A method for data processing and evaluation of heavy metal content at soil risk monitoring sites

Abstract

This invention relates to the field of environmental monitoring technology, specifically to a method for processing and evaluating heavy metal content data at soil risk monitoring sites. The method includes the following steps: acquiring historical heavy metal content data and historical X-ray fluorescence spectral data for soil risk monitoring sites; constructing a heavy metal content inversion model, training and validating the model using the historical heavy metal content data and the historical X-ray fluorescence spectral data; obtaining the inverted heavy metal content through the trained model, and combining the inverted heavy metal content with the geographical characteristics of the soil risk monitoring site to obtain the heavy metal variation diffusion coefficient; and evaluating the soil risk monitoring site based on the heavy metal variation diffusion coefficient. This invention predicts the heavy metal content for a projected period by inverting the heavy metal content and then calculating the metal variation diffusion coefficient based on geographical characteristics, which is beneficial for accurately assessing soil quality and guiding environmental governance.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, specifically to a method for processing and evaluating heavy metal content data at soil risk monitoring points. Background Technology

[0002] Soil is inextricably linked to production and daily life. Whether it's agricultural production, industrial development, or scientific research, soil resources are indispensable. Heavy metals naturally exist in the Earth's geological structure, but with the large-scale use of chemical fertilizers in agriculture and the discharge of waste products from industry, heavy metals are released into the environment as raw materials and intermediate products. These environmental heavy metal pollutants, through geological movements and natural phenomena, eventually accumulate in the soil, leading to a significant buildup of heavy metals in the Earth's surface. Because heavy metals are not easily decomposed by soil microorganisms and are persistent, they continue to accumulate and pose a threat to human health. Therefore, land planning and management are crucial. However, accurately and efficiently assessing soil heavy metal pollution levels over a given period remains a challenge in land planning and management. Summary of the Invention

[0003] To address the shortcomings of existing methods and the needs of practical applications, and to solve the problem of accurately and efficiently assessing soil heavy metal pollution over a certain period of time, thus providing a scientific basis for land resource management and utilization, this invention provides a method for processing and evaluating heavy metal content data at soil risk monitoring points. This method includes the following steps:

[0004] Historical heavy metal content data and historical X-ray fluorescence spectral data of soil risk monitoring sites are obtained; a heavy metal content inversion model is constructed, and the heavy metal content inversion model is trained and validated using the historical heavy metal content data and the historical X-ray fluorescence spectral data; the heavy metal inversion content is obtained through the trained heavy metal content inversion model, and the heavy metal variation diffusion coefficient is obtained by combining the heavy metal inversion content with the geographical characteristics of the soil risk monitoring sites; the soil risk monitoring sites are evaluated based on the heavy metal variation diffusion coefficient.

[0005] This invention constructs a heavy metal content inversion model to invert heavy metal content, then calculates the metal variation diffusion coefficient based on the geographical characteristics of soil risk monitoring points, thereby predicting the heavy metal content in the estimated period, and finally assessing the heavy metal pollution status of the soil in the estimated period. This is beneficial for accurately assessing soil quality, guiding environmental governance, rationally planning land use, guiding soil pollution remediation, and promoting coordinated economic and environmental development.

[0006] Optionally, the method for processing and evaluating heavy metal content data at soil risk monitoring points further includes the following steps:

[0007] This invention improves the threshold processing function of the wavelet denoising algorithm by introducing the hyperbolic tangent function; the improved wavelet denoising algorithm is then used to denoise the spectral data. This invention utilizes the hyperbolic tangent function to improve the threshold processing function of the wavelet denoising algorithm, which is beneficial for reducing noise in X-ray fluorescence spectral data and improving the accuracy of heavy metal content retrieval.

[0008] Optionally, the threshold processing function of the improved wavelet denoising algorithm by introducing the hyperbolic tangent function satisfies the following formula:

[0009]

[0010] in, Indicates the first Layer Wavelet coefficients after an improved wavelet transform algorithm Represents a symbolic function. Indicates the first Layer One standard wavelet coefficient, This represents the optimal wavelet decomposition level. Indicates the first Wavelet threshold of the layer.

