A method and system for evaluating energy distribution of a pollution source by spatial gridding modeling

Abstract

The present application relates to the technical field of environmental monitoring, and proposes a pollution source energy distribution evaluation method and system based on spatial gridding modeling, which comprises the following steps: uniformly gridding and dividing a target area according to spatial boundary information to obtain a spatial grid set; extracting pollution source monitoring data of the spatial grid set and decoupling the features of the pollution source monitoring data to obtain an energy feature vector of the spatial grid set; mapping the energy feature vector and the spatial grid set to construct an initial energy distribution field; performing interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain a local deviation coefficient; performing variational assimilation correction and field superposition on the initial energy distribution field to obtain a corrected energy distribution field; performing contour line tracking and grade assignment rendering on the corrected energy distribution field to obtain a pollution source energy distribution evaluation map of the target area; and the present application can improve the efficiency of the pollution source energy distribution evaluation based on spatial gridding modeling.

Description

Technical Field

[0001] This invention relates to the field of environmental monitoring technology, and in particular to a method and system for assessing the energy distribution of pollution sources using spatial grid modeling. Background Technology

[0002] Existing pollution source energy distribution assessment technologies lack a standardized spatial gridded modeling framework, and lack a complete technical process for processing spatial boundary data of the target area. The original geographic boundary data has not undergone topological consistency repair, and operations such as curvature gradient inversion and extreme value calibration of the boundary geometric contour are missing. It is impossible to accurately determine the boundary extreme value coordinates and the rectangular outer envelope. The regional rasterization only uses simple equidistant subdivision and does not use the real boundary as a template for trimming and adaptation, making it difficult to generate a regular spatial raster set that fits the target area. As a result, the pollution source energy data lacks a stable and standardized spatial carrying base, and the matching and adaptability between the data and spatial units is extremely poor, laying the foundation for errors in subsequent energy field construction.

[0003] Traditional assessment methods fail to decouple multi-source attribute features from pollution source monitoring data, making it impossible to decompose core data such as pollution source location, emission type, and emission rate into independent feature vectors. They also lack topological cascading and ordered recombination of feature dimensions, resulting in a lack of precise mechanisms for constructing energy characterization vectors. The initial energy distribution field is generated solely through basic interpolation fitting, without interpolation residual analysis or local deviation coefficient calculation for monitoring points. Variational assimilation correction and deviation compensation processes are absent, failing to correct errors in the initial field. Furthermore, the methods lack contour tracking, grade assignment, and color rendering, leading to insufficient accuracy and poor visualization of the assessment results, ultimately hindering overall assessment efficiency and reliability. Therefore, improving the accuracy, efficiency, and visualization of pollution source energy distribution assessment has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for assessing the energy distribution of pollution sources using spatial grid modeling, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for assessing the energy distribution of pollution sources using spatial gridding modeling, comprising:

[0006] P1. Obtain the spatial boundary information of the target area, and divide the target area into uniform grids based on the spatial boundary information to obtain the spatial grid set of the target area;

[0007] P2. Extract the pollution source monitoring data of the spatial grid set, and perform feature decoupling on the pollution source monitoring data to obtain the energy characterization vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information and emission rate information.

[0008] P3. Map the energy representation vector to the spatial grid set in a spatial field to construct the initial energy distribution field of the target region;

[0009] P4. Perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficient of the monitoring points;

[0010] P5. Based on the local deviation coefficient, the initial energy distribution field is subjected to variational assimilation correction, and the corrected deviation compensation field is superimposed with the initial energy distribution field to obtain the corrected energy distribution field of the target region.

[0011] P6. Perform contour tracing on the modified energy distribution field, and assign level values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution assessment map of the target area.

[0012] In a preferred embodiment, the step of acquiring the spatial boundary information of the target region and, based on the spatial boundary information, uniformly rasterizing the target region to obtain a spatial raster set of the target region includes:

[0013] Collect the original geographic boundary data of the target area, and perform topological consistency repair on the original geographic boundary data to obtain the repaired boundary data of the target area;

[0014] Based on the repaired boundary data, the boundary geometric contour of the target region is subjected to extreme value analysis and calibration to obtain the boundary extreme value coordinates of the target region.

[0015] The boundary extreme value coordinates are subjected to an outer enclosure configuration to obtain the rectangular outer envelope surface of the target region;

[0016] The rectangular outer envelope is divided into equidistant regular subdivisions to obtain the initial grid array of the target region;

[0017] Using the repaired boundary data as a clipping template, the initial raster array is clipped, and the raster elements located inside the repaired boundary data after clipping are taken as the spatial raster set of the target region.

[0018] In a preferred embodiment, the step of performing extreme value analysis and calibration on the boundary geometric contour of the target region based on the repaired boundary data to obtain the boundary extreme value coordinates of the target region includes:

[0019] The repaired boundary data is reconstructed using vector topology to obtain the boundary geometric contour of the target region;

[0020] Traverse the contour nodes of the boundary geometric contour line and perform curvature gradient inversion on the contour nodes to obtain the node curvature extreme value distribution of the boundary geometric contour line.

[0021] Ridge connectivity fitting is performed on the node curvature extremum distribution to obtain the curvature ridge of the node curvature extremum distribution;

[0022] Projecting the curvature ridge line onto the spatial reference of the repair boundary data yields the set of ridge line intersection points of the curvature ridge line;

[0023] Iterative convergence localization is performed on the set of ridge intersection points to obtain the boundary extreme coordinates of the target region.

[0024] In a preferred embodiment, the step of extracting pollution source monitoring data from the spatial grid set and performing feature decoupling on the pollution source monitoring data to obtain the energy representation vector of the spatial grid set, wherein the pollution source monitoring data includes pollution source location information, emission type information, and emission rate information, including:

[0025] Extract pollution source monitoring data from the spatial grid set, wherein the pollution source monitoring data includes pollution source location information, emission type information, and emission rate information;

[0026] Multi-source attribute analysis is performed on the pollution source monitoring data to obtain the location feature vector, type feature vector, and rate feature vector of the pollution source monitoring data.

[0027] The location feature vector, the type feature vector, and the rate feature vector are topologically concatenated according to their feature dimensions to obtain the fusion feature matrix of the pollution source monitoring data.

[0028] The fused feature matrix is ​​weighted and encoded, and the encoded energy feature tensor is sequentially reorganized according to the grid spatial order of the spatial grid set to obtain the energy representation vector of the spatial grid set.

[0029] In a preferred embodiment, the step of spatially mapping the energy representation vector to the spatial grid set to construct the initial energy distribution field of the target region includes:

[0030] The spatial grid set is coupled with the energy representation vector through global matching to obtain the grid energy attachment pairs of the spatial grid set;

[0031] The grid energy attachment pairs are discretized and arranged in the field to obtain the energy field scatter cloud of the grid energy attachment pairs;

[0032] The energy field scatter cloud is continuously interpolated and fitted to obtain the continuous energy field base surface of the energy field scatter cloud;

[0033] Based on the continuous energy field datum, energy shaping quantization is performed on the grid nodes of the spatial grid set to obtain the grid node energy values ​​of the spatial grid set;

[0034] The energy values ​​of the grid nodes are arrayed and arranged, and the arranged grid energy array is reconstructed in the whole domain to obtain the initial energy distribution field of the target area.

