A method and system for monitoring soil pollutants in a power transmission and transformation project

Abstract

The application relates to the technical field of soil monitoring, and discloses a method and system for monitoring soil pollutants in a power transmission and transformation project, wherein the method comprises the following steps: collecting hyperspectral image data in a power transmission and transformation project area; processing the hyperspectral image data by adopting a multistage spectral transformation mechanism to obtain characteristic wave bands representing pollutant contents; inputting the characteristic wave bands into a preset spectral inversion model to generate a concentration spatial distribution map of soil pollutants; constructing a soil and groundwater diffusion model according to the concentration spatial distribution map; and generating a migration path identification map of soil pollutants and an underground pollution risk area identification map based on the soil and groundwater diffusion model. The method has the beneficial effect of improving pollution identification precision and migration prediction accuracy.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of soil monitoring, in particular to a method and system for monitoring soil pollutants in a power transmission and transformation project. BACKGROUND

[0002] Soil, as the core carrier of the ecological system, undertakes key functions such as material transformation, energy flow and water regulation, and its quality is directly related to food security and public health. However, the industrialization process has led to a large amount of heavy metals (such as cadmium and lead), persistent organic pollutants (POPs) and petroleum hydrocarbons invading the soil, causing the pollution exceeding standard rate to rise. As an important energy infrastructure, the soil pollution problem in the region of a power transmission and transformation project cannot be ignored. The power transmission and transformation project involves the construction and operation of devices such as substations, switch stations and power transmission line towers, and during the process, the soil may be contaminated by characteristic pollutants due to device leakage (such as transformer oil and sulfur hexafluoride decomposition products), material corrosion (such as heavy metal residues) and accumulation of engineering waste. Such pollution has the characteristics of strong concealment, complex diffusion path (affected by groundwater flow and soil permeability) and close association with engineering equipment distribution, which puts special requirements on the timeliness, accuracy and spatial coverage capability of the monitoring technology. The related soil pollution monitoring methods for power transmission and transformation projects have the defects of slow response, low precision and difficult prediction, which restricts the timeliness and pertinence of pollution control. SUMMARY

[0003] The application provides a method and system for monitoring soil pollutants in a power transmission and transformation project, which solves the technical problems of insufficient sensitivity and difficult prediction of related monitoring methods, and achieves the technical effect of improving pollution identification accuracy and migration prediction accuracy.

[0004] In order to achieve the above purpose, the main technical scheme adopted by the application includes:

[0005] In a first aspect, the application provides a method for monitoring soil pollutants in a power transmission and transformation project, which includes: collecting hyperspectral image data in the region of a power transmission and transformation project; processing the hyperspectral image data using a multi-stage spectral transformation mechanism to obtain a characteristic band representing the content of pollutants; inputting the characteristic band into a preset spectral inversion model to generate a concentration spatial distribution map of soil pollutants; constructing a soil and groundwater diffusion model according to the concentration spatial distribution map, and generating a migration path identification map of soil pollutants and a groundwater pollution risk area identification map based on the soil and groundwater diffusion model.

[0006] The method for monitoring soil pollutants in a power transmission and transformation project provided in the embodiments of the present application comprises the following steps: collecting hyperspectral image data in a power transmission and transformation project area; processing the hyperspectral image data by using a multi-stage spectral transformation mechanism to obtain characteristic bands representing pollutant content; inputting the characteristic bands into a preset spectral inversion model to generate a concentration spatial distribution map of soil pollutants; constructing a soil and groundwater diffusion model according to the concentration spatial distribution map, and generating a migration path identification map of soil pollutants and an underground pollution risk area identification map based on the soil and groundwater diffusion model, thereby solving the technical problems of insufficient sensitivity and difficult prediction of related monitoring methods and achieving the technical effects of improving pollution identification accuracy and migration prediction accuracy.

[0007] Optionally, the method further comprises: collecting the hyperspectral image data through a plurality of monitoring points preset in the power transmission and transformation project area; wherein each monitoring point is provided with a differentiated marker pollutant, and each marker pollutant has a sensitive feature at a specific band; the sensitive feature is a regular change mode of spectral reflectance curve caused by an increase in pollutant concentration.

[0008] Optionally, the method further comprises: spatiotemporally aligning multi-temporal hyperspectral image data with in-situ ground data to generate a pollutant reference concentration matrix; the pollutant reference concentration matrix comprises four-tuple data of position, time, spectrum and concentration; constructing a pollutant diffusion model based on the pollutant reference concentration matrix and a groundwater diffusion model, and extracting time-series spectral features based on the pollutant diffusion model; the time-series spectral features are used to represent changes in pollutant concentration and spectral dynamics; and grading and calibrating a pollutant concentration enhancement area according to the time-series spectral features and a preset concentration change rate threshold.

[0009] Optionally, the method further comprises: processing the hyperspectral image data by using a recursive feature elimination method to obtain characteristic bands representing pollutant content; and judging the pollutant concentration grade of each monitoring point by using adaptive threshold mapping based on the characteristic bands to generate a pollutant distribution map, wherein the adaptive threshold mapping is used to associate pollutant types and characteristic band thresholds, and the width of the characteristic band is used to represent pollutant concentration.

[0010] Optionally, the method further comprises: constructing an adversarial hyperspectral sample simulating an interference environment of a power transmission and transformation project; identifying abnormal disturbances in the process of adaptive threshold mapping based on the adversarial hyperspectral sample; and correcting the pollutant concentration of the characteristic band based on the abnormal disturbances.

[0011] Optionally, the characteristic waveband is input into a spectrum inversion model, including: determining a dynamic sensitive waveband according to a pollutant absorption peak matched with the characteristic waveband, the dynamic sensitive waveband being used to represent a spectrum waveband having significant sensitivity to a change in pollutant concentration or a migration process; processing the dynamic sensitive waveband by the spectrum inversion model to generate a concentration spatial distribution map of the soil pollutant, the concentration spatial distribution map including initial distribution data of the soil pollutant and real-time distribution data of the soil pollutant in a diffusion state with the groundwater at any time.

