Intelligent carbon emission dynamic tracking and early warning method and system

Abstract

The present invention discloses a dynamic tracking and early warning method and system for intelligent carbon emissions, which relates to the field of carbon emission management technology. The method includes: constructing a digital twin model of the target area, and performing grid division based on monitoring accuracy, and laying out the first layer of fixed monitoring points; planning a mobile monitoring path in combination with the carbon emission focus fitting results, and configuring the second layer of mobile monitoring points; collecting data through the two layers of monitoring points to establish a carbon emission data network; then performing airflow simulation based on the digital twin model, performing source tracing inversion in combination with the data network, and locating the emission source; finally, achieving device-level positioning and carbon emission tracking and early warning through device matching analysis. The present invention solves the technical problems in the prior art of limited carbon emission monitoring coverage, insufficient source tracing capabilities, and difficulty in achieving accurate positioning and real-time early warning of carbon emission sources, and achieves the technical effect of high-precision source tracing and positioning of carbon emission sources and real-time tracking and early warning.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon emission management, and in particular to a method and system for dynamic tracking and early warning of intelligent carbon emissions. Background Art

[0002] The demand for corporate carbon emissions regulation is growing. Traditional data collection methods relying on fixed monitoring equipment are no longer sufficient to meet the dynamic control requirements of today's complex urban emissions environment. Current monitoring methods suffer from insufficient distribution density, numerous blind spots, slow response to anomalies, and a lack of emission path tracking and equipment traceability. These factors hinder the timely detection, accurate location, and effective resolution of emissions issues. This is particularly true in industrial parks, high-density emission areas, or non-point source scenarios, where emissions exhibit significant spatial diffusion and temporal dynamics. Static monitoring alone is difficult to achieve comprehensive coverage and accurate identification. Summary of the Invention

[0003] This application provides a dynamic tracking and early warning method and system for intelligent carbon emissions, which is used to solve the technical problems in the existing technology of limited carbon emission monitoring coverage, insufficient traceability capabilities, and difficulty in achieving accurate positioning and real-time early warning of carbon emission sources.

[0004] The first aspect of the present application provides a dynamic tracking and early warning method for intelligent carbon emissions, which includes: executing digital twin modeling of the target area, configuring the grid granularity according to the monitoring accuracy, executing grid segmentation of the target area, and distributing the first-level fixed monitoring points according to the grid segmentation results; using the digital twin model to perform carbon emission focus fitting in the target area, establishing a mobile monitoring path according to the carbon emission focus fitting results, and configuring the second-level mobile monitoring points through the mobile monitoring path; after monitoring the target area by the first-level fixed monitoring points and the second-level mobile monitoring points, a carbon emission data network is established; based on the digital twin model, airflow simulation in the target area is performed, and source inversion is performed according to the airflow simulation results and the carbon emission data network to establish a source inversion result; according to the source inversion result, equipment matching analysis is performed in the target area to establish an equipment positioning result, and carbon emission tracking and early warning is established according to the equipment positioning result.

[0005] The second aspect of the present application provides a dynamic tracking and early warning system for intelligent carbon emissions, the system comprising: a fixed monitoring point distribution module, the fixed monitoring point distribution module is used to perform digital twin modeling of the target area, and after configuring the grid granularity according to the monitoring accuracy, perform grid segmentation of the target area, and distribute the first-level fixed monitoring points according to the grid segmentation result; a mobile monitoring point configuration module, the mobile monitoring point configuration module is used to use the digital twin model to perform carbon emission focus fitting of the target area, establish a mobile monitoring path according to the carbon emission focus fitting result, and configure the second-level mobile monitoring points through the mobile monitoring path; a carbon emission data network establishment module, the carbon emission data network establishment module is used to establish a carbon emission data network after the target area is monitored by the first-level fixed monitoring points and the second-level mobile monitoring points; a traceability inversion module, the traceability inversion module is used to perform airflow simulation in the target area based on the digital twin model, and according to the airflow simulation result, the The carbon emission data network is traced back and inverted to establish the traced back and inversion results, including: inputting the carbon emission data network into the feature extraction channel, executing feature extraction, and establishing feature extraction results, including: a: reading the carbon concentration value of the continuous time node for each position point, calculating the time derivative of the carbon concentration value, and establishing a local temporal gradient feature; b: constructing a spatial gradient field through spatial interpolation of the local temporal gradient features of all position points, and establishing a spatial gradient distribution feature; c: performing gradient change feature extraction based on the local temporal gradient feature and the spatial gradient distribution feature, establishing a key gradient feature, and outputting the key gradient feature as a feature extraction result; performing traced back and inversion based on the feature extraction result and the airflow simulation result; a carbon emission tracking and early warning module, the carbon emission tracking and early warning module is used to perform equipment matching analysis in the target area based on the traced back and inversion result, establish an equipment positioning result, and establish a carbon emission tracking and early warning based on the equipment positioning result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The intelligent carbon emission dynamic tracking and early warning method and system provided in this application relate to the field of carbon emission management technology. Through digital twin modeling, a virtual environment of the target area is constructed, and fixed monitoring points are arranged in grids according to monitoring accuracy. Combined with carbon emission focus fitting, a mobile monitoring path is generated to form a carbon emission data network covering the entire area. Then, based on airflow simulation and data network, source tracing and inversion are performed, and equipment calibration data is matched to realize source positioning, and finally dynamic tracking and early warning of carbon emissions are realized. This solves the technical problems in the existing technology of limited carbon emission monitoring coverage, insufficient traceability capability, and difficulty in achieving accurate positioning and real-time early warning of carbon emission sources. It realizes the technical effect of high-precision traceability and real-time tracking and early warning of carbon emission sources by constructing a multi-level monitoring network and introducing airflow simulation and emission feature matching mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A flow chart of a method for dynamic tracking and early warning of intelligent carbon emissions provided in an embodiment of the present application;

[0010] Figure 2 Schematic diagram of the structure of the dynamic tracking and early warning system for intelligent carbon emissions provided in an embodiment of the present application.

