Ozone concentration prediction method and device, electronic device, and readable storage medium

Abstract

The present disclosure provides an ozone concentration prediction method and device, electronic device, and readable storage medium, which belong to the field of environmental monitoring technology. The method includes: determining target ozone concentration data in a target area, where the target area is the area where the monitoring point corresponding to the target ozone concentration data is located; determining a target fitting regression equation that matches the target ozone concentration data based on the monitoring point and the meteorological data corresponding to the monitoring point; inputting the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area. The ozone concentration prediction method and device, electronic device, and readable storage medium provided by the present disclosure can improve the accuracy of ozone concentration prediction.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of environmental monitoring, and more specifically, relates to an ozone concentration prediction method and device, an electronic device, and a readable storage medium. Background Art

[0002] The current environmental pollution prevention and control has achieved phased results, the concentration of fine particles has dropped significantly, and the proportion of days with PM2.5 as the primary pollutant exceeding the standard has decreased year by year. However, ozone, as a secondary pollutant, has shown an upward trend year by year, becoming the main factor affecting the improvement of air quality. The existing prediction methods for ozone concentration mainly include numerical model prediction. The prediction method based on numerical models is aimed at urban ozone concentration prediction, which is not only costly, but also requires the use of pollution source emission lists. The unclear list and complex sources of precursors lead to low accuracy of the prediction results. Summary of the invention

[0003] The purpose of the present disclosure is to provide an ozone concentration prediction method and device, an electronic device, and a readable storage medium to solve the problem of low accuracy of ozone concentration prediction in the prior art.

[0004] A first aspect of the embodiments of the present disclosure provides an ozone concentration prediction method, comprising:

[0005] Determine target ozone concentration data in a target area, where the target area is an area where a monitoring point corresponding to the target ozone concentration data is located;

[0006] Determine a target fitting regression equation matching the target ozone concentration data according to the monitoring point and the meteorological data corresponding to the monitoring point;

[0007] The target ozone concentration data is input into the target fitting regression equation to obtain the predicted ozone concentration data of the target area.

[0008] A second aspect of the embodiments of the present disclosure provides an ozone concentration prediction device, comprising:

[0009] A data acquisition module, used to determine target ozone concentration data in a target area, where the target area is an area where a monitoring point corresponding to the target ozone concentration data is located;

[0010] A regression equation determination module, used to determine a target fitting regression equation matching the target ozone concentration data according to the monitoring point and the meteorological data corresponding to the monitoring point;

[0011] A calculation module is used to input the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area.

[0012] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned ozone concentration prediction method when executing the computer program.

[0013] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned ozone concentration prediction method are implemented.

[0014] The ozone concentration prediction method and device, electronic device, and readable storage medium provided by the embodiments of the present disclosure have the following beneficial effects:

[0015] First of all, the present invention determines the target fitting regression equation by targeting the meteorological data of the monitoring point and the area where it is located. Compared with the general prediction model, it can fully consider the variation law of ozone concentration at each monitoring point and better capture the subtle fluctuations and changing trends of ozone concentration, thereby significantly improving the accuracy and reliability of the prediction.

[0016] Secondly, the present invention predicts ozone concentration data with the help of less meteorological data, making it more convenient and quick to obtain predicted data, greatly reducing the prediction cost and expanding the scope of application.

[0017] Finally, the present disclosure fully considers the impact of weather changes on the accuracy of ozone concentration prediction. In traditional methods, regression equations based on normal weather conditions are often used for prediction. However, when encountering extreme or special weather types, the prediction accuracy of this method will be significantly reduced. In order to overcome this limitation, the present disclosure innovatively designs regression equations for different weather types. In this way, when the actual weather changes, the monitoring point can quickly select the regression equation that best matches the current weather type for prediction. Doing so can not only significantly improve the accuracy of the prediction, but also better reflect the actual changes in ozone concentration under different weather conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 A schematic diagram of a flow chart of an ozone concentration prediction method provided in an embodiment of the present disclosure;

[0020] Figure 2A schematic diagram of a monitoring grid provided in an embodiment of the present disclosure;

[0021] Figure 3 A fitting regression equation under normal weather conditions provided by an embodiment of the present disclosure;

[0022] Figure 4 A fitting regression equation under sandstorm weather provided by an embodiment of the present disclosure;

[0023] Figure 5 A fitting regression equation under rainy weather provided by an embodiment of the present disclosure;

[0024] Figure 6 A complete flow chart for ozone concentration prediction provided by an embodiment of the present disclosure;

[0025] Figure 7 A structural block diagram of an ozone concentration prediction device provided in one embodiment of the present disclosure;

[0026] Figure 8 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0028] First, the professional knowledge involved in this disclosure is explained.