[0012] Optionally, the concentration spatial distribution map contains a geographic elevation display map based on the power transmission and transformation project area; the geographic elevation display map is constructed based on fusion of dynamic environmental parameters and ground in-situ monitoring data; a migration path prediction map of the soil pollutant is generated based on the geographic elevation display map and a migration risk value, the migration path prediction map being used to represent a migration trend of the pollutant; a migration path identification map of the soil pollutant is generated according to the migration path prediction map and the migration risk value.

[0013] Optionally, constructing the soil and groundwater diffusion model according to the concentration spatial distribution map includes: loading the concentration spatial distribution map into a preset physical diffusion model to generate a pollutant diffusion matrix based on three-dimensional migration data; the pollutant diffusion matrix includes a soil intrusion type diffusion matrix and a groundwater high-speed dispersion diffusion matrix; determining a spatiotemporal state feature of the pollutant based on the pollutant diffusion matrix, the spatiotemporal state feature being diffusion state data of the pollutant in a time dimension and a space dimension; constructing the soil and groundwater diffusion model based on the spatiotemporal state feature.

[0014] Optionally, generating the migration path identification map of the soil pollutant and the underground pollution risk area identification map based on the soil and groundwater diffusion model includes: generating three-dimensional migration data based on the soil and groundwater diffusion model; determining a diffusion weight of different migration diffusion coordinate points on a migration trajectory according to the three-dimensional migration data, and determining an emergency control risk value based on the diffusion weight; generating a migration path identification map according to the emergency control risk value; performing vulnerability calculation of the power transmission and transformation project area according to the migration path identification map to obtain vulnerability values of different areas, and generating an underground pollution risk area identification map based on the vulnerability values and the emergency control risk value.

[0015] In a second aspect, the embodiments of the present application provide a monitoring system for soil pollutants in a power transmission and transformation project, comprising: a collection module configured to collect hyperspectral image data in a power transmission and transformation project area; a transformation module configured to perform spectral transformation processing on the hyperspectral image data to obtain characteristic bands representing pollutant content; a generation module configured to input the characteristic bands into a spectral inversion model to generate a concentration spatial distribution map of soil pollutants; and a marking module configured to construct a soil and groundwater diffusion model according to the concentration spatial distribution map, and generate a migration path marking map of soil pollutants and a marking map of a groundwater pollution risk area based on the soil and groundwater diffusion model.

[0016] In a third aspect, the embodiments of the present application provide a computer device, comprising: a memory and a processor, which are in communication connection with each other, and the memory stores computer instructions, and the processor executes the computer instructions to perform the monitoring method for soil pollutants in a power transmission and transformation project.

[0017] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores computer instructions, and the computer instructions are used to make a computer execute the monitoring method for soil pollutants in a power transmission and transformation project.

[0018] In a fifth aspect, the embodiments of the present application provide a computer program product, which comprises computer instructions, and the computer instructions are used to make a computer execute the monitoring method for soil pollutants in a power transmission and transformation project. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the description of the embodiments or the prior art will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0020] Figure 1 A flow chart of the monitoring method for soil pollutants in a power transmission and transformation project provided by the embodiments of the present application;

[0021] Figure 2 A schematic diagram of the monitoring system for soil pollutants in a power transmission and transformation project provided by the embodiments of the present application;

[0022] Figure 3 A structural schematic diagram of a computer device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0024] Soil, as a core component of the ecosystem, is the core medium for key ecological processes such as material transformation, energy flow, and water regulation. Its quality is directly related to food security and public health. However, the industrialization process has led to a large amount of heavy metals (such as cadmium and lead), persistent organic pollutants (POPs), and petroleum hydrocarbons entering and accumulating in the soil, causing serious pollution. Such pollution is characterized by complex types, varying degrees, and hidden diffusion. In particular, in the area of power transmission and transformation projects, unique pollution sources such as transformer oil leakage and sulfur hexafluoride decomposition further exacerbate the difficulty of governance.

[0025] Traditional monitoring methods mainly refer to laboratory chemical analysis, such as atomic absorption spectrometry (AAS) and gas chromatography-mass spectrometry (GC-MS). Although these methods have high accuracy, they have problems such as long sampling period (usually several weeks), high cost (single sample detection cost exceeds one thousand yuan), and limited spatial coverage, making it difficult to meet the needs of large-scale and dynamic monitoring. In recent years, the integrated application of 3S technology (remote sensing-RS, geographic information system-GIS, global positioning system-GPS) has significantly improved monitoring efficiency. For example, hyperspectral remote sensing can identify specific absorption bands of heavy metals in soil, and combined with GIS spatial analysis, it can quickly delineate the pollution range. Biological monitoring technology indirectly reflects the degree of pollution stress by detecting changes in soil microbial community structure or plant physiological response, but its quantitative accuracy is greatly affected by environmental factors. In addition, the development of Internet of Things sensing technology has given rise to real-time soil parameter monitoring networks. Electrochemical sensors and fluorescent probes can obtain pH, conductivity, and specific pollutant concentration data online. However, due to limitations in sensor stability and anti-interference ability, their application in complex soil matrix is still not ideal. Overall, existing soil pollution monitoring technologies face three major challenges: traditional laboratory methods are inefficient, requiring multiple manual operations from sampling, pretreatment to analysis, making it difficult to meet the emergency response needs of sudden pollution incidents; field rapid detection devices have limited sensitivity, and their ability to identify low-concentration pollutants (such as μg / kg heavy metals) is limited, which can lead to missed detection and misjudgment; the fusion capability of multi-source data is weak, and remote sensing inversion, ground sensing, and laboratory data lack a unified scale system, which restricts the accuracy of pollution migration model construction. For example, in a chemical site remediation project, traditional grid sampling requires the deployment of hundreds of points, and it takes three months to complete the preliminary assessment. However, the pollution plume has already spread to the downstream water source during this period, highlighting the passive situation caused by the challenges.

[0026] The embodiment of the present application provides a power transmission and transformation project soil pollutant monitoring method, it is necessary to point out that the steps shown in the flowchart of the drawing can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0027] Please refer to Figure 1 , Figure 1 The flowchart of the power transmission and transformation project soil pollutant monitoring method provided by the embodiment of the present application is shown in Figure 1, and the flowchart comprises the following steps: Figure 1

[0028] Step S100, collecting hyperspectral image data in the power transmission and transformation project area.