[0011] Explanation of the accompanying symbols: fixed monitoring point distribution module 11, mobile monitoring point configuration module 12, carbon emission data network establishment module 13, tracing and inversion module 14, carbon emission tracking and early warning module 15. DETAILED DESCRIPTION

[0012] This application provides a dynamic tracking and early warning method and system for intelligent carbon emissions, which is used to solve the technical problems in the existing technology of limited carbon emission monitoring coverage, insufficient traceability capabilities, and difficulty in achieving accurate positioning and real-time early warning of carbon emission sources.

[0013] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0014] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or devices.

[0015] Example 1, as Figure 1As shown, this application provides a dynamic tracking and early warning method for intelligent carbon emissions, which includes:

[0016] P10: Execute digital twin modeling of the target area, configure the grid granularity according to the monitoring accuracy, perform grid segmentation of the target area, and distribute the first-level fixed monitoring points according to the grid segmentation results.

[0017] Specifically, digital twin modeling of the target area is first carried out. This involves combining physical modeling with data-driven modeling to construct a virtual regional model with high simulation accuracy and dynamic response capabilities based on basic information such as the target area's building layout, topography, meteorological characteristics, existing monitoring data, and carbon emission source types. This digital twin model supports continuous access to and feedback from real-time monitoring data, dynamically mapping the spatiotemporal evolution of carbon emissions within the target area, and providing fundamental support for subsequent monitoring path planning, emission fitting, and inversion.

[0018] After completing the digital twin modeling, it is necessary to perform grid granularity configuration operations based on the requirements of the actual monitoring task for carbon concentration perception accuracy. Grid granularity refers to the degree of fineness of grid division in the digital twin model, which directly affects the accuracy and computational complexity of subsequent monitoring data. This operation can determine the size and shape of the grid division by analyzing factors such as the spatial scale of the target area, the expected monitoring accuracy, and the distribution density of carbon emission sources. For example, an equilateral regular grid (such as a square or hexagon) or an irregular adaptive grid is used. The specific granularity size is positively correlated with the complexity of the area. For example, in densely populated, busy traffic, or carbon source-intensive areas, smaller granularity should be used to enhance monitoring resolution; in open areas or areas with stable carbon emission behavior, larger granularity can be used to save resources.

[0019] After the granularity is determined, grid segmentation is further performed, that is, the target area is divided into several spatial units according to the set grid granularity. This operation can be completed with the assistance of the GIS geographic information system to achieve automatic alignment and adaptation with the regional physical topography. After the segmentation is completed, appropriate monitoring locations are selected based on the grid center, boundary intersections and typical scene points (such as main road intersections and industrial equipment concentration areas), and the first level of fixed monitoring points are distributed. These monitoring points are immovable sensor terminals deployed in the area, usually with real-time detection capabilities for carbon gas concentrations such as carbon dioxide and methane. At the same time, they integrate communication modules (such as LoRa, NB-IoT or 5G modules) and positioning modules (such as GPS) for data backhaul and device status synchronization.

[0020] Furthermore, to improve the coverage and timeliness of monitoring data, the layout of fixed monitoring points can be optimized by combining grid locations with meteorological simulation results from the digital twin model. For example, the density of fixed monitoring points can be increased downwind or in areas of convergence to enhance the sensitivity of source identification. Through these operations, the first-level fixed monitoring network is constructed, forming a static, distributed infrastructure for collecting carbon emissions information in the target area. This provides the basic data support and spatial reference framework for subsequent high-precision, dynamic carbon emissions tracking and early warning.

[0021] P20: Use the digital twin model to fit the carbon emission concerns of the target area, establish a mobile monitoring path based on the carbon emission concern fitting results, and configure the second-layer mobile monitoring points through the mobile monitoring path.

[0022] Furthermore, step P20 in this embodiment of the present application further includes:

[0023] P21: Read the fixed monitoring data set of the first-level fixed monitoring points; P22: Perform carbon emission clustering on the fixed monitoring data set to generate carbon emission clustering results; P23: Perform monitoring coverage weakness analysis in the carbon emission clustering results to establish real-time weakness concerns; P24: Generate real-time location concerns based on the carbon emission clustering results; P25: Establish the mobile monitoring path after compensation based on the real-time weakness concerns, the real-time location concerns, and the carbon emission concerns fitting results.

[0024] It should be understood that the carbon emission focus fitting for the target area based on the existing digital twin model uses real-time, dynamically updated environmental parameters as input, including carbon emission concentrations at fixed monitoring points, regional wind speed and direction, temperature and humidity, terrain structure, building shielding characteristics, and a list of potential emission sources. By modeling the spatiotemporal evolution of carbon concentrations within the region, it identifies areas of abnormal carbon emission concentration and their boundaries, and establishes a dynamic spatial focus map of carbon emission hotspots. Based on this fitting result, an efficient mobile monitoring mechanism can be further constructed to enable flexible supplementary measurements in areas that are not fully covered or cannot respond in a timely manner by the fixed monitoring network, thereby improving the response range and temporal resolution of the overall monitoring system.

[0025] During the specific implementation process, the fixed monitoring data set uploaded by the first-level fixed monitoring points is first read and sorted. This data set covers the carbon gas concentration collected by each monitoring point within the preset time window (such as 、 , etc.), environmental meteorological parameters (wind speed, wind direction, temperature and humidity), along with corresponding spatial coordinates and timestamps, thus forming a multidimensional monitoring data set with geographic tags and time series characteristics. Cluster analysis is then performed on this data set, using algorithms such as K-Means, hierarchical clustering, and DBSCAN. Based on spatial proximity and carbon concentration similarity, the target area is divided into several sub-regions with similar carbon emission levels, generating carbon emission clustering results. This clustering result not only reveals the local characteristics and trend boundaries of carbon emissions within the region, but also provides data support for the subsequent identification of monitoring blind spots and areas of concern.

[0026] Furthermore, a monitoring coverage weakness analysis was conducted for each subregion. This involved overlaying and comparing the cluster boundaries with the coverage of currently fixed monitoring points, and calculating the relationship between the density of monitoring points and the rate of change of carbon concentration within each subregion. If a cluster region experienced significant carbon concentration fluctuations and a sparse monitoring population, this region was marked as a weak monitoring coverage area and designated a real-time weak focus area. Furthermore, representative coordinate points were extracted at the cluster center, carbon concentration peak locations, and boundaries with frequent fluctuations to construct real-time location focus points.