[0029] Ozone is a light blue, strongly oxidizing gas with a peculiar smell. It has an obvious vertical distribution from near the ground to high altitude. 90% of ozone is in the stratosphere. This part of ozone can absorb short-wave radiation in ultraviolet radiation, protecting human health and the stability of the ecosystem.

[0030] The hazards of ozone in the troposphere: It irritates the respiratory mucosa, destroys the cell structure of the lungs, causes coughing, sore throat, chest tightness, triggers various skin diseases, accelerates skin aging, and in severe cases can cause breathing difficulties, asthma, induce cancer and cardiovascular diseases. In addition to affecting human health, ozone pollution also harms plant growth, such as reducing the chlorophyll content in plant leaves, causing yellowing of leaves, and hindering photosynthesis; damaging the plant membrane system, affecting the plant's absorption, transformation and distribution of nutrients; changing the soil environment, reducing the content of essential nutrients in the soil, resulting in reduced crop yields and reduced quality, causing economic losses, etc.

[0031] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0032] Please refer to Figure 1 , Figure 1 A schematic diagram of a flow chart of an ozone concentration prediction method provided in an embodiment of the present disclosure, the method comprising:

[0033] S101: Determine target ozone concentration data in a target area, where the target area is an area where monitoring points corresponding to the target ozone concentration data are located.

[0034] In the present embodiment, the target area refers to a specific geographical area where ozone concentration monitoring is required. The target area is divided into multiple sub-areas according to the geographical location, and each sub-area is provided with multiple monitoring points. For example, the target area can be a city, a province, a country or a wider geographical area, and the sub-areas can be divided based on administrative regions, natural environmental characteristics, population density or other relevant factors, and each sub-area is a specific part of the target area. Multiple monitoring points are provided in each sub-area, and these monitoring points are arranged at different geographical locations, such as the main roads, industrial parks, parks, residential areas, etc. of the city. Each monitoring point is provided with equipment for collecting ozone concentration data to ensure that the ozone concentration in the sub-area can be fully and accurately reflected.

[0035] refer to Figure 2 , the monitoring points in each sub-area include key monitoring points and micro monitoring points, wherein the number of key monitoring points is less than the number of micro monitoring points, the key monitoring points collect ozone concentration data once every second time period, and the micro monitoring points collect ozone concentration data once every third time period, and the second time period is greater than the third time period. For example, the key monitoring points collect ozone concentration data once every hour, and the micro monitoring points collect ozone concentration data once every 10 minutes.

[0036] Although the number of key monitoring points is small, the types of data collected by key monitoring points are greater than those collected by micro monitoring points. For example, in addition to collecting ozone concentration data, key monitoring points can also collect other air pollutant data and even monitor weather changes. In this embodiment, ozone concentration data, meteorological data, wind direction, etc. collected by key monitoring points and conventional monitoring points are mainly used to predict ozone concentration.

[0037] The target ozone concentration data is obtained by preprocessing the collected initial ozone concentration data. The preprocessing may include data cleaning (removing outliers), data interpolation (filling missing values), data smoothing (reducing noise), etc. Through these processes, the accuracy, completeness and consistency of the target ozone concentration data can be ensured, thereby improving the accuracy and reliability of ozone concentration prediction.

[0038] S102: Determine a target fitting regression equation that matches the target ozone concentration data based on the monitoring points and the meteorological data corresponding to the monitoring points.

[0039] In this embodiment, meteorological data refers to various data related to weather conditions, including but not limited to weather type, temperature, humidity, air pressure, wind speed, wind direction, precipitation, etc. In this embodiment, meteorological data mainly refers to weather type.

