Cloud computing method for surface sand risk based on surface ecology and meteorological state

Abstract

The application provides a cloud computing method for surface sand-raising risk based on surface ecology and meteorological state, which comprises the following steps: constructing a multi-factor coupled surface sand-raising risk index model in advance; container mirroring the multi-factor coupled surface sand-raising risk index model and deploying it on a cloud computing platform; collecting container index data and local surface sand-raising risk prediction request characteristic data in response to a local surface sand-raising risk prediction request; calculating a container and local surface sand-raising risk prediction request matching value according to the container index data and the local surface sand-raising risk prediction request characteristic data; and selecting a container with the largest matching value for the local surface sand-raising risk prediction request in the cloud to process the local surface sand-raising risk prediction request. The cloud computing method for surface sand-raising risk based on surface ecology and meteorological state realizes sand-raising risk prediction in the cloud and rapid evaluation of sand-raising risk in a large range and high-concurrency area.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a cloud computing method for assessing the risk of surface sandstorms based on surface ecology and meteorological conditions. Background Technology

[0002] Dust storms are significant natural disasters affecting air quality, traffic safety, and human health. Traditional dust storm models (RWEQ, WEPS, DPM) typically operate offline, requiring manual downloading of terabytes of remote sensing / meteorological data, local interpolation, and format conversion, resulting in long processing times and poor timeliness.

[0003] Existing dust storm prediction methods are mostly based on single meteorological factors or remote sensing inversion data, lacking cloud computing architecture support, making it difficult to rapidly assess the risk of dust storms over large areas with high concurrency. They also lack the ability to identify dust storm precursors, making it difficult to identify potential dust storm areas in advance.

[0004] Existing cloud solutions only move some data or results visualization to the cloud, while the core wind erosion equations are still calculated locally, failing to solve the problems of elastic computing power, parallelization, and data homogeneity.

[0005] Therefore, the urgent technical problem to be solved is: how to provide a cloud computing method for predicting the risk of sandstorms based on the surface ecology and meteorological conditions, realize the prediction of sandstorm risk in the cloud, achieve rapid assessment of sandstorm risk in large-scale, high-concurrency areas, and solve the problems of elastic computing power, parallelization and data homogeneity. Summary of the Invention

[0006] The purpose of this application is to provide a cloud computing method for predicting surface sandstorm risk based on surface ecology and meteorological conditions, enabling rapid assessment of sandstorm risk in large-scale, high-concurrency areas, and solving the problems of elastic computing power, parallelization, and data homogeneity.

[0007] To achieve the above objectives, this application provides a cloud computing method for assessing surface dust storm risk based on surface ecology and meteorological conditions. The method includes: pre-constructing a multi-factor coupled surface dust storm risk index model; mirroring the multi-factor coupled surface dust storm risk index model container and deploying it on a cloud computing platform; responding to local surface dust storm risk prediction requests by collecting container index data and local surface dust storm risk prediction request feature data; calculating the matching value between the container and the local surface dust storm risk prediction request based on the container index data and the local surface dust storm risk prediction request feature data; and in the cloud, selecting the container with the largest matching value to the local surface dust storm risk prediction request and processing the local surface dust storm risk prediction request according to the multi-factor coupled surface dust storm risk index model.

[0008] The cloud computing method for assessing surface dust generation risk based on surface ecology and meteorological conditions, as described above, includes the following steps for processing local surface dust generation risk prediction requests: On the cloud computing platform side, a set of remote sensing surface ecological parameters, a set of reanalysis meteorological parameters, and topographic and land use data are loaded via a spatiotemporal alignment interface; a selected container is invoked, and the loaded set of remote sensing surface ecological parameters, the set of reanalysis meteorological parameters, and the topographic and land use data are input into a multi-factor coupled surface dust generation risk index model for prediction to obtain an initial risk value; the wind erosion impact coefficient is calculated within the container; the wind erosion impact coefficient is input into the trained multi-factor coupled surface dust generation risk index model to correct the error of the initial risk value and generate the final dust generation risk index.

