Regional atmospheric pollution and carbon emission reduction cooperative benefit evaluation method, system and equipment

Abstract

The invention discloses a regional atmospheric pollution and carbon emission reduction cooperative benefit evaluation method, system and device, and relates to the technical field of atmospheric pollution and carbon emission reduction, and the method comprises the steps: carrying out the evaluation of the regional policy scene parameters of a target region based on a greenhouse gas-atmospheric pollution cooperative effect model according to the regional policy scene parameters of the target region; determining a pollutant emission list and PM2.5 space distribution concentration prediction data; based on a machine learning algorithm, determining O3 spatial distribution concentration prediction data according to the pollutant emission list and the PM2.5 spatial distribution concentration prediction data; calculating health benefits by adopting an environmental benefit evaluation model according to the PM2.5 spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data; and based on a life value method, calculating economic benefits according to health benefits. The method is high in evaluation efficiency, more comprehensive in evaluation, high in precision and good in practicability.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of atmospheric pollution and carbon emission reduction, in particular to a regional atmospheric pollution and carbon emission reduction synergistic benefit evaluation method, system and equipment. BACKGROUND

[0002] The current technical system usually uses a macro scenario evaluation model (such as GAINS) to predict the concentration change of primary pollutants (such as PM 2.5 ), and combines an environmental benefit evaluation model (such as BenMAP-CE) to quantify its health and economic impact. However, there is a key technical gap in this evaluation chain: the macro model cannot simulate the generation process of the important secondary pollutant ozone (O3), and O3 is an indispensable indicator for evaluating air quality health hazards. If the impact of O3 is ignored in the evaluation, the comprehensive benefits of emission reduction will be seriously underestimated, which may mislead environmental decision-making.

[0003] To solve the problem of O3 concentration simulation, the existing technology has to rely on a chemical transport model with extremely complex calculation process and huge resource consumption. This scheme not only has low operation efficiency and high time cost, but also makes it difficult to efficiently and smoothly couple with the macro evaluation model, resulting in a fragmented evaluation process that cannot meet the real demand for rapid iteration and selection of multiple emission reduction scenarios. SUMMARY

[0004] The purpose of the present application is to provide a regional atmospheric pollution and carbon emission reduction synergistic benefit evaluation method, system and equipment, which has high evaluation efficiency, more comprehensive and high precision, and good practicality.

[0005] To achieve the above purpose, the present application provides the following scheme: In a first aspect, the present application provides a regional atmospheric pollution and carbon emission reduction synergistic benefit evaluation method, comprising: Based on a greenhouse gas-atmospheric pollution synergistic effect model, determining a pollutant emission inventory and PM 2.5 spatial distribution concentration prediction data according to regional policy scenario parameters of a target region; the regional policy scenario parameters are used to simulate a specific development path in the future; Based on a machine learning algorithm, determining O3 spatial distribution concentration prediction data according to the pollutant emission inventory and the PM 2.5 spatial distribution concentration prediction data; Using an environmental benefit evaluation model, calculating health benefits according to the PM 2.5 spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data; Based on the life value method, calculating economic benefits according to the health benefits.

[0006] Secondly, this application provides a regional air pollution and carbon emission reduction synergy benefit assessment system, which applies a regional air pollution and carbon emission reduction synergy benefit assessment method. The system includes: The GAINS model processing module is used to: determine pollutant emission inventories and PM2.5 levels based on the greenhouse gas-air pollution synergistic effect model and regional policy scenario parameters of the target area. 2.5 Spatial distribution concentration prediction data; the regional policy scenario parameters are used to simulate specific future development paths; The machine learning model processing module is used to: based on machine learning algorithms, and according to the pollutant emission inventory and the PM2.5... 2.5 Spatial distribution concentration prediction data, determine the spatial distribution concentration prediction data of O3; The BenMAP-CE model processing module is used to: employ an environmental benefit assessment model, based on the PM... 2.5 Based on the spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data, calculate the health benefits; based on the life value method, calculate the economic benefits according to the health benefits.

[0007] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a method for assessing the synergistic benefits of regional air pollution and carbon emission reduction.

