WO2024103616A1 - 空气污染预警方法、装置、电子设备及存储介质 - Google Patents

空气污染预警方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2024103616A1
WO2024103616A1 PCT/CN2023/087822 CN2023087822W WO2024103616A1 WO 2024103616 A1 WO2024103616 A1 WO 2024103616A1 CN 2023087822 W CN2023087822 W CN 2023087822W WO 2024103616 A1 WO2024103616 A1 WO 2024103616A1
Authority
WO
WIPO (PCT)
Prior art keywords
air pollution
station
micro
standard monitoring
historical
Prior art date
Application number
PCT/CN2023/087822
Other languages
English (en)
French (fr)
Inventor
张朝
马景金
张彤
郑娜
付文杰
张振忠
马博健
潘本峰
Original Assignee
河北先河环保科技股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 河北先河环保科技股份有限公司 filed Critical 河北先河环保科技股份有限公司
Publication of WO2024103616A1 publication Critical patent/WO2024103616A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0004—Gaseous mixtures, e.g. polluted air
    • G01N33/0009—General constructional details of gas analysers, e.g. portable test equipment
    • G01N33/0062—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display
    • G01N33/0063—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a threshold to release an alarm or displaying means
    • G01N33/0065—General constructional details of gas analysers, e.g. portable test equipment concerning the measuring method or the display, e.g. intermittent measurement or digital display using a threshold to release an alarm or displaying means using more than one threshold
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • G06N5/025—Extracting rules from data

