Air quality forecasting method and device, storage medium and electronic equipment

Abstract

The application provides an air quality prediction method and device, a storage medium and an electronic device. The method comprises the following steps: obtaining initial air quality prediction data and site set prediction data, wherein the initial air quality prediction data comprises initial pollutant concentration prediction values of each target grid in a target area, and each target grid is a grid division result of the target area at a high resolution; determining first regional concentration prediction results of each sub-region in the target area based on the initial air quality prediction data, and determining second regional concentration prediction results of each sub-region based on the site set prediction data; and determining prediction deviation coefficients of each sub-region based on the first regional concentration prediction results and the second regional concentration prediction results of each sub-region respectively, so as to correct the initial air quality prediction data and obtain target air quality prediction data. The embodiment of the application can improve the accuracy of high-resolution air quality prediction.

Description

Technical Field

[0001] The present invention relates to the field of air quality technology, and in particular to an air quality forecasting method, device, storage medium and electronic equipment. Background Art

[0002] Currently, numerical models used to forecast the spatial distribution of pollutant concentrations typically have a spatial resolution of 27 km (kilometers) to 9 km, or a nested configuration of 27 km, 9 km, and 3 km. However, to better support precision pollution control efforts, pollution forecasts with higher spatial precision (i.e., higher resolution) are required. The process of obtaining finer resolution (i.e., high resolution, small scale) forecasts from coarse-resolution (i.e., low resolution, large scale) forecasts is generally referred to as downscaling. Relevant technologies typically use numerical modeling techniques to refine the coarse-resolution results by nesting high-resolution sub-regions within the coarse-resolution simulation domain. However, mature numerical models are typically based on research results at mesoscale resolution. While increasing spatial resolution is feasible at the software level, the forecast performance is poor and the accuracy is low. Therefore, there is currently no effective solution for improving the accuracy of high-resolution air quality forecasts. Summary of the Invention

[0003] In view of this, an embodiment of the present invention provides an air quality forecasting method, device, storage medium and electronic device to solve the problem of low accuracy of high-resolution air quality forecast in related technologies. That is to say, the embodiment of the present invention can determine the forecast deviation coefficient of each sub-area through site collection forecast data, etc., so as to correct the initial air quality forecast data and obtain target air quality forecast data with higher accuracy, which can effectively improve the accuracy of high-resolution air quality forecast, that is, the target air quality forecast data can retain the characteristics of high-precision spatial distribution and have a more accurate pollutant concentration forecast level.

[0004] According to one aspect of the present invention, there is provided an air quality forecasting method, the method comprising:

[0005] Acquiring initial air quality forecast data and site aggregate forecast data, wherein the initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid in the target area, wherein each target grid is a high-resolution grid division result of the target area;

[0006] Determining a first regional concentration forecast result for each sub-region in the target area based on the initial air quality forecast data, and determining a second regional concentration forecast result for each sub-region based on the site aggregate forecast data;

[0007] determine a prediction deviation coefficient of each of the sub-regions based on the first regional concentration prediction result and the second regional concentration prediction result of the sub-region respectively;

[0008] correct the initial air quality prediction data based on the prediction deviation coefficient of each of the sub-regions to obtain target air quality prediction data.

[0009] According to another aspect of the present application, there is provided an air quality prediction device, the device comprising:

[0010] an obtaining unit configured to obtain initial air quality prediction data and site set prediction data, the initial air quality prediction data comprising initial pollutant concentration prediction values of each target grid in a target region, the target grid being a grid division result of the target region at a high resolution;

[0011] a processing unit configured to determine a first regional concentration prediction result of each of the sub-regions based on the initial air quality prediction data, and determine a second regional concentration prediction result of each of the sub-regions based on the site set prediction data;

[0012] the processing unit is further configured to determine a prediction deviation coefficient of each of the sub-regions based on the first regional concentration prediction result and the second regional concentration prediction result of the sub-region respectively;

[0013] the processing unit is further configured to correct the initial air quality prediction data based on the prediction deviation coefficient of each of the sub-regions to obtain target air quality prediction data.

[0014] According to another aspect of the present application, there is provided an electronic device comprising a processor and a memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the above-mentioned method.

[0015] According to another aspect of the present application, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the above-mentioned method.

[0016] Embodiments of the present invention can obtain initial air quality forecast data and site aggregate forecast data. The initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid within the target area. Each target grid represents a high-resolution grid division of the target area. Based on the initial air quality forecast data, a first regional concentration forecast result for each sub-region within the target area can be determined. Based on the site aggregate forecast data, a second regional concentration forecast result for each sub-region can be determined. Based on this, a forecast deviation coefficient for each sub-region can be determined based on the first and second regional concentration forecast results, respectively. Based on the forecast deviation coefficients for each sub-region, the initial air quality forecast data can be corrected to obtain target air quality forecast data. Thus, embodiments of the present invention can determine the forecast deviation coefficients for each sub-region using site aggregate forecast data, etc., thereby correcting the initial air quality forecast data to obtain highly accurate target air quality forecast data. This effectively improves the accuracy of high-resolution air quality forecasts, ensuring that the target air quality forecast data retains the characteristics of high-precision spatial distribution while also providing a relatively accurate pollutant concentration forecast level. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Further details, features and advantages of the present invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0018] Figure 1 A schematic flow chart of an air quality forecasting method according to an exemplary embodiment of the present invention is shown;

[0019] Figure 2 A schematic flow chart of another air quality forecasting method according to an exemplary embodiment of the present invention is shown;

[0020] Figure 3 A schematic flow chart of another air quality forecasting method according to an exemplary embodiment of the present invention is shown;

[0021] Figure 4 A schematic block diagram of an air quality forecasting device according to an exemplary embodiment of the present invention is shown;

[0022] Figure 5 A block diagram of an exemplary electronic device capable of implementing the embodiments of the present invention is shown. DETAILED DESCRIPTION

[0023] Embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of protection of the present invention.

