Vegetation remote sensing monitoring method and system based on geographic information cloud platform

Abstract

The invention provides a vegetation remote sensing monitoring method and system based on a geographic information cloud platform, and the method comprises the steps: determining the time and region of target monitoring, and determining the geographic boundary and time range of target monitoring according to the demands of a user; screening a suitable data source, and cutting the screened remote sensing image; carrying out cloud layer interference processing on the image data by adopting a cloud removal algorithm, and removing pixels covered by a cloud layer; carrying out radiation correction, geometric correction and atmospheric correction standardization preprocessing on the image; calculating a vegetation ecological index, a vegetation drought index and a meteorological factor of the target area based on the preprocessed remote sensing image; and displaying the processed vegetation growth time sequence monitoring data on a user interface in an image form, and supporting exported data of the data for subsequent analysis. According to the method, through an efficient processing algorithm, the precision and timeliness of vegetation growth state monitoring are remarkably improved, and important technical support is provided for vegetation management, ecological protection and scientific research.

Description

Technical Field

[0001] The present invention relates to the field of vegetation monitoring technology, and in particular to a vegetation remote sensing monitoring method and system based on a geographic information cloud platform. Background Art

[0002] As a powerful geographic information cloud platform, Google Earth Engine (GEE) provides a wealth of remote sensing data sets and processing functions, becoming an important tool for remote sensing data analysis and visualization. GEE has powerful cloud computing capabilities and can efficiently process and analyze large-scale remote sensing image data, especially in the fields of vegetation monitoring, climate change analysis, and environmental assessment.

[0003] In recent years, with the continuous development of remote sensing technology, vegetation monitoring and analysis based on remote sensing data has become a key technology in the fields of agriculture, water resources management, and ecological and environmental protection. More and more studies have begun to combine the GEE platform with application programs (APPs) to provide more convenient remote monitoring and data analysis methods. Many journal articles have begun to include GEE application links related to research. This form of development has greatly reduced the threshold for use. Even if users do not have a GEE account, they can directly access, operate, and verify the developed system through the web page. This approach provides a new way to quickly disseminate research results, verify algorithms, and achieve widespread application of scientific research results.

[0004] In the field of vegetation monitoring, traditional remote sensing technology is often limited by factors such as data processing efficiency, computing power and user operation complexity. The use of the GEE platform to develop a vegetation remote sensing monitoring system can not only give full play to the platform's cloud computing and big data processing capabilities, but also allow users to quickly access and operate through a simple web interface. The development of the GEE APP is similar to the development of front-end web pages. Through technologies such as HTML, JavaScript and CSS, combined with the APIs and tools provided by GEE, real-time display, dynamic analysis and customized operations of data can be achieved, providing intuitive geospatial information.

[0005] The GEE platform itself has large-scale data storage and efficient computing capabilities, which greatly improves the real-time and accuracy of vegetation remote sensing monitoring. The vegetation remote sensing monitoring method based on GEE can extract vegetation-related indicators such as the vegetation index NDVI (Normalized Difference Vegetation Index), the drought index TVDI (Temperature-Vegetation Dryness Index), the leaf area index LAI (Leaf Area Index), etc. through the processing and analysis of remote sensing images, providing a scientific basis for agricultural production and ecological environment management. At the same time, users can not only monitor the vegetation growth dynamics of the target area in real time, but also flexibly export data according to needs to provide accurate decision-making support.

[0006] Therefore, vegetation remote sensing monitoring based on GEE not only helps to promote the research of remote sensing science, but also provides effective tools and methods for resource management and environmental protection in practical applications. Summary of the invention

[0007] In view of the technical problems existing in the prior art, the present invention provides a vegetation remote sensing monitoring method and system based on a geographic information cloud platform, aiming to provide a vegetation remote sensing monitoring solution that is efficient, convenient and easy to promote and apply.