[0035] In a preferred embodiment, the step of performing interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficients of the monitoring points includes:

[0036] Spatial residual spectrum analysis is performed on the monitoring points in the initial energy distribution field to obtain the residual energy spectrum of the monitoring points;

[0037] The residual energy values ​​in the residual energy spectrum are reduced by energy mean to construct the normalized bias field of the residual energy spectrum;

[0038] The effective deviation field of the normalized deviation field is obtained by removing the extreme energy ridges in the normalized deviation field.

[0039] The effective deviation field is refined by condensing deviation characteristics, and the monitoring point is used as the index reference to shape the local coefficients of the refined deviation field to obtain the local deviation coefficients of the monitoring point.

[0040] In a preferred embodiment, the step of performing energy mean reduction on the residual energy values ​​in the residual energy spectrum to construct the normalized bias field of the residual energy spectrum includes:

[0041] The residual energy of the residual spectrum nodes in the residual energy spectrum is interpreted to obtain the residual energy value of the residual spectrum node;

[0042] The residual energy value is aggregated in the neighborhood to obtain the neighborhood average residual energy of the residual spectrum node;

[0043] The residual energy value and the neighborhood average residual energy are correlated to construct the nodal reduction coefficients of the residual energy spectrum. The calculation formula for the nodal reduction coefficients is as follows:

[0044] ;

[0045] in, Indicates the first The nodal reduction coefficients of the residual spectrum nodes. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The neighbor node index set of the residual spectrum nodes This represents the total number of indexes in the adjacent node index set;

[0046] Based on the node reduction coefficients, the residual energy spectrum is normalized and mapped to obtain the normalized bias field of the residual energy spectrum.

[0047] In a preferred embodiment, the step of performing variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and then superimposing the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region includes:

[0048] The initial energy distribution field is deconstructed by field gradient, and the deconstructed gradient component field is subjected to bias weighted modulation based on the local bias coefficient to obtain the bias modulated gradient field of the initial energy distribution field.

[0049] Based on the deviation modulation gradient field, variational iterative derivation is performed on the deviation modulation gradient field to obtain the deviation compensation field of the initial energy distribution field;

[0050] The deviation compensation field is superimposed with the initial energy distribution field to obtain the initial correction field of the initial energy distribution field.

[0051] The initial correction field is subjected to boundary constraint regularization to obtain the boundary fidelity correction field of the initial correction field;

[0052] The boundary fidelity correction field is globally smoothed and optimized to obtain the corrected energy distribution field of the target region.

[0053] In a preferred embodiment, the step of performing contour tracing on the corrected energy distribution field and assigning grade values ​​to the traced energy distribution contours to obtain a pollution source energy distribution assessment map of the target area includes:

[0054] By performing energy contour tracing on the modified energy distribution field, the energy contour lines of the modified energy distribution field are obtained.

[0055] The energy contour lines are sorted by energy level segments to obtain a mapping table of energy contour line level segments.

[0056] The chromaticity spectrum of the level segment mapping table is assigned a chromaticity code to obtain the chromaticity coding spectrum of the level segment mapping table.

[0057] The energy contour lines and the chromaticity coding spectrum are fused and colored to obtain a pollution source energy distribution assessment map of the target area.

[0058] To address the above problems, the present invention also provides a spatial gridded modeling system for assessing the energy distribution of pollution sources, the system comprising:

[0059] The rasterization boundary segmentation module is used to acquire the spatial boundary information of the target region, and to perform uniform rasterization division of the target region based on the spatial boundary information to obtain the spatial raster set of the target region.

[0060] The pollution source feature decoupling module is used to extract pollution source monitoring data from the spatial grid set and perform feature decoupling on the pollution source monitoring data to obtain the energy characterization vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information, and emission rate information.

[0061] The energy field mapping module is used to perform spatial field mapping between the energy representation vector and the spatial grid set to construct the initial energy distribution field of the target region.

[0062] The residual deviation analysis module is used to perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficients of the monitoring points.

[0063] The variational assimilation correction module is used to perform variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and to superimpose the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region.

[0064] The contour rendering and evaluation module is used to perform contour tracing on the modified energy distribution field and to assign grade values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution evaluation map of the target area.

[0065] Compared with the prior art, the present invention has the following beneficial effects:

[0066] 1. This invention, through a standardized spatial gridding modeling process, completes the precise repair of the spatial boundary of the target area, extreme value calibration, and uniform gridding division, constructing a regular spatial grid set that fits the contour of the area. This enables the decoupling of multi-source features of pollution source monitoring data and the accurate generation of energy characterization vectors, achieving efficient spatial field mapping between energy characterization vectors and spatial grid sets. It also allows for the rapid construction of the initial energy distribution field of the target area, ensuring the standardization of energy distribution modeling and the spatial adaptability of data, and significantly improving the efficiency and basic accuracy of pollution source energy distribution modeling.

[0067] 2. This invention generates accurate local deviation coefficients by accurately performing interpolation residual analysis on the initial energy distribution field monitoring points. Through variational assimilation correction, it completes deviation compensation, boundary regularization, and global optimization of the energy field, constructing a highly accurate corrected energy distribution field. It efficiently realizes energy distribution contour tracking, level assignment, and color rendering, and quickly outputs a standardized and clear pollution source energy distribution assessment map. This comprehensively improves the accuracy, efficiency, and visualization effect of pollution source energy distribution assessment, ensuring the reliability and intuitiveness of the assessment results. Attached Figure Description

[0068] Figure 1 This is a flowchart illustrating a method for assessing the energy distribution of pollution sources using spatial gridding modeling, as provided in an embodiment of the present invention.

[0069] Figure 2 A functional block diagram of a pollution source energy distribution assessment system based on spatial grid modeling, provided in an embodiment of the present invention;

[0070] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0071] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0072] This application provides a method for assessing the energy distribution of pollution sources using spatial grid modeling. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for assessing the energy distribution of pollution sources using spatial grid modeling can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0073] Reference Figure 1 The diagram shown is a flowchart illustrating a method for assessing the energy distribution of pollution sources using spatial grid modeling, according to an embodiment of the present invention. In this embodiment, the method for assessing the energy distribution of pollution sources using spatial grid modeling includes:

[0074] P1. Obtain the spatial boundary information of the target area, and divide the target area into uniform grids based on the spatial boundary information to obtain the spatial grid set of the target area;

[0075] In this embodiment of the invention, the step of obtaining spatial boundary information of the target region and, based on the spatial boundary information, uniformly rasterizing the target region to obtain a spatial raster set of the target region includes:

[0076] Collect the original geographic boundary data of the target area, and perform topological consistency repair on the original geographic boundary data to obtain the repaired boundary data of the target area;

[0077] Based on the repaired boundary data, the boundary geometric contour of the target region is subjected to extreme value analysis and calibration to obtain the boundary extreme value coordinates of the target region.