[0029] The hyperspectral image data contains ground object reflectivity information, which can reflect the spectral characteristics of pollutants in the soil. In the process of acquiring hyperspectral image data, a hyperspectral imager is carried on an unmanned aerial vehicle for aerial scanning. In the scanning process, the soil surface reflectivity curve is obtained by continuous spectral imaging in multiple waveband ranges. The soil surface reflectivity curve can reflect the characteristic absorption valley of pollutants in the visible-near infrared waveband. Combined with the second derivative spectrum technology, the weak characteristic signal is amplified, and the amplified weak signal is the unique spectral absorption characteristic of different pollutants such as heavy metals and oil stains.

[0030] Step S300, processing the hyperspectral image data by using a multi-stage spectral transformation mechanism to obtain a characteristic waveband representing the content of the pollutant.

[0031] The original hyperspectral image data has noise and redundancy, and the spectral transformation is a second derivative transformation process of the hyperspectral image data, which highlights and enhances the spectral curve change of the pollutant characteristics. The multi-stage spectral transformation mechanism includes a first-stage spectral transformation mechanism for eliminating noise, a second-stage spectral transformation mechanism for enhancing the difference of the pollutant characteristic waveband, and a third-stage spectral transformation mechanism for determining the multi-scale spectral characteristics of the pollutant. The first-stage processing adopts a wavelet packet decomposition and reconstruction algorithm to separate the instrument noise and environmental interference in the frequency domain space. By establishing a noise feature library, the best denoising basis function is dynamically matched to retain the effective spectral information of the pollutant. The second-stage processing develops a spectral differential enhancement operator, and adopts a fractional derivative algorithm to amplify the detail difference of the reflectivity curve of the characteristic waveband. For different types of pollutants (such as oil and heavy metals), the first or second order of differentiation is adaptively selected to break through the sensitivity limit of the traditional integer order derivative. The third-stage processing constructs a pyramid analysis model, and extracts the cross-scale spectral characteristics of the pollutant particles through Gaussian scale space transformation. Combined with morphological opening and closing operation, the spectral response mode of the pollutant aggregation area and the dispersed distribution area is separated. ​

[0032] The recursive feature elimination method is used to screen the band combination that is significantly correlated with the target pollutant concentration, and the band index is used to construct the quantitative pollution degree. In the process of quantifying the pollution degree, first, the hyperspectral image data is taken as the initial feature set, the pre-set regression model is trained, and the mapping relationship between spectral reflectance and pollutant concentration is determined. Based on the importance weight of different bands (according to the band and the corresponding pollutant, the weight is set), the bands with low importance ranking are removed, and the characteristic bands are screened out. The characteristic band is the band that is significantly correlated with the target pollutant concentration, for example, the characteristic band of Pb is 620-650 nm, and then the band of 620-650 nm is selected as the characteristic band of Pb. The band index represents the index of quantifying the pollution degree, and is based on the physical correlation between the optical reflection characteristics and the chemical properties of the pollutant, for example: heavy metals cause the shift of specific absorption peaks.

[0033] Step S500, input the characteristic band into the pre-set spectral inversion model to generate a concentration spatial distribution map of soil pollutants.

[0034] The spectral inversion model is based on a machine learning algorithm or a physical model (such as a radiation transfer model), and determines the mapping relationship between spectral features and concentration through training samples. The concentration spatial distribution map includes initial distribution data of soil pollutants and real-time distribution data of soil pollutants in a diffusion state with groundwater at any time. The initial distribution data is calculated by the spectral inversion model to calculate the pollutant concentration at the monitoring time, and then a static distribution map is generated; the real-time diffusion data is combined with the groundwater flow direction (obtained by a hydrological model) and the time series hyperspectral image data to dynamically update the pollutant diffusion range data.

[0035] Step S700, according to the concentration spatial distribution map, a soil and groundwater diffusion model is constructed, and based on the soil and groundwater diffusion model, a migration path identification map of soil pollutants and a groundwater pollution risk area identification map are generated.

[0036] According to the initial distribution data and the real-time distribution data, a soil and groundwater diffusion model is constructed to generate a soil pollutant migration path identification map and a groundwater pollution risk area identification map. The diffusion model is based on the convection-dispersion equation. By inputting soil parameters, groundwater parameters and pollutant parameters, numerical simulation is performed to calculate the migration path of the pollutant in the soil and groundwater, and then combined with the risk assessment standard, the risk area is divided, and then the corresponding migration path identification map and groundwater pollution risk area identification map are generated. The embodiments of the application realize the rapid scanning of the radius range of power transmission and transformation equipment by the mobile hyperspectral inspection device, and are particularly suitable for power transmission corridors in complex terrain mountainous areas. Spectral transformation processing reduces the detection limit of heavy metals and improves the identification accuracy of oil pollutants. By fusing soil permeability coefficient and groundwater flow field data, the future pollution plume diffusion range can be predicted, and the timeliness is improved compared with the static evaluation model. The pollution barrier trench position is accurately determined by the migration path identification map, so that the soil repair work quantity is reduced.

[0037] In some embodiments, the hyperspectral image data is collected by a plurality of monitoring points preset in the power transmission and transformation project area; each monitoring point is provided with a differentiated marker pollutant, and each marker pollutant has a sensitive feature in a specific wave band; the sensitive feature is that, within a preset time period, the pollutant spectral reflectance curve shows a regular change with the increase of the concentration.

[0038] When performing pollutant monitoring on any power transmission and transformation project area, first, monitoring points are set according to the main power transmission and transformation equipment in the power transmission and transformation project area. The main power transmission and transformation equipment includes substation, switch station, series compensation station and tower of power transmission line and other project equipment. The monitoring points are arranged in a ring around the main power transmission and transformation equipment, or can be arranged by grid method and zoning method to cover the surrounding sensitive area of the main power transmission and transformation equipment.