[0027] Furthermore, to establish a mobile monitoring path that meets the supplementary monitoring needs, the system integrates real-time weak focus areas and real-time location focus points based on the generated carbon emission focus fitting results, and constructs a path through a path planning algorithm. During the path generation process, factors such as monitoring priority, spatial coverage efficiency, path length, monitoring frequency, and geographical accessibility (such as whether it is a drone flight restricted area or ground obstacle area) are comprehensively considered to optimize the path and obtain the optimal mobile monitoring path map. This path is used to guide monitoring equipment with mobile capabilities (such as drones, inspection robots, or portable devices) to cruise, stay, or loop back for sampling in sequence within a specified time period. A second layer of mobile monitoring points is deployed at key points along the path or in high-frequency change areas to collect high-frequency, high-spatial-resolution carbon emission data, realizing dynamic reinforcement of the fixed monitoring system.

[0028] Furthermore, step P25 of the embodiment of the present application further includes:

[0029] P25-1: Use the real-time weak concern and the real-time location concern to compensate for the carbon emission concern fitting results, and establish a collection location set, which has location importance and location time limit concern identifiers; P25-2: Configure the maximum number of mobile monitoring devices; P25-3: Within the maximum number of devices, execute the mobile monitoring device to perform collection adaptation optimization of the collection location set, and generate a collection adaptation optimization result; P25-4: Establish the mobile monitoring path based on the collection adaptation optimization result.

[0030] Optionally, on the basis of executing mobile monitoring path planning, a fusion compensation of multi-source attention results and a path adaptation mechanism under resource constraints can be introduced to achieve priority coverage of key carbon emission areas and efficient sampling scheduling under the constraints of limited monitoring equipment resources, thereby improving the feasibility of path generation and the overall operating efficiency of the system.

[0031] First, using the real-time weak focus areas and real-time location focus points generated above, the carbon emission focus fitting results obtained through the digital twin model are compensated in both spatial and temporal dimensions to establish a collection location set. The collection location set refers to a group of spatial points identified by the system as requiring key supplementary measurements or dynamic coverage, and each location is assigned a location importance identifier and a location time limit focus identifier. Among them, the location importance is used to characterize the contribution of the sampling point to the inversion of the carbon emission status of the entire region, which is related to the historical concentration volatility, clustering weight or downstream influencing factors of the location; the location time limit focus indicates that the data collection at the location is time-sensitive, such as rapidly changing emission hotspots or areas greatly affected by meteorological interference. Collection must be completed within a specific time window to ensure data validity and timeliness.

[0032] Then, based on the current availability of available monitoring resources, a maximum number of mobile monitoring devices is configured. This sets the total number of mobile monitoring terminals that can simultaneously participate in task scheduling during the current monitoring cycle. This limit can be dynamically adjusted based on the remaining device battery, operating radius, task priority, or scheduling strategy, and is input as a constraint into the subsequent path optimization model.

[0033] Under the premise of limited number of devices, the collection location set is optimized by performing collection adaptation, that is, under the constraint of the number of devices, using heuristic search algorithms (such as ), integer linear programming models, genetic algorithms, particle swarm optimization, and other multi-objective optimization algorithms jointly solve the allocation relationship between each mobile device and collection point, path coverage path, energy consumption cost, and time window matching, generating a collection adaptation optimization result. This result clearly specifies the list of points, sampling order, and path trajectory that each device should cover within the mission cycle, and maximizes coverage of high-weight collection points while meeting path length and device capacity constraints.

[0034] Ultimately, based on the collected, adapted, and optimized results, one or more practical, executable mobile monitoring paths are established and output. These paths not only meet the objectives of shortest path, optimal time, or comprehensive coverage, but also possess deployable features such as high device capability matching and strong data timeliness. This path is distributed to each mobile terminal device in real time and can be dynamically adjusted or adaptively optimized during execution based on real-time feedback data. This creates a highly efficient, low-latency, and wide-coverage mobile carbon emissions monitoring mechanism, further improving the collaborative coverage capabilities of the fixed + mobile dual-layer network.

[0035] Furthermore, step P25-3 of the embodiment of the present application further includes:

[0036] P25-31: Establish a number of mobile monitoring devices to enable penalties; P25-32: Within the limit of the number of devices, execute path planning covering the collection location set, and evaluate the path fitness through location importance, location time limit attention mark, and number-enabled penalties, and establish a fitness evaluation result that is mapped to the path; P25-33: Path screening is performed through the fitness evaluation results to establish a collection adaptation optimization result.

[0037] Specifically, the process of establishing mobile monitoring paths can be further refined. First, a penalty mechanism for the number of mobile monitoring devices activated is established. This involves setting a penalty coefficient for the number of devices actually scheduled, forming a constraint function for device activation behavior. This penalty mechanism aims to avoid excessive resource utilization, which leads to energy waste and increased scheduling complexity. Based on the ratio of the number of activated devices to the maximum device capacity, and incorporating factors such as device operating costs, battery remaining, and deployment risk, a nonlinear or piecewise penalty function is established as one of the key parameters for subsequent path evaluation.

[0038] Then, within the determined limit of the number of devices, a multi-objective path planning calculation is performed on the path set covering the current collection location set. The path planning process uses a heuristic search algorithm (such as , genetic algorithms, simulated annealing, etc.), based on the shortest path cost function, combines the location importance and location time limit attention flags of the sampling points covered on each path as path priority weights. Based on this, a path fitness evaluation index system is established, which comprehensively considers the following three core factors: first, the weighted sum of the high-importance points covered within the path; second, whether the path sampling time window meets the time limit requirements of all locations; and third, whether the number of devices required for the path imposes a high penalty value. These factors are combined to form a fitness evaluation function, which is used to quantitatively score each candidate path, forming a one-to-one mapping between path and fitness, namely the fitness evaluation result of the path mapping.

