axis, and two time period start-end lines are obtained after the two perpendicular lines intersect the X-axis, and the total area of ​​the closed figure formed by the time period anomaly curve, the two time period start-end lines and the X-axis is marked as the total time period anomaly value DSm.

5. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 3 is characterized in that: The time period anomaly value of the anomaly identification period is obtained through the following steps: collecting various types of core impact data in the soil heavy metal pollution area within the anomaly identification period, and then obtaining the core impact value of each type of core impact data, setting the core impact demarcation value, when the core impact value is greater than or equal to the core impact demarcation value, marking this type of core impact data as core abnormal data, when the core impact value is less than the core impact demarcation value, marking this type of core impact data as core normal data, marking the number of core normal data as kzr, and grouping all core abnormal data into a core abnormal group in pairs, and combining the two cores in a core abnormal group. The core impact values ​​of the abnormal data are summed and averaged to obtain the core impact group value, and the core impact group threshold is set. When the core impact group value is greater than or equal to the core impact group threshold, the core abnormal group is marked as a core diffusion abnormal group, and the number of core diffusion abnormal groups is marked as acg. The core impact values ​​of two core abnormal data in a core abnormal group are calculated by difference and the absolute value is taken to obtain the core impact deviation value, and the core impact threshold deviation value is set. When the core impact deviation value is less than the core impact threshold deviation value, the core abnormal group is marked as a core synchronization abnormal group, and the number of core synchronization abnormal groups is marked as byt. The formula is used. The time period abnormal value Shp of the abnormal identification period is obtained, where wa is the core normal coefficient, wb is the core diffusion coefficient, and wc is the core synchronization coefficient.

6. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 5 is characterized in that: The core impact value of each type of core impact data is obtained through the following steps: obtaining the core impact model corresponding to each type of core impact data, preprocessing each type of core impact data, and inputting the preprocessed core impact data of each type into the corresponding core impact model, thereby obtaining the core impact value of each type of core impact data.

7. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 1 is characterized in that: The soil heavy metal abnormal area is graded for abnormal evaluation, specifically: obtaining the graded abnormal evaluation value MZg of the soil heavy metal abnormal area, setting the range of each graded abnormal evaluation value to correspond to an abnormal evaluation grade, wherein the range of the graded abnormal evaluation value includes (0, MZ1], (MZ1, MZ2], …, (MZg-1, MZg], MZ1<MZ2<…<MZg-1<MZg, the abnormal evaluation grades include abnormal evaluation grade 1, abnormal evaluation grade 2, …, abnormal evaluation grade g-1, abnormal evaluation grade g, the higher the abnormal evaluation grade, the more abnormal the soil heavy metal pollution in the soil heavy metal abnormal area is.

8. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 7 is characterized in that: The graded abnormal evaluation value of the soil heavy metal abnormal area is obtained by the following steps: determine the regional abnormal distance according to the regional abnormal identification value AGPk of the soil heavy metal abnormal area, mark the remaining soil heavy metal abnormal areas as abnormal evaluation influence areas, obtain the distance between the soil heavy metal abnormal area and each abnormal evaluation influence area, and when the distance between the soil heavy metal abnormal area and the abnormal evaluation influence area is less than the regional abnormal distance, increase the regional abnormal spread number by one, mark the regional abnormal spread number as HBCe, and use the formula The graded anomaly evaluation value MZg of the soil heavy metal abnormal area is obtained, where fa is the regional anomaly coefficient and fb is the regional anomaly propagation coefficient.

9. The method for identifying and evaluating abnormal soil heavy metal pollution areas based on multi-source data according to claim 8, characterized in that: The regional anomaly distance is determined according to the regional anomaly identification value AGPk of soil heavy metals, specifically: the range of each regional anomaly identification value is set to correspond to a regional anomaly distance, wherein the range of the regional anomaly identification value includes (0, AGP1], (AGP1, AGP2], …, (AGPk-1, AGPk], AGP1<AGP2<…<AGPk-1<AGPk, the regional anomaly distance includes regional anomaly distance 1, regional anomaly distance 2, …, regional anomaly distance k-1, regional anomaly distance k, the length of regional anomaly distance 1<the length of regional anomaly distance 2<…<the length of regional anomaly distance k-1<the length of regional anomaly distance k.

Images