Definitions

  • the present application belongs to the field of pollutant monitoring technology, and in particular, relates to an air pollution early warning method, device, electronic equipment and storage medium.
  • the current monitoring network has many micro monitoring stations (micro stations) in addition to standard monitoring stations, such as national control stations, provincial control stations, and municipal control stations.
  • the micro-station closest to the pollution source detects air pollution first, and after a period of time, the standard monitoring station closer to the pollution source can detect air pollution, that is, the standard monitoring station has a certain lag in detecting pollution relative to the micro-station. Therefore, how to associate the standard monitoring station with the micro-station, and when the micro-station detects pollution, predict and warn the pollution that the standard monitoring station is about to detect, so as to carry out prevention and cause analysis in advance, is a problem that needs to be solved urgently.
  • embodiments of the present application provide an air pollution warning method, device, electronic device, and storage medium to predict and warn of impending pollution at standard monitoring sites.
  • a first aspect of an embodiment of the present application provides an air pollution early warning method, comprising:
  • the association rule probability library contains the association relationship between each micro-station and each standard monitoring station under different wind directions, and the probability of air pollution events occurring at each standard monitoring station associated with each micro-station under different wind directions when an air pollution event occurs;
  • air pollution warnings are issued to each standard monitoring station associated with the micro station.
  • a process of establishing an association rule probability library includes:
  • any micro-station under any wind direction if a certain standard monitoring station also detects a historical air pollution event within a preset time after the micro-station detects a historical air pollution event, and the micro-station and the standard monitoring station meet the preset association prerequisite, then the standard monitoring station is associated with the micro-station, and the association relationship between the micro-station and each standard monitoring station under the wind direction is obtained by traversing all the historical air pollution events detected by the micro-station under the wind direction;
  • the number k1 of historical air pollution events that occurred at the microstation under the wind direction and the number k2 of historical air pollution events that occurred at each standard monitoring station associated with the microstation under the wind direction are counted, and the ratio of k2 to k1 is calculated to obtain the probability of air pollution events occurring at each standard monitoring station associated with the microstation when an air pollution event occurs at the microstation under the wind direction; an association rule probability library is established based on the association relationship between each microstation and each standard monitoring station under different wind directions and the probability of air pollution events occurring at each standard monitoring station associated with each microstation when an air pollution event occurs at the microstation under different wind directions.
  • determining the historical air pollution events detected by each micro-station in the target area and the historical air pollution events detected by each standard monitoring station includes:
  • historical air pollution events are determined from the historical air monitoring data through the peak detection algorithm, and the historical air pollution events detected by each microstation in the target area and the historical air pollution events detected by each standard monitoring station are obtained.
  • the air pollution events and historical air pollution events are carbon monoxide pollution events, and the historical air monitoring data are carbon monoxide concentration monitoring data; or, the air pollution events and historical air pollution events are sulfur dioxide pollution events, and the historical air monitoring data are sulfur dioxide concentration monitoring data;
  • the detection parameters of the peak detection algorithm are different.
  • determining whether the micro station and the standard monitoring station meet the preset association prerequisite includes:
  • the first condition, the second condition and the third condition are simultaneously met within a preset time after the microstation detects a historical air pollution event, it is determined that the preset association precondition is met;
  • the first condition is that the distance is less than a preset distance threshold
  • the second condition is that the angle is less than a preset angle threshold
  • the third condition is that the wind speed in the target area is within a preset wind speed range.
  • the method further includes updating the association rule probability database at preset time intervals;
  • the process of updating the association rule probability library includes:
  • the air pollution events occurring at each microstation and each standard monitoring station within the preset time interval are added to the corresponding historical air pollution events, and the probability of air pollution events occurring at each standard monitoring station associated with each microstation under different wind directions is recalculated.
  • the method further includes:
  • a standard monitoring station associated with the micro station also detects the air pollution event, then it is determined that the two air pollution events are related.
  • a second aspect of an embodiment of the present application provides an air pollution warning device, comprising:
  • An acquisition module is used to obtain the air pollution detection results of each micro-station in the target area
  • a query module is used to obtain the current wind direction of the target area if any micro station detects an air pollution event, and query the probability of air pollution events occurring at each standard monitoring station associated with the micro station under the current wind direction from a preset association rule probability library;
  • the association rule probability library contains the association relationship between each micro station and each standard monitoring station under different wind directions, and the probability of air pollution events occurring at each standard monitoring station associated with each micro station under different wind directions when an air pollution event occurs;
  • the early warning module is used to issue an air pollution early warning to each standard monitoring station associated with the micro station according to the probability of an air pollution event occurring at each standard monitoring station associated with the micro station under the queried current wind direction.
  • a third aspect of an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the steps of the air pollution warning method of the first aspect described above are implemented.
  • a fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program.
  • the computer program is executed by a processor, the steps of the air pollution warning method as described in the first aspect above are implemented.
  • the embodiment of the present application establishes an association rule probability library of the target area in advance, and the association rule probability library contains the association relationship between each micro station and each standard monitoring station under different wind directions, and the probability of air pollution events occurring at each standard monitoring station associated with each micro station when an air pollution event occurs under different wind directions, so that when any micro station detects an air pollution event, according to the current wind direction of the target area, the probability of air pollution events occurring at each standard monitoring station associated with the micro station under the current wind direction can be queried from the preset association rule probability library, and then air pollution warnings are issued for each standard monitoring station associated with the micro station.
  • the embodiment of the present application can predict and warn of the air pollution that is about to occur at the standard monitoring station, and can also provide an analysis basis for air pollution events detected at the standard monitoring station, such as discovering the source of pollutants, clarifying the cause of pollution, etc., to help relevant departments to control.
  • FIG1 is a schematic diagram of the distribution of air quality monitoring sites provided in an embodiment of the present application.
  • FIG2 is a schematic diagram of an implementation flow of an air pollution early warning method provided in an embodiment of the present application.
  • FIG. 3 is a schematic diagram of the association relationship between a micro station and a standard monitoring station provided in an embodiment of the present application;
  • FIG4 is a schematic diagram of the structure of an air pollution warning device provided in an embodiment of the present application.
  • FIG. 5 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
  • Micro stations are mostly deployed at locations where pollution sources may exist to monitor air pollution in a small area.
  • Standard monitoring stations such as national control stations, provincial control stations, and municipal control stations, monitor air pollution in a large area. Therefore, when an air pollution incident occurs, the micro station closest to the pollution source usually detects air pollution first, and the standard monitoring station can detect air pollution after a period of time.
  • area A as an example, as shown in Figure 1, there are more than a thousand air quality monitoring stations of various types (only some micro stations and some standard monitoring stations are shown in Figure 1).
  • Using the monitoring data of these air quality monitoring stations to explore the association rules of standard monitoring stations and micro stations, it is possible to predict and warn of the impending pollution at the standard monitoring stations, find possible sources of pollutants, clarify the causes of pollution, and help relevant departments to control.
  • FIG2 is a schematic diagram of the implementation process of the air pollution early warning method provided in the embodiment of the present application. As shown in FIG2, the method includes:
  • Step S101 obtaining air pollution detection results of each micro station in the target area.
  • the current air pollution detection results of each micro-station in the target area can be directly obtained from the monitoring network system, for example, which micro-station currently has an air pollution event.
  • the target area can be a city, and the air pollution event can be CO pollution, SO2 pollution, etc.
  • the monitoring data of the standard monitoring station and the micro station can be read every half an hour, and then merged with the historical monitoring data, and the pollution cases can be found and divided through data preprocessing and peak detection algorithms to determine the pollution cases that occurred at each micro station in the past half an hour, and obtain the air pollution detection results of each micro station.
  • the data preprocessing and peak detection algorithms will be introduced in detail later in this manual.
  • Step S102 if any micro station detects an air pollution event, the current wind direction of the target area is obtained, and the probability of an air pollution event occurring at each standard monitoring station associated with the micro station under the current wind direction is queried from the preset association rule probability library;
  • the association rule probability library contains the association relationship between each micro station and each standard monitoring station under different wind directions, and the probability of an air pollution event occurring at each standard monitoring station associated with each micro station under different wind directions when an air pollution event occurs.