[0009] The cloud computing method for assessing surface dust initiation risk based on surface ecology and meteorological conditions, as described above, includes the following steps for calculating the wind erosion impact coefficient within a container: 1) Calculate the instantaneous dust initiation wind speed based on surface roughness length and aerodynamic impedance; 2) Calculate the effective dust initiation kinetic energy based on the instantaneous dust initiation wind speed and ecological inhibition factor; 3) Calculate the instantaneous wind-driven soil erosion rate based on the effective dust initiation kinetic energy; 4) Calculate the wind erosion impact coefficient based on the instantaneous wind-driven soil erosion rate.

[0010] The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions, as described above, involves writing the final sandstorm risk index into a cloud-native spatiotemporal database for real-time access by business systems.

[0011] The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions, as described above, displays the final sandstorm risk index on a visual interface on both web and mobile devices.

[0012] The cloud computing method for assessing surface dust initiation risk based on surface ecology and meteorological conditions, as described above, includes the following formula for calculating the instantaneous dust initiation wind speed:

[0013] ;

[0014] in, Indicates the instantaneous wind speed at which the sandstorm begins; The critical frictional velocity representing an ideally smooth surface; This represents the roughness length correction factor; Indicates the aerodynamic impedance correction factor; Indicates the length of surface roughness; Indicates aerodynamic impedance; This represents the natural logarithm function.

[0015] The cloud computing method for assessing surface sand-lifting risk based on surface ecology and meteorological conditions, as described above, uses the following formula to calculate the effective sand-lifting kinetic energy:

[0016] ;

[0017] in, Indicates effective sand-lifting kinetic energy; Indicates the wind erosion coefficient; This indicates the actual wind speed at a height of 2 meters. Indicates the instantaneous wind speed at which the sandstorm begins; Indicates vegetation coverage; This indicates the water content per unit volume of soil. This indicates a land cover type inhibition factor.

[0018] The cloud computing method for landslide risk based on land surface ecology and meteorological conditions, as described above, includes the following steps: mirroring the multi-factor coupled landslide risk index model container and deploying it on a cloud computing platform: constructing a mirror of the multi-factor coupled landslide risk index model; and creating multiple containers based on the mirror of the multi-factor coupled landslide risk index model.

[0019] The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions, as described above, includes container metrics such as CPU utilization, memory usage, request processing latency, current request queue length, and the number of pending regional assessment tasks.

[0020] The characteristic data requested for local surface sandstorm risk prediction includes: geographic data of the requested region and regional priority.

[0021] The cloud computing method for assessing surface sand erosion risk based on surface ecology and meteorological conditions, as described above, includes the following: a set of remote sensing surface ecological parameters: vegetation cover, normalized difference vegetation index, land cover, soil texture type, net ecosystem carbon exchange, soil microbial respiration, surface energy flux, and water content; a set of reanalyzed meteorological parameters: wind speed, wind direction, air temperature, soil temperature, humidity, precipitation, and snow depth; and topographic and land use data: slope, aspect, and land cover type.

[0022] The beneficial effects achieved by this application are as follows:

[0023] (1) This application realizes the prediction of sandstorm risk in the cloud and realizes the rapid assessment of sandstorm risk in a large-scale, high-concurrency area.

[0024] (2) Based on the container index data and the local surface sandstorm risk prediction request feature data, this application calculates the matching value between the container and the local surface sandstorm risk prediction request, improves resource utilization, avoids mismatch waste and overload idleness, selects the container with the largest matching value with the local surface sandstorm risk prediction request, and processes the local surface sandstorm risk prediction request. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0026] Figure 1 This is a flowchart illustrating a cloud computing method for assessing the risk of surface sandstorms based on surface ecology and meteorological conditions, as described in an embodiment of this application.

[0027] Figure 2 This is a flowchart illustrating a method for processing local surface sandstorm risk prediction requests, as exemplified in this application. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0029] like Figure 1 As shown, this application provides a cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions. The method includes:

[0030] Step S1: Pre-construct a multi-factor coupled surface sandstorm risk index model.