[0011] Optionally, the construction of the heavy metal content inversion model includes the following steps:

[0012] The convergence factor of the Grey Wolf Optimization Algorithm is improved based on the fitness value; the coefficient vector of the Grey Wolf Optimization Algorithm is improved based on the optimized convergence factor; the optimal inversion parameters of the neural network algorithm are obtained using the improved Grey Wolf Optimization Algorithm, and the heavy metal content inversion model is constructed based on the optimal inversion parameters. This invention improves the convergence factor of the Grey Wolf Optimization Algorithm based on the fitness value, increasing the adaptability of the convergence factor, which can improve the convergence speed and further improve the efficiency of this invention.

[0013] Optionally, the convergence factor of the gray wolf optimization algorithm improved based on the fitness value satisfies the following formula:

[0014]

[0015] in, This represents the convergence factor of the improved Grey Wolf optimization algorithm. Indicates the first The fitness value of the wolf at the next iteration Indicates the first The fitness value of the leader wolf in the next iteration. Indicates the maximum number of iterations. This indicates the current iteration number.

[0016] Optionally, improving the coefficient vector of the Grey Wolf optimization algorithm based on the optimized convergence factor includes the following steps:

[0017] A coefficient vector selection factor is set; the coefficient vector is adjusted by combining the optimized convergence factor and the coefficient vector selection factor. This invention improves the uniformity of the gray wolf's position transformation distribution by adjusting the coefficient vector through the coefficient vector selection factor, further facilitating the global search for the optimal solution.

[0018] Optionally, obtaining the heavy metal variation diffusion coefficient by combining the heavy metal inversion content and the geographical characteristics of the soil risk monitoring points includes the following steps:

[0019] Based on the monitoring period, the rate of change of heavy metal content at the soil risk monitoring points is obtained using the heavy metal inversion content. A threshold for the rate of change of heavy metal content is set, and the soil risk monitoring points are screened using this threshold. The physical similarity between the screened soil risk monitoring points is obtained based on their geographical characteristics. The heavy metal variation diffusion coefficient is obtained by combining the rate of change of heavy metal content and the physical similarity. This invention first reduces the amount of data computation and improves the computational efficiency by screening soil risk monitoring points. Then, it constructs a heavy metal variation diffusion coefficient based on the physical similarity of the monitoring points and the rate of change of heavy metal content. This coefficient can fully represent the changes in heavy metal content at the monitoring points, which is beneficial for accurately obtaining the changes in heavy metal content during the assessment period, thereby improving the accuracy of this invention.

[0020] Optionally, the heavy metal variation diffusion coefficient is obtained by combining the rate of change of heavy metal content and the physical similarity, satisfying the following formula:

[0021]

[0022] in, Indicates the first The variational diffusion coefficient of heavy metals at each soil risk monitoring point This indicates the number of soil risk monitoring points after screening. Indicates the first The rate of change of heavy metal content at each soil risk monitoring point Indicates the first The soil risk monitoring points and the first Physical similarity of soil risk monitoring sites No. The rate of change of heavy metal content at each soil risk monitoring point.

[0023] Optionally, evaluating the soil risk monitoring sites based on the heavy metal variation diffusion coefficient includes the following steps:

[0024] Based on the heavy metal variation diffusion coefficient, the heavy metal content of the soil risk monitoring points during the assessment period is predicted; the heavy metal content during the assessment period is then used to evaluate the soil risk monitoring points. This invention provides objective and accurate data on the heavy metal content during the assessment period obtained based on the heavy metal variation diffusion coefficient, which is beneficial for providing a scientific basis for land resource management and utilization.

[0025] Optionally, the evaluation of the soil risk monitoring sites includes the following steps:

[0026] The geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index of the soil risk monitoring sites are calculated. Based on these indices, the soil risk monitoring sites are comprehensively evaluated. This invention comprehensively assesses soil heavy metal pollution through multiple evaluation indicators, further ensuring the objectivity and accuracy of the invention. Attached Figure Description

[0027] Figure 1 This is a flowchart of a method for processing and evaluating heavy metal content data at soil risk monitoring points, provided by an embodiment of the present invention.

[0028] Figure 2 This is a framework diagram of a soil risk monitoring point heavy metal content data processing and evaluation system provided in an embodiment of the present invention. Detailed Implementation

[0029] Specific embodiments of the present invention will now be described in detail. It should be noted that the embodiments described herein are for illustrative purposes only and are not intended to limit the invention. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that these specific details are not necessary to practice the invention. In other instances, well-known circuits, software, or methods have not been specifically described to avoid obscuring the invention.