  • a micro station detects an air pollution event, such as CO pollution, and if the current wind direction is easterly, the probability of air pollution events occurring at each standard monitoring station associated with the micro station when the wind direction is easterly can be queried from the preset association rule probability library. It is understandable that due to the geographical location relationship between the micro station and the standard monitoring station, the standard monitoring station associated with the micro station is generally different under different wind directions, so the influence of wind direction must be considered when searching for associated standard monitoring stations.
  • an air pollution event such as CO pollution
  • Step S103 according to the queried probability of air pollution events occurring at each standard monitoring station associated with the micro station under the current wind direction, air pollution warning is issued to each standard monitoring station associated with the micro station.
  • the probabilities of air pollution events occurring at various standard monitoring stations associated with the microstation under the current wind direction queried in the association rule probability library are generally different. Standard monitoring stations with higher probabilities can be screened out to predict and warn of upcoming air pollution events.
  • a standard monitoring station associated with the micro station also detects the air pollution event, then it is determined that the two air pollution events are related.
  • the preset time can be set to a time period of 1-1.5 hours in the future. For example, when CO pollution is detected at a certain micro station within a time period of 1-1.5 hours after a certain standard monitoring station detects CO pollution, it can be determined that the two air pollution events are related. According to the location of the micro station, the source of pollutants and the cause of pollution of CO pollution detected by the standard monitoring station can be analyzed, thereby helping relevant departments to control.
  • the embodiment of the present application establishes an association rule probability library of the target area in advance, and the association rule probability library contains the association relationship between each micro station and each standard monitoring station under different wind directions, and the probability of air pollution events occurring at each standard monitoring station associated with each micro station when an air pollution event occurs under different wind directions, so that when any micro station detects an air pollution event, according to the current wind direction of the target area, the probability of air pollution events occurring at each standard monitoring station associated with the micro station under the current wind direction can be queried from the preset association rule probability library, and then air pollution warnings are issued for each standard monitoring station associated with the micro station.
  • the embodiment of the present application can predict and warn of the impending air pollution at the standard monitoring station, and can also provide an analysis basis for air pollution events detected at the standard monitoring station, such as discovering the source of pollutants, clarifying the cause of pollution, etc., to help relevant departments to control.
  • the process of establishing the above association rule probability library includes:
  • any micro-station under any wind direction if a certain standard monitoring station also detects a historical air pollution event within a preset time after the micro-station detects a historical air pollution event, and the micro-station and the standard monitoring station meet the preset association prerequisite, then the standard monitoring station is associated with the micro-station, and the association relationship between the micro-station and each standard monitoring station under the wind direction is obtained by traversing all the historical air pollution events detected by the micro-station under the wind direction;
  • the number k1 of historical air pollution events that occurred at the microstation under the wind direction and the number k2 of historical air pollution events that occurred at each standard monitoring station associated with the microstation under the wind direction are counted, and the ratio of k2 to k1 is calculated to obtain the probability of air pollution events occurring at each standard monitoring station associated with the microstation when an air pollution event occurs at the microstation under the wind direction; an association rule probability library is established based on the association relationship between each microstation and each standard monitoring station under different wind directions and the probability of air pollution events occurring at each standard monitoring station associated with each microstation when an air pollution event occurs at the microstation under different wind directions.
  • the association rule probability library is automatically constructed based on the urban data calculated by the model, according to the layout characteristics of the city's standard monitoring stations, micro stations, etc., and the correlation between standard monitoring stations and micro stations under the influence of different wind directions, wind speeds and distances.
  • the historical air pollution events of the standard monitoring stations and micro stations in City A in the last two months from the current time node are selected, and the historical air pollution events of the standard monitoring stations and the micro stations are associated. Since the detection of the standard monitoring stations has a lag, the association principle is that the historical air pollution events occurring at the standard monitoring stations are delayed by a preset time (for example, 1-2 hours after the historical air pollution events at the micro stations), and the preset association prerequisites are met between the two.
  • the results of the association analysis are shown in Table 1 and Figure 3, and each standard monitoring station and the ten micro stations with a high matching degree are obtained, and the number of associations between the standard monitoring stations and the micro stations with a high matching degree are also obtained.
  • the ratio of the number of times the standard monitoring station associated with the microstation is polluted under the current wind direction to the number of times the microstation is polluted under the current wind direction is the probability that the associated standard monitoring station will have an air pollution event when the microstation has an air pollution event under the current wind direction.
  • the probability library of some association rules can be seen in Table 2, which shows the microstation site name, the number of times the microstation is polluted under different wind direction conditions, and the corresponding probability of pollution at each standard monitoring station.
  • historical air pollution events are determined from the historical air monitoring data through the peak detection algorithm, and the historical air pollution events detected by each microstation in the target area and the historical air pollution events detected by each standard monitoring station are obtained.
  • standard monitoring site data, micro-station data, and meteorological data of the target city on the FTP server side may be collected, and the collected historical air monitoring data may be cleaned as follows (i.e., the historical air monitoring data may be pre-processed):
  • a peak detection algorithm is designed for the above-mentioned cleaned time series data, and high-value time periods are adaptively divided to find pollution cases.
  • the width of the peak cannot be determined in advance, and the peak height deviates significantly from other values.
  • the algorithm is updated in real time (each data point is updated). The algorithm steps are as follows:
  • Set the initial mobile calculation area size to n, the fluctuation parameter to threshold, the influence parameter to influence, and the activity data vector filteredY(n) y(1), etcy(n) in the mobile calculation area.
  • the air pollution events and historical air pollution events are carbon monoxide pollution events, and the historical air monitoring data are carbon monoxide concentration monitoring data; or, the air pollution events and historical air pollution events are sulfur dioxide pollution events, and the historical air monitoring data are sulfur dioxide concentration monitoring data; for different historical air monitoring data, the detection parameters of the peak detection algorithm are different.
  • the size of the mobile calculation area, fluctuation parameters, impact parameters, etc. are adjusted accordingly, so that air pollution events can be identified more accurately.
  • determining whether the micro station and the standard monitoring station meet the preset association prerequisite includes:
  • the first condition, the second condition and the third condition are simultaneously met within a preset time after the microstation detects a historical air pollution event, it is determined that the preset association precondition is met;
  • the first condition is that the distance is less than a preset distance threshold
  • the second condition is that the angle is less than a preset angle threshold
  • the third condition is that the wind speed in the target area is within a preset wind speed range.
  • association process may also be described in detail as follows:
  • the main thread program runs and reads the half-hourly data of the FTP server standard monitoring site and micro site every half hour.
  • the new standard monitoring site data and the new micro site data are merged with the three-day historical accumulated data.
  • the accumulated data maintains three days of data, and the data beyond the three days before the current time is automatically deleted.
  • the secondary thread program runs and reads meteorological data from the FTP server every three days.
  • the meteorological data contains information such as wind speed and wind direction in the past three days.
  • the meteorological data is matched with the standard monitoring station and microstation data in the past three days according to the hourly time.
  • the third step is to divide the micro-station pollution cases in the main thread.
  • the cleaned micro-station data of the last three days is processed through the peak detection algorithm to form high, low and flat signals.
  • the high-value signal data is selected for division.
  • the division standard is that the time interval is less than 1 hour. If the high-value signal data is continuous, it is a pollution case. If the pollution case interval is greater than or equal to 1 hour, it is divided into another pollution case.
  • the standard monitoring station also runs in the secondary thread in the same way, and the pollution cases are divided according to the CO and SO2 parameters.
  • the time interval of 1 hour is selected according to the actual situation. If the interval is too small, multiple pollution cases may be caused by the same pollution event. If it is set too large, the same pollution case may be caused by multiple pollution events.
  • the fourth step is to match and merge the pollution cases of the micro-station and the standard monitoring station according to wind direction, wind speed, station distance, etc. Traverse the station name of the micro-station and the pollution cases to which it belongs. Since the standard monitoring station has a lag in responding to pollution relative to the micro-station, you can select the pollution case of the standard monitoring station whose peak value appears one to two hours later than the peak time of the pollution case, and the pollution case starts half an hour later than the pollution case. If the pollution case of the standard monitoring station does not exist, loop through the next one; if it exists, associate and merge the station name, start time, end time, peak time, longitude and latitude of the micro-station pollution case with the pollution case of the standard monitoring station.
  • the distance and angle between the two stations are calculated by the plane coordinate system of the standard monitoring station and the micro-station. Taking the micro-station as the starting point, the angle between the straight line connecting the micro-station and the standard monitoring station and the straight line in the direction of 0 degrees north is the angle between the two.