[0078] The boundary extreme value coordinates are subjected to an outer enclosure configuration to obtain the rectangular outer envelope surface of the target region;

[0079] The rectangular outer envelope is divided into equidistant regular subdivisions to obtain the initial grid array of the target region;

[0080] Using the repaired boundary data as a clipping template, the initial raster array is clipped, and the raster elements located inside the repaired boundary data after clipping are taken as the spatial raster set of the target region.

[0081] The step of performing extreme value analysis and calibration on the boundary geometric contour of the target region based on the repaired boundary data to obtain the boundary extreme value coordinates of the target region includes:

[0082] The repaired boundary data is reconstructed using vector topology to obtain the boundary geometric contour of the target region;

[0083] Traverse the contour nodes of the boundary geometric contour line and perform curvature gradient inversion on the contour nodes to obtain the node curvature extreme value distribution of the boundary geometric contour line.

[0084] Ridge connectivity fitting is performed on the node curvature extremum distribution to obtain the curvature ridge of the node curvature extremum distribution;

[0085] Projecting the curvature ridge line onto the spatial reference of the repair boundary data yields the set of ridge line intersection points of the curvature ridge line;

[0086] Iterative convergence localization is performed on the set of ridge intersection points to obtain the boundary extreme coordinates of the target region.

[0087] Collect the original geographic boundary data corresponding to the target area, perform comprehensive topological consistency repair on the original geographic boundary data, and check and correct various problems in the original geographic boundary data one by one, such as missing nodes, misaligned lines, non-closed outlines, and conflicting topological relationships, to ensure that the spatial topological structure of the boundary data is complete and logically consistent, so that the boundary data can accurately reflect the real geographic boundary shape of the target area, and finally obtain the repaired boundary data of the target area.

[0088] Vector topology reconstruction is performed on the repaired boundary data. The connection relationship and spatial direction of the nodes and line segments inside the boundary data are reorganized strictly according to the topology rules of vector data. The originally discrete boundary line segments are integrated into continuous and closed geometric lines, completely eliminating the problems of discontinuity and misalignment of boundary lines, forming a complete and coherent boundary outline, and finally obtaining the boundary geometric outline of the target area.

[0089] The process iterates through all the contour nodes on the boundary geometric contour line one by one, and accurately calculates the curvature value of each contour node on the boundary geometric contour line. Through curvature gradient inversion, the curvature change trend and extreme value characteristics of each node are comprehensively analyzed. The curvature extreme value information of all contour nodes is statistically integrated to form a complete and continuous curvature value distribution result, and finally the node curvature extreme value distribution of the boundary geometric contour line is obtained.

[0090] Ridge connectivity fitting is performed on the distribution of node curvature extrema. Based on the distribution characteristics of node curvature extrema, the contour nodes corresponding to the curvature extrema are linearly connected in an orderly manner. The connected lines are processed by a smooth fitting method to make the connected lines continuous and smooth and completely fit the distribution direction of curvature extrema, forming a line structure that can accurately represent the core direction of contour curvature extrema, and finally obtaining the curvature ridge of node curvature extrema distribution.

[0091] The curvature ridges are projected onto the spatial reference of the repair boundary data, so that the curvature ridges and the repair boundary data adopt a completely consistent spatial coordinate reference system, accurately matching their spatial positional relationship. All nodes where the curvature ridges intersect and merge are identified one by one, and these intersection nodes are fully integrated into a unified node set, ultimately obtaining the set of ridge intersection points of the curvature ridges.

[0092] Iterative convergence localization is performed on the set of ridge intersection points. For each intersection point in the set of ridge intersection points, multiple cyclic localization calculations are performed to gradually correct the spatial position deviation of the nodes, so that the node positions continuously converge towards the accurate coordinates until the node positions reach a stable and accurate state. The extreme coordinate information of the boundary of the target area is determined, and finally the boundary extreme coordinates of the target area are obtained.

[0093] The boundary extreme value coordinates are enclosed and shaped. The horizontal maximum and minimum values ​​and the vertical maximum and minimum values ​​of the boundary extreme value coordinates are used as the core defining criteria to construct a rectangular geometric surface that can completely cover the area defined by the boundary extreme value coordinates. This ensures that the rectangular geometric surface completely covers the entire boundary range of the target area without any boundary parts being omitted, and finally the rectangular outer envelope surface of the target area is obtained.

[0094] The rectangular outer envelope is divided into equal-distance regular subdivisions. The rectangular outer envelope is uniformly divided into multiple grid combinations with identical specifications and neat arrangement at a uniform and fixed interval. The divided grids form a regular and orderly array structure that completely covers the spatial range of the entire rectangular outer envelope, and finally the initial grid array of the target area is obtained.

[0095] Using the repaired boundary data as a clipping template, the initial raster array is clipped. According to the precise outline shape of the repaired boundary data, the raster parts located outside the repaired boundary data in the initial raster array are removed one by one, while all raster elements inside the repaired boundary data are completely preserved. The preserved raster elements are then integrated in a regular and orderly manner to finally obtain the spatial raster set of the target area.

[0096] The beneficial effects are as follows: through a refined process involving topological restoration, vector topological reconstruction, curvature gradient inversion, ridge connectivity fitting, projection matching, and iterative convergence positioning of the original geographic boundary data of the target area, the boundary extreme coordinates are accurately obtained and a standardized rectangular outer envelope surface is constructed. Then, through equidistant regular subdivision and precise boundary trimming, a spatial grid set that is highly adapted to the contour of the target area is obtained. The accuracy, standardization, and completeness of the spatial grid construction are ensured throughout the process, providing a stable and reliable spatial foundation for subsequent pollution source monitoring data feature decoupling, energy field mapping, and energy distribution assessment, and comprehensively improving the basic accuracy and data adaptation effect of spatial grid modeling.

[0097] P2. Extract the pollution source monitoring data of the spatial grid set, and perform feature decoupling on the pollution source monitoring data to obtain the energy characterization vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information and emission rate information.

[0098] In this embodiment of the invention, the step of extracting pollution source monitoring data from the spatial grid set and performing feature decoupling on the pollution source monitoring data to obtain the energy representation vector of the spatial grid set, wherein the pollution source monitoring data includes pollution source location information, emission type information, and emission rate information, including:

[0099] Extract pollution source monitoring data from the spatial grid set, wherein the pollution source monitoring data includes pollution source location information, emission type information, and emission rate information;

[0100] Multi-source attribute analysis is performed on the pollution source monitoring data to obtain the location feature vector, type feature vector, and rate feature vector of the pollution source monitoring data.