[0031] The multi-factor coupled surface sand-raising risk index model is as follows:

[0032] SERI=f(NDVI, FVC, LZ, NEE, RH, Rn, U, SWC, WT, ST, ET0, P, SD, Slope, LandType);

[0033] Where SERI is the risk index, f() is the function f; the function f is obtained by training based on machine learning algorithms (such as XGBoost, LightGBM, random forest, etc.), the model input is the above-mentioned ecological and meteorological parameters, and the output is the initial risk value of sandstorms. NDVI represents the normalized vegetation index; FVC represents vegetation cover; Lz represents soil texture type; NEE represents net ecosystem carbon exchange; RH represents soil microbial respiration carbon emissions; Rn represents net surface radiation; U represents wind speed; SWC represents soil moisture content; WT represents soil temperature; ST represents soil moisture; ET0 represents reference crop evapotranspiration; P represents precipitation; SD represents snow depth; Slope represents terrain slope; and LandType represents land cover type.

[0034] Step S2 involves mirroring the multi-factor coupled surface sand-raising risk index model container and deploying it on a cloud computing platform.

[0035] The multi-factor coupled surface sandstorm risk index model is containerized into a lightweight image, which means that the multi-factor coupled surface sandstorm risk index model, dependency libraries, time series libraries, configurations, and certificates are all solidified into a horizontally replicable image. This horizontally replicable lightweight image is deployed on cloud computing platforms (such as Alibaba Cloud, AWS, and Google Cloud), and containerization technology (Docker + Kubernetes) is used to achieve elastic scaling and parallel processing capabilities of the model, supporting hourly updates of sandstorm risk predictions nationwide.

[0036] Step S2 includes:

[0037] Step S210: Based on the multi-factor coupled surface sand-raising risk index model, construct a mirror image of the multi-factor coupled surface sand-raising risk index model.

[0038] Specifically, the process of building a multi-factor coupled surface sandstorm risk index model includes: preparing containerized model materials, defining image building rules, building the image and verifying it locally, and pushing the image to the repository (for cluster retrieval).

[0039] Preferably, the model code is packaged into the image, while dynamic data (such as real-time NDVI and meteorological observation data) is obtained through external mounting or API to avoid the image size from increasing.

[0040] Preferably, by using multi-stage building, clearing the cache, and selecting a streamlined base image, the image size can be kept within 1GB (reducing the pull time).

[0041] Step S220: Create multiple containers based on the mirror image of the multi-factor coupled surface sand-raising risk index model.

[0042] Among them, the mirroring of the surface sandstorm risk index model based on multi-factor coupling creates multiple containers, including: defining container deployment configuration, deploying containers to the cluster, configuring service discovery and load balancing (supporting multi-container collaboration), and dynamically adjusting the number of containers.

[0043] Preferably, the container configuration is adjusted according to the model's computational characteristics (such as whether it relies on GPUs for parallel computation).

[0044] Each container contains a mirror image of a multi-factor coupled surface sandstorm risk index model.

[0045] Step S3: In response to the local surface sandstorm risk prediction request, collect container index data and local surface sandstorm risk prediction request feature data.

[0046] The container metrics data include: CPU utilization, memory usage, request processing latency, current request queue length, and number of pending region assessment tasks.

[0047] The requested feature data for local surface sandstorm risk prediction includes: geographic data of the requested region (such as locally cached soil and vegetation data) and regional priority. High-priority regions (such as ecologically fragile areas and densely populated areas) and low-priority regions are non-critical areas.

[0048] Step S4: Calculate the matching value between the container and the local surface sandstorm risk prediction request based on the container index data and the local surface sandstorm risk prediction request feature data.

[0049] The calculation method for the matching value of the container with the local surface sand-raising risk prediction request is as follows:

[0050] ;

[0051] in, This indicates the matching value between the container and the local surface sandstorm risk prediction request; This indicates the weight of the impact of container load on the matching value; This indicates the total number of container metric data categories; Indicates the first Weighting factors for container indicator data; Indicates the first The numerical values ​​of the container index data; This indicates the weight of the data localization factor on the matching value; Indicates the data localization factor; This represents the weight of the container's effective computing power on the matching value. Indicates the container's effective computing power; Indicates the minimum computing power required for the request; This indicates the weight of the model version compatibility factor on the matching value.

[0052] Among them, the effective computing power of containers HCPU indicates the number of CPU cores. HGPU indicates the number of GPU cores.

[0053] In this case, the node where the container resides caches all the necessary data for that region. If the node where the container resides caches some data, then... If the node where the container resides has no cache, then ; This indicates the model version compatibility factor; if the model version fully supports the parameters for this region, then... If the model version requires slight adaptation, then If the model version does not support it, then .

[0054] Step S5: In the cloud, select the container with the largest matching value to the local surface sandstorm risk prediction request, and process the local surface sandstorm risk prediction request according to the multi-factor coupled surface sandstorm risk index model.

[0055] Step S5 includes:

[0056] Step S510: In the cloud, select the container with the largest matching value to the local surface sandstorm risk prediction request as the optimal container.

[0057] Step S520: The local surface sandstorm risk prediction request is routed to the optimal container.

[0058] In step S530, the container processes local surface sandstorm risk prediction requests based on the built-in multi-factor coupled surface sandstorm risk index model.

[0059] Step S540: The container returns the processing result.

[0060] like Figure 2 As shown, the methods for processing local surface sandstorm risk prediction requests include:

[0061] Step T1: On the cloud computing platform side, load the remote sensing surface ecological parameter set, the reanalysis meteorological parameter set, and the topographic and land use data through the spatiotemporal alignment interface.

[0062] The set of remote sensing surface ecological parameters includes: vegetation coverage, normalized difference vegetation index, land cover, soil texture type, net ecosystem carbon exchange, soil microbial respiration, surface energy flux, and water content.

[0063] The reanalysis of meteorological parameters includes wind speed, wind direction, air temperature, soil temperature, humidity, precipitation, and snow depth.

[0064] Among them, topographic and land use data include: slope, aspect, land cover type, etc.

[0065] Step T2: Invoke the selected container and input the loaded remote sensing surface ecological parameter set, reanalysis meteorological parameter set, and topographic and land use data into the multi-factor coupled surface sandstorm risk index model for prediction to obtain the initial risk value of sandstorm.

[0066] Step T3 involves performing the wind erosion impact coefficient calculation process within the container.

[0067] The process of calculating the wind erosion impact coefficient in a container includes:

[0068] Step T310: Calculate the instantaneous dust initiation wind speed based on the surface roughness length and aerodynamic impedance.

[0069] The formula for calculating the instantaneous dust storm initiation wind speed is as follows:

[0070] ;

[0071] in, Indicates the instantaneous wind speed at which the sandstorm begins; The critical frictional velocity representing an ideally smooth surface; This represents the roughness length correction factor; Indicates the aerodynamic impedance correction factor; Indicates the length of surface roughness; Indicates aerodynamic impedance; This represents the natural logarithm function.

[0072] The rougher the surface (greater the resistance) or the stronger the airflow resistance (greater the resistance), the higher the wind speed is required to overcome the resistance and move the sand particles. Follow , Increase and rise (e.g., the critical wind speed for sand lifting in grassland is significantly higher than that in bare sand).

[0073] Step T320: Calculate the effective sand-raising kinetic energy based on the instantaneous sandstorm initiation wind speed and ecological inhibition factor.

[0074] Among them, ecological inhibition factors include: NDVI, soil moisture content, and land cover type.

[0075] The formula for calculating the effective sand-lifting kinetic energy is as follows:

[0076] ;

[0077] in, Indicates effective sand-lifting kinetic energy; Indicates the wind erosion coefficient; This indicates the actual wind speed at a height of 2 meters. Indicates the instantaneous wind speed at which the sandstorm begins; Indicates vegetation coverage; This indicates the water content per unit volume of soil. This indicates a land cover type inhibition factor. Represented by natural constant An exponential function with base 0.

[0078] Step T330: Calculate the instantaneous wind-driven soil loss rate based on the effective sand-lifting kinetic energy.