[0008] According to a first aspect of the present invention, the present invention provides a vegetation remote sensing monitoring method based on a geographic information cloud platform, comprising the following steps: Determine the time and area of ​​target monitoring, and clarify the geographical boundaries and time range of target monitoring according to user needs; Obtain remote sensing data sources suitable for monitoring needs of the target area, filter remote sensing image data, and crop the filtered remote sensing image data according to the scope of the target area; The cloud removal algorithm is used to process the cloud interference of remote sensing image data and remove the pixels covered by clouds; Performing standardized preprocessing on remote sensing image data, the preprocessing includes: radiation correction, geometric correction, atmospheric correction and data interpolation; Calculate the vegetation ecological index, vegetation drought index and meteorological factors of the target area based on the preprocessed remote sensing image data; The processed vegetation ecological indicators, vegetation drought indicators and meteorological factors are displayed in the form of images on the user interface, and the data can be exported for subsequent analysis.

[0009] Based on the above technical solution, the present invention can also make the following improvements.

[0010] Optionally, the determining of the geographical boundaries and time range of target monitoring according to user needs includes: Collect the specific needs of users, including the specific geographical coordinates of the target monitoring area, the monitoring time period, and the specific requirements of users for monitoring results; Mark the target monitoring area on the map according to the geographic coordinates provided by the user, and define the geographic boundaries of the target area by uploading vector data files; Automatically parse the start and end dates based on the time range entered by the user.

[0011] Optionally, the step of obtaining a remote sensing data source suitable for monitoring needs of the target area and screening remote sensing image data includes: The remote sensing data sources suitable for the monitoring needs of the target area are obtained from the Google Earth Engine platform, and the remote sensing data sources include Landsat, MODIS and Sentinel image data.

[0012] Optionally, the step of clipping the filtered remote sensing image data according to the target area range includes the following steps: Receive target monitoring time range and plot vector data; Filter the initial remote sensing image dataset based on the time range; The initial remote sensing image dataset is clipped according to the plot boundaries to generate a remote sensing image dataset that meets the needs of the target area.

[0013] Optionally, the cloud removal algorithm is used to process the remote sensing image data for cloud interference, and the removal of pixels covered by clouds includes the following steps: Automatically extract preset pixels based on the cloud detection band of the image to generate cloud pixel data; Generate a cloud mask layer based on cloud pixel data; The cloud mask layer is used to perform mask operations on the remote sensing image dataset, remove cloud-covered areas and perform pixel completion to obtain the preset de-clouded remote sensing image dataset.

[0014] Optionally, vegetation ecological indicators for the target area may include: Based on the remote sensing images of the target area, the normalized vegetation index is calculated and the kernel normalized difference vegetation index is generated to reflect the temporal and spatial variation trend of crop growth in the target plot; Extract the leaf area index of the target area and analyze the growth dynamic characteristics of the crop canopy; Based on remote sensing data and regional meteorological conditions, the vegetation light energy absorption fraction and net primary productivity were calculated to evaluate the light energy utilization efficiency and carbon absorption capacity of the vegetation ecosystem.

[0015] Optionally, vegetation drought indicators for the target area are calculated including: By combining the surface temperature and vegetation coverage of remote sensing images, a temperature vegetation drought index is constructed to generate a dynamic distribution map of drought conditions in the target area, providing drought monitoring data support for agricultural and ecological management.

[0016] Optionally, the meteorological factors include precipitation and temperature. Through multi-source remote sensing data and meteorological station observation data, the precipitation and temperature information of the target area is extracted to provide necessary parameters for the calculation of vegetation ecological indicators and drought indicators.

[0017] Optionally, displaying the processed vegetation ecological index, vegetation drought index and meteorological factor in the form of images on the user interface includes: The user interface displays monitoring data in the form of a spatial distribution map, and provides interactive map functions, supports area zooming in, zooming out, marking and plot selection, supports data export functions, selects vegetation ecological indicators, drought index, meteorological factors, and exports data according to specified time periods and areas.

[0018] According to a second aspect of the present invention, a vegetation remote sensing monitoring system based on a geographic information cloud platform is provided, comprising: Data acquisition module: used to acquire remote sensing image data, and filter and crop remote sensing image data that meets the target area according to the time range and plot vector boundary specified by the user; Communication interface: used for data interaction with the server, supporting data transmission between remote data calls and local storage; Processor module: used to pre-process the acquired remote sensing image data, including cloud removal, radiation correction, geometric correction, atmospheric correction and data interpolation, and supports the calculation of vegetation ecological indicators, vegetation drought indicators and meteorological factors; Display module: used to display the processed monitoring results in a visual form, including spatial distribution diagrams, dynamic time series curves, support interactive operations and provide data export functions.