[0024] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0025] The term "including" and its variations used in this document are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description. It should be noted that the concepts of "first", "second", etc. mentioned in the present invention are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0026] It should be noted that the modifications of "one" and "multiple" mentioned in the present invention are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0027] The names of the messages or information exchanged between multiple devices in the embodiments of the present invention are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0028] It should be noted that the air quality forecasting method provided in the embodiments of the present invention may be executed by one or more electronic devices, which is not limited in the present invention. Specifically, the electronic device may be a terminal (i.e., a client) or a server. If the execution entity includes multiple electronic devices, and the multiple electronic devices include at least one terminal and at least one server, the air quality forecasting method provided in the embodiments of the present invention may be jointly executed by the terminal and the server. Accordingly, the terminals mentioned herein may include, but are not limited to, smartphones, tablets, laptops, desktop computers, smart watches, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, and the like. The servers mentioned herein may be independent physical servers, server clusters or distributed systems consisting of multiple physical servers, or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDNs (Content Delivery Networks), and big data and artificial intelligence platforms.

[0029] Based on the above description, an embodiment of the present invention proposes an air quality forecasting method, which can be executed by the electronic device (terminal or server) mentioned above; or, the air quality forecasting method can be executed by the terminal and the server together. For the sake of convenience, the following description will take the electronic device executing the air quality forecasting method as an example; Figure 1 As shown, the air quality forecasting method may include the following steps S101-S104:

[0030] S101, obtaining initial air quality forecast data and site aggregate forecast data, the initial air quality forecast data including initial pollutant concentration forecast values ​​of each target grid in the target area, each target grid being a high-resolution grid division result of the target area.

[0031] Optionally, the resolution (i.e., spatial resolution) corresponding to each target grid (i.e., grid point) can be 1 km, 2 km, or the like; this is not limited in this embodiment of the present invention. Optionally, a pollutant concentration forecast value (such as an initial pollutant concentration forecast value) can be a target pollutant concentration forecast value, meaning that embodiments of the present invention can predict or observe the concentration of a target pollutant. Optionally, the target pollutant can be PM2.5 (fine particulate matter), CO (carbon monoxide), NOx (nitrogen oxides), or the like; this is not limited in this embodiment of the present invention. Optionally, the target area can be any area; this is not limited in this embodiment of the present invention.

[0032] In the embodiment of the present invention, the initial air quality forecast data may be obtained in the following ways, but is not limited to:

[0033] The first acquisition method: the initial air quality forecast data is stored in the storage space of the electronic device itself. In this case, the initial air quality forecast data can be obtained from the storage space itself.

[0034] The second acquisition method: The electronic device can obtain the initial air quality forecast data download link and use the forecast data downloaded based on the initial air quality forecast data download link as the initial air quality forecast data.

[0035] A third acquisition method: The electronic device may acquire low-resolution grid concentration prediction data and downscaling indicator data. The low-resolution grid concentration prediction data may include concentration prediction results for each initial grid in the target area. The resolution corresponding to each initial grid is lower than the resolution corresponding to each target grid (i.e., the scale corresponding to each initial grid is larger than the scale corresponding to each target grid, and the larger the scale, the lower the resolution). The downscaling indicator data may include grid indicator data for each target grid. The electronic device may then invoke a target statistical downscaling model to perform downscaling prediction based on the low-resolution grid concentration prediction data and the downscaling indicator data to obtain initial air quality forecast data, thereby acquiring the initial air quality forecast data. Optionally, each initial grid may be a grid division result of the target area at a low resolution (e.g., 27 km or 9 km). In other words, the resolution corresponding to each initial grid may be 27 km or 9 km, etc. This is not limited in this embodiment of the present invention. Optionally, the grid indicator data for a target grid may include, but is not limited to, at least one of the following: geographic information (e.g., terrain height, land use type, etc.), emission information (e.g., population, vehicle flow, emission rate, etc.), and meteorological information (e.g., temperature, humidity, wind speed, etc.) of the corresponding target grid; this is not limited in this embodiment of the present invention. Based on this, the downscaling indicator data may include, but is not limited to, at least one of the following: high-precision emissions (including emission information for each target grid), high-precision geographic information (including geographic information for each target grid), and high-precision meteorological information (including meteorological information for each target grid); this is not limited in this embodiment of the present invention.

[0036] Optionally, when obtaining low-resolution grid concentration prediction data, the electronic device may store low-resolution grid concentration prediction data in its own storage space, so that the low-resolution grid concentration prediction data can be obtained from its own storage space; or, a low-resolution grid concentration prediction data download link may be obtained, so that the prediction data downloaded based on the low-resolution grid concentration prediction data download link can be used as the low-resolution grid concentration prediction data; or, the electronic device may call a target air quality numerical model and determine the low-resolution grid concentration prediction data based on the data to be predicted, that is, input the data to be predicted into the target air quality numerical model to output the low-resolution grid concentration prediction data, thereby obtaining the low-resolution grid concentration prediction data, etc.; the embodiment of the present invention is not limited to this. Optionally, the target air quality numerical model can be NAQPMS (Nested Air Quality Prediction Modeling System), CMAQ (an air quality forecast and assessment system), CAMx (an atmospheric chemistry-based atmospheric pollutant calculation model for ozone, particulate matter, etc.), WRF-Chem (an atmospheric chemistry online coupling model), etc.; the embodiment of the present invention is not limited to this. Optionally, the data to be forecasted may include, but is not limited to, at least one of the following: emission information, geographic information, meteorological information, and initial pollutant concentrations of each initial grid within a target time range (e.g., the next 7 days or 15 days, etc.), which is not limited in this embodiment of the present invention; optionally, the target time range may include a target forecast time, which may be any forecast time (e.g., a certain hour on the first day of the future or the second day of the future, etc.), which is not limited in this embodiment of the present invention. In this embodiment of the present invention, low-resolution grid concentration forecast data, initial air quality forecast data, target air quality forecast data, and site aggregate forecast data may all include corresponding values ​​(e.g., concentration forecast results, initial pollutant concentration forecast values, target pollutant concentration forecast values, or site pollutant concentration forecast values, etc.) of corresponding forecast objects (e.g., initial grids, target grids, or observation sites, etc.) at the target forecast time. In other words, one piece of data may correspond to one forecast time, and so on.

[0037] Accordingly, when acquiring the downscaling indication data, the electronic device may store the downscaling indication data in its own storage space, and in this case, the downscaling indication data may be acquired from the own storage space; or, a downscaling indication data download link may be acquired, and the downscaling indication data may be acquired based on the downscaling indication data download link, etc. Optionally, the downscaling indication data may include grid indication data for each target grid at the target forecast time.

[0038] Furthermore, when the target statistical downscaling model is invoked to perform downscaling prediction based on the low-resolution grid concentration prediction data and the downscaling indicator data to obtain initial air quality forecast data, the electronic device may input the low-resolution grid concentration prediction data and the downscaling indicator data into the target statistical downscaling model to output the initial air quality forecast data. Based on this, the initial air quality forecast data may be obtained through a statistical downscaling method. Optionally, the target statistical downscaling model may be a logistic regression model, a linear regression model, or any neural network model, etc.; this is not limited in this embodiment of the present invention.

[0039] Optionally, methods for obtaining site aggregate forecast data may include but are not limited to at least one of the following:

[0040] The first acquisition method: the electronic device stores the site collection forecast data in its own storage space. In this case, the electronic device can acquire the site collection forecast data from its own storage space.

[0041] The second acquisition method: the electronic device may obtain a site aggregate forecast data download link to download the site aggregate forecast data based on the site aggregate forecast data download link.

[0042] The third acquisition method: the electronic device can obtain the data to be forecasted, and call each air quality numerical model in the air quality numerical model set respectively, and determine the air quality forecast data under each air quality numerical model based on the data to be forecasted, and then input the data to be forecasted into each air quality numerical model respectively to output the air quality forecast data under each air quality numerical model; then, the site forecast data to be corrected under each air quality numerical model can be determined from the air quality forecast data under each air quality numerical model; further, the deviation correction parameter set under each air quality numerical model can be determined, and based on the deviation correction parameter set under each air quality numerical model, the site forecast data to be corrected under each air quality numerical model can be corrected respectively to obtain the corrected site forecast data under each air quality numerical model; based on this, the site set forecast data can be determined based on the corrected site forecast data under each air quality numerical model to achieve the acquisition of the site set forecast data, and so on. Optionally, the air quality numerical model set may include but is not limited to at least one of the following: NAQPMS, CMAQ, CAMx, and WRF-Chem, etc.; this is not limited in this embodiment of the present invention.

[0043] Among them, the site forecast data to be revised under an air quality numerical model may include the site forecast concentration value to be revised for each observation site in the target area under the corresponding air quality numerical model, and the air quality forecast data under an air quality numerical model may include the pollutant concentration forecast value (i.e., the pollutant concentration forecast value of the target pollutant) of each grid in the target area (such as the initial grid or the grid divided according to other resolutions) under the corresponding air quality numerical model. Optionally, when determining the site forecast data to be revised under each air quality numerical model from the air quality forecast data under each air quality numerical model, for any air quality numerical model in the air quality numerical model set and any observation site in the target area, the electronic device can determine the pollutant concentration forecast value of the grid closest to any observation site from the air quality forecast data under any air quality numerical model as the site forecast concentration value to be revised under any air quality numerical model for any observation site, so as to determine the site forecast data to be revised under any air quality numerical model from the air quality forecast data under any air quality numerical model; or, the pollutant concentration forecast values ​​of the first P grids closest to any observation site can be determined for weighted summation, thereby obtaining the site forecast concentration value to be revised under any air quality numerical model for any observation site, where P is a positive integer, and so on; this embodiment of the present invention is not limited to this. Optionally, an observation site can be a national control site, and so on.

[0044] Optionally, the deviation correction parameter set under each air quality numerical model can be set according to experience or actual needs, or can be determined by historical forecast data and historical observation data under each air quality numerical model. The embodiment of the present invention is not limited to this. Optionally, the historical forecast data under an air quality numerical model may include at least one historical concentration forecast value (i.e., the historical concentration forecast value of the target pollutant) for each observation site under the corresponding air quality numerical model, that is, it may include at least one historical concentration forecast value for each observation site under the corresponding air quality numerical model and at least one historical forecast time, where the time forecast index corresponding to each historical forecast time may be the same as the time forecast index corresponding to the target forecast time (a time forecast index may be used to indicate the interval length of the forecast time, such as the time forecast index may all be the second day in the future, in which case a historical concentration forecast value may be a historical concentration forecast value obtained by forecasting the second day after any historical time in the past, and so on), the historical observation data may include at least one historical concentration observation value for each observation site at at least one historical forecast time (that is, it may include at least one historical concentration observation value (i.e., the historical concentration observation value of the target pollutant) for each observation site), a historical concentration forecast value for an observation site corresponds to a historical concentration observation value for the corresponding observation site, that is, a historical concentration forecast value for an observation site at a historical forecast time corresponds to a historical concentration observation value for the corresponding observation site at the corresponding historical forecast time.

[0045] In one embodiment, a deviation correction parameter set under an air quality numerical model may include the deviation correction parameters of each observation site under the corresponding air quality numerical model, that is, it may include the deviation correction parameters of each observation site under the corresponding air quality numerical model and the time forecast index corresponding to the target forecast time. Then, when determining the deviation correction parameter set under each air quality numerical model based on the historical forecast data and historical observation data under each air quality numerical model, for any observation site in the target area and any air quality numerical model in the air quality numerical model set, the electronic device may perform root mean square error calculation on at least one historical concentration forecast value of any observation site under any air quality numerical model and at least one historical concentration observation value of any observation site to obtain the root mean square error of any observation site under any air quality numerical model, and determine the deviation correction parameter set of any observation site under any air quality numerical model based on the mean operation result between the difference between at least one historical concentration observation value of any observation site and the corresponding historical concentration forecast value of any observation site under any air quality numerical model. The sign of the root mean square error under the air quality numerical model (i.e., positive or negative sign, such as positive if the mean operation result is positive, negative if the mean operation result is negative, and so on) is used to determine the deviation correction parameter of any observation station under any air quality numerical model (such as a positive root mean square error, or a negative root mean square error, etc.) based on the root mean square error of any observation station under any air quality numerical model and the sign of the root mean square error of any observation station under any air quality numerical model; or, the mean operation result between the difference between at least one historical concentration observation value of any observation station and the corresponding historical concentration forecast value of any observation station under any air quality numerical model can be used as the deviation correction parameter of any observation station under any air quality numerical model; or, the mean operation result between the ratio of at least one historical concentration observation value of any observation station to the corresponding historical concentration forecast value of any observation station under any air quality numerical model can be used as the deviation correction parameter of any observation station under any air quality numerical model, and so on; the embodiment of the present invention is not limited to this. In this case, the embodiment of the present invention can more accurately describe the deviation correction parameters of different observation sites under different air quality numerical models.

[0046] In another embodiment, a deviation correction parameter set under an air quality numerical model may include deviation correction parameters under the corresponding air quality numerical model, that is, deviation correction parameters under the corresponding air quality numerical model and the time forecast index corresponding to the target forecast time. At this time, the deviation correction parameters under the same air quality numerical model are the same for different observation sites. Then, when determining the deviation correction parameter set under each air quality numerical model based on the historical forecast data and historical observation data under each air quality numerical model, for any air quality numerical model in the air quality numerical model set, the electronic device may determine the deviation correction parameter under any air quality numerical model based on at least one historical concentration forecast value of each observation site under any air quality numerical model and at least one historical concentration observation value of each observation site, so as to obtain a deviation correction parameter set under any air quality numerical model, such as taking the mean operation result between the difference between at least one historical concentration observation value of each observation site and the corresponding historical concentration forecast value of the corresponding observation site under any air quality numerical model as the deviation correction parameter under any air quality numerical model, and so on. The embodiment of the present invention is not limited to this. In this case, the deviation correction parameters of different observation sites under any air quality numerical model can all be the deviation correction parameters under any air quality numerical model, that is, the deviation correction parameters of different observation sites under any air quality numerical model can be the same.

[0047] Optionally, based on the deviation correction parameter set under each air quality numerical model, the site forecast data to be corrected under each air quality numerical model is corrected respectively to obtain the corrected site forecast data under each air quality numerical model. For any observation site in the target area and any air quality numerical model in the air quality numerical model set, the electronic device can use the deviation correction parameter of any observation site under any air quality numerical model to correct the site forecast concentration value to be corrected for any observation site under any air quality numerical model to obtain the corrected site forecast concentration value for any observation site under any air quality numerical model. The corrected site forecast data under one air quality numerical model include the corrected site forecast concentration value of each observation site under the corresponding air quality numerical model. Optionally, when a deviation correction parameter is used to indicate the difference between the historical concentration observation value and the historical concentration forecast value of an observation site (such as the deviation correction parameter determined by the difference between the historical concentration observation value and the historical concentration forecast value), the forecast concentration value of the site to be corrected at any observation site under any air quality numerical model can be added to the deviation correction parameter of any observation site under any air quality numerical model to achieve correction of the forecast concentration value of the site to be corrected at any observation site under any air quality numerical model; or, when a deviation correction parameter is used to indicate the difference between the historical concentration forecast value and the historical concentration observation value of an observation site (such as the deviation correction parameter determined by the difference between the historical concentration forecast value and the historical concentration observation value), the forecast concentration value of the site to be corrected at any observation site under any air quality numerical model can be subtracted from the deviation correction parameter of any observation site under any air quality numerical model to achieve correction of the forecast concentration value of the site to be corrected at any observation site under any air quality numerical model. The point forecast concentration value is corrected; or, when a deviation correction parameter is used to indicate the ratio between the historical concentration forecast value and the historical concentration observation value of an observation site (such as the deviation correction parameter determined by the ratio between the historical concentration forecast value and the historical concentration observation value), the forecast concentration value of the to-be-corrected site of any observation site under any air quality numerical model can be divided by the deviation correction parameter of any observation site under any air quality numerical model to achieve correction of the forecast concentration value of the to-be-corrected site of any observation site under any air quality numerical model; or, when a deviation correction parameter is used to indicate the ratio between the historical concentration observation value and the historical concentration forecast value of an observation site, the forecast concentration value of the to-be-corrected site of any observation site under any air quality numerical model can be multiplied by the deviation correction parameter of any observation site under any air quality numerical model to achieve correction of the forecast concentration value of the to-be-corrected site of any observation site under any air quality numerical model, and so on; the embodiment of the present invention is not limited to this.

[0048] Optionally, when determining the site set forecast data based on the revised site forecast data under each air quality numerical model, the electronic device may determine the weight of each air quality numerical model for any observation site in the target area, and perform weighted summation of the revised site forecast concentration values ​​of any observation site under each air quality numerical model according to the weight of each air quality numerical model to obtain the site pollutant concentration forecast value of any observation site. Optionally, the weight of each air quality numerical model may be set according to experience or actual needs, or may be determined by historical forecast data and historical observation data under each air quality numerical model (the higher the accuracy of the historical forecast data under an air quality numerical model (such as the smaller the difference between the historical forecast data under an air quality numerical model and the historical observation data, or the higher the correlation with the historical observation data), the greater the weight of the corresponding air quality numerical model, and the weight proportion of the better numerical model may be highlighted at this time), etc.; the embodiment of the present invention is not limited to this. Optionally, in other embodiments, the corrected site-forecast concentration values ​​for any observation site under various air quality numerical models may be averaged to obtain a site-forecast pollutant concentration value for any observation site, and so on; the present invention is not limited thereto. Based on this, embodiments of the present invention can obtain highly accurate site-aggregate forecast data, effectively improving the accuracy of the site-forecast pollutant concentration value for each observation site, thereby correcting the initial air quality forecast data using the more accurate site-forecast pollutant concentration values.

[0049] Optionally, the number of both initial air quality forecast data and site aggregate forecast data can be one or more, with one initial air quality forecast data corresponding to one site aggregate forecast data. That is, the number of both target areas and target forecast times can be one or more, and this is not limited in the embodiments of the present invention. For example, when there are multiple target forecast times, the target air quality forecast data for the target area at each target forecast time can be determined separately, and so on. For ease of explanation, the following description will take one initial air quality forecast data and one site aggregate forecast data, that is, one target area and one target forecast time, as an example.

[0050] S102: Determine a first regional concentration forecast result for each sub-region in the target area based on the initial air quality forecast data, and determine a second regional concentration forecast result for each sub-region based on the site aggregate forecast data.

[0051] The target area may include at least one sub-area. Optionally, a sub-area may be a city (such as a county or a city), an area divided according to a specified area division method, or the entire target area, etc.; this is not limited in this embodiment of the present invention. Optionally, the specified area division method may be set based on experience or actual needs, which is not limited in this embodiment of the present invention.

[0052] S103 , determining a forecast deviation coefficient for each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region.

[0053] S104: Based on the forecast deviation coefficient of each sub-region, the initial air quality forecast data is corrected to obtain target air quality forecast data.

[0054] In summary, the initial air quality forecast data can be determined by a target statistical downscaling model (i.e., it can be determined by a statistical downscaling method). In this case, an embodiment of the present invention can implement a downscaling result optimization method based on the statistical downscaling forecast result (i.e., the initial air quality forecast data) and the site aggregate forecast data. That is, the site aggregate forecast data of the site type can be used to correct and optimize the grid type initial air quality forecast data, so that the optimized downscaling forecast result (i.e., the target air quality forecast data described below) retains the characteristics of high-precision spatial distribution and has a relatively accurate pollutant concentration forecast level. Furthermore, the core of the dynamic downscaling method (i.e., nesting high-resolution sub-regions within a coarse-resolution simulation region to simulate and refine the coarse-resolution results using numerical modeling techniques) is downscaling based on numerical modeling methods. However, the atmospheric evolution equations represented by the numerical model are highly complex, and the numerical solution process involves a large number of iterative calculations, resulting in a large consumption of computational resources by this method. Based on this, embodiments of the present invention may also obtain initial air quality forecast data through a statistical downscaling method to effectively reduce the consumption of computational resources. However, although the initial air quality forecast data obtained through the statistical downscaling method are gridded results, their accuracy is low. The site ensemble forecast data is a site-type result and cannot express the spatial distribution of pollutants in a more refined and comprehensive manner, but the site ensemble forecast data has a higher accuracy. Therefore, embodiments of the present invention may correct and optimize the gridded initial air quality forecast data obtained through downscaling using the site-type site ensemble forecast data to obtain an accurate and comprehensive gridded downscaling result (i.e., target air quality forecast data). This, while ensuring low computational resource consumption, obtains both accurate and comprehensive target air quality forecast data, effectively improving the pollutant concentration forecast accuracy of the statistical downscaling forecast results.

[0055] Embodiments of the present invention can obtain initial air quality forecast data and site aggregate forecast data. The initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid within the target area. Each target grid represents a high-resolution grid division of the target area. Based on the initial air quality forecast data, a first regional concentration forecast result for each sub-region within the target area can be determined. Based on the site aggregate forecast data, a second regional concentration forecast result for each sub-region can be determined. Based on this, a forecast deviation coefficient for each sub-region can be determined based on the first and second regional concentration forecast results, respectively. Based on the forecast deviation coefficients for each sub-region, the initial air quality forecast data can be corrected to obtain target air quality forecast data. Thus, embodiments of the present invention can determine the forecast deviation coefficients for each sub-region using site aggregate forecast data, etc., thereby correcting the initial air quality forecast data to obtain highly accurate target air quality forecast data. This effectively improves the accuracy of high-resolution air quality forecasts, ensuring that the target air quality forecast data retains the characteristics of high-precision spatial distribution while also providing a relatively accurate pollutant concentration forecast level.

[0056] Based on the above description, the embodiment of the present invention further proposes a more specific air quality forecasting method. Accordingly, the air quality forecasting method can be executed by the electronic device (terminal or server) mentioned above; or, the air quality forecasting method can be executed by the terminal and the server together. For the sake of convenience, the following description will take the electronic device executing the air quality forecasting method as an example; please refer to Figure 2 The air quality forecasting method may include the following steps S201-S205:

[0057] S201, obtaining initial air quality forecast data and site aggregate forecast data, the initial air quality forecast data including initial pollutant concentration forecast values ​​of each target grid in the target area, each target grid being a high-resolution grid division result of the target area.

[0058] S202: Determine a first regional concentration forecast result for each sub-region in the target area based on the initial air quality forecast data, and determine a second regional concentration forecast result for each sub-region based on the site aggregate forecast data.

[0059] Optionally, when determining the first regional concentration forecast results for each sub-region in the target region based on the initial air quality forecast data, the electronic device may determine, for any sub-region in the target region, a site forecast result for each observation site in any sub-region based on the initial air quality forecast data. Optionally, for any observation site in any sub-region, the initial pollutant concentration forecast value of a target grid closest to any observation site may be determined from the initial air quality forecast data, so that the initial pollutant concentration forecast value of the target grid closest to any observation site is used as the site forecast result for any observation site; or, the initial pollutant concentration forecast values ​​of the first Q target grids closest to any observation site may be determined from the initial air quality forecast data, so that the initial pollutant concentration forecast values ​​of the first Q target grids closest to any observation site are weighted and summed, so that the weighted sum result is used as the site forecast result for any observation site, where Q is a positive integer, and the weight of the initial pollutant concentration forecast value of a target grid may be negatively correlated with the distance between the corresponding target grid and any observation site, etc.; this embodiment of the present invention is not limited to this.

[0060] Based on this, the electronic device can use the site prediction results of each of the above-mentioned observation sites (i.e., each observation site in any sub-area) to calculate the first regional concentration forecast result of any sub-area. Optionally, the electronic device can use the average of the site prediction results of each observation site in any sub-area as the first regional concentration forecast result of any sub-area; for example, taking the target pollutant as PM2.5 and any sub-area as a city as an example, assuming that there are 10 observation sites in any sub-area (respectively represented as ST1, ST2, ..., ST10), and the site prediction results of each observation site in any sub-area are respectively represented as PM2.5 SG1KM-ST1 、PM2.5 SG1KM-ST2 ,…,PM2.5 SG1KM-ST10 , then the first regional concentration forecast result PM2.5 of any sub-region SG1KM-CITY =(PM2.5 SG1KM-ST1 +PM2.5 SG1KM-ST2 +…+PM2.5 SG1KM-ST10 ) / 10. Optionally, the electronic device may also determine the weights of the observation stations within any sub-region, and perform a weighted summation of the station prediction results of the observation stations within any sub-region according to the weights of the observation stations within any sub-region to obtain the first regional concentration forecast result for any sub-region, and so on. Optionally, the weights of the observation stations within any sub-region may be set based on experience or time requirements, and this is not limited in this embodiment of the present invention.