  • the calculation process is as follows:
  • dif_lon longitude of the micro-station plane coordinate system - longitude of the standard monitoring station plane coordinate system;
  • dif_lat the latitude of the plane coordinate system of this micro station - the latitude of the plane coordinate system of this standard monitoring station;
  • the wind speed of the microstation pollution case is less than or equal to 1 meter/second at this time, then remove the pollution case, otherwise keep the pollution case and proceed to the next step; if the wind speed of the pollution case is greater than 7.9 meters/second, then remove it as abnormal data and no longer retain the pollution case; loop calculation, finally filter out the cases where the distance between the microstation and the standard monitoring site is less than or equal to 40KM and meets the above wind direction angle and wind speed conditions.
  • the cases selected are associated with one microstation and one pollution case.
  • the nested loop traverses to obtain the standard monitoring site pollution case data set M associated with all microstations and all their pollution cases.
  • association rule probability database is established, the association rule probability database is updated at preset time intervals.
  • the process of updating the association rule probability library includes:
  • the air pollution events occurring at each microstation and each standard monitoring station within the preset time interval are added to the corresponding historical air pollution events, and the probability of air pollution events occurring at each standard monitoring station associated with each microstation under different wind directions is recalculated.
  • the probability library can be updated every three days based on data such as wind direction, wind speed, and distance to associated sites. With the continuous accumulation of pollution cases and the continuous updating and improvement of the probability library, the probability library will become more and more consistent with the potential connection characteristics between the micro-station and the standard monitoring sites in the city under the influence of different wind speeds, wind directions, and distances, making the warning probability more and more accurate.
  • the historical pollution times of the micro station plus the pollution times of the micro station in the last three days are taken as the new pollution times of the updated micro station.
  • the pollution times of each standard monitoring station associated with the micro station are added to the historical pollution times as the new pollution times of the associated standard monitoring station.
  • the pollution times of each standard monitoring station associated with the micro station are divided by the pollution times of the micro station, which is the probability of pollution occurring at each standard monitoring station associated with the micro station when pollution occurs, and the probability library that has been updated once is obtained.
  • a certain micro-station a_Dongfeng_updated pollution times micro-station a_Dongfeng_original probability database pollution times + micro-station a_Dongfeng_pollution times in the last three days;
  • the updated pollution times of a standard monitoring station b_Dongfeng the pollution times of the original probability database of the standard monitoring station b_Dongfeng + the pollution times of the last three days of the standard monitoring station b_Dongfeng;
  • this application can establish an adaptive and self-updating association rule probability library based on the standard monitoring stations and micro-station data in different cities, predict and warn of impending pollution at standard monitoring stations, discover possible sources of pollutants, clarify the causes of pollution, and help relevant departments to control it.
  • the device 40 includes:
  • the acquisition module 41 is used to obtain the air pollution detection results of each micro station in the target area.
  • the query module 42 is used to obtain the current wind direction of the target area if any micro station detects an air pollution event, and query from the preset association rule probability library the probability of an air pollution event occurring at each standard monitoring station associated with the micro station under the current wind direction;
  • the association rule probability library contains the association relationship between each micro station and each standard monitoring station under different wind directions, and the probability of an air pollution event occurring at each standard monitoring station associated with each micro station under different wind directions when an air pollution event occurs.
  • the early warning module 43 is used to issue an air pollution early warning to each standard monitoring station associated with the micro station according to the probability of an air pollution event occurring at each standard monitoring station associated with the micro station under the queried current wind direction.
  • the query module 42 is further used for:
  • any micro-station under any wind direction if a certain standard monitoring station also detects a historical air pollution event within a preset time after the micro-station detects a historical air pollution event, and the micro-station and the standard monitoring station meet the preset association prerequisite, then the standard monitoring station is associated with the micro-station, and the association relationship between the micro-station and each standard monitoring station under the wind direction is obtained by traversing all the historical air pollution events detected by the micro-station under the wind direction;
  • the number k1 of historical air pollution events that occurred at the microstation under the wind direction and the number k2 of historical air pollution events that occurred at each standard monitoring station associated with the microstation under the wind direction are counted, and the ratio of k2 to k1 is calculated to obtain the probability of air pollution events occurring at each standard monitoring station associated with the microstation when an air pollution event occurs at the microstation under the wind direction; an association rule probability library is established based on the association relationship between each microstation and each standard monitoring station under different wind directions and the probability of air pollution events occurring at each standard monitoring station associated with each microstation when an air pollution event occurs at the microstation under different wind directions.
  • the query module 42 is further used to:
  • historical air pollution events are determined from the historical air monitoring data through the peak detection algorithm, and the historical air pollution events detected by each microstation in the target area and the historical air pollution events detected by each standard monitoring station are obtained.
  • the air pollution events and historical air pollution events are carbon monoxide pollution events, and the historical air monitoring data are carbon monoxide concentration monitoring data; or, the air pollution events and historical air pollution events are sulfur dioxide pollution events, and the historical air monitoring data are sulfur dioxide concentration monitoring data; for different historical air monitoring data, the detection parameters of the peak detection algorithm are different.
  • the query module 42 is specifically used for:
  • the first condition, the second condition and the third condition are simultaneously met within a preset time after the microstation detects a historical air pollution event, it is determined that the preset association precondition is met;
  • the first condition is that the distance is less than a preset distance threshold
  • the second condition is that the angle is less than a preset angle threshold
  • the third condition is that the wind speed in the target area is within a preset wind speed range.
  • the query module 42 is further used to:
  • the air pollution events occurring at each microstation and each standard monitoring station within the preset time interval are added to the corresponding historical air pollution events, and the probability of air pollution events occurring at each standard monitoring station associated with each microstation under different wind directions is recalculated.
  • the warning module 43 is further used to:
  • a standard monitoring station associated with the micro station also detects the air pollution event, then it is determined that the two air pollution events are related.
  • FIG5 is a schematic diagram of an electronic device 50 provided in an embodiment of the present application.
  • the electronic device 50 of this embodiment includes: a processor 51, a memory 52, and a computer program 53 stored in the memory 52 and executable on the processor 51, such as an air pollution warning program.
  • the processor 51 executes the computer program 53, the steps in the above-mentioned air pollution warning method embodiments are implemented, such as steps S101 to S103 shown in FIG2 .
  • the processor 51 executes the computer program 53
  • the functions of the modules in the above-mentioned device embodiments are implemented, such as the functions of modules 41 to 43 shown in FIG4 .
  • the computer program 53 may be divided into one or more modules/units, one or more modules/units are stored in the memory 52, and executed by the processor 51 to complete the present application.
  • One or more modules/units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 53 in the electronic device 50.
  • the electronic device 50 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server.
  • the electronic device 50 may include, but is not limited to, a processor 51 and a memory 52.
  • FIG. 5 is only an example of the electronic device 50 and does not constitute a limitation on the electronic device 50.
  • the electronic device 50 may include more or fewer components than shown in the figure, or may combine certain components, or different components.
  • the electronic device 50 may also include input and output devices, network access devices, buses, etc.
  • the processor 51 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general-purpose processor may be a microprocessor or any conventional processor, etc.
  • the memory 52 may be an internal storage unit of the electronic device 50, such as a hard disk or memory of the electronic device 50.
  • the memory 52 may also be an external storage device of the electronic device 50, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 50.
  • the memory 52 may also include both an internal storage unit of the electronic device 50 and an external storage device.
  • the memory 52 is used to store computer programs and other programs and data required by the electronic device 50.
  • the memory 52 may also be used to temporarily store data that has been output or is to be output.
  • the technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration.
  • the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
  • the functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units.
  • the disclosed devices/electronic devices and methods can be implemented in other ways.
  • the device/electronic device embodiments described above are merely schematic.
  • the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
  • the integrated module/unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.
  • the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program.
  • the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor.
  • the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form.
  • Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal and software distribution medium, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Biochemistry (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Pathology (AREA)
  • Immunology (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Analytical Chemistry (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Medicinal Chemistry (AREA)
  • Food Science & Technology (AREA)
  • Combustion & Propulsion (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Emergency Alarm Devices (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Alarm Systems (AREA)