[0039] Finally, based on the fitness evaluation results, all candidate paths are screened and retained to select the paths with the highest global fitness under the current constraints. These paths are then output as the final collection and adaptation optimization results. For example, a fixed threshold method (retaining paths with a fitness greater than the threshold), a Pareto optimality method (retaining the optimal solution for multi-objective equilibrium), or a dynamic hierarchical selection mechanism (preferentially retaining paths covering high-priority sampling points) can be used to ensure that the output paths have high task completion rates, reasonable resource consumption levels, and good execution stability.

[0040] P30: After the target area is monitored by the first-layer fixed monitoring points and the second-layer mobile monitoring points, a carbon emission data network is established.

[0041] Optionally, during the monitoring process of the target area, the first-tier fixed monitoring points and the second-tier mobile monitoring points work together to collect carbon emission data. Fixed monitoring points are distributed according to a pre-set grid, continuously and stably collecting carbon emission data at their locations. This data includes but is not limited to carbon emission concentration, emission rate, monitoring timestamp, and geographic location information. Mobile monitoring points, based on the optimized mobile monitoring path, move flexibly within the target area to conduct supplementary monitoring of key locations and areas with weak monitoring, also collecting data such as carbon emission concentration and emission rate, and recording the monitoring time and specific location.

[0042] The collected data is transmitted in real time to a data processing center via wireless communication technologies (such as 4G, 5G, and NB-IoT) or wired communication methods (such as Ethernet). At the data processing center, data from both fixed and mobile monitoring points undergoes preprocessing, including data cleaning, format unification, and outlier removal. Data cleaning aims to remove erroneous data caused by factors such as equipment failure and signal interference; format unification converts data collected from different monitoring points into a unified format for easier processing; and outlier removal prevents extreme data from impacting overall analysis results.

[0043] The preprocessed data will be integrated into the carbon emissions data network. The carbon emissions data network is a time-series data distribution set that records carbon emissions data from various monitoring points within the target area at different points in time, using time as the axis. This network uses data fusion technology to combine data from fixed and mobile monitoring points to form a comprehensive and dynamic view of carbon emissions data. During the data fusion process, algorithms such as weighted averaging and Kalman filtering can be used to integrate data from different monitoring points to improve data accuracy and reliability. For example, data from the same location within a similar time period can be weighted averaged, assigning different weights based on the accuracy and reliability of the monitoring points, to obtain more accurate carbon emissions data.

[0044] The carbon emissions data network will also conduct spatiotemporal analysis of the data. Spatially, using Geographic Information System (GIS) technology, carbon emissions data will be combined with geographic information to generate carbon emissions distribution maps, visually demonstrating the spatial distribution characteristics of carbon emissions within the target area. Temporally, carbon emissions data from the same monitoring point at different times will be analyzed to create a carbon emissions time series curve, reflecting the dynamic trends of carbon emissions. This spatiotemporal analysis can identify high-value carbon emission areas and periods, providing data support for subsequent carbon emission tracing, equipment matching analysis, and early warning.

[0045] Furthermore, after the carbon emission data network is established, the embodiment of the present application further includes step P30a, which further includes:

[0046] P31a: Performing carbon emission early warning analysis on the carbon emission data network and establishing early warning associated areas; P32a: Reporting carbon emission anomalies based on the early warning associated areas.

[0047] In a possible embodiment of the present application, after completing the construction of the carbon emission data network, step P30a can be continued to realize carbon emission early warning analysis and active reporting of abnormal information based on the data network, thereby extending the monitoring results from the static data level to the dynamic response mechanism, and building an intelligent environmental supervision system with autonomous perception and active alarm capabilities.

[0048] First, a carbon emissions early warning analysis is conducted within the established carbon emissions data network. Using real-time monitoring data from the network as input, combined with historical monitoring data, regional emission background models, meteorological impact models, and established emission risk thresholds, trends and risk assessments are performed for carbon emissions at each node and its adjacent regions. This early warning analysis focuses not only on absolute carbon concentration violations but also on multi-dimensional indicators such as short-term rate of change, spatial diffusion trends, and deviations from airflow simulation models. Real-time identification of emission anomalies is achieved by employing multi-level threshold models (e.g., general warning, strong warning, and emergency warning) or machine learning models (e.g., time series anomaly detection and LSTM prediction models).

[0049] After completing the early warning analysis, a further step is to establish an early warning correlation zone. This zone not only covers the core location where abnormal emission concentrations occur, but also deduces the potential extended range of carbon emissions by predicting the spatiotemporal diffusion path of carbon emissions, combined with meteorological data (wind direction and speed), building shielding structures, topographical undulations, and other environmental factors. This creates a dynamic correlation block centered on the core abnormal point. For example, Geographic Information System (GIS) technology can be used to combine carbon emission data to generate a carbon emission distribution map, which can be used to intuitively identify high-emission areas.

[0050] Subsequently, based on the results of the aforementioned warning association area construction, the carbon emission anomaly reporting operation is completed. This reporting process supports various triggering mechanisms, including periodic reporting, immediate reporting triggered by threshold crossing, and reporting based on mutation rate detection. Reporting content is standardized to generate event objects, including but not limited to: anomaly occurrence time, anomaly type, warning level, impact range, core emission point number, monitoring data summary, deviation rate from historical average, etc., and is pushed to the supervision platform, industrial equipment control system, or third-party environmental platform through the platform interface. If necessary, this anomaly report can also be linked to other modules within the system (such as the path reconstruction module and the inversion analysis module) to achieve subsequent automated response processing.

[0051] P40: Based on the digital twin model, perform airflow simulation in the target area, perform source tracing and inversion according to the airflow simulation results and the carbon emission data network, and establish source tracing and inversion results.

[0052] Furthermore, step P40 in this embodiment of the present application further includes:

[0053] P41: Input the carbon emission data network into the feature extraction channel, perform feature extraction, and establish feature extraction results, including: a: read the carbon concentration value of continuous time nodes for each position point, calculate the time derivative of the carbon concentration value, and establish a local time series gradient feature; b: construct a spatial gradient field through spatial interpolation of the local time series gradient features of all position points, and establish a spatial gradient distribution feature; c: perform gradient change feature extraction based on the local time series gradient features and the spatial gradient distribution features, establish key gradient features, and output the key gradient features as feature extraction results; P42: Perform source tracing inversion based on the feature extraction results and the airflow simulation results.