[0040] According to the monitoring points and the meteorological data corresponding to the monitoring points, the target fitting regression equation matching the target ozone concentration data is determined, including:

[0041] Determine a set of fitted regression equations, each of which corresponds to a monitoring point and a weather type;

[0042] Determine a plurality of first fitting regression equations according to matching results between the monitoring points and the monitoring points corresponding to each fitting regression equation in the set of fitting regression equations;

[0043] The target fitting regression equation corresponding to the monitoring point is determined according to the matching results between the meteorological data corresponding to the monitoring point and the plurality of first fitting regression equations.

[0044] In this embodiment, all equations in the fitting regression equation are obtained based on historical ozone concentration data. Assuming that there are N monitoring points and M weather types, there are N×M fitting regression equations in the fitting regression equation set, and each equation corresponds to one monitoring point and one weather type. For the first monitoring point (the current monitoring point), determine all first fitting regression equations that match the first monitoring point. Assuming that the current monitoring point is the kth, M first fitting regression equations will be obtained. For each equation in the first fitting regression equation set, calculate the similarity or match between its corresponding weather type and the current weather type. The calculation method of the similarity or match can be selected according to the actual situation, such as using the Euclidean distance, Manhattan distance, etc. of meteorological data. Select the equation with the highest similarity or match as the target fitting regression equation.

[0045] Exemplarily, there are three monitoring points A, B, and C, and the weather types are normal weather, dust weather, and rainy weather. The fitting regression equation for normal weather at point A is equation 1, the fitting regression equation for dust weather at point A is equation 2, and the fitting regression equation for rainy weather at point A is equation 3; the fitting regression equation for normal weather at point B is equation 4, the fitting regression equation for dust weather at point B is equation 5, and the fitting regression equation for rainy weather at point B is equation 6; the fitting regression equation for normal weather at point C is equation 7, the fitting regression equation for dust weather at point C is equation 8, and the fitting regression equation for rainy weather at point C is equation 9. If the current monitoring point is B and the monitored weather type is normal weather, the target fitting regression equation is equation 4.

[0046] S103: Input the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area.

[0047] In this embodiment, the target fitting regression equation is a mathematical model constructed based on statistics or machine learning algorithms, which can be used to predict the future changes in ozone concentration at each monitoring point. The predicted ozone concentration data is obtained by inputting the target ozone concentration data into the target fitting regression equation, and the predicted ozone concentration data represents an estimated value of the ozone concentration in the target area at a certain time point or time period in the future. These predicted data can be used to formulate environmental policies, monitor air quality, evaluate the effectiveness of emission reduction measures, etc.

[0048] From the above, it can be concluded that, firstly, the present invention determines the target fitting regression equation by targeting the meteorological data of the monitoring point and the area where it is located. Compared with the general prediction model, it can fully consider the variation law of ozone concentration at each monitoring point, and can better capture the subtle fluctuations and changing trends of ozone concentration, thereby significantly improving the accuracy and reliability of the prediction.

[0049] Secondly, the present invention uses less meteorological data to predict ozone concentration data, making it more convenient and quick to obtain predicted data, greatly reducing prediction costs and expanding the scope of application.

[0050] Finally, the present disclosure fully considers the impact of weather changes on the accuracy of ozone concentration prediction. In traditional methods, regression equations based on normal weather conditions are often used for prediction. However, when encountering extreme or special weather types, the prediction accuracy of this method will be significantly reduced. In order to overcome this limitation, the present disclosure innovatively designs regression equations for different weather types. In this way, when the actual weather changes, the monitoring point can quickly select the regression equation that best matches the current weather type for prediction. Doing so can not only significantly improve the accuracy of the prediction, but also better reflect the actual changes in ozone concentration under different weather conditions.

[0051] In one embodiment of the present disclosure, determining target ozone concentration data in a target area includes:

[0052] Identify the types of outliers in the initial ozone concentration data;

[0053] The outliers in the initial ozone concentration data collected at each monitoring point are eliminated or corrected according to the outlier type to obtain the target ozone concentration data.

[0054] In this embodiment, the outlier type refers to the data type that does not conform to the normal distribution law or expected range in the initial ozone concentration data. Outliers refer to those values ​​that are obviously deviated from other observed values ​​in the data set. These values ​​may be caused by measurement errors, instrument failures, data transmission errors, data entry errors, or natural variations. These outliers may be caused by instrument failures, data transmission errors, or other reasons. Common outlier types include constant value types, negative value types, and outlier types.

