Full coverage daily scale AOD inversion method, device, system and storage medium

Abstract

The present invention discloses a method, device, system, and storage medium for inverting daily-scale AOD with full coverage. The method comprises: processing station data, meteorological data sets, terrain data sets, and population data using a linear interpolation method, and performing spatiotemporal matching with MAICAAOD to obtain a modeling data set; performing triangular irregular network interpolation on MAICAAOD to obtain preliminary daily AOD data and annual average AOD data; constructing a multi-layer LGBM model based on the preliminary daily AOD data and annual average AOD data, and performing multi-step simulation to correct and fill errors to obtain an adjusted optimal prediction model; and using the optimal prediction model to perform estimation based on the modeling data set to obtain a daily AOD product with full coverage in the region. The daily AOD product obtained by the present invention is substantially consistent with the measured data at the monitoring station, and can obtain a product with 100% full coverage and good spatiotemporal continuity. At the same time, the recovered AOD product is consistent with the original data and has high accuracy and reliability.

Description

Technical Field

[0001] The present invention belongs to the technical field of aerosol optical depth inversion. Specifically, the present invention provides a full-coverage daily-scale AOD inversion method, device, system and storage medium. Background Art

[0002] Atmospheric aerosols are solid or liquid particles suspended in the air. They significantly impact human health, air quality, ecosystems, and climate change by altering Earth's atmospheric circulation and radiation balance. Therefore, the spatiotemporal distribution of aerosols has become a focus of current research. As one of the most important optical characteristics of aerosols, aerosol optical depth (AOD), defined as the vertical integral of the aerosol extinction coefficient, can characterize the level and distribution of aerosol loads. It is a key indicator for quantifying aerosol content and has been widely used in atmospheric environmental research.

[0003] There are two main methods for measuring AOD: ground-based and satellite-based. Ground-based measurements, primarily through the Aerosol Robotic Network (AERONET) using solar spectrophotometers, provide relatively accurate AOD values ​​and regional analysis. However, these data lack continuity and coverage over large spatial scales. Therefore, satellite-derived AOD products are increasingly used as the primary data source for AOD research and are considered the best source for global-scale studies.

[0004] Common AOD products are derived from various sensors, such as the Advanced Very High Resolution Radiometer (AVHRR), the Moderate Resolution Imaging Spectroradiometer (MODIS), and the Ozone Monitoring Instrument (OMI). MODIS, using the advanced Multi-angle Implementation of Atmospheric Correction (MAIAC) algorithm, provides a global, high-resolution daily AOD retrieval product (36 spectral channels, a 1-2 day repeat period, and spatial resolutions of 250, 500, and 1000 meters). These products can better identify AOD information in areas with clouds and snow, and are widely used in research and applications. However, due to the limited detection capabilities of sensors at high altitudes, in mountainous areas, or in areas with high surface reflectivity and elevated aerosol concentrations, the original MAIC AOD product suffers from significant data omissions, resulting in an average coverage rate of only 30.42%. Because the MAIAC AOD product is only available under clear skies, frequent rainy or cloudy weather can also result in poor spatial continuity, limiting its application at the regional scale, especially in specific areas, and limiting the accuracy of subsequent atmospheric pollutant forecasting and analysis. At the same time, clear days can also result in data loss due to unfavorable surface conditions (snow cover) or errors in data preprocessing (misclassification of heavy aerosol layers as clouds). Therefore, restoring gaps in MAICA AOD data to improve the quality and availability of AOD products, enhance the spatial continuity of AOD, and expand its application range is of great significance and research prospect.

[0005] To date, various methods have been proposed to restore AOD data products. The earliest and most widely used approach is based on spatial statistical methods such as kriging, which utilizes localized null information within the AOD product itself to restore AOD gaps. However, the AOD restored by this method exhibits high spatiotemporal variability and is unsuitable for predicting missing AOD data. Another common approach is to improve data quality by fusing multi-source AOD data products. However, this approach often fails to unify the uncertainties between different AOD products and does not effectively address the impact of cloud contamination. Given the continuous advancements and improvements in machine learning technology, many researchers have begun training models to restore missing AOD values. Restoration results show that algorithms developed based on machine learning techniques can not only produce spatially continuous AOD products but also achieve high accuracy. Consequently, they are increasingly being used to restore AOD products.

[0006] Aerosol concentrations generally change dramatically and rapidly over short periods of time. Therefore, developing algorithms that combine machine learning with the continuous temporal information of the original AOD product to recover a single-day AOD product is most suitable for practical applications. However, currently developed algorithms, limited by the limited information available in single-day imagery, are limited in their ability to generate comprehensive AOD products over large areas. Consequently, linear functions are commonly used in large-scale applications. Therefore, a novel algorithm is needed that fully utilizes single-day AOD information to recover comprehensive, high-precision AOD products over large areas, thus overcoming the limitations of scarce complementary information. Summary of the Invention

[0007] The present invention is provided to solve the above problems existing in the prior art. Therefore, a full coverage daily scale AOD inversion method, device, system and storage medium are needed.

[0008] According to a first technical solution of the present invention, a full coverage daily scale AOD inversion method is provided, the method comprising:

[0009] The station data, meteorological data set, terrain data set and population data are processed using a linear interpolation method to obtain preprocessed data, and the preprocessed data is spatially and temporally matched with MAICAAOD to obtain a modeling data set;

[0010] The triangular irregular network interpolation of MAICAAOD was performed to obtain preliminary daily AOD data and annual average AOD data;

[0011] Based on the preliminary daily full-coverage AOD data and the annual average AOD data, a multi-layer LGBM model was constructed, and multi-step simulations were performed to correct the filling errors and obtain the adjusted optimal prediction model;

[0012] Based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product with full coverage in the region.

[0013] Furthermore, the site data, meteorological data set, terrain data set and population data are processed using a linear interpolation method to obtain preprocessed data, and the preprocessed data is spatially and temporally matched with MAICAAOD to obtain a modeling data set, including:

[0014] Get site data using The index interpolates the two adjacent bands of 670nm and 440nm to obtain the AOD parameters at 550nm, so that the site data can meet the consistency with MAIAC AOD when comparing the accuracy;

[0015] Obtain NDVI data, DEM data, and population datasets;

[0016] The site data, NDVI data, DEM data, and population data were matched with the MAICAAOD data accuracy and used as the modeling dataset.

[0017] Furthermore, the temporal and spatial resolutions of the NDVI data are 16 days and 250M respectively, the resolution of the DEM data is 30m, and the resolution of the population dataset is 1km.

[0018] Furthermore, triangular irregular network interpolation is performed on MAICAAOD to obtain full coverage AOD data and annual average AOD data, including:

[0019] Get MAICAAOD;

[0020] According to the quality assurance mark and valid AOD range provided by the MAIAC AOD product, the MAIACAOD data was cleaned and AOD values ​​greater than 3 were excluded;

[0021] The existing daily MAICAAOD data are used to perform TIN interpolation on the missing areas in MAIACAOD to perform large-scale restoration using the existing spatial information, thereby obtaining a daily AOD with sufficient data volume.

[0022] Furthermore, the temporal and spatial resolutions of the MAICAAOD are 1 day and 1 km×1 km, respectively.

[0023] Furthermore, based on the full coverage AOD data and the annual average AOD data, a multi-layer LGBM model was constructed, and multi-step simulation was performed to correct the filling error, and the adjusted optimal prediction model was obtained, including:

[0024] A multi-layer LGBM model was constructed. In the multi-layer LGBM model, the first layer used the initially obtained full-coverage AOD product and the annual average AOD as the main explanatory variables to fill in the seasonal average value. The second layer used the annual and seasonal AOD products as explanatory variables to calculate the monthly average AOD value. The third layer used the annual, seasonal, and monthly AOD products to fill in the weekly AOD. The last layer used the annual, seasonal, monthly, and weekly AOD products as explanatory variables to fill in the daily AOD on a large scale. The calculation formula of the last layer is expressed as follows:

[0025]

[0026] Among them, AOD Daily (i, j) represents the actual daily AOD level of the specified pixel (i, j); LGBM represents the last layer of the LGBM model; AOD Year (i, j) represents the preliminary obtained annual average AOD; AOD Quarterly (i, j) represents the seasonal average AOD obtained by the first-layer model; AOD Monthly(i, j) represents the monthly average AOD obtained by the second-layer model; AOD Weekly (i, j) represents the weekly AOD obtained by the third-layer model; NDVI (i, j) represents the normalized vegetation index value of the specified pixel point (i, j); DEM (i, j) represents the elevation value of the specified pixel point (i, j); POP (i, j) represents the population data of the specified pixel point (i, j).

[0027] Furthermore, based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product covering the entire region, including:

[0028] All modeling data are processed into standard spatial grids, and the optimal prediction model is used to restore the daily AOD values ​​in the area to obtain a daily AOD product that covers the entire area.

[0029] According to a second technical solution of the present invention, a full-coverage daily-scale AOD inversion device is provided, comprising:

[0030] A spatiotemporal matching module is configured to process the site data, the meteorological dataset, the terrain dataset, and the population data using a linear interpolation method to obtain preprocessed data, and perform spatiotemporal matching of the preprocessed data with MAICAAOD to obtain a modeling dataset;

[0031] The data construction module is configured to perform triangular irregular network interpolation on MAICAAOD to obtain full coverage AOD data and annual average AOD data;

[0032] The model inversion module is configured to construct a multi-layer LGBM model based on the full-coverage AOD data and the annual average AOD data, and perform multi-step simulation to correct the filling error to obtain an adjusted optimal prediction model; based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product with full coverage in the area.

[0033] According to a third technical solution of the present invention, a full-coverage daily-scale AOD inversion system is provided, the system comprising:

[0034] memory for storing computer programs;

[0035] A processor is configured to execute the computer program to implement the method described above.

[0036] According to a fourth technical solution of the present invention, a non-transitory computer-readable storage medium storing instructions is provided. When the instructions are executed by a processor, the method described above is executed.

[0037] The full-coverage daily-scale AOD inversion method, device, system, and storage medium according to various solutions of the present invention have at least the following technical effects:

[0038] This method can produce a daily-scale AOD product with full regional coverage. Verification shows that the restored results match the AERONET measured AOD at a 96.8% match rate, with an R ratio of 0.86 and an RMSE of 0.33. After restoration, MAICAAOD coverage has increased from approximately 40% daily coverage to 100% coverage, with good spatiotemporal continuity. Furthermore, the spatial distribution characteristics of the annual and monthly mean values ​​of the restored AOD product are consistent with those of the original MAICAAOD. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In the drawings, which are not necessarily drawn to scale, the same reference numerals may describe similar components in different views. The same reference numerals with letter suffixes or different letter suffixes may represent different instances of similar components. The accompanying drawings generally illustrate various embodiments by way of example and not limitation, and together with the description and claims, serve to illustrate the embodiments of the invention. Where appropriate, the same reference numerals are used throughout the drawings to refer to the same or similar parts. Such embodiments are illustrative and are not intended to be exhaustive or exclusive of the embodiments of the present apparatus or method.

[0040] Figure 1 A flowchart of a full coverage daily-scale AOD inversion method according to an embodiment of the present invention is shown;

[0041] Figure 2 A diagram showing the accuracy comparison results between the multi-layer LGBM model according to an embodiment of the present invention and the traditional model;

[0042] Figure 3 A monthly accuracy verification graph of a multi-layer LGBM model according to an embodiment of the present invention is shown;

[0043] Figure 4 It shows the time series distribution diagram of AOD products restored by the model according to an embodiment of the present invention in the target area and typical areas;

[0044] Figure 5 A structural diagram of a full-coverage daily-scale AOD inversion device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. The embodiments of the present invention are further described in detail below with reference to the accompanying drawings and specific embodiments, but are not intended to limit the present invention. For the various steps described herein, if there is no necessity for a contextual relationship between each other, the order in which they are described as examples herein should not be regarded as limiting, and those skilled in the art should know that they can be adjusted in order as long as the logic between them is not destroyed, resulting in the inability to implement the entire process.

[0046] The embodiment of the present invention provides a full coverage daily scale AOD inversion method, such as Figure 1 As shown, the method includes the following steps S10 to S40, which are described in detail below.

[0047] S1. Use linear interpolation method to process site data, meteorological data set, terrain data set and population data to obtain preprocessed data, and perform spatiotemporal matching between the preprocessed data and MAICAAOD to obtain a modeling data set.

[0048] In this embodiment, a linear interpolation method is used to process the station data, meteorological data set, terrain data set and population data, and these data are matched with MAICAAOD in time and space. Specifically, the present invention uses MAICAAOD data, station data, NDVI, DEM and population data.

[0049] The station data used is the 1.5 and 2.0 level data of the AERONET station version 3. AERONET uses a sun photometer to provide AOD spectral measurements with high time resolution (15 minutes) in the 0.34-1.06μm band. The network has three quality levels of data sets: level 1.0 (unscreened), level 1.5 (cloud screening), and level 2.0 (cloud screening and quality assurance). Among them, since the uncertainty of level 1.5 and level 2.0 in version 3 is lower, the level 1.5 and level 2.0 data are used as ground truth for accuracy verification. Since AERONET does not measure AOD at 550nm, the AERONET data is used. The index interpolates the two adjacent bands of 670nm and 440nm to obtain the AOD parameters at 550nm, so that it meets the consistency with MAIACAOD when comparing the accuracy.

[0050] The data were collected using the 500-meter spatial resolution global Normalized Difference Vegetation Index (NDVI) provided every 16 days by the MODIS MOD13A1 product; the 30-meter digital elevation model (DEM) data provided by the Shuttle Radar Topography Mission (SRTM); and the 1-kilometer LandScan population dataset developed by Oak Ridge National Laboratory (ORNL) and provided by East View Cartographic (https: / / landscan.ornl.gov / ).

[0051] The MAICAAOD data provided by NASA were used, with a temporal and spatial resolution of 1 day and 1 km × 1 km. Based on the quality assurance (QA) mark and valid AOD range provided by the MAICAAOD product, the data were cleaned (QAcloud_mask = clear) and AOD values ​​greater than 3 were excluded.

[0052] The station data, NDVI, DEM and population data were matched with the MAICAAOD data accuracy and used as the modeling dataset.

[0053] S2. Perform triangular irregular network interpolation on MAICAAOD to obtain preliminary full-coverage AOD data and annual average AOD data.

[0054] In this example, MAICAAOD data provided by NASA was obtained, with a temporal and spatial resolution of 1 day and 1 km × 1 km, respectively. Based on the quality assurance (QA) mark and valid AOD range provided by the MAICAAOD product, the data was cleaned (QAcloud_mask=clear), and AOD values ​​greater than 3 were excluded.

[0055] Using existing daily MAICAAOD data, we performed TIN interpolation on missing areas, leveraging existing spatial information for large-scale restoration, resulting in a sufficient daily AOD. TIN interpolation preserves the spatial information inherent in the daily AOD and also yields a more accurate annual mean AOD that reflects interannual AOD information, providing robust spatiotemporal information for model development.

[0056] S3. Based on the full coverage AOD data and the annual average AOD data, a multi-layer LGBM model is constructed, and multi-step simulation is performed to correct the filling error and obtain the adjusted optimal prediction model.

[0057] In this embodiment, the processed variable data are combined into a modeling dataset, and the matching dataset is modeled using a multi-layer LGBM model. Specifically, the model selected by the present invention is a multi-layer machine learning model. It is believed that the AOD levels at different scales reflect the different spatiotemporal variation characteristics of AOD. The AOD at the annual and seasonal scales reflects the overall trend of AOD over a whole year: the annual scale reflects the overall trend of AOD over a year, while the seasonal scale characterizes the fluctuations that AOD may produce during that year. The AOD at the monthly and weekly scales reflects the overall trend of AOD in a local time period: the monthly scale reflects the overall change in AOD in this time period, while the weekly scale reflects the random variation of AOD in this time period. The final daily AOD represents the dynamic change state of AOD every day. These are coupled and influence each other. Therefore, the accuracy of the results at each scale and the completeness of the spatiotemporal information extracted within the scale have a significant impact on the accuracy of AOD recovery. Therefore, based on this mechanism, the LGBM model is used to perform multi-step simulation to recover AOD on a large scale.

[0058] Due to the complex relationship between the temporal and spatial information of AOD, it is difficult to describe it with a single model. Therefore, based on the above mechanism, a multi-layer LGBM model was constructed: the first layer uses the initially obtained full-coverage AOD product and the annual average AOD as the main explanatory variables to fill in the seasonal mean value; the second layer uses the annual and seasonal AOD products as the main explanatory variables to calculate the monthly average AOD value; the third layer uses the annual, seasonal, and monthly AOD products to fill in the weekly AOD; and finally, using the annual, seasonal, monthly, and weekly AOD products as the main explanatory variables, the daily AOD is filled in on a large scale:

[0059]

[0060] Among them, AOD Daily (i, j) refers to the actual daily AOD level of the specified pixel (i, j); a series of explanatory variables include the multi-scale AOD spatiotemporal information and related auxiliary factors simulated by the previous layer LGBM. LGBM represents the last layer of the LGBM model; AOD Year (i, j) represents the preliminary obtained annual average AOD; AOD Quarterly (i, j) represents the seasonal average AOD obtained by the first-layer model; AOD Monthly (i, j) represents the monthly average AOD obtained by the second-layer model; AOD Weekly (i, j) represents the weekly AOD obtained by the third-layer model; NDVI (i, j) represents the normalized vegetation index value of the specified pixel point (i, j); DEM (i, j) represents the elevation value of the specified pixel point (i, j); POP (i, j) represents the population data of the specified pixel point (i, j).

[0061] Exemplarily, this embodiment evaluates the performance of the proposed model in two ways. First, the original MAICAAOD, the AOD after TIN filling, and the AOD restored by the MLL-MST model are evaluated with the ground AOD measured at the AERONET site. Secondly, the data restored by the model in the blank area of ​​the original MAICAAOD are evaluated with the AERONET site measurement data adjacent to the area. Thereafter, four statistical indicators including the correlation coefficient (R), the mean relative error (MRE), the root mean square error (RMSE), and the expected error (EE) envelope are used to evaluate the accuracy of the proposed method. Among them, according to the definition of the EE envelope, the proportion within the EE envelope is also calculated to evaluate the percentage of qualified data.

[0062]

[0063] EE=±(0.05+0.15×AOD)

[0064] AOD-EE≤AOD Sat ≤AOD+EE

[0065] Among them, AOD Aero is the AOD measured at the AERONET site. Sat represent the daily AOD products of original MAICAAOD, TIN-filled AOD, and model-restored AOD, respectively; and is the corresponding mean value; N is the number of matches between the restored daily AOD product and the ground-measured AOD.

[0066] from Figure 2 As can be seen, the multi-layer LGBM model achieves the best agreement with the AERONET measurements, with an R ratio of 0.90. Compared to the validation results using the original AOD, the full-coverage AOD performance degrades slightly, with MRE and RMSE improving by 0.004 and 0.003, respectively. However, it is clear that after the AOD is restored using the multi-layer LGBM model, the number of matching points increases to 8200, with a matching rate of 96.8%. Notably, the within EE ratio for the multi-layer LGBM model increases from 55% to 60%, while the above and below EE ratios decrease.

[0067] Based on the model validation, this example counted the data distribution of the original MAICAAOD, TIN MAICAAOD and multi-layer LGBM model AOD products in the study area and calculated the monthly average of the three products to verify the accuracy of the overall recovery results ( Figure 3). Overall, the performance trends of the three products are generally consistent, that is, they all show an upward trend from January to April, and a gradually downward trend from April to December. By comparing the lengths of the boxes, it can be found that the multi-layer LGBM model product can better restore the fluctuation level of AOD than the TIN model product, which improves the credibility of the product data. At the same time, by comparing the position differences of the horizontal lines in the boxes, it is found that the average level trend of MAICAAOD restored by the multi-layer LGBM model is more consistent with the original MAICAAOD. Moreover, the monthly average values ​​show the same phenomenon, that is, although the multi-layer LGBM model and the TIN model both show overestimation, this is also related to the filling of a large number of vacant values. However, the multi-layer LGBM model shows a mean level that is closer to the actual site than the TIN model, and does not show an excessively high overestimation level. Moreover, its change trend is more similar to the actual situation than TINAOD.

[0068] In the long-term change, the ability to fit the overall trend and the ability to capture local features are equally important in measuring the overall expressiveness of the dataset. The measured data from three AERONET stations in the target area were used to compare with the original MAICAAOD, TIN model AOD, and multi-layer LGBM model AOD products, and the AOD time series distribution map for 2023 was drawn ( Figure 4 ) to further evaluate the accuracy of the multi-layer LGBM model results. Overall, the changing trends of the AOD levels of the multi-layer LGBM model are not much different from the changing trends shown by the measured data at the stations, and can basically simulate the actual annual AOD level trend. At the same time, observing the fitting of the multi-layer LGBM model when the AOD is at low levels, it is found that the multi-layer LGBM model can sensitively capture local small fluctuations, which is approximately the same as the actual situation of AERONET, indicating the reliability of the model recovery results. However, for different stations, due to factors such as the quality of the original MAICAAOD data and the different AOD levels in the region, there are certain differences between the recovered AOD results. But overall, the AOD product restored by the multi-layer LGBM model shows better accuracy and reliability than the AOD restored by TIN, and has higher precision to support scientific research.

[0069] From a temporal perspective, the original MAICA AOD product's average temporal coverage in the target area in 2023 was 46.9%, or approximately 171 days. While temporal coverage was high in most northern regions, typically exceeding six months, in the south, it was lower, with some areas experiencing zero coverage. This limited its applicability in the southern region, necessitating an update to the MAICA AOD product to ensure its universal applicability and reliability. The improvement results show that both the TIN and multi-layer LGBM models significantly improved temporal coverage. Furthermore, both methods were able to achieve full coverage of the previously zero-coverage areas in the south, demonstrating the strong performance of both models in recovering the temporal characteristics of the data. However, since AOD inherently contains rich spatiotemporal information, measuring temporal completeness alone is insufficient to fully evaluate the AOD product. Therefore, spatial coverage and improvement effects were calculated. As can be seen, the spatial coverage of the original MAICA AOD product in the target area in 2023 was approximately 43.9%, reaching a maximum of 58.7% and a minimum of 24.6%. Compared with the original product, the full-coverage AOD product restored by the multi-layer LGBM model improved by an average of 127.5% in 2023, providing good data support for the application analysis of AOD on a daily scale.

[0070] S4. Based on the modeling data set, use the optimal prediction model to perform estimation to obtain a daily AOD product that covers the entire area.

[0071] In this embodiment, all modeling data are subjected to standard spatial gridding processing, and the established multi-layer LGBM model is used to restore the AOD values ​​of each day in the region to obtain a daily AOD product with full coverage in the region. Specifically, in order to better demonstrate the restoration results, the multi-layer LGBM model built by the present invention is used to restore the AOD of the target area. According to the comparison between the restored daily AOD product and the traditional model, it can be seen that this is a day with a low coverage of the original MAICAAOD product, only 26.8%. The areas it covers are mostly concentrated in the western region, and only a few cities have achieved full coverage, which has very large limitations on AOD research in hot spots and city scales. For the restored daily AOD products, both models have achieved the level of full coverage, and the changing trends in the areas covered by the original MAICAAOD product are generally consistent. Although the overall levels of the two models are not much different (the overall mean only differs by 0.01), the TIN model lacks more detailed expression compared to the multi-layer LGBM model. From the perspective of local recovery, although the magnitude of the eigenvalues ​​(maximum and mean) is not significantly different, the TIN smoothes out excessive detail, resulting in a more pronounced overestimation. Information at adjacent longitudes and latitudes within the region is highly similar, which does not reflect the actual AOD. The AOD product recovered using the multi-layer LGBM model retains the spatiotemporal characteristics of the original MAICAAOD product while leveraging AOD-related auxiliary variables to recover more random characteristics of the daily AOD.

[0072] To further investigate the reliability of the restored AOD product's spatiotemporal distribution over the target area, the restored AOD was compared with the original MAICAAOD's annual average distribution over the target area in 2023. The annual averages of the two products near the AERONET station in the target area were also calculated to analyze the consistency between the product and the station data.

[0073] According to the above comparison, we can conclude that: (1) The distribution effect of the AOD product restored by the multi-layer LGBM model is very consistent with the original MAICAAOD product. Both products show that the distribution in the east is higher than that in the west. And like the original MAICAAOD, the AOD product restored by the multi-layer LGBM model has a certain hierarchical gradient: it decreases from the southeast to the northwest, and at the same time, in some areas, the boundaries of high / low value areas are presented. This shows that the change trend of the original AOD has not been overly masked. The MLL-MST model can better retain the original spatiotemporal information while filling the original gaps, reflecting more realistic aerosol spatiotemporal distribution characteristics. (2) The phenomenon of a large number of missing AOD pixels is very common in the original MAICAAOD. Averaging the original MAICA AOD in the absence of sufficient AOD pixels will result in a lower annual average value of the original MAICAAOD (the average AOD value is 0.20). After filling the gaps, the mean of the AOD product restored by the multi-layer LGBM model only rose to 0.25. The deviation of 0.05 proves that the deviation of the multi-layer LGBM model is not large, which better avoids overestimation and can more accurately restore the missing AOD data. (3) Observing the annual mean effect near the AERONET station, both products show a high degree of consistency. Taking the ground monitoring data provided by the AERONET station as a reference, the AOD product restored by the multi-layer LGBM model shows a certain stability and accuracy in different geographical locations and meteorological conditions, which once again demonstrates the reliability of the restored product in estimating the true AOD.

[0074] Although the AOD product restored by the multi-layer LGBM model demonstrates excellent overall trend performance, AOD, as a key optical property of aerosols, is highly dynamic and stochastic, like aerosols, exhibiting significant temporal and spatial variability. Therefore, evaluating the accuracy of the AOD product restored by the multi-layer LGBM model solely on the overall annual trend is unreliable. Therefore, we compared the monthly cyclical variations before and after restoration to verify the performance of the multi-layer LGBM model in characterizing the dynamic and stochastic nature of AOD.

[0075] Overall, missing values ​​in the original MAICAAOD occur primarily in spring and winter, while both products are able to restore the integrity of the AOD well. The original MAICAAOD exhibits an overall trend of spring > winter > summer > autumn. The AOD product restored by the multi-layer LGBM model is also generally consistent with the original MAICAAOD. While there is some positive deviation, it is not particularly large. In detail, the multi-layer LGBM model is able to recover more local random features. The MLL-MST restored results not only preserve the distribution of the original data, broadly aligning with the variation trends of the original MAICAAOD, but also recover an AOD distribution with more dynamic layers and random gradients. Furthermore, a comparison of the statistical measures between the two products shows that the minimum deviation between the eigenvalues ​​of the multi-layer LGBM model and the original MAICAAOD results reaches 0.02, and the maximum is only 0.07, further verifying the reliability of the multi-layer LGBM model in recovering the dynamic random characteristics of the AOD product.

[0076] The embodiment of the present invention also provides a full coverage daily scale AOD inversion device, such as Figure 5 As shown, the device includes:

[0077] A spatiotemporal matching module is configured to process the site data, the meteorological dataset, the terrain dataset, and the population data using a linear interpolation method to obtain preprocessed data, and perform spatiotemporal matching of the preprocessed data with MAICAAOD to obtain a modeling dataset;

[0078] The data construction module is configured to perform triangular irregular network interpolation on MAICAAOD to obtain full coverage AOD data and annual average AOD data;

[0079] The model inversion module is configured to construct a multi-layer LGBM model based on the full-coverage AOD data and the annual average AOD data, and perform multi-step simulation to correct the filling error to obtain an adjusted optimal prediction model; based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product with full coverage in the area.

[0080] In some embodiments, the spatiotemporal matching module is further configured to:

[0081] Get site data using The index interpolates the two adjacent bands of 670nm and 440nm to obtain the AOD parameters at 550nm, so that the site data can meet the consistency with MAIAC AOD when comparing the accuracy;

[0082] Obtain NDVI data, DEM data, and population datasets;

[0083] The site data, NDVI data, DEM data, and population data were matched with the MAICAAOD data accuracy and used as the modeling dataset.

[0084] In some embodiments, the temporal and spatial resolutions of the NDVI data are 16 days and 250M respectively, the resolution of the DEM data is 30m, and the resolution of the population dataset is 1km.

[0085] In some embodiments, the data construction module is further configured to:

[0086] Get MAICAAOD;

[0087] According to the quality assurance mark and valid AOD range provided by the MAIAC AOD product, the MAIACAOD data was cleaned and AOD values ​​greater than 3 were excluded;

[0088] The existing daily MAICAAOD data are used to perform TIN interpolation on the missing areas in the MAIAC AOD so as to perform large-scale restoration using the existing spatial information, thereby obtaining the daily AOD with sufficient data volume.

[0089] In some embodiments, the temporal and spatial resolutions of the MAICAAOD are 1 d and 1 km×1 km, respectively.

[0090] In some embodiments, the model inversion module is further configured to:

[0091] A multi-layer LGBM model was constructed. In the multi-layer LGBM model, the first layer used the initially obtained full-coverage AOD product and the annual average AOD as the main explanatory variables to fill in the seasonal average value. The second layer used the annual and seasonal AOD products as explanatory variables to calculate the monthly average AOD value. The third layer used the annual, seasonal, and monthly AOD products to fill in the weekly AOD. The last layer used the annual, seasonal, monthly, and weekly AOD products as explanatory variables to fill in the daily AOD on a large scale. The calculation formula of the last layer is expressed as follows:

[0092]

[0093] Among them, AOD Daily (i, j) represents the actual daily AOD level of the specified pixel (i, j); LGBM represents the last layer of the LGBM model; AOD Year (i, j) represents the preliminary obtained annual average AOD; AOD Quarterly (i, j) represents the seasonal average AOD obtained by the first-layer model; AOD Monthly (i, j) represents the monthly average AOD obtained by the second-layer model; AOD Weekly(i, j) represents the weekly AOD obtained by the third-layer model; NDVI (i, j) represents the normalized vegetation index value of the specified pixel point (i, j); DEM (i, j) represents the elevation value of the specified pixel point (i, j); POP (i, j) represents the population data of the specified pixel point (i, j).

[0094] In some embodiments, the model inversion module is further configured to:

[0095] All modeling data are processed into standard spatial grids, and the optimal prediction model is used to restore the daily AOD values ​​in the area to obtain a daily AOD product that covers the entire area.

[0096] It should be noted that the modules involved in the embodiments of the present invention may be implemented in software or hardware, and the modules described may also be set in a processor. In some cases, the names of these modules do not constitute limitations on the modules themselves.

[0097] The aerosol optical thickness inversion device mentioned in the embodiment of the present invention belongs to the same technical concept as the method described previously, and the technical effects they achieve are basically the same, which will not be repeated here.

[0098] An embodiment of the present invention further provides an aerosol optical thickness inversion system, the system comprising:

[0099] memory for storing computer programs;

[0100] A processor is used to execute the computer program to implement the full coverage daily scale AOD inversion method of any embodiment of the present invention.

[0101] An embodiment of the present invention further provides a non-transitory computer-readable medium storing instructions, which, when executed by a processor, executes the full-coverage daily-scale AOD inversion method according to any embodiment of the present invention.

[0102] Furthermore, although exemplary embodiments have been described herein, the scope includes any and all embodiments based on the present invention having equivalent elements, modifications, omissions, combinations (e.g., schemes where various embodiments intersect), adaptations, or changes. The elements in the claims are to be interpreted broadly based on the language employed in the claims and are not limited to the examples described in this specification or during the prosecution of this application, which examples are to be interpreted as non-exclusive. Therefore, this specification and examples are intended to be considered as examples only, with the true scope and spirit being indicated by the following claims and the full scope of their equivalents.

[0103] The above description is intended to be illustrative rather than restrictive. For example, the above examples (or one or more of their solutions) can be used in combination with each other. For example, those of ordinary skill in the art may use other embodiments when reading the above description. In addition, in the above-mentioned specific embodiments, various features can be grouped together to simplify the present invention. This should not be interpreted as an intention that a feature of an invention that is not claimed for protection is necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of the embodiments of a particular invention. Thus, the following claims are incorporated into the specific embodiments as examples or embodiments, wherein each claim is independently a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or arrangements. The scope of the present invention should be determined with reference to the appended claims and the full scope of equivalents to which these claims are entitled.

Claims

1. A full coverage daily scale AOD inversion method, characterized by: The method comprises: The station data, meteorological data set, terrain data set and population data are processed using a linear interpolation method to obtain preprocessed data, and the preprocessed data is spatially and temporally matched with MAICAAOD to obtain a modeling data set; The MAICA AOD was interpolated using a triangular irregular network to obtain preliminary daily AOD data and annual average AOD data; Based on preliminary daily AOD data and annual average AOD data, a multi-layer LGBM model was constructed, and multi-step simulations were performed to correct the filling errors and obtain the adjusted optimal prediction model; Based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product with full coverage in the region; Based on preliminary daily AOD data and annual average AOD data, a multi-layer LGBM model was constructed and multi-step simulation was performed to correct the filling errors and obtain the adjusted optimal prediction model, including: A multi-layer LGBM model was constructed. In the multi-layer LGBM model, the first layer used the initially obtained full-coverage AOD product and the annual average AOD as the main explanatory variables to fill in the seasonal average value. The second layer used the annual and seasonal AOD products as explanatory variables to calculate the monthly average AOD value. The third layer used the annual, seasonal, and monthly AOD products to fill in the weekly AOD. The last layer used the annual, seasonal, monthly, and weekly AOD products as explanatory variables to fill in the daily AOD on a large scale. The calculation formula of the last layer is expressed as follows: Among them, AOD Daily (i, j) represents the actual daily AOD level of the specified pixel (i, j); LGBM represents the last layer of the LGBM model; AOD Year (i, j) represents the preliminary obtained annual average AOD; AOD Quarterly (i, j) represents the seasonal average AOD obtained by the first-layer model; AOD Monthly (i, j) represents the monthly average AOD obtained by the second-layer model; AOD Weekly (i, j) represents the weekly AOD obtained by the third-layer model; NDVI (i, j) represents the normalized vegetation index value of the specified pixel point (i, j); DEM (i, j) represents the elevation value of the specified pixel point (i, j); POP (i, j) represents the population data of the specified pixel point (i, j).

2. The full coverage daily scale AOD inversion method according to claim 1 is characterized in that: The station data, meteorological data set, terrain data set and population data are processed using a linear interpolation method to obtain preprocessed data. The preprocessed data is then spatially matched with the MAICA AOD to obtain a modeling data set, including: Get site data using The index interpolates the two adjacent bands of 670nm and 440nm to obtain the AOD parameters at 550nm, so that the site data meets the consistency with MAIACAOD when comparing the accuracy; Obtain NDVI data, DEM data, and population datasets; The site data, NDVI data, DEM data, and population data were matched with the MAICAAOD data accuracy and used as the modeling dataset.

3. The full coverage daily scale AOD inversion method according to claim 2, characterized in that: The temporal and spatial resolutions of the NDVI data are 16 days and 250M respectively, the resolution of the DEM data is 30m, and the resolution of the population dataset is 1km.

4. The full coverage daily scale AOD inversion method according to claim 1, characterized in that: The triangular irregular network interpolation of MAICAAOD is performed to obtain the full coverage AOD data and the annual average AOD data, including: Get MAICAAOD; According to the quality assurance mark and valid AOD range provided by the MAIACAOD product, the MAIACAOD data was cleaned and AOD values ​​greater than 3 were excluded; The existing daily MAICAAOD data are used to perform TIN interpolation on the missing areas in MAIACAOD to perform large-scale restoration using the existing spatial information, thereby obtaining a daily AOD with sufficient data volume.

5. The full coverage daily scale AOD inversion method according to claim 4 is characterized in that: The temporal and spatial resolutions of the MAICAAOD are 1 day and 1 km × 1 km, respectively.

6. The full coverage daily scale AOD inversion method according to claim 1, characterized in that: Based on the modeling data set, the optimal prediction model is used to estimate and obtain a daily AOD product with full coverage in the region, including: All modeling data are processed into standard spatial grids, and the optimal prediction model is used to restore the daily AOD values ​​in the area to obtain a daily AOD product that covers the entire area.

7. A full coverage daily scale AOD inversion device, characterized by: The device comprises: a spatiotemporal matching module configured to process the site data, the meteorological dataset, the terrain dataset, and the population data using a linear interpolation method to obtain preprocessed data, and to perform spatiotemporal matching of the preprocessed data with MAICAAOD to obtain a modeling dataset; The data construction module is configured to perform triangular irregular network interpolation on MAICAAOD to obtain full coverage AOD data and annual average AOD data; The model inversion module is configured to construct a multi-layer LGBM model based on the full coverage AOD data and the annual average AOD data, and perform multi-step simulation to correct the filling error to obtain an adjusted optimal prediction model; based on the modeling data set, the optimal prediction model is used to perform estimation to obtain a daily AOD product with full coverage in the area; The model inversion module is further configured to: A multi-layer LGBM model was constructed. In the multi-layer LGBM model, the first layer used the initially obtained full-coverage AOD product and the annual average AOD as the main explanatory variables to fill in the seasonal average value. The second layer used the annual and seasonal AOD products as explanatory variables to calculate the monthly average AOD value. The third layer used the annual, seasonal, and monthly AOD products to fill in the weekly AOD. The last layer used the annual, seasonal, monthly, and weekly AOD products as explanatory variables to fill in the daily AOD on a large scale. The calculation formula of the last layer is expressed as follows: Among them, AOD Daily (i, j) represents the actual daily AOD level of the specified pixel (i, j); LGBM represents the last layer of the LGBM model; AOD Year (i, j) represents the preliminary obtained annual average AOD; AOD Quarterly (i, j) represents the seasonal average AOD obtained by the first-layer model; AOD Monthly (i, j) represents the monthly average AOD obtained by the second-layer model; AOD Weekly (i, j) represents the weekly AOD obtained by the third-layer model; NDVI (i, j) represents the normalized vegetation index value of the specified pixel point (i, j); DEM (i, j) represents the elevation value of the specified pixel point (i, j); POP (i, j) represents the population data of the specified pixel point (i, j).

8. A full coverage daily scale AOD inversion system, characterized by: The system comprises: memory for storing computer programs; A processor, configured to execute the computer program to implement the full coverage daily-scale AOD inversion method according to any one of claims 1 to 6. 9 . A non-transitory computer-readable storage medium storing instructions, which, when executed by a processor, performs the full coverage daily-scale AOD inversion method according to claim 1 .

Images