[0019] Technical effects and advantages of the present invention: The present invention provides a vegetation remote sensing monitoring method and system based on a geographic information cloud platform, which is novel in existing remote sensing monitoring methods by deeply integrating the powerful cloud computing capabilities of the Google Earth Engine platform with vegetation remote sensing monitoring technology. The Google Earth Engine platform can not only meet the needs of data collection, data calculation, data display, etc., but also provide an efficient and real-time data processing and analysis environment for vegetation remote sensing monitoring through its powerful cloud computing capabilities. Through automated data screening and processing, the monitoring efficiency is significantly improved, and the complexity and error rate of manual operations are reduced. The present invention makes full use of the powerful cloud computing capabilities and large-scale data storage advantages of the GEE platform to solve the problems of low computing efficiency, cumbersome operations, and difficult data acquisition in traditional remote sensing monitoring methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 2 It is a vector graphic schematic diagram of a target study area of ​​a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of a cropped, cloud-free, and pre-processed remote sensing image of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of NDVI monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of kNDVI monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided in an embodiment of the present invention; Figure 6 It is a schematic diagram of NPP monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 7 It is a schematic diagram of TVDI monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Figure 8 It is a schematic diagram of LAI monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig. 9 It is a schematic diagram of FPAR monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig.10 It is a schematic diagram of precipitation monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig.11 It is a schematic diagram of temperature monitoring data of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig.12 It is a flow chart of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig.13 It is a front-end schematic diagram of a vegetation remote sensing monitoring method based on a geographic information cloud platform provided by an embodiment of the present invention; Fig.14 It is a schematic diagram of a vegetation remote sensing monitoring system based on a geographic information cloud platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] It is understandable that, based on the defects in the background technology, the embodiment of the present invention proposes a vegetation remote sensing monitoring method based on a geographic information cloud platform, specifically as follows: Figure 1 As shown, the following steps are included: Step S1. Determine the time and area of ​​target monitoring, clarify the geographical boundaries and time range of target monitoring according to user needs, and provide a basis for remote sensing image data processing; Determining the time and area of ​​target monitoring and clarifying the geographical boundaries and time range of target monitoring according to user needs include: First, the system receives the user's specific needs, including the specific geographic coordinates of the target monitoring area, the monitoring time period (such as a certain year, a certain few months or a certain season), and the user's specific requirements for the monitoring results (such as vegetation coverage, growth status, etc.). Secondly, based on the geographic coordinates provided by the user, the system can mark the target monitoring area on the map. For complex geographic boundaries, users can define the exact boundaries of the target area by uploading vector data files (such as shapefiles); finally, the system automatically parses the start and end dates based on the time range entered by the user to ensure the accuracy of the time range. For long-term monitoring projects, the system can support users to select different time periods, such as all months of a year or certain seasons.

[0023] It should be noted that the uploaded vector data determines the research area, as shown in the following example: Figure 2As shown, users can define the geographic boundaries of the target area by uploading vector data files to ensure the accuracy of the study area.

[0024] In the specific application of the present invention, the embodiment of the present invention takes a certain irrigation area as the case area, takes 2020 as the research time, and the target area is the Hetao Irrigation Area. The system uses the GEE platform to automatically read and load the vector boundary, and uses it as the basis for subsequent remote sensing image cropping. The user also needs to specify the time range of the study. For example, if the research year is entered as 2020, the system will automatically parse the start and end dates and generate a specific time period (such as January 1, 2020 to December 31, 2020).

[0025] Step S2. Acquire a remote sensing data source suitable for monitoring needs of the target area, filter the remote sensing image data, and crop the filtered remote sensing image data; In this embodiment, remote sensing data sources suitable for monitoring needs of the target area are obtained from the GEE platform, including but not limited to Landsat, MODIS and Sentinel image data, and the image data are cropped according to the scope of the target area; The remote sensing image data screening and cutting comprises the following steps: Receive target monitoring time range and plot vector data; Filter the initial remote sensing image dataset based on the time range; The initial image dataset is clipped according to the plot boundaries to generate a remote sensing image dataset that meets the needs of the target area.

[0026] It should be noted that the system selects suitable remote sensing data sets from the GEE image library according to the time range and geographic area specified by the user, including but not limited to common high-resolution data sources such as MODIS, Landsat series (such as Landsat 8 and Landsat 9), and Sentinel-2. Since the study area is large and involves long-term dynamic monitoring, MODIS data with high temporal resolution and wide coverage is preferred as the main data source, and Landsat images with higher spatial resolution are combined for supplementation and verification. Finally, the system completes the preliminary screening and loading of remote sensing images within the target area and time range, providing basic data support for subsequent image processing and indicator calculation. This step greatly reduces the user's manual operation burden and improves monitoring efficiency and accuracy. Step S3. Using a cloud removal algorithm to process the image data for cloud interference, remove pixels covered by clouds, and improve the integrity and quality of the image; It should be noted that in remote sensing image processing, cloud is an important factor affecting image quality and subsequent analysis accuracy, especially for vegetation monitoring over a large time series, where the presence of cloud may lead to incomplete data and biased analysis results. Therefore, the present invention uses an advanced cloud removal algorithm to effectively remove cloud interference and ensure the integrity and quality of image data.

[0027] The cloud removal process comprises the following steps: Extract low-quality pixels based on the cloud detection band of the image to generate cloud pixel data; Generate a cloud mask layer based on cloud pixel data; The cloud mask layer is used to perform mask operations on the remote sensing image dataset, remove cloud-covered areas and perform pixel completion to obtain a high-quality de-clouded remote sensing image dataset.

[0028] Specifically, the de-clouding process can be divided into the following steps: Extract low-quality pixels from cloud detection bands: First, potential cloud areas are automatically extracted based on the cloud detection bands of the image (such as infrared bands, short-wave infrared bands, etc.). These bands can help identify the characteristics of clouds, especially under different lighting conditions, clouds usually show more special spectral characteristics. Through these band analyses, the system can identify low-quality pixels covered by clouds in the image and generate cloud pixel data, which can be used as the basis for subsequent processing.

[0029] Generate cloud mask layer: Through further analysis of cloud pixel data, the system automatically generates a cloud mask layer. The cloud mask layer identifies cloud areas in binary form, usually marking cloud-covered areas as 1 and non-cloud-covered areas as 0. The generation of this mask layer is one of the key steps in cloud removal processing. It can accurately identify which areas need to be removed, thereby preventing clouds from affecting subsequent image analysis.

[0030] Masking: Based on the cloud mask layer, the system performs masking on the remote sensing image dataset. The specific operation is to remove the cloud area in the image (the part marked by the cloud mask layer) from the original image.

[0031] Through the above cloud removal processing, a set of high-quality remote sensing image data sets without cloud interference is obtained. Figure 3 As shown in the figure, the part describing the selection of suitable data sources and the clipping of the screened remote sensing image data is used to display the clipped, cloud-free, and pre-processed remote sensing images. These data sets can provide more reliable basic data support for subsequent vegetation growth monitoring, drought assessment, and water resources analysis. The use of cloud removal algorithms greatly improves the efficiency of remote sensing image use, reduces analysis errors caused by cloud effects, and enhances the accuracy and practicality of monitoring results.

[0032] Step S4. performing standardized preprocessing on the remote sensing image data, wherein the preprocessing includes: radiation correction, geometric correction, atmospheric correction and data interpolation; Consider interpolation of some missing data to ensure the temporal and spatial consistency of image data; The radiation correction: eliminates the sensor system error by adjusting the spectral value of the image to ensure the physical authenticity of the image data; in this example, the built-in radiation correction tool of GEE is used to eliminate the sensor system error in the remote sensing image and convert the original digital value (DN value) of the image into ground reflectivity. This process ensures the physical authenticity of the image data and is applicable to remote sensing datasets such as MODIS and Landsat. By using functions such as landsat.calibrate() or MODIS.calibrate(), we can adjust the spectral information in the image to make it consistent with the ground true reflectivity. This step can effectively avoid the impact of sensor errors on subsequent analysis results and improve the quality of the image.