[0055] A constant value indicates a value that does not change over a period of time, a negative value indicates a value that is less than 0, and an outlier type refers to an excessively high outlier, an excessively low outlier, or a sudden change outlier.

[0056] Outliers are those observations with abnormally high values ​​in the initial ozone concentration data. These values ​​can be caused by instrument failure (such as sensor damage or oversensitivity), data transmission errors (such as data encoding errors or signal interference during transmission), or other unknown reasons. Outliers are usually significantly deviated from the normal range of other observations in the data set, which can mislead subsequent data analysis and predictions.

[0057] Low outliers refer to those observations with abnormally low values ​​in the initial ozone concentration data. These values ​​are also caused by instrument failure (such as sensor failure or insufficient sensitivity), data transmission errors (such as data loss or bit errors), or other factors. Low outliers can also distort the true distribution characteristics of the data and affect the accuracy of data analysis and prediction.

[0058] Sudden outliers refer to those observations in the initial ozone concentration data that suddenly change significantly in a short period of time. These values ​​can be caused by instrument failure (such as sudden sensor failure or recovery), data transmission errors (such as sudden loss or re-receipt of data packets), human intervention (such as data entry errors or intentional tampering), etc. Sudden outliers usually appear as "jump points" in the data sequence, which damage the continuity and stability of the data.

[0059] According to the outlier type, the outliers in the initial ozone concentration data collected at each monitoring point are removed or corrected to obtain the target ozone concentration data. Different outlier types have different processing methods. These outliers are removed or corrected according to the outlier type to obtain accurate target ozone concentration data.

[0060] It can be concluded from the above that in the prior art, the abnormal values ​​are generally determined first and then the abnormal data are deleted. However, this processing method may cause all the data of a certain monitoring point or a certain period of time to be deleted, thereby affecting the prediction of ozone concentration.

[0061] In contrast, the method proposed in the present disclosure is more detailed and flexible. It is not limited to simply deleting outliers, but selectively processes them according to the type of outliers. Specifically, the outliers in the initial ozone concentration data are first carefully classified and identified, and then targeted processing measures are taken according to different types of outliers. These measures may include deleting outliers that are obviously wrong or cannot be corrected, and correcting outliers that may be caused by instrument errors, data transmission problems, or changes in meteorological conditions through interpolation, smoothing, or other statistical methods.

[0062] In one embodiment of the present disclosure, the outlier type includes a constant value type, a negative value type, and an outlier type;

[0063] According to the outlier type, the outliers in the initial ozone concentration data collected at each monitoring point are eliminated or corrected to obtain the target ozone concentration data, including:

[0064] If the outlier type is a constant value type, the outlier will be removed;

[0065] If the outlier type is a negative value type and the outlier value is less than or equal to the first value, the outlier value is removed;

[0066] If the outlier type is a negative value type, and the outlier is greater than the first value, and the outlier is less than the second value, the outlier is corrected to the third value;

[0067] If the outlier type is an outlier type, the outlier will be removed;

[0068] The first value is smaller than the second value, and the second value is smaller than the third value.

[0069] In this embodiment, if the initial ozone concentration data of any monitoring point remains unchanged for a consecutive hour, and the initial ozone concentration value is greater than the value in other time periods, it is an outlier, and the outlier type is a constant value type. In this case, the outlier can be removed and the monitoring point corresponding to the outlier is marked.

[0070] If the initial ozone concentration value within b hours is less than or equal to the first value (for example, -10 micrograms / cubic meter), it is an abnormal value, and the abnormal type is a negative value type. In this case, the abnormal value can be removed. If the initial ozone concentration value within b hours is greater than the first value (for example, -10 micrograms / cubic meter), and the abnormal value is less than the second value (for example, 0 micrograms / cubic meter), these initial ozone concentration values ​​are corrected to a fourth value (for example, 2 micrograms / cubic meter). The fourth value is greater than the second value.

[0071] If the outlier type is an outlier type, it includes:

[0072] If the outlier value exceeds x times the ozone concentration data a hours before and after the current monitoring point, and / or if the outlier value exceeds x times the ozone concentration data in the adjacent area, and / or if the outlier value exceeds x times the ozone concentration data at each monitoring point in the area, then the outlier type is an outlier type.

