CN115578227A - Method for determining atmospheric particulate pollution key area based on multi-source data - Google Patents
Method for determining atmospheric particulate pollution key area based on multi-source data Download PDFInfo
- Publication number
- CN115578227A CN115578227A CN202211109754.1A CN202211109754A CN115578227A CN 115578227 A CN115578227 A CN 115578227A CN 202211109754 A CN202211109754 A CN 202211109754A CN 115578227 A CN115578227 A CN 115578227A
- Authority
- CN
- China
- Prior art keywords
- atmospheric particulate
- pollution
- area
- sensitive physical
- atmospheric
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000012544 monitoring process Methods 0.000 claims abstract description 42
- 238000004364 calculation method Methods 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 239000013618 particulate matter Substances 0.000 claims description 34
- 238000009792 diffusion process Methods 0.000 claims description 25
- 230000005540 biological transmission Effects 0.000 claims description 15
- 239000008277 atmospheric particulate matter Substances 0.000 claims description 13
- 230000005571 horizontal transmission Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000011109 contamination Methods 0.000 claims description 5
- 239000003344 environmental pollutant Substances 0.000 abstract description 7
- 231100000719 pollutant Toxicity 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 description 7
- 230000007613 environmental effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 239000002245 particle Substances 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000012351 Integrated analysis Methods 0.000 description 1
- CBENFWSGALASAD-UHFFFAOYSA-N Ozone Chemical compound [O-][O+]=O CBENFWSGALASAD-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/06—Investigating concentration of particle suspensions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/02—Instruments for indicating weather conditions by measuring two or more variables, e.g. humidity, pressure, temperature, cloud cover or wind speed
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Environmental & Geological Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Educational Administration (AREA)
- Dispersion Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Development Economics (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for determining an atmospheric particulate pollution key area based on multi-source data, which relates to the technical field of atmospheric pollutant monitoring and comprises the steps of selecting a station address of an atmospheric particulate monitoring station; monitoring original multi-source data in a station address, determining a sensitive physical parameter, and taking the sensitive physical parameter as a model input parameter; acquiring various sensitive physical parameters of a period of time in a station site area, preprocessing the parameters and constructing a training sample; establishing an atmospheric particulate pollution occurrence condition judgment model at a station site, performing model training on a training sample, and acquiring a calculation model for determining an atmospheric particulate pollution key area; sensitive physical parameter data in a target area to be distinguished are used as model input parameters, and a distinguishing result of an atmospheric particulate pollution key occurrence area is obtained based on a calculation model. The atmospheric particulate pollution key area can be efficiently obtained, and then the operating personnel can make corresponding processing decisions timely and accurately.
Description
Technical Field
The invention relates to the technical field of atmospheric pollutant monitoring, in particular to a method for determining an atmospheric particulate pollution key area based on multi-source data.
Background
With the rapid advance of urbanization and industrialization in China, the living standard of people is increasingly improved, but more and more environmental problems are caused, and especially the atmospheric pollution mainly comprising particulate matters seriously threatens the environmental quality and the human health, so that the environmental pollution is gradually the research focus in the field of atmospheric environment.
In the area of the basin region, pollutants generated in the upwind area are easy to transmit to the basin region across the region, and the pollutants are blocked by the terrain and are not easy to diffuse, so that the regional transmission pollution brings new challenges to the supervision and control of the air quality to a great extent.
Disclosure of Invention
The invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which aims to solve the problems in the background technology.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a method for determining an atmospheric particulate pollution focal region based on multi-source data comprises the following steps:
selecting a site of an atmospheric particulate monitoring station, and erecting a monitoring field on the site;
monitoring original multi-source data in the station site, determining a sensitive physical parameter, and taking the sensitive physical parameter as a model input parameter, wherein the sensitive physical parameter is at least one item in the multi-source data, and the sensitive physical parameter is a factor influencing atmospheric particulate pollution;
acquiring various sensitive physical parameters of the station site area for a period of time, preprocessing the parameters and constructing a training sample;
establishing an atmospheric particulate pollution occurrence condition discrimination model at the site, and performing model training on the training sample to obtain a calculation model for determining an atmospheric particulate pollution key area;
and obtaining a judgment result of an important occurrence area including atmospheric particulate pollution based on the calculation model by taking the sensitive physical parameter data in the target area to be judged as a model input parameter.