[0039] Among them, the monitoring points contain marker pollutants, the types of marker pollutants at each monitoring point are different, and the marker pollutants have sensitive features in specific wave bands; the sensitive feature is the pollutant concentration enhancement data of the dynamic pollutant hotspot area that the pollutant spectral reflectance curve in the power transmission and transformation project area has diffusion trend and migration trend within a preset monitoring time period. There can be multiple pollutants in the power transmission and transformation project area. By setting marker pollutants at different monitoring points, high-spectral image data strongly related to the pollutant can be collected. For typical pollutants of power transmission and transformation projects (transformer oil, sulfur hexafluoride decomposition product, heavy metal, etc.), a spectral reflectance benchmark curve database with engineering characteristics is established. By setting differentiated marker pollutants, a multi-dimensional monitoring index system is formed, thereby solving the misjudgment problem caused by the confusion of pollutant characteristics.

[0040] The embodiment of the application adopts a time domain convolutional neural network (TCN) to analyze the morphological evolution of the spectral curve in a continuous monitoring period, and capture the gradient change characteristics of the reflectivity of the characteristic waveband. Through a dynamic threshold adjustment mechanism, the waveband shift phenomenon representing the migration of pollutants is identified. A pollutant diffusion path network is constructed based on graph theory, the concentration change of the marker pollutant at each monitoring point is mapped to the weight change of the network node, and the spatial boundary of the concentration enhancement region is determined through the connection strength calculation between nodes.

[0041] The differential marker sets the identity label of the pollution source, and can accurately identify the responsible source in a mixed pollution scene by tracking the characteristic waveband, for example, to distinguish between transformer oil leakage and battery acid leakage. The dynamic sensitive feature identification technology can capture the weak spectral changes in the early stage of pollution diffusion, and compared with the traditional fixed threshold monitoring method, the pollution event discovery time window is advanced by several monitoring periods. Through the spatial distribution characteristic analysis of the marker pollutant, the unmanned aerial vehicle inspection path is intelligently planned, so that the monitoring frequency of the key area is improved without increasing the equipment load.

[0042] In some embodiments, the multi-temporal hyperspectral image data and the ground in-situ data are spatio-temporally aligned to generate a pollutant reference concentration matrix; the pollutant reference concentration matrix includes four-tuple data of position, time, spectrum and concentration; a pollutant diffusion model is constructed based on the pollutant reference concentration matrix and a groundwater diffusion model, and a time-series spectral feature is extracted based on the pollutant diffusion model; the time-series spectral feature is used to represent the concentration change and spectral dynamic change of the pollutant; and a pollutant concentration enhancement region is graded and calibrated according to the time-series spectral feature and a preset concentration change rate threshold.

[0043] Specifically, multi-temporal hyperspectral images and ground in-situ data are collected and spatio-temporally aligned to generate a pollutant reference concentration matrix; the pollutant reference concentration matrix is used to represent four-tuple data of the initial position, time, spectrum and concentration of the pollutant in the power transmission and transformation project area; the multi-temporal hyperspectral images are data collected by unmanned aerial vehicle / satellite hyperspectral sensors at different time points, and the multi-temporal hyperspectral images cover the spectral reflectance information of the power transmission and transformation project area; the ground in-situ data are actual pollutant concentration data of each point obtained by soil sampling on the same date at the corresponding time phase. The spatio-temporal alignment is to match the pixel of the hyperspectral image with the position of the ground sampling point through GPS coordinates, and synchronize the time stamp. The pollutant reference concentration matrix is to integrate the aligned multi-temporal data into a three-dimensional matrix, and each element stores the correlation value of the hyperspectral reflectance-actual concentration at the corresponding position and time. Dynamic calibration is performed in this process, which means that the matrix is automatically updated with the addition of new time phase data.

[0044] According to the pollutant benchmark concentration matrix, a pollutant diffusion model of the power transmission and transformation project area is constructed, and time sequence spectral characteristics are determined. The pollutant diffusion model is composed of a groundwater diffusion model of the power transmission and transformation project area combined with the pollutant benchmark concentration matrix, and the time sequence spectral characteristics include a concentration change rate of the pollutant and spectral dynamic change characteristics. The pollutant migration is simulated under the convection-dispersion equation by taking the benchmark concentration matrix as input and combining hydrogeological parameters to form the pollutant diffusion model. The concentration change rate is the concentration increment of each position and each phase in the benchmark matrix. The spectral dynamic change characteristics refer to the extraction of spectral reflectance changes of the same spatial position and different time points in the benchmark matrix, the calculation of the quantitative values of the change trends represented by specific waveband combinations, and the determination of the characteristics.

[0045] According to the time sequence spectral characteristics, the pollutant concentration enhancement area corresponding to each marker pollutant in the power transmission and transformation project area is graded and calibrated under a preset concentration change rate threshold. The concentration change rate threshold is set according to the risk acceptance level of the power transmission and transformation project, such as specific values of high, medium and low threshold levels. Based on the spectral dynamic change separation model, the pollutant concentration change and soil background interference (humidity, organic matter change) are signal decoupled by independent component analysis (ICA), and only the time sequence characteristics reflecting the pollution diffusion process are extracted. Based on the concentration grading system of the migration trend, the core pollution area, the diffusion influence area and the potential risk area are dynamically divided according to the concentration gradient change rate in the diffusion direction of the pollution plume, and a hierarchical management atlas with spatial topological relationship is formed.

[0046] The embodiments of the present application realize the dual functions of reverse deduction and forward prediction of the pollutant diffusion path through the spatio-temporal fusion of multi-temporal data, and can accurately restore the dynamic evolution process after the pollution event occurs. The time sequence characteristic decoupling technology effectively removes the environmental background noise, so that the signal-to-noise ratio of the weak pollution signal is improved to the engineering recognizable level, and is especially suitable for continuous monitoring in the scene of severe soil humidity change in the rainy season. Based on the dynamic calibration system of the concentration gradient, a differentiated emergency response strategy is automatically generated: physical barriers are implemented in the core area, chemical remediation is started in the diffusion area, and a three-level prevention and control network of monitoring and early warning is deployed in the risk area.