[0073] For example, a is 1 and x is 1. Compare the ozone concentration data of the current monitoring point one hour before and after. If it exceeds 1 times, it is an outlier. Compare the ozone concentration data of the current monitoring point with that of each monitoring point in the adjacent area. If it exceeds 1 times, it is an outlier. Compare the ozone concentration data of other monitoring points in the area where the current monitoring point is located. If it exceeds 1 times, it is an outlier. These outliers are directly eliminated.

[0074] It can be concluded from the above that this embodiment, by implementing the above-mentioned outlier processing strategy, can accurately identify and effectively eliminate or correct constant values, negative values ​​and outliers in the initial ozone concentration data, thereby significantly improving the accuracy and reliability of the data set.

[0075] In one embodiment of the present disclosure, the ozone concentration prediction method further includes:

[0076] Classifying the historical ozone concentration data collected at each monitoring point according to the historical meteorological data of each monitoring point to obtain first historical ozone concentration data;

[0077] The historical meteorological data includes multiple weather characteristics, and the first historical ozone concentration data is the historical ozone concentration data corresponding to each weather characteristic;

[0078] A fitting regression equation corresponding to each weather feature is obtained according to the first historical ozone concentration data.

[0079] In this embodiment, first, historical meteorological data and corresponding historical ozone concentration data are collected from each monitoring point. These historical data are the basis for establishing a prediction model. The historical meteorological data contains multiple weather characteristics, which are important factors affecting ozone concentration.

[0080] The historical ozone concentration data are classified according to different weather characteristics. Specifically, the historical ozone concentration data corresponding to each weather characteristic is extracted separately to form the first historical ozone concentration data. In this way, each weather characteristic will have a set of corresponding ozone concentration data.

[0081] Using statistical methods or machine learning algorithms, the first historical ozone concentration data corresponding to each weather feature is fitted to obtain a fitted regression equation corresponding to each weather feature. These fitted regression equations describe the mathematical relationship between weather features and ozone concentration. For example, a regression equation may indicate that as temperature increases, ozone concentration will also increase accordingly.

[0082] It can be concluded from the above that the present embodiment can accurately associate the historical ozone concentration data with the corresponding weather characteristics and construct a corresponding fitting regression equation for each weather characteristic, which greatly improves the accuracy of ozone concentration prediction.

[0083] In one embodiment of the present disclosure, the ozone concentration prediction method further includes:

[0084] The fitting regression equation is updated according to the historical ozone concentration data within the first time period and the historical meteorological data corresponding to each monitoring point.

[0085] In this embodiment, the first duration can be 15 days, 1 month or other durations. The equipment at the monitoring point can integrate the historical ozone concentration data of the monitoring point for the past 15 days, 1 month or other durations and the meteorological data corresponding to the monitoring point into the data source every first duration to automatically update the fitting regression equation. In this embodiment, by regularly integrating the historical ozone concentration data and the corresponding meteorological data (such as every 15 days or 1 month), the fitting regression equation is updated, which can significantly improve the timeliness and accuracy of the ozone concentration prediction. This dynamic update mechanism ensures that the prediction model can keep up with environmental changes, promptly reflect the relationship between the latest meteorological conditions and ozone concentrations, and provide a more reliable scientific basis for air quality management and environmental protection.

[0086] In one embodiment of the present disclosure, the fitting regression equation corresponding to each weather feature is calculated by a first formula, and the first formula is:

[0087]

[0088] in, represents the predicted ozone concentration value for the n+1th hour under the ith weather feature, represents the predicted ozone concentration value at the nth hour under the ith weather feature, represents the fitted regression coefficient of the ith weather feature, Represents the random error of the fitting regression equation corresponding to the i-th weather feature, where n,i is a positive integer.

[0089] In this embodiment, reference Figure 3 , Figure 4 and Figure 5 ,in, Figure 3 is the fitting regression equation under the first weather characteristic (normal weather), . The coefficient of determination measures the proportion of the variation in the dependent variable (the actual monitoring outcome) in the regression model that can be explained by the independent variables (the factors in the prediction model). The value of is between 0 and 1. The closer it is to 1, the stronger the predictive ability of the model and the more reliable the prediction results. It represents the coefficient of determination of the regression model under normal weather conditions. The horizontal axis represents the ozone concentration value at 10:00 (current hour) under normal weather conditions, and the vertical axis represents the predicted ozone concentration value at 11:00 (next hour) under normal weather conditions.