Abstract

一种空气污染预警方法、装置、电子设备及存储介质，该方法包括：获取目标区域内各个微站的空气污染检测结果(S101)；若任意一个微站检测到发生空气污染事件，则获取目标区域的当前风向，并从预设的关联规则概率库中查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率(S102)；根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对各个标准监测站点进行空气污染预警(S103)。该方法能够对标准监测站点即将发生的污染进行预测预警。

Description

空气污染预警方法、装置、电子设备及存储介质
本专利申请要求于2022年11月17日提交的中国专利申请No.CN202211438849.8的优先权。在先申请的公开内容通过整体引用并入本申请。
技术领域
本申请属于污染物监测技术领域，尤其涉及一种空气污染预警方法、装置、电子设备及存储介质。
 背景技术
随着空气质量污染物监测网络的不断完善，现在的监测网络除了标准监测站点，如国控站、省控站、市控站外，还有众多的微型监测站点（微站）。
由于微站的数量远远多于标准监测站点，且微站大多布设在污染源可能存在的位置，因此，当发生污染时，距离污染源最近的微站先检测到空气污染，一段时间后距离污染源较近的标准监测站点才能检测到空气污染，即标准监测站点相对于微站，检测污染存在一定的滞后性。因此，如何对标准监测站点和微站进行关联，当微站检测到污染时，对标准监测站点即将检测到的污染进行预测预警，从而提前进行预防和成因分析，是目前亟需解决的问题。
 技术问题
有鉴于此，本申请实施例提供了一种空气污染预警方法、装置、电子设备及存储介质，以对标准监测站点即将发生的污染进行预测预警。
 解决方案
本申请实施例的第一方面提供了一种空气污染预警方法，包括：
获取目标区域内各个微站的空气污染检测结果；
若任意一个微站检测到发生空气污染事件，则获取目标区域的当前风向，并从预设的关联规则概率库中查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；
根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警。
结合第一方面，在第一方面的一种可能的实现方式中，关联规则概率库的建立过程包括：
获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件和历史风向数据；
对于任意一种风向下的任意一个微站，若在该微站检测到历史空气污染事件后预设时间内，某个标准监测站点也检测到历史空气污染事件，并且该微站与该标准监测站点之间满足预设的关联前提条件，则将该标准监测站点与该微站进行关联，通过遍历该风向下该微站检测到的所有历史空气污染事件，得到该风向下该微站与各个标准监测站点之间的关联关系；
统计该风向下该微站发生历史空气污染事件的次数k1、以及该风向下与该微站关联的各个标准监测站点发生历史空气污染事件的次数k2，并计算k2与k1的比值，得到该风向下该微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；基于不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，建立关联规则概率库。
进一步的，在获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件之前，还包括确定目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件的过程；确定目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件，包括：
获取目标区域内各个微站和各个标准监测站点的历史空气监测数据；
对历史空气监测数据进行预处理后，通过峰值检测算法从历史空气监测数据中确定历史空气污染事件，得到目标区域内各个微站检测到的历史空气污染事件以及各个标准监测站点检测到的历史空气污染事件。
进一步的，空气污染事件和历史空气污染事件为一氧化碳污染事件，历史空气监测数据为一氧化碳浓度监测数据；或者，空气污染事件和历史空气污染事件为二氧化硫污染事件，历史空气监测数据为二氧化硫浓度监测数据；
对于不同的历史空气监测数据，峰值检测算法的检测参数不同。
进一步的，判断该微站与该标准监测站点之间是否满足预设的关联前提条件，包括：
在平面坐标系中计算该微站与该标准监测站点之间的距离、以及该微站指向该标准监测站点的方向与风向的夹角；
若在该微站检测到历史空气污染事件后预设时间内，同时满足第一条件、第二条件和第三条件，则判定满足预设的关联前提条件；
第一条件为距离小于预设距离阈值；
第二条件为夹角小于预设角度阈值；
第三条件为目标区域的风速位于预设的风速区间范围内。
进一步的，在建立关联规则概率库之后，还包括每隔预设时间间隔对关联规则概率库进行更新；
对关联规则概率库进行更新的过程包括：
将预设时间间隔内各个微站和各个标准监测站点发生的空气污染事件添加到相应的历史空气污染事件中，并重新计算不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
结合第一方面，在第一方面的一种可能的实现方式中，在对与该微站关联的各个标准监测站点进行空气污染预警之后，还包括：
若在该微站检测到空气污染事件后的预设时间内，某个与该微站关联的标准监测站点也检测到空气污染事件，则确定两个空气污染事件相关。
本申请实施例的第二方面提供了一种空气污染预警装置，包括：
获取模块，用于获取目标区域内各个微站的空气污染检测结果；
查询模块，用于若任意一个微站检测到发生空气污染事件，则获取目标区域的当前风向，并从预设的关联规则概率库中查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；
预警模块，用于根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警。
本申请实施例的第三方面提供了一种电子设备，包括存储器、处理器以及存储在存储器中并可在处理器上运行的计算机程序，处理器执行计算机程序时实现如上述第一方面的空气污染预警方法的步骤。
本申请实施例的第四方面提供了一种计算机可读存储介质，计算机可读存储介质存储有计算机程序，计算机程序被处理器执行时实现如上述第一方面的空气污染预警方法的步骤。
 有益效果
本申请实施例通过预先建立目标区域的关联规则概率库，关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，从而任意一个微站检测到发生空气污染事件时，根据目标区域的当前风向，从预设的关联规则概率库中可以查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，进而对与该微站关联的各个标准监测站点进行空气污染预警。本申请实施例能够对标准监测站点即将发生的空气污染进行预测预警，并且还能为标准监测站点检测到的空气污染事件提供分析依据，例如发现污染物来源、明确污染成因等，帮助相关部门进行管控。
 附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例提供的空气质量监测站点的分布示意图；
图2是本申请实施例提供的空气污染预警方法的实现流程示意图；
图3是本申请实施例提供的微站与标准监测站点的关联关系示意图；
图4是本申请实施例提供的空气污染预警装置的结构示意图；
图5是本申请实施例提供的电子设备的结构示意图。
 本发明的实施方式
以下描述中，为了说明而不是为了限定，提出了诸如特定***结构、技术之类的具体细节，以便透彻理解本申请实施例。然而，本领域的技术人员应当清楚，在没有这些具体细节的其它实施例中也可以实现本申请。在其它情况中，省略对众所周知的***、装置、电路以及方法的详细说明，以免不必要的细节妨碍本申请的描述。
为了说明本申请所述的技术方案，下面通过具体实施例来进行说明。
首先对微站和标准监测站点进行简单介绍。
微站大多布设在污染源可能存在的位置，监测小范围内的空气污染。而标准监测站点，如国控站、省控站、市控站等监测大范围内的空气污染。因此，当发生空气污染事件时，通常距离污染源最近的微站先检测到空气污染，一段时间后标准监测站点才能检测到空气污染。以区域A为例，如图1所示，各类空气质量监测站点加起来有一千多个（图1中仅示出了部分微站和部分标准监测站点），利用这些空气质量监测站点的监测数据探究标准监测站点和微站的关联规则，能够对标准监测站点即将发生的污染进行预测预警，发现可能的污染物来源、明确污染成因，帮助相关部门进行管控。
图2是本申请实施例提供的空气污染预警方法的实现流程示意图。如图2所示，该方法包括：
步骤S101，获取目标区域内各个微站的空气污染检测结果。
在本申请实施例中，可以直接从监测网络***上获取目标区域内各个微站的当前空气污染检测结果，例如，当前哪个微站发生了空气污染事件。其中，目标区域可以是某个城市，空气污染事件可以是CO污染、SO 2污染等。
或者，可以每半个小时读取一次标准监测站点和微站的监测数据，然后与历史监测数据合并，通过数据预处理及峰值检测算法寻找划分污染案例，确定近半个小时内各个微站发生的污染案例，得到各个微站的空气污染检测结果。数据预处理及峰值检测算法在本说明书后续将进行详细介绍。
步骤S102，若任意一个微站检测到发生空气污染事件，则获取目标区域的当前风向，并从预设的关联规则概率库中查询，当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
在本实施例中，若某一个微站检测到发生空气污染事件，例如CO污染，若当前风向为东风，则可以从预设的关联规则概率库中查询，风向为东风时与该微站关联的各个标准监测站点发生空气污染事件的概率。可以理解的是，由于微站与标准监测站点之间的地理位置关系，不同风向下，微站关联的标准监测站点一般不同，因此寻找关联的标准监测站点时必须考虑风向的影响。
步骤S103，根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警。
在本实施例中，关联规则概率库中查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率一般不相同，可以筛选出概率较高的标准监测站点，对其即将发生的空气污染事件进行预测预警。
作为一种可能的实现方式中，在对与该微站关联的各个标准监测站点进行空气污染预警之后，还可以包括：
若在该微站检测到空气污染事件后的预设时间内，某个与该微站关联的标准监测站点也检测到空气污染事件，则确定两个空气污染事件相关。