In some embodiments, the step of monitoring raw multi-source data in the site, determining sensitive physical parameters, and using the sensitive physical parameters as model input parameters includes air station particulate matter concentration, road particulate matter concentration, site particulate matter concentration, particulate matter focus grid data, focus area particulate matter concentration, underlying surface data, mixed layer height data, and wind direction data.
In some embodiments, in the step of obtaining sensitive physical parameters of the site area for a period of time, preprocessing the sensitive physical parameters, and constructing a training sample,
acquiring the sensitive physical parameters in a first time period, and recording the wind speed and the wind direction;
after the interval of the first preset time, acquiring the sensitive physical parameters in the second time period again, and recording the wind speed and the wind direction;
after a second preset time interval, acquiring the sensitive physical parameters in a third time period again, and recording the wind speed and the wind direction;
and when the difference value of every two wind speeds is smaller than a first threshold value and the difference value of every two wind directions is smaller than a second threshold value in the three obtained results, preprocessing the average value of each sensitive physical parameter in the three obtained results and then taking the preprocessed average value as the training sample.
In some embodiments, in the step of obtaining sensitive physical parameters of the site area for a period of time and preprocessing, when a difference between every two wind speeds is greater than a first threshold value or a difference between every two wind directions is greater than a second threshold value in results obtained in three times, the sensitive physical parameters in the results obtained in the three times are preprocessed and then used as the training samples.
In some embodiments, in the step of establishing an atmospheric particulate pollution occurrence condition discrimination model in the site by regions, and performing model training on the training sample, the atmospheric particulate pollution occurrence condition discrimination model includes an input layer, a hidden layer, and an output layer, where the number of nodes of the input layer is the same as the number of terms of the sensitive physical parameter, the number of nodes of the output layer is the same as the number of model output variables, and the number of hidden layers and the number of nodes are selected comprehensively according to training errors and discrimination accuracy.
In some embodiments, before the step of calculating the judgment result of the atmospheric particulate pollution occurrence area based on the calculation model by using the sensitive physical parameter data in the target area to be judged as the model input parameters,
calculating sensitive physical parameter data of a known atmospheric particulate pollution area as a model input parameter to obtain an atmospheric particulate pollution area calculation value containing a geographical position coordinate;
comparing the coordinates of the calculated value of the atmospheric particulate pollution area with the coordinates of the real atmospheric particulate pollution area;
and when the coordinates of the calculated value of the atmospheric particulate pollution area are consistent with the coordinates of the real atmospheric particulate pollution area, the calculation model is accurate.
In some embodiments, after the step of obtaining the calculation model for determining the atmospheric particulate pollution key region, based on the determination result, the atmospheric particulate region transmission event identification, the horizontal transmission characteristic, the vertical diffusion characteristic, and the key region feature are analyzed to obtain a diffusion rule of the atmospheric particulate pollution, where the diffusion rule is used to predict an area where the atmospheric particulate pollution occurs and an atmospheric particulate pollution diffusion condition.
In some embodiments, a database is established based on the correspondence between the diffusion rules and the calculation model, and the database is used as a reference for assisting at least one of pollution accurate prediction and auxiliary supervision decision.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the technical progress that at least one of the following steps is included:
1. the invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which comprises the steps of determining sensitive physical parameters from the multi-source data, then carrying out model training to obtain a calculation model, determining a judgment result comprising the atmospheric particulate pollution key area based on the calculation model, and carrying out timely and accurate supervision and decision-making on the atmospheric particulate pollution area according to the judgment result by related workers;
2. the invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which is beneficial to comprehensively considering factors of all aspects and enabling a final monitoring result to be accurate by taking data such as air station particulate concentration, road particulate concentration, construction site particulate concentration and the like as sensitive physical parameters;
3. the invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which is beneficial to ensuring the accuracy of a training sample by determining the training sample in a mode of comparing a wind direction difference value with a wind direction difference value;
4. the invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which is beneficial to predicting the pollution time of a target point in a certain period of time next by analyzing the transmission event identification, horizontal transmission characteristic, vertical diffusion characteristic and key area characteristic of the atmospheric particulate area, so as to be beneficial to taking precautions;
5. the invention provides a method for determining an atmospheric particulate pollution key area based on multi-source data, which is characterized in that a database is established based on the corresponding relation between the diffusion rule and the calculation model, related workers can conveniently call data for analysis, the data can be used as a reference for at least one of auxiliary pollution accurate prediction and auxiliary supervision decision, and the accurate decision of the workers is further promoted.