[0047] In some embodiments, the hyperspectral image data is processed by a recursive feature elimination method to obtain a characteristic waveband representing the pollutant content; based on the characteristic waveband, the pollutant concentration level of each monitoring point is judged by adaptive threshold mapping, and a pollutant distribution map is generated, wherein the adaptive threshold mapping is used to associate the pollutant type and the characteristic waveband threshold, and the width of the characteristic waveband is used to represent the pollutant concentration.

[0048] The hyperspectral image data is subjected to adaptive threshold mapping through a multi-stage spectral transformation mechanism to generate a pollutant distribution map based on concentration labels of monitoring points; wherein the adaptive threshold mapping is a correlated mapping of pollutant types and threshold values of characteristic wavebands, and the width of the characteristic waveband is the pollutant concentration.

[0049] Through a hierarchical progressive processing mechanism, the characteristic spectrum of the pollutant submerged in the environmental background is effectively extracted, and the early identification of trace leakage of aging equipment is particularly suitable. Through multi-scale feature analysis technology, oil film pollution and heavy metal particle pollution can be identified simultaneously, solving the misjudgment problem caused by spectral mixing effect. The adaptive threshold mapping mechanism can automatically match the best processing parameters according to different power transmission and transformation engineering scenes (such as converter stations / switch stations), reducing the dependence on expert manual parameter adjustment.

[0050] In the specific implementation process, the pollutant concentration is determined by spectral characteristics, and a pollutant distribution map is generated. First, for hyperspectral image data, a plurality of different types of representative hyperspectral image data samples are obtained from different monitoring points, and then a multi-stage spectral transformation mechanism is used to measure the spectral data of the hyperspectral image data samples to obtain characteristic waveband data as an independent variable, and determine the pollutant content as a dependent variable. The collected spectral data and pollutant element content data are cleaned to remove outliers and error data, and are standardized to make the data comparable. An effective pollutant content prediction model is established using spectral characteristics to generate a pollutant distribution map.

[0051] In some embodiments, an adversarial hyperspectral sample simulating the interference environment of the power transmission and transformation project is constructed; based on the adversarial hyperspectral sample, an abnormal disturbance is identified in the process of adaptive threshold mapping; and based on the abnormal disturbance, the pollutant concentration of the characteristic waveband is corrected.

[0052] The adversarial hyperspectral sample is used to simulate the interference environment of the power transmission and transformation project area. Based on a preset typical interference spectral feature library of power transmission and transformation (including electromagnetic pulse interference, device thermal radiation noise, vegetation seasonal change interference, etc.), a physically interpretable adversarial hyperspectral sample set is constructed through a generative adversarial network to form a spectral interference dictionary covering all working conditions. In the adaptive threshold mapping, the adversarial hyperspectral sample is migrated to the hyperspectral image data to determine whether there is an abnormal disturbance. Based on the residual attention mechanism feature migration algorithm, the interference feature space of the adversarial hyperspectral sample is mapped to the actual monitoring data domain, and the abnormal disturbance component is identified through the channel attention weight matrix. According to the abnormal disturbance, the pollutant concentration value belonging to the characteristic waveband in different monitoring points is determined. A dual-channel parallel processing architecture is constructed: the main channel executes the concentration mapping process, and the auxiliary channel dynamically corrects the characteristic waveband weight coefficient output by the main channel by comparing the disturbance mode of the adversarial hyperspectral sample.

[0053] The application embodiment solves the problem of spectrum distortion in a strong electromagnetic environment of a power transmission and transformation project, ensures the effectiveness of the monitoring data of the device in the time domain, and solves the pain point of strong coupling between the monitoring data and the start-stop state of the device in the traditional method. Through the dynamic expansion mechanism of the adversarial hyperspectral sample library, the system has self-adaptive ability to cope with special scenes such as seasonal vegetation coverage change and metal dust interference during equipment maintenance. Through abnormal disturbance separation, real pollution caused by device leakage and transient interference caused by construction activities can be effectively distinguished to provide technical evidence for accident responsibility identification.

[0054] In some embodiments, the characteristic waveband is input into a spectrum inversion model, including: determining a dynamic sensitive waveband according to the pollutant absorption peak matched with the characteristic waveband, the dynamic sensitive waveband being used to represent a spectrum waveband with significant sensitivity to changes in pollutant concentration or migration process; processing the dynamic sensitive waveband through the spectrum inversion model to generate a concentration spatial distribution map of soil pollutants, the concentration spatial distribution map including initial distribution data of soil pollutants and real-time distribution data of soil pollutants in a diffusion state with groundwater at any time.

[0055] The characteristic waveband matches the pollutant absorption peak of the corresponding waveband, and the dynamic sensitive waveband is determined; the dynamic sensitive waveband is used to represent a spectrum waveband with significant sensitivity to changes in pollutant concentration or migration process over time or environmental conditions; through the establishment of a dynamic tracking algorithm of pollutant spectrum fingerprint, the absorption valley shape characteristics (such as absorption valley width, symmetry, red shift amount) of the target pollutant in the characteristic waveband are matched through a sliding window, the deformation law of the absorption peak affected by environmental factors is identified, and through the development of a waveband optimization algorithm based on migration trend, the sensitive waveband combination weight is dynamically adjusted according to the spectral response gradient change in the diffusion direction of the pollutant, and a waveband set suitable for different migration stages is formed.

[0056] According to the dynamic sensitive waveband, a mixed driving inversion model is constructed to generate a migration risk value based on the concentration of the pollutant; wherein the migration risk value is determined based on the fusion of spectral features and simulated diffusion features. The mixed driving spectrum inversion model is realized through the fusion of data driving (spectral features) and physical driving (diffusion model). The data driving is based on the reflectivity data of the input dynamic sensitive waveband to invert the current pollutant concentration. The physical driving is to input hydrogeological parameters and historical concentration data to simulate the future pollution migration trend through the advection-dispersion equation (ADE), and then determine.

[0057] By constructing a neural network architecture under the constraint of a physical equation, the fluid mechanics diffusion equation is embedded in the network hidden layer, and the spatio-temporal coupling expression of pollution risk is realized through the tensor fusion of spectral features and migration features. The current concentration of the spectrum inversion and the migration rate, direction and other features of the diffusion model are fused to determine the migration risk value.