[0090] Figure 4 is the fitting regression equation under the second weather feature (sandstorm weather), . It represents the determination coefficient of the regression model under dust weather. The horizontal axis represents the ozone concentration value at 10:00 (current hour) under dust weather, and the vertical axis represents the predicted ozone concentration value at 11:00 (next hour) under dust weather.

[0091] Figure 5 is the fitting regression equation under the third weather feature (rainy weather), . It represents the coefficient of determination of the regression model under rainy weather. The horizontal axis represents the ozone concentration value at 10 o'clock (current hour) under rainy weather, and the vertical axis represents the predicted ozone concentration value at 11 o'clock (next hour) under rainy weather.

[0092] In one embodiment of the present disclosure, the ozone concentration prediction method further includes:

[0093] Determine an abnormal ozone concentration prediction value based on the predicted ozone concentration data;

[0094] The type of pollution source is determined based on the predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in the same area corresponding to the predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in other areas corresponding to the predicted ozone concentration anomaly value, and the wind direction.

[0095] In this embodiment, the ozone concentration data of each monitoring point under different wind directions will be affected, so the historical ozone concentration data of each monitoring point under different wind directions are classified and counted. The wind direction may include north wind, northeast wind, east wind, southeast wind, south wind, southwest wind, west wind and northwest wind. The ozone concentration abnormality prediction value in all current monitoring points is determined, and the ozone concentration abnormality prediction value represents the ozone concentration value greater than the first preset threshold.

[0096] The predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in the same area corresponding to the predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in other areas corresponding to the predicted ozone concentration anomaly value and the wind direction are input into the analysis system. The analysis system calls the classification statistical results of the historical ozone concentration data of different wind directions of each monitoring point and the predicted ozone concentration data of each current monitoring point to judge the type of pollution source.

[0097] For example, if the predicted ozone concentration data upwind of the current monitoring point (ozone concentration data in other areas) is greater than the predicted value of the abnormal ozone concentration, the pollution source is judged to be of the "external input" type. For example, the current monitoring point is monitoring point A, and monitoring point B (a monitoring point in other adjacent areas of the area where monitoring point A is located) is located northwest of monitoring point A. When the wind direction corresponding to the ozone concentration data collected by monitoring point A is northwest wind, it is necessary to consider whether the predicted ozone concentration data of monitoring point B (upwind) is greater than the predicted value of the abnormal ozone concentration (high value point) of monitoring point A.

[0098] If the predicted ozone concentration data upwind of the current monitoring point is less than or equal to the predicted value of the abnormal ozone concentration, and the predicted ozone concentration data of other monitoring points in the same area as the current monitoring point is greater than the predicted value of the abnormal ozone concentration, it is judged to be local pollution and can be traced in detail in combination with local pollution sources.

[0099] refer to Figure 6 , Figure 6 A complete flow chart for ozone concentration prediction provided for an embodiment of the present disclosure. The monitoring system can be a monitoring terminal, an electronic device, etc. The monitoring system monitors the ozone concentration data and meteorological data uploaded by each monitoring point in real time, and analyzes whether there are abnormal values ​​in the ozone concentration data. If so, the abnormal values ​​are removed or corrected; if not, the fitting regression equation between the hourly ozone concentration data under different weather types is determined based on the historical ozone concentration data, meteorological data and wind direction, and the corresponding ozone concentration data under different weather types at each current monitoring point is input into the fitting regression equation to obtain the predicted ozone concentration data for the next hour. The ozone concentration at each monitoring point is predicted, and the high ozone value is warned based on the predicted value. The high ozone value, the monitoring points around the current monitoring point, and the predicted ozone concentration at the upwind monitoring point are compared and analyzed to identify the type of pollution source.