[0008] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application first determines the pollutant emission inventory and PM2.5 based on the greenhouse gas-air pollution synergistic effect model and the regional policy scenario parameters of the target area. 2.5 Spatial distribution concentration prediction data will transform macro-level, qualitative environmental and energy policies into quantitative pollutant emission inventories and primary pollutant (PM2.5) data that can be used for subsequent scientific calculations. 2.5 O3 concentration data. Then, based on machine learning algorithms, predicted spatial distribution concentration data of O3 is determined. Through this process, PM2.5 can be learned and characterized more effectively. 2.5 The complex nonlinear mapping relationship between some pollutant emission data and O3 concentration yielded more stable and robust predictive performance than any single model, significantly improving prediction accuracy. Furthermore, the use of machine learning algorithms achieved orders-of-magnitude efficiency improvements and a significant reduction in computational costs. Finally, an environmental benefit assessment model was employed to calculate health benefits, and subsequently, economic benefits. This transformed abstract changes in air quality concentration into concrete public health impact indicators that are easily understood by the public and policymakers, enabling intuitive measurement and high practicality. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 This is an application environment diagram of the regional air pollution and carbon emission reduction synergistic benefit assessment method in one embodiment of this application.

[0011] Figure 2 This is a flowchart illustrating the method for assessing the synergistic benefits of regional air pollution and carbon emission reduction in one embodiment of this application.

[0012] Figure 3 This is a schematic diagram of a regional air pollution and carbon emission reduction synergy assessment system in one embodiment of this application.

[0013] Figure 4 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0015] This application provides a systematic assessment method for quantifying the synergistic benefits of regional air pollution control and carbon emission reduction, integrating macroeconomic policy assessment models, machine learning prediction models, and health benefit assessment models. Through the coupling and data flow between specific models, an efficient and complete assessment chain of "policy input - emission prediction - air quality response - health and economic benefit output" is constructed. In particular, it innovatively uses machine learning models to solve the problem of predicting the concentration of key pollutant (O3).

[0016] This application uses a lightweight and efficient machine learning model to replace the traditional bulky CTM, aiming to remove technical bottlenecks in the assessment chain and build an integrated solution that can conduct a complete, rapid, economical and scientific assessment of coordinated emission reduction policies.

[0017] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, this application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] The regional air pollution and carbon emission reduction synergistic benefit assessment method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 101 communicates with server 102 via a network. A data storage system can store the data that server 102 needs to process. The data storage system can be set up independently, integrated into server 102, or placed in the cloud or on another server. Terminal 101 can send regional policy scenario parameters and economic and energy data of the target area to server 102. After receiving the data, server 102 determines the pollutant emission inventory and PM2.5 concentration. 2.5 The system first obtains spatial distribution concentration prediction data, then calls a machine learning algorithm to determine the spatial distribution concentration prediction data for O3, and finally calculates the health and economic benefits. Server 102 can then feed back the obtained health and economic benefits to terminal 101. Furthermore, in some embodiments, the method for assessing the synergistic benefits of regional air pollution and carbon emission reduction can also be implemented independently by server 102 or terminal 101.

[0019] The terminal 101 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 102 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0020] In one exemplary embodiment, such as Figure 2 As shown, a method for assessing the synergistic benefits of regional air pollution and carbon emission reduction is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 102 as an example, the explanation includes the following steps 201 to 204.

[0021] Step 201: Based on the greenhouse gas-air pollution synergistic effect model, determine the pollutant emission inventory and PM2.5 emissions according to the regional policy scenario parameters of the target area. 2.5 Spatial distribution concentration prediction data; the regional policy scenario parameters are used to simulate specific future development paths.

[0022] In one embodiment, pollutant emission inventories and PM2.5 2.5 The process of determining spatially distributed concentration prediction data includes: (11) Obtain regional policy scenario parameters for the target area; the regional policy scenario parameters include at least: economic activity level data, energy structure data and penetration rate data of end-of-pipe pollution control technology; wherein, the penetration rate data of end-of-pipe control technology measures the proportion of facilities or production capacity that adopt "end-of-pipe control technology" in the entire economic system or a specific industry; end-of-pipe control technology refers to equipment or methods for treating pollutants after they are generated and before they are discharged into the environment.

[0023] (12) Call the Greenhouse Gas-Air Pollution Synergistic Effect Model (GAINS).

[0024] (13) Input the regional policy scenario parameters into the greenhouse gas-air pollution synergistic effect model to obtain the pollutant emission inventory and PM2.5. 2.5 Spatial distribution concentration prediction data. The pollutant emission inventory is one or more data files, including at least: carbon dioxide (CO2), sulfur dioxide (SO2), and nitrogen oxides (NOx) for target years under a specific future development path scenario. x The predicted emissions of PM2.5 can be used as a reference, and other greenhouse gases and air pollutants can be selected as needed. 2.5 Spatial distribution concentration prediction data represent the PM2.5 concentration in the target area for a target year under a specific future development path scenario. 2.5 The concentration.