[0058] The embodiment of the application fuses physical mechanism spectrum inversion, breaks through the overfitting limitation of traditional data-driven models, and realizes millimeter-level spatial resolution of pollution migration path under complex geological conditions. The sensitive band evolution mechanism makes the model adapt to different diffusion stages (penetration period / stable period / acceleration period), accurately capturing the pollution plume flow forward motion trajectory. The spatiotemporal coupling expression of the risk value generates an operable prevention and control heat map, guiding the timing of barrier engineering implementation and the allocation of remediation resources.

[0059] In some embodiments, the concentration spatial distribution map includes a geographic elevation display map based on the power transmission and transformation project area; the geographic elevation display map is constructed based on the fusion of dynamic environmental parameters and ground in-situ monitoring data; based on the geographic elevation display map and the migration risk value, a migration path prediction map of soil pollutants is generated, the migration path prediction map being used to represent the migration trend of the pollutants; according to the migration path prediction map and the migration risk value, a migration path identification map of soil pollutants is generated.

[0060] The concentration spatial distribution map includes a geographic elevation display map based on the power transmission and transformation project area. The geographic elevation display map is based on dynamic environmental parameters and ground in-situ monitoring data, and constitutes a migration path prediction map of pollutants. The migration path prediction map constitutes a pollutant concentration spatial dynamic evolution parameter based on concentration prediction under the migration risk value. Based on the deep coupling algorithm of terrain elevation data and pollutant parameters, the spatial distribution function of gravity potential and osmotic pressure in the diffusion model is automatically corrected through slope and slope direction analysis of the digital elevation model (DEM), solving the error accumulation problem of terrain factor simplification in traditional two-dimensional models. The spatiotemporal evolution process of pollution diffusion is simulated by using the particle system, the migration risk value is mapped to the particle emission rate, motion trajectory and attenuation coefficient, and the visualization deduction of the pollution diffusion front motion trend is realized through the particle behavior rules constrained by fluid mechanics (such as Brownian motion superimposed on convection vector). An adaptive interpolation model of dynamic environmental parameters (wind speed, humidity) and ground monitoring data is constructed, and high-resolution environmental field data is generated by using the Kriging spatial interpolation algorithm to provide physical driving boundary conditions for the migration path prediction.

[0061] The embodiment of the application realizes the synchronous deduction of the multi-medium diffusion process of underground infiltration, surface runoff and atmospheric deposition through the deep coupling of elevation data and fluid parameters, accurately identifies the hidden migration path in complex terrains such as mountain substations, and supports the time axis sliding control of the pollution diffusion process. The dynamic evolution parameter can simulate the inhibition effect of different disposal schemes (such as excavation barrier, chemical neutralization) on the pollution front motion, and provide a digital test field for emergency plan comparison and selection. The three-dimensional visualization deduction system breaks down the barriers between environmental monitoring and civil engineering, and the output results can directly guide the design of engineering details such as the construction angle of the cutoff wall and the addition point of the remediation agent.

[0062] In some embodiments, according to the concentration spatial distribution map, the soil and groundwater diffusion model is constructed by: loading the concentration spatial distribution map into a preset physical diffusion model to generate a pollutant diffusion matrix based on three-dimensional migration data; the pollutant diffusion matrix includes a soil invasion diffusion matrix and a groundwater high-speed dispersion diffusion matrix; determining the spatio-temporal state characteristics of the pollutant based on the pollutant diffusion matrix, the spatio-temporal state characteristics being diffusion state data of the pollutant in the time dimension and the space dimension; and constructing the soil and groundwater diffusion model based on the spatio-temporal state characteristics.

[0063] In some embodiments, according to the concentration spatial distribution map, the soil and groundwater diffusion model is constructed by: loading the concentration spatial distribution map into a preset physical diffusion model to generate a pollutant diffusion matrix based on three-dimensional migration data; the pollutant diffusion matrix includes a soil invasion diffusion matrix and a groundwater high-speed dispersion diffusion matrix; determining the spatio-temporal state characteristics of the pollutant based on the pollutant diffusion matrix, the spatio-temporal state characteristics being diffusion state data of the pollutant in the time dimension and the space dimension; and constructing the soil and groundwater diffusion model based on the spatio-temporal state characteristics.

[0064] The embodiments of the present application can accurately distinguish between vertical migration dominated by capillary penetration and horizontal diffusion driven by hydraulic gradient through independent construction and interface coupling of the soil and groundwater diffusion model, and solve the prediction distortion problem of the traditional method of blurring the cross-medium process.

[0065] The spatio-temporal feature extraction technology in the embodiments of the present application can identify abnormal diffusion signals of hidden channels such as bedrock fissures and abandoned pipe corridors, and early warning of pollution eddy current risk in non-uniform media. Through the difference output of the double-medium model, a collaborative remediation scheme of soil gas phase extraction and groundwater permeable reaction wall is formed to avoid the pollution back-seepage between media caused by single remediation technology.

[0066] In some embodiments, based on the soil and groundwater diffusion model, a migration path identification map of soil pollutants and an underground pollution risk area identification map are generated, including: generating three-dimensional migration data based on the soil and groundwater diffusion model; determining the diffusion weight of different migration diffusion coordinate points on the migration trajectory according to the three-dimensional migration data, and determining the emergency control risk value based on the diffusion weight; generating a migration path identification map according to the emergency control risk value; calculating the vulnerability of the power transmission project area according to the migration path identification map to obtain the vulnerability value of different areas, and generating an underground pollution risk area identification map based on the vulnerability value and the emergency control risk value.