[0100] From the above, it can be concluded that considering that the hourly ozone prediction of the monitoring point plays a vital role in the refined control of urban ozone, the present disclosure proposes to use only the data law of the ozone concentration itself to predict the hourly concentration, which requires less data, has low calculation cost, short time consumption, and strong scalability. The predicted results of the ozone concentration prediction method proposed in the present disclosure are different from the actual monitoring results R 2 The prediction accuracy is as high as 0.9 or above, the average deviation is below 1%, and the prediction accuracy is high. In addition, the disclosure also combines the special weather conditions such as sandstorms and rainfall, reduces the deviation between the prediction results and the actual monitoring results by 0.2% on sandstorm days, and reduces the deviation between the prediction results and the actual monitoring results by 1.6% on precipitation days, which improves the prediction accuracy and is of great significance for guiding the prevention and control of ozone pollution.

[0101] Corresponding to the ozone concentration prediction method in the above embodiment, Figure 7 This is a block diagram of the structure of an ozone concentration prediction device provided by an embodiment of the present disclosure. For the sake of convenience, only the parts related to the embodiment of the present disclosure are shown. Figure 7 The ozone concentration prediction device 20 includes: a data acquisition module 21, a regression equation determination module 22 and a calculation module 23.

[0102] The data acquisition module 21 is used to determine the target ozone concentration data in the target area, where the target area is the area where the monitoring point corresponding to the target ozone concentration data is located;

[0103] A regression equation determination module 22, for determining a target fitting regression equation matching the target ozone concentration data according to the monitoring point and the meteorological data corresponding to the monitoring point;

[0104] The calculation module 23 is used to input the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area.

[0105] In one embodiment of the present disclosure, the data acquisition module 21 is specifically used for:

[0106] Identify the types of outliers in the initial ozone concentration data;

[0107] The outliers in the initial ozone concentration data collected at each monitoring point are eliminated or corrected according to the outlier type to obtain the target ozone concentration data.

[0108] In one embodiment of the present disclosure, the data acquisition module 21 is specifically used for:

[0109] The types of outliers include constant value type, negative value type and outlier type;

[0110] According to the outlier type, the outliers in the initial ozone concentration data collected at each monitoring point are eliminated or corrected to obtain the target ozone concentration data, including:

[0111] If the outlier type is a constant value type, the outlier will be removed;

[0112] If the outlier type is a negative value type and the outlier value is less than or equal to the first value, the outlier value is removed;

[0113] If the outlier type is a negative value type, and the outlier is greater than the first value, and the outlier is less than the second value, the outlier is corrected to the third value;

[0114] If the outlier type is an outlier type, the outlier will be removed;

[0115] The first value is smaller than the second value, and the second value is smaller than the third value.

[0116] In one embodiment of the present disclosure, the regression equation determination module 22 is further used to:

[0117] Classifying the historical ozone concentration data collected at each monitoring point according to the historical meteorological data of each monitoring point to obtain first historical ozone concentration data;

[0118] The historical meteorological data includes multiple weather characteristics, and the first historical ozone concentration data is the historical ozone concentration data corresponding to each weather characteristic;

[0119] A fitting regression equation corresponding to each weather feature is obtained according to the first historical ozone concentration data.

[0120] In one embodiment of the present disclosure, the regression equation determination module 22 is further used to:

[0121] The fitting regression equation is updated according to the historical ozone concentration data within the first time period and the historical meteorological data corresponding to each monitoring point.

[0122] In one embodiment of the present disclosure, the fitting regression equation corresponding to each weather feature is calculated by a first formula, and the first formula is:

[0123]

[0124] in, represents the predicted ozone concentration value for the n+1th hour under the ith weather feature, represents the predicted ozone concentration value at the nth hour under the ith weather feature, represents the fitted regression coefficient of the ith weather feature, Represents the random error of the fitting regression equation corresponding to the i-th weather feature, where n,i is a positive integer.

[0125] In one embodiment of the present disclosure, the calculation module 23 is further used to:

[0126] Determine an abnormal ozone concentration prediction value based on the predicted ozone concentration data;

[0127] The type of pollution source is determined based on the predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in the same area corresponding to the predicted ozone concentration anomaly value, the predicted ozone concentration data of each monitoring point in other areas corresponding to the predicted ozone concentration anomaly value, and the wind direction.

[0128] See also Figure 8 , Figure 8 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 8 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 7 The functions of modules 21 to 23 are shown.

[0129] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be 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 the processor may also be any conventional processor, etc.

[0130] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0131] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0132] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the ozone concentration prediction method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device described in the embodiments of the present disclosure, which will not be repeated here.

[0133] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, 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, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0134] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0135] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0136] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0137] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0138] 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 embodiments of the present disclosure.