在本实施例中，由于标准监测站点相对于微站响应污染存在滞后性，因此预设时间可以设置为未来1-1.5h的时间段。示例性的，当某个微站检测到CO污染后1-1.5h的时间段内，在某个标准监测站点也检测到CO污染，则可以确定两个空气污染事件相关，根据微站的位置可以分析标准监测站点此次检测到CO污染的污染物来源、污染成因等，从而帮助相关部门进行管控。
可见，本申请实施例通过预先建立目标区域的关联规则概率库，关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，从而任意一个微站检测到发生空气污染事件时，根据目标区域的当前风向，从预设的关联规则概率库中可以查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，进而对与该微站关联的各个标准监测站点进行空气污染预警。本申请实施例能够对标准监测站点即将发生的空气污染进行预测预警，还能为标准监测站点检测到的空气污染事件提供分析依据，例如发现污染物来源、明确污染成因等，帮助相关部门进行管控。
作为一种可能的实现方式中，上述关联规则概率库的建立过程包括：
获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件和历史风向数据；
对于任意一种风向下的任意一个微站，若在该微站检测到历史空气污染事件后预设时间内，某个标准监测站点也检测到历史空气污染事件，并且该微站与该标准监测站点之间满足预设的关联前提条件，则将该标准监测站点与该微站进行关联，通过遍历该风向下该微站检测到的所有历史空气污染事件，得到该风向下该微站与各个标准监测站点之间的关联关系；
统计该风向下该微站发生历史空气污染事件的次数k1、以及该风向下与该微站关联的各个标准监测站点发生历史空气污染事件的次数k2，并计算k2与k1的比值，得到该风向下该微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；基于不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，建立关联规则概率库。
在本实施例中，关联规则概率库以模型所运算城市数据为基准，根据城市标准监测站点、微站等布局特点、以及标准监测站点和微站在不同风向、风速及距离影响下的关联性进行自动化构建。
现以A市为例，选取A市距离当前时间节点最近两个月的标准监测站点和微站的历史空气污染事件，对标准监测站点历史空气污染事件、微站历史空气污染事件进行关联，由于标准监测站点的检测具有滞后性，因此关联原则为标准监测站点发生的历史空气污染事件比微站发生的历史空气污染事件延后预设时间（例如微站发生历史空气污染事件后的1-2h），且两者之间满足预设的关联前提条件。以CO为例，关联分析结果如表1和图3所示，得到每一个标准监测站点以及与之匹配度较高的十个微站，还得到标准监测站点和匹配度较高的微站关联的次数。
表1 关联关系表
然后，分别统计不同风向条件下每个微站发生污染的次数，以及与之关联的标准监测站点发生污染的次数，当前风向下与该微站关联的标准监测站点发生污染的次数与当前风向下该微站发生污染次数的比值，即为微站在当前风向下发生空气污染事件时，关联的标准监测站点即将发生空气污染事件的概率。部分关联规则概率库可以参见表2所示，表2中显示了微站站点名称、微站在不同的风向条件下发生污染的次数，以及对应的每个标准监测站点发生污染的概率。
表2 关联概率表
作为一种可能的实现方式，在获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件之前，还包括确定目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件的过程。
确定目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件，可以详述为：
获取目标区域内各个微站和各个标准监测站点的历史空气监测数据；
对历史空气监测数据进行预处理后，通过峰值检测算法从历史空气监测数据中确定历史空气污染事件，得到目标区域内各个微站检测到的历史空气污染事件以及各个标准监测站点检测到的历史空气污染事件。
在本实施例中，可以采集FTP服务器端目标城市的标准监测站点数据、微站数据和气象相关的数据，对上述采集的历史空气监测数据进行如下的数据清洗（即对历史空气监测数据进行预处理）：
（1）删除空值、零值、负值的数据并插值；
（2）将微站数据统一为五分钟数据；
（3）将标准监测站点、微站的分钟数据按小时进行滑动平均，减少数据忽高忽低的问题；
（4）去除数据昼夜周期性，便于寻找发生污染的时段。
然后，对上述清洗的时间序列数据进行峰值检测算法设计，自适应划分高值时段，寻找污染案例。
具体的，在峰值检测算法中，峰的宽度无法事先确定，峰高明显偏离其他值，算法实时更新（每个数据点都会更新），算法步骤如下：
将污染活动数据向量逐个输入固定长度的移动计算区域，设初始移动计算区域大小为n，波动参数设为threshold，影响参数设为influence，移动计算区域内的活动数据向量filteredY(n)=y(1),.....y(n)。
计算当前移动计算区域内的活动数据算术平均值：
计算当前移动计算区域内的活动数据标准偏差：
计算当前移动计算区域外第一个数据y(n+i)（i=1....L-n）和目前移动计算区域内活动数据算术平均值的差值的绝对值：
diff(n+i) = |y(n+i)-avgFilter(n)|
计算当前移动计算区域内活动数据向量波动量大小：
fluctuate（n）= threshold * stdFilter(n)
如果满足diff(n+i) > fluctuate（n）并且y(n+i) > avgFilter(n)，设第n+i个数据的信号值为1（高值信号）。如果此时diff(n+i) > fluctuate（n）并且y(n+i) < avgFilter(n)，设第n+i个数据的信号值为-1（低值信号）。上述过程之后将filteredY(n+i)变量进行削峰赋值：
filteredY(n+i) = influence * y(n+i) + (1-influence) * filteredY(n)
如果满足diff(n+i) < fluctuate（n），设第n+i个数据的信号值为0（平值信号），并将filteredY(n+i)赋值为y(n+i)：
filteredY(n+i) = y(n+i)
循环计算，将移动计算区域向后移动一个单位时间数据，并计算执行上述过程，得到下一个数据的信号值，直到将L长度的活动数据向量计算完成并得到最终的信号向量signals，根据signals划分高低平信号寻找空气污染事件。
作为一种可能的实现方式，空气污染事件和历史空气污染事件为一氧化碳污染事件，历史空气监测数据为一氧化碳浓度监测数据；或者，空气污染事件和历史空气污染事件为二氧化硫污染事件，历史空气监测数据为二氧化硫浓度监测数据；对于不同的历史空气监测数据，峰值检测算法的检测参数不同。
在本实施例中，根据不同污染物的历史变化规律与特征，相应调整移动计算区域大小、波动参数、影响参数等，能够更准确地识别空气污染事件。
作为一种可能的实现方式，判断该微站与该标准监测站点之间是否满足预设的关联前提条件，包括：
在平面坐标系中计算该微站与该标准监测站点之间的距离、以及该微站指向该标准监测站点的方向与风向的夹角；
若在该微站检测到历史空气污染事件后预设时间内，同时满足第一条件、第二条件和第三条件，则判定满足预设的关联前提条件；
第一条件为距离小于预设距离阈值；
第二条件为夹角小于预设角度阈值；
第三条件为目标区域的风速位于预设的风速区间范围内。
在一个实施例中，示例性的，关联过程还可以详述为：
第一步，主线程程序运行，每隔半小时读取一次FTP服务器标准监测站点和微站半小时数据，新的标准监测站点数据和新的微站数据与历史积累三天数据进行合并，积累数据保持三天的数据量，超过当前时间以前三天的数据自动剔除。
第二步，副线程程序运行，每隔三天在FTP服务器读取一次气象数据，气象数据包含最近三天的风速、风向等信息，将气象数据分别与最近三天的标准监测站点和微站数据按照小时时间进行匹配。
第三步，在主线程中划分微站污染案例，将清洗后的最近三天的微站数据经过峰值检测算法后形成高低平信号，选取高值信号数据进行划分，划分标准为时间间隔小于1小时，如果高值信号数据一直连续，则为一个污染案例，如果污染案例间隔大于等于1小时，则划分为另外一个污染案例。标准监测站点也按照相同的方法在副线程运行，分别按CO和SO 2参数划分污染案例，其中时间间隔1小时是根据实际情况选择的，如果间隔过小，则多个污染案例可能是同一个污染事件引起的，设置过大，则同一个污染案例可能是多个污染事件引起的。
第四步，根据风向、风速、站点距离等匹配合并微站和标准监测站点的污染案例。遍历微站站点名称以及其所属污染案例，由于标准监测站点相对于微站响应污染存在滞后性，可以选取峰值比该污染案例峰值时间晚出现一个小时至两个小时，并且污染案例开始时间比该污染案例晚半个小时的标准监测站点污染案例，如果该标准监测站点污染案例不存在，则循环遍历下一个；若存在，则把该微站污染案例的站点名称、开始时间、结束时间、峰值时间、经纬度等信息与该标准监测站点污染案例进行关联合并。先将标准监测站点、微站的经纬度转换为地理坐标系，再将地理坐标系转换为平面坐标系，通过标准监测站点和微站的平面坐标系计算得出两个站点之间的距离distance和夹角angle，以微站为起点，连接微站与标准监测站点的直线与正北0度方向的直线的夹角即为二者夹角，计算过程如下：
dif_lon =此微站平面坐标系经度-此标准监测站点平面坐标系经度；
dif_lat =此微站平面坐标系纬度-此标准监测站点平面坐标系纬度；
令x=dif_lon，y= dif_lat，如果满足x>0并且y > 0，
如果满足x>0并且y<0，
如果满足x<0并且y<0，
如果满足x<0并且y>0，
计算微站-风向角度（即该微站指向该标准监测站点的方向与风向的夹角）与微站-标准监测站点夹角angle的角度差，如果该微站污染案例某一个五分钟数据风向满足：|风向角度-angle|<30或|风向角度-angle|>330，则保留该污染案例，继续下一步，否则，剔除该污染案例。如果此时该微站污染案例风速都小于等于1米/秒，则剔除该污染案例，否则保留该污染案例并进行下一步；如果该污染案例风速都大于7.9米/秒，则作为异常数据剔除，不再保留该污染案例；循环计算，最后筛选出微站、标准监测站点距离小于等于40KM，并且满足上述风向角度和风速条件的案例，此时筛选出的是与一个微站一个污染案例关联匹配案例。嵌套循环遍历得出所有微站及其所有污染案例相关联匹配的标准监测站点污染案例数据集M。
进一步的，在建立关联规则概率库之后，还包括每隔预设时间间隔对关联规则概率库进行更新。