Drawings
FIG. 1 is a block flow diagram of a method for determining an area of concern of atmospheric particulate contamination based on multi-source data according to a first embodiment of the present invention;
FIG. 2 is a block flow diagram of a sample determining step in a method for determining an atmospheric particulate contamination (PM) key region based on multi-source data according to a second embodiment of the present invention;
FIG. 3 is a block flow diagram illustrating the steps of the verification calculation model in the method for determining the atmospheric particulate contamination key region based on the multi-source data according to the second embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following examples:
although along with the development of science and technology, science and technology environmental protection project is more and more, and all kinds of monitoring systems are complicated various, can effectively save each item monitoring data, but independent operation between each monitoring system for environmental supervision deals with the department and is sensitive inadequately to the discernment of atmospheric particulates pollution incident, and the processing to atmospheric particulates pollution is timely inadequately, has seriously restricted atmospheric environment quality to improve.
Based on the defects, the method and the device are used for monitoring multi-source data, determining sensitive physical parameters as model input parameters, and establishing the corresponding relation between the atmospheric pollutant particles and the region through model training so as to predict the key region polluted by the atmospheric particulate matters timely and accurately and facilitate the timely processing of related personnel. The method for determining the atmospheric particulate pollution key area based on multi-source data is specifically explained below.
As shown in fig. 1, a method for determining an atmospheric particulate pollution focal region based on multi-source data includes the following steps:
in step 100, a site of an atmospheric particulate monitoring station is selected, and a monitoring field is erected on the site.
The method comprises the steps that a national standard air monitoring station is used as a station address, the station address is used as a center, the range with the outward radiation radius of 1 kilometer is determined as an area to be monitored, and the national standard air quality monitoring station networking can monitor real-time data of the concentration of particles in the air station. At the moment, the range of the area to be monitored can meet the diffusion movement of particulate pollution in the atmosphere, and the monitoring range can be narrowed as much as possible on the basis of meeting the sampling requirement, so that the monitoring efficiency and accuracy are improved.
It should be noted that the monitoring of atmospheric particulate pollution is generally performed in terms of PM 10 And PM 2.5 And monitoring the monitored object.
In step 200, original multi-source data in the station site are monitored, sensitive physical parameters are determined, and the sensitive physical parameters are used as model input parameters, wherein the sensitive physical parameters are at least one item in the multi-source data, and the sensitive physical parameters are factors influencing atmospheric particulate pollution.
It will be appreciated that the raw multi-source data may be any variable factor that may affect the monitoring of the distribution of the atmospheric particulate matter region, such as weather data including rainfall, wind direction, wind speed, and the like, and atmospheric particulate matter type, and the like. Experiments show that sensitive physical parameters influencing the generation of atmospheric particulate pollution can be obtained by analyzing the relationship between atmospheric particulate matters and meteorological factors and precursors. And in some embodiments, the sensitive physical parameters include air station particulate matter concentration, road particulate matter concentration, worksite particulate matter concentration, particulate matter focus grid data, region of focus particulate matter concentration, underlying surface data, blend layer height data, and wind direction data. Wherein, the meteorological data is data of the nearest position from the center of the effective environment monitoring station; the underlying surface information mainly comprises terrain height, land coverage and soil texture. The correlation coefficient of each physical parameter and the atmospheric particulate pollution is shown in table 1.
Table 1. Correlation coefficient of each physical parameter with atmospheric particulate pollution.
It can be understood that in the process of monitoring original multi-source data in a station site, appropriate monitoring equipment can be selected according to actual needs, for example, when the concentration of particulate matters in a target area needs to be monitored, national standard air quality monitoring stations can be adopted for networking; when the concentration of the road particles needs to be monitored, a taxi cruising road monitoring system can be adopted; when the concentration of the particulate matters on the construction site needs to be monitored, a construction site lift monitoring system can be adopted; when the key grid concentration data of the particulate matter needs to be monitored, a satellite remote sensing particulate matter monitoring system can be adopted; when the concentration data of the particulate matters in the key area needs to be monitored, a laser radar navigation monitoring system can be adopted.