[0101] The location feature vector, the type feature vector, and the rate feature vector are topologically concatenated according to their feature dimensions to obtain the fusion feature matrix of the pollution source monitoring data.

[0102] The fused feature matrix is ​​weighted and encoded, and the encoded energy feature tensor is sequentially reorganized according to the grid spatial order of the spatial grid set to obtain the energy representation vector of the spatial grid set.

[0103] The corresponding pollution source data is extracted one by one from all monitoring points covered by the spatial grid set. The spatial location information of the pollution source, the emission type information of the pollution source, and the emission rate information of the pollution source are collected completely. The data is collected according to the correspondence of the spatial grid to ensure that each monitoring data is accurately assigned to the corresponding grid without any data omission, misalignment or duplicate collection. Finally, the pollution source monitoring data of the spatial grid set is obtained.

[0104] Multi-source attribute analysis was conducted on pollution source monitoring data. Pollution source location information was decomposed into independent spatial location feature dimensions according to spatial coordinates and distribution characteristics. All location features were organized into a continuous and complete vector form according to a fixed sequence. Emission type information was decomposed into independent category attribute feature dimensions according to category attributes and emission characteristics. All type features were organized into a continuous and complete vector form according to a fixed sequence. Emission rate information was decomposed into independent emission intensity feature dimensions according to emission intensity and change characteristics. All rate features were organized into a continuous and complete vector form according to a fixed sequence. Corresponding data vectors were generated for each, and finally, the location feature vector, type feature vector, and rate feature vector of the pollution source monitoring data were obtained.

[0105] The location feature vector, type feature vector, and rate feature vector are sequentially connected and combined according to a fixed feature dimension topology relationship, keeping the dimensional structure and data information of each feature vector intact. Through orderly dimensional splicing, the three types of feature vectors are integrated into a unified matrix structure, allowing the three types of feature data to be arranged in an orderly manner and interconnected in the matrix, fully integrating all the information of the three types of features, and finally obtaining the fusion feature matrix of pollution source monitoring data.

[0106] Each set of feature data within the fused feature matrix is ​​assigned a unique feature weight. The weight allocation is completed based on the degree of influence of the feature data on the energy representation. The weighted feature data is then encoded according to a unified encoding rule, and the fused feature matrix is ​​converted into a feature data structure in tensor form. All feature information, weight information, and dimensional relationships are fully preserved, and finally, the encoded energy feature tensor is obtained.

[0107] According to the pre-determined spatial arrangement order of the spatial grid set, the energy feature tensors are sorted and integrated one by one. The energy feature tensors are recombined into a continuous and ordered vector structure according to the spatial order of the grid, so that the vector content, data arrangement and spatial grid arrangement order are completely matched and corresponded, and finally the energy representation vector of the spatial grid set is obtained.

[0108] The beneficial effects are as follows: by accurately extracting pollution source monitoring data within the spatial grid set, deeply analyzing multi-source attributes, topologically cascading and fusing multiple types of feature vectors, weighted encoding and strengthening of feature data, and sequential reorganization based on grid spatial order, all core feature information of pollution source location, emission type, and emission rate is completely preserved. This achieves accurate conversion of discrete pollution source monitoring data into standardized energy features, allowing the generated energy representation vector to form a highly compatible correlation with the spatial grid set, clearly and completely carrying the pollution source energy attributes corresponding to the grid. This provides accurate, standardized, and compatible feature data support for subsequent energy field mapping and initial energy distribution field construction, comprehensively improving the completeness, accuracy, and standardization of pollution source energy feature extraction and representation.

[0109] P3. Map the energy representation vector to the spatial grid set in a spatial field to construct the initial energy distribution field of the target region;

[0110] In this embodiment of the invention, the step of mapping the energy representation vector to the spatial grid set in a spatial field to construct the initial energy distribution field of the target region includes:

[0111] The spatial grid set is coupled with the energy representation vector through global matching to obtain the grid energy attachment pairs of the spatial grid set;

[0112] The grid energy attachment pairs are discretized and arranged in the field to obtain the energy field scatter cloud of the grid energy attachment pairs;

[0113] The energy field scatter cloud is continuously interpolated and fitted to obtain the continuous energy field base surface of the energy field scatter cloud;

[0114] Based on the continuous energy field datum, energy shaping quantization is performed on the grid nodes of the spatial grid set to obtain the grid node energy values ​​of the spatial grid set;

[0115] The energy values ​​of the grid nodes are arrayed and arranged, and the arranged grid energy array is reconstructed in the whole domain to obtain the initial energy distribution field of the target area.

[0116] Based on the full spatial coverage of the spatial grid set and the preset grid spatial arrangement order, each independent grid in the spatial grid set is traversed one by one. Each grid is precisely matched with the energy feature information of the corresponding position in the energy representation vector. This ensures that each spatial grid can be bound to a unique and matching energy representation vector, and completely eliminates mismatches, omissions, or duplicate bindings between grids and energy vectors. This forms a stable combination structure with a one-to-one correspondence between spatial grids and energy representation vectors, and finally obtains the grid energy attachment pairs of the spatial grid set.

[0117] All grid energy attachment pairs are placed sequentially into the corresponding spatial field locations within the target area according to their actual spatial coordinates within the target area, ensuring that the spatial locations of the grid energy attachment pairs are completely consistent with the real geographic space of the target area. This allows all grid energy attachment pairs to exhibit an independent and discrete distribution across the entire spatial domain. All discretely distributed grid energy attachment pairs are then uniformly collected and integrated to form a point set covering the entire target area, ultimately yielding a scattered cloud of energy fields for the grid energy attachment pairs.

[0118] Using each discrete energy point in the energy field scatter cloud as a basic reference, continuous energy value transition processing is carried out in the blank space region between adjacent energy points. The gaps in energy values ​​between discrete points are filled by smooth connection, so that the originally independent discrete energy points are connected to form a continuous spatial energy surface without discontinuity or fault, so that the energy distribution of the entire field presents a continuous and smooth state, and finally the continuous energy field base surface of the energy field scatter cloud is obtained.

[0119] Based on the global energy distribution pattern presented by the continuous energy field datum, the energy values ​​of all nodes in each grid of the spatial grid set are accurately matched and determined. The continuous energy distribution information of the continuous energy field datum is transformed into specific energy values ​​that the grid nodes can bear, ensuring that the energy value of each grid node is completely consistent with the energy pattern of the continuous energy field datum, fully restoring the energy attributes corresponding to the grid nodes, and finally obtaining the grid node energy values ​​of the spatial grid set.

[0120] According to the original spatial array arrangement rules and grid arrangement order of the spatial grid set, the energy values ​​of all grid nodes are arranged and combined in an orderly manner to form a grid energy array that is completely consistent with the spatial structure of the spatial grid set. Then, the grid energy array is restored to the entire space of the target area to completely reconstruct the entire spatial field, so that the energy values ​​and spatial structure are deeply integrated, and finally the initial energy distribution field of the target area is obtained.