对关联规则概率库进行更新的过程包括：
将预设时间间隔内各个微站和各个标准监测站点发生的空气污染事件添加到相应的历史空气污染事件中，并重新计算不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
在本实施例中，可以每隔三天结合风向、风速、关联站点距离等数据更新概率库，随着污染案例的不断积累和概率库的不断更新完善，概率库会越来越符合该城市在不同风速、风向、距离等影响下，微站和标准监测站点之间潜在联系特性，能够使预警概率越来越准确。
计算这三天中所有微站在不同风向条件下的污染案例数量，得到数据集N；循环嵌套遍历风向和微站站点名称，在指定风向下，根据微站名称定位到第四步数据集M中，数据集M中每一行代表一次污染事件，遍历该微站对应的数据集M中标准监测站点名称，并计数行数，可以得到该微站在该风向下对应的每个标准监测站点发生污染的次数，在数据集N中可以的得到该风向下该微站在最近三天一共发生污染的次数，将该风向下该微站发生的污染次数与该微站关联的各个标准监测站点发生污染次数进行合并，循环操作可以得到不同风向下不同微站与其关联标准监测站点分别发生污染事件的次数，即为最近三天数据得出的新的概率库。将该微站的历史污染次数加上该微站最近三天污染次数作为更新后的该微站新的污染次数，与以上相同，将该微站关联的每个标准监测站点污染次数与历史污染次数相加作为该关联标准监测站点新的污染次数，分别将该微站关联的每个标准监测站点的污染次数除以该微站的污染次数，即为该微站发生污染时所关联的每个标准监测站点发生污染概率，得到更新完一次的概率库。
示例性的，计算公式如下：
某微站a_东风_更新后的污染次数=微站a_东风_原概率库污染次数+微站a_东风_最近三天污染次数；
某标准监测站点b_东风_更新后的污染次数=标准监测站点b_东风_原概率库污染次数+标准监测站点b_东风_最近三天污染次数；
微站a发生污染后标准监测站点b发生污染概率(更新后的概率)=标准监测站点b_东风_更新后的污染次数/微站a_东风_更新后的污染次数。
结合以上内容，本申请能够根据不同城市的标准监测站点和微站数据，建立自适应、自更新的关联规则概率库，对标准监测站点即将发生的污染进行预测预警，发现可能的污染物来源、明确污染成因，帮助相关部门进行管控。
应理解，上述实施例中各步骤的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本申请实施例提供了一种空气污染预警装置，如图4所示，该装置40包括：
获取模块41，用于获取目标区域内各个微站的空气污染检测结果。
查询模块42，用于若任意一个微站检测到发生空气污染事件，则获取目标区域的当前风向，并从预设的关联规则概率库中查询，当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
预警模块43，用于根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警。
作为一种可能的实现方式，查询模块42还用于：
获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件和历史风向数据；
对于任意一种风向下的任意一个微站，若在该微站检测到历史空气污染事件后预设时间内，某个标准监测站点也检测到历史空气污染事件，并且该微站与该标准监测站点之间满足预设的关联前提条件，则将该标准监测站点与该微站进行关联，通过遍历该风向下该微站检测到的所有历史空气污染事件，得到该风向下该微站与各个标准监测站点之间的关联关系；
统计该风向下该微站发生历史空气污染事件的次数k1、以及该风向下与该微站关联的各个标准监测站点发生历史空气污染事件的次数k2，并计算k2与k1的比值，得到该风向下该微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；基于不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，建立关联规则概率库。
作为一种可能的实现方式，在获取目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件之前，查询模块42还用于：
获取目标区域内各个微站和各个标准监测站点的历史空气监测数据；
对历史空气监测数据进行预处理后，通过峰值检测算法从历史空气监测数据中确定历史空气污染事件，得到目标区域内各个微站检测到的历史空气污染事件以及各个标准监测站点检测到的历史空气污染事件。
作为一种可能的实现方式，空气污染事件和历史空气污染事件为一氧化碳污染事件，历史空气监测数据为一氧化碳浓度监测数据；或者，空气污染事件和历史空气污染事件为二氧化硫污染事件，历史空气监测数据为二氧化硫浓度监测数据；对于不同的历史空气监测数据，峰值检测算法的检测参数不同。
作为一种可能的实现方式，查询模块42具体用于：
在平面坐标系中计算该微站与该标准监测站点之间的距离、以及该微站指向该标准监测站点的方向与风向的夹角；
若在该微站检测到历史空气污染事件后预设时间内，同时满足第一条件、第二条件和第三条件，则判定满足预设的关联前提条件；
第一条件为距离小于预设距离阈值；
第二条件为夹角小于预设角度阈值；
第三条件为目标区域的风速位于预设的风速区间范围内。
作为一种可能的实现方式，在建立关联规则概率库之后，查询模块42还用于：
将预设时间间隔内各个微站和各个标准监测站点发生的空气污染事件添加到相应的历史空气污染事件中，并重新计算不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
作为一种可能的实现方式，在对与该微站关联的各个标准监测站点进行空气污染预警之后，预警模块43还用于：
若在该微站检测到空气污染事件后的预设时间内，某个与该微站关联的标准监测站点也检测到空气污染事件，则确定两个空气污染事件相关。
图5是本申请实施例提供的电子设备50的示意图。如图5所示，该实施例的电子设备50包括：处理器51、存储器52以及存储在存储器52中并可在处理器51上运行的计算机程序53，例如空气污染预警程序。处理器51执行计算机程序53时实现上述各个空气污染预警方法实施例中的步骤，例如图2所示的步骤S101至S103。或者，处理器51执行计算机程序53时实现上述各装置实施例中各模块的功能，例如图4所示模块41至43的功能。
示例性的，计算机程序53可以被分割成一个或多个模块/单元，一个或者多个模块/单元被存储在存储器52中，并由处理器51执行，以完成本申请。一个或多个模块/单元可以是能够完成特定功能的一系列计算机程序指令段，该指令段用于描述计算机程序53在电子设备50中的执行过程。
电子设备50可以是桌上型计算机、笔记本、掌上电脑及云端服务器等计算设备。电子设备50可包括，但不仅限于，处理器51、存储器52。本领域技术人员可以理解，图5仅仅是电子设备50的示例，并不构成对电子设备50的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件，例如电子设备50还可以包括输入输出设备、网络接入设备、总线等。
所称处理器51可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器 (Digital Signal Processor，DSP)、专用集成电路 (Application Specific Integrated Circuit，ASIC)、现成可编程门阵列 (Field-Programmable Gate Array，FPGA) 或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
存储器52可以是电子设备50的内部存储单元，例如电子设备50的硬盘或内存。存储器52也可以是电子设备50的外部存储设备，例如电子设备50上配备的插接式硬盘，智能存储卡（Smart Media Card, SMC），安全数字（Secure Digital, SD）卡，闪存卡（Flash Card）等。进一步地，存储器52还可以既包括电子设备50的内部存储单元也包括外部存储设备。存储器52用于存储计算机程序以及电子设备50所需的其他程序和数据。存储器52还可以用于暂时地存储已经输出或者将要输出的数据。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，仅以上述各功能单元、模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元、模块完成，即将装置的内部结构划分成不同的功能单元或模块，以完成以上描述的全部或者部分功能。实施例中的各功能单元、模块可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中，上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。另外，各功能单元、模块的具体名称也只是为了便于相互区分，并不用于限制本申请的保护范围。上述***中单元、模块的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述或记载的部分，可以参见其它实施例的相关描述。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
在本申请所提供的实施例中，应该理解到，所揭露的装置/电子设备和方法，可以通过其它的方式实现。例如，以上所描述的装置/电子设备实施例仅仅是示意性的，例如，模块或单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通讯连接可以是通过一些接口，装置或单元的间接耦合或通讯连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实现上述实施例方法中的全部或部分流程，也可以通过计算机程序来指令相关的硬件来完成，的计算机程序可存储于一计算机可读存储介质中，该计算机程序在被处理器执行时，可实现上述各个方法实施例的步骤。其中，计算机程序包括计算机程序代码，计算机程序代码可以为源代码形式、对象代码形式、可执行文件或某些中间形式等。计算机可读介质可以包括：能够携带计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器（ROM，Read-Only Memory）、随机存取存储器（RAM，Random Access Memory）、电载波信号、电信信号以及软件分发介质等。
以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围，均应包含在本申请的保护范围之内。