[0030] Throughout this specification, references to "an embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with that embodiment or example is included in at least one embodiment of the invention. Therefore, the phrases "in an embodiment," "in an embodiment," "an example," or "an example" appearing in various places throughout the specification do not necessarily refer to the same embodiment or example. Furthermore, specific features, structures, or characteristics can be combined in one or more embodiments or examples in any suitable combination and / or sub-combination. Moreover, those skilled in the art will understand that the illustrations provided herein are for illustrative purposes and are not necessarily drawn to scale.

[0031] Please see Figure 1 To address the challenge of accurately and efficiently assessing soil heavy metal pollution and providing a scientific basis for land resource management and utilization, this invention offers a method for processing and evaluating heavy metal content data at soil risk monitoring points. Figure 1 As shown, in one embodiment, the method includes the following steps:

[0032] S1. Obtain historical heavy metal content data and historical X-ray fluorescence spectral data of soil risk monitoring points.

[0033] Soil risk monitoring points refer to the locations set up in and around soil environmental risk sources (pollution sources) that are already polluted or may be polluted, as well as in sensitive areas, to meet specific objectives of soil environmental supervision.

[0034] In this embodiment, heavy metals that are highly toxic in the soil and pose a threat to human health, including copper, lead, cadmium, chromium, mercury, arsenic, and nickel, are selected as targets for soil pollution screening. Furthermore, the content of heavy metal elements is usually expressed as mass concentration, reflecting the relative content of heavy metals in a particular substance. To ensure the effective training of the heavy metal content inversion model in subsequent steps, the content of heavy metal elements is preferably measured experimentally.

[0035] X-ray fluorescence spectroscopy data refers to data obtained by analyzing soil samples using X-ray fluorescence spectroscopy. When high-energy X-rays collide with atoms in the sample, they excite the transition of inner-shell electrons, releasing characteristic X-ray fluorescence, thus yielding X-ray fluorescence spectroscopy data.

[0036] Specifically, historical data is retrieved from relevant environmental management and monitoring databases. In order to further train the heavy metal content inversion model in subsequent steps, it is preferable to obtain a large amount of sample data. The more historical data samples obtained, the better the training effect.

[0037] It should be understood that, due to the relatively low content of heavy metal elements in soil, weak peaks are easily lost under severe noise conditions. At the same time, the spectral signal is subject to background interference due to instrument and environmental factors. Furthermore, soil heavy metal element analysis suffers from severe spectral interference problems such as interference from adjacent elements, overlapping peaks, and L-layer and K-layer spectral lines. X-ray fluorescence spectral data also needs to undergo noise reduction processing to address noise and baseline drift issues caused by the instrument itself, the external environment, and human factors.

[0038] Furthermore, the X-ray fluorescence spectroscopy data undergoes noise reduction processing, including the following steps:

[0039] S11. Introduce the hyperbolic tangent function to improve the threshold processing function of the wavelet denoising algorithm.

[0040] Specifically, the threshold processing function of the improved wavelet denoising algorithm by introducing the hyperbolic tangent function satisfies the following formula:

[0041]

[0042] in, Indicates the first Layer Wavelet coefficients after an improved wavelet transform algorithm Represents a symbolic function. Indicates the first Layer One standard wavelet coefficient, This represents the optimal wavelet decomposition level. Indicates the first Wavelet threshold of the layer.

[0043] Wavelet denoising algorithms use thresholding of wavelet coefficients to set smaller wavelet coefficients to 0 while retaining larger ones. The thresholding function determines the precision and accuracy of wavelet coefficient quantization. Traditional wavelet denoising algorithms use hard thresholding and soft thresholding.

[0044] The hard thresholding function is a piecewise discontinuous function, which is discontinuous at the threshold, causing signal oscillation during signal reconstruction. The soft thresholding function, in order to maintain the continuity of the function as a whole, performs threshold reduction on the part of the wavelet coefficients whose absolute values ​​are greater than the threshold. By subtracting the threshold from the wavelet coefficients with larger absolute values, the overall function becomes smooth and continuous. However, this also causes a constant deviation between the processed wavelet coefficients and the wavelet coefficients of the real signal, resulting in a decrease in the accuracy of the reconstructed signal.

[0045] This invention introduces a hyperbolic tangent function to improve the threshold processing function of the wavelet denoising algorithm. This avoids the disadvantage of discontinuity at the threshold in the hard threshold processing function and the disadvantage of constant deviation in the soft threshold function. The constructed threshold processing function is smooth and continuous, retains most of the wavelet coefficients with large absolute values, and sets the smaller wavelet coefficients to zero.