[0025] Through the above steps, macro-level, qualitative environmental and energy policies (such as "increasing the proportion of clean energy") are transformed into quantitative pollutant emission inventories and primary pollutant (PM2.5) data that can be used for subsequent scientific calculations. 2.5 Concentration data.

[0026] Step 202: Based on machine learning algorithms, according to the pollutant emission inventory and the PM2.5 concentration... 2.5 Spatial distribution concentration prediction data, determining the spatial distribution concentration prediction data of O3; in one embodiment, this step includes the following processing: (21) Invoke a pre-trained ensemble machine learning model; the ensemble machine learning model is a Stacking ensemble learning model; the Stacking ensemble learning model selects one of XG Boost, Random Forest, Gradient Boosting Decision Tree, Light GBM, and Ada Boost as the base learner, and uses a resilient network with cross-validation as the meta-learner to integrate the prediction results of the base learners. The ensemble machine learning model internally embeds the PM (Programmable Array Module). 2.5 Nonlinear mapping relationship between concentration, emissions of other pollutants and O3 concentration.

[0027] (22) Extract pollutant emission data to be used from the pollutant emission inventory according to preset rules; wherein, other relevant data in the pollutant emission inventory may be selectively combined as input features, such as NO x Emissions. In other words, which specific data point is extracted is determined based on the input features of the ensemble machine learning model during its training process.

[0028] (23) The PM 2.5 Spatial distribution concentration prediction data and the pollutant emission data to be used are input into the integrated machine learning model to obtain O3 spatial distribution concentration prediction data. The O3 spatial distribution concentration prediction data can be in a gridded format, recording the spatial distribution concentration of ozone (O3) within the study area for the corresponding future target year.

[0029] In this step, machine learning technology was used to efficiently and cost-effectively solve the technical problem that traditional macroscopic models cannot directly predict the concentration of secondary pollutant O3, thereby extending the assessment chain from primary pollutants to secondary pollutants and opening up a key link for achieving a comprehensive benefit assessment.

[0030] While existing approaches employ simplified chemical mechanism models or traditional statistical regression methods to establish the relationship between pollutants and O3 concentrations, these methods suffer from limitations in predictive accuracy and reliability due to either oversimplification of physicochemical processes or difficulty in capturing the strong nonlinear characteristics of O3 formation. The Stacking ensemble learning model preferred in this application, by combining the advantages of multiple algorithms, typically achieves more stable and robust predictive performance than any single model. Therefore, compared to various alternatives, the technical approach proposed in this application achieves a better balance between evaluation efficiency, predictive accuracy, and implementation cost, making it a superior choice for the scientific evaluation of synergistic benefits.

[0031] Step 203: Using the BenMAP-CE environmental benefit assessment model, based on the PM2.5... 2.5 The health benefits are calculated using the spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data.

[0032] In one embodiment, population spatial distribution data and multi-disease benchmark mortality data are retrieved from a localized database; then, based on the health impact function built into the environmental benefit assessment model, combined with the PM2.5 concentration data... 2.5 Spatial distribution concentration prediction data and the aforementioned O3 spatial distribution concentration prediction data are used to perform health benefit calculations to obtain health benefit data, clearly listing the effects of PM2.5 on health benefits. 2.5 The number of all-cause deaths, cardiovascular disease deaths, and respiratory disease deaths avoided due to improved O3 concentration. The formula for calculating the health benefits is: .

[0033] in, The estimated health effects of changes in air pollutant concentrations, i.e., the number of premature deaths that can be avoided, correspond to the health benefits in this application, in units of persons; β is the relationship coefficient between pollutant concentration and health effects (i.e., the exposure-response relationship coefficient), which is a known parameter read from a localized database, such as "cardiovascular disease mortality rate per 100,000 people"; Including PM 2.5 Spatial distribution concentration changes and O3 spatial distribution concentration changes were compared with the PM2.5 concentration. 2.5 The spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data are calculated by comparing them with the baseline scenario concentration, with the unit being μg / m³. 3 Incidence represents the mortality rate for different diseases, which is a known quantity; POP represents the number of exposed people, which is a known population number corresponding to a specific grid area, read from a localized database.

[0034] This step transforms abstract changes in air quality concentration into concrete public health impact indicators that are easy for the public and policymakers to understand, serving as a bridge connecting environmental improvement and social well-being.