[0054] It should be understood that based on the digital twin model, high-precision airflow simulation is carried out on the air flow in the target area, and the simulation results are combined with the established carbon emission data network to perform carbon emission source tracing and inversion operations to determine the possible sources of abnormal carbon emission concentrations and their diffusion paths, thereby realizing reverse tracking of pollution results.

[0055] First, based on the building geometry, terrain, thermal environment, and real-time meteorological parameters (such as wind speed, direction, temperature, and humidity) in the digital twin model, computational fluid dynamics (CFD) simulation algorithms or wind field simulation methods based on a grid particle model are used to perform three-dimensional spatial modeling of the airflow state within the target area, generating high-resolution wind speed vector fields and airflow direction fields. These airflow simulation results provide the driving force for subsequent inversion calculations of carbon concentration changes and movement trends.

[0056] Furthermore, the constructed carbon emissions data network is input into the feature extraction channel, and a series of spatiotemporal gradient feature extraction operations are performed. For example, for each monitoring location, the carbon concentration measurements at multiple consecutive time nodes are read. The rate of change of concentration at that point in the time dimension is calculated using a differential or smoothed derivative algorithm to form a local temporal gradient feature at that point, which reflects the rapid growth or decay trend of carbon concentration at that point. Then, spatial interpolation (such as kriging interpolation or inverse distance weighted method) is performed on the temporal gradient values ​​of all location points at the spatial level to form a continuous spatial gradient field, that is, a spatial distribution map of the carbon concentration change rate in different regions, thereby constructing the overall spatial gradient distribution feature.

[0057] On this basis, the two types of gradient information are integrated to analyze the coordination and anomalies of gradient changes in time and space, identifying key gradient features that represent the propagation or possible sources of emission anomalies. This process can be combined with gradient convergence point detection, streamline backtracking analysis, or high-order derivative feature analysis methods to dynamically extract the diffusion center of local emission peaks and output this result as a feature extraction result.

[0058] Finally, the above-mentioned key gradient feature results are used in conjunction with the airflow simulation output to perform joint modeling and carbon emission source inversion. In this process, the gradient change direction of the carbon concentration is compared with the wind field simulation results in a vector direction, and a set of inversion equations is established in combination with the concentration change rate. Through reverse path tracing methods (such as reverse particle tracking and source model regularization solution), the possible starting point and path of the carbon emission anomaly are inferred and output as a structured source inversion result, including core fields such as origin coordinates, inversion path, time window, and credibility score. The source inversion results will provide a scientific basis for subsequent equipment matching analysis and carbon emission tracking and early warning, helping to achieve effective management and control of carbon emissions in the target area.

[0059] Furthermore, the embodiment of the present application further includes step P40a, which further includes:

[0060] P41a: Establish an inversion adaptation pattern database for instantaneous emissions, continuous emissions, and intermittent emissions; P42a: When performing source tracing inversion, use the inversion adaptation pattern database to perform carbon emission data network matching, and perform source tracing inversion based on the inversion adaptation pattern matching results and airflow simulation results.

[0061] Optionally, in order to improve the accuracy and adaptability of carbon emission source tracing and inversion, after completing the basic inversion based on airflow simulation and gradient feature extraction, the emission behavior pattern recognition and inversion adaptation mechanism can be introduced. By constructing an emission characteristic pattern database and matching strategy, the inversion accuracy under complex emission types and the source differentiation capability under multi-source emission situations can be improved.

[0062] First, an inversion adaptation pattern database for instantaneous emissions, continuous emissions, and intermittent emissions is constructed. This database classifies and models a large number of historical emission event samples, summarizes the regular characteristics of different types of emission events in terms of carbon concentration temporal changes, spatial diffusion paths, gradient characteristic structures, etc., and establishes corresponding inversion adaptation templates. Among them, the instantaneous emission pattern corresponds to the scenario of a large amount of carbon gas released in a short period of time, and is characterized by a rapid increase in concentration in a very short time and a clear diffusion wave front; the continuous emission pattern is suitable for scenarios where industrial equipment or pipelines release carbon gas stably for a long time, and is characterized by a high concentration level but a gentle change, and a relatively stable spatiotemporal gradient; the intermittent emission pattern is more common in periodically operating equipment, and is characterized by regular concentration fluctuations within a certain time period, with periodic temporal characteristics and local spatial aggregation. Each emission pattern is associated with the corresponding typical concentration change curve, spatial gradient morphology, propagation time window, wind field disturbance response model and other information in the database for matching and adaptation in the subsequent tracing process.

[0063] After the database is built, that is, during the carbon emission source inversion process, the actual observation data in the currently constructed carbon emission data network is first matched and identified with the various emission patterns in the inversion adaptation pattern database. This matching process can comprehensively judge the emission pattern that best matches the current observation situation based on multi-dimensional indicators such as time series trend similarity (such as DTW dynamic time warping), gradient distribution consistency measurement (such as structural similarity index), and wind field response behavior consistency comparison. After identifying the most suitable emission pattern, the typical diffusion characteristics, response delay parameters, and reverse path morphology contained in the pattern are introduced into the inversion calculation model as supplementary constraints.

[0064] Subsequently, the inversion adaptation pattern matching results were combined with existing airflow simulation results, key gradient features, and path inversion equations to perform a joint modeling. High-precision source tracing inversion was then re-performed through difference compensation, path adjustment, and credibility weighting. Compared to traditional methods, this joint inversion result can more effectively correct for systematic deviations in the inversion path caused by differences in emission patterns, improving the ability to identify multiple types of emission sources and the accuracy of source location.

[0065] P50: Perform equipment matching analysis in the target area based on the traceability inversion results, establish equipment positioning results, and establish carbon emission tracking and early warning based on the equipment positioning results.