Through multiple types of particulate matter concentrations such as integrated analysis air station particulate matter concentration, road particulate matter concentration and building site particulate matter concentration to combine underlying surface data, mix layer height data and wind direction data, can balance the influence of each factor to atmospheric particulates pollution diffusion, and then help considering each factor comprehensively, and then accurately acquire the model that can confirm atmospheric particulates pollution focus area.
In step 300, the sensitive physical parameters of the station area are obtained for a period of time, and are preprocessed to construct a training sample.
It should be noted that, when the model is trained, the number of samples is not less than 45, and because the multidimensional input samples belong to different dimensions and the order of magnitude difference is large, each input parameter must be preprocessed, so that the influence on the network identification precision due to the order of magnitude difference is avoided. And in some embodiments, the preprocessing mode adopts normalization processing, that is, the input parameters are normalized to be between 0 and 1 by adopting a maximum and minimum value normalization method.
In some embodiments, as shown in fig. 2, in the step of obtaining sensitive physical parameters of a site area for a period of time and performing preprocessing, the method specifically includes the following steps:
step 320, after the interval of the first preset time, acquiring the sensitive physical parameters in the second time period again, and recording the wind speed and the wind direction;
and 340, calculating the difference value of every two wind speeds of every two wind directions of every two wind speeds and the difference value of every two wind directions, wherein when the difference value of every two wind speeds is smaller than a first threshold value and the difference value of every two wind directions is smaller than a second threshold value in the results obtained in three times, the influence of environmental factors on the results obtained in three times is small, and therefore the average value of all sensitive physical parameters in the results obtained in three times is preprocessed to be used as a training sample.
And 350, when the difference value of every two wind speeds is greater than a first threshold value or the difference value of every two wind directions is greater than a second threshold value in the three acquired results, preprocessing all the sensitive physical parameters in the three acquired results to serve as training samples.
Wherein, the sampling is generally performed within 1.5-2 hours, and the first predetermined time and the second predetermined time may be the same or different, for example, the first predetermined time and the second predetermined time may be both 30min. The first threshold may be 0.6, 0.8, or 1; the second threshold value can be 1, 1.2 or 1.5, and the first threshold value and the second threshold value can be set according to the actual monitoring condition.
According to the difference of every two wind speeds and the difference of every two wind directions, sampling is carried out, the accuracy of the samples is improved, and the accuracy of the final result is improved.
In step 400, an atmospheric particulate pollution occurrence condition discrimination model is established at the site, model training is performed on a training sample, and a calculation model for determining an atmospheric particulate pollution key area is obtained.
Wherein, in some embodiments, also can carry out the subregion to the station address to establish the discriminant model respectively in different regions and train, at this moment, can reduce the region to atmospheric particulates pollution's influence, and then help whole atmospheric particulates pollutant monitoring process more accurate. Since the data processing processes in the respective areas are consistent, the following embodiments are specifically described in the case of non-partitioned areas for convenience of description, and experiments show that different partitions in a site area have less influence on atmospheric particulate pollution.
It can be understood that the required discriminant model is finally obtained by selecting a proper transfer function, a learning training function, training times, a target error and a target error measurement index, and repeatedly adjusting the weight and the threshold value through signal forward propagation and error backward propagation until the preset learning training times or the output error is reduced to an allowable degree.
For example, in some embodiments, the transfer function used for model training is a logarithmic sigmoid transfer function (logsig), the learning training function is a gradient descent method (slingdx) with momentum and adaptive learning rate, the training times are 10000, the target error metric is Mean Square Error (MSE), and the target error is selected according to specific requirements. In other examples, these parameters may be adjusted as the case may be. And (3) repeatedly adjusting the weight and the threshold value through signal forward propagation and error backward propagation until preset learning training times or the output error is reduced to an allowable degree, and finally obtaining the required discrimination model. In the present embodiment, the modeling uses a BP neural network, and in actual operation, other machine learning methods may also be used to replace the BP neural network, for example: random forest, long and short time memory neural network, GRU (Gated Recurrent) neural network, etc.