[0035] Step 204: Based on the Vital Values ​​(VSL) method, calculate the economic benefits according to the stated health benefits, clearly demonstrating the economic value corresponding to the health benefits brought about by improved air quality. In one embodiment, it is usually necessary to localize the Vital Values ​​(VSL) formula as follows: .

[0036] Subsequently, the adjusted Multiplying the health benefits by the economic benefits yields the final economic benefits: .

[0037] Where E represents economic benefits, in yuan; The life value, adjusted for regional income levels, is an intermediate calculation result. For health benefits; The baseline life value for the baseline year is a known constant; , denoted as the target year per capita income of the target region and the benchmark year per capita income of the benchmark region, both of which are known constants; e is the income elasticity coefficient, which is also a known constant.

[0038] The above steps provide crucial evidence for cost-benefit analysis in the final decision-making process. By monetizing health benefits, the overall value of the policy can be measured and compared more intuitively.

[0039] Based on the same inventive concept, this application also provides a system for implementing the methods described above. The solution provided by this system is similar to the solution described in the methods above; therefore, specific limitations in one or more system embodiments provided below can be found in the limitations of the methods described above, and will not be repeated here.

[0040] In an exemplary embodiment, a regional air pollution and carbon emission reduction synergistic benefit assessment system is provided, which applies the aforementioned regional air pollution and carbon emission reduction synergistic benefit assessment method, including: The GAINS model processing module is used to: determine pollutant emission inventories and PM2.5 levels based on the greenhouse gas-air pollution synergistic effect model and regional policy scenario parameters of the target area. 2.5 Spatial distribution concentration prediction data; the regional policy scenario parameters are used to simulate specific future development paths. This module incorporates a greenhouse gas-air pollution synergistic effect model, performs macro-scenario simulations, and outputs a pollutant emission inventory (including CO2, SO2, NO). x PM 2.5 (etc.) and PM 2.5 Concentration grid data serves to transform qualitative policies into quantitative emission and primary pollutant concentration data, providing a basis for subsequent assessments.

[0041] The machine learning model processing module is used to: based on machine learning algorithms, and according to the pollutant emission inventory and the PM2.5... 2.5 This module provides spatial distribution concentration prediction data for O3. It incorporates a pre-trained Stacking ensemble learning model that predicts O3 concentration through nonlinear mapping relationships. Its purpose is to efficiently and accurately address the technical challenge of traditional models being unable to directly simulate the concentration of secondary pollutant O3, thus expanding the scope of assessment.

[0042] The BenMAP-CE model processing module is used to: employ an environmental benefit assessment model, based on the PM... 2.5 The module uses spatial distribution concentration prediction data and O3 spatial distribution concentration prediction data to calculate health benefits; based on the value-of-life approach, it calculates economic benefits based on these health benefits. This module incorporates an environmental benefit assessment model (BenMAP-CE), which, combined with population and health data, performs health impact functions and economic calculations, outputting the number of premature deaths avoided and the economic value. Its function is to transform air quality data into health and economic indicators that are of concern to policymakers.

[0043] In one embodiment, such as Figure 3 As shown, the system also includes: The data input interface module is used to: receive regional policy scenario parameters (such as economic activity level, energy structure, and technology penetration rate), baseline vital statistics, baseline year per capita income, known population, relationship coefficients between pollutant concentration and health effects, and income elasticity coefficients for the target area, either input by the user or read from an external database; transmit the regional policy scenario parameters to the GAINS model processing module; and transmit the baseline vital statistics, baseline year per capita income, known population, relationship coefficients between pollutant concentration and health effects, and income elasticity coefficients to the BenMAP-CE model processing module. The function of this module is to provide initial data input for the entire assessment system, ensuring that the assessment is based on a specific region and policy scenario.

[0044] The data storage module is used to: store regional policy scenario parameters of the target area, the baseline vital value, the baseline year per capita income, the known population, the relationship coefficient between pollutant concentration and health effect, the income elasticity coefficient, the pollutant emission inventory, and the PM2.5 concentration. 2.5 Spatial distribution concentration prediction data, the O3 spatial distribution concentration prediction data, the health benefits, and the economic benefits, ensuring data traceability and the repeatability of the evaluation process.

[0045] The results output interface module is used to output the health benefits and economic benefits to the user in a visual or document format (such as tables or charts) to provide intuitive evaluation results and support decision analysis.

[0046] Regarding module connectivity: The data input interface module connects to the GAINS model processing module for transmitting policy scenario parameters and economic and energy data. The GAINS model processing module connects to the machine learning model processing module for transmitting PM data. 2.5 Concentration data and other relevant emission data. Both the GAINS model processing module and the machine learning model processing module are connected to the BenMAP-CE model processing module for transmitting PM2.5 concentration data and other relevant emission data. 2.5 The system also includes O3 concentration data. The data storage module connects to the GAINS model processing module, machine learning model processing module, and BenMAP-CE model processing module to store input data, intermediate results, and output data. Finally, the results output interface module connects to the BenMAP-CE model processing module to output health and economic benefit data.

[0047] Compared with the prior art, this application has the following advantages: (1) High evaluation efficiency and low cost. This application adopts a pre-trained ensemble machine learning model. Once trained, the prediction process of this model is an efficient forward computation, avoiding the complex nonlinear partial differential equation solution and a large number of chemical reaction mechanism calculations in CTM, thereby achieving an order-of-magnitude improvement in efficiency and a significant reduction in computational cost. Therefore, this application can quickly complete the entire chain evaluation from policy scenario input to health and economic benefit output, reducing the time taken from several weeks or months in traditional methods to several hours or days, and significantly reducing the demand for computing resources.

[0048] (2) Improved evaluation accuracy and reliability. The Stacking ensemble learning model adopted in this application, by integrating the predictive advantages of multiple heterogeneous base learners (such as XG Boost and Light GBM), can more effectively learn and represent PM. 2.5 The complex nonlinear mapping relationship between precursor emissions and O3 concentration yields more stable and robust predictive performance than any single model, significantly improving prediction accuracy. Therefore, this application demonstrates higher accuracy in predicting the concentration of the key secondary pollutant O3, resulting in more scientific and reliable subsequent health and economic benefit assessments.

[0049] (3) Enhanced comprehensiveness and systematicness of the assessment. This application, through the synergistic effect of steps 201 to 204 in the entire technical solution, ensures the authority and systematicness of the macroeconomic policy scenario and primary pollutant simulation, crucially filling the technical gap of "missing O3 concentration" in the traditional assessment chain, and incorporating PM... 2.5 The concentration changes of two key pollutants, O3 and E2, are incorporated into the health and economic impact assessment framework. This complete closed-loop design, encompassing "policy → emissions → primary pollutants → secondary pollutants → health impacts → economic value," ensures the comprehensiveness and scientific rigor of the assessment results.

[0050] Based on the above processing, this application realizes an integrated, full-chain assessment of the comprehensive benefits of coordinated emission reduction policies (covering CO2, multiple air pollutants, health impacts, and economic value), overcoming the problem of serious underestimation of benefits caused by neglecting O3 in traditional assessments.

[0051] (4) Strong decision support capability and good practicality. This application uses the BenMAP-CE model to "translate" abstract concentration data into the number of deaths avoided and economic value that decision-makers care about. Therefore, this application can provide decision-makers with intuitive and quantitative health and economic benefit data, support rapid iteration, comparison and optimization of different policy scenarios, and has high practical value.

[0052] Furthermore, the high degree of integration and automation of the entire system provided in this application (all modules are automatically executed sequentially via evaluation computer terminals) allows users to simply configure policy parameters, and the system can automatically complete the entire complex evaluation process and output final decision indicators. This "one-stop" design greatly reduces the technical barrier to entry and enhances the practicality of the method and its support effectiveness for policy formulation.

[0053] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 4 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and databases. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for assessing the synergistic benefits of regional air pollution and carbon emission reduction.

[0054] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0055] In one exemplary embodiment, a computer device is also provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the above-described method embodiments.

[0056] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0057] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0058] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0059] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0060] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0061] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0062] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for evaluating the synergistic effect of regional air pollution and carbon emission reduction, characterized in that, The method comprises: Based on the greenhouse gas-atmospheric pollution synergistic effect model, according to the regional policy scenario parameters of the target region, the pollutant emission inventory and PM 2.5 spatial distribution concentration prediction data; the regional policy scenario parameters are used to simulate a specific development path in the future; based on a machine learning algorithm, on the basis of the pollutant emission inventory and the PM 2.5 spatial distribution concentration prediction data, determining O3 spatial distribution concentration prediction data; The environmental benefit evaluation model is used to calculate the health benefit according to the PM 2.5 The spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data are used to calculate the health benefit. calculating economic benefits according to the health benefits based on the value of life method.

