Method, device and electronic equipment for evaluating spatial distribution of air pollution simulation

Abstract

The present invention provides an atmospheric pollution simulation spatial distribution assessment method, device and electronic device, the method comprising: determining M target forecast pollution areas and N target observation pollution areas from the target area; determining the assessment index data of each target forecast pollution area respectively, and determining the assessment index data of each target observation pollution area respectively; determining the target similarity index weight group of the target pollution object, and based on the assessment index data of each target forecast pollution area, the assessment index data of each target observation pollution area and the target similarity index weight group, determining the assessment matching degree of each target forecast pollution area respectively; based on the assessment matching degree of each target forecast pollution area, determining the target atmospheric pollution simulation assessment result. The embodiment of the present invention can improve the accuracy of atmospheric pollution simulation spatial distribution assessment.

Description

Technical Field

[0001] The present invention relates to the field of air quality technology, and in particular to an atmospheric pollution simulation spatial distribution assessment method, device and electronic equipment. Background Art

[0002] The evaluation and verification of numerical forecasts is an important part of the application of numerical models; however, related technologies usually use objective statistical tests with observation data as the true value to achieve air pollution simulation evaluation, such as absolute measurement methods based on root mean square error, that is, usually through point-to-point verification (such as point-to-point comparison between station data and forecast data) to achieve air pollution simulation evaluation, which makes it difficult to make a comprehensive evaluation of the forecast performance of numerical models in the spatial distribution characteristics of small and medium-scale pollution events, that is, it is impossible to give quantitative test results for spatial indicators such as the location, range and intensity of pollution belts that are more concerned in forecasts, resulting in low accuracy of air pollution simulation evaluation results (i.e., air pollution simulation spatial distribution evaluation results). Based on this, there is currently no good solution for how to improve the accuracy of air pollution simulation spatial distribution evaluation. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method, device and electronic device for evaluating the spatial distribution of atmospheric pollution simulation to solve the problem of low accuracy of spatial distribution evaluation of atmospheric pollution simulation caused by related technologies; that is, an embodiment of the present invention can fully consider the influence of at least one evaluation space indicator on the atmospheric pollution simulation evaluation through the evaluation index data of each target predicted pollution area and the evaluation index data of each target observed pollution area, and can realize a comprehensive evaluation of the forecasting performance of the spatial distribution characteristics of the target pollution object, thereby effectively improving the accuracy of the spatial distribution evaluation of atmospheric pollution simulation.

[0004] According to one aspect of an embodiment of the present invention, a method for evaluating the spatial distribution of air pollution simulation is provided, the method comprising:

[0005] Acquiring target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area;

[0006] Based on the target forecast data, M target forecast contaminated areas are determined from the target area; and based on the target observation data, N target observation contaminated areas are determined from the target area, where M and N are both positive integers;

[0007] Determine evaluation index data of each target forecast pollution area in the M target forecast pollution areas respectively, and determine evaluation index data of each target observation pollution area in the N target observation pollution areas respectively, one evaluation index data includes evaluation information of each evaluation space index in the corresponding pollution area in at least one evaluation space index;

[0008] Determine a target similarity index weight group of the target pollution object, and determine the evaluation matching degree of each target forecast pollution area based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index;

[0009] Based on the evaluation matching degree of each target predicted pollution area, a target atmospheric pollution simulation evaluation result is determined, and the target atmospheric pollution simulation evaluation result supports indicating the simulation effect of the target numerical model on the target pollution object.

[0010] According to another aspect of an embodiment of the present invention, there is provided an atmospheric pollution simulation spatial distribution assessment device, the device comprising:

[0011] an acquisition unit, configured to acquire target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area;

[0012] A processing unit, configured to determine M target forecast contaminated areas from the target area based on the target forecast data; and to determine N target observed contaminated areas from the target area based on the target observation data, where M and N are both positive integers;

[0013] The processing unit is further used to respectively determine the evaluation index data of each target forecast pollution area in the M target forecast pollution areas, and respectively determine the evaluation index data of each target observation pollution area in the N target observation pollution areas, wherein one evaluation index data includes evaluation information of each evaluation space index in the corresponding pollution area in at least one evaluation space index;

[0014] The processing unit is further used to determine a target similarity index weight group of the target pollution object, and determine the evaluation matching degree of each target forecast pollution area based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index;

[0015] The processing unit is further used to determine a target atmospheric pollution simulation evaluation result based on the evaluation matching degree of each target predicted pollution area, and the target atmospheric pollution simulation evaluation result supports indicating the simulation effect of the target numerical model on the target pollution object.

[0016] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising a processor and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, enable the processor to perform the above-mentioned method.

[0017] According to another aspect of an embodiment of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the above-mentioned method.

[0018] According to an embodiment of the present invention, after acquiring the target forecast data and the target observation data, based on the target forecast data, M target forecast pollution areas can be determined from the target area; and based on the target observation data, N target observation pollution areas can be determined from the target area, wherein the target forecast data includes forecast information of the target pollution object in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollution object in each grid area, and both M and N are positive integers. Furthermore, the evaluation index data of each target forecast pollution area among the M target forecast pollution areas can be determined respectively, and the evaluation index data of each target observation pollution area among the N target observation pollution areas can be determined respectively, and one evaluation index data includes the evaluation information of each evaluation space index in at least one evaluation space index under the corresponding pollution area; based on this, the target similarity index weight group of the target pollution object can be determined, and based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observation pollution area and the target similarity index weight group, the evaluation matching degree of each target forecast pollution area can be determined respectively; the target similarity index weight group includes the target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index; then accordingly, the target atmospheric pollution simulation evaluation result can be determined based on the evaluation matching degree of each target forecast pollution area, and the target atmospheric pollution simulation evaluation result supports the simulation effect of the target numerical model for indicating the target pollution object. It can be seen that the embodiments of the present invention can fully consider the impact of at least one evaluation space indicator on the atmospheric pollution simulation assessment through the evaluation index data of each target predicted pollution area and the evaluation index data of each target observed pollution area, and can realize a comprehensive assessment of the forecasting performance of the spatial distribution characteristics of the target pollution object, thereby effectively improving the accuracy of the spatial distribution assessment of atmospheric pollution simulation; in addition, the embodiments of the present invention can further improve the accuracy of the spatial distribution assessment of atmospheric pollution simulation through a target similarity indicator weight group adapted to the target pollution object. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Further details, features and advantages of the invention are disclosed in the following description of exemplary embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 A schematic flow chart of a method for evaluating the spatial distribution of air pollution simulation according to an exemplary embodiment of the present invention is shown;

[0021] Figure 2 A schematic flow chart of another method for evaluating the spatial distribution of air pollution simulation according to an exemplary embodiment of the present invention is shown;

[0022] Figure 3A schematic block diagram of an atmospheric pollution simulation spatial distribution evaluation device according to an exemplary embodiment of the present invention is shown;

[0023] Figure 4 A block diagram of an exemplary electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] 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 being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments of the present invention are only for exemplary purposes and are not intended to limit the scope of protection of the present invention.

[0025] 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.

[0026] 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". 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.

[0027] It should be noted that the modifications of "one" and "plurality" mentioned in the present invention are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0028] 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.

[0029] It should be noted that the execution subject of the air pollution simulation spatial distribution assessment method provided in the embodiment of the present invention may be one or more electronic devices, and the present invention does not limit this; wherein, the electronic device may be a terminal (i.e., a client) or a server, then when the execution subject includes multiple electronic devices, and the multiple electronic devices include at least one terminal and at least one server, the air pollution simulation spatial distribution assessment method provided in the embodiment of the present invention may be jointly executed by the terminal and the server. Accordingly, the terminal mentioned here may include but is not limited to: smart phones, tablet computers, laptop computers, desktop computers, etc.; the server mentioned here may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing (cloud computing), cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms, etc.

[0030] Based on the above description, an embodiment of the present invention proposes a method for evaluating the spatial distribution of air pollution simulation, which can be executed by the electronic device (terminal or server) mentioned above; or, the method for evaluating the spatial distribution of air pollution simulation can be executed by the terminal and the server together. For the sake of convenience, the following description will be given by taking the electronic device executing the method for evaluating the spatial distribution of air pollution simulation as an example; Figure 1 As shown, the air pollution simulation spatial distribution assessment method may include the following steps S101-S105:

[0031] S101, obtaining target forecast data and target observation data, wherein the target forecast data includes forecast information of target pollutants in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of target pollutants in each grid area.

[0032] Optionally, the target pollution object can be any pollutant (such as PM 10 (inhalable particulate matter), PM 2.5(fine particulate matter), CO (carbon monoxide) or O3 (ozone), etc.), or AQI (Air Quality Index), etc., which is not limited in the embodiment of the present invention. Optionally, the target area can be any area, which is not limited in the embodiment of the present invention; illustratively, the target area can be nationwide, or it can be the area where a province is located, and so on. Optionally, the target forecast data and the target observation data can be data for the target area within a target time range, and the target time range can be any time range, that is, the target forecast data and the target observation data can be data for the target area within the same time range; that is, the target forecast data can be forecast data for the target area within the target time range through a target numerical mode, and the target observation data can be monitoring data for the target area within the target time range, and so on; this is not limited in the embodiment of the present invention. Optionally, the target numerical mode can be any numerical mode, that is, it can be any air quality numerical mode, which is not limited in the embodiment of the present invention.

[0033] Optionally, the target area may include multiple grid areas, and each grid area in the target area may be each grid area in the multiple grid areas; optionally, the resolution of the target area (i.e., the grid area division method) may be set according to experience or according to actual needs, and the embodiments of the present invention are not limited to this.

[0034] In the embodiment of the present invention, the target forecast data may be obtained in the following ways, but not limited to:

[0035] The first acquisition method: the electronic device's own storage space may store forecast data for the target area within multiple time ranges. In this case, the electronic device may select the forecast data for the target area within the target time range from the forecast data for the target area within multiple time ranges to use the forecast data for the target area within the target time range as the target forecast data. The multiple time ranges may include the target time range.

[0036] The second acquisition method: the electronic device can obtain a target forecast data download link, and download the target forecast data based on the target forecast data download link to achieve acquisition of the target forecast data, and so on.

[0037] Accordingly, the target observation data may be obtained in the following ways, including but not limited to:

[0038] The first acquisition method: the observation data of the target area within multiple time ranges can be stored in the electronic device's own storage space. In this case, the electronic device can select the observation data of the target area within the target time range from the observation data of the target area within multiple time ranges, and use the observation data of the target area within the target time range as the target observation data.

[0039] The second acquisition method: the electronic device can obtain the target observation data download link, and download the target observation data based on the target observation data download link to achieve the acquisition of the target observation data. Optionally, the electronic device can also obtain the data integration download link, and use the forecast data in the data downloaded based on the data integration download link as the target forecast data, and use the observation data in the data downloaded based on the data integration download link as the target observation data.

[0040] The third acquisition method: the electronic device can obtain the observation site data of the target area within the target time range, and the observation site data includes the observation values ​​of the target pollutant object at each of the multiple observation sites included in the target area; based on this, the target observation data can be determined based on the observation site data, that is, the observation site data can be interpolated into spatial data with the same resolution as the target forecast data (also called the target forecast field) through the spatial interpolation method, so as to obtain the target observation data, and so on.

[0041] Exemplarily, for any grid area in the target area, the electronic device can determine the first W observation sites that are closest to any grid area from multiple observation sites, and perform weighted summation on the observation values ​​of the target polluted object at each monitoring site in the first W observation sites to obtain the observation information of the target polluted object in any grid area, so as to obtain the target observation data, where W is a positive integer; optionally, the weight of each observation site in the first W observation sites can be the same (such as summation operation or mean operation, etc.), or can be the inverse of the distance between any grid area, etc., and the embodiment of the present invention is not limited to this.

[0042] S102, based on the target forecast data, determining M target forecast contaminated areas from the target area; and based on the target observation data, determining N target observation contaminated areas from the target area, where M and N are both positive integers.

[0043] In an embodiment of the present invention, when M target forecast pollution areas are determined from the target area based on the target forecast data, the electronic device may determine at least one forecast pollution grid area whose forecast information is greater than or equal to a preset target pollution object threshold from the target area based on the target forecast data, and determine the M target forecast pollution areas based on at least one forecast pollution grid area. Optionally, the preset target pollution object threshold may be a pollution object threshold of the target pollution object; optionally, the target pollution object threshold may be set according to experience or according to actual needs, which is not limited in the embodiment of the present invention; illustratively, when the target pollution object is ozone, the target pollution object threshold may be 215 μg / m 3 (micrograms per cubic meter).

[0044] In a specific implementation, the mask field P can be determined based on the preset target polluted object threshold and the target forecast data, so as to mark the grid area where the forecast information is greater than or equal to the preset target polluted object threshold as 1, and mark the grid area below the preset target polluted object threshold as 0; illustratively, the mask field P can be shown as formula 1.1:

[0045]

[0046] Wherein, (x, y) represents the grid area of ​​the xth row and the yth column, P(x, y) may represent the mask value (i.e., mark) of the grid area of ​​the xth row and the yth column, f(x, y) may represent the forecast information of the target polluted object in the grid area of ​​the xth row and the yth column, and T may represent the preset target polluted object threshold.

[0047] Based on this, the forecast information of the target polluted object in any grid area can be updated based on the mask value of any grid area (i.e., the grid area of ​​the xth row and the yth column) and the forecast information of the target polluted object in any grid area, and at least one forecast polluted grid area can be determined based on the updated target forecast data. Exemplarily, the forecast information of the target polluted object in any grid area can be updated using formula 1.2:

[0048] F(x,y)=P(x,y)×f(x,y) Formula 1.2

[0049] Among them, F(x,y) can represent the update result of the forecast information of the target polluted object in the grid area of ​​the xth row and the yth column, so that the forecast information in the grid area of ​​the target area whose forecast information is less than the preset target polluted object threshold can be set to 0, and the forecast information in the grid area of ​​the target area whose forecast information is greater than or equal to the preset target polluted object threshold is retained, so that the polluted areas reaching the preset target polluted object threshold can be distinguished from each other. In this case, based on the updated target forecast data, the grid area in the target area whose forecast information is not zero can be used as the grid area in at least one forecast polluted grid area to determine at least one forecast polluted grid area; and the target area can be divided into one or more polluted grid areas through the grid area whose forecast information is zero, so that the polluted areas are distinguished from each other.

[0050] In another specific implementation, the electronic device may also directly use the grid area in the target area whose forecast information is greater than or equal to a preset target pollution object threshold as the grid area in at least one predicted pollution grid area based on the target forecast data, so as to determine at least one predicted pollution grid area, and so on.

[0051] Optionally, when determining M target forecast pollution areas in at least one forecast pollution grid area, the electronic device may determine at least one initial pollution area from the at least one forecast pollution grid area, and an initial pollution area may include one or more adjacent (i.e., connected) grid areas in the at least one forecast pollution grid area, that is, any two adjacent grid areas in the at least one forecast pollution grid area may be divided into the same initial pollution area, then correspondingly, each initial pollution area in the at least one initial pollution area may be used as a target forecast pollution area to achieve the determination of M target forecast pollution areas; or, at least one initial pollution area may be subjected to regional fusion processing to fuse each initial pollution area group that meets the fusion condition in the at least one initial pollution area into a target forecast pollution area, and each initial pollution area that does not meet the fusion condition in the at least one initial pollution area is used as a target forecast pollution area, multiple initial pollution areas in an initial pollution area group meet the fusion condition, and multiple initial pollution areas in an initial pollution area group may be fused into a target forecast pollution area to achieve the determination of M target forecast pollution areas, and so on.

[0052] Optionally, multiple initial contaminated areas whose distance is less than a preset area distance threshold can be used as an initial contaminated area group that meets the fusion condition, and the distance between an initial contaminated area in an initial contaminated area group and another initial contaminated area in the initial contaminated area group is less than the preset area distance threshold; or, multiple initial contaminated areas whose difference between average forecast information is less than a preset information difference threshold can be used as an initial contaminated area group that meets the fusion condition, and the average forecast information of an initial contaminated area can be the average of the forecast information in each grid area of ​​the corresponding initial contaminated area, and the difference between the average forecast information of an initial contaminated area in an initial contaminated area group and the average forecast information of another initial contaminated area in the initial contaminated area group is less than the preset information difference threshold, and so on; the embodiment of the present invention is not limited to this. Optionally, the preset area distance threshold and the preset information difference threshold can be set according to experience or according to actual needs, and the embodiment of the present invention is not limited to this.

[0053] Then, accordingly, when N target observation pollution areas are determined from the target area based on the target observation data, the electronic device can determine at least one observation pollution grid area whose observation information is greater than or equal to the preset target pollution object threshold from the target area based on the target observation data, and determine the N target observation pollution areas based on the at least one observation pollution grid area. It should be noted that the method for determining the N target observation pollution areas is the same as the method for determining the M target forecast pollution areas, and the embodiments of the present invention will not be repeated here.

[0054] S103, respectively determine the evaluation index data of each target forecast pollution area in the M target forecast pollution areas, and respectively determine the evaluation index data of each target observation pollution area in the N target observation pollution areas, one evaluation index data includes the evaluation information of each evaluation space indicator in at least one evaluation space indicator under the corresponding pollution area.

[0055] Optionally, at least one evaluation space indicator may include, but is not limited to: area, centroid, axis angle, and intensity percentile, etc.; the embodiment of the present invention is not limited to this. It should be noted that the at least one evaluation space indicator can be determined based on the characteristics of the spatial distribution of atmospheric pollutants, such as slow movement, obvious flaky structure, and large range; based on this, the key characteristics of the atmospheric pollution process and the overall spatial inspection effect can be obtained by calculating the similarity index of these spatial attributes of the simulated forecast (i.e., target forecast data) and the target observation data (i.e., evaluation space indicators).

[0056] Among them, the area can be the range of the pollution area, such as expressed by the number of grid areas in the pollution area; the centroid can be the grid point where the geometric center of the pollution area is located (that is, it can be the center point of the grid area where the geometric center of the pollution area is located); the axis angle can be the acute angle formed by the symmetry axis of the pollution area and the east-west horizontal axis, which can be used to evaluate the spatial direction of the entire pollution area; the intensity percentile can be the values ​​of the target pollution objects in the pollution area (such as pollutant concentration) arranged from small to large, and the intensity of at least one specified percentile of the arrangement result is taken respectively (the intensity at a specified percentile is the value of the target pollution object at the corresponding specified percentile in the arrangement result), such as at least one specified percentile may include but is not limited to the 50th percentile (that is, the 50th position), the 75th percentile (that is, the 75th position) and the 90th percentile (that is, the 90th position), etc., and the embodiment of the present invention is not limited to this.

[0057] Based on this, when at least one evaluation space indicator includes area, centroid, axis angle and intensity percentile, the evaluation indicator data of any polluted area (such as any target forecast polluted area or any target observed polluted area, etc.) may include area evaluation information of any polluted area (which may include the number of grid areas in any polluted area and / or the grid area identification of each grid area in any polluted area), centroid evaluation information (which may be the centroid coordinates of any polluted area, such as longitude and latitude centroid coordinates, etc.), axis angle evaluation information (which may be the axis angle of any polluted area) and intensity percentile evaluation information (which may include the intensity of any polluted area at each specified percentile in at least one specified percentile). In other words, for any of the M target predicted pollution areas and the N target observed pollution areas, the number of grid areas in any pollution area and / or the grid area identifier of each grid area in any pollution area can be added to the area evaluation information of the evaluation space indicator "area" under any pollution area to obtain the area evaluation information of the evaluation space indicator "area" under any pollution area; and / or, the centroid coordinates of any pollution area can be determined, and the centroid coordinates of any pollution area can be used as the centroid evaluation information of the evaluation space indicator "centroid" under any pollution area; and / or, the axis angle of any pollution area can be used as the axis angle evaluation information of the evaluation space indicator "axis angle" under any pollution area; and / or, the target The information (such as forecast information or observation information) of the target polluted object in each grid area of ​​any polluted area is sorted to obtain the sorting result of any polluted area, so as to determine the intensity of each specified percentile in at least one specified percentile from the sorting result of any polluted area (that is, the value of the sorting result of any polluted area at each specified percentile), so as to add the intensity of each specified percentile to the intensity percentile evaluation information of any polluted area, so as to obtain the intensity percentile evaluation information of the evaluation space indicator "intensity percentile" under any polluted area, and so on; based on this, it is possible to determine the evaluation index data of any target forecast polluted area, and to determine the evaluation index data of any target observed polluted area. Optionally, at least one specified percentile can be set according to experience or according to actual needs, which is not limited in the embodiment of the present invention. Optionally, a grid area identifier can be used to indicate a grid area; optionally, a grid area identifier can be the code of the corresponding grid area, or the coordinates of the corresponding grid area (such as the xth row and the yth column), etc., which is not limited in the embodiment of the present invention.

[0058] In summary, for any target forecast pollution area among the M target forecast pollution areas, the evaluation index data of any target forecast pollution area can be determined based on the forecast information of the target polluted object in each grid area of ​​any target forecast pollution area and the grid area information of any target forecast pollution area; and for any target observed pollution area among the N target observation pollution areas, the evaluation index data of any target observed pollution area can be determined based on the observation information of the target polluted object in each grid area of ​​any target observation pollution area and the grid area information of any target observation pollution area. Optionally, the grid area information of a pollution area may include but is not limited to at least one of the following: the number of grid areas in the corresponding pollution area, the grid area identification of each grid area in the corresponding pollution area, and the location information of each grid area in the corresponding pollution area (such as the center point coordinates, etc.), etc.; the embodiment of the present invention is not limited to this.

[0059] It can be seen that the embodiment of the present invention can realize the quantitative test results of each evaluation space indicator through the evaluation information of each evaluation space indicator in any pollution area, so as to realize the quantitative test results of each similarity indicator later.

[0060] S104, determining a target similarity index weight group of the target pollution object, and determining the evaluation matching degree of each target forecast pollution area based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index.

[0061] Optionally, at least one similarity index may include, but is not limited to: axis angle difference (corresponding to axis angle), intersection ratio (corresponding to area), area ratio (corresponding to area), centroid distance (corresponding to centroid) and intensity percentile ratio (corresponding to intensity percentile), etc., which is not limited in the embodiment of the present invention. Optionally, the similarity index value of a similarity index may be calculated from the evaluation information of the corresponding evaluation space index.

[0062] Among them, the axial angle difference can be used to indicate the axial angle difference between two polluted areas. It is a similarity index indicating the direction of the target polluted object and is closely related to the shape of the spatial distribution of the polluted object. The intersection ratio can be used to indicate the ratio of the intersection of the areas of two polluted areas, which can quantify the hit rate of the forecast field (i.e., target forecast data) for the pollution process. The area ratio can be used to indicate the ratio of the areas of the two polluted areas, which is closely related to the forecast effect of the numerical model on the impact range of a pollution event. The centroid distance can be used to determine the location of the polluted object. The intensity percentile ratio can be used to indicate the ratio of the intensity percentiles of the same intensity percentiles of the two polluted areas. The intensity percentile ratio can be used to evaluate the quality of the simulated values ​​of the pollutant concentration values ​​of the numerical model, and whether the simulated intensity is equivalent to the actual measurement at different percentiles, so as to understand the effect of the simulated concentration, and so on.

[0063] Based on this, when determining the evaluation matching degree of each target forecast contamination area based on the evaluation index data of each target forecast contamination area, the evaluation index data of each target observed contamination area and the target similarity index weight group, the electronic device can calculate the regional similarity between any target forecast contamination area and each target observed contamination area for any target forecast contamination area among the M target forecast contamination areas based on the evaluation index data of any target forecast contamination area, the evaluation index data of each target observed contamination area and the target similarity index weight group; and take the maximum regional similarity among the regional similarities between any target forecast contamination area and each target observed contamination area as the evaluation matching degree of any target forecast contamination area.

[0064] For example, assuming that any target predicted contaminated area is the first target predicted contaminated area among M target predicted contaminated areas, then the first target predicted contaminated area can be calculated with N target observed contaminated areas to obtain N regional similarities (i.e., the regional similarities between the first target predicted contaminated area and each target observed contaminated area) {I 11 , I 12 ,…,I 1N}, so that {I 11 , I 12 ,…,I 1N The maximum value among them is taken as the evaluation matching degree I of the first target forecast pollution area. 1max (also known as the optimal matching degree); accordingly, M target predicted contaminated areas can obtain M evaluation matching degrees (that is, the evaluation matching degree of each target predicted contaminated area can be obtained) {I 1max , I 2max ,…,I Mmax}.

[0065] Optionally, when calculating the regional similarity between any target predicted contaminated area and each target observed contaminated area based on the evaluation index data of any target predicted contaminated area, the evaluation index data of each target observed contaminated area and the target similarity index weight group, for any target observed contaminated area among the N target observed contaminated areas, the electronic device may calculate the similarity index value of each similarity index between any target predicted contaminated area and any target observed contaminated area based on the evaluation index data of any target predicted contaminated area and the evaluation index data of any target observed contaminated area; and may calculate the regional similarity between any target predicted contaminated area and any target observed contaminated area based on the similarity index value of each similarity index between any target predicted contaminated area and any target observed contaminated area and the target similarity index weight group.

[0066] Optionally, for any similarity indicator among at least one similarity indicator, the electronic device can determine the first evaluation information of the evaluation space indicator corresponding to any similarity indicator in any target predicted contaminated area from the evaluation index data of any target predicted contaminated area, and determine the second evaluation information of the evaluation space indicator corresponding to any similarity indicator in any target observed contaminated area from the evaluation index data of any target observed contaminated area, so as to calculate the similarity index value of any similarity indicator between any target predicted contaminated area and any target observed contaminated area using the first evaluation information and the second evaluation information. The similarity index value of any similarity indicator between any target predicted contaminated area and any target observed contaminated area can also be called the similarity index value of any similarity indicator in any target predicted contaminated area and any target observed contaminated area.

[0067] Exemplarily, if any similarity index is an axis angle difference, the axis angle evaluation information of any target predicted contaminated area can be used as the first evaluation information, and the axis angle evaluation information of any target observed contaminated area can be used as the second evaluation information. At this time, the inverse of the difference between the first evaluation information and the second evaluation information can be used as the similarity index value of any similarity index between any target predicted contaminated area and any target observed contaminated area; if any similarity index is an intersection ratio, the area evaluation information of any target predicted contaminated area can be used as the first evaluation information, and the area evaluation information of any target observed contaminated area can be used as the second evaluation information, and the intersection area between any target predicted contaminated area and any target observed contaminated area can be determined based on the first evaluation information and the second evaluation information (such as the intersection area can be the number of identical grid area identifiers between the grid area identifier in the first evaluation information and the grid area identifier in the second evaluation information) and the union area (such as the union area can be the number of grid area identifiers in the first evaluation information + the number of grid area identifiers in the second evaluation information - the intersection area, or can be the number of grid areas in the first evaluation information + the number of grid areas in the second evaluation information - the intersection area, etc.), so that The ratio between the intersection area and the union area is used as the similarity index value of any similarity index between any target predicted contaminated area and any target observed contaminated area; if any similarity index is an area ratio, the area evaluation information of any target predicted contaminated area can be used as the first evaluation information, and the area evaluation information of any target observed contaminated area can be used as the second evaluation information, and the first grid area number and the second grid area number are determined from the first evaluation information and the second evaluation information, the first grid area number is less than or equal to the second grid area number, and one grid area number is the number of grid areas in a contaminated area, so that the ratio between the first grid area number and the second grid area number is used as the similarity index value of any similarity index between any target predicted contaminated area and any target observed contaminated area; if any similarity index is a centroid distance, the centroid evaluation information of any target predicted contaminated area can be used as the first evaluation information, and the centroid evaluation information of any target observed contaminated area can be used as the second evaluation information, so that the reciprocal of the distance between the first evaluation information and the second evaluation information is used as the similarity index value of any similarity index between any target predicted contaminated area and any target observed contaminated area;If any similarity index is an intensity percentile ratio, the intensity percentile evaluation information of any target predicted contaminated area is used as the first evaluation information, and the intensity percentile evaluation information of any target observed contaminated area is used as the second evaluation information, so that the intensity ratios at each specified percentile can be determined based on the intensity at each specified percentile in the first evaluation information and the intensity at each specified percentile in the second evaluation information, respectively (the intensity ratio at any specified percentile can be the ratio between the first intensity at any specified percentile and the second intensity at any specified percentile, the first intensity at any specified percentile can be the minimum value between the intensity at any specified percentile in the first evaluation information and the intensity at any specified percentile in the second evaluation information, and the second intensity at any specified percentile can be the maximum value between the intensity at any specified percentile in the first evaluation information and the intensity at any specified percentile in the second evaluation information), and the intensity ratios at each specified percentile are weighted summed (such as mean operation) to obtain the similarity index value of any similarity index between any target predicted contaminated area and any target observed contaminated area, and so on; the embodiment of the present invention is not limited to this. The effect of the forecast information can be evaluated according to the magnitude of the intensity ratio. Optionally, the weight of each specified percentile can be set according to experience or according to actual needs, which is not limited in the embodiment of the present invention. ;

[0068] It should be understood that when calculating the regional similarity between any target predicted contaminated area and any target observed contaminated area based on the similarity index values ​​of each similarity index between any target predicted contaminated area and any target observed contaminated area and the target similarity index weight group, the similarity index values ​​of each similarity index between any target predicted contaminated area and any target observed contaminated area can be weightedly summed based on the target weight value of each similarity index under the target pollution object to obtain a weighted summation result of the similarity indicators, so as to determine the regional similarity between any target predicted contaminated area and any target observed contaminated area based on the weighted summation result of the similarity indicators.

[0069] Optionally, take any target predicted contaminated area as the mth target predicted contaminated area among M target predicted contaminated areas, and any target observed contaminated area as the nth target observed contaminated area among N target observed contaminated areas as an example for explanation, m∈[1,M], n∈[1,N]; the electronic device may use formula 1.3 to calculate the regional similarity between the mth target predicted contaminated area and the nth target observed contaminated area:

[0070]

[0071] Among them, I mnIt can represent the regional similarity between the mth target predicted pollution area and the nth target observed pollution area, Q can be the number of similarity indicators in at least one similarity indicator, q∈[1,Q]; w q may be the target weight value of the qth similarity index in at least one similarity index under the target contaminated object, qmn It can represent the similarity function of the mth target predicted pollution area and the nth target observed pollution area under the qth similarity index (i.e., the similarity index value of the qth similarity index between the mth target predicted pollution area and the nth target observed pollution area, which can range from 0 to 1). Optionally, the sum of the target weight values ​​of each similarity index under the target pollution object can be equal to the sum of preset weights, that is, the sum of the weight values ​​of each similarity index in a similarity index weight group can be equal to the sum of preset weights; optionally, the sum of preset weights can be set according to experience or according to actual needs, which is not limited in the embodiment of the present invention; illustratively, the sum of preset weights can be 10.

[0072] Correspondingly, c qm It can be the credibility function of the qth similarity index in the mth target forecast pollution area (it can be used to adjust the similarity contribution of the evaluation space index so that the similarity index has a dynamic weight, which can also be called confidence level or confidence); for example, the shape of a polluted area is approximately circular, and the change in shape is not obvious visually, but the axis angle difference can have a significant change. At this time, this change in the axis angle difference is overly sensitive. Therefore, when the shape of the polluted area is closer to a circle (aspect ratio = 1), the contribution of the similarity of the axis angle difference to the total similarity (i.e., regional similarity) should be smaller. At this time, it can be a function of the aspect ratio (such as the aspect ratio of any target forecast pollution area). Optionally, when the qth similarity index is the axis angle difference, the electronic device can use formula 1.4 to calculate the confidence level of the qth similarity index in the mth target forecast pollution area:

[0073]

[0074] Among them, r can be the aspect ratio of the mth target predicted pollution area, which can also be expressed as r m .

[0075] Optionally, when the qth similarity index is not the axis angle difference, the confidence level of the qth similarity index in the mth target predicted contaminated area may be a preset confidence level; optionally, the preset confidence level may be set according to experience or according to actual needs, and the embodiment of the present invention is not limited to this; illustratively, the preset confidence level may be 1.

[0076] S105, based on the evaluation matching degree of each target predicted pollution area, determine the target air pollution simulation evaluation result, the target air pollution simulation evaluation result supports the simulation effect of the target numerical model on the target pollution object.

[0077] In one embodiment, the electronic device can determine the comprehensive similarity of the target forecast data based on the evaluation matching degree of each target forecast pollution area; and determine multiple similarity threshold ranges, and determine the similarity threshold range where the comprehensive similarity of the target forecast data is located from the multiple similarity threshold ranges, and one similarity threshold range corresponds to an atmospheric pollution simulation evaluation result; based on this, the atmospheric pollution simulation evaluation result corresponding to the similarity threshold range where the comprehensive similarity of the target forecast data is located can be used as the target atmospheric pollution simulation evaluation result. Optionally, the electronic device can use the median of the evaluation matching degree of each target forecast pollution area as the comprehensive similarity of the target forecast data, that is, the evaluation matching degree of each target forecast pollution area can be sorted in order from small to large to obtain the evaluation matching degree sorting result, and the median (i.e., median) can be determined from the evaluation matching degree sorting result to use the median as the comprehensive similarity of the target forecast data; or, the evaluation matching degree of each target forecast pollution area can be averaged to obtain the evaluation matching degree mean, and the evaluation matching degree mean can be used as the comprehensive similarity of the target forecast data, and so on.

[0078] Optionally, the above-mentioned multiple similarity threshold ranges can be set according to experience or according to actual needs, and the embodiment of the present invention does not limit this; accordingly, the atmospheric pollution simulation assessment result corresponding to a similarity threshold range can be set according to experience or according to actual needs, and the embodiment of the present invention does not limit this. Based on this, the embodiment of the present invention can refine different evaluation indicators (i.e., atmospheric pollution simulation assessment results) for similarity evaluation, that is, the number of similarity threshold ranges in multiple similarity threshold ranges can be greater than 2, and can be increased from the original good or bad binary evaluation to an evaluation greater than 2 (such as increasing to four levels of evaluation, etc.), thereby providing a more detailed and multi-dimensional evaluation for the simulation effect, which can fully reflect the complexity of the simulation effect; in other words, the embodiment of the present invention can refine the judgment criteria for similarity, changing the original binary judgment system to a multi-level judgment, thereby providing a more accurate evaluation of the simulation effect of the model (i.e., the target numerical mode).

[0079] Exemplarily, multiple similarity threshold ranges may be as shown in Table 1:

[0080] Table 1

[0081] High Similarity Similar Low Similarity No significant similarity Similarity threshold range [0.7，1] [0.5，0.7) [0.3，0.5) [0，0.3)

[0082] Among them, multiple similarity threshold ranges may include [0.7, 1], [0.5, 0.7), [0.3, 0.5) and [0, 0.3), and the atmospheric pollution simulation assessment results corresponding to each similarity threshold range in the multiple similarity threshold ranges may be high similarity, medium similarity, low similarity and no significant similarity, respectively; that is, the embodiment of the present invention may further adopt a multi-level similarity threshold range to make a simulation effect judgment on the similarity. When the comprehensive similarity is greater than or equal to 0.7, it can be considered that the simulated pollution area and the measured field have a high similarity, indicating that the simulation effect is relatively ideal. When the comprehensive similarity is less than 0.7 and greater than or equal to 0.5, it indicates that the simulation effect is good. When the comprehensive similarity is lower than 0.5 and greater than or equal to 0.3, the simulation effect is poor. When the comprehensive similarity is lower than 0.3, it indicates that the simulation effect is extremely poor. For example, assuming that the comprehensive similarity of the target forecast data is 0.6, the atmospheric pollution simulation assessment result "medium similarity" corresponding to the similarity threshold range [0.5, 0.7) of the comprehensive similarity of the target forecast data can be used as the target atmospheric pollution simulation assessment result, and so on.

[0083] In another implementation, the electronic device may also use the comprehensive similarity of the target forecast data as a target air pollution simulation evaluation result, and so on.

[0084] According to an embodiment of the present invention, after acquiring the target forecast data and the target observation data, based on the target forecast data, M target forecast pollution areas can be determined from the target area; and based on the target observation data, N target observation pollution areas can be determined from the target area, wherein the target forecast data includes forecast information of the target pollution object in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollution object in each grid area, and both M and N are positive integers. Furthermore, the evaluation index data of each target forecast pollution area among the M target forecast pollution areas can be determined respectively, and the evaluation index data of each target observation pollution area among the N target observation pollution areas can be determined respectively, and one evaluation index data includes the evaluation information of each evaluation space index in at least one evaluation space index under the corresponding pollution area; based on this, the target similarity index weight group of the target pollution object can be determined, and based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observation pollution area and the target similarity index weight group, the evaluation matching degree of each target forecast pollution area can be determined respectively; the target similarity index weight group includes the target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index; then accordingly, the target atmospheric pollution simulation evaluation result can be determined based on the evaluation matching degree of each target forecast pollution area, and the target atmospheric pollution simulation evaluation result supports the simulation effect of the target numerical model for indicating the target pollution object. It can be seen that the embodiments of the present invention can fully consider the impact of at least one evaluation space indicator on the atmospheric pollution simulation assessment through the evaluation index data of each target predicted pollution area and the evaluation index data of each target observed pollution area, and can realize a comprehensive assessment of the forecasting performance of the spatial distribution characteristics of the target pollution object, thereby effectively improving the accuracy of the spatial distribution assessment of atmospheric pollution simulation; in addition, the embodiments of the present invention can further improve the accuracy of the spatial distribution assessment of atmospheric pollution simulation through a target similarity indicator weight group adapted to the target pollution object.

[0085] Based on the above description, the embodiment of the present invention also proposes a more specific method for evaluating the spatial distribution of air pollution simulation. Accordingly, the method for evaluating the spatial distribution of air pollution simulation can be executed by the electronic device (terminal or server) mentioned above; or, the method for evaluating the spatial distribution of air pollution simulation can be executed by the terminal and the server together. For the sake of ease of explanation, the following description will be given by taking the electronic device executing the method for evaluating the spatial distribution of air pollution simulation as an example; please refer to Figure 2 The air pollution simulation spatial distribution assessment method may include the following steps S201-S209:

[0086] S201, obtaining target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area.

[0087] S202, based on the target forecast data, determine M target forecast contaminated areas from the target area; and based on the target observation data, determine N target observation contaminated areas from the target area, where M and N are both positive integers.

[0088] S203, respectively determine the evaluation index data of each target forecast pollution area in the M target forecast pollution areas, and respectively determine the evaluation index data of each target observation pollution area in the N target observation pollution areas, one evaluation index data includes the evaluation information of each evaluation space indicator in at least one evaluation space indicator under the corresponding pollution area.

[0089] S204, obtaining multiple initial similarity indicator weight groups under the target polluted object, and obtaining at least one label prediction data and label observation data corresponding to each label prediction data in at least one label prediction data, a similarity indicator weight group includes the weight value of each similarity indicator, and a label prediction data and a label observation data both include information of the target polluted object in each grid area.

[0090] Among them, a label prediction data may include prediction information of the target polluted object in each grid area and a time range, a label observation data may include observation information of the target polluted object in each grid area and a time range, and a label prediction data and the label observation data corresponding to the corresponding label prediction data may include data of the target polluted object within the same time range.

[0091] In the embodiment of the present invention, the target pollution object can be any pollution object (such as any pollutant or AQI, etc.). The embodiment of the present invention can specifically consider the spatial characteristics of different pollution objects to specifically determine the similarity index weight group of different pollution objects. For example, the pollution object "PM 2.5 For pollution in a large area in winter, the weight of the similarity indicator "area ratio" should be higher, that is, PM 2.5 The impact range and the hit rate of the pollution process are considered, so the weights of the intersection ratio and area ratio can be given higher values, and PM 2.5 Pollution events mostly occur in winter, and the atmospheric stratification is relatively stable in winter, and the movement speed of the pollution belt is slow, so the weight of the axis angle difference can be reduced accordingly, and PM 2.5The concentration value is also crucial for assessing the degree of pollution, so the intensity percentile ratio has a higher weight. 10 For the pollution events, most of them occur in spring, with a larger impact area and faster movement speed. The linear structure is more obvious than other pollution objects. Therefore, the weight of the axis angle difference can be given a higher value. And because there is a time phase difference between the forecast and the observation, the hit rate of the target numerical model is low, so the PM2.5 can be appropriately reduced. 10 The weight of the intersection ratio is ; while the assessment of CO mainly focuses on the pollution area and its hit rate on pollutants, so the weights of the intersection ratio and area ratio can be higher; NO2 (nitrogen dioxide), as a precursor of O3, mainly comes from transportation and industrial emissions. In the assessment process, more attention is paid to its pollution impact range and pollutant location, so the weights of the intersection ratio and area ratio can be higher; O3, as a secondary pollutant, its pollution concentration shows obvious daily variation characteristics, and the movement speed of the pollution area is slow, so the weight of the axis angle difference can be reduced, and in the simulation assessment of O3, the impact range is the main consideration, so the weight of the area ratio can be increased accordingly; for pollutants with more obvious point source effects such as SO2 (sulfur dioxide), a single pollution area is difficult to simulate, and the weight of its area ratio can be appropriately reduced, and so on. It should be noted that the centroid distance is mainly used to determine the landing area of ​​pollutants. What needs to be considered when determining the weight is the spatial distribution characteristics. When the area is large, the movement is slower and the centroid does not change much, so the weight can be relatively small; and, for pollutants with a concentrated range, most of them are ellipsoidal, and the weight of the axis angle difference can be lower; and for pollutant forecasts, the hit rate of the landing area is more important, so the weight of the intersection ratio can be higher.

[0092] Optionally, when obtaining multiple initial similarity indicator weight groups under the target pollution object, the weight range of each similarity indicator under the target pollution object can be obtained; and based on the weight range of each similarity indicator under the target pollution object, the weight values ​​of each similarity indicator are arranged and combined to obtain multiple initial similarity indicator weight groups under the target pollution object. Optionally, the weight range of each similarity indicator under the target pollution object can be stored in the electronic device's own storage space, and the weight range of each similarity indicator under the target pollution object can be obtained from its own storage space; or, a weight range download link for the target pollution object can be obtained, and the weight range indication data of the target pollution object can be downloaded based on the weight range download link of the target pollution object to obtain the weight range of each similarity indicator under the target pollution object, and so on. Optionally, the weight range of each similarity indicator under the target pollution object can be set based on the spatial characteristics of the target pollution object; exemplarily, as shown in the spatial characteristics of different pollution objects mentioned above, when the target pollution object is PM 2.5When the target pollution object is PM, the weight ranges of the axis angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance can be [1, 2], [1, 3], [2, 4], [2, 4] and [1, 2] respectively. 10 When the target pollution object is CO, the weight ranges of the axis angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can be [3, 5], [1, 2], [1, 3], [1, 3] and [1, 2] respectively; when the target pollution object is NO2, the weight ranges of the axis angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can be [1, 3], [2, 4], [2, 5], [1, 2] and [1, 2] respectively. The weight ranges of the axial angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can be [1, 3], [1, 3], [3, 5], [1, 2] and [1, 2] respectively; when the target pollution object is SO2, the weight ranges of the axial angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can be [1, 3], [3, 5], [1, 3], [1, 2] and [1, 2] respectively; when the target pollution object is O3, the weight ranges of the axial angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can be [1, 2], [1, 3], [3, 5], [1, 3] and [1, 2] respectively, and so on. It should be noted that the embodiment of the present invention does not limit the specific values ​​of the weight ranges of each similarity index under the target pollution object; if the target pollution object is PM 2.5 When , the weight ranges of the axis angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object can also be [1, 2], [2, 3], [2, 4], [2, 4] and [1, 2], etc.

[0093] Furthermore, the electronic device can arrange and combine the weight values ​​of each similarity indicator based on the preset weight sum and the weight range of each similarity indicator under the target pollution object to obtain multiple initial similarity indicator weight groups under the target pollution object; that is, the weight values ​​of each similarity indicator can be arranged and combined based on the weight range of each similarity indicator under the target pollution object to obtain multiple arrangement and combination results, and all arrangement and combination results in which the sum of each weight value in the arrangement and combination results is equal to the preset weight sum can be selected from the multiple arrangement and combination results, so that all the selected arrangement and combination results can be added to the multiple initial similarity indicator weight groups under the target pollution object, and each selected arrangement and combination result can be used as an initial similarity indicator weight group under the target pollution object, so as to obtain multiple initial similarity indicator weight groups under the target pollution object. Exemplarily, taking the target pollution object as PM2.5 Taking an example for illustration, assuming that at least one similarity index includes axial angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance, and the weight ranges of axial angle difference, intersection ratio, area ratio, intensity percentile ratio and centroid distance under the target pollution object are [1, 2], [1, 3], [2, 4], [2, 4] and [1, 2] respectively, then the above multiple permutation and combination results may include {1, 1, 2, 2, 1}, {1, 2, 2, 2, 1}, {1, 3, 2, 2, 1}, …, {2, 1, 2, 2, 1}, {2, 2, 2, 2, 1}, {2, 3, 2, 2, 1}, …, {2, 3, 4, 4, 2}; then correspondingly, assuming that the total preset weights is 10, then all permutation and combination results in which the sum of each weight value in the permutation and combination results is 10 (such as {1, 2, 3, 3, 1}, {1, 2, 4, 2, 1}, etc.) can be selected from multiple permutation and combination results, so that each permutation and combination result in which the sum of each weight value in the permutation and combination result is 10 is used as an initial similarity index weight group under the target contamination object, so as to obtain multiple initial similarity index weight groups under the target contamination object, and so on.

[0094] In other embodiments, the multiple initial similarity index weight groups under the target contamination object may also be set according to experience or actual needs, which is not limited in the embodiment of the present invention.

[0095] Optionally, the electronic device's own storage space may store at least one label prediction data and label observation data corresponding to each label prediction data, then at least one label prediction data and label observation data corresponding to each label prediction data may be obtained from its own storage space; or, a label data download link may be obtained to download at least one label prediction data and label observation data corresponding to each label prediction data based on the label data download link, and so on; the embodiments of the present invention are not limited to this. Optionally, at least one label forecast data and the label observation data corresponding to each label forecast data may be manually annotated to screen out each label forecast data and the label observation data corresponding to each label forecast data with a higher similarity (such as a comprehensive similarity) from multiple historical forecast data and the historical observation data corresponding to each historical forecast data in the multiple historical forecast data, that is, a label forecast data and the corresponding label observation data are data with a higher similarity; or, the electronic device may obtain at least one label observation data, and randomly perturb the observation information in each grid area included in each label observation data in the at least one label observation data according to a preset disturbance threshold, to obtain the perturbation data of each label observation data (the perturbation data of a label observation data may include the corresponding label observation data According to the random perturbation result of the observation information in each grid area in the data, the perturbation data of each label observation data is respectively used as a label prediction data, so as to obtain at least one label prediction data. At this time, the label observation data corresponding to a label prediction data can be the label observation data of the perturbation generation corresponding label prediction data (i.e., the generated perturbation data), wherein the preset perturbation threshold can be a smaller value, which can make the difference between an observation information and the perturbation result of the corresponding observation information less than the preset perturbation threshold, that is, the difference between an observation information and the perturbation result of the corresponding observation information is smaller, so that the perturbation data of any label observation data has a higher similarity with any label observation data, that is, the similarity between a label prediction data and the corresponding label observation data is higher, and so on. Optionally, the preset perturbation threshold can be set according to experience or according to actual needs, and the embodiments of the present invention are not limited to this.Exemplarily, assuming that at least one label observation data includes label observation data 1 and label observation data 2, then the label observation data 1 and the label observation data 2 can be randomly perturbed according to a preset disturbance threshold to obtain perturbation data 1 of label observation data 1 and perturbation data 2 of label observation data 2. Then the perturbation data 1 can be used as label prediction data 1, and the perturbation data 2 can be used as label prediction data 2. At this time, the label prediction data 1 can correspond to the label observation data 1, and the label prediction data 2 can correspond to the label observation data 2, that is, the label observation data corresponding to the label prediction data 1 can be the label observation data 1, and the label observation data corresponding to the label prediction data 2 can be the label observation data 2, so as to obtain at least one label prediction data (that is, label prediction data 1 and label prediction data 2) and the label observation data corresponding to each label prediction data.

[0096] S205, based on each label prediction data, determine from the target area at least one label prediction contaminated area under each label prediction data, and based on the label observation data corresponding to each label prediction data, determine from the target area at least one label observation contaminated area under the label observation data corresponding to each label prediction data; and respectively determine the evaluation index data of each label prediction contaminated area under each label prediction data, and respectively determine the evaluation index data of each label observation contaminated area under the label observation data corresponding to each label prediction data.

[0097] Among them, each label prediction contamination area under a label prediction data may be each label prediction contamination area in at least one label prediction contamination area under the corresponding label prediction data, and each label observation contamination area under a label observation data may be each label observation contamination area in at least one label observation contamination area under the corresponding label observation data. It should be understood that the method for determining at least one label prediction contamination area under each label prediction data and at least one label observation contamination area under the label observation data corresponding to each label prediction data may be the same as the method for determining the above-mentioned M target prediction contamination areas, and the embodiments of the present invention will not be repeated here.

[0098] Correspondingly, the method for determining the evaluation index data of each label predicted contaminated area under each label prediction data and the method for determining the evaluation index data of each label observed contaminated area under the label observation data corresponding to each label prediction data may be the same as the method for determining the evaluation index data of any of the above-mentioned target predicted contaminated areas, and the embodiments of the present invention will not be repeated here.

[0099] S206, based on the evaluation index data of each label prediction contaminated area under each label prediction data, the evaluation index data of each label observation contaminated area under the label observation data corresponding to each label prediction data, and multiple initial similarity index weight groups, determine the similarity evaluation indication information under each initial similarity index weight group in the multiple initial similarity index weight groups.

[0100] In an embodiment of the present invention, for any initial similarity indicator weight group among multiple initial similarity indicator weight groups, and any label prediction data among at least one label prediction data, the electronic device can determine the evaluation matching degree of each label prediction contamination area under any label prediction data under any initial similarity indicator weight group based on the evaluation indicator data of each label prediction contamination area under any label prediction data, the evaluation indicator data of each label observation contamination area under the label observation data corresponding to any label prediction data, and any initial similarity indicator weight group. It should be understood that the method for determining the evaluation matching degree of each label prediction contaminated area under any label prediction data under any initial similarity index weight group may be the same as the method for determining the evaluation matching degree of any target prediction contaminated area mentioned above; that is, for any label prediction contaminated area under any label prediction data, the regional similarity between any label prediction contaminated area under any label prediction data and each label observation contaminated area under the label observation data corresponding to any label prediction data may be calculated based on the evaluation index data of any label prediction contaminated area under any label prediction data, the evaluation index data of each label observation contaminated area under the label observation data corresponding to any label prediction data, and any initial similarity index weight group, so as to take the maximum regional similarity among the regional similarities between any label prediction contaminated area under any label prediction data and each label observation contaminated area under the label observation data corresponding to any label prediction data as the evaluation matching degree of any label prediction contaminated area under any label prediction data under any initial similarity index weight group, and so on; the embodiments of the present invention will not be repeated here.

[0101] Furthermore, the electronic device may determine the comprehensive similarity of any label prediction data under any initial similarity index weight group based on the evaluation matching degree of each label prediction contaminated area under any label prediction data under any initial similarity index weight group. It should be understood that the method for determining the comprehensive similarity of any label prediction data under any initial similarity index weight group may be the same as the method for determining the comprehensive similarity of the above-mentioned target prediction data, and the embodiments of the present invention will not be repeated here.

[0102] Then correspondingly, after obtaining the comprehensive similarity of each label prediction data under any initial similarity index weight group, the electronic device can determine the similarity evaluation indication information under any initial similarity index weight group based on the comprehensive similarity of each label prediction data under any initial similarity index weight group. Optionally, the electronic device can use the mean operation result between the comprehensive similarities of each label prediction data under any initial similarity index weight group as the similarity evaluation indication information under any initial similarity index weight group; or, the median of the comprehensive similarities of each label prediction data under any initial similarity index weight group can be used as the similarity evaluation indication information under any initial similarity index weight group; or, the sum of the comprehensive similarities of each label prediction data under any initial similarity index weight group can be used as the similarity evaluation indication information under any initial similarity index weight group, and so on; the embodiments of the present invention are not limited to this.

[0103] S207 , based on the similarity evaluation indication information under each initial similarity index weight group, selecting a target similarity index weight group of the target contamination object from the multiple initial similarity index weight groups.

[0104] In an embodiment of the present invention, the electronic device may use the initial similarity index weight group with the largest similarity evaluation indication information among multiple initial similarity index weight groups as the target similarity index weight group to select the target similarity index weight group of the target pollution object from the multiple initial similarity index weight groups.

[0105] Furthermore, the electronic device may also add the target similarity index weight group to the polluted object variable parameter data. Optionally, the electronic device may also determine whether the polluted object variable parameter data includes the target similarity index weight group of the target polluted object; if the polluted object variable parameter data includes the target similarity index weight group, the target similarity index weight group may be determined from the polluted object variable parameter data; if the polluted object variable parameter data does not include the target similarity index weight group, the above-mentioned acquisition of multiple initial similarity index weight groups under the target polluted object, and the acquisition of at least one label forecast data and the label observation data corresponding to each label forecast data in at least one label forecast data may be triggered to execute the above-mentioned steps S204-S207 to achieve the determination of the target similarity index weight group of the target polluted object. Optionally, if the polluted object variable parameter data includes the target weight values ​​of each similarity index under the target polluted object, it can be determined that the polluted object variable parameter data includes the target similarity index weight group; if the polluted object variable parameter data does not include the target weight value of any similarity index under the target polluted object, it can be determined that the polluted object variable parameter data does not include the target similarity index weight group. Optionally, the polluted object variable parameter data can be a table data, so in the subsequent application process, the parameters of the required polluted object variable (such as the target polluted object) (i.e., the similarity index weight group of the required polluted object) can be determined by the table lookup method when necessary. In other words, in other embodiments, if the polluted object variable parameter data includes the target similarity index weight group, the electronic device can directly obtain the target similarity index weight group from the polluted object variable parameter data to determine the target similarity index weight group.

[0106] Based on this, the polluted object variable parameter data may include a similarity index weight group of each polluted object in at least one polluted object, and a similarity index weight group of a polluted object may include a weight value of each similarity index in at least one similarity index under the corresponding polluted object. Exemplarily, the polluted object variable parameter data may be shown in Table 2:

[0107] Table 2

[0108] Similarity index Axis angle difference Intersection Ratio Area ratio Intensity Percentile Ratio Centroid distance <![CDATA[PM 2.5 ]]> 1 2 3 3 1 <![CDATA[PM 10 ]]> 4 1 2 2 1 CO 2 3 3 1 1 <![CDATA[NO2]]> 2 2 4 1 1 <![CDATA[SO2]]> 2 4 2 1 1 <![CDATA[O3]]> 1 2 4 2 1

[0109] In summary, at this time, we can first find the target similarity index weight group through the pollution object variable parameter data, so as to quickly obtain the target similarity index weight group when the pollution object variable parameter data includes the target similarity index weight group. Then, when the pollution object variable parameter data includes the weight values ​​of each similarity index under different pollution objects, the weight values ​​of each similarity index under different pollution objects can be quickly obtained, which can effectively improve the efficiency of spatial distribution assessment of atmospheric pollution simulation.

[0110] Optionally, the pollutant variable parameter data may also store the weight percentage of each weight value in the similarity index weight group of any pollutant relative to the preset weight sum; for example, when the preset weight sum is 10, the axis angle difference is in the pollutant PM 2.5 The weight value under the condition can be obtained by the axis angle difference in the polluted object PM 2.5 The weight percentage under this condition indicates that the above axis angle difference is in the pollution object PM 2.5 The weight value below can be expressed as 1 / 10=10%, and so on.

[0111] S208, based on the evaluation index data of each target predicted pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group, determine the evaluation matching degree of each target predicted pollution area respectively; the target similarity index weight group includes the target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index.

[0112] S209, based on the evaluation matching degree of each target predicted pollution area, determine the target atmospheric pollution simulation evaluation result, the target atmospheric pollution simulation evaluation result supports the simulation effect of the target numerical model on the target pollution object.

[0113] Optionally, the number of target forecast data may be one or more, and the number of target observation data may be one or more, and one target forecast data corresponds to one target observation data, which is not limited in the embodiment of the present invention. Optionally, when the number of target forecast data and the number of target observation data are multiple, the electronic device may determine the comprehensive similarity of any target forecast data based on any target forecast data among the multiple target forecast data and the target observation data corresponding to any target forecast data, thereby determining the target atmospheric pollution simulation evaluation result based on the comprehensive similarity of each target forecast data. Optionally, the electronic device may perform a mean operation on the comprehensive similarities of each target forecast data to obtain a comprehensive similarity mean, and use the atmospheric pollution simulation evaluation result corresponding to the similarity threshold range where the comprehensive similarity mean is located as the simulation effect of the target pollution object; or, the comprehensive similarity mean may be used as the simulation effect of the target pollution object, and so on; the embodiment of the present invention is not limited in this regard.

[0114] According to an embodiment of the present invention, after obtaining the target forecast data and the target observation data, M target forecast pollution areas can be determined from the target area based on the target forecast data; and N target observation pollution areas can be determined from the target area based on the target observation data, wherein the target forecast data includes forecast information of the target pollution object in each grid area in the target area, the target forecast data is forecasted by the target numerical model, and the target observation data includes observation information of the target pollution object in each grid area. Then, the evaluation index data of each target forecast pollution area in the M target forecast pollution areas can be determined respectively, and the evaluation index data of each target observation pollution area in the N target observation pollution areas can be determined respectively, and one evaluation index data includes evaluation information of each evaluation space index in the corresponding pollution area in at least one evaluation space index. Accordingly, multiple initial similarity indicator weight groups under the target contaminated object can be obtained, as well as at least one label prediction data and label observation data corresponding to each label prediction data in at least one label prediction data. A similarity indicator weight group includes weight values ​​of each similarity indicator, and a label prediction data and a label observation data both include information of the target contaminated object in each grid area; based on each label prediction data, at least one label prediction contaminated area under each label prediction data is determined from the target area, and based on the label observation data corresponding to each label prediction data, at least one label observation contaminated area under the label observation data corresponding to each label prediction data is determined from the target area; and evaluation indicator data of each label prediction contaminated area under each label prediction data is determined, and evaluation indicator data of each label observation contaminated area under the label observation data corresponding to each label prediction data is determined. Furthermore, based on the evaluation index data of each label predicted contaminated area under each label predicted data, the evaluation index data of each label observed contaminated area under the label observed data corresponding to each label predicted data, and multiple initial similarity index weight groups, the similarity evaluation indication information under each initial similarity index weight group in the multiple initial similarity index weight groups can be determined; and based on the similarity evaluation indication information under each initial similarity index weight group, the target similarity index weight group of the target contaminated object can be selected from the multiple initial similarity index weight groups.Accordingly, the evaluation matching degree of each target forecast pollution area can be determined respectively based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes the target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index; and based on the evaluation matching degree of each target forecast pollution area, the target atmospheric pollution simulation evaluation result is determined, and the target atmospheric pollution simulation evaluation result supports the simulation effect of the target numerical model for indicating the target pollution object. It can be seen that the embodiment of the present invention can identify M target forecast pollution areas and N target observation pollution areas from the target area, and assign at least one evaluation space index to these pollution areas, so as to realize the spatial distribution evaluation of atmospheric pollution simulation through the evaluation index data of each target forecast pollution area and the evaluation index data of each target observation pollution area. That is to say, the embodiment of the present invention can use the spatial similarity matching method to evaluate and inspect the target pollution object, taking into account the location, structure and range of the target pollution object, so as to effectively improve the accuracy of the spatial distribution evaluation of atmospheric pollution simulation; and the target pollution object can be any pollution object (such as pollutants, etc.), that is, the embodiment of the present invention can set specific algorithm parameters for the evaluation of different pollution objects (that is, the target similarity index weight group can be determined for the target pollution object, and the similarity index weight groups of different pollution objects can be different, so as to combine the spatial distribution characteristics of different pollution objects to determine the weight values ​​of each similarity index under different pollution objects), which can avoid manual judgment to achieve weight assignment of different similarity indicators, that is, to avoid the problem of large subjectivity and uncertainty caused by manual judgment in setting weights, and can effectively improve the accuracy and objectivity of the evaluation of the spatial distribution characteristics of the target pollution object.

[0115] Based on the description of the relevant embodiments of the above-mentioned atmospheric pollution simulation spatial distribution assessment method, the embodiment of the present invention also proposes an atmospheric pollution simulation spatial distribution assessment device, which can be a computer program (including program code) running in an electronic device; Figure 3 As shown, the air pollution simulation spatial distribution evaluation device may include an acquisition unit 301 and a processing unit 302. The air pollution simulation spatial distribution evaluation device may execute Figure 1 or Figure 2 The method for evaluating the spatial distribution of air pollution simulation shown, that is, the device for evaluating the spatial distribution of air pollution simulation can run the above-mentioned units:

[0116] An acquisition unit 301 is used to acquire target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area;

[0117] The processing unit 302 is configured to determine M target forecast contaminated areas from the target area based on the target forecast data; and determine N target observed contaminated areas from the target area based on the target observation data, where M and N are both positive integers;

[0118] The processing unit 302 is further configured to respectively determine evaluation index data of each target forecast contaminated area in the M target forecast contaminated areas, and respectively determine evaluation index data of each target observed contaminated area in the N target observed contaminated areas, wherein one evaluation index data includes evaluation information of each evaluation space index in the corresponding contaminated area in at least one evaluation space index;

[0119] The processing unit 302 is further used to determine a target similarity index weight group of the target polluted object, and determine the evaluation matching degree of each target forecast polluted area based on the evaluation index data of each target forecast polluted area, the evaluation index data of each target observed polluted area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target polluted object, and one similarity index corresponds to one evaluation space index;

[0120] The processing unit 302 is further used to determine a target atmospheric pollution simulation evaluation result based on the evaluation matching degree of each target predicted pollution area, and the target atmospheric pollution simulation evaluation result supports indicating the simulation effect of the target numerical model on the target pollution object.

[0121] In one embodiment, when the processing unit 302 determines the evaluation matching degree of each target forecast contaminated area based on the evaluation index data of each target forecast contaminated area, the evaluation index data of each target observed contaminated area, and the target similarity index weight group, it can be specifically used to:

[0122] For any target predicted contaminated area among the M target predicted contaminated areas, respectively based on the evaluation index data of the any target predicted contaminated area, the evaluation index data of each target observed contaminated area and the target similarity index weight group, calculate the regional similarity between the any target predicted contaminated area and each target observed contaminated area;

[0123] The maximum regional similarity among the regional similarities between any target predicted contaminated area and each target observed contaminated area is used as the evaluation matching degree of any target predicted contaminated area.

[0124] In another embodiment, when the processing unit 302 calculates the regional similarity between any target predicted contaminated area and each target observed contaminated area based on the evaluation index data of any target predicted contaminated area, the evaluation index data of each target observed contaminated area, and the target similarity index weight group, it can be specifically used to:

[0125] For any target observed contaminated area among the N target observed contaminated areas, based on the evaluation index data of any target predicted contaminated area and the evaluation index data of any target observed contaminated area, calculate the similarity index values ​​of each similarity index between any target predicted contaminated area and any target observed contaminated area

[0126] Based on the similarity index values ​​of the respective similarity indexes between the any target predicted contaminated area and the any target observed contaminated area and the target similarity index weight group, the regional similarity between the any target predicted contaminated area and the any target observed contaminated area is calculated.

[0127] In another embodiment, when determining the target similarity index weight group of the target contamination object, the processing unit 302 may be specifically used to:

[0128] Acquire multiple initial similarity index weight groups under the target polluted object, and acquire at least one label prediction data and label observation data corresponding to each label prediction data in the at least one label prediction data, wherein a similarity index weight group includes weight values ​​of each similarity index, and a label prediction data and a label observation data both include information of the target polluted object in each grid area;

[0129] Based on the respective label prediction data, at least one label prediction contaminated area under the respective label prediction data is determined from the target area, and based on the label observation data corresponding to the respective label prediction data, at least one label observation contaminated area under the label observation data corresponding to the respective label prediction data is determined from the target area; and evaluation index data of each label prediction contaminated area under the respective label prediction data is determined, and evaluation index data of each label observation contaminated area under the label observation data corresponding to the respective label prediction data is determined;

[0130] Determine similarity evaluation indication information under each initial similarity indicator weight group in the multiple initial similarity indicator weight groups based on the evaluation index data of each label prediction contaminated area under the label observation data corresponding to each label prediction data, and the multiple initial similarity indicator weight groups;

[0131] Based on the similarity evaluation indication information under each of the initial similarity index weight groups, a target similarity index weight group of the target contamination object is selected from the multiple initial similarity index weight groups.

[0132] In another embodiment, the processing unit 302, based on the evaluation index data of each label prediction contaminated area under the label observation data corresponding to each label prediction data, the evaluation index data of each label observation contaminated area under the label observation data corresponding to each label prediction data, and the multiple initial similarity index weight groups, determines the similarity evaluation indication information under each initial similarity index weight group in the multiple initial similarity index weight groups, which can be specifically used to:

[0133] For any initial similarity indicator weight group among the multiple initial similarity indicator weight groups, and any label prediction data among the at least one label prediction data, based on the evaluation indicator data of each label prediction contaminated area under the any label prediction data, the evaluation indicator data of each label observation contaminated area under the label observation data corresponding to the any label prediction data, and the any initial similarity indicator weight group, determine the evaluation matching degree of each label prediction contaminated area under the any label prediction data under the any initial similarity indicator weight group;

[0134] Determine the comprehensive similarity of any label prediction data under any initial similarity index weight group based on the evaluation matching degree of each label prediction contaminated area under any label prediction data under any initial similarity index weight group;

[0135] After obtaining the comprehensive similarities of the various label prediction data under the any initial similarity indicator weight group, similarity evaluation indication information under the any initial similarity indicator weight group is determined based on the comprehensive similarities of the various label prediction data under the any initial similarity indicator weight group.

[0136] In another implementation manner, when the processing unit 302 determines M target predicted contaminated areas from the target area based on the target prediction data, it may be specifically configured to:

[0137] Based on the target forecast data, determining at least one forecast pollution grid area whose forecast information is greater than or equal to a preset target pollution object threshold from the target area, and based on the at least one forecast pollution grid area, determining M target forecast pollution areas;

[0138] When the processing unit 302 determines N target observation contaminated areas from the target area based on the target observation data, it can be specifically used to:

[0139] Based on the target observation data, at least one observation pollution grid area whose observation information is greater than or equal to the preset target pollution object threshold is determined from the target area, and based on the at least one observation pollution grid area, N target observation pollution areas are determined.

[0140] In another embodiment, when the processing unit 302 determines the target air pollution simulation assessment result based on the assessment matching degree of each target forecast pollution area, it can be specifically used to:

[0141] Determining the comprehensive similarity of the target forecast data based on the evaluation matching degree of each target forecast contaminated area;

[0142] Determine a plurality of similarity threshold ranges, and determine a similarity threshold range where the comprehensive similarity of the target forecast data lies from the plurality of similarity threshold ranges, wherein one similarity threshold range corresponds to one atmospheric pollution simulation assessment result;

[0143] The air pollution simulation evaluation result corresponding to the similarity threshold range where the comprehensive similarity of the target forecast data lies is used as the target air pollution simulation evaluation result.

[0144] According to one embodiment of the present invention, Figure 3 Each unit in the shown air pollution simulation spatial distribution assessment device can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple smaller units in function to constitute, 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 practical applications, the function 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 pollution simulation spatial distribution assessment device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0145] 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 medium (RAM), a read-only memory medium (ROM), and other processing elements and storage elements. Figure 1 or Figure 2 A computer program (including program code) for each step involved in the corresponding method shown in Figure 3 The air pollution simulation spatial distribution evaluation device shown in and the air pollution simulation spatial distribution evaluation method of the embodiment of the present invention are implemented. The computer program can be recorded on, for example, a computer storage medium, and loaded into the above-mentioned electronic device through the computer storage medium and run therein.

[0146] Based on the description of the above method embodiment and device embodiment, the exemplary embodiment of the present invention further provides an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program that can be executed by the at least one processor, and the computer program is used to enable the electronic device to perform the method according to the embodiment of the present invention when executed by the at least one processor.

[0147] Exemplary embodiments of the present invention also 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 used to cause the computer to perform a method according to an embodiment of the present invention.

[0148] An exemplary embodiment of the present invention further provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor of a computer, the computer is used to enable the computer to perform a method according to an embodiment of the present invention.

[0149] refer to Figure 4 , a block diagram of an electronic device 400 that can be used as a server or client of the present invention will now be described, which is an example of a hardware device that can be applied to various aspects of the present invention. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0150] like Figure 4As shown, the electronic device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0151] A plurality of components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, an output unit 407, a storage unit 408, and a communication unit 409. The input unit 406 may be any type of device capable of inputting information to the electronic device 400, and the input unit 406 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 407 may 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. The storage unit 408 may include, but is not limited to, a disk, an optical disk. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices via a computer network 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 a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0152] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above. For example, in some embodiments, the atmospheric pollution simulation spatial distribution assessment method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via ROM 402 and / or communication unit 409. In some embodiments, the computing unit 401 may be configured to perform the atmospheric pollution simulation spatial distribution assessment method by any other appropriate means (e.g., by means of firmware).

[0153] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes 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 the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0154] 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 equipment. 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, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0155] As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0156] 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).

[0157] Furthermore, it should be understood that what is disclosed above is only a preferred embodiment of the present invention, and certainly cannot be used to limit the scope of rights 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. A method for evaluating the spatial distribution of air pollution simulation, characterized in that: include: Acquiring target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area; Based on the target forecast data, determining M target forecast pollution areas from the target area; Based on the target observation data, N target observation contaminated areas are determined from the target area, where M and N are both positive integers; Determine evaluation index data of each target forecast pollution area in the M target forecast pollution areas respectively, and determine evaluation index data of each target observation pollution area in the N target observation pollution areas respectively, one evaluation index data includes evaluation information of each evaluation space index in the corresponding pollution area in at least one evaluation space index; Determine a target similarity index weight group of the target pollution object, and determine the evaluation matching degree of each target forecast pollution area based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index; Based on the evaluation matching degree of each target predicted pollution area, a target atmospheric pollution simulation evaluation result is determined, and the target atmospheric pollution simulation evaluation result supports indicating the simulation effect of the target numerical model on the target pollution object.

2. The method according to claim 1, characterized in that The step of determining the evaluation matching degree of each target forecast contaminated area based on the evaluation index data of each target forecast contaminated area, the evaluation index data of each target observed contaminated area, and the target similarity index weight group includes: For any target predicted contaminated area among the M target predicted contaminated areas, respectively based on the evaluation index data of the any target predicted contaminated area, the evaluation index data of each target observed contaminated area and the target similarity index weight group, calculate the regional similarity between the any target predicted contaminated area and each target observed contaminated area; The maximum regional similarity among the regional similarities between any target predicted contaminated area and each target observed contaminated area is used as the evaluation matching degree of any target predicted contaminated area.

3. The method according to claim 2, characterized in that The calculating the regional similarity between any target predicted contaminated area and each target observed contaminated area based on the evaluation index data of any target predicted contaminated area, the evaluation index data of each target observed contaminated area and the target similarity index weight group respectively includes: For any target observed contaminated area among the N target observed contaminated areas, based on the evaluation index data of the any target predicted contaminated area and the evaluation index data of the any target observed contaminated area, calculate the similarity index values ​​of the respective similarity indexes between the any target predicted contaminated area and the any target observed contaminated area; Based on the similarity index values ​​of the respective similarity indexes between the any target predicted contaminated area and the any target observed contaminated area and the target similarity index weight group, the regional similarity between the any target predicted contaminated area and the any target observed contaminated area is calculated.

4. The method according to any one of claims 1 to 3, characterized in that: The step of determining a target similarity index weight group of the target contamination object comprises: Acquire multiple initial similarity index weight groups under the target polluted object, and acquire at least one label prediction data and label observation data corresponding to each label prediction data in the at least one label prediction data, wherein a similarity index weight group includes weight values ​​of each similarity index, and a label prediction data and a label observation data both include information of the target polluted object in each grid area; Based on the respective label prediction data, at least one label prediction contaminated area under the respective label prediction data is determined from the target area, and based on the label observation data corresponding to the respective label prediction data, at least one label observation contaminated area under the label observation data corresponding to the respective label prediction data is determined from the target area; and evaluation index data of each label prediction contaminated area under the respective label prediction data is determined, and evaluation index data of each label observation contaminated area under the label observation data corresponding to the respective label prediction data is determined; Determine similarity evaluation indication information under each initial similarity indicator weight group in the multiple initial similarity indicator weight groups based on the evaluation index data of each label prediction contaminated area under the label observation data corresponding to each label prediction data, and the multiple initial similarity indicator weight groups; Based on the similarity evaluation indication information under each of the initial similarity index weight groups, a target similarity index weight group of the target contamination object is selected from the multiple initial similarity index weight groups.

5. The method according to claim 4, characterized in that The determining of similarity evaluation indication information under each initial similarity indicator weight group in the multiple initial similarity indicator weight groups based on the evaluation index data of each label prediction contaminated area under the label observation data corresponding to each label prediction data and the multiple initial similarity indicator weight groups includes: For any initial similarity indicator weight group among the multiple initial similarity indicator weight groups, and any label prediction data among the at least one label prediction data, based on the evaluation indicator data of each label prediction contaminated area under the any label prediction data, the evaluation indicator data of each label observation contaminated area under the label observation data corresponding to the any label prediction data, and the any initial similarity indicator weight group, determine the evaluation matching degree of each label prediction contaminated area under the any label prediction data under the any initial similarity indicator weight group; Determine the comprehensive similarity of any label prediction data under any initial similarity index weight group based on the evaluation matching degree of each label prediction contaminated area under any label prediction data under any initial similarity index weight group; After obtaining the comprehensive similarities of the various label prediction data under the any initial similarity indicator weight group, similarity evaluation indication information under the any initial similarity indicator weight group is determined based on the comprehensive similarities of the various label prediction data under the any initial similarity indicator weight group.

6. The method according to any one of claims 1 to 3, characterized in that: The step of determining M target predicted contaminated areas from the target area based on the target forecast data includes: Based on the target forecast data, determining at least one forecast pollution grid area whose forecast information is greater than or equal to a preset target pollution object threshold from the target area, and based on the at least one forecast pollution grid area, determining M target forecast pollution areas; The determining N target observation contaminated areas from the target area based on the target observation data includes: Based on the target observation data, at least one observation pollution grid area whose observation information is greater than or equal to the preset target pollution object threshold is determined from the target area, and based on the at least one observation pollution grid area, N target observation pollution areas are determined.

7. The method according to any one of claims 1 to 3, characterized in that: Determining the target atmospheric pollution simulation assessment result based on the assessment matching degree of each target forecast pollution area includes: Determining the comprehensive similarity of the target forecast data based on the evaluation matching degree of each target forecast contaminated area; Determine a plurality of similarity threshold ranges, and determine a similarity threshold range where the comprehensive similarity of the target forecast data lies from the plurality of similarity threshold ranges, wherein one similarity threshold range corresponds to one atmospheric pollution simulation assessment result; The air pollution simulation evaluation result corresponding to the similarity threshold range where the comprehensive similarity of the target forecast data lies is used as the target air pollution simulation evaluation result.

8. An atmospheric pollution simulation spatial distribution assessment device, characterized in that: The device comprises: an acquisition unit, configured to acquire target forecast data and target observation data, wherein the target forecast data includes forecast information of the target pollutant in each grid area in the target area, the target forecast data is forecasted by a target numerical model, and the target observation data includes observation information of the target pollutant in each grid area; A processing unit, configured to determine M target forecast contaminated areas from the target area based on the target forecast data; and to determine N target observed contaminated areas from the target area based on the target observation data, where M and N are both positive integers; The processing unit is further used to respectively determine the evaluation index data of each target forecast pollution area in the M target forecast pollution areas, and respectively determine the evaluation index data of each target observation pollution area in the N target observation pollution areas, wherein one evaluation index data includes evaluation information of each evaluation space index in the corresponding pollution area in at least one evaluation space index; The processing unit is further used to determine a target similarity index weight group of the target pollution object, and determine the evaluation matching degree of each target forecast pollution area based on the evaluation index data of each target forecast pollution area, the evaluation index data of each target observed pollution area and the target similarity index weight group; the target similarity index weight group includes a target weight value of each similarity index in at least one similarity index under the target pollution object, and one similarity index corresponds to one evaluation space index; The processing unit is further used to determine a target atmospheric pollution simulation evaluation result based on the evaluation matching degree of each target predicted pollution area, and the target atmospheric pollution simulation evaluation result supports indicating the simulation effect of the target numerical model on the target pollution object.

9. 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 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1-7.

Images