[0046] S12. The spectral data is denoised using an improved wavelet denoising algorithm.

[0047] Specifically, the spectral data is first decomposed using wavelet transform to obtain a series of wavelet coefficients, which contain information about the signal at different frequencies and locations. Second, thresholding is performed using an improved thresholding function to remove noise from the wavelet coefficients. Finally, wavelet reconstruction is performed using the processed wavelet coefficients and inverse wavelet transform to reconstruct the denoised signal. By decomposing the spectral data signal into wavelet subspaces of different frequencies and utilizing the sparsity and statistical properties of wavelet coefficients, noise is effectively removed while preserving the main features of the signal.

[0048] S2. Construct a heavy metal content inversion model, and train and verify the heavy metal content inversion model using the historical heavy metal content data and the historical X-ray fluorescence spectroscopy data.

[0049] In this embodiment, step S2, which involves constructing a heavy metal content inversion model, includes the following steps:

[0050] S21. Improve the convergence factor of the gray wolf optimization algorithm based on the fitness value.

[0051] Specifically, the convergence factor of the gray wolf optimization algorithm improved based on the fitness value satisfies the following formula:

[0052]

[0053] in, This represents the convergence factor of the improved Grey Wolf optimization algorithm. Indicates the first The fitness value of the wolf at the next iteration Indicates the first The fitness value of the leader wolf in the next iteration. Indicates the maximum number of iterations. This indicates the current iteration number.

[0054] In the gray wolf optimization algorithm, the gray wolf gradually approaches and surrounds its prey while searching for it. The mathematical model for this prey-surrounding process considers factors such as the wolf's position, the current iteration number, the prey's position, and the distance between the wolf and prey. To simulate this approaching of the prey, the convergence factor in the algorithm is gradually reduced, thereby decreasing the fluctuation range of A. In the iterative process of the traditional gray wolf optimization algorithm, when the convergence factor decreases linearly from 2 to 0, the corresponding value of A also varies within a certain range. This linear decrease in the convergence factor can lead to the problem of getting stuck in local optima, making it impossible to analyze and find the optimal parameters from a global perspective to achieve the best optimization of the model. This invention utilizes the gray wolf's fitness value to adjust the convergence factor, adaptively controlling the convergence effect based on the solution results, further improving the solution capability of this invention and thus improving the inversion accuracy of the heavy metal content inversion model.

[0055] S22. Based on the optimized convergence factor, improve the coefficient vector of the Grey Wolf optimization algorithm.

[0056] In this embodiment, improving the coefficient vector of the Grey Wolf optimization algorithm based on the optimized convergence factor includes the following steps:

[0057] S221, Set the coefficient vector selection factor.

[0058] The coefficient vector selection factor is used to balance global search speed and local search accuracy. In the Grey Wolf optimization algorithm, a broad global search is often required in the early stages of iteration, while a detailed local search is performed in the later stages. In this embodiment, the coefficient vector selection factor is half of the maximum number of iterations, i.e. .

[0059] S222. Combine the optimized convergence factor and the coefficient vector selection factor to adjust the coefficient vector.

[0060] The coefficient vectors A and C are used to simulate the attack behavior of gray wolves on their prey and to provide random weights, respectively. Furthermore, by combining the optimized convergence factor and the coefficient vector selection factor, the coefficient vector can be adjusted to improve the uniformity of the gray wolf's position change distribution, which is more conducive to global search for the optimal solution.

[0061] In an optional embodiment, the coefficient vector is adjusted by combining the optimized convergence factor and the coefficient vector selection factor to satisfy the following formula:

[0062]

[0063] in, , This represents the coefficient vector of the Grey Wolf optimization algorithm. Indicates the maximum number of iterations. Indicates the current iteration number. This represents the selection factor for the coefficient vector. This represents the convergence factor of the improved Grey Wolf optimization algorithm. Represents a random number between [0, 1].

[0064] S23. Using the improved gray wolf optimization algorithm, the optimal inversion parameters of the neural network algorithm are obtained, and the heavy metal content inversion model is constructed based on the optimal inversion parameters.

[0065] In this embodiment, the neural network consists of multiple layers, typically including an input layer, multiple hidden layers, and an output layer. Each neuron receives multiple input signals, performs weighted summation, and generates an output signal through an activation function. By receiving input data (features) and the corresponding output (target value), it continuously adjusts its internal weights and biases to minimize prediction error.