Claims (8)

  1. 一种空气污染预警方法，其特征在于，包括：
    获取目标区域内各个微站的空气污染检测结果；
    若任意一个微站检测到发生空气污染事件，则获取所述目标区域的当前风向，并从预设的关联规则概率库中查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；所述关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；
    根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警；
    所述关联规则概率库的建立过程包括：
    获取所述目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件和历史风向数据；
    对于任意一种风向下的任意一个微站，若在该微站检测到历史空气污染事件后预设时间内，某个标准监测站点也检测到历史空气污染事件，并且该微站与该标准监测站点之间满足预设的关联前提条件，则将该标准监测站点与该微站进行关联，通过遍历该风向下该微站检测到的所有历史空气污染事件，得到该风向下该微站与各个标准监测站点之间的关联关系；
    统计该风向下该微站发生历史空气污染事件的次数k1、以及该风向下与该微站关联的各个标准监测站点发生历史空气污染事件的次数k2，并计算k2与k1的比值，得到该风向下该微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；基于不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率，建立关联规则概率库；
    判断该微站与该标准监测站点之间是否满足预设的关联前提条件，包括：
    在平面坐标系中计算该微站与该标准监测站点之间的距离、以及该微站指向该标准监测站点的方向与风向的夹角；
    若在该微站检测到历史空气污染事件后预设时间内，同时满足第一条件、第二条件和第三条件，则判定满足预设的关联前提条件；
    所述第一条件为所述距离小于预设距离阈值；
    所述第二条件为所述夹角小于预设角度阈值；
    所述第三条件为所述目标区域的风速位于预设的风速区间范围内。
  2. 如权利要求1所述的空气污染预警方法，其特征在于，在获取所述目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件之前，还包括确定所述目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件的过程；
    所述确定所述目标区域内各个微站检测到的历史空气污染事件、各个标准监测站点检测到的历史空气污染事件，包括：
    获取目标区域内各个微站和各个标准监测站点的历史空气监测数据；
    对所述历史空气监测数据进行预处理后，通过峰值检测算法从所述历史空气监测数据中确定历史空气污染事件，得到所述目标区域内各个微站检测到的历史空气污染事件以及各个标准监测站点检测到的历史空气污染事件。
  3. 如权利要求2所述的空气污染预警方法，其特征在于，所述空气污染事件和历史空气污染事件为一氧化碳污染事件，所述历史空气监测数据为一氧化碳浓度监测数据；或者，所述空气污染事件和历史空气污染事件为二氧化硫污染事件，所述历史空气监测数据为二氧化硫浓度监测数据；
    对于不同的历史空气监测数据，所述峰值检测算法的检测参数不同。
  4. 如权利要求1所述的空气污染预警方法，其特征在于，在建立关联规则概率库之后，还包括每隔预设时间间隔对所述关联规则概率库进行更新；
    对所述关联规则概率库进行更新的过程包括：
    将预设时间间隔内各个微站和各个标准监测站点发生的空气污染事件添加到相应的历史空气污染事件中，并重新计算不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率。
  5. 如权利要求1所述的空气污染预警方法，其特征在于，在对与该微站关联的各个标准监测站点进行空气污染预警之后，还包括：
    若在该微站检测到空气污染事件后的预设时间内，某个与该微站关联的标准监测站点也检测到空气污染事件，则确定两个空气污染事件相关。
  6. 一种空气污染预警装置，其特征在于，包括：
    获取模块，用于获取目标区域内各个微站的空气污染检测结果；
    查询模块，用于若任意一个微站检测到发生空气污染事件，则获取所述目标区域的当前风向，并从预设的关联规则概率库中查询当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率；所述关联规则概率库中包含不同风向下各个微站与各个标准监测站点之间的关联关系、以及不同风向下每个微站发生空气污染事件时与其关联的各个标准监测站点发生空气污染事件的概率；
    预警模块，用于根据查询到的当前风向下与该微站关联的各个标准监测站点发生空气污染事件的概率，对与该微站关联的各个标准监测站点进行空气污染预警。
  7. 一种电子设备，包括存储器、处理器以及存储在所述存储器中并可在所述处理器上运行的计算机程序，其特征在于，所述处理器执行所述计算机程序时实现如权利要求1至5任一项所述的空气污染预警方法的步骤。
  8. 一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现如权利要求1至5任一项所述的空气污染预警方法的步骤。
PCT/CN2023/087822 2022-11-17 2023-04-12 空气污染预警方法、装置、电子设备及存储介质 WO2024103616A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211438849.8 2022-11-17
CN202211438849.8A CN115561408B (zh) 2022-11-17 2022-11-17 空气污染预警方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2024103616A1 true WO2024103616A1 (zh) 2024-05-23

Family

ID=84770306

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/087822 WO2024103616A1 (zh) 2022-11-17 2023-04-12 空气污染预警方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115561408B (zh)
WO (1) WO2024103616A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115561408B (zh) * 2022-11-17 2023-04-28 河北先河环保科技股份有限公司 空气污染预警方法、装置、电子设备及存储介质
CN116738360B (zh) * 2023-05-25 2023-11-03 青岛海科微纳传感技术有限公司 一种基于多维融合模型的空气检测***及方法
CN117591907B (zh) * 2024-01-18 2024-03-26 四川国蓝中天环境科技集团有限公司 基于密集型空气质量微站监测的污染发生及传播感知方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090098127A (ko) * 2008-03-13 2009-09-17 (주)바이오텔 대기 오염물질 모니터링 시스템 및 그 방법
CN112465243A (zh) * 2020-12-02 2021-03-09 南通大学 一种空气质量预报方法及***
CN113125635A (zh) * 2019-12-31 2021-07-16 北京蛙鸣华清环保科技有限公司 一种大气污染预警方法、装置及可读存储介质
CN113793028A (zh) * 2021-09-14 2021-12-14 济南东之林智能软件有限公司 污染源关联信息的确定方法、装置及终端设备
CN114280695A (zh) * 2017-05-09 2022-04-05 西南石油大学 一种空气污染物监测预警方法及云平台
CN115295086A (zh) * 2022-08-04 2022-11-04 厦门新能汇聚智能科技有限公司 空气质量预测模型的建模方法、装置、设备和存储介质
CN115561408A (zh) * 2022-11-17 2023-01-03 河北先河环保科技股份有限公司 空气污染预警方法、装置、电子设备及存储介质

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003208686A (ja) * 2002-01-10 2003-07-25 Moritoshi Sato 大気汚染観測データ送受信システム
CN105488316B (zh) * 2014-09-17 2018-11-16 日本电气株式会社 用于预测空气质量的***和方法
US10438125B2 (en) * 2015-11-12 2019-10-08 International Business Machines Corporation Very short-term air pollution forecasting

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090098127A (ko) * 2008-03-13 2009-09-17 (주)바이오텔 대기 오염물질 모니터링 시스템 및 그 방법
CN114280695A (zh) * 2017-05-09 2022-04-05 西南石油大学 一种空气污染物监测预警方法及云平台
CN113125635A (zh) * 2019-12-31 2021-07-16 北京蛙鸣华清环保科技有限公司 一种大气污染预警方法、装置及可读存储介质
CN112465243A (zh) * 2020-12-02 2021-03-09 南通大学 一种空气质量预报方法及***
CN113793028A (zh) * 2021-09-14 2021-12-14 济南东之林智能软件有限公司 污染源关联信息的确定方法、装置及终端设备
CN115295086A (zh) * 2022-08-04 2022-11-04 厦门新能汇聚智能科技有限公司 空气质量预测模型的建模方法、装置、设备和存储介质
CN115561408A (zh) * 2022-11-17 2023-01-03 河北先河环保科技股份有限公司 空气污染预警方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN115561408B (zh) 2023-04-28
CN115561408A (zh) 2023-01-03

Similar Documents

Publication Publication Date Title
WO2024103616A1 (zh) 空气污染预警方法、装置、电子设备及存储介质
CN108513676A (zh) 一种路况识别方法、装置及设备
CN110175691B (zh) 规划区域交通运营线路的方法、装置和电子设备
Lv et al. Outlier trajectory detection: A trajectory analytics based approach
US20230215272A1 (en) Information processing method and apparatus, computer device and storage medium
CN112885099B (zh) 用于确定车辆轨迹关键点的方法、装置及设备
US20220221281A1 (en) System and method for processing vehicle event data for analysis of road segments and turn ratios
CN112492275A (zh) 一种区域监测点的布局方法、装置及存储介质
CN111046895A (zh) 一种确定目标区域的方法和装置
Ho et al. Amic: An adaptive information theoretic method to identify multi-scale temporal correlations in big time series data
CN110597248B (zh) 园区无人智慧巡检方法、装置、设备及存储介质
CN112579915A (zh) 一种出行链的分析方法及装置
Zhu et al. Mining large-scale GPS streams for connectivity refinement of road maps
CN114357099B (zh) 一种聚类方法、聚类***和存储介质
CN113342782B (zh) 一种基于高速公路的数据监测方法、设备及介质
CN113761390B (zh) 一种用于属性亲密度的分析方法和***
CN114490833A (zh) 一种图计算结果可视化方法和***
Fourati et al. FANSI-tool: An integrated software for floating data analytics
CN114357102A (zh) 一种路网数据生成方法和装置
Zhao et al. A framework for group converging pattern mining using spatiotemporal trajectories
CN112948520A (zh) 一种绕行路径的确定方法、装置及存储介质
CN110188818A (zh) 热点区域聚类方法、装置及电子设备
CN113008246A (zh) 地图匹配方法和装置
CN115102920B (zh) 基于关系网络的个体的传输管控方法
Li et al. An improved hidden Markov model-based map matching algorithm considering candidate point grouping and trajectory connectivity

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23890061

Country of ref document: EP

Kind code of ref document: A1