2. The method according to claim 1, wherein, The pollutant emission inventory and the PM 2.5 The determination process of the spatial distribution concentration prediction data comprises: obtaining regional policy scenario parameters of a target region; the regional policy scenario parameters at least include economic activity level data, energy structure data, and penetration rate data of end-of-pipe pollution control technology; calling a greenhouse gas-atmospheric pollution synergy effect model; inputting the regional policy scenario parameter into the greenhouse gas-atmospheric pollution synergistic effect model to obtain a pollutant emission inventory and PM 2.5 spatial distribution concentration prediction data.

3. The method of claim 1, wherein, based on a machine learning algorithm, on the basis of the pollutant emission inventory and the PM 2.5 spatial distribution concentration prediction data, determining O3 spatial distribution concentration prediction data, comprising: calling a pre-trained integrated machine learning model; extracting to-be-used pollutant emission data from the pollutant emission list according to a preset rule; The PM 2.5 The spatial distribution concentration prediction data and the to-be-used pollutant emission data are input into the integrated machine learning model to obtain O3 spatial distribution concentration prediction data.

4. The method according to claim 3, wherein, the integrated machine learning model is a Stacking integrated learning model; the Stacking integrated learning model selects any one of XG Boost, random forest, gradient boosting decision tree, Light GBM, and Ada Boost as a base learner, and adopts an elastic network with cross-validation as a meta-learner.

5. The method of claim 1, wherein, a calculation formula of the health benefits is: ； wherein, β is a known parameter; including PM 2.5 The spatial distribution concentration change amount and the O3 spatial distribution concentration change amount are calculated by comparing the PM 2.5 The spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data are calculated based on the baseline scenario concentration; incidence is the mortality rate of different diseases; and POP is the number of exposed population, which is the known population number of the target area. 6.The method of claim 1, wherein, a calculation formula of the economic benefits is: ； ； Wherein, E is economic benefit, is the life statistics value after the regional income level adjustment, is the health benefit; is the benchmark life statistics value of the benchmark year, which is a known constant; , is the per capita income of the target region in the target year and the per capita income of the benchmark region in the benchmark year, both of which are known constants; e is the income elasticity coefficient, which is a known constant.

7. The method of claim 1, wherein, the pollutant emission list at least includes predicted emission amounts of carbon dioxide, sulfur dioxide, and nitrogen oxides in a target year under a future specific development path scenario.

8. A system for evaluating the synergistic benefits of regional air pollution and carbon emission reduction, applying the method for evaluating the synergistic benefits of regional air pollution and carbon emission reduction according to any one of claims 1-7, characterized in that, The system comprises: The GAINS model processing module is configured to: based on a greenhouse gas-atmospheric pollution synergistic effect model, determine a pollutant emission inventory and PM 2.5 spatial distribution concentration prediction data according to regional policy scenario parameters of the target region; the regional policy scenario parameters are used to simulate a specific development path in the future. a machine learning model processing module, configured to: based on a machine learning algorithm, determine the PM 2.5 spatial distribution concentration prediction data, determine O3 spatial distribution concentration prediction data; a BenMAP-CE model processing module configured to: apply an environmental benefit assessment model to calculate an environmental benefit based on the PM 2.5 spatial distribution concentration prediction data and the O3 spatial distribution concentration prediction data, calculate a health benefit; and calculate an economic benefit based on the health benefit using a value of a statistical life method.

9. The system for evaluating the synergistic effect of regional air pollution and carbon emission reduction according to claim 8, wherein, The system further comprises: a data input interface module, configured to: receive regional policy scenario parameters of a target region, a baseline value of life statistics, per capita income in a baseline year, a known population number, a relationship coefficient between pollutant concentration and health effects, and an income elasticity coefficient input by a user or read from an external database; transmit the regional policy scenario parameters to the GAINS model processing module; and transmit the baseline value of life statistics, the per capita income in the baseline year, the known population number, the relationship coefficient between pollutant concentration and health effects, and the income elasticity coefficient to the BenMAP-CE model processing module; a data storage module, configured to store the regional policy scenario parameter of the target region, the baseline vital statistics value, the baseline per capita income, the known population, the relationship coefficient between the pollutant concentration and the health effect, the income elasticity coefficient, the pollutant emission inventory, the PM 2.5 spatial distribution concentration prediction data, O3 spatial distribution concentration prediction data, health benefits and economic benefits; a result output interface module, configured to: output the health benefits and the economic benefits to a user in a visual or file format.

10. A computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the regional atmospheric pollution and carbon emission reduction synergy benefit evaluation method in any one of claims 1-7.

Images