[0139] In addition, each functional unit in each embodiment of the present disclosure 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.

[0140] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for predicting ozone concentration, characterized in that: include: Determine target ozone concentration data in a target area, where the target area is an area where a monitoring point corresponding to the target ozone concentration data is located; Determine a target fitting regression equation matching the target ozone concentration data according to the monitoring point and the meteorological data corresponding to the monitoring point; Inputting the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area; The ozone concentration prediction method further comprises: Classifying the historical ozone concentration data collected at each monitoring point according to the historical meteorological data of each monitoring point to obtain first historical ozone concentration data; Wherein, the historical meteorological data includes a plurality of weather characteristics, and the first historical ozone concentration data is the historical ozone concentration data corresponding to each weather characteristic; Obtaining a fitting regression equation corresponding to each weather feature according to the first historical ozone concentration data; The fitting regression equation corresponding to each weather feature is calculated by a first formula, and the first formula is: in, represents the predicted ozone concentration value for the n+1th hour under the ith weather feature, represents the predicted ozone concentration value at the nth hour under the ith weather feature, represents the fitted regression coefficient of the ith weather feature, Represents the random error of the fitting regression equation corresponding to the i-th weather feature, where n,i is a positive integer.

2. The ozone concentration prediction method according to claim 1, characterized in that: Determining target ozone concentration data in the target area includes: Identify the types of outliers in the initial ozone concentration data; According to the abnormal value type, the abnormal values ​​in the initial ozone concentration data collected at each monitoring point are eliminated or corrected to obtain the target ozone concentration data.

3. The ozone concentration prediction method according to claim 2, characterized in that: The outlier types include constant value type, negative value type and outlier type; The step of removing or correcting the abnormal values ​​in the initial ozone concentration data collected from each monitoring point according to the abnormal value type to obtain the target ozone concentration data includes: If the abnormal value type is a constant value type, the abnormal value is removed; If the abnormal value type is a negative value type, and the abnormal value is less than or equal to the first value, the abnormal value is removed; If the abnormal value type is a negative value type, and the abnormal value is greater than the first value, and the abnormal value is less than the second value, then the abnormal value is corrected to a third value; If the outlier type is an outlier type, the outlier is removed; The first value is smaller than the second value, and the second value is smaller than the third value.

4. The ozone concentration prediction method according to claim 1, characterized in that: Also includes: The fitting regression equation is updated according to the historical ozone concentration data within the first time period and the historical meteorological data corresponding to each monitoring point.

5. The ozone concentration prediction method according to claim 1, characterized in that: Also includes: Determining an abnormal ozone concentration prediction value according to the predicted ozone concentration data; The type of pollution source is determined based on the ozone concentration anomaly prediction value, the predicted ozone concentration data of each monitoring point in the same area corresponding to the ozone concentration anomaly prediction value, the predicted ozone concentration data of each monitoring point in other areas corresponding to the ozone concentration anomaly prediction value, and the wind direction.

6. An ozone concentration prediction device, characterized in that: include: A data acquisition module, used to determine target ozone concentration data in a target area, where the target area is an area where a monitoring point corresponding to the target ozone concentration data is located; A regression equation determination module, used to determine a target fitting regression equation matching the target ozone concentration data according to the monitoring point and the meteorological data corresponding to the monitoring point; A calculation module, used for inputting the target ozone concentration data into the target fitting regression equation to obtain the predicted ozone concentration data of the target area; The regression equation determination module is also used to: Classifying the historical ozone concentration data collected at each monitoring point according to the historical meteorological data of each monitoring point to obtain first historical ozone concentration data; The historical meteorological data includes a plurality of weather characteristics, and the first historical ozone concentration data is the historical ozone concentration data corresponding to each weather characteristic; Obtaining a fitting regression equation corresponding to each weather feature according to the first historical ozone concentration data; The fitting regression equation corresponding to each weather feature is calculated by a first formula, and the first formula is: in, represents the predicted ozone concentration value for the n+1th hour under the ith weather feature, represents the predicted ozone concentration value at the nth hour under the ith weather feature, represents the fitted regression coefficient of the ith weather feature, Represents the random error of the fitting regression equation corresponding to the i-th weather feature, where n,i is a positive integer.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images