In some embodiments, the atmospheric particulate pollution occurrence condition discrimination model comprises an input layer, a hidden layer and an output layer, the number of nodes of the input layer is the same as the number of terms of the sensitive physical parameter, the number of nodes of the output layer is the same as the number of model output variables, and the hidden layer is hiddenAnd the number of layers and the number of nodes are comprehensively selected according to the training error and the judgment accuracy. For example, in some embodiments, when the sensitive physical parameters are air station particulate matter concentration, road particulate matter concentration, construction site particulate matter concentration, particulate matter key grid data, key area particulate matter concentration, underlying surface data, mixed layer height data and wind direction data, and the data output after calculation by the atmospheric particulate matter pollution occurrence condition judgment model is PM in atmospheric particulate matter pollution 10 And PM 2.5 The total concentration, the level of the total concentration and the coordinate position of the area, so that the number of nodes of the input layer is 8, and the number of nodes of the output layer is 5. Wherein PM 10 And PM 2.5 The grade of the total concentration of (a) is preset by a human.
It should be noted that too few hidden layers and nodes tend to result in poor training results, and too many nodes tend to result in long training time, so it is important to select the appropriate number of nodes of the hidden layers by using training errors and discrimination accuracy. The training error is the mean square error of the network training result and the expected result value. The network training result is correct when the network training result is consistent with the expected result, and is wrong when the network training result is inconsistent with the expected result, and the judgment accuracy rate refers to the percentage of the correct sample number to the total sample number. From the viewpoint of saving computing resources and achieving ideal discrimination capability, the number of nodes of the hidden layer of the first layer is set to be proper between [7,9], and the number of nodes of the hidden layer of the second layer is 1-2 more than that of the nodes of the first layer.
Through the experiments of the application, the r value of the obtained calculation model is kept between 0.914 and 0.925 (PM) 2.5 )，0.943-0.955(PM 10 ) Therefore, the correlation between the predicted value and the actual value of the calculation model is better, and the model is more reliable.
In some embodiments, as shown in fig. 3, when the calculation model is obtained after the model training is completed, the following steps may be further performed:
and step 410, calculating by using the sensitive physical parameter data of the known atmospheric particulate pollution area as a model input parameter, and acquiring an atmospheric particulate pollution area calculation value containing a geographical position coordinate.
And step 420, comparing the coordinates of the calculated value of the atmospheric particulate pollution area with the coordinates of the real atmospheric particulate pollution area.
And 430, when the coordinates of the calculated value of the atmospheric particulate pollution area are consistent with the coordinates of the real atmospheric particulate pollution area, indicating that the calculation model is accurate.
Sensitive physical parameter data of the atmospheric particulate pollution area are known to be historical live data or measured data.
By the mode, whether the calculation model is accurate or not can be effectively verified, and after 120 times of verification, the calculation model can be found to have the accuracy rate of over 94.9% and meet the test requirements, namely the calculation model has relatively accurate identification and judgment capacity and is expected to become a new assessment and prediction method for preventing and treating the atmospheric ozone pollution.
In step 500, sensitive physical parameter data in a target area to be distinguished is used as a model input parameter, and a distinguishing result of an atmospheric particulate pollution key occurrence area is obtained based on a calculation model.
In some embodiments, the analysis and research of the system can be performed on the contents of the atmospheric particulate matter region transmission event recognition, the horizontal transmission characteristic, the vertical diffusion characteristic, the key region characteristic and the like based on the judgment result including the key region of the atmospheric particulate matter pollution, so as to obtain the diffusion rule of the atmospheric particulate matter pollution, wherein the diffusion rule is used for predicting the region of the atmospheric particulate matter pollution and the diffusion condition of the atmospheric particulate matter pollution.
Wherein, the transmission event identification relates to air quality monitoring data in all areas near the station, and is mainly characterized by the transmission range of the atmospheric particulate pollutants, namely the overall particulate matter concentration in a large-scale (natural area where the target station is located, such as city, province and customs plain) area; the horizontal transmission characteristics relate to meteorological data (mainly wind speed, wind direction, temperature and humidity) and are mainly used for representing a wind-following transmission path of atmospheric particulates; the vertical diffusion condition relates to height data of an atmospheric boundary layer and is mainly used for representing the concentration change condition of atmospheric particulate matters of a target site; the key area features relate to air quality monitoring data of a site monitoring area, and are mainly used for representing the concentration of small-scale (within one kilometer of a target site) particles. The method is favorable for accurately predicting the atmospheric particulate pollution transmission condition of the key area to be detected according to the diffusion rule.