[0121] The beneficial effects are as follows: through the precise global matching and coupling of spatial grid sets and energy characterization vectors, the real spatial discrete arrangement of grid energy attachment pairs, the uninterrupted continuous interpolation fitting of energy field scatter cloud, the precise energy shaping quantization of grid nodes, and the standardized global field reconstruction of grid energy arrays, the deep spatial field mapping of energy characterization vectors and spatial grid sets is fully realized. This transforms the discrete and fragmented energy characteristics of pollution sources into a continuous and complete initial energy distribution field that fits the spatial structure of the target area. It accurately preserves the spatial distribution law, numerical characteristics, and spatial correlation of pollution source energy, giving the initial energy distribution field extremely high spatial adaptability and data accuracy. This provides a stable, reliable, and complete basic field condition for subsequent monitoring point interpolation residual analysis, local deviation coefficient calculation, and energy field variational assimilation correction, comprehensively improving the standardization, continuity, accuracy, and spatial matching of the initial energy distribution field construction.

[0122] P4. Perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficient of the monitoring points;

[0123] In this embodiment of the invention, the step of performing interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficients of the monitoring points includes:

[0124] Spatial residual spectrum analysis is performed on the monitoring points in the initial energy distribution field to obtain the residual energy spectrum of the monitoring points;

[0125] The residual energy values ​​in the residual energy spectrum are reduced by energy mean to construct the normalized bias field of the residual energy spectrum;

[0126] The effective deviation field of the normalized deviation field is obtained by removing the extreme energy ridges in the normalized deviation field.

[0127] The effective deviation field is refined by condensing deviation characteristics, and the monitoring point is used as the index reference to shape the local coefficients of the refined deviation field to obtain the local deviation coefficients of the monitoring point.

[0128] The step of performing energy mean reduction on the residual energy values ​​in the residual energy spectrum to construct the normalized bias field of the residual energy spectrum includes:

[0129] The residual energy of the residual spectrum nodes in the residual energy spectrum is interpreted to obtain the residual energy value of the residual spectrum node;

[0130] The residual energy value is aggregated in the neighborhood to obtain the neighborhood average residual energy of the residual spectrum node;

[0131] The residual energy value and the neighborhood average residual energy are correlated to construct the nodal reduction coefficients of the residual energy spectrum. The calculation formula for the nodal reduction coefficients is as follows:

[0132] ;

[0133] in, Indicates the first The nodal reduction coefficients of the residual spectrum nodes. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The neighbor node index set of the residual spectrum nodes This represents the total number of indexes in the adjacent node index set;

[0134] Based on the node reduction coefficients, the residual energy spectrum is normalized and mapped to obtain the normalized bias field of the residual energy spectrum.

[0135] The spatial distribution of all monitoring points in the initial energy distribution field is traversed. The theoretical energy value generated by each monitoring point in the initial energy distribution field and the actual monitored energy value are extracted. The residual energy information between the two types of values ​​is calculated. The residual energy information of all monitoring points is integrated according to the spatial distribution law to form a complete spectral data set, which fully presents the spatial distribution characteristics of the residual energy of the monitoring points, and finally the residual energy spectrum of the monitoring points is obtained.

[0136] The residual energy information carried by each residual spectrum node in the residual energy spectrum is analyzed one by one. The abstract residual energy characteristics in the spectrum set are transformed into intuitive and quantifiable residual energy values. The residual energy magnitude corresponding to each residual spectrum node is accurately determined, the core residual energy data of the node is completely extracted, and finally the residual energy value of the residual spectrum node is obtained.

[0137] Taking each residual spectrum node as the center, the residual energy values ​​of all neighboring residual spectrum nodes around the node are collected. The residual energy values ​​of these neighboring nodes are comprehensively summarized and integrated, and the overall average level is calculated to intuitively reflect the overall residual energy status of the area around the residual spectrum node. Finally, the neighborhood average residual energy of the residual spectrum node is obtained.

[0138] A direct numerical correlation is established between the residual energy value of a single residual spectrum node and the average residual energy of its corresponding neighborhood. Based on the correspondence between the two, a correlation coefficient that reflects the degree of relative deviation is constructed, clearly showing the degree of difference between the residual energy of a single node and the overall residual energy of the neighborhood. Finally, the node reduction coefficients of the residual energy spectrum are obtained.

[0139] The node reduction coefficient is calculated by precisely comparing the residual energy value of the node itself with the average residual energy of its neighborhood. The residual energy value of the node itself is obtained by performing a comprehensive residual energy interpretation operation on the corresponding residual energy node in the residual energy spectrum. The average residual energy of the neighborhood of a residual energy node is calculated by fully averaging the residual energy values ​​of all neighboring residual energy nodes centered on that node. The residual energy values ​​of neighboring residual energy nodes are obtained by performing a comprehensive residual energy interpretation operation on the corresponding neighboring residual energy nodes in the residual energy spectrum. The neighboring node index set is a complete set of nodes formed by gathering all surrounding neighboring residual energy nodes centered on the target residual energy node. The total number of indices in the neighboring node index set is obtained by precisely counting the number of each node included in the neighboring node index set.

[0140] This calculation method quantifies the precise deviation of the residual energy value of a single residual spectrum node from the overall residual energy level of its neighborhood. It maps residual energy values ​​of different magnitudes to a standardized numerical range, providing a core basis for the normalization of the residual energy spectrum. The calculated node reduction coefficients can be directly used for the normalization mapping operation of the residual energy spectrum, supporting the standardized construction of the normalized bias field. This calculation method effectively eliminates the interference of differences in residual energy magnitudes across different regions on bias analysis, ensuring the global consistency of the bias field. Furthermore, this method accurately characterizes the local bias features of a single residual spectrum node, providing reliable data support for the subsequent construction of an effective bias field.

[0141] When the residual energy value of a single residual spectrum node increases, the node reduction coefficient increases synchronously. When the residual energy value of a single residual spectrum node decreases, the node reduction coefficient decreases synchronously. When the neighborhood average residual energy of a residual spectrum node increases, the node reduction coefficient decreases synchronously. When the neighborhood average residual energy of a residual spectrum node decreases, the node reduction coefficient increases synchronously. The change in the node reduction coefficient is stably positively correlated with the residual energy value of a single residual spectrum node. The change in the node reduction coefficient is stably negatively correlated with the neighborhood average residual energy of a residual spectrum node. When the residual energy value of a single residual spectrum node is equal to the neighborhood average residual energy, the node reduction coefficient remains stable.

[0142] Using the node reduction coefficient as a unified adjustment basis, the residual energy values ​​of all residual spectrum nodes in the residual energy spectrum are standardized and adjusted, and the residual energy values ​​of different orders of magnitude are uniformly mapped to the same numerical range, forming a deviation distribution field with consistent numerical standards across the entire domain, and finally obtaining the normalized deviation field of the residual energy spectrum.