[0033] Geometric correction: The image is accurately aligned with the geographic coordinates through geometric transformation to eliminate the geometric deviation caused by the change of sensor position; in order to eliminate the geometric deviation caused by the change of sensor position or the influence of terrain, the image is geometrically corrected using the ee.Image.reproject() method of GEE. This method accurately aligns the image to the global geographic coordinate system to ensure the consistency of the image space. In this example, the image is reprojected according to the coordinate system of the target area to ensure that the image can be effectively connected with other data sets such as vector data and geographic information system (GIS) data. GEE provides powerful geometric correction functions, supporting various common coordinate systems and projection methods, so that the image spatial resolution and geographic location are accurately aligned.

[0034] Atmospheric correction: Use the radiation transfer model to reduce the impact of atmospheric scattering and absorption and restore the true reflectivity of the surface. In order to reduce the impact of atmospheric interference on image quality, we use multiple atmospheric correction tools in GEE, especially the ee.Algorithms.Landsat.TOA() and ee.Algorithms.Landsat.TOS() methods for Landsat datasets. These tools calculate the impact of atmospheric scattering and absorption through the radiation transfer model to restore the true reflectivity of the surface. After using these methods, the atmospheric impact in the image is effectively removed, ensuring that the image data can more accurately reflect the surface characteristics. Whether it is Landsat or MODIS datasets, GEE can automatically select the appropriate atmospheric correction method to meet the characteristics and requirements of different datasets.

[0035] Data interpolation: For some areas with missing data, use time series analysis or spatial interpolation algorithms to complete the pixel values ​​to improve data continuity and accuracy. In remote sensing image processing, cloud cover or sensor failure may cause some data to be missing. In this example, we used GEE's time series analysis and spatial interpolation methods to complete the missing data. Through the ee.ImageCollection() function, we can interpolate the missing pixel values ​​based on the time series data. For example, in the time period of missing data, we use the previous and next time series data for interpolation filling to ensure the continuity and accuracy of the data. In addition, using spatial interpolation methods such as ee.Reducer.mean(), we can infer the pixel data of the missing area based on the values ​​of the surrounding pixels, thereby improving the integrity of the data. This process is particularly suitable for long-term monitoring projects and trend analysis to ensure the reliability and continuity of data.

[0036] Step S5. Calculating vegetation ecological indicators, vegetation drought indicators and meteorological factors in the target area based on the preprocessed remote sensing image data; Specific as Figure 4-9 As shown, the calculation of vegetation ecological index, vegetation drought index and meteorological factor includes the following steps: Calculation of vegetation ecological indicators: including: Normalized Difference Vegetation Index (NDVI) (such as Figure 4 ) and the kernel normalized difference vegetation index (KNDI) (such as Figure 5 ). Based on the remote sensing image of the target area, NDVI is calculated and kNDVI is generated to reflect the temporal and spatial variation trend of crop growth in the target plot. Leaf Area Index (LAI): The leaf area index (LAI) of the target area is extracted using the radiation transfer model or empirical formula (such as Figure 8 ), analyze the dynamic characteristics of crop canopy growth. Fraction of Photosynthetically Active Radiation and Net Primary Productivity (e.g. Figure 6 ): Calculate the fraction of light energy absorbed by vegetation (FPAR) based on remote sensing data and regional meteorological conditions (such as Fig. 9 ) and net primary productivity (NPP), assessing the light energy utilization efficiency and carbon absorption capacity of vegetation ecosystems; Calculation of vegetation drought index: TVDI (such as Figure 7 ): Combining the surface temperature and vegetation coverage of remote sensing images, the Temperature Vegetation Drought Index (TVDI) is constructed to generate a dynamic distribution map of drought conditions in the target area, providing drought monitoring data support for agricultural and ecological management.

[0037] Extraction of meteorological factors: The meteorological factors include: precipitation (such as Fig.10 ) and temperature (e.g. Fig.11 ). Through multi-source remote sensing data and meteorological station observation data, the precipitation and temperature information of the target area are extracted to provide the necessary parameters for the calculation of vegetation ecological indicators and drought indicators.