[0061] In an embodiment of the present invention, the site set forecast data may include the site pollutant concentration forecast value of each observation site in the target area, that is, it may include the site pollutant concentration forecast value of each observation site at the target forecast time; based on this, when determining the second regional concentration forecast result of each sub-area based on the site set forecast data, for any sub-area in the target area, the electronic device may determine the site pollutant concentration forecast value of each observation site in any sub-area from the site set forecast data; and use the site pollutant concentration forecast value of each observation site to calculate the second regional concentration forecast result of any sub-area. Optionally, the electronic device may use the mean value between the site pollutant concentration forecast values ​​of each observation site in any sub-area as the second regional concentration forecast result of any sub-area, that is, perform mean operation on the site pollutant concentration forecast values ​​of each observation site in any sub-area to obtain the second regional concentration forecast result of any sub-area; for example, taking the target pollutant as PM2.5 as an example, it is assumed that the site pollutant concentration forecast values ​​of each observation site in any sub-area are PM2.5 respectively. OEF-ST1 、PM2.5 OEF-ST2 ,…,PM2.5 OEF-ST10 , then the second area concentration forecast result PM2.5 of any sub-area OEF-CITY =(PM2.5 OEF-ST1 +PM2.5 OEF-ST2 +…+PM2.5 OEF-ST10 ) / 10. Optionally, the electronic device may also perform a weighted summation of the site pollutant concentration forecast values ​​of each observation site within any sub-area according to the weight of each observation site within any sub-area to obtain a second regional concentration forecast result for any sub-area, and so on. OEF may represent Optimal Ensemble Forecast, with the mark representing ensemble forecast; optionally, the weights of the aforementioned air quality numerical models may be determined using the OEF algorithm based on historical forecast data and historical observation data for each air quality numerical model, to highlight the weight proportion of the superior numerical model, and so on.

[0062] S203 , determining a forecast deviation coefficient for each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region.

[0063] In an embodiment of the present invention, for the mth sub-area in the target area, the electronic device may use the ratio between the second area concentration forecast result of the mth sub-area and the first area concentration forecast result of the mth sub-area as the forecast deviation coefficient of the mth sub-area, where m∈[1,M], and M is the number of sub-areas in the target area. For example, taking PM2.5 as an example, assuming that the second area concentration forecast result of the mth sub-area is PM2.5 OEF-CITY , the first area concentration forecast result of the mth sub-area is PM2.5 SG1KM-CITY , then the forecast deviation coefficient B of the mth sub-region is PM2.5-CITY =PM2.5 OEF-CITY / PM2.5 SG1KM-CITY .

[0064] Optionally, in other embodiments, the electronic device may also use the ratio between the first area concentration forecast result of the mth sub-area and the second area concentration forecast result of the mth sub-area as the forecast deviation coefficient of the mth sub-area, and so on; the present invention is not limited to this.

[0065] S204 , for any target grid in the target area, determining the forecast deviation coefficient of the sub-area where the target grid is located from the forecast deviation coefficients of each sub-area.

[0066] S205, using the forecast deviation coefficient of the sub-region where any target grid is located, to correct the initial pollutant concentration forecast value of any target grid to obtain the target pollutant concentration forecast value of any target grid. The target air quality forecast data includes the target pollutant concentration forecast value of each target grid.

[0067] In an embodiment of the present invention, the electronic device may use the multiplication result between the forecast deviation coefficient of the sub-region where any target grid is located and the initial pollutant concentration forecast value of any target grid as the target pollutant concentration forecast value of any target grid, so as to realize the correction of the initial pollutant concentration forecast value of any target grid. For example, assuming that any target grid G A The sub-region is CITY1 (one sub-region is one city), and the forecast deviation coefficient of this sub-region is B PM2.5-CITY1 , then any target grid G A The revised result (i.e. the predicted value of target pollutant concentration) G A-rev =G A ×B PM2.5-CITY1 In this case, the forecast deviation coefficient of the mth sub-region may be: the ratio between the second regional concentration forecast result of the mth sub-region and the first regional concentration forecast result of the mth sub-region.

[0068] Optionally, in other embodiments, when the forecast deviation coefficient of the mth sub-region is the ratio between the first area concentration forecast result of the mth sub-region and the second area concentration forecast result of the mth sub-region, the result of the division operation between the initial pollutant concentration forecast value of any target grid and the forecast deviation coefficient of the sub-region where any target grid is located can be used as the target pollutant concentration forecast value of any target grid, that is, at this time, the target pollutant concentration forecast value of any target grid can be the result of dividing the initial pollutant concentration forecast value of any target grid by the forecast deviation coefficient of the sub-region where any target grid is located, and so on; the present invention is not limited to this.

[0069] Optionally, the target air quality forecast data may include the target pollutant concentration forecast value of each target grid at the target forecast time, that is, the target pollutant concentration forecast value of the above-mentioned target grid may refer to the target pollutant concentration forecast value of the corresponding target grid at the target forecast time.

[0070] Based on this, the embodiment of the present invention can determine the inclusion relationship between each target grid and the sub-area according to the grid position, and then perform deviation correction on each target grid respectively, thereby realizing the correction of the initial air quality forecast data to obtain the target pollutant concentration forecast value of each target grid, such as Figure 3 Correspondingly, when a sub-region is a city, the embodiment of the present invention can ultimately obtain a gridded high-precision downscaling forecast result that maintains both reasonable spatial distribution and high overall city forecast accuracy.

[0071] Embodiments of the present invention can obtain initial air quality forecast data and site aggregate forecast data. The initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid within a target area. Each target grid is a high-resolution grid division of the target area. A first regional concentration forecast result for each sub-region within the target area can then be determined based on the initial air quality forecast data, and a second regional concentration forecast result for each sub-region can be determined based on the site aggregate forecast data. Based on this, a forecast deviation coefficient for each sub-region can be determined based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region. Furthermore, for any target grid within the target area, a forecast deviation coefficient for the sub-region within which the target grid resides can be determined from the forecast deviation coefficients for each sub-region. The forecast deviation coefficient for the sub-region within which the target grid resides can then be used to correct the initial pollutant concentration forecast value for the target grid, resulting in a target pollutant concentration forecast value for the target grid. The target air quality forecast data includes the target pollutant concentration forecast value for each target grid. It can be seen that the embodiments of the present invention can effectively improve the accuracy of gridded target air quality forecast data, and the target air quality forecast data with higher spatial resolution (i.e., finer spatial scale) can enable atmospheric pollution prevention and control personnel to have a more detailed understanding of the distribution of pollutants, thereby supporting more precise prevention and control measures in highly polluted areas.

[0072] Based on the description of the relevant embodiments of the above-mentioned air quality forecasting method, the embodiment of the present invention further proposes an air quality forecasting device, which can be a computer program (including program code) running in an electronic device; Figure 4 As shown, the air quality forecasting device may include an acquisition unit 401 and a processing unit 402. The air quality forecasting device may perform Figure 1 or Figure 2 The air quality forecasting method shown, that is, the air quality forecasting device can run the above units:

[0073] An acquisition unit 401 is configured to acquire initial air quality forecast data and site aggregate forecast data, wherein the initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid in the target area, wherein each target grid is a high-resolution grid division result of the target area;

[0074] The processing unit 402 is configured to determine a first regional concentration forecast result for each sub-region in the target area based on the initial air quality forecast data, and determine a second regional concentration forecast result for each sub-region based on the site aggregate forecast data;

[0075] The processing unit 402 is further configured to determine a forecast deviation coefficient for each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region;

[0076] The processing unit 402 is further configured to correct the initial air quality forecast data based on the forecast deviation coefficients of the respective sub-regions to obtain target air quality forecast data.

[0077] In one embodiment, when the processing unit 402 determines the forecast deviation coefficient of each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result of each sub-region, it can be specifically configured to:

[0078] For the mth sub-region in the target area, the ratio between the second regional concentration forecast result of the mth sub-region and the first regional concentration forecast result of the mth sub-region is used as the forecast deviation coefficient of the mth sub-region, m∈[1,M], M is the number of sub-regions in the target area.

[0079] In another embodiment, when determining the first regional concentration forecast result of each sub-region in the target region based on the initial air quality forecast data, the processing unit 402 may be specifically configured to:

[0080] For any sub-area in the target area, determining a site prediction result for each observation site in the sub-area based on the initial air quality forecast data;

[0081] The site prediction results of each observation site are used to calculate the first regional concentration forecast result of any sub-region.

[0082] In another embodiment, the site aggregate forecast data includes a site pollutant concentration forecast value for each observation site in the target area; when determining the second area concentration forecast result for each sub-area based on the site aggregate forecast data, the processing unit 402 may be specifically configured to:

[0083] For any sub-area in the target area, determining the site pollutant concentration forecast value of each observation site in the sub-area from the site set forecast data;

[0084] The site pollutant concentration forecast values ​​of each observation site are used to calculate the second area concentration forecast result of any sub-area.

[0085] In another embodiment, when the processing unit 402 corrects the initial air quality forecast data based on the forecast deviation coefficient of each sub-region to obtain the target air quality forecast data, it can be specifically used to:

[0086] For any target grid in the target area, determining the forecast deviation coefficient of the sub-area where the target grid is located from the forecast deviation coefficients of the sub-areas;

[0087] The initial pollutant concentration forecast value of any target grid is corrected using the forecast deviation coefficient of the sub-area where any target grid is located to obtain the target pollutant concentration forecast value of any target grid. The target air quality forecast data includes the target pollutant concentration forecast values ​​of each target grid.

[0088] In another embodiment, when acquiring the initial air quality forecast data, the acquiring unit 401 may be specifically configured to:

[0089] Obtaining low-resolution grid concentration prediction data and downscaling indication data, wherein the low-resolution grid concentration prediction data includes concentration prediction results of each initial grid in the target area, the resolution corresponding to each initial grid is lower than the resolution corresponding to each target grid, and the downscaling indication data includes grid indication data of each target grid;

[0090] The target statistical downscaling model is called to perform downscaling prediction based on the low-resolution grid concentration prediction data and the downscaling indicator data to obtain initial air quality forecast data.

[0091] In another embodiment, when acquiring the site aggregate forecast data, the acquiring unit 401 may be specifically configured to:

[0092] Acquire the data to be forecasted, and respectively call each air quality numerical model in the air quality numerical model set, and determine the air quality forecast data under each air quality numerical model based on the data to be forecasted;

[0093] Determining, from the air quality forecast data under each of the air quality numerical models, the site forecast data to be corrected under each of the air quality numerical models;

[0094] Determining a set of deviation correction parameters under each of the air quality numerical models, and correcting the to-be-corrected site forecast data under each of the air quality numerical models based on the set of deviation correction parameters under each of the air quality numerical models to obtain corrected site forecast data under each of the air quality numerical models;

[0095] Based on the revised site forecast data under each of the air quality numerical models, the site ensemble forecast data is determined.

[0096] According to one embodiment of the present invention, Figure 4Each unit in the air quality forecasting device shown can be individually or completely combined into one or several other units to form a whole, or one (or more) of the units can be further divided into multiple functionally smaller units to form a whole, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present invention. The above-mentioned units are divided based on logical functions. In actual applications, the functions of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present invention, any air quality forecasting device can also include other units. In actual applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0097] According to another embodiment of the present invention, the program can be executed by running a program on a general electronic device such as a computer including a central processing unit (CPU), a random access memory (RAM), a read-only memory (ROM), and other processing elements and storage elements. Figure 1 or Figure 2 The computer program (including program code) of each step involved in the corresponding method shown in is constructed as follows Figure 4 The air quality forecasting device shown in and the air quality forecasting method of the embodiment of the present invention are implemented. The computer program can be recorded on a computer storage medium, for example, and loaded into the above-mentioned electronic device through the computer storage medium and run therein.

[0098] Embodiments of the present invention can obtain initial air quality forecast data and site aggregate forecast data. The initial air quality forecast data includes initial pollutant concentration forecast values ​​for each target grid within the target area. Each target grid represents a high-resolution grid division of the target area. Based on the initial air quality forecast data, a first regional concentration forecast result for each sub-region within the target area can be determined. Based on the site aggregate forecast data, a second regional concentration forecast result for each sub-region can be determined. Based on this, a forecast deviation coefficient for each sub-region can be determined based on the first and second regional concentration forecast results, respectively. Based on the forecast deviation coefficients for each sub-region, the initial air quality forecast data can be corrected to obtain target air quality forecast data. Thus, embodiments of the present invention can determine the forecast deviation coefficients for each sub-region using site aggregate forecast data, etc., thereby correcting the initial air quality forecast data to obtain highly accurate target air quality forecast data. This effectively improves the accuracy of high-resolution air quality forecasts, ensuring that the target air quality forecast data retains the characteristics of high-precision spatial distribution while also providing a relatively accurate pollutant concentration forecast level.