In some embodiments, the diffusion rules are associated with the calculation model, and a database is established based on the association, wherein the database is used for assisting in reference of at least one of pollution accurate prediction and supervision decision. The database has a strong storage function, is beneficial to workers to call and analyze data at any time, and makes effective decisions based on the data of the database.
By establishing an atmospheric particulate pollution area transmission research method based on multi-source data, the identification and transmission channel reconstruction of the area atmospheric pollution transmission event, the horizontal transmission characteristic analysis and the vertical diffusion characteristic analysis in the atmospheric particulate pollution transmission process are completed, the diffusion characteristic of atmospheric particulate pollution is facilitated to be known, the possible development trend of atmospheric particulate matters and the pollution time, the area and the concentration which are possible to be diffused in a certain time period next to a target point can be accurately predicted, and the atmospheric particulate pollution area transmission research method can be used as an effective reference in pollution accurate prediction and auxiliary supervision decision; and the computer dispatching system can also send out early warning, and the target point position receiving the early warning signal can be prevented in advance.
For example, a particle pollution key area within a radius of 1 kilometer is identified through a calculation model, a 'precise pollution control' management and control suggestion is formed, a management and control task is distributed through a command scheduling system at the first time, an environmental management department is assisted in targeted supervision, and the working efficiency of pollution disposal is improved.
For another example, when the atmospheric particulate pollution concentration in a certain area is monitored, the position coordinates of the area can be obtained through the calculation model, and the diffusion rule of the atmospheric particulate pollution in the area can be obtained through the database, so that relevant workers can be guided to make a decision quickly and accurately, and the PM is reduced as much as possible 2.5 And PM 10 The effect of the dominant particulate matter on urban areas.
In some embodiments, monitoring tasks and alarm processing may be set up at the site, separately for the PM 10 And PM 2.5 The concentration ranking end station alarms, and when PM is generated 2.5 Less than or equal to 20 microgram/cubic meter, and PM 10 When the concentration is less than or equal to 5 micrograms/cubic meter, no alarm is generated. And alarms within 24h may be merged for display, e.g., if the last hour of alarms was not processed, the hour of alarms may be merged into one presentation.
In some embodiments, when the alarm with the same rule and the same index exists for three consecutive hours, the alarm is a first-level alarm, and related personnel are supervised to go to an atmospheric particulate pollution area for treatment. When a task is processed, the task is not issued again; however, if the task in the process lasts for 24 hours, the task is issued again.
The method has the advantages that the station address of the atmospheric particulate monitoring station is selected, the sensitive physical parameters are determined, model training is carried out to obtain a calculation model, the judgment result of the atmospheric particulate pollution key occurrence area is determined based on the calculation model, and the judgment result can be used as effective reference of relevant workers to enable the workers to make decisions and supervise accurately; further, the air station particulate matter concentration, the road particulate matter concentration, the construction site particulate matter concentration, the particulate matter key grid data, the key area particulate matter concentration, the underlying surface data, the mixed layer height data, the wind direction data and other data are used as sensitive physical parameters, so that the final monitoring result is accurate by balancing all factors; further, by analyzing the atmospheric particle area transmission event identification, the horizontal transmission characteristic, the vertical diffusion characteristic and the key area characteristic, the method is beneficial to predicting the pollution time of the target point in a certain period of time, and further beneficial to preventing; and further, the accuracy of the training sample is favorably ensured by comparing the wind speed difference value with the wind direction difference value.
The foregoing description, for purposes of explanation, has been presented in conjunction with specific embodiments. However, the foregoing discussion in some embodiments is not intended to be exhaustive or to limit the implementations to the precise forms disclosed above. Many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles and the practical application, to thereby enable others skilled in the art to best utilize the embodiments and various embodiments with various modifications as are suited to the particular use contemplated, and it is therefore to be understood that various modifications and improvements will be apparent to those skilled in the art upon the basis of the present invention. Therefore, modifications or improvements are within the scope of the invention without departing from the spirit of the inventive concept.