[0067] According to the three-dimensional migration data, the diffusion weight of different migration diffusion coordinate points on the migration trajectory is determined, and the emergency control risk value based on the diffusion weight is determined. A three-dimensional trajectory energy field model based on migration potential energy is developed, a weight calculation function coupled with multiple factors is constructed through the diffusion direction of the pollutants, the medium adsorption coefficient and the terrain potential energy gradient, and the potential contribution of each migration path to the ecological system is quantified. According to the emergency control risk value, a migration path identification map corresponding to the migration path is generated; a fuzzy membership function of risk value-control level is established, the continuous risk value is discretized into a three-level control system of emergency disposal area, monitoring and early warning area and normal observation area, and the visual spatial mapping of risk decision is realized. According to the migration path identification map, the vulnerability of the power transmission project area is calculated, and the migration path identification map is formed according to the vulnerability value of different areas. The application designs a vulnerability evaluation index system including soil ecological sensitivity, groundwater use function and surface vegetation type, generates a spatial vulnerability gradient map through the analytic hierarchy process, and forms a prevention and control priority matrix by superimposing the risk identification map.

[0068] Through migration trajectory energy field analysis, the application embodiments automatically identify the minimum resistance channel of pollution diffusion, guide the layout of engineering facilities such as interception wall and monitoring well along the optimal prevention and control axis, and improve the interception efficiency. The double-dimensional evaluation system simultaneously considers the sensitivity of the pollution source and the receptor, avoids excessive treatment of high-risk low-vulnerability areas in traditional methods, and realizes precise placement of repair resources. The three-level control system forms a red-orange-yellow early warning mechanism, supports the automatic triggering of differentiated emergency processes for different risk levels, and significantly shortens the emergency response decision chain.

[0069] Correspondingly, please refer to Figure 2 , Figure 2 A schematic diagram of the monitoring system of soil pollutants in power transmission projects provided by the application embodiments is as follows: Figure 2As shown, the soil pollutant monitoring system of the power transmission and transformation project comprises: a collection module configured to collect hyperspectral image data in a power transmission and transformation project area; a transformation module configured to perform spectral transformation processing on the hyperspectral image data to obtain a characteristic band representing pollutant content; a generation module configured to input the characteristic band into a spectral inversion model to generate a concentration spatial distribution map of soil pollutants; and an identification module configured to construct a soil and groundwater diffusion model according to the concentration spatial distribution map, and generate a migration path identification map of soil pollutants and an underground pollution risk area identification map based on the soil and groundwater diffusion model.

[0070] In the embodiments of the present application, the functional modules are loosely coupled through standardized data interfaces. The collection module integrates hyperspectral imaging and Beidou positioning technology, the transformation module embeds adaptive learning algorithms, the generation module carries a hybrid driven inversion engine, and the identification module runs a multi-medium diffusion model, forming a fully automatic processing chain from data collection to decision output. A computing resource allocation algorithm based on microservices is developed to dynamically allocate GPU computing power to spectral transformation (high real-time requirement) or diffusion modeling (computationally intensive) links according to task priority, achieving optimal utilization of hardware resources. A spatio-temporal unified database architecture is constructed to support multi-source data streams such as unmanned aerial vehicle aerial images, ground sensor networks, and weather monitoring stations, and to achieve near-real-time data preprocessing and feature extraction through edge computing nodes.

[0071] The present application converts laboratory-level monitoring technology into engineering equipment that can be deployed in harsh outdoor environments through deep integration of hardware, algorithms, and models, solving the contradiction between equipment portability and computing efficiency in traditional methods. From unmanned aerial vehicle autonomous inspection, edge real-time processing to cloud intelligent decision-making, the chain collaboration realizes pollution event discovery, assessment, and early warning; the standardized data interface design is compatible with mainstream GIS platforms and power operation and maintenance systems, and the output results can be directly imported into the power transmission and transformation asset management system to trigger maintenance work orders.

[0072] Further function descriptions of the above-mentioned modules and units are the same as those of the corresponding embodiments described above, and will not be repeated here.

[0073] The soil pollutant monitoring system of the power transmission and transformation project in the embodiments is presented in the form of functional units, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0074] Please refer to Figure 3 , Figure 3 A structural schematic diagram of a computer device provided by the embodiments of the present application is shown in Figure 3As shown, the computer device includes one or more processors 10, memory 20, and interfaces 30 for the various components to communicate with one another. The various components communicate through the use of the various buses, and can be mounted on a common motherboard or in other manners as appropriate. The processor 10 can process instructions for execution within the computer device, including instructions stored in the memory 20 or elsewhere by a storage device, such as a disk storage or an optical storage. In some optional embodiments, multiple processors and / or multiple buses can be employed as appropriate, as will be appreciated by those of ordinary skill in the art, especially in light of the following disclosure. Also, various elements of the computer device can be located on a single circuit board, or can be distributed among different circuit boards in a distributed, or modular, fashion, as is appropriate for a given implementation. Figure 3 The processor 10 is taken as an example in the embodiments.

[0075] The processor 10 can be a central processing unit, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic device, a general array logic, or any combination thereof.

[0076] The memory 20 stores instructions that are executable by the at least one processor 10, so as to enable the at least one processor 10 to perform the method shown in the above embodiments.

[0077] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system, application programs required by at least one function, and the like. The data storage area can store data created according to the use of the computer device, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage device. In some optional embodiments, the memory 20 can optionally include a memory that is remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0078] The memory 20 can include a volatile memory, such as a random access memory, and can also include a non-volatile memory, such as a flash memory, a hard disk, or a solid state disk. The memory 20 can further include a combination of the above-mentioned kinds of memories.

[0079] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0080] The embodiments of the present application further provide a computer readable storage medium, and the method according to the embodiments of the present application can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer code stored in a remote storage medium or a non-transitory machine readable storage medium and stored in a local storage medium to be downloaded through a network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special hardware. The storage medium can be a disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned memories. It can be understood that the computer, the processor, the microprocessor controller, or the programmable hardware includes a storage component that can store or receive software or computer code, and when the software or computer code is accessed and executed by the computer, the processor, or the hardware, the method shown in the above embodiments is implemented.

[0081] The embodiments of the present application provide a computer program product, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to perform the method of any of the embodiments of the present application.

[0082] The system or module illustrated in the above embodiments can be implemented by a computer chip or entity, or by a product having certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0083] For the convenience of description, the above apparatus is described as various units in terms of functions to be described respectively. Of course, the functions of the units can be implemented in the same or multiple software and / or hardware in the implementation of the present application.