[0143] Identify the extreme energy ridge structure composed of abnormal deviation values ​​in the normalized deviation field, completely remove these extreme energy ridges that deviate from the normal deviation distribution law from the field, retain the deviation data that conforms to the normal distribution law and the complete field structure, remove the interference of abnormal data on deviation analysis, and finally obtain the effective deviation field of the normalized deviation field.

[0144] Extract the core deviation distribution characteristics and key numerical information from the effective deviation field, filter out redundant detailed deviation information in the field, and centrally integrate and refine the core deviation characteristics to form a deviation field structure with clear characteristics and no redundant information, thus obtaining the condensed deviation field.

[0145] Using the monitoring points in the initial energy distribution field as spatial index references, the core deviation characteristics in the condensed deviation field are precisely spatially correlated with each monitoring point. Each monitoring point is assigned a unique coefficient that reflects its own local deviation state, accurately characterizing the local deviation characteristics of a single monitoring point, and finally obtaining the local deviation coefficient of the monitoring point.

[0146] The beneficial effects are as follows: by performing spatial residual spectrum analysis of the initial energy distribution field monitoring points, interpreting and aggregating residual energy values, constructing node reduction coefficients, generating normalized deviation fields, eliminating extreme energy ridges, refining effective deviation field features, and shaping local coefficients under the monitoring point index, the system fully realizes accurate interpolation residual analysis of the initial energy distribution field monitoring points. It effectively eliminates interference from abnormal deviation data, accurately extracts the local deviation features of each monitoring point, and generates local deviation coefficients that can truly reflect the local energy deviation state of the monitoring points. This provides accurate and reliable deviation data support for the subsequent variational assimilation correction of the initial energy distribution field, and comprehensively improves the accuracy, effectiveness, and relevance of residual analysis.

[0147] P5. Based on the local deviation coefficient, the initial energy distribution field is subjected to variational assimilation correction, and the corrected deviation compensation field is superimposed with the initial energy distribution field to obtain the corrected energy distribution field of the target region.

[0148] In this embodiment of the invention, the step of performing variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and then superimposing the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region, includes:

[0149] The initial energy distribution field is deconstructed by field gradient, and the deconstructed gradient component field is subjected to bias weighted modulation based on the local bias coefficient to obtain the bias modulated gradient field of the initial energy distribution field.

[0150] Based on the deviation modulation gradient field, variational iterative derivation is performed on the deviation modulation gradient field to obtain the deviation compensation field of the initial energy distribution field;

[0151] The deviation compensation field is superimposed with the initial energy distribution field to obtain the initial correction field of the initial energy distribution field.

[0152] The initial correction field is subjected to boundary constraint regularization to obtain the boundary fidelity correction field of the initial correction field;

[0153] The boundary fidelity correction field is globally smoothed and optimized to obtain the corrected energy distribution field of the target region.

[0154] The entire spatial range of the initial energy distribution field is traversed, and the overall energy distribution pattern of the initial energy distribution field is comprehensively decomposed. The energy change characteristics of each spatial location in the initial energy distribution field are decomposed into independent gradient component structures. The energy change gradient information of the entire initial energy distribution field is completely extracted to form a set of gradient components covering the entire target area. Then, using the local deviation coefficient as a unified weight benchmark, each set of gradient components in the gradient component field is weighted and adjusted one by one. The local deviation characteristics corresponding to the monitoring point are accurately integrated into the gradient components of the corresponding location. The gradient adjustment intensity in the deviation area is strengthened, and the gradient adjustment amplitude in the non-deviation area is weakened. This allows the gradient component field to fully bear the correction requirements of the local deviation, and finally, the deviation modulation gradient field of the initial energy distribution field is obtained.

[0155] Based on the bias modulation gradient field, multiple rounds of iterative deduction and calculation are carried out on the bias modulation gradient field. Each iteration takes the gradient change characteristics of the bias modulation gradient field as the core basis, gradually deduces and corrects the bias compensation amount at each spatial location in the field, continuously optimizes the accuracy and adaptability of the bias compensation, until the bias compensation amount reaches a stable convergence state, and finally obtains the bias compensation field of the initial energy distribution field that can accurately compensate for the local bias of the initial energy distribution field.

[0156] The deviation compensation field and the initial energy distribution field are precisely matched in the whole domain according to the completely consistent spatial coordinate position. The deviation compensation amount in the deviation compensation field is superimposed one by one to the corresponding spatial position of the initial energy distribution field, so that each spatial position of the initial energy distribution field completes targeted deviation compensation. The energy information of the deviation compensation field and the initial energy distribution field are fully integrated, and finally the initial correction field of the initial energy distribution field is obtained.

[0157] Using the repair boundary data of the target area as a rigid constraint benchmark, the boundary area of ​​the initial correction field is comprehensively normalized to correct the energy distortion and morphological deviation in the boundary area of ​​the initial correction field, so that the boundary morphology of the initial correction field is completely consistent with the real geographical boundary of the target area, ensuring that the energy distribution of the boundary area conforms to the spatial characteristics of the real boundary, and finally obtaining the boundary fidelity correction field of the initial correction field.

[0158] A comprehensive smoothing optimization process is performed on the entire space of the boundary fidelity correction field to eliminate local energy abrupt changes caused by deviation compensation and boundary regularization. This ensures that the global energy distribution of the boundary fidelity correction field remains continuous and smooth, fully preserving the true energy distribution characteristics and spatial structure of the target region, and finally obtaining the corrected energy distribution field of the target region.

[0159] The beneficial effects are as follows: through a complete closed-loop process of global field gradient deconstruction of the initial energy distribution field, gradient component bias weighted modulation based on local bias coefficients, variational iterative derivation of the bias-modulated gradient field, global energy superposition of the bias compensation field and the initial energy distribution field, boundary constraint regularization of the initial correction field, and global smoothing optimization of the boundary fidelity correction field, the initial energy distribution field is accurately assimilated and corrected by relying on local bias coefficients. This effectively eliminates interpolation errors and local biases in the initial energy distribution field, comprehensively improves the spatial accuracy and data reliability of the energy distribution field, and ensures that the boundary morphology of the corrected energy distribution field completely matches the real geographical boundary of the target area. The global energy distribution remains continuous and smooth, and the real energy distribution characteristics and spatial structure of the target area are fully preserved. This provides a stable and reliable high-precision field foundation for the subsequent accurate assessment and visualization of pollution source energy distribution, and comprehensively improves the accuracy, continuity, and spatial adaptability of pollution source energy distribution assessment.

[0160] P6. Perform contour tracing on the modified energy distribution field, and assign level values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution assessment map of the target area.