[0066] Specifically, the inversion parameters of the neural network algorithm include parameters that affect prediction accuracy, such as the number of hidden layer nodes and activation functions.

[0067] Furthermore, a certain number of gray wolf individuals are randomly generated based on the inversion parameters of the neural network algorithm, with each individual representing a potential solution. Then, the improved gray wolf optimization algorithm is used to obtain the optimal inversion parameters of the neural network algorithm. The obtained optimal inversion parameters are applied to the neural network algorithm to obtain the heavy metal content inversion model.

[0068] S3. Obtain the heavy metal inversion content through the trained heavy metal content inversion model, and obtain the heavy metal variation diffusion coefficient by combining the heavy metal inversion content with the geographical characteristics of the soil risk monitoring points.

[0069] Specifically, X-ray fluorescence spectral data are obtained at soil risk monitoring points, and then the heavy metal content is obtained by using a trained heavy metal content inversion model.

[0070] Furthermore, the step of combining the heavy metal inversion content with the geographical characteristics of the soil risk monitoring points to obtain the heavy metal variation diffusion coefficient includes the following steps:

[0071] S31. Based on the monitoring period, the rate of change of heavy metal content at the soil risk monitoring point is obtained using the heavy metal inversion content.

[0072] In this embodiment, heavy metal pollution does not form in a short period of time. Therefore, in order to avoid wasting monitoring resources, it is necessary to set a monitoring cycle according to actual needs, and then obtain the rate of change of heavy metal content at the soil risk monitoring point based on the change in heavy metal content at the soil risk monitoring point within a cycle.

[0073] S32. Set a threshold for the rate of change of heavy metal content, and use the threshold for the rate of change of heavy metal content to screen the soil risk monitoring points.

[0074] A small rate of change in heavy metal content indicates stable heavy metal content, meaning that existing data can be used to assess heavy metal pollution at the corresponding soil risk monitoring sites, reducing the waste of computational resources.

[0075] Specifically, a threshold for the rate of change of heavy metal content is set according to the actual situation, and soil risk monitoring points with a rate of change of heavy metal content less than the threshold are screened out.

[0076] S33. Based on the geographical characteristics of the selected soil risk monitoring points, obtain the physical similarity between the soil risk monitoring points.

[0077] The geographical characteristics of soil risk monitoring sites refer to the geological factors that affect heavy metal deposition, such as latitude and longitude, altitude, land use, and geomorphological features of the location of the soil risk monitoring sites.

[0078] Furthermore, a geographic feature matrix of soil risk monitoring points is constructed based on geographical characteristics, and then a similarity algorithm is used to calculate the physical similarity between the soil risk monitoring points. In this embodiment, the similarity algorithm is the Pearson correlation coefficient method. In other embodiments, other similarity algorithms such as the Euclidean distance method can also be used.

[0079] S34. Combining the rate of change of heavy metal content and the physical similarity, obtain the heavy metal variation diffusion coefficient.

[0080] In this embodiment, the heavy metal variation diffusion coefficient is obtained by combining the rate of change of heavy metal content and the physical similarity, satisfying the following formula:

[0081]

[0082] in, Indicates the first The variational diffusion coefficient of heavy metals at each soil risk monitoring point This indicates the number of soil risk monitoring points after screening. Indicates the first The rate of change of heavy metal content at each soil risk monitoring point Indicates the first The soil risk monitoring points and the first Physical similarity of soil risk monitoring sites No. The rate of change of heavy metal content at each soil risk monitoring point.

[0083] S4. Evaluate the soil risk monitoring points based on the heavy metal variation diffusion coefficient.

[0084] In this embodiment, evaluating the soil risk monitoring sites based on the heavy metal variation diffusion coefficient includes the following steps:

[0085] S41. Based on the heavy metal variation diffusion coefficient, predict the heavy metal content of the soil risk monitoring point during the assessment period.

[0086] In this embodiment, the rate of change of heavy metal content at the soil risk monitoring point during the assessment period is calculated based on the heavy metal variation diffusion coefficient. Then, the assessment period is determined based on planning requirements, and the heavy metal content at the soil risk monitoring point during the assessment period is predicted.