[0066] Furthermore, step P50 in the embodiment of the present application further includes:

[0067] P51: Obtain the carbon emission data of the equipment calibration working condition in the target area; P52: Use the traceability inversion results to adapt and match the carbon emission data of the equipment calibration working condition; P53: If the adaptation and matching results meet the first constraint condition, then after the enterprise authorization and permission, read the working data of the corresponding equipment, and perform matching verification based on the working data to establish the equipment positioning result.

[0068] Specifically, based on the traceability inversion results obtained in the above steps, further equipment matching analysis and positioning identification are carried out in the target area to achieve accurate traceability of carbon emission sources and identification of responsible parties, and accordingly establish a targeted carbon emission tracking and early warning mechanism.

[0069] First, obtain calibrated operating carbon emissions data for all registered or filed emission-related equipment within the target area. This data includes baseline carbon emissions values ​​for each device under different operating conditions, emission rate characteristic curves, carbon emission factors per unit of energy consumption, and emission cycles and time series characteristics corresponding to operating modes. Data sources can include enterprise self-monitoring systems, environmental protection department filings, and performance parameters provided by equipment manufacturers. The data format must conform to the system's unified standards to facilitate subsequent automated comparison and analysis.

[0070] Next, based on the generated source inversion results, including the coordinates of the anomaly source point, spatiotemporal diffusion trajectories, emission intensity characteristics, and key gradient indicators, an adaptation and matching operation is performed on the calibration operating condition data of each device. This matching process is implemented based on a multi-dimensional comparison strategy. For example, the relative error between the emission intensity amplitude and the standard emission level is calculated; the shape similarity analysis of the time series concentration variation characteristics and the operating condition emission curve is performed (using indicators such as correlation coefficient, DTW, and structural similarity); and the spatial compatibility is determined by combining indicators such as the geographical distance between the device and the inversion results and the overlap of wind field paths.

[0071] After completing the preliminary matching, if the matching result of a certain device meets the preset first constraint condition (such as: the shape similarity exceeds the threshold, the spatiotemporal matching rate is higher than the set value, the relative error of the emission intensity is less than the specified limit, etc.), the device is judged to be a possible emission source, and the real-time or historical working data of the device is further retrieved under the premise of authorization and permission from the enterprise. The working data may include the operating time period, load status, start and stop records, production process parameters, etc. of the equipment. The data is compared in depth with the emission time series information obtained by inversion, and a matching verification analysis is carried out from the perspectives of the logical consistency of workload and emission intensity, the overlap of the operating cycle and the abnormal time point, etc. If the verification result further meets the set multi-level matching conditions, the device is confirmed to be the directly responsible device for this carbon emission event, and a device positioning result with device number, positioning coordinates, emission behavior characteristics and matching credibility is generated.

[0072] Based on the equipment positioning results, carbon emission tracking warning information is immediately generated and released. The warning information not only includes the abnormal location and time period, but can also be associated with the responsible equipment identification, emission intensity, warning level and disposal suggestions, etc., to form an intelligent warning output with operational significance for enterprises or regulatory units, and support rapid response to subsequent emission control or automated intervention links.

[0073] Furthermore, step P52 of the embodiment of the present application further includes:

[0074] P52-1: If the adaptation and matching result cannot meet the first constraint condition, a joint equipment emission constraint is established; P52-2: Joint equipment adaptation and matching of the traceability inversion result is performed according to the joint equipment emission constraint to establish an equipment positioning result.

[0075] In a possible embodiment of the present application, in order to cope with the complex situation where carbon emission behavior may be caused by the coordinated or superimposed emissions of multiple devices, a joint emission adaptation mechanism can be introduced when single device matching fails to hold, so as to enhance the system's adaptability and positioning accuracy in a multi-source emission environment.

[0076] First, the preliminary matching results are judged. If the adaptation matching results of a single device cannot meet the first constraint condition (that is, it cannot simultaneously meet the thresholds set by the system in terms of emission intensity, temporal characteristics, spatial matching, etc.), it is inferred that the current emission behavior may be caused by two or more devices emitting together or alternatingly. At this time, the equipment positioning process is not terminated directly, but the joint matching analysis path is entered, and a joint equipment emission constraint model is established accordingly. This constraint model takes the equipment combination as a unit and defines the theoretical carbon concentration synthesis result within the target time and space range after the emissions of multiple devices are superimposed. Specific constraint parameters include: the maximum allowable emission intensity of the participating equipment, the overlapping relationship of emission time, the overlapping area of ​​spatial diffusion impact, the probability of coordination between equipment (which can be based on historical joint operation records), and its distance weight function near the inversion source point.

[0077] Subsequently, based on the above-mentioned joint equipment emission constraints, a joint equipment adaptation and matching analysis is performed on the source inversion results. During this analysis, the emission operating condition data of all equipment or equipment combinations in the target area are combined and iterated to simulate the synthetic impact of their joint emissions on the local spatiotemporal carbon concentration changes, and a full-dimensional comparison is performed with key gradient features, path diffusion patterns, airflow disturbance trajectories and other elements in the source inversion results. Through the multi-objective fitting function, the minimum residual between the concentration simulation value and the actual measurement value of each combination is evaluated, and the morphological consistency and change trend consistency of the fitting curve are scored, and finally the optimal equipment combination is determined as the suspected joint emission source.

[0078] When a combination meets the set joint adaptation constraints (such as the minimum sum of squared residuals, fitting similarity above the threshold, high credibility score, etc.), the combination will be output as the final device positioning result. At the same time, it will be clearly marked that the emission behavior is jointly generated by multiple devices, and detailed information such as the joint emission intensity ratio, the contribution score of each device, and the matching confidence level will be attached.

[0079] By introducing the above steps, a dynamic adaptation and intelligent collaborative reasoning mechanism is realized in the case of single emission source matching failure, which significantly improves the problem closure capability, source identification comprehensiveness and supervision accuracy in actual complex carbon emission scenarios.

[0080] In summary, the embodiments of the present application have at least the following technical effects:

[0081] This application uses digital twin modeling to construct a virtual environment for the target area. Fixed monitoring points are arranged in a grid based on monitoring accuracy. Mobile monitoring paths are generated based on carbon emission focus fitting, forming a carbon emissions data network covering the entire area. Source inversion is then performed based on airflow simulation and the data network. Device calibration data is matched to locate the source, ultimately achieving dynamic tracking and early warning of carbon emissions. This achieves the technical effect of achieving high-precision traceability and real-time tracking and early warning of carbon emission sources by building a multi-level monitoring network and introducing airflow simulation and emission feature matching mechanisms.