[0084] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0085] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart or flowsheet block or blocks. Figure 1 The flowchart and / or block diagram in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks.

[0086] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagram in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks.

[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagram in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. It should be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, implement the functions specified in the flowchart and / or block diagram block or blocks. Figure 1 These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart and / or block diagram block or blocks.

[0088] It should be noted that the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an overly literal or overly formal sense unless expressly so defined herein.

[0089] The various embodiments in the specification are described progressively, and the same or similar parts between the embodiments can be mutually referred to. Each embodiment focuses on the differences from other embodiments.

[0090] The above merely provides an example of the present application, but is not intended to limit the present application. The present application can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principle of the present application shall be included in the scope of claims of the present application.

[0091] Although the embodiments of the present application are described with reference to the drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes shall fall within the scope defined by the appended claims.

Claims

1. A method for monitoring soil pollutants in power transmission and transformation projects, characterized in that, The method includes: Collect hyperspectral image data within the power transmission and transformation project area; The hyperspectral image data is processed using a multi-level spectral transformation mechanism to obtain characteristic bands representing pollutant content. The multi-level spectral transformation mechanism includes wavelet packet decomposition and reconstruction algorithm, fractional derivative algorithm, and Gaussian scale space transformation. The characteristic bands are input into a preset spectral inversion model to generate a spatial distribution map of soil pollutant concentrations. This includes: determining dynamic sensitive bands based on the pollutant absorption peaks matched to the characteristic bands, wherein the dynamic sensitive bands are spectral bands that are significantly sensitive to changes in pollutant concentrations or migration processes; and processing the dynamic sensitive bands through the spectral inversion model to generate a spatial distribution map of soil pollutant concentrations, wherein the spatial distribution map includes initial distribution data of soil pollutants and real-time distribution data of soil pollutants diffused with groundwater at any given time. Constructing a soil and groundwater diffusion model based on the concentration spatial distribution map includes: loading the concentration spatial distribution map into a preset physical diffusion model to generate a pollutant diffusion matrix based on three-dimensional migration data; the pollutant diffusion matrix includes a soil intrusive diffusion matrix and a groundwater high-speed dispersion diffusion matrix; determining the spatiotemporal state characteristics of pollutants based on the pollutant diffusion matrix, wherein the spatiotemporal state characteristics are the diffusion state data of pollutants in the time and spatial dimensions; and constructing a soil and groundwater diffusion model based on the spatiotemporal state characteristics. Based on the soil and groundwater diffusion model, a migration path identification map of soil pollutants and a groundwater pollution risk area identification map are generated, including: generating three-dimensional migration data based on the soil and groundwater diffusion model; determining the diffusion weight of different migration and diffusion coordinate points on the migration trajectory based on the three-dimensional migration data, and determining the emergency control risk value based on the diffusion weight; generating a migration path identification map based on the emergency control risk value; calculating the vulnerability of the power transmission and transformation project area based on the migration path identification map to obtain the vulnerability value of different areas, and generating a groundwater pollution risk area identification map based on the vulnerability value and the emergency control risk value.

2. The method according to claim 1, characterized in that, The method further includes: collecting hyperspectral image data through multiple monitoring points preset within the power transmission and transformation project area; wherein, each monitoring point is equipped with differentiated marker pollutants, and each marker pollutant has sensitive characteristics in a specific spectral band; the sensitive characteristics are the regular change patterns of the spectral reflectance curve caused by the increase of pollutant concentration.

3. The method according to claim 1, characterized in that, The method further includes: Multi-temporal hyperspectral image data and in-situ ground data are spatiotemporally aligned to generate a pollutant baseline concentration matrix; the pollutant baseline concentration matrix contains quadruple data of location, time, spectrum and concentration; Based on the pollutant baseline concentration matrix and the groundwater diffusion model, a pollutant diffusion model is constructed, and time-series spectral features are extracted based on the pollutant diffusion model; the time-series spectral features are used to characterize the concentration changes and spectral dynamic changes of pollutants. Based on the time-series spectral characteristics and the preset concentration change rate threshold, regions with increased pollutant concentrations are classified and calibrated.

4. The method according to claim 1, characterized in that, The method further includes: The hyperspectral image data is processed by a recursive feature elimination method to obtain characteristic bands representing pollutant content. Based on the characteristic bands, the pollutant concentration levels at each monitoring point are determined by adaptive threshold mapping, and a pollutant distribution map is generated. The adaptive threshold mapping is used to associate pollutant types with characteristic band thresholds, and the width of the characteristic bands is used to characterize pollutant concentrations.

5. The method according to claim 4, characterized in that, The method further includes: Constructing adversarial hyperspectral samples to simulate interference environments in power transmission and transformation projects; Based on the adversarial hyperspectral samples, anomalous perturbations are identified during the adaptive threshold mapping process; The pollutant concentration in the characteristic band is corrected based on the anomalous perturbation.

6. The method according to claim 1, characterized in that, The concentration spatial distribution map includes a geographic elevation map based on the power transmission and transformation project area; the geographic elevation map is constructed based on the fusion of dynamic environmental parameters and ground in-situ monitoring data; based on the geographic elevation map and migration risk values, a migration path prediction map of soil pollutants is generated, which is used to characterize the migration trend of pollutants. Based on the migration path prediction map and the migration risk value, a migration path identification map of soil pollutants is generated.

7. A monitoring system for soil pollutants in power transmission and transformation projects, capable of implementing the monitoring method for soil pollutants in power transmission and transformation projects as described in any one of claims 1-6, characterized in that, The system includes: The acquisition module is used to acquire hyperspectral image data within the power transmission and transformation project area; The transformation module is used to perform spectral transformation processing on the hyperspectral image data to obtain characteristic bands characterizing pollutant content; The generation module is used to input the characteristic bands into the spectral inversion model to generate a spatial distribution map of soil pollutant concentrations; The identification module is used to construct a soil and groundwater diffusion model based on the concentration spatial distribution map; and to generate a soil pollutant migration path identification map and a groundwater pollution risk area identification map based on the soil and groundwater diffusion model.

Images