[0099] Based on the description of the method embodiments and the device embodiments, the exemplary embodiments of the present application further provide an electronic device, comprising: at least one processor; and a memory connected with the at least one processor in communication. The memory stores a computer program capable of being executed by the at least one processor, and the computer program, when executed by the at least one processor, is configured to cause the electronic device to perform the method according to the embodiments of the present application.

[0100] The exemplary embodiments of the present application further provide a non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is configured to cause the computer to perform the method according to the embodiments of the present application.

[0101] The exemplary embodiments of the present application further provide a computer program product comprising a computer program, wherein the computer program, when executed by a processor of a computer, is configured to cause the computer to perform the method according to the embodiments of the present application.

[0102] Reference Figure 5 will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. The electronic device is intended to represent various forms of digital electronic computer devices such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices such as personal digital processors, cellular telephones, smart phones, wearable devices, and other like computing devices. The components shown here, their connections, and their functions, as well as their relationships to one another, are merely exemplary and are not intended to limit the implementations of the present application described and / or claimed in this document to the embodiments herein.

[0103] As Figure 5 shown, the electronic device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0104] Multiple components within electronic device 500 are connected to I / O interface 505, including an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. Input unit 506 can be any type of device capable of inputting information into electronic device 500. Input unit 506 can receive input numeric or character information and generate key input signals related to user settings and / or function control of the electronic device. Output unit 507 can be any type of device capable of presenting information and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. Storage unit 508 may include, but is not limited to, a magnetic disk or an optical disk. Communication unit 509 allows electronic device 500 to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver and / or chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0105] The computing unit 501 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the air quality forecasting method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 500 via the ROM 502 and / or the communication unit 509. In some embodiments, the computing unit 501 can be configured to perform the air quality forecasting method by any other suitable means (e.g., via firmware).

[0106] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0107] In the context of the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0108] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0109] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0110] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0111] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0112] Furthermore, it should be understood that the above disclosure is only a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. An air quality forecasting method, characterized in that: include: Obtaining initial air quality forecast data and site aggregate forecast data, wherein the initial air quality forecast data includes an initial pollutant concentration forecast value for each target grid in the target area, wherein each target grid is a high-resolution grid division result of the target area, and the site aggregate forecast data includes a site pollutant concentration forecast value for each observation site in the target area; For any sub-area in the target area, determining, based on the initial air quality forecast data, site prediction results of each observation site in the any sub-area, and using the site prediction results of each observation site to calculate a first regional concentration forecast result for the any sub-area, and determining, based on the site aggregate forecast data, a second regional concentration forecast result for each sub-area; Determining a forecast deviation coefficient for each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region; For any target grid in the target area, the forecast deviation coefficient of the sub-area where the any target grid is located is determined from the forecast deviation coefficients of the various sub-areas, and the forecast deviation coefficient of the sub-area where the any target grid is located is used to correct the initial pollutant concentration forecast value of the any target grid to obtain the target pollutant concentration forecast value of the any target grid.

2. The method according to claim 1, characterized in that The determining of the forecast deviation coefficient of each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result of each sub-region includes: For the mth sub-region in the target area, the ratio between the second regional concentration forecast result of the mth sub-region and the first regional concentration forecast result of the mth sub-region is used as the forecast deviation coefficient of the mth sub-region, m∈[1,M], M is the number of sub-regions in the target area.

3. The method according to claim 1 or 2, characterized in that Determining the second regional concentration forecast result for each sub-region based on the site set forecast data includes: For any sub-area in the target area, determining the site pollutant concentration forecast value of each observation site in the sub-area from the site set forecast data; The site pollutant concentration forecast values ​​of each observation site are used to calculate the second area concentration forecast result of any sub-area.

4. The method according to claim 1 or 2, characterized in that The obtaining of initial air quality forecast data includes: Obtaining low-resolution grid concentration prediction data and downscaling indication data, wherein the low-resolution grid concentration prediction data includes concentration prediction results of each initial grid in the target area, the resolution corresponding to each initial grid is lower than the resolution corresponding to each target grid, and the downscaling indication data includes grid indication data of each target grid; The target statistical downscaling model is called to perform downscaling prediction based on the low-resolution grid concentration prediction data and the downscaling indicator data to obtain initial air quality forecast data.

5. The method according to claim 1 or 2, characterized in that The obtaining of site aggregate forecast data includes: Acquire the data to be forecasted, and respectively call each air quality numerical model in the air quality numerical model set, and determine the air quality forecast data under each air quality numerical model based on the data to be forecasted; Determining, from the air quality forecast data under each of the air quality numerical models, the site forecast data to be corrected under each of the air quality numerical models; Determining a set of deviation correction parameters under each of the air quality numerical models, and correcting the to-be-corrected site forecast data under each of the air quality numerical models based on the set of deviation correction parameters under each of the air quality numerical models to obtain corrected site forecast data under each of the air quality numerical models; Based on the revised site forecast data under each of the air quality numerical models, the site ensemble forecast data is determined.

6. An air quality forecasting device, characterized in that: The device comprises: an acquisition unit, configured to acquire initial air quality forecast data and site aggregate forecast data, wherein the initial air quality forecast data includes an initial pollutant concentration forecast value for each target grid in the target area, wherein each target grid is a high-resolution grid division result of the target area, and the site aggregate forecast data includes a site pollutant concentration forecast value for each observation site in the target area; a processing unit configured to determine, for any sub-region in the target region, a site prediction result of each observation site in the sub-region based on the initial air quality forecast data, calculate a first regional concentration forecast result for the sub-region using the site prediction results of each observation site, and determine a second regional concentration forecast result for each sub-region based on the site aggregate forecast data; The processing unit is further configured to determine a forecast deviation coefficient for each sub-region based on the first regional concentration forecast result and the second regional concentration forecast result for each sub-region; The processing unit is further used to determine, for any target grid in the target area, the forecast deviation coefficient of the sub-area where the any target grid is located from the forecast deviation coefficients of the respective sub-areas, and to use the forecast deviation coefficient of the sub-area where the any target grid is located to correct the initial pollutant concentration forecast value of the any target grid to obtain the target pollutant concentration forecast value of the any target grid.

7. An electronic device, characterized in that: include: processor; as well as Memory for storing programs, The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 5.

Images