Claims (8)
1. A method for determining an atmospheric particulate contamination focal region based on multi-source data, the method comprising:
selecting a site of an atmospheric particulate monitoring station, and erecting a monitoring field on the site;
monitoring original multi-source data in the station site, determining a sensitive physical parameter, and taking the sensitive physical parameter as a model input parameter, wherein the sensitive physical parameter is at least one item in the multi-source data, and the sensitive physical parameter is a factor influencing atmospheric particulate pollution;
acquiring various sensitive physical parameters of the station site area for a period of time, preprocessing the parameters and constructing a training sample;
establishing an atmospheric particulate pollution occurrence condition judgment model at the site, and performing model training on the training sample to obtain a calculation model for determining an atmospheric particulate pollution key area;
and taking the sensitive physical parameter data in the target area to be distinguished as a model input parameter, and obtaining a distinguishing result of the major occurrence area including the atmospheric particulate pollution based on the calculation model.
2. The method of claim 1, wherein the step of monitoring the original multi-source data in the site, determining the sensitive physical parameter, and using the sensitive physical parameter as a model input parameter, comprises:
the sensitive physical parameters comprise air station particulate matter concentration, road particulate matter concentration, construction site particulate matter concentration, particulate matter key grid data, key area particulate matter concentration, underlying surface data, mixed layer height data and wind direction data.
3. The method for determining the atmospheric particulate pollution focal region based on the multi-source data according to claim 2, wherein in the steps of obtaining various sensitive physical parameters in the site region for a period of time, preprocessing the parameters, and constructing a training sample, the method is characterized in that:
acquiring the sensitive physical parameter in a first time period, and recording the wind speed and the wind direction;
after the interval of the first preset time, acquiring the sensitive physical parameters in the second time period again, and recording the wind speed and the wind direction;
after a second preset time interval, acquiring the sensitive physical parameters in a third time period again, and recording the wind speed and the wind direction;
and when the difference value of every two wind speeds is smaller than a first threshold value and the difference value of every two wind directions is smaller than a second threshold value in the three obtained results, preprocessing the average value of each sensitive physical parameter in the three obtained results and then taking the preprocessed average value as the training sample.
4. The method for determining the atmospheric particulate pollution focal region based on the multi-source data according to claim 3, wherein in the step of obtaining and preprocessing the sensitive physical parameters of the site region for a period of time, the method is characterized in that:
and when the difference value of every two wind speeds is greater than a first threshold value or the difference value of every two wind directions is greater than a second threshold value in the three acquired results, preprocessing all the sensitive physical parameters in the three acquired results to serve as the training samples.
5. The method for determining the atmospheric particulate pollution key area based on the multi-source data according to claim 1, wherein in the step of establishing an atmospheric particulate pollution occurrence condition discrimination model in the site division area and performing model training on the training sample, the method is characterized in that:
the atmospheric particulate pollution occurrence condition judgment model comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the input layer is the same as the number of terms of the sensitive physical parameters, the number of nodes of the output layer is the same as the number of model output variables, and the number of the hidden layer and the number of nodes are selected comprehensively according to training errors and judgment accuracy.
6. The method for determining the atmospheric particulate pollution important region based on the multi-source data according to claim 5, wherein before the step of calculating the judgment result of the atmospheric particulate pollution occurrence region based on the calculation model by using the sensitive physical parameter data in the target region to be judged as the model input parameters, the method is characterized in that:
calculating sensitive physical parameter data of a known atmospheric particulate pollution area as a model input parameter to obtain an atmospheric particulate pollution area calculation value containing a geographical position coordinate;
comparing the coordinate of the calculated value of the atmospheric particulate pollution area with the coordinate of the real atmospheric particulate pollution area;
and when the coordinates of the calculated value of the atmospheric particulate pollution area are consistent with the coordinates of the real atmospheric particulate pollution area, the calculation model is accurate.
7. The method for determining the atmospheric particulate pollution focal region based on the multi-source data according to any one of claims 1 to 6, after the step of obtaining the calculation model for determining the atmospheric particulate pollution focal region, the method is characterized in that:
and analyzing the atmospheric particulate matter region transmission event recognition, the horizontal transmission characteristic, the vertical diffusion characteristic and the key region characteristic based on the judgment result to obtain a diffusion rule of atmospheric particulate matter pollution, wherein the diffusion rule is used for predicting the region where the atmospheric particulate matter pollution occurs and the atmospheric particulate matter pollution diffusion condition.