[0161] In this embodiment of the invention, the step of performing contour tracing on the modified energy distribution field and assigning grade values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution assessment map of the target area includes:

[0162] By performing energy contour tracing on the modified energy distribution field, the energy contour lines of the modified energy distribution field are obtained.

[0163] The energy contour lines are sorted by energy level segments to obtain a mapping table of energy contour line level segments.

[0164] The chromaticity spectrum of the level segment mapping table is assigned a chromaticity code to obtain the chromaticity coding spectrum of the level segment mapping table.

[0165] The energy contour lines and the chromaticity coding spectrum are fused and colored to obtain a pollution source energy distribution assessment map of the target area.

[0166] By traversing every spatial location in the entire modified energy distribution field, the precise energy value of the corresponding location is extracted. Continuous points are connected according to the spatial distribution locations of the same energy value. The spatial contour trajectory of the same energy value is traced segment by segment along the trend of energy value change in the modified energy distribution field. All continuous points with the same energy value are integrated into a closed and continuous line structure, fully presenting the spatial contour shape of different energy values ​​in the modified energy distribution field, and finally obtaining the energy contour lines of the modified energy distribution field.

[0167] The energy values ​​corresponding to all energy contour lines are analyzed, and the energy contour lines are divided into levels according to the order of energy values ​​from low to high. Energy contour lines with similar energy values ​​are grouped into the same energy level segment. The energy value range and the corresponding energy contour line for each energy level segment are defined, and a complete one-to-one correspondence between energy level segments and energy contour lines is established. All energy level segments, energy value ranges and corresponding energy contour lines are organized into a standardized table, and finally, a mapping table of energy contour level segments is obtained.

[0168] Based on the energy level segment division results in the level segment mapping table, a unique color identifier is matched for each independent energy level segment. The energy level segments are matched with a gradient and highly distinguishable color spectrum in order from low to high. Each energy level segment is fixedly bound to the corresponding color to form a complete color coding correspondence. The color coding information of all energy level segments is integrated to form a continuous color coding system, and finally the chromaticity coding spectrum of the level segment mapping table is obtained.

[0169] According to the correspondence between energy level segments and colors in the colorimetric coding spectrum, the corresponding colors are filled into the spatial area enclosed by the energy contour lines. The lines of the energy contour lines and the enclosed areas are uniformly colored, while the outline shape of the energy contour lines and the color differentiation characteristics of the energy level segments are preserved. The colored energy contour lines are accurately superimposed and integrated with the spatial outline of the target area to form a complete and intuitive visualization assessment graphic, and finally, the pollution source energy distribution assessment map of the target area is obtained.

[0170] The beneficial effects are as follows: by correcting the energy contour of the energy distribution field, tracing the energy level segments of the energy contour lines, assigning chromaticity codes to the level segment mapping table, and fusing the energy contour lines with the chromaticity coding spectrum for color rendering, the visualization transformation of pollution source energy distribution is fully realized. The energy contour features of the corrected energy distribution field are accurately extracted, and the spatial distribution range of different energy levels is clearly distinguished through energy level sequencing and chromaticity coding. The generated pollution source energy distribution assessment map is intuitive, clear, and hierarchical, and can accurately reflect the spatial distribution pattern and level differences of pollution source energy in the target area. It provides intuitive and reliable visualization results for pollution source energy distribution assessment, and comprehensively improves the intuitiveness, readability, and practicality of the assessment results.

[0171] like Figure 2 The diagram shown is a functional block diagram of a pollution source energy distribution assessment system based on spatial grid modeling, provided in an embodiment of the present invention.

[0172] The pollution source energy distribution assessment system 100 based on spatial grid modeling described in this invention can be installed in an electronic device. Depending on the functions implemented, the pollution source energy distribution assessment system 100 may include a gridded boundary segmentation module 101, a pollution source feature decoupling module 102, an energy field mapping module 103, a residual deviation analysis module 104, a variational assimilation correction module 105, and a contour rendering assessment module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0173] In this embodiment, the functions of each module / unit are as follows:

[0174] The rasterization boundary segmentation module 101 is used to acquire the spatial boundary information of the target area, and to perform uniform rasterization division of the target area according to the spatial boundary information to obtain the spatial raster set of the target area.

[0175] The pollution source feature decoupling module 102 is used to extract pollution source monitoring data from the spatial grid set and perform feature decoupling on the pollution source monitoring data to obtain the energy characterization vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information, and emission rate information.

[0176] The energy field mapping module 103 is used to perform spatial field mapping between the energy representation vector and the spatial grid set to construct the initial energy distribution field of the target region.

[0177] The residual deviation analysis module 104 is used to perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficient of the monitoring points.

[0178] The variational assimilation correction module 105 is used to perform variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and to superimpose the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region.

[0179] The contour rendering and evaluation module 106 is used to perform contour tracing on the modified energy distribution field and to perform level assignment rendering on the traced energy distribution contour lines to obtain a pollution source energy distribution evaluation map of the target area.

[0180] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0181] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0183] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0184] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0185] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for assessing the energy distribution of pollution sources using spatial gridding modeling, characterized in that, The method includes: P1. Obtain the spatial boundary information of the target area, and divide the target area into uniform grids based on the spatial boundary information to obtain the spatial grid set of the target area; P2. Extract pollution source monitoring data from the spatial grid set, and perform feature decoupling on the pollution source monitoring data to obtain the energy representation vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information, and emission rate information, including: The spatial grid set is coupled with the energy representation vector through global matching to obtain the grid energy attachment pairs of the spatial grid set; The grid energy attachment pairs are discretized and arranged in the field to obtain the energy field scatter cloud of the grid energy attachment pairs; The energy field scatter cloud is continuously interpolated and fitted to obtain the continuous energy field base surface of the energy field scatter cloud; Based on the continuous energy field datum, energy shaping quantization is performed on the grid nodes of the spatial grid set to obtain the grid node energy values ​​of the spatial grid set; The energy values ​​of the grid nodes are arrayed and arranged, and the arranged grid energy array is reconstructed in the global field to obtain the initial energy distribution field of the target area. P3. Map the energy representation vector to the spatial grid set in a spatial field to construct the initial energy distribution field of the target region; P4. Perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficient of the monitoring points; P5. Based on the local deviation coefficient, the initial energy distribution field is subjected to variational assimilation correction, and the corrected deviation compensation field is superimposed with the initial energy distribution field to obtain the corrected energy distribution field of the target region. P6. Perform contour tracing on the modified energy distribution field, and assign level values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution assessment map of the target area.

2. The method for assessing pollution source energy distribution through spatial gridding modeling as described in claim 1, characterized in that, The step of acquiring the spatial boundary information of the target region and, based on the spatial boundary information, uniformly rasterizing the target region to obtain a spatial raster set of the target region includes: Collect the original geographic boundary data of the target area, and perform topological consistency repair on the original geographic boundary data to obtain the repaired boundary data of the target area; Based on the repaired boundary data, the boundary geometric contour of the target region is subjected to extreme value analysis and calibration to obtain the boundary extreme value coordinates of the target region. The boundary extreme value coordinates are subjected to an outer enclosure configuration to obtain the rectangular outer envelope surface of the target region; The rectangular outer envelope is divided into equidistant regular subdivisions to obtain the initial grid array of the target region; Using the repaired boundary data as a clipping template, the initial raster array is clipped, and the raster elements located inside the repaired boundary data after clipping are taken as the spatial raster set of the target region.

