Method and system for evaluating influence of setting off fireworks and crackers on PM2.5 concentration

Abstract

The invention provides a method and system for evaluating the influence of setting off fireworks and crackers on PM2.5 concentration, and relates to the technical field of environmental atmospheric pollutant evaluation, and the method comprises the steps: obtaining evaluation data of each time point in a setting off period of a monitoring station, including metal ion concentration, meteorological conditions and spatial-temporal characteristics; based on the evaluation data, the PM2.5 concentration under the firework setting-off scene and the PM2.5 concentration under the firework-free setting-off scene are predicted through a firework scene model and a background reference model; and calculating the contribution rate of the set-off fireworks and crackers to the PM2.5 concentration from two aspects of a single time point and a whole set-off time period by utilizing the predicted value of the PM2.5 concentration. According to the method, based on the firework scene model and the background reference model, efficient and accurate quantitative analysis on the influence of the set-off fireworks and crackers on the PM2.5 concentration is carried out from the two aspects of the single time point and the whole set-off time period.

Description

Technical Field

[0001] The present disclosure relates to the technical field of environmental air pollutant assessment, and in particular to an assessment method and system for the impact of setting off fireworks and firecrackers on PM2.5 concentration. Background Art

[0002] Fine particulate matter (PM 2.5 ) is a key pollutant in the tropospheric atmosphere, PM 2.5 It not only causes direct damage to the human respiratory system, but also actively participates in and aggravates the atmospheric pollution process; through complex photochemical reactions, PM 2.5 It will generate a variety of secondary pollutants, posing a long-term and far-reaching threat to the natural ecosystem and public health. Setting off fireworks is a traditional custom that carries a profound cultural heritage and national sentiment. It is not only a way of celebration, but also people’s expectation for a better life and a good blessing for auspiciousness and peace. However, setting off fireworks will significantly increase PM 2.5 The concentration of PM2.5 in the atmosphere has the potential to threaten the property safety and health of residents, especially during important festivals such as New Year's Day, New Year's Eve, Spring Festival and Lantern Festival. The concentrated setting off of fireworks and firecrackers has become one of the significant sources of urban air pollution during these festivals. 2.5 The concentration is an extremely complex system, which is affected by multiple factors such as meteorological conditions, emission sources, long-distance transmission, atmospheric chemical reactions, etc. How to accurately separate the impact of fireworks and firecrackers on PM from these complex factors? 2.5 The specific impact of pollution has always been a research difficulty that environmental regulators and the scientific community have continued to pay attention to.

[0003] Existing research methods can be divided into two categories: atmospheric chemistry simulation and statistical analysis. In the field of atmospheric chemistry simulation, models such as WRF-CMAQ and WRF-Chem are widely used, but these models have significant limitations: on the one hand, they consume a lot of computing resources, and on the other hand, they are limited by the emission inventory, resulting in relatively poor timeliness and accuracy; statistical methods such as multivariate linear regression and Kolmogorov-Zurbenko filtering (KZ filter) also face challenges due to the PM in the atmosphere. 2.5 There is a nonlinear relationship between PM concentration and various factors. The interpretation and prediction capabilities of traditional multivariate linear regression are extremely limited. The KZ filter can, to a certain extent, remove the influence of meteorological conditions on PM 2.5 The concentration of fireworks can be affected, but it is impossible to achieve accurate quantitative analysis of the burning of fireworks.

[0004] In recent years, machine learning has made breakthrough progress in the field of atmospheric pollutant prediction and simulation. These new methods not only overcome the timeliness and accuracy bottlenecks of traditional models, but also can effectively decouple the effects of meteorology and emissions on PM2.5 with low computing resource consumption. 2.5The combined impact of concentration, for example, rmweather and other methods show great potential. However, the limitation of this method is that it can only decouple the overall emissions from the meteorological environment, and has not yet achieved the PM2.5 emission caused by fireworks, a single emission source. 2.5 Accurate quantitative analysis of concentration changes. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes an evaluation method and system for the impact of setting off fireworks and firecrackers on PM2.5 concentration. Based on a fireworks scenario model and a background benchmark model, an efficient and accurate quantitative analysis of the impact of setting off fireworks and firecrackers on PM2.5 concentration is performed from two levels: a single time point and the entire setting off period.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions: The assessment method for the impact of fireworks and firecrackers on PM2.5 concentration includes: Obtain assessment data at each time point during the discharge period of the monitoring station, including metal ion concentrations, meteorological conditions, and spatiotemporal characteristics; Based on the evaluation data, the PM2.5 concentration in the fireworks scenario and the PM2.5 concentration in the no-fireworks scenario were predicted using the fireworks scenario model and the background baseline model respectively. Using the predicted value of PM2.5 concentration, the contribution rate of fireworks to PM2.5 concentration is calculated from two levels: a single time point and the entire firing period.

[0007] According to some embodiments, the present disclosure adopts the following technical solutions: The assessment system for the impact of fireworks and firecrackers on PM2.5 concentration includes: The data acquisition module is configured to: acquire evaluation data at each time point during the discharge period of the monitoring station, including metal ion concentration, meteorological conditions and spatiotemporal characteristics; The concentration prediction module is configured to: predict the PM2.5 concentration in the fireworks setting scenario and the PM2.5 concentration in the no-fireworks setting scenario respectively through the fireworks scenario model and the background benchmark model based on the evaluation data; The impact assessment module is configured to use the predicted value of PM2.5 concentration to calculate the contribution rate of fireworks to PM2.5 concentration from two levels: a single time point and the entire firing period.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions: A computer program product includes a computer program, which, when executed by a processor, implements the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions: A non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration is implemented.

[0010] According to some embodiments, the present disclosure adopts the following technical solutions: An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration.

[0011] Compared with the prior art, the present invention has the following beneficial effects: The present invention predicts the PM2.5 concentration in the fireworks scenario and the PM2.5 concentration in the no-fireworks scenario through a fireworks scenario model and a background benchmark model respectively, and then efficiently and accurately calculates the contribution rate of fireworks to PM2.5 concentration from two levels, namely, a single time point and the entire fireworks period, to achieve precise quantitative analysis of the impact of fireworks on PM2.5 concentration.

[0012] This paper adopts a combination of single-point analysis and time period analysis to evaluate the impact of fireworks on PM2.5 concentration, that is, the contribution rate. Impact(t) at time point t can reveal the instantaneous impact of fireworks on PM2.5 concentration at a specific moment, which helps to identify peak time periods. It provides an overview of the overall impact, which helps to evaluate the contribution of pollution sources from a global perspective. The calculation of relative contribution rate, through normalization, avoids distortion of results caused by differences in background concentrations between different time periods or regions, making the analysis results more comparable. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0014] Figure 1 This is a flow chart of the method of Example 1. DETAILED DESCRIPTION

[0015] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0016] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0017] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0018] Example 1 In one embodiment of the present disclosure, a method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration is provided, comprising: Step S1: Obtaining evaluation data at each time point during the discharge period of the monitoring station, including metal ion concentration, meteorological conditions, and spatiotemporal characteristics; Step S2: Based on the evaluation data, the PM2.5 concentration in the fireworks scenario and the PM2.5 concentration in the no-fireworks scenario are predicted by the fireworks scenario model and the background baseline model respectively; Step S3: Using the predicted value of PM2.5 concentration, calculate the contribution rate of fireworks to PM2.5 concentration from two levels: a single time point and the entire firing period.

[0019] As an embodiment, the evaluation method of the impact of setting off fireworks and firecrackers on PM2.5 concentration disclosed in the present invention is based on a fireworks scenario model and a background reference model, and performs an efficient and accurate quantitative analysis of the impact of setting off fireworks and firecrackers on PM2.5 concentration from two levels: a single time point and the entire setting off period. Figure 1 The specific implementation process is as follows: 1. Get data: 1.1 Data Source Monitoring site data, including ion chemical composition (i.e. metal ions, typical products of fireworks) and PM2.5 concentration data as well as meteorological observation data.

[0020] The optional metal cations are: potassium ion (K+), sodium ion (Na+), copper ion (Cu2+); The optional heavy metal ions are: strontium ion (Sr2+), barium ion (Ba2+), aluminum ion (Al3+), boron ion (B3+); Optional meteorological observation data include: temperature, relative humidity, wind speed, wind direction, atmospheric pressure, precipitation, boundary layer height, total cloud cover, etc.

[0021] 1.2 Spatiotemporal Feature Engineering Add temporal and geographic features to the dataset.

[0022] (1) Optional time features include: Julian Date (JulianDate), which represents dates as consecutive integers, facilitates mathematical processing and cycle analysis of time.

[0023] Months are used to capture seasonal variations, such as the significant increase in PM2.5 concentrations during the winter heating period.

[0024] Hourly: reflects daily variations, such as fluctuations in pollutant concentrations during morning and evening rush hours.

[0025] Holiday tags: Mark special dates (such as statutory holidays, traditional festivals, etc.) to analyze the impact of festive activities on pollution. Holidays are usually accompanied by activities such as fireworks and changes in traffic flow, which have a significant impact on air quality.

[0026] (2) Optional geographical features: latitude and longitude of monitoring station, city / region code.

[0027] Specifically, hourly ion data are obtained from monitoring sites, including potassium ions (K + ), copper ions (Cu 2+ ), strontium ions (Sr 2+ ), barium ions (Ba 2+ ), aluminum ions (Al 3+ ), meteorological data, such as temperature (T), relative humidity (RH), wind speed (WS), wind direction (WD), atmospheric pressure (P), precipitation (TP).

[0028] 2. Definition of concentrated and non-concentrated fireworks and firecrackers discharge periods: Concentrated fireworks periods refer to the time periods when fireworks are frequently and intensely set off, usually related to traditional festivals or important celebrations, specifically: 2.1 Optional concentrated firing periods During the Spring Festival: From the Lunar New Year's Eve to the fifteenth day of the first lunar month, this is the most concentrated period of fireworks during Chinese traditional festivals, especially on New Year's Eve and the Lantern Festival, when the amount of fireworks reaches its peak.

[0029] New Year's Eve: From the evening of December 31st to the early morning of the next day, many areas will celebrate the arrival of the new year with fireworks displays.

[0030] Mid-Autumn Festival: Some areas hold fireworks shows during the Mid-Autumn Festival, especially local celebrations with fireworks as the theme.

[0031] National Day Fireworks Show: Every year on October 1st, National Day, many cities hold large-scale fireworks shows, especially in first-tier cities and tourist hotspots.

[0032] Local festivals: For example, temple fairs, lantern festivals and other local festivals. These activities are usually accompanied by fireworks. The impact may be limited to a specific area, but the intensity cannot be ignored.

[0033] 2.2 Non-centralized fireworks period In order to compare and analyze the impact of fireworks on air quality, the selection of non-centralized fireworks periods is also crucial. The division of non-centralized fireworks periods needs to avoid other special events that may interfere with the research. The optional non-centralized fireworks periods include: Ordinary dates in the same season: Choose an ordinary weekday or weekend in the same season as the concentrated fireworks display period to avoid differences in background pollution caused by seasonal changes.

[0034] Specifically, the concentrated fireworks display periods are: 20:00 on December 31 to 3:00 a.m. the next day, 18:00 on New Year's Eve to 18:00 the next day, and 18:00 on the fifteenth day of the first lunar month to 18:00 the next day. The rest of the time are non-concentrated fireworks display periods.

[0035] 3. Data preprocessing: Data preprocessing and quality control are important steps to ensure the accuracy and reliability of analysis results. Raw data often contain missing values ​​and outliers, which may significantly affect the analysis results. Therefore, before data analysis, the data must be systematically cleaned and quality controlled.

[0036] Data cleaning includes the processing of missing values ​​and the identification and processing of outliers. Scientific and reasonable methods are used to correct different types of data problems to improve the integrity and consistency of the data.

[0037] 3.1 Missing Value Processing Missing values ​​are a common problem in data analysis. They may be caused by equipment failure, recording errors, or sampling conditions. The first step in dealing with missing values ​​is to identify their types, which can be divided into the following two categories: Missing Completely at Random (MCAR): The occurrence of missing values ​​is completely random and has nothing to do with any variable. This type of missingness is easier to handle and has less impact on the analysis results.

[0038] Systematic missingness (Missing at Random, MAR): The occurrence of missing values ​​is related to certain variables and may lead to bias in the analysis results.

[0039] Depending on the proportion and type of missing values, you can choose the following processing methods: Complete deletion method: Applicable to situations where the missing ratio is low (usually <5%). Directly delete records or variables with missing values. It is simple and efficient, but some information may be lost.

[0040] Mean / median filling: Use the mean or median of the variable to replace the missing values. It is suitable for situations where the variable distribution is relatively symmetrical and the missing proportion is moderate.

[0041] Multiple Imputation: Estimate missing values ​​based on statistical models (such as regression models), repeat the imputation multiple times and integrate the results. It is suitable for data with a high missing ratio or complex distribution.

[0042] Advanced imputation methods: Predict missing values ​​based on machine learning algorithms (such as random forest, KNN, deep learning). This method can capture complex relationships between variables, but requires more computing resources and model debugging.

[0043] In addition, before processing missing values, its potential impact on the analysis results needs to be evaluated to ensure that the selected processing method will not introduce new biases.

[0044] 3.2 Identification and processing of outliers Outliers are data points that deviate significantly from the normal range and may be caused by measurement errors, input errors, or real extreme events. The presence of outliers may have a significant impact on statistical analysis and modeling, so they need to be identified and processed.

[0045] The available outlier identification methods are: 3σ principle: Assuming that the data follows a normal distribution, define the outliers as points that are more than 3 standard deviations away from the mean. This method is simple and intuitive and is suitable for data with a distribution that is approximately normal.

[0046] Box plot method: Calculate the range of outliers based on quartiles (Q1, Q3). Define outliers as data points below Q1-1.5IQR or above Q3+1.5IQR, where IQR is the interquartile range (Q3-Q1). This method is more suitable for non-normally distributed data.

[0047] Time series analysis: For time series data, mutation points can be identified through sliding windows or difference methods.

[0048] Machine learning methods: Identify outliers in complex patterns based on anomaly detection algorithms (such as isolation forests and support vector machines).

[0049] The available outlier handling methods are: Direct deletion: Outliers with obvious measurement errors or that do not meet the research objectives can be directly eliminated.

[0050] Replacement treatment: Replace outliers with mean, median or adjacent values, which is suitable for situations where the proportion of outliers is low.

[0051] Group processing: Outliers are grouped together and analyzed separately to avoid interfering with the overall data distribution.

[0052] Weight adjustment: giving lower weights to outliers in statistical models to reduce their impact on model results.

[0053] When dealing with outliers, we should consider the specific research context and data characteristics to determine whether the outliers are noise or meaningful information. For example, a surge in pollutant concentrations caused by extreme weather events may be a real phenomenon and should not be simply deleted or replaced.

[0054] 4. Model construction and training: In order to evaluate the impact of fireworks on PM2.5 concentration, based on LightGBM, this embodiment designs two models: Model 1 (fireworks scenario model) and Model 2 (background benchmark model). By comparing the outputs of the two models, the contribution of fireworks to air quality is quantitatively evaluated.

[0055] 4.1 Model 1: Fireworks scenario model (m1) Model description: Model 1 targets the scenario of fireworks display, and its feature set includes metal ion concentration, meteorological conditions, and spatiotemporal characteristics. Metal ion concentration is an important marker of fireworks display, and its significant change can reflect the intensity of fireworks display. Therefore, Model 1 can better simulate PM during fireworks display. 2.5 Dynamic changes in concentration.

[0056] Feature Set: Metal ion concentration: including potassium ions (K+), sodium ions (Na+), copper ions (Cu2+), etc. These ions are typical products of fireworks.

[0057] Meteorological conditions: including temperature, relative humidity, wind speed, wind direction, atmospheric pressure, precipitation, boundary layer height and total cloud cover, which affect the diffusion, deposition and transformation of pollutants.

[0058] Spatiotemporal characteristics: including Julian date, month, hour, week, holiday, longitude and latitude of monitoring station, city / region code, reflecting the temporal periodicity of pollutant concentration, festival influence and regional characteristics.

[0059] Tags: PM 2.5 concentration, as the prediction target of the model.

[0060] Modeling goals: Model 1 simulates PM under fireworks scenario 2.5The concentration changes provide data support for the quantitative analysis of the pollution contribution of fireworks.

[0061] 4.2 Model 2: Background baseline model (m2) Model description: Model 2 targets the scenario of no fireworks and uses only meteorological conditions and spatiotemporal characteristics as input features. This model can simulate PM2.5 under the condition of no fireworks. 2.5 concentration.

[0062] Feature Set: Meteorological conditions: Same as Model 1, including variables such as temperature, relative humidity, wind speed, wind direction, atmospheric pressure, precipitation, boundary layer height, and total cloud cover.

[0063] Spatiotemporal characteristics: including Julian date, month, hour, week, holiday, longitude and latitude of monitoring station, city / region code, reflecting the temporal periodicity of pollutant concentration, festival influence and regional characteristics.

[0064] Tags: PM 2.5 concentration, as the prediction target of the model.

[0065] Modeling objective: Through Model 2, simulate PM2.5 in a scenario without fireworks 2.5 concentration, providing a benchmark for subsequent assessment of the net contribution of fireworks.

[0066] 4.3 Model Training Details PM 2.5 The concentration of fireworks is used as a label to construct two training data sets: a concentrated firing period data set and a non-concentrated firing period data set, which are used to train the fireworks scenario model and background benchmark model built based on LightGBM respectively. The model verification of the training set and the validation set is used to ensure the prediction accuracy of LightGBM.

[0067] In order to ensure the generalization ability and prediction accuracy of the model, this embodiment divides the data set into a training set and a validation set, which are used for model training and performance evaluation respectively.

[0068] Dataset division: According to the amount of data, the data set is divided into a training set and a validation set by random division.

[0069] Training set: used to train the model to ensure that the model can capture the patterns in the data. The training set ratio can be selected to be 60%-80%.

[0070] Validation set: used to evaluate the performance of the model on unseen data to avoid overfitting of the model. The validation set ratio can be 20%-40%.

[0071] Note: Data division should try to ensure that the distribution of the training set and the validation set is consistent to avoid affecting model performance due to data bias.

[0072] For time series data, it is recommended to use a time sliding window or time-based stratified sampling to avoid future information leakage into the training set.

[0073] 4.4 Model Tuning In order to further improve the prediction performance of the model, this embodiment optimizes the hyperparameters of the LightGBM model.

[0074] (1) Optional hyperparameter optimization methods are: Grid Search: Traverse all possible parameter combinations to find the optimal configuration. This method is suitable for situations where the parameter space is small, but the amount of calculation is large.

[0075] Random Search: Randomly selects parameter combinations in the parameter space for evaluation. It has high computational efficiency and is suitable for situations where the parameter space is large.

[0076] Bayesian Optimization: By building a proxy model (such as a Gaussian process) to predict the optimal value of the parameter, the optimization is done step by step. This method is efficient and can quickly find the global optimal solution.

[0077] (2) The key tuning parameters are: Learning Rate: Controls the step size of each iteration. A lower learning rate can improve the stability of the model, but the training time will be longer.

[0078] Tree depth (MaxDepth): Limits the maximum depth of the decision tree to prevent overfitting and affect the complexity of the model.

[0079] Number of leaf nodes (NumLeaves): The maximum number of leaf nodes for each tree, which determines the complexity and fitting ability of the tree.

[0080] SubsampleRate: Randomly sampling some samples for training can reduce the risk of overfitting and improve the generalization ability of the model.

[0081] (3) Tuning process: Preliminary parameter setting: Set the initial parameter range based on experience or references.

[0082] Parameter optimization: Select an optimization method (such as random search) and adjust the parameters within the initial range to find the optimal configuration.

[0083] Verification and fine-tuning: Evaluate the optimized parameter combination on the validation set and perform fine-tuning based on the results to ensure stable model performance.

[0084] Model evaluation: Finally, the parameter combination with the best performance is selected for the final training and prediction of the model.

[0085] Note: Hyperparameter optimization requires selecting an appropriate method based on computing resources and time constraints.

[0086] During the tuning process, attention should be paid to the model's training time, prediction accuracy, and generalization ability to avoid excessive model complexity due to over-tuning.

[0087] Among them, the root mean square error (RMSE), mean absolute error (MAE) and determination coefficient (R) are used to evaluate the accuracy of model prediction. RMSE: emphasizes the impact of large errors and is suitable for scenarios that focus on outliers; MAE: reflects the average level of errors and can intuitively measure the overall deviation of model predictions. R: measures the overall fit of the model to the data, with a value range of [−∞,1]; by comparing the above three indicators on the training set and the validation set, the generalization ability of the model can be judged, and the overfitting problem of LightGBM can be discovered and prevented in a timely manner.

[0088] 5. Use the two trained models to quantitatively calculate the impact of fireworks on PM2.5 concentration: Metal ions, as markers of fireworks, reflect the intensity of fireworks to a certain extent. Therefore, Model 1, which is trained using metal ions, meteorological conditions, and spatiotemporal characteristics, represents the scenario of concentrated fireworks display (i.e., fireworks display scenario), while Model 2, which is trained only using meteorological conditions and spatiotemporal characteristics, represents the scenario of no fireworks display (i.e., no fireworks display scenario). This comprehensively analyzes the impact of fireworks display on air quality from two levels: a single time point and the entire fireworks display period.

[0089] 5.1 Calculation of impact at a single time point For each time point t in the fireworks period T to be evaluated, the impact of fireworks on PM is calculated using the following formula: 2.5 Effect of concentration:

[0090] The numerator CM1(t)−CM2(t) represents the PM under the fireworks display scenario. 2.5 The absolute increase in concentration compared to the scenario without fireworks. The denominator CM1(t) is used for normalization and calculation of the relative increase to facilitate comparative analysis between different time points. CM1(t) is the PM at time point t in the fireworks scenario predicted by model 1. 2.5concentration, CM2(t) is the PM at time point t in the scenario without fireworks predicted by model 2. 2.5 concentration, Impact(t) is the relative contribution rate of fireworks and firecrackers to PM2.5 concentration at time point t.

[0091] 5.2 Calculation of the impact of the entire concentrated fireworks period In order to evaluate the impact of fireworks during the entire evaluation period T, the average impact rate is calculated using the following formula:

[0092] in, is the PM of the entire fireworks period T under the fireworks scenario predicted by the fireworks scenario model 2.5 The total concentration, is the PM of the entire fireworks period T under the scenario of no fireworks predicted by the background baseline model 2.5 The total concentration, |T| is the number of time points in the firing period T, The effect of fireworks and firecrackers on PM during the entire firing period 2.5 The average relative contribution of concentration.

[0093] Example 2 In one embodiment of the present disclosure, a system for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration is provided, comprising: The data acquisition module is configured to: acquire evaluation data at each time point during the discharge period of the monitoring station, including metal ion concentration, meteorological conditions and spatiotemporal characteristics; The concentration prediction module is configured to: predict the PM2.5 concentration in the fireworks setting scenario and the PM2.5 concentration in the no-fireworks setting scenario respectively through the fireworks scenario model and the background benchmark model based on the evaluation data; The impact assessment module is configured to use the predicted value of PM2.5 concentration to calculate the contribution rate of fireworks to PM2.5 concentration from two levels: a single time point and the entire firing period.

[0094] Example 3 In one embodiment of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration.

[0095] Example 4 In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration is implemented.

[0096] Example 5 In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration.

[0097] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration, characterized in that: include: Obtain assessment data at each time point during the discharge period of the monitoring station, including metal ion concentrations, meteorological conditions, and spatiotemporal characteristics; Based on the evaluation data, the PM2.5 concentration in the fireworks scenario and the PM2.5 concentration in the no-fireworks scenario were predicted using the fireworks scenario model and the background baseline model respectively. Using the predicted value of PM2.5 concentration, the contribution rate of fireworks to PM2.5 concentration is calculated from two levels: a single time point and the entire firing period.

2. The method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as claimed in claim 1, characterized in that: The metal ion concentration is a typical product concentration of fireworks, including metal cations and heavy metal ions; The meteorological conditions include temperature, relative humidity, wind speed, wind direction, atmospheric pressure, precipitation, boundary layer height, and total cloud cover; The spatiotemporal characteristics include information on monitoring sites and time points.

3. The method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as claimed in claim 1, characterized in that: The fireworks scenario model and background benchmark model are constructed based on LightGBM and are trained using a concentrated firing period data set and a non-concentrated firing period data set, respectively.

4. The method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as claimed in claim 3, characterized in that: The fireworks scenario model takes metal ion concentration, meteorological conditions and spatiotemporal characteristics as inputs and outputs the predicted value of PM2.5 concentration under the fireworks scenario; The background benchmark model takes meteorological conditions and spatiotemporal characteristics as input and outputs the predicted value of PM2.5 concentration in a scenario without fireworks.

5. The method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as claimed in claim 1, characterized in that: The contribution rate of the single time point is expressed by the formula: Among them, CM1(t) is the PM at time point t in the fireworks scenario predicted by the fireworks scenario model. 2.5 concentration, CM2(t) is the PM at time point t predicted by the background baseline model in the scenario without fireworks. 2.5 concentration, Impact(t) is the relative contribution rate of fireworks and firecrackers to PM2.5 concentration at time point t.

6. The method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as claimed in claim 1, characterized in that: The contribution rate of the entire firing period is expressed by the formula: in, is the PM of the entire fireworks period T under the fireworks scenario predicted by the fireworks scenario model 2.5 The total concentration, is the PM of the entire fireworks period T under the scenario of no fireworks predicted by the background baseline model 2.5 The total concentration, |T| is the number of time points in the firing period T, The effect of fireworks and firecrackers on PM during the entire firing period 2.5 The average relative contribution of concentration.

7. An evaluation system for the impact of fireworks on PM2.5 concentration, characterized in that: include: The data acquisition module is configured to: acquire evaluation data at each time point during the discharge period of the monitoring station, including metal ion concentration, meteorological conditions and spatiotemporal characteristics; The concentration prediction module is configured to: predict the PM2.5 concentration in the fireworks setting scenario and the PM2.5 concentration in the no-fireworks setting scenario respectively through the fireworks scenario model and the background benchmark model based on the evaluation data; The impact assessment module is configured to use the predicted value of PM2.5 concentration to calculate the contribution rate of fireworks to PM2.5 concentration from two levels: a single time point and the entire firing period.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration is implemented as described in any one of claims 1-6.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method for evaluating the impact of setting off fireworks and firecrackers on PM2.5 concentration as described in any one of claims 1-6.

Images