8. The method for determining the atmospheric particulate contamination focal region based on multi-source data according to claim 7, wherein:
and establishing a database based on the corresponding relation between the diffusion rule and the calculation model, wherein the database is used as a reference for assisting at least one of accurate pollution prediction and auxiliary supervision decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211109754.1A CN115578227A (en) | 2022-09-13 | 2022-09-13 | Method for determining atmospheric particulate pollution key area based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211109754.1A CN115578227A (en) | 2022-09-13 | 2022-09-13 | Method for determining atmospheric particulate pollution key area based on multi-source data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115578227A true CN115578227A (en) | 2023-01-06 |
Family
ID=84581341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211109754.1A Pending CN115578227A (en) | 2022-09-13 | 2022-09-13 | Method for determining atmospheric particulate pollution key area based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115578227A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115950797A (en) * | 2023-03-02 | 2023-04-11 | 北京复兰环保科技有限公司 | Pollutant tracing method and system |
| CN117434295A (en) * | 2023-10-24 | 2024-01-23 | 广州远动信息技术有限公司 | Intelligent processing and evaluating method for acoustic chromatographic signal intensity data |
-
2022
- 2022-09-13 CN CN202211109754.1A patent/CN115578227A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115950797A (en) * | 2023-03-02 | 2023-04-11 | 北京复兰环保科技有限公司 | Pollutant tracing method and system |
| CN117434295A (en) * | 2023-10-24 | 2024-01-23 | 广州远动信息技术有限公司 | Intelligent processing and evaluating method for acoustic chromatographic signal intensity data |
| CN117434295B (en) * | 2023-10-24 | 2024-04-05 | 广州远动信息技术有限公司 | Intelligent processing and evaluating method for acoustic chromatographic signal intensity data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106650825B (en) | Motor vehicle exhaust emission data fusion system | |
| CN115578227A (en) | Method for determining atmospheric particulate pollution key area based on multi-source data | |
| CN112308292B (en) | Method for drawing fire risk grade distribution map | |
| CN114118677A (en) | Tailing pond risk monitoring and early warning system based on Internet of things | |
| CN105069537B (en) | A kind of construction method of combination type air Quality Prediction | |
| CN109784752A (en) | A kind of reservoir area of Three Gorges water eutrophication risk assessment early warning system and its analysis method | |
| CN115358332A (en) | Atmospheric pollution tracing method for multi-source data | |
| CN104899437A (en) | Early-warning method for heavy-rainfall type landslide hazard | |
| CN110084418A (en) | A kind of monitoring point optimization distribution method of burst atmosphere pollution accident emergency monitoring | |
| CN111009155B (en) | Air traffic flow complexity quantitative analysis method based on airspace structure and flight flow | |
| CN112132371A (en) | Urban flood risk assessment method based on coupled entropy weight-fuzzy clustering algorithm | |
| CN114155129A (en) | Atmospheric environment traceability method and system based on industrial park | |
| CN114077970B (en) | Method and device for determining carbon emission related factor based on urban morphology | |
| CN114662344B (en) | Atmospheric pollution source tracing prediction method and system based on continuous online observation data | |
| CN113836808A (en) | PM2.5 deep learning prediction method based on heavy pollution feature constraint | |
| CN115759488A (en) | Carbon emission monitoring and early warning analysis system and method based on edge calculation | |
| CN116402369A (en) | Smart city traffic operation safety monitoring data evaluation system and method | |
| Hernandez et al. | Analysis of the information obtained from PM 2.5 concentration measurements in an urban park | |
| CN117538503A (en) | Real-time intelligent soil pollution monitoring system and method | |
| CN115146484A (en) | Environment-friendly monitoring system and monitoring method for detecting environmental parameters | |
| CN117761261B (en) | Big data-based carbon emission monitoring system and method | |
| CN117312784A (en) | Pollution source tracing method based on receptor model and big data combination | |
| CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
| CN112257329A (en) | Method for judging influence of typhoon on line | |
| CN113295589B (en) | Raise dust monitoring method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |