Satellite cloud classification method, device, server and medium suitable for multiple scenarios

Abstract

The present invention provides a satellite cloud classification method, device, server, and medium applicable to multiple scenarios, relating to the field of data processing technology, including: receiving a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, the cloud classification request carrying an identifier of the specified cloud classification scenario and an identifier of the specified star source; determining the target cloud basic product data corresponding to the cloud classification request from a cloud basic product data set corresponding to multiple star sources obtained in advance based on the identifier of the specified cloud classification scenario and the identifier of the specified star source; calling a cloud classification algorithm corresponding to the specified cloud classification scenario based on the identifier of the specified cloud classification scenario, so as to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result. The present invention can alleviate the problem of the current cloud classification product having the limitation of a single application scenario, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a satellite cloud classification method, device, server and medium applicable to multiple scenarios. Background Art

[0002] Current cloud classification research based on satellite data typically uses the International Satellite Cloud Climatology Project (ISCCP) standard, which classifies clouds into nine categories based on their optical thickness and cloud top height: Cirrus, Cirrostratus, Deep Convection, Altocumulus, Altostratus, Nimbostratus, Cumulus, Stratocumulus, and Stratus. However, existing cloud classification results often fail to meet the needs of diverse application scenarios.

[0003] In practical applications, different industries or fields focus on different cloud characteristics. For example, in aviation and weapons launch, the focus is usually on cloud height, allowing for accurate assessments of flight safety and target impact. Therefore, cloud height classification becomes a primary task, with classifications such as high, medium, and low clouds. In weather forecasting, atmospheric chemistry, atmospheric composition research, and weather modification operations, cloud composition is a more important aspect. For example, clouds with different compositions, such as ice clouds and water clouds, have a significant impact on atmospheric properties. Furthermore, the aviation and energy industries may be more concerned with cloud shape. Because different cloud forms have different impacts on the generation and utilization of energy sources such as solar radiation and wind power, clouds need to be classified into different forms, such as layered clouds, heaped clouds, stratocumulus clouds, thin clouds, and rain clouds.

[0004] Therefore, the current cloud classification results have the limitation of single application scenarios and cannot meet the diverse needs of cloud features in different fields. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a satellite cloud classification method, device, server and medium suitable for multiple scenarios, so as to alleviate the problem of the limitation of current cloud classification products in single application scenarios, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

[0006] In a first aspect, the present invention provides a satellite cloud classification method applicable to multiple scenarios. The method is applied to a satellite cloud classification system, wherein the satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios. The method includes:

[0007] Receive a cloud classification request sent by a user for a specified cloud classification scenario and a specified satellite source, where the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified satellite source;

[0008] Based on the identifier of the specified cloud classification scenario and the identifier of the specified star source, the target cloud basic product data corresponding to the cloud classification request is determined from the cloud basic product data sets corresponding to multiple star sources obtained in advance;

[0009] Based on the identifier of the specified cloud classification scenario, the cloud classification algorithm corresponding to the specified cloud classification scenario is called to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result.

[0010] In one embodiment, before receiving a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, the method further includes:

[0011] Obtain satellite observation data and satellite cloud detection products from multiple star sources;

[0012] For any star source, obtain the numerical model data and static data corresponding to the satellite observation data of the star source, and perform preprocessing, quality control, time matching and normalization on the satellite observation data, satellite cloud detection products, numerical model data and static data of the star source to obtain the target satellite observation data, target satellite cloud detection products, target numerical model data and target static data corresponding to the star source;

[0013] Through the inversion model corresponding to the satellite source, based on the target satellite observation data, target satellite cloud detection products, target numerical model data and target static data, the cloud basic product dataset corresponding to the satellite source is inverted;

[0014] Among them, the cloud basic product data set includes target satellite observation data, target satellite cloud detection products, cloud optical thickness inversion products, cloud top pressure inversion products and cloud top temperature inversion products.

[0015] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on the ISCCP classification standard, and the cloud classifications in the cloud classification scenario include cirrus, cirrostratus, deep convection, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, and stratus;

[0016] Based on the identifier of the specified cloud classification scenario and the identifier of the specified star source, target cloud basic product data corresponding to the cloud classification request is determined from the cloud basic product datasets corresponding to the multiple star sources obtained in advance, including: extracting the cloud optical thickness inversion product and the cloud top pressure inversion product from the cloud basic product dataset corresponding to the specified star source as the target cloud basic product data corresponding to the cloud classification request;

[0017] The cloud classification algorithm corresponding to the specified cloud classification scenario is used to process the target cloud basic product data to obtain the cloud classification response result, including: comparing the cloud optical thickness inversion product and cloud top pressure inversion product in the target cloud basic product data with the threshold set in the pre-set ISCCP classification standard to obtain the cloud classification response result under the cloud classification scenario based on the ISCCP classification standard.

[0018] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud top height, and the cloud classification in the cloud classification scenario includes high clouds, medium clouds, low clouds, and straight clouds;

[0019] Based on the identifier of the specified cloud classification scenario and the identifier of the specified star source, target cloud basic product data corresponding to the cloud classification request is determined from the cloud basic product datasets corresponding to the multiple star sources obtained in advance, including: extracting target satellite observation data, cloud optical thickness inversion products, cloud top pressure inversion products, and cloud top temperature inversion products from the cloud basic product datasets corresponding to the specified star source as the target cloud basic product data corresponding to the cloud classification request;

[0020] The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain the cloud classification response result, including: comparing the cloud top pressure inversion product in the target cloud basic product data with the threshold values ​​corresponding to high clouds, middle clouds, and low clouds respectively, and comparing the brightness temperature data, cloud optical thickness inversion product, and cloud top temperature inversion product of the target satellite observation data in the target cloud basic product data with the threshold values ​​corresponding to straight-spread clouds, so as to obtain the cloud classification response result under the cloud classification scenario based on cloud top height.

[0021] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud components, wherein the cloud classifications in the cloud classification scenario include water clouds, ice clouds, mixed phase clouds, supercooled water clouds, deep convective clouds, precipitation clouds, aerosol and pollution clouds, and dust rolls;

[0022] Based on the identifier of the specified cloud classification scenario and the identifier of the specified star source, target cloud basic product data corresponding to the cloud classification request is determined from the cloud basic product datasets corresponding to the multiple star sources obtained in advance, including: extracting target satellite observation data, cloud optical thickness inversion products, and cloud top temperature inversion products from the cloud basic product datasets corresponding to the specified star source as the target cloud basic product data corresponding to the cloud classification request;

[0023] The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: performing radiation calibration and cloud mask processing on the target satellite observation data in the target cloud basic product data to obtain multi-band brightness temperature, and obtaining a first coarse classification result based on the difference between the brightness temperatures in different bands, the cloud optical thickness inversion product, and the cloud top temperature inversion product; and obtaining a second coarse classification result based on the target satellite observation data, the cloud optical thickness inversion product, and the cloud top temperature inversion product in the target cloud basic product data through a first neural network model; and correcting the first and second coarse classification results based on the classification rules that fuse spectral characteristics and microphysical parameters to obtain a cloud classification response result under a cloud classification scenario based on cloud composition.

[0024] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud shape, wherein the cloud classifications in the cloud classification scenario include layered clouds, heap clouds, stratocumulus clouds, thin clouds, and rain clouds;

[0025] Based on the identifier of the designated cloud classification scenario and the identifier of the designated satellite source, target cloud basic product data corresponding to the cloud classification request is determined from cloud basic product datasets corresponding to multiple satellite sources obtained in advance through inversion, including: extracting target satellite observation data from the cloud basic product dataset corresponding to the designated satellite source as the target cloud basic product data corresponding to the cloud classification request;

[0026] The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: extracting two-dimensional satellite images from the target satellite observation data within the target cloud basic product data, and stacking the two-dimensional satellite images of multiple consecutive time frames into three-dimensional data blocks; through a second neural network, generating a cloud classification response result in a cloud classification scenario based on cloud shape based on the three-dimensional data blocks.

[0027] In one embodiment, the cloud classification scenario includes a custom cloud classification scenario, and the method includes:

[0028] Receive a cloud classification definition request from a user to determine a custom cloud classification, and receive a cloud classification label annotation request from a user to determine a custom cloud classification label corresponding to the custom cloud classification;

[0029] Receive a cloud basic product data selection request sent by a user to determine the custom cloud basic product data from the cloud basic product data set corresponding to Star Source;

[0030] The third neural network is trained using the custom cloud basic product data, the custom cloud classification and its corresponding custom cloud classification labels, so as to generate cloud classification response results in the custom cloud classification scenario through the trained third neural network.

[0031] In a second aspect, the present invention further provides a satellite cloud classification device applicable to multiple scenarios. The device is applied to a satellite cloud classification system. The satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios. The device includes:

[0032] A request receiving module is used to receive a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, where the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified star source;

[0033] A data determination module is used to determine target cloud basic product data corresponding to the cloud classification request from cloud basic product data sets corresponding to multiple star sources obtained in advance based on the identifier of the specified cloud classification scenario and the identifier of the specified star source;

[0034] The cloud classification module is used to call the cloud classification algorithm corresponding to the specified cloud classification scenario based on the identifier of the specified cloud classification scenario, so as to use the cloud classification algorithm corresponding to the specified cloud classification scenario to process the target cloud basic product data to obtain a cloud classification response result.

[0035] In a third aspect, the present invention further provides a server comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0036] In a fourth aspect, the present invention further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0037] The present invention provides a satellite cloud classification method, device, server, and medium applicable to multiple scenarios. If a cloud classification request is received from a user for a specified cloud classification scenario and a specified star source, the target cloud basic product data corresponding to the cloud classification request is determined from the cloud basic product data sets corresponding to the multiple star sources obtained in advance based on the identifier of the specified cloud classification scenario and the identifier of the specified star source carried in the cloud classification request. Finally, the cloud classification algorithm corresponding to the specified cloud classification scenario is called based on the identifier of the specified cloud classification scenario, so as to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result. The above method uses cloud classification algorithms corresponding to multiple cloud classification scenarios and cloud basic product data sets corresponding to multiple star sources to generate cloud classification response results under multiple cloud classification scenarios, so as to alleviate the problem of the limitation of the current cloud classification products in the single application scenario, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

[0038] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or understood by practicing the present invention. The purposes and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A schematic diagram of a flow chart of a satellite cloud classification method applicable to multiple scenarios provided by an embodiment of the present invention;

[0042] Figure 2 An overall flow chart of a satellite cloud classification method applicable to multiple scenarios provided by an embodiment of the present invention;

[0043] Figure 3 A DNN model structure diagram provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of ISCCP cloud classification provided by an embodiment of the present invention;

[0045] Figure 5 A schematic structural diagram of a satellite cloud classification device applicable to multiple scenarios provided by an embodiment of the present invention;

[0046] Figure 6 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0048] At present, the current cloud classification results have the limitation of a single application scenario, which makes it difficult to meet the diverse needs of cloud features in different fields. Based on this, the present invention implements a satellite cloud classification method, device, server and medium suitable for multiple scenarios to alleviate the problem of the limitation of the current cloud classification products in a single application scenario, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

[0049] To facilitate understanding of this embodiment, a satellite cloud classification method applicable to multiple scenarios disclosed in an embodiment of the present invention is first introduced in detail. The method is applied to a satellite cloud classification system. The satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios. The multiple cloud classification scenarios include one or more of a cloud classification scenario based on the ISCCP classification standard, a cloud classification scenario based on cloud top height, a cloud classification scenario based on cloud composition, a cloud classification scenario based on cloud shape, and a custom cloud classification scenario. See Figure 1 The flowchart of a satellite cloud classification method applicable to multiple scenarios is shown in FIG. 1 , which mainly includes the following steps S102 to S106:

[0050] Step S102: receiving a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, wherein the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified star source.

[0051] In one example, the front end of the satellite cloud classification system displays multiple cloud classification scenarios and multiple star sources through a graphical user interface, responds to the user's selection operation for the cloud classification scenario to determine the specified cloud classification scenario, and responds to the user's selection operation for the star source to determine the specified star source, and then generates a cloud classification request based on the identification of the specified cloud classification scene and the identification of the specified star source.

[0052] Step S104 : Based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, target cloud basic product data corresponding to the cloud classification request is determined from cloud basic product data sets corresponding to multiple star sources obtained in advance through inversion.

[0053] In one example, the satellite cloud classification system monitors the satellite platform and timely obtains data from multiple star sources provided by the satellite platform, and then inverts multiple cloud basic product data based on the data to obtain cloud basic product data sets corresponding to multiple star sources. The cloud basic product data sets include target satellite observation data, target satellite cloud detection products, cloud optical thickness inversion products, cloud top pressure inversion products, and cloud top temperature inversion products.

[0054] In one example, different cloud classification scenarios require different cloud basic product data. Therefore, a mapping relationship between the identifiers of each cloud classification scenario and the type of cloud basic product data can be preconfigured. Based on this, the identifier of a specified star source is first used as a search condition to filter out the cloud basic product dataset corresponding to the specified star source from the cloud basic product datasets corresponding to multiple star sources. Then, the identifier of the specified cloud classification scenario is used as a search condition to filter out the target cloud basic product data from the cloud basic product dataset corresponding to the specified star source.

[0055] Step S106: Based on the identifier of the specified cloud classification scenario, a cloud classification algorithm corresponding to the specified cloud classification scenario is called to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result.

[0056] In one example, the data processing flow corresponding to each cloud classification scenario can be compiled into a cloud classification algorithm in advance. The cloud classification algorithm corresponding to the specified cloud classification scenario is used to process the target cloud basic product data to obtain the cloud classification response result under the specified cloud classification scenario. The cloud classification response result is used to characterize the cloud classification (also called cloud type) to which the pixel belongs.

[0057] For example, cloud classification scenarios based on the ISCCP classification standard include cirrus clouds, cirrostratus clouds, deep convection clouds, altocumulus clouds, altostratus clouds, nimbostratus clouds, cumulus clouds, stratocumulus clouds, and stratus clouds; cloud classification scenarios based on cloud top height include high clouds, middle clouds, low clouds, and straight-spreading clouds; cloud classification scenarios based on cloud composition include water clouds, ice clouds, mixed-phase clouds, supercooled water clouds, deep convective clouds, precipitation clouds, aerosol and pollution clouds, and dust rolls; cloud classification scenarios based on cloud shape include layered clouds, heap clouds, stratocumulus clouds, thin clouds, and rain clouds.

[0058] The satellite cloud classification method applicable to multiple scenarios provided by the embodiments of the present invention utilizes cloud classification algorithms corresponding to multiple cloud classification scenarios and generates cloud classification response results under multiple cloud classification scenarios based on cloud basic product datasets corresponding to multiple satellite sources. This alleviates the limitation of current cloud classification products in the single application scenario, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

[0059] For ease of understanding, the present invention provides a specific implementation of a satellite cloud classification method applicable to multiple scenarios, see Figure 2 The overall flow chart of a satellite cloud classification method applicable to multiple scenarios is shown, including:

[0060] (1) Satellite source selection:

[0061] To enhance autonomous and controllable capabilities, this embodiment utilizes the Fengyun series of satellites to classify cloud types. These include the operational Fengyun-4B, Fengyun-3D (an afternoon satellite, passing around 1:30 PM), and Fengyun-3F (a morning satellite, passing around 10:30 AM). Users can select one of the following satellite sources based on the area of ​​interest and desired frequency.

[0062] The Fengyun-4B (FY-4B) is a geostationary satellite located in a geosynchronous orbit approximately 36,000 kilometers above the equator. FY-4B's subsatellite coordinates are approximately 104.7° East longitude and 0° North latitude, close to the surface of China. This enables it to continuously monitor weather conditions in East Asia and the western Pacific. The FY-4B has the advantage of high frequency, completing a full-disk image every 15 minutes; however, its spatial resolution is relatively low, with its cloud products all having a resolution of 4 km. Therefore, cloud classification based on the FY-4B is applicable to a wide range of areas.

[0063] Fengyun-3D (FY-3D) and Fengyun-3F (FY-3F), two polar-orbiting meteorological satellites in the Fengyun-3 series, provide global observations in the afternoon and morning, respectively. They complement each other, providing all-weather, multi-layered atmospheric and climate data, offering strong technical support for meteorological services, climate research, and disaster warning systems. Through joint observations, the two satellites can provide cloud products with a temporal resolution of approximately six hours and a spatial resolution of up to 1 kilometer. This finer spatial scale than the FY-4B allows for higher-resolution cloud classification in smaller, focused areas.

[0064] The following cloud classification results are available for FY-3D, FY-3F, and FY-4B.

[0065] (2) Preparation and inversion of cloud-based products:

[0066] In one embodiment, the present invention provides a specific implementation of cloud-based product preparation and inversion, including:

[0067] (2.1) Obtain satellite observation data and satellite cloud detection products from multiple star sources.

[0068] The embodiment of the present invention considers classifying cloud types from different perspectives such as cloud temperature, height, composition, and shape. Before this, it is necessary to prepare cloud basic products in advance, including cloud detection, cloud top temperature, cloud top pressure, and cloud optical thickness, so that they can be added as characteristic factors to the cloud classification model.

[0069] The Fengyun Satellite Remote Sensing Data Service Network (https: / / satellite.nsmc.org.cn / ) provides the following data:

[0070] The L1-level observation data and L2-level cloud detection (CLM) products, cloud top temperature (CTT) products, and cloud top pressure (CTP) products of the AGRI sensor on the FY-4B satellite; the L1-level observation data and L2-level cloud detection (CLM) products of the MERSI sensor on the FY-3D satellite; and the L1-level observation data and L2-level cloud detection (CLM) products of the MERSI sensor on the FY-3F satellite.

[0071] The above data and products can be downloaded directly from the website for use. Figure 2 As shown, it is necessary to complete the inversion of cloud optical thickness (COT) products for the FY-4B satellite; and to complete the inversion of cloud top temperature (CTT), cloud top pressure (CTP) and cloud optical thickness (COT) products for the FY-3D and FY-3F satellites.

[0072] (2.2) For any satellite source, obtain the numerical model data and static data corresponding to the satellite observation data of the source, and perform preprocessing, quality control, time matching and normalization on the satellite observation data, satellite cloud detection products, numerical model data and static data of the source to obtain the target satellite observation data, target satellite cloud detection products, target numerical model data and target static data corresponding to the source;

[0073] (2.3) Using the inversion model corresponding to the satellite source, based on the target satellite observation data, target satellite cloud detection products, target numerical model data, and target static data, the cloud basic product dataset corresponding to the satellite source is inverted. The inversion model may include a deep neural network (DNN)-based cloud optical thickness inversion model, a deep neural network (DNN)-based cloud top temperature inversion model, and a deep neural network (DNN)-based cloud top pressure inversion model.

[0074] The embodiments of the present invention provide specific implementation methods for inversion of cloud optical thickness (COT), cloud top temperature (CTT), and cloud top pressure (CTP):

[0075] In one example, the process of retrieving cloud optical thickness (COT) is as follows:

[0076] Traditional physical models typically consider cloud reflectivity in the visible light band to be primarily related to the cloud optical thickness. In the near-infrared and mid-infrared bands, cloud reflectivity is primarily influenced by the effective cloud droplet radius. Therefore, radiative transfer models are used to jointly invert cloud optical thickness and effective cloud droplet radius based on dual-channel satellite observations. However, these radiative transfer models (such as RTTOV) treat both water and ice clouds as single-layer clouds and the atmosphere as a parallel atmosphere. However, in reality, most clouds are multi-layered, the atmosphere is approximately spherical, and the radiative transfer equation does not have a unique solution. These factors can lead to errors in simulation and calculation.

[0077] To address this issue, an embodiment of the present invention proposes using a machine learning model to directly learn and invert cloud optical thickness from input multi-band observation data. Machine learning models have advantages in processing complex inputs and nonlinear relationships, and can overcome the limitations of multiple assumptions in radiation transfer models. Satellite remote sensing data is large in volume and updated frequently. Deep neural networks have good scalability and can process large amounts of data through parallel computing. They are also highly efficient in the estimation process and are suitable for real-time applications. Therefore, an embodiment of the present invention proposes using a deep neural network (DNN) model to perform cloud optical thickness inversion.

[0078] The technical methods are as follows:

[0079] 1) Build a training sample library:

[0080] Since FY-4B, FY-3D, and FY-3F all require cloud optical thickness inversion, when the input satellite data is FY-4B, the corresponding true value is the sunflower-9 cloud optical thickness product; when the input satellite data is FY-3D or FY-3F, the corresponding true value is the MODIS cloud optical thickness product.

[0081] First, we collect multi-source data such as satellite observation data (including FY-4B, FY-3D, and FY-3F observation channel data and GEO data), satellite cloud detection products (including FY-4B, FY-3D, and FY-3F cloud detection products), numerical model data (including 2-meter atmospheric temperature T2m, relative humidity RH, surface air pressure SP, downwelling shortwave radiation DSWRF, total column water content TCW, 10-m U wind U10, 10-mV wind V10, total precipitation TP, atmospheric boundary layer height PBLH, vertical velocity VV, etc.), target cloud optical thickness products (H9COT, MODIS COT), and static data (including digital elevation model and surface cover type).

[0082] The data were then preprocessed, quality-controlled, time-matched, and normalized. Computer raster processing tools were used to analyze the multi-source data, perform projection conversion, spatial scale conversion, and temporal scale aggregation. This resulted in a grid dataset with uniform resolution (4 km for FY-4B COT inversion data and 1 km for FY-3D / FCOT inversion data) and uniform time scale (1 hour for FY-4B COT inversion data and 1 day for FY-3D / FCOT inversion data) in WGS84 and other latitude and longitude coordinate systems.

[0083] The main purpose of normalization is to unify the data into a certain range to achieve consistent iteration speed of gradient descent parameters, unify the range of each feature, make the iteration speed consistent, obtain the optimal solution at the same time, converge at the same time, reduce the number of iterations, and speed up the model.

[0084] The normalization method is mainly maximum and minimum value normalization, and its formula is:

[0085]

[0086] Among them, X nom is the normalized value, X is the original value, and X max and X min are the maximum and minimum values ​​of the original sequence respectively.

[0087] 2) DNN model training:

[0088] Deep neural network (DNN) is a technology in the field of machine learning. It is a neural network model for deep learning developed based on the perceptron. Figure 3 The following diagram shows a DNN model structure. Based on the location of different layers, the neural network layers within a DNN can be divided into: input layer, hidden layer, and output layer. Generally, the first layer is the input layer, the last layer is the output layer, and all layers in between are hidden layers. Layers are fully connected, meaning that any neuron in layer i is connected to any neuron in layer i+1.

[0089] Like other machine learning methods, the core idea of ​​DNN is to establish a stable nonlinear function between input variables and output based on multi-source auxiliary data. In the DNN used in the embodiment of the present invention, the output is H9 COT or MODISCOT, and the input is the channel visible light, near infrared, and long-wave infrared data of the pixel position (including 0.65um reflectivity data, 1.6um reflectivity data, 11um brightness temperature data), numerical model data (T2m, RH, SP, DSWRF, TCW, U10, V10, TP, PBLH, VV and other elements) and auxiliary data describing pixel feature information (including cloud detection products CLM, digital elevation model DEM, surface cover type LC, longitude and latitude Lat / lon, and number of days in the year DOY). Therefore, COT-DNN aims to establish the following relationship:

[0090] COT=f DNN (VIS 0.65 ,VIS 1.6 ,TB 11,T2m,RH,SP,DSWRF,TCW,U10,V10,TP,PBLH,VV,DEM,LC,Lat,Lon,DOY);

[0091] Here, DEM represents the influence of terrain, while Lat, Lon, and DOY represent the influence of three-dimensional data. In practice, the above-mentioned model can be used to invert cloud optical thickness for FY-4B, FY-3D, and FY-3F.

[0092] In one example, the process of cloud top temperature (CTT) and cloud top pressure (CTP) inversion is as follows:

[0093] The embodiment of the present invention requires the inversion of cloud top temperature and cloud top pressure for FY-3D and FY-3F. The Satellite Meteorological Center has not publicly provided the cloud top temperature and cloud top pressure products of FY-3D and FY-3F on its official website, but its public research has given the cloud top temperature and cloud top pressure products based on FY-3D. The MERSI-II cloud top product algorithm and accuracy test results, taking the MODIS cloud product as the true value, found that the FY-3D / MERSI-II water cloud cloud top temperature accuracy is -1.2±4.6K, the cloud top height accuracy is 1.4±1.8km, and the cloud top pressure accuracy is -140.9±114.5hPa; the thick ice cloud cloud top temperature accuracy is 7.0±6.0K, the cloud top height accuracy is -1.0±0.9km, and the cloud top pressure accuracy is 37.1±36.0hPa; the mixed cloud cloud top temperature accuracy is 1.5±8.5K, the cloud top height accuracy is 0.8±2.2km, and the cloud top pressure accuracy is -87.4±157.8hPa. The inversion deviation of single-layer cirrus clouds and multi-layer clouds is relatively large. Radiative transfer models play a critical role in the inversion of cloud top properties, but our current understanding of the properties of ice clouds, especially cirrus clouds, is insufficient. Therefore, how to accurately describe the radiation characteristics of ice crystals and improve the simulation accuracy of radiative transfer of ice clouds, especially cirrus clouds, will be the focus of the next step.

[0094] Considering that the physical method of using the radiation transfer model to invert cloud top products has limitations that have not yet been overcome, and that MODIS cloud products are currently the most recognized cloud products, including cloud top temperature and cloud top pressure, which can be downloaded from the official website for free, this embodiment of the present invention proposes using a machine learning method to construct a relationship model between the morning TerraMODIS cloud product MOD06 and the FY-3F MERSI-III observation data and auxiliary data, using the official MODIS cloud products as the true value; and to construct a relationship model between the afternoon AquaMODIS cloud product MYD06 and the FY-3D MERSI-II observation data and auxiliary data, to achieve the inversion of FY-3D and FY-3F cloud top temperature and cloud top pressure.

[0095] The machine learning model also chooses to use the deep neural network DNN model. The overall implementation technical ideas refer to the cloud optical thickness inversion and will not be repeated here.

[0096] (3) Cloud classification scenario selection:

[0097] The system comes with four pre-set cloud classification scenarios: Scenario 1: Classification based on the ISCCP classification standard; Scenario 2: Classification based on cloud top height; Scenario 3: Classification based on cloud composition; and Scenario 4: Classification based on cloud shape. Additionally, Scenario 5: Customized cloud classification allows users to customize cloud classification standards based on their needs.

[0098] Scenario 1: Cloud classification scenario based on the ISCCP classification standard:

[0099] From the cloud basic product dataset corresponding to the specified star source, the cloud optical thickness inversion product and the cloud top pressure inversion product are extracted as the target cloud basic product data corresponding to the cloud classification request; the cloud optical thickness inversion product and the cloud top pressure inversion product in the target cloud basic product data are compared with the threshold set in the pre-set ISCCP classification standard to obtain the cloud classification response result in the cloud classification scenario based on the ISCCP classification standard.

[0100] For details, see Figure 4 Figure 1 shows an ISCCP cloud classification diagram. The ISCCP cloud classification system categorizes clouds into nine types based on cloud top height and cloud optical thickness. It is currently the most widely used cloud classification standard for satellite remote sensing. Using cloud top pressure and cloud optical thickness products from the Fengyun series of satellites (FY-4B / FY-3D / FY-3F), clouds are classified according to this standard into nine types: cirrus, cirrostratus, deep convection, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, and stratus.

[0101] Scenario 2: Cloud classification based on cloud top height:

[0102] From the cloud basic product dataset corresponding to the specified star source, the target satellite observation data, cloud optical thickness inversion product, cloud top pressure inversion product and cloud top temperature inversion product are extracted as the target cloud basic product data corresponding to the cloud classification request; the cloud top pressure inversion product in the target cloud basic product data is compared with the threshold values ​​corresponding to high clouds, middle clouds and low clouds respectively, and the brightness temperature data, cloud optical thickness inversion product and cloud top temperature inversion product of the target satellite observation data in the target cloud basic product data are compared with the threshold values ​​corresponding to straight-spread clouds to obtain the cloud classification response results in the cloud classification scenario based on cloud top height.

[0103] Specifically, considering that air pressure and altitude are closely related in the atmosphere, cloud top pressure can reflect cloud top altitude. According to the ISCCP standard, based on the cloud top pressure product, clouds can be divided into three types: high clouds, medium clouds, and low clouds using the threshold method. The specific classification standard is as follows:

[0104] High cloud: CTP≤440hpa;

[0105] Medium cloud: 440hPa<CTP≤680hPa;

[0106] Low cloud: CTP>680hpa;

[0107] High clouds mean clouds are located at an altitude of about 6 kilometers or more, medium clouds are between 2 and 6 kilometers, and low clouds are usually below 2 kilometers.

[0108] In addition, some clouds with large vertical extents, such as Cumulonimbus (Cb), can have cloud tops extending from the lower layers to the upper layers, even into the stratosphere, potentially covering the range of high, mid, and low clouds. They have low cloud bases but thick cloud bodies, often accompanied by severe convective weather. These clouds are defined as straight-spread clouds. These large vertically extended clouds are not easily distinguished by cloud top pressure alone, so they are identified using a combination of multiple cloud parameters. The identification method is as follows:

[0109] Zhizhan Cloud: Among them, BT 11um This is the brightness temperature data of the 11um band.

[0110] Therefore, in this scenario, clouds are divided into four categories: high clouds, medium clouds, low clouds and straight clouds.

[0111] Scenario 3: Cloud classification based on cloud components:

[0112] Clouds are primarily composed of water droplets, ice crystals, and aerosols. Cloud classification not only helps us understand their physical properties and formation mechanisms but also has important implications for weather forecasting and climate research. Clouds are divided into eight categories based on their composition: water clouds, ice clouds, mixed-phase clouds, supercooled water clouds, deep convective clouds, precipitation clouds, aerosol and pollution clouds, and dust rolls.

[0113] Among them, water clouds are composed of liquid water droplets, usually appearing at lower altitudes, with higher cloud top temperatures and higher reflectivity; ice clouds are composed of ice crystals, usually appearing in the upper atmosphere, with lower cloud top temperatures and a strong scattering effect on the infrared band; mixed-phase clouds are usually below 0°C in temperature, but are not completely frozen, and contain supercooled water droplets and ice crystals, usually appearing in mesosphere clouds or in cumulonimbus clouds and other convective clouds; supercooled water clouds are composed of water droplets whose temperatures are below 0°C but still remain liquid, usually appearing in mountainous areas or in the middle and upper atmosphere, and supercooled water clouds pose a greater icing risk to aircraft; deep convective clouds usually contain a large number of liquid water droplets, supercooled water droplets and ice crystals, have strong vertical development, and the cloud tops can reach the stratosphere. The top temperature is extremely low and the cloud optical thickness is extremely large. Deep convective clouds are accompanied by weather phenomena such as heavy precipitation, thunderstorms, and hail. Precipitation clouds are mainly composed of liquid water droplets, supercooled water droplets, and ice crystals, and are usually accompanied by continuous precipitation. Their cloud top temperature is relatively high, but their optical thickness is large and their reflectivity is also high. Aerosol and pollution clouds are composed of aerosol particles, water droplets, and other pollutants suspended in the atmosphere. They are usually formed over urban areas or industrial areas. They have strong absorption of visible light and shortwave radiation, which often leads to a decrease in atmospheric transparency. Dust clouds contain a large number of sand and dust particles and are commonly found in desert areas or accompanied by sandstorms. Due to the presence of sand and dust, the cloud optical thickness increases, and the reflection of shortwave radiation is strong, and the scattering and absorption of infrared radiation are more significant.

[0114] This special report proposes a comprehensive cloud type identification method based on cloud composition, considering the characteristics of various cloud types in visible light, infrared, cloud optical thickness, and cloud top temperature. Specifically, the algorithm combines multi-band satellite data with machine learning methods, using band-to-band difference (BTD) methods, physical model inversion, and deep learning techniques to accurately classify different cloud types. By utilizing multi-band observation data from Fengyun satellites, the algorithm not only relies on simple threshold judgments but also incorporates comprehensive characteristics such as cloud optical thickness, cloud top temperature, and albedo, improving its ability to distinguish cloud types and its advanced nature.

[0115] The implementation methods are as follows:

[0116] a. Data input and processing:

[0117] From the cloud basic product dataset corresponding to the specified star source, the target satellite observation data, cloud optical thickness inversion product and cloud top temperature inversion product are extracted as the target cloud basic product data corresponding to the cloud classification request. The target satellite observation data in the target cloud basic product data are subjected to radiometric calibration and cloud mask processing to obtain the multi-band brightness temperature.

[0118] Specifically, we use multi-band data from FY-3D, FY-3F, and FY-4A satellites, including visible light, near-infrared, short-wave infrared, long-wave infrared, and microwave, to perform radiometric calibration and cloud mask processing on the data:

[0119] Visible light and near infrared: 0.55μm, 0.67μm, 0.87μm;

[0120] Shortwave infrared: 1.6μm, 2.2μm;

[0121] Long-wave infrared: 10.8μm, 11.2μm, 12.0μm;

[0122] Microwave: 6.9GHz, 10.7GHz.

[0123] b. Preliminary classification based on the inter-band difference method: Based on the difference between the brightness temperatures in different bands, the cloud optical thickness inversion product and the cloud top temperature inversion product, the first coarse classification result is obtained.

[0124] Specifically, the band-to-band difference (BTD) is used in combination with the cloud optical thickness (COT) and the cloud top temperature (CTT) to preliminarily distinguish water clouds, ice clouds, mixed phase clouds and supercooled water clouds.

[0125] Water cloud: BTD (11.2-12.0)>0, COT>20, CTT>0℃;

[0126] Ice cloud: BTD (10.8-11.2) < 0, COT < 10, CTT < -20℃;

[0127] Mixed phase cloud: BTD (10.8-11.2) ≈ 0, COT medium, CTT ≈ 0°C;

[0128] Supercooled water cloud: BTD (11.2-12.0)>0, CTT<0℃, mainly liquid water droplets.

[0129] c. Deep Learning Model Classification: A second coarse classification result is obtained using the first neural network model, which is a pre-trained convolutional neural network (CNN), based on target satellite observation data, cloud optical thickness inversion products, and cloud top temperature inversion products within the target cloud basic product data.

[0130] Specifically, a convolutional neural network (CNN) is used to identify the spatial structure and texture characteristics of clouds. The model inputs include multi-band brightness temperature differences, cloud optical thickness, cloud top temperature, and albedo. By training on samples of different cloud types in the dataset, the model automatically learns classification rules for complex cloud structures. This model is particularly suitable for complex cloud types such as deep convective clouds, dust rolls, and aerosol-contaminated clouds.

[0131] d. Classification rules based on spectral features and microphysical parameters: The first and second coarse classification results are corrected based on the classification rules based on spectral features and microphysical parameters to obtain the cloud classification response results in the cloud classification scenario based on cloud composition.

[0132] Specifically, for the detailed classification of various cloud types, the spectral characteristics of satellite observations, physical inversion parameters, and machine learning model output are integrated, and a multi-dimensional feature combination is used to make the final cloud classification judgment:

[0133] Deep convective clouds: COT>50, CTT<-50℃, strong vertical development, using the spatial structure information extracted by the CNN model combined with microwave channel data to distinguish deep convective clouds;

[0134] Precipitation clouds: BTD (10.8-11.2) ≈ 0, COT > 30, CTT > -10°C, heavy precipitation clouds with significant albedo and high water path, distinguished by microwave channels;

[0135] Cirrostratus: COT < 10, CTT < -20°C, using the convolutional layer of a deep learning model to identify the characteristics of thin clouds;

[0136] Aerosol and pollution cloud: Apparent reflectivity of satellite channel with central wavelength around 0.47 μm after removing the contribution of Rayleigh scattering of air molecules And the ratio of its apparent reflectivity to the satellite channel with a central wavelength of around 2.1 μm BTD (11.2-12.0)>0;

[0137] Dust roll: Daytime: VIS1.6 / VIS0.87>1, e ((BT12 -1.0) / BT10.8-1.0) >1, (BT12-BT10.8) / (BT12+BT10.8)+0.001>0; Night: e ((BT12 -1.0) / BT10.8-1.0) >1, (BT12-BT10.8) / (BT12+BT10.8)+0.001>0.

[0138] e. Output cloud classification products based on cloud components

[0139] After the above classification steps, a classification product containing eight cloud categories is generated and verified using observational data. Quantitative metrics (such as precision, recall, and F1 value) are used to evaluate the classification results.

[0140] Scenario 4: Cloud classification based on cloud shape:

[0141] The target satellite observation data is extracted from the cloud basic product dataset corresponding to the specified star source as the target cloud basic product data corresponding to the cloud classification request; two-dimensional satellite images are extracted from the target satellite observation data within the target cloud basic product data, and the two-dimensional satellite images of multiple consecutive time frames are stacked into three-dimensional data blocks; through the second neural network, cloud classification response results are generated in a cloud classification scenario based on cloud shape based on the three-dimensional data blocks.

[0142] Specifically, clouds are classified according to their shape because different cloud shapes are closely related to meteorological phenomena, weather forecasts, and climate change. Clouds of different shapes usually reflect different meteorological conditions and atmospheric stability. For example, layered clouds are usually associated with mild precipitation and stable weather systems, while heap clouds are often associated with unstable weather and heavy precipitation. Cirrus clouds are generally not accompanied by precipitation. Based on this, clouds are divided into five categories: layered clouds, heap clouds, stratocumulus clouds, thin clouds, and rain clouds. By classifying clouds by shape, meteorologists can help more accurately predict the weather, assess the risk of meteorological disasters, and provide important meteorological information for agriculture, shipping, and other industries. Therefore, this classification has practical application value.

[0143] Considering the multi-scale variation characteristics of clouds, such as space and time, especially rain clouds and stratus clouds, which have significant variation characteristics in the time dimension, a 3D convolutional network (3D-CNN) is used to extract the spatiotemporal characteristics of clouds, and then realize the classification of cloud types.

[0144] The implementation methods are as follows:

[0145] a. Data preprocessing:

[0146] Multi-temporal satellite imagery data for the same area is obtained from Fengyun satellites. For each time point, a 2D satellite image (height H and width W) of the corresponding area is extracted. T consecutive time frames are stacked to form a 3D data block. The input shape of each sample is (T, H, W, C), where C is the number of spectral channels (such as visible light, shortwave infrared, and longwave infrared). The training set is enhanced through rotation, flipping, and scaling techniques to improve the model's generalization capabilities. The image data is normalized to the range [0, 1] to accelerate the training process.

[0147] b.3D Convolutional Network Architecture:

[0148] Input layer: The input data shape is (T, H, W, C);

[0149] Convolution layer: Use convolution kernel size (k T ,k H ,k W ) with a 3D convolution kernel of shape (T′,H′,W′,N), where N is the number of output feature maps;

[0150]

[0151] Activation layer: Apply activation function (such as ReLU) to perform nonlinear transformation on the convolution result.

[0152] Pooling layer: Add a 3D max pooling layer to reduce the size of the feature map.

[0153]

[0154] Fully connected layer: The extracted features are flattened and connected to the fully connected layer.

[0155] Output layer: Use the softmax activation function to output the probability distribution of each cloud type.

[0156] c. Model training:

[0157] The entire dataset is divided into training set (70%), validation set (15%) and test set (15%) according to the proportion.

[0158] Training parameter settings: Batch size is set to 64; the initial learning rate is 0.001, and learning rate scheduling (such as ReduceLROnPlateau) is used; the maximum number of iterations (Epochs) is set to 100, and early stopping is used to monitor validation loss.

[0159] Training process;

[0160] Forward propagation:

[0161] Loss calculation:

[0162] Backward Propagation:

[0163] At the end of each epoch, the model performance is evaluated using the validation set, and the validation loss and accuracy are recorded.

[0164] d. Model evaluation:

[0165] Test set evaluation: Load the model weights that perform best on the validation set, use the test set to make predictions, and obtain the performance of the model on unseen data.

[0166]

[0167] Evaluation indicator calculation:

[0168] Accuracy:

[0169] Accuracy:

[0170] Recall:

[0171] F1-score:

[0172] The trained model is applied to real-time cloud image data to classify cloud types.

[0173] Scenario 5: Customized cloud classification scenario:

[0174] Create a custom cloud classification tool. Users can define the name of the output cloud type in the front-end interactive interface and draw samples of each type of cloud by themselves. Using a deep learning model, considering multiple factors (such as CLM, CTT, CTP, COT, etc.) as variables, the corresponding cloud classification is output according to the sample definition, realizing the production of custom cloud classification products.

[0175] The implementation methods are as follows:

[0176] a. Front-end user interface design, including: receiving cloud classification definition requests sent by users to determine custom cloud classifications, receiving cloud classification label annotation requests sent by users to determine custom cloud classification labels corresponding to custom cloud classifications, and receiving cloud basic product data selection requests sent by users to determine custom cloud basic product data from the cloud basic product data set corresponding to Star Source.

[0177] The details are as follows:

[0178] Cloud type definition: Users can enter a custom cloud type name, multiple types are supported, and a drop-down list is provided to select existing cloud types (such as cumulus, stratus, etc.).

[0179] Sample Outlining: This feature allows users to upload satellite imagery and outline samples using visualization tools (e.g., rectangle selection tool, polygon drawing tool). A sample label input box allows users to enter cloud type labels for the outlined samples.

[0180] Factor selection: Multiple factor options are provided (such as satellite channels, CLM, CTT, COT, CTP, etc.), and users can select the required factors as model input.

[0181] Users can start model training and monitor its progress. One-click inference allows users to input new data into the model for cloud classification.

[0182] b. Data processing and feature extraction:

[0183] Data collection: Acquire Fengyun satellite data (such as FY-3D, FY-3F, FY-4B) and extract user-selected factor data (such as CLM, CTT, CTP, COT, etc.).

[0184] Sample preparation: Generate training sets, validation sets, and test sets based on the sample areas and labels defined by the user.

[0185] c. Deep Learning Model Construction: Utilizing custom cloud basic product data, custom cloud classifications, and their corresponding custom cloud classification labels, the third neural network is trained to generate cloud classification response results for custom cloud classification scenarios. Specifically, a convolutional neural network or a 3D convolutional network (3D-CNN) is used to extract temporal and spatial features. 3D-CNN requires time series data. The model construction, training, and evaluation methods have been mentioned in scenarios three and four and will not be repeated here.

[0186] d. Output cloud classification results: Output cloud classification results, including model performance indicators, and generate visual thematic maps to demonstrate cloud classification effects.

[0187] (4) Automatically generate cloud classification reports:

[0188] For the cloud classification response results of any of the above scenarios, a cloud classification result report is automatically generated. The report includes a thematic map of the cloud classification results, the area and proportion of each type of cloud. If a machine learning or deep learning model is used for cloud classification, the report also includes the model evaluation results, showing the classification accuracy, confusion matrix, etc., clearly demonstrating the performance of the model in each category.

[0189] In summary, the purpose of the present invention is to construct a multi-source satellite cloud classification method and device applicable to multiple scenarios to solve the problems and defects of current cloud classification products. In view of the fact that the cloud classification results in the existing technology are fixed and cannot meet the needs of different application scenarios, the embodiment of the present invention aims to design a flexible and multifunctional cloud classification method, which can accurately identify and classify the characteristics of the cloud such as height, composition and morphology based on multi-source satellite data according to the needs of different industries or fields, and realize dynamic monitoring and tracking of cloud characteristics to adapt to the changes in clouds in different regions, different seasons and different weather conditions. In addition, the embodiment of the present invention is entirely based on the domestically produced Fengyun series satellites, combining the advantages of the high frequency of the Fengyun-4 geostationary meteorological satellite with the advantages of the higher spatial resolution of the Fengyun-3 polar-orbiting meteorological satellite, breaking the monopoly of foreign technology, and enhancing the independent capabilities in the field of cloud classification and remote sensing monitoring, especially in responding to emergencies and natural disasters, to enhance the emergency response capabilities of satellite remote sensing data. The satellite cloud classification method applicable to multiple scenarios provided by the embodiment of the present invention has at least the following characteristics:

[0190] (1) Flexible adaptation to various application scenarios:

[0191] The embodiments of this invention utilize a flexible cloud classification method and device design, enabling customization of cloud classification to meet the needs of various industries and applications, achieving adaptability to diverse application scenarios. This method can accurately identify cloud height, composition, and morphology as required, meeting the specialized needs of various fields, including agriculture, weather forecasting, and environmental monitoring.

[0192] (2) Dynamically monitor changes in cloud characteristics:

[0193] Utilizing multi-source Fengyun satellite data, the present invention enables dynamic cloud monitoring and tracking, accurately characterizing cloud characteristics over time and space. Combining the high-frequency observations of the Fengyun-4 geostationary meteorological satellite and the high spatial resolution of the Fengyun-3 polar-orbiting satellite, the system can address cloud variations in different regions, seasons, and weather conditions, effectively improving the accuracy of capturing changes in cloud characteristics.

[0194] (3) Improving emergency response capabilities:

[0195] This method, fully leveraging data from the domestically produced Fengyun series of satellites, enables rapid response to sudden meteorological events and natural disasters, enhancing the emergency application capabilities of satellite remote sensing data. In extreme weather conditions such as typhoons and heavy rains, the device can quickly and accurately provide cloud data, providing timely support for disaster warning and emergency response.

[0196] (4) Enhance independent innovation and break dependence on foreign technology:

[0197] By fully leveraging domestic satellite data resources, this embodiment of the present invention breaks reliance on foreign technology and enhances independent innovation capabilities in cloud classification and remote sensing monitoring. Furthermore, leveraging the unique advantages of Fengyun satellite data, this device ensures high-precision and timely cloud classification, supporting a stronger voice in international remote sensing technology.

[0198] Based on the above embodiments, the present invention provides an implementation of a satellite cloud classification device applicable to multiple scenarios. The device is applied to a satellite cloud classification system. The satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios. Figure 5 The structure diagram of a satellite cloud classification device suitable for multiple scenarios is shown in FIG. The device mainly includes the following parts:

[0199] The request receiving module 502 is configured to receive a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, wherein the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified star source;

[0200] The data determination module 504 is configured to determine target cloud basic product data corresponding to the cloud classification request from cloud basic product data sets corresponding to multiple star sources obtained in advance based on the identifier of the specified cloud classification scenario and the identifier of the specified star source;

[0201] The cloud classification module 506 is used to call the cloud classification algorithm corresponding to the specified cloud classification scenario based on the identifier of the specified cloud classification scenario, so as to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result.

[0202] The satellite cloud classification device applicable to multiple scenarios provided by the embodiment of the present invention utilizes cloud classification algorithms corresponding to multiple cloud classification scenarios and generates cloud classification response results under multiple cloud classification scenarios based on cloud basic product data sets corresponding to multiple satellite sources, so as to alleviate the limitation of the current cloud classification products in the single application scenario, thereby meeting the needs of different industries or fields for accurate identification and quantitative analysis of cloud features.

[0203] In one embodiment, the system further includes a data processing module for:

[0204] Obtain satellite observation data and satellite cloud detection products from multiple star sources;

[0205] For any star source, obtain the numerical model data and static data corresponding to the satellite observation data of the star source, and perform preprocessing, quality control, time matching and normalization on the satellite observation data, satellite cloud detection products, numerical model data and static data of the star source to obtain the target satellite observation data, target satellite cloud detection products, target numerical model data and target static data corresponding to the star source;

[0206] Through the inversion model corresponding to the satellite source, based on the target satellite observation data, target satellite cloud detection products, target numerical model data and target static data, the cloud basic product dataset corresponding to the satellite source is inverted;

[0207] Among them, the cloud basic product data set includes target satellite observation data, target satellite cloud detection products, cloud optical thickness inversion products, cloud top pressure inversion products and cloud top temperature inversion products.

[0208] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on the ISCCP classification standard, and the cloud classifications in the cloud classification scenario include cirrus, cirrostratus, deep convection, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, and stratus;

[0209] The data determination module 504 is specifically configured to extract cloud optical thickness inversion products and cloud top pressure inversion products from the cloud basic product dataset corresponding to the specified star source as target cloud basic product data corresponding to the cloud classification request;

[0210] The cloud classification module 506 is specifically used to compare the cloud optical thickness inversion product and the cloud top pressure inversion product in the target cloud basic product data with the thresholds set in the pre-set ISCCP classification standard to obtain the cloud classification response results in the cloud classification scenario based on the ISCCP classification standard.

[0211] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud top height, and the cloud classification in the cloud classification scenario includes high clouds, medium clouds, low clouds, and straight clouds;

[0212] The data determination module 504 is specifically configured to extract target satellite observation data, cloud optical thickness inversion products, cloud top pressure inversion products, and cloud top temperature inversion products from the cloud basic product dataset corresponding to the specified star source as target cloud basic product data corresponding to the cloud classification request;

[0213] The cloud classification module 506 is specifically used to compare the cloud top pressure inversion product in the target cloud basic product data with the threshold values ​​corresponding to high clouds, middle clouds and low clouds respectively, and to compare the brightness temperature data, cloud optical thickness inversion product and cloud top temperature inversion product of the target satellite observation data in the target cloud basic product data with the threshold values ​​corresponding to straight-spread clouds, so as to obtain the cloud classification response results in the cloud classification scenario based on cloud top height.

[0214] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud components, wherein the cloud classifications in the cloud classification scenario include water clouds, ice clouds, mixed phase clouds, supercooled water clouds, deep convective clouds, precipitation clouds, aerosol and pollution clouds, and dust rolls;

[0215] The data determination module 504 is specifically configured to extract target satellite observation data, cloud optical thickness inversion products, and cloud top temperature inversion products from the cloud basic product dataset corresponding to the specified star source as target cloud basic product data corresponding to the cloud classification request;

[0216] The cloud classification module 506 is specifically used to: perform radiometric calibration and cloud mask processing on the target satellite observation data in the target cloud basic product data to obtain multi-band brightness temperature, and obtain a first coarse classification result based on the difference between the brightness temperatures in different bands, the cloud optical thickness inversion product, and the cloud top temperature inversion product; and obtain a second coarse classification result based on the target satellite observation data, the cloud optical thickness inversion product, and the cloud top temperature inversion product in the target cloud basic product data through a first neural network model; and correct the first coarse classification result and the second coarse classification result based on the classification rules of the fusion spectral characteristics and microphysical parameters to obtain a cloud classification response result in a cloud classification scenario based on cloud composition.

[0217] In one embodiment, the cloud classification scenario includes a cloud classification scenario based on cloud shape, wherein the cloud classifications in the cloud classification scenario include layered clouds, heap clouds, stratocumulus clouds, thin clouds, and rain clouds;

[0218] The data determination module 504 is specifically configured to extract target satellite observation data from the cloud basic product data set corresponding to the specified satellite source as target cloud basic product data corresponding to the cloud classification request;

[0219] The cloud classification module 506 is specifically used to: extract two-dimensional satellite images from the target satellite observation data within the target cloud basic product data, and stack the two-dimensional satellite images of multiple consecutive time frames into three-dimensional data blocks; through a second neural network, generate cloud classification response results in a cloud classification scenario based on cloud shape based on the three-dimensional data blocks.

[0220] In one embodiment, the cloud classification scenario includes a custom cloud classification scenario and also includes a custom module for:

[0221] Receive a cloud classification definition request from a user to determine a custom cloud classification, and receive a cloud classification label annotation request from a user to determine a custom cloud classification label corresponding to the custom cloud classification;

[0222] Receive a cloud basic product data selection request sent by a user to determine the custom cloud basic product data from the cloud basic product data set corresponding to Star Source;

[0223] The third neural network is trained using the custom cloud basic product data, the custom cloud classification and its corresponding custom cloud classification labels, so as to generate cloud classification response results in the custom cloud classification scenario through the trained third neural network.

[0224] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment.

[0225] An embodiment of the present invention provides a server. Specifically, the server includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0226] Figure 6 A structural diagram of a server provided in an embodiment of the present invention, wherein the server 100 includes: a processor 60, a memory 61, a bus 62 and a communication interface 63, wherein the processor 60, the communication interface 63 and the memory 61 are connected via the bus 62; the processor 60 is used to execute an executable module stored in the memory 61, such as a computer program.

[0227] The memory 61 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 63 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0228] The bus 62 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0229] Among them, the memory 61 is used to store programs, and the processor 60 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 60 or implemented by the processor 60.

[0230] The processor 60 may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method may be performed by hardware integrated logic circuits or software instructions within the processor 60. The processor 60 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the present invention may be directly executed by a hardware decoding processor or by a combination of hardware and software modules within the decoding processor. The software modules may be located in storage media well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or the like. The storage medium is located in the memory 61 , and the processor 60 reads the information in the memory 61 and completes the steps of the above method in combination with its hardware.

[0231] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be referred to the previous method embodiment and will not be repeated here.

[0232] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0233] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A satellite cloud classification method applicable to multiple scenarios, characterized in that: The method is applied to a satellite cloud classification system, wherein the satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios, and the method includes: receiving a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, wherein the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified star source; Based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, determining target cloud basic product data corresponding to the cloud classification request from cloud basic product data sets corresponding to multiple star sources obtained in advance by inversion; Invoking the cloud classification algorithm corresponding to the specified cloud classification scenario based on the identifier of the specified cloud classification scenario, so as to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result; Before receiving a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, the method further includes: Obtain satellite observation data and satellite cloud detection products from multiple star sources; For any of the star sources, obtain numerical model data and static data corresponding to the satellite observation data of the star source, and perform preprocessing, quality control, time matching, and normalization on the satellite observation data, the satellite cloud detection product, the numerical model data, and the static data of the star source to obtain the target satellite observation data, target satellite cloud detection product, target numerical model data, and target static data corresponding to the star source; Using the inversion model corresponding to the star source, based on the target satellite observation data, the target satellite cloud detection product, the target numerical model data, and the target static data, the cloud basic product dataset corresponding to the star source is inverted; Among them, the cloud basic product dataset includes the target satellite observation data, the target satellite cloud detection product, cloud optical thickness inversion product, cloud top pressure inversion product and cloud top temperature inversion product.

2. The satellite cloud classification method applicable to multiple scenarios according to claim 1, characterized in that: The cloud classification scenario includes a cloud classification scenario based on the ISCCP classification standard, and the cloud classifications in the cloud classification scenario include cirrus, cirrostratus, deep convection, altocumulus, altostratus, nimbostratus, cumulus, stratocumulus, and stratus; Based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, determining target cloud basic product data corresponding to the cloud classification request from cloud basic product datasets corresponding to multiple star sources obtained in advance through inversion, including: extracting the cloud optical thickness inversion product and the cloud top pressure inversion product from the cloud basic product dataset corresponding to the designated star source as the target cloud basic product data corresponding to the cloud classification request; The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: comparing the cloud optical thickness inversion product and the cloud top pressure inversion product in the target cloud basic product data with thresholds set in a preset ISCCP classification standard to obtain a cloud classification response result under a cloud classification scenario based on the ISCCP classification standard.

3. The satellite cloud classification method applicable to multiple scenarios according to claim 1, characterized in that: The cloud classification scenario includes a cloud classification scenario based on cloud top height, and the cloud classifications in the cloud classification scenario include high clouds, medium clouds, low clouds, and straight clouds; Based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, determining target cloud basic product data corresponding to the cloud classification request from cloud basic product datasets corresponding to multiple star sources obtained in advance through inversion, including: extracting the target satellite observation data, the cloud optical thickness inversion product, the cloud top pressure inversion product, and the cloud top temperature inversion product from the cloud basic product dataset corresponding to the designated star source as the target cloud basic product data corresponding to the cloud classification request; The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: comparing the cloud top pressure inversion product in the target cloud basic product data with the threshold values ​​corresponding to the high clouds, the middle clouds, and the low clouds, respectively; and comparing the brightness temperature data of the target satellite observation data, the cloud optical thickness inversion product, and the cloud top temperature inversion product in the target cloud basic product data with the threshold values ​​corresponding to the straight-spread clouds, so as to obtain a cloud classification response result under a cloud classification scenario based on cloud top height.

4. The satellite cloud classification method applicable to multiple scenarios according to claim 1, characterized in that: The cloud classification scenario includes a cloud classification scenario based on cloud components, and the cloud classifications in this cloud classification scenario include water clouds, ice clouds, mixed phase clouds, supercooled water clouds, deep convective clouds, precipitation clouds, aerosol and pollution clouds, and dust rolls; Based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, determining target cloud basic product data corresponding to the cloud classification request from cloud basic product datasets corresponding to multiple star sources obtained in advance through inversion, including: extracting the target satellite observation data, the cloud optical thickness inversion product, and the cloud top temperature inversion product from the cloud basic product dataset corresponding to the designated star source as the target cloud basic product data corresponding to the cloud classification request; The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: performing radiometric calibration and cloud mask processing on the target satellite observation data in the target cloud basic product data to obtain multi-band brightness temperature, and obtaining a first coarse classification result based on the difference between the brightness temperatures in different bands, the cloud optical thickness inversion product, and the cloud top temperature inversion product; and obtaining a second coarse classification result based on the target satellite observation data, the cloud optical thickness inversion product, and the cloud top temperature inversion product in the target cloud basic product data through a first neural network model; and correcting the first coarse classification result and the second coarse classification result based on a classification rule that integrates spectral features and microphysical parameters to obtain a cloud classification response result in a cloud classification scenario based on cloud composition.

5. The satellite cloud classification method applicable to multiple scenarios according to claim 1, characterized in that: The cloud classification scenario includes a cloud classification scenario based on cloud shape, and the cloud classifications in the cloud classification scenario include layered clouds, heap clouds, stratocumulus clouds, thin clouds and rain clouds; Determining target cloud basic product data corresponding to the cloud classification request from cloud basic product datasets corresponding to multiple star sources obtained in advance based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, including: extracting the target satellite observation data from the cloud basic product dataset corresponding to the designated star source as the target cloud basic product data corresponding to the cloud classification request; The target cloud basic product data is processed using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result, including: extracting two-dimensional satellite images from the target satellite observation data within the target cloud basic product data, and stacking the two-dimensional satellite images of multiple consecutive time frames into a three-dimensional data block; and generating a cloud classification response result in a cloud classification scenario based on cloud shape based on the three-dimensional data block through a second neural network.

6. The satellite cloud classification method applicable to multiple scenarios according to claim 1, characterized in that: The cloud classification scenario includes a custom cloud classification scenario, and the method includes: receiving a cloud classification definition request sent by the user to determine a custom cloud classification, and receiving a cloud classification tag annotation request sent by the user to determine a custom cloud classification tag corresponding to the custom cloud classification; receiving a cloud basic product data selection request sent by the user to determine customized cloud basic product data from the cloud basic product data set corresponding to the star source; The third neural network is trained using the custom cloud basic product data, the custom cloud classification and its corresponding custom cloud classification label, so as to generate a cloud classification response result in a custom cloud classification scenario through the trained third neural network.

7. A satellite cloud classification device suitable for multiple scenarios, characterized in that: The device is applied to a satellite cloud classification system, wherein the satellite cloud classification system is configured with cloud classification algorithms corresponding to multiple cloud classification scenarios, and the device includes: a request receiving module, configured to receive a cloud classification request sent by a user for a specified cloud classification scenario and a specified star source, wherein the cloud classification request carries an identifier of the specified cloud classification scenario and an identifier of the specified star source; a data determination module, configured to determine, based on the identifier of the designated cloud classification scenario and the identifier of the designated star source, target cloud basic product data corresponding to the cloud classification request from cloud basic product data sets corresponding to multiple star sources obtained in advance by inversion; a cloud classification module, configured to call the cloud classification algorithm corresponding to the specified cloud classification scenario based on the identifier of the specified cloud classification scenario, so as to process the target cloud basic product data using the cloud classification algorithm corresponding to the specified cloud classification scenario to obtain a cloud classification response result; It also includes a data processing module for: Obtain satellite observation data and satellite cloud detection products from multiple star sources; For any of the star sources, obtain numerical model data and static data corresponding to the satellite observation data of the star source, and perform preprocessing, quality control, time matching, and normalization on the satellite observation data, the satellite cloud detection product, the numerical model data, and the static data of the star source to obtain the target satellite observation data, target satellite cloud detection product, target numerical model data, and target static data corresponding to the star source; Using the inversion model corresponding to the star source, based on the target satellite observation data, the target satellite cloud detection product, the target numerical model data, and the target static data, the cloud basic product dataset corresponding to the star source is inverted; Among them, the cloud basic product dataset includes the target satellite observation data, the target satellite cloud detection product, cloud optical thickness inversion product, cloud top pressure inversion product and cloud top temperature inversion product.

8. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 6.

Images