[0087] Specifically, based on the heavy metal variation diffusion coefficient, the heavy metal content at the soil risk monitoring site during the assessment period is predicted, satisfying the following formula:

[0088]

[0089] in, Indicates the heavy metal content during the assessment period. Indicates the current heavy metal content. This indicates the rate of change of heavy metal content at soil risk monitoring sites. This represents the variational diffusion coefficient of heavy metals at soil risk monitoring sites. Indicates a time period.

[0090] S42. Evaluate the soil risk monitoring points based on the heavy metal content during the assessment period.

[0091] In this embodiment, the evaluation of soil risk monitoring sites based on heavy metal content during the assessment period includes the following steps:

[0092] S421. Calculate the geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index for the soil risk monitoring points.

[0093] Geoaccumulation index is used for quantitative assessment of the degree of heavy metal pollution in soil. It takes into account the combined effects of natural geological activities and human behavior on heavy metal environmental pollution, thus reflecting the degree of heavy metal pollution in regional soils and helping to distinguish the impact of human activities.

[0094] The Nemerow Pollution Index (NRI) is a comprehensive pollution assessment method, developed based on the single-factor index method. Compared to single-factor index methods, the NRI considers more influencing factors of pollutants, including average and maximum concentrations, as well as the combined effects between various pollutants. This allows the NRI to more comprehensively assess the degree of soil pollution, particularly for more severe pollutants.

[0095] The pollution load index can provide a comprehensive indicator to represent the pollution level of a region or sample point by multiple heavy metals, thereby providing a more comprehensive assessment of the degree of soil pollution.

[0096] The potential ecological risk index calculates a risk index for each pollutant by taking into account factors such as the toxicity and environmental concentration of pollutants, and then comprehensively assesses the overall ecological risk in the region.

[0097] Calculating the geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index for the soil risk monitoring points is a routine skill possessed by those skilled in the art, and therefore will not be described in detail.

[0098] S422. Based on the aforementioned geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index, comprehensively evaluate the soil risk monitoring points.

[0099] Specifically, the weight allocation of each index is determined according to the specific circumstances. By combining the values ​​and weights of each index, a comprehensive score or evaluation level is obtained to reflect the overall status of soil risk.

[0100] Please see Figure 2 In this embodiment, to efficiently execute the method for processing and evaluating heavy metal content data at soil risk monitoring points provided by this invention, this invention also provides a system for processing and evaluating heavy metal content data at soil risk monitoring points, comprising: an input device, an output device, a processor, and a memory. The input device, output device, processor, and memory are interconnected. The memory contains program instructions used for the steps of the method for processing and evaluating heavy metal content data at soil risk monitoring points. The system for processing and evaluating heavy metal content data at soil risk monitoring points provided by this invention has a compact structure and stable performance, and can stably execute the method for processing and evaluating heavy metal content data at soil risk monitoring points provided by this invention, further enhancing the overall applicability and practical application capability of this invention.

[0101] In embodiments, the processor may be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Input devices can be used to acquire data information. Output devices can be used to output the results obtained by storing program instructions contained in a computer program in the memory provided by this invention. The memory may include read-only memory and random access memory, and provides instructions and data to the processor. A portion of the memory may also include non-volatile random access memory.

[0102] In one possible implementation, the memory may include a stored program area and a stored data area. The stored program area may store the operating system and applications required for at least one function; the stored data area may store data created during use. Furthermore, the memory may include read-only memory and random access memory, providing instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores the operating system and operating instructions, executable modules, or data structures, or subsets thereof, or extended sets thereof. The operating instructions may include various operation instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and handling hardware-based tasks.

[0103] The embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described method for processing and evaluating heavy metal content data at soil risk monitoring points.

[0104] The storage medium can include various media that can store program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0105] In summary, this invention constructs a heavy metal content inversion model to invert heavy metal content, then calculates the metal variation diffusion coefficient based on the geographical characteristics of soil risk monitoring points, thereby predicting the heavy metal content in the estimated period. Finally, it assesses the heavy metal pollution status of the soil in the estimated period, which is beneficial for accurately assessing soil quality, guiding environmental governance, rationally planning land use, guiding soil pollution remediation, and promoting coordinated economic and environmental development.

[0106] Therefore, this invention effectively overcomes the various shortcomings of the prior art and has high industrial application value.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the present invention.