[0082] Example 2, based on the same inventive concept as the dynamic tracking and early warning method of intelligent carbon emissions in the above embodiment, Figure 2 As shown, this application provides a dynamic tracking and early warning system for intelligent carbon emissions. The system and method embodiments in the embodiments of this application are based on the same inventive concept. The system includes:

[0083] The fixed monitoring point distribution module 11 is used to perform digital twin modeling of the target area, configure the grid granularity according to the monitoring accuracy, perform grid segmentation of the target area, and distribute the first-level fixed monitoring points according to the grid segmentation results.

[0084] The mobile monitoring point configuration module 12 is used to use the digital twin model to perform carbon emission attention fitting in the target area, establish a mobile monitoring path according to the carbon emission attention fitting results, and configure the second-layer mobile monitoring points through the mobile monitoring path.

[0085] The carbon emission data network establishment module 13 is used to establish a carbon emission data network after the target area is monitored by the first layer of fixed monitoring points and the second layer of mobile monitoring points.

[0086] The source tracing inversion module 14 is used to simulate the airflow in the target area based on the digital twin model, perform source tracing inversion according to the airflow simulation results and the carbon emission data network, and establish a source tracing inversion result.

[0087] The carbon emission tracking and early warning module 15 is used to perform equipment matching analysis in the target area according to the tracing and inversion results, establish equipment positioning results, and establish carbon emission tracking and early warning according to the equipment positioning results.

[0088] Furthermore, the mobile monitoring point configuration module 12 is further configured to perform the following steps:

[0089] Read the fixed monitoring data set of the first-level fixed monitoring points; perform carbon emission clustering on the fixed monitoring data set to generate a carbon emission clustering result; perform monitoring coverage weakness analysis in the carbon emission clustering result to establish a real-time weakness concern; generate a real-time location concern based on the carbon emission clustering result; establish the mobile monitoring path after compensating the real-time weakness concern, the real-time location concern, and the carbon emission concern fitting results.

[0090] Furthermore, the mobile monitoring point configuration module 12 is further configured to perform the following steps:

[0091] The real-time weak concern and the real-time location concern are used to compensate for the carbon emission concern fitting result, and a collection location set is established, wherein the collection location set has location importance and location time limit concern identifiers; the maximum number of mobile monitoring devices is configured; within the maximum number of devices, the mobile monitoring device is executed to perform collection adaptation optimization of the collection location set to generate a collection adaptation optimization result; and the mobile monitoring path is established according to the collection adaptation optimization result.

[0092] Furthermore, the mobile monitoring point configuration module 12 is further configured to perform the following steps:

[0093] Establish a number of mobile monitoring devices to enable penalties; within the limit of the number of devices, execute path planning that covers the collection location set, and evaluate the path fitness through location importance, location time limit attention mark, and number-enabled penalties, and establish a fitness evaluation result mapped to the path; use the fitness evaluation result to screen the path to establish a collection adaptation optimization result.

[0094] Furthermore, the carbon emission data network establishment module 13 is further configured to perform the following steps:

[0095] Perform carbon emission early warning analysis on the carbon emission data network and establish early warning associated areas; and report carbon emission anomalies based on the early warning associated areas.

[0096] Furthermore, the source tracing and inversion module 14 is further configured to perform the following steps:

[0097] The carbon emission data network is input into the feature extraction channel, feature extraction is performed, and feature extraction results are established, including: a: reading the carbon concentration values ​​of continuous time nodes for each position point, calculating the time derivative of the carbon concentration value, and establishing a local temporal gradient feature; b: constructing a spatial gradient field through spatial interpolation of the local temporal gradient features of all position points, and establishing a spatial gradient distribution feature; c: performing gradient change feature extraction based on the local temporal gradient features and the spatial gradient distribution features, establishing a key gradient feature, and outputting the key gradient feature as a feature extraction result; and performing source tracing inversion based on the feature extraction results and the airflow simulation results.

[0098] Furthermore, the source tracing and inversion module 14 is further configured to perform the following steps:

[0099] Establish an inversion adaptation pattern database for instantaneous emissions, continuous emissions, and intermittent emissions; when performing source tracing inversion, use the inversion adaptation pattern database to perform carbon emission data network matching, and perform source tracing inversion based on the inversion adaptation pattern matching results and airflow simulation results.

[0100] Furthermore, the carbon emission tracking and early warning module 15 is further configured to perform the following steps:

[0101] Obtain the equipment calibration working condition carbon emission data in the target area; use the traceability inversion result to adapt and match the equipment calibration working condition carbon emission data; if the adaptation and matching result meets the first constraint condition, then after the enterprise authorization and permission, read the working data of the corresponding equipment, and perform matching verification based on the working data to establish the equipment positioning result.

[0102] Furthermore, the carbon emission tracking and early warning module 15 is further configured to perform the following steps:

[0103] If the adaptation and matching result cannot satisfy the first constraint condition, a joint device emission constraint is established; and joint device adaptation and matching of the source tracing inversion result is performed according to the joint device emission constraint to establish a device positioning result.

[0104] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0105] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

[0106] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. A dynamic tracking and early warning method for intelligent carbon emissions, characterized by: The method comprises: Execute digital twin modeling of the target area, configure the grid granularity according to the monitoring accuracy, perform grid segmentation of the target area, and distribute the first-level fixed monitoring points according to the grid segmentation results; Use the digital twin model to fit the carbon emission concerns of the target area, establish a mobile monitoring path based on the carbon emission concern fitting results, and configure the second-layer mobile monitoring points through the mobile monitoring path; After monitoring the target area by the first-tier fixed monitoring points and the second-tier mobile monitoring points, a carbon emission data network is established; Perform airflow simulation in the target area based on the digital twin model, perform source tracing and inversion based on the airflow simulation results and the carbon emission data network, and establish source tracing and inversion results, including: Inputting the carbon emission data network into a feature extraction channel, performing feature extraction, and establishing feature extraction results include: a: Read the carbon concentration values ​​of consecutive time nodes at each location point, calculate the time derivative of the carbon concentration value, and establish the local time series gradient feature; b: The local temporal gradient features of all position points are used to construct the spatial gradient field through spatial interpolation to establish the spatial gradient distribution features; c. extracting gradient change features based on the local temporal gradient features and the spatial gradient distribution features, establishing key gradient features, and outputting the key gradient features as feature extraction results; Performing source tracing inversion based on the feature extraction results and the airflow simulation results; Perform equipment matching analysis in the target area based on the traceability inversion results, establish equipment positioning results, and establish carbon emission tracking and early warning based on the equipment positioning results.