3. The method for assessing pollution source energy distribution through spatial gridding modeling as described in claim 2, characterized in that, The step of performing extreme value analysis and calibration on the boundary geometric contour of the target region based on the repaired boundary data to obtain the boundary extreme value coordinates of the target region includes: The repaired boundary data is reconstructed using vector topology to obtain the boundary geometric contour of the target region; Traverse the contour nodes of the boundary geometric contour line and perform curvature gradient inversion on the contour nodes to obtain the node curvature extreme value distribution of the boundary geometric contour line. Ridge connectivity fitting is performed on the node curvature extremum distribution to obtain the curvature ridge of the node curvature extremum distribution; Projecting the curvature ridge line onto the spatial reference of the repair boundary data yields the set of ridge line intersection points of the curvature ridge line; Iterative convergence localization is performed on the set of ridge intersection points to obtain the boundary extreme coordinates of the target region.

4. The method for assessing the energy distribution of pollution sources using spatial gridding modeling as described in claim 1, characterized in that, The step of mapping the energy representation vector to the spatial grid set to construct the initial energy distribution field of the target region includes: The spatial grid set is coupled with the energy representation vector through global matching to obtain the grid energy attachment pairs of the spatial grid set; The grid energy attachment pairs are discretized and arranged in the field to obtain the energy field scatter cloud of the grid energy attachment pairs; The energy field scatter cloud is continuously interpolated and fitted to obtain the continuous energy field base surface of the energy field scatter cloud; Based on the continuous energy field datum, energy shaping quantization is performed on the grid nodes of the spatial grid set to obtain the grid node energy values ​​of the spatial grid set; The energy values ​​of the grid nodes are arrayed and arranged, and the arranged grid energy array is reconstructed in the whole domain to obtain the initial energy distribution field of the target area.

5. The method for assessing the energy distribution of pollution sources using spatial gridding modeling as described in claim 1, characterized in that, The interpolation residual analysis of the monitoring points in the initial energy distribution field to obtain the local deviation coefficients of the monitoring points includes: Spatial residual spectrum analysis is performed on the monitoring points in the initial energy distribution field to obtain the residual energy spectrum of the monitoring points; The residual energy values ​​in the residual energy spectrum are reduced by energy mean to construct the normalized bias field of the residual energy spectrum; The effective deviation field of the normalized deviation field is obtained by removing the extreme energy ridges in the normalized deviation field. The effective deviation field is refined by condensing deviation characteristics, and the monitoring point is used as the index reference to shape the local coefficients of the refined deviation field to obtain the local deviation coefficients of the monitoring point.

6. The method for assessing the energy distribution of pollution sources using spatial gridding modeling as described in claim 5, characterized in that, The step of performing energy mean reduction on the residual energy values ​​in the residual energy spectrum to construct the normalized bias field of the residual energy spectrum includes: The residual energy of the residual spectrum nodes in the residual energy spectrum is interpreted to obtain the residual energy value of the residual spectrum node; The residual energy value is aggregated in the neighborhood to obtain the neighborhood average residual energy of the residual spectrum node; The residual energy value and the neighborhood average residual energy are correlated to construct the nodal reduction coefficients of the residual energy spectrum. The calculation formula for the nodal reduction coefficients is as follows: ； in, Let represent the nodal reduction coefficient of the i-th residual spectrum node. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The residual energy value of each of the residual spectrum nodes. Indicates the first The neighbor node index set of the residual spectrum nodes This represents the total number of indexes in the adjacent node index set; Based on the node reduction coefficients, the residual energy spectrum is normalized and mapped to obtain the normalized bias field of the residual energy spectrum.

7. The method for assessing pollution source energy distribution using spatial gridding modeling as described in claim 1, characterized in that, The step of performing variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and then superimposing the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region includes: The initial energy distribution field is deconstructed by field gradient, and the deconstructed gradient component field is subjected to bias weighted modulation based on the local bias coefficient to obtain the bias modulated gradient field of the initial energy distribution field. Based on the deviation modulation gradient field, variational iterative derivation is performed on the deviation modulation gradient field to obtain the deviation compensation field of the initial energy distribution field; The deviation compensation field is superimposed with the initial energy distribution field to obtain the initial correction field of the initial energy distribution field. The initial correction field is subjected to boundary constraint regularization to obtain the boundary fidelity correction field of the initial correction field; The boundary fidelity correction field is globally smoothed and optimized to obtain the corrected energy distribution field of the target region.

8. The method for assessing the energy distribution of pollution sources using spatial gridding modeling as described in claim 1, characterized in that, The process of performing contour tracing on the corrected energy distribution field and assigning grade values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution assessment map of the target area includes: By performing energy contour tracing on the modified energy distribution field, the energy contour lines of the modified energy distribution field are obtained. The energy contour lines are sorted by energy level segments to obtain a mapping table of energy contour line level segments. The chromaticity spectrum of the level segment mapping table is assigned a chromaticity code to obtain the chromaticity coding spectrum of the level segment mapping table. The energy contour lines and the chromaticity coding spectrum are fused and colored to obtain a pollution source energy distribution assessment map of the target area.

9. A pollution source energy distribution assessment system based on spatial grid modeling, characterized in that, The system for implementing the spatial gridded modeling method for assessing pollution source energy distribution as described in claim 1 includes: The rasterization boundary segmentation module is used to acquire the spatial boundary information of the target region, and to perform uniform rasterization division of the target region based on the spatial boundary information to obtain the spatial raster set of the target region. The pollution source feature decoupling module is used to extract pollution source monitoring data from the spatial grid set and perform feature decoupling on the pollution source monitoring data to obtain the energy characterization vector of the spatial grid set. The pollution source monitoring data includes pollution source location information, emission type information, and emission rate information. The energy field mapping module is used to perform spatial field mapping between the energy representation vector and the spatial grid set to construct the initial energy distribution field of the target region. The residual deviation analysis module is used to perform interpolation residual analysis on the monitoring points in the initial energy distribution field to obtain the local deviation coefficients of the monitoring points. The variational assimilation correction module is used to perform variational assimilation correction on the initial energy distribution field based on the local deviation coefficient, and to superimpose the corrected deviation compensation field with the initial energy distribution field to obtain the corrected energy distribution field of the target region. The contour rendering and evaluation module is used to perform contour tracing on the modified energy distribution field and to assign grade values ​​to the traced energy distribution contour lines to obtain a pollution source energy distribution evaluation map of the target area.

Images