Claims

1. A method for processing and evaluating heavy metal content data at soil risk monitoring points, characterized in that, The method for processing and evaluating heavy metal content data at soil risk monitoring points includes the following steps: Obtain historical heavy metal content data and historical X-ray fluorescence spectral data for soil risk monitoring sites; A heavy metal content inversion model was constructed, and the heavy metal content inversion model was trained and validated using the historical heavy metal content data and the historical X-ray fluorescence spectroscopy data. The heavy metal inversion content is obtained by using a trained heavy metal content inversion model. The heavy metal variation diffusion coefficient is obtained by combining the heavy metal inversion content with the geographical characteristics of the soil risk monitoring points. The soil risk monitoring sites are evaluated based on the aforementioned heavy metal variation diffusion coefficient. The process of obtaining the heavy metal variation diffusion coefficient by combining the heavy metal inversion content with the geographical characteristics of the soil risk monitoring points includes the following steps: Based on the monitoring period, the rate of change of heavy metal content at the soil risk monitoring points is obtained using the heavy metal inversion content. Set a threshold for the rate of change of heavy metal content, and use the threshold for the rate of change of heavy metal content to screen the soil risk monitoring points; Based on the geographical characteristics of the selected soil risk monitoring sites, the physical similarity between the soil risk monitoring sites is obtained. The heavy metal variation diffusion coefficient is obtained by combining the rate of change of heavy metal content and the physical similarity. The heavy metal variation diffusion coefficient is obtained by combining the rate of change of heavy metal content and the physical similarity, and satisfies the following formula: in, Indicates the first The variational diffusion coefficient of heavy metals at each soil risk monitoring point This indicates the number of soil risk monitoring points after screening. Indicates the first The rate of change of heavy metal content at each soil risk monitoring point Indicates the first The soil risk monitoring points and the first Physical similarity of soil risk monitoring sites Indicates the first The rate of change of heavy metal content at each soil risk monitoring point; The evaluation of the soil risk monitoring sites based on the heavy metal variation diffusion coefficient includes the following steps: Based on the aforementioned heavy metal variation diffusion coefficient, the heavy metal content at the soil risk monitoring points during the assessment period is predicted. The soil risk monitoring sites are evaluated based on the heavy metal content during the assessment period. Based on the aforementioned heavy metal variation diffusion coefficient, the heavy metal content at the soil risk monitoring sites during the assessment period is predicted, satisfying the following formula: in, Indicates the heavy metal content during the assessment period. This indicates the current heavy metal content. This indicates the rate of change of heavy metal content at soil risk monitoring sites. This represents the variational diffusion coefficient of heavy metals at soil risk monitoring sites. Indicates a time period.

2. The method for processing and evaluating heavy metal content data at soil risk monitoring points according to claim 1, characterized in that, It also includes the following steps: The threshold processing function of the wavelet denoising algorithm is improved by introducing the hyperbolic tangent function; An improved wavelet denoising algorithm is used to denoise spectral data.

3. The method for processing and evaluating heavy metal content data at soil risk monitoring points according to claim 2, characterized in that, The threshold processing function of the improved wavelet denoising algorithm, which incorporates the hyperbolic tangent function, satisfies the following formula: in, Indicates the first Layer Wavelet coefficients after an improved wavelet transform algorithm Represents a symbolic function. Indicates the first Layer One standard wavelet coefficient, This represents the optimal wavelet decomposition level. Indicates the first Wavelet threshold of the layer.

4. The method for processing and evaluating heavy metal content data at soil risk monitoring points according to claim 1, characterized in that, The construction of the heavy metal content inversion model includes the following steps: The convergence factor of the gray wolf optimization algorithm is improved based on the fitness value; Based on the optimized convergence factor, the coefficient vector of the Grey Wolf optimization algorithm is improved; The optimal inversion parameters of the neural network algorithm are obtained by using the improved gray wolf optimization algorithm, and the heavy metal content inversion model is constructed based on the optimal inversion parameters.

5. The method for processing and evaluating heavy metal content data at soil risk monitoring points according to claim 4, characterized in that, The improvement of the coefficient vector of the Grey Wolf optimization algorithm based on the optimized convergence factor includes the following steps: Set the coefficient vector selection factor; The coefficient vector is adjusted by combining the optimized convergence factor and the coefficient vector selection factor.

6. The method for processing and evaluating heavy metal content data at soil risk monitoring points according to claim 1, characterized in that, The evaluation of the soil risk monitoring sites includes the following steps: Calculate the geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index for the soil risk monitoring sites; The soil risk monitoring sites are comprehensively evaluated based on the geoaccumulation index, Nemerow pollution index, pollution load index, and potential ecological risk index.

Images