[0079] The formula for calculating the instantaneous wind-driven soil loss rate is as follows:

[0080] ;

[0081] in, Indicates the instantaneous wind-driven soil loss rate; express Effective sand-lifting kinetic energy at all times; to Indicates the calculation period; Indicates soil erodibility factor; It represents the time derivative.

[0082] Step T340: Calculate the wind erosion impact coefficient based on the instantaneous wind-driven soil loss rate.

[0083] The formula for calculating the wind erosion impact coefficient is as follows:

[0084] ;

[0085] Where Xf represents the wind erosion impact coefficient; Lf represents the reference wind erosion rate; tanh() is the hyperbolic tangent function; tanh() converts arbitrarily large values ​​of Xf into the hyperbolic tangent function. The value is compressed to -1 to 1, and saturates in the high-value area, which is consistent with the fact that the risk no longer increases linearly after wind erosion exceeds a certain level.

[0086] Step T4: Input the wind erosion impact coefficient into the trained multi-factor coupled surface sandstorm risk index model, correct the error of the initial risk value, and generate the final sandstorm risk index.

[0087] Among them, the multi-factor coupled surface dust storm risk index model adopts online incremental learning, and updates the weights with the latest dust storm event observation labels to keep the model drift adaptive.

[0088] Step T5: Write the final sandstorm risk index into the cloud-native spatiotemporal database for real-time access by business systems.

[0089] Step T6 displays the final sandstorm risk index on the web and mobile visualization interfaces.

[0090] Among them, it displays a map showing the hourly risk level of sandstorms over the next 72 hours, and supports functions such as area filtering, timeline playback, and risk level warning push.

[0091] This application also provides a computer storage medium storing computer instructions, which, when invoked, execute the address mapping method of the large-capacity solid-state drive. The computer storage medium includes one or more program instructions, which are executed by a processor as a cloud computing method based on the risk of surface sandstorms caused by surface ecology and meteorological conditions.

[0092] The embodiments disclosed in this invention provide a computer-readable storage medium storing computer program instructions. When the computer program instructions are executed on a computer, the computer performs the aforementioned cloud computing method for assessing the risk of surface sandstorms based on surface ecology and meteorological conditions.

[0093] This invention provides a processor for processing the aforementioned cloud computing method for assessing the risk of surface sandstorms based on surface ecology and meteorological conditions.

[0094] In this embodiment of the invention, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, 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.

[0095] The various methods, steps, and logic diagrams disclosed in the embodiments of this invention can be implemented or executed. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The processor reads information from the storage medium and, in conjunction with its hardware, completes the steps of the above methods.

[0096] The storage medium can be memory, such as volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0097] The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EEPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0098] The beneficial effects achieved by this application are as follows:

[0099] (1) This application realizes the prediction of sandstorm risk in the cloud and realizes the rapid assessment of sandstorm risk in a large-scale, high-concurrency area.

[0100] (2) Based on the container index data and the local surface sandstorm risk prediction request feature data, this application calculates the matching value between the container and the local surface sandstorm risk prediction request, improves resource utilization, avoids mismatch waste and overload idleness, selects the container with the largest matching value with the local surface sandstorm risk prediction request, and processes the local surface sandstorm risk prediction request.

[0101] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0102] In the description of this application, the word "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0103] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions, characterized in that, The method includes: A multi-factor coupled surface sand-raising risk index model is pre-constructed; The multi-factor coupled surface sand-raising risk index model was containerized and deployed on a cloud computing platform; In response to local requests for surface sandstorm risk prediction, container index data and local surface sandstorm risk prediction request feature data are collected. Based on container index data and local surface sandstorm risk prediction request feature data, calculate the matching value between the container and the local surface sandstorm risk prediction request; In the cloud, the container with the largest matching value to the local surface sandstorm risk prediction request is selected, and the local surface sandstorm risk prediction request is processed according to the multi-factor coupled surface sandstorm risk index model. Methods for processing local surface dust rise risk prediction requests include: On the cloud computing platform side, remote sensing surface ecological parameter sets, reanalysis meteorological parameter sets, and topographic and land use data are loaded through the spatiotemporal alignment interface. The selected container is invoked, and the loaded set of remote sensing surface ecological parameters, reanalysis meteorological parameters, and topographic and land use data are input into the multi-factor coupled surface sandstorm risk index model for prediction to obtain the initial risk value. Perform the calculation of wind erosion impact coefficient in a container; The wind erosion impact coefficient is input into the trained multi-factor coupled surface sand-raising risk index model to correct the error of the initial risk value and generate the final sand-raising risk index. The method for calculating the wind erosion impact coefficient in a container is as follows: Calculate the instantaneous dust initiation wind speed based on the surface roughness length and aerodynamic impedance; The effective kinetic energy for sand lifting is calculated based on the instantaneous sandstorm initiation wind speed and ecological inhibition factors; Calculate the instantaneous wind-driven soil loss rate based on the effective sand-lifting kinetic energy; The wind erosion impact coefficient is calculated based on the instantaneous wind-driven soil loss rate. The calculation method for the matching value of the container with the local surface sand-raising risk prediction request is as follows: ； in, This indicates the matching value between the container and the local surface sandstorm risk prediction request; This indicates the weight of the impact of container load on the matching value; This indicates the total number of container metric data categories; Indicates the first Weighting factors for container indicator data; Indicates the first The numerical values ​​of the container index data; This indicates the weight of the data localization factor on the matching value; Indicates the data localization factor; This represents the weight of the container's effective computing power on the matching value. Indicates the container's effective computing power; Indicates the minimum computing power required for the request; This indicates the weight of the model version compatibility factor on the matching value; Among them, the container's effective computing power HCPU represents the number of CPU cores; HGPU represents the number of GPU cores. Wherein, the node where the container resides caches all the required data in the region, then If the node where the container resides caches some data, then... If the node where the container resides has no cache, then ; This indicates the model version compatibility factor; if the model version fully supports the parameters for this region, then... If the model version requires slight adaptation, then If the model version does not support it, then .

2. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The final sandstorm risk index is written into a cloud-native spatiotemporal database for real-time access by business systems.

3. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The final sandstorm risk index will be displayed on a visual interface on both web and mobile devices.

4. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The formula for calculating the instantaneous wind speed at which a sandstorm begins is: ； in, Indicates the instantaneous wind speed at which the sandstorm begins; The critical frictional velocity representing an ideally smooth surface; This represents the roughness length correction factor; Indicates the aerodynamic impedance correction factor; Indicates the length of surface roughness; It represents aerodynamic impedance.

5. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The formula for calculating the effective kinetic energy of sand lifting is: ； in, Indicates effective sand-lifting kinetic energy; Indicates the wind erosion coefficient; This indicates the actual wind speed at a height of 2 meters. Indicates the instantaneous wind speed at which the sandstorm begins; Indicates vegetation coverage; This indicates the water content per unit volume of soil. This indicates a land cover type inhibition factor.

6. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The process of containerizing and deploying a multi-factor coupled surface sand-raising risk index model on a cloud computing platform includes: Based on the multi-factor coupled surface sand-raising risk index model, a mirror image of the multi-factor coupled surface sand-raising risk index model is constructed. Multiple containers are created based on a mirror image of the surface sand-raising risk index model with multi-factor coupling.

7. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, Container metrics include: CPU utilization, memory usage, request processing latency, current request queue length, and number of pending region assessment tasks; The characteristic data requested for local surface sandstorm risk prediction includes: geographic data of the requested region and regional priority.

8. The cloud computing method for assessing surface sandstorm risk based on surface ecology and meteorological conditions according to claim 1, characterized in that, The set of remote sensing surface ecological parameters includes: vegetation cover, normalized difference vegetation index, land cover, soil texture type, net ecosystem carbon exchange, soil microbial respiration, surface energy flux, and water content. Further analysis of the meteorological parameter set includes: wind speed, wind direction, air temperature, soil temperature, humidity, precipitation, and snow depth; Topographic and land use data: slope, aspect and land cover type.

Images