2. The intelligent carbon emission dynamic tracking and early warning method according to claim 1 is characterized in that: The step of establishing a mobile monitoring path based on the carbon emission attention fitting result and configuring the second-layer mobile monitoring points through the mobile monitoring path includes: Reading the fixed monitoring data set of the first-level fixed monitoring points; Performing carbon emission clustering on the fixed monitoring data set to generate a carbon emission clustering result; Conduct monitoring coverage weakness analysis in carbon emission clustering results and establish real-time weakness focus; generating real-time location concerns based on the carbon emission clustering results; The mobile monitoring path is established after compensation based on the fitting results of the real-time weakness concern, the real-time location concern, and the carbon emission concern.

3. The intelligent carbon emission dynamic tracking and early warning method according to claim 2, characterized in that: The establishing of the mobile monitoring path after compensation based on the fitting results of the real-time weakness concern, the real-time location concern, and the carbon emission concern includes: Compensating the carbon emission concern fitting result by using the real-time weak concern and the real-time position concern to establish a collection location set, wherein the collection location set carries location importance and location time limit concern identifiers; Configure the maximum number of mobile monitoring devices; Within the limit of the number of devices, execute the collection adaptation optimization of the collection location set by the mobile monitoring device and generate the collection adaptation optimization result; The mobile monitoring path is established according to the acquisition adaptation optimization result.

4. The intelligent carbon emission dynamic tracking and early warning method according to claim 3 is characterized in that: The step of executing the collection adaptation optimization of the collection location set by the mobile monitoring device within the limit number of devices and generating the collection adaptation optimization result includes: Establish penalties for the number of mobile monitoring devices enabled; Within the limit of the number of devices, execute path planning that covers the collection location set, and evaluate the path fitness through location importance, location time limit attention mark, and quantity activation penalty, and establish the fitness evaluation result mapped with the path; Path screening is performed based on the fitness evaluation results to establish a collection adaptation optimization result.

5. The intelligent carbon emission dynamic tracking and early warning method according to claim 1, characterized in that: The device matching analysis in the target area is performed based on the source tracing inversion result to establish the device positioning result, including: Obtain carbon emission data of equipment in the target area under calibrated working conditions; Using the traceability inversion results to adapt and match the carbon emission data of the equipment calibration working condition; If the adaptation matching result satisfies the first constraint condition, then after the enterprise authorizes and permits, the working data of the corresponding device is read, and matching verification is performed based on the working data to establish the device positioning result.

6. The intelligent carbon emission dynamic tracking and early warning method according to claim 5, characterized in that: The adaption and matching of the carbon emission data of the equipment calibration working condition using the traceability inversion result includes: If the adaptation and matching result cannot satisfy the first constraint condition, then a joint equipment emission constraint is established; The joint device adaptation matching of the source tracing inversion result is performed according to the joint device emission constraint to establish a device positioning result.

7. The intelligent carbon emission dynamic tracking and early warning method according to claim 1, characterized in that: The tracing back and inversion based on the airflow simulation results and the carbon emission data network also includes: Establish an inversion adaptation model database for instantaneous emissions, continuous emissions, and intermittent emissions; When performing source tracing inversion, the inversion adaptation pattern database is used to perform carbon emission data network matching, and source tracing inversion is performed based on the inversion adaptation pattern matching results and the airflow simulation results.

8. The intelligent carbon emission dynamic tracking and early warning method according to claim 1, characterized in that: After the carbon emission data network is established, the following steps are also included: Conducting carbon emission early warning analysis on the carbon emission data network and establishing early warning associated areas; Abnormal carbon emissions are reported based on the warning associated areas.

9. Intelligent carbon emission dynamic tracking and early warning system, characterized by: The system comprises: A fixed monitoring point distribution module is used to perform digital twin modeling of the target area, configure the grid granularity according to the monitoring accuracy, perform grid segmentation of the target area, and distribute the first-level fixed monitoring points according to the grid segmentation results; A mobile monitoring point configuration module, which is used to use the digital twin model to perform carbon emission focus fitting in the target area, establish a mobile monitoring path based on the carbon emission focus fitting results, and configure the second-layer mobile monitoring points through the mobile monitoring path; A carbon emission data network establishment module, wherein the carbon emission data network establishment module is used to establish a carbon emission data network after monitoring the target area by the first layer of fixed monitoring points and the second layer of mobile monitoring points; A source tracing and inversion module, which is used to simulate the airflow in the target area based on the digital twin model, perform source tracing and inversion according to the airflow simulation results and the carbon emission data network, and establish a source tracing and inversion result, including: inputting the carbon emission data network into the feature extraction channel, performing feature extraction, and establishing a feature extraction result, including: a: reading the carbon concentration value of the continuous time node for each position point, calculating the time derivative of the carbon concentration value, and establishing a local temporal gradient feature; b: constructing a spatial gradient field through spatial interpolation of the local temporal gradient features of all position points, and establishing a spatial gradient distribution feature; c: performing gradient change feature extraction according to the local temporal gradient feature and the spatial gradient distribution feature, establishing a key gradient feature, and outputting the key gradient feature as a feature extraction result; performing source tracing and inversion according to the feature extraction result and the airflow simulation result; a carbon emission tracking and early warning module, which is used to perform equipment matching analysis in the target area according to the source tracing and inversion result, establish an equipment positioning result, and establish a carbon emission tracking and early warning according to the equipment positioning result.

Images