[0038] For the calculation of vegetation ecological indicators, Landsat, MODIS, and Sentinel-2 images were used. Specific indicators include Fig.12 As shown in the figure, NDVI is a commonly used remote sensing indicator to measure vegetation coverage and growth conditions. The calculation formula is:

[0039] Among them, NIR stands for near-infrared band reflectance, and RED stands for red band reflectance. The value of NDVI ranges from -1 to +1, and the larger the value, the more lush the vegetation.

[0040] kNDVI: The calculated NDVI is used to describe the vegetation growth status of the target area, and further generate the kernel normalized difference vegetation index (kNDVI) to reflect the temporal and spatial variation trend of vegetation growth. The calculation formula of kNDVI is:

[0041] Where: is the length scale parameter specified in each specific application, representing the sensitivity of the index to sparse / dense vegetation areas; It is near infrared band; It is the red light band; () is the hyperbolic tangent function. The calculation can be taken as the average value:

[0042] In this case The formula is as follows:

[0043] LAI: A parameter that quantifies vegetation canopy structure, representing the total green leaf area per unit surface area.

[0044] FPAR: Fractional Phototropy Absorption by Vegetation (FPAR) refers to the proportion of total solar radiation absorbed by vegetation.

[0045] Both LAI and FPAR data use the MODIS MOD15A2H v6.1 dataset, which is an 8-day synthetic composite data with a resolution of 500 meters.

[0046] NPP: Net primary productivity (NPP) reflects the amount of organic matter produced by plant photosynthesis in an ecosystem. NPP is an indicator that reflects the amount of organic matter produced by plant photosynthesis in an ecosystem. The calculation of NPP generally relies on FPAR and LAI data, combined with a certain photosynthetic efficiency formula for estimation.

[0047] For the calculation of vegetation drought index: TVDI is an indicator that reflects drought conditions by combining the vegetation index (NDVI) and land surface temperature (LST). First of all, NDVI (Normalized Difference Vegetation Index) and LST (Daytime Land Surface Temperature) are considered to be two important factors reflecting vegetation growth and water conditions. The larger the NDVI, the more lush the vegetation and the sufficient water; the lower the LST, it usually means that the vegetation is growing well and there is sufficient water; while the higher the LST, it may indicate drought or heat stress. Next, based on the fitted linear equation, we calculated the minimum and maximum LST corresponding to each NDVI value. This is obtained by multiplying the NDVI with the fitted linear equation, and the formula is as follows:

[0048]

[0049] Where d and c are the slope and intercept of the minimum linear regression, and b and a are the slope and intercept of the maximum linear regression. TVDI is calculated by the following formula:

[0050] This indicates the degree of deviation from the LST, with values ​​closer to 1 indicating more severe drought and values ​​closer to 0 indicating wetter or normal conditions.

[0051] For the extraction of meteorological factors: the temperature and precipitation data used are from the ERA5 dataset, which is released by the European Centre for Medium-Range Weather Forecasts (ECMWF) and belongs to the fifth generation of global climate atmospheric reanalysis products. ERA5 constructs a high-precision, globally consistent climate dataset by combining observational data from all over the world with the output of numerical weather forecast models. As the successor to the ERA-Interim reanalysis data, ERA5 has higher temporal resolution and spatial accuracy. The ERA5DAILY dataset provides a daily summary of seven key climate variables, including: air temperature at 2 meters, dew point temperature at 2 meters, total precipitation, sea level pressure, surface pressure, u wind component at 10 meters, and v wind component. In addition, other relevant meteorological parameters can also be queried. ERA5 DAILY also calculates the daily minimum and maximum temperatures by processing the 2-meter air temperature data every hour, while precipitation is provided as a daily sum, and other parameters are daily averages.

[0052] Step S6. The processed vegetation ecological index, vegetation drought index and meteorological factor are displayed in the form of images on the user interface, and the data can be exported for subsequent analysis.

[0053] Specifically, the processed vegetation growth time series monitoring data, including vegetation ecological indicators, vegetation drought indicators and meteorological factors, are intuitively presented on the user interface in the form of a spatial distribution map. The user interface is as follows: Fig.13 As shown, data visualization and export include the following steps: Display monitoring data in the form of spatial distribution maps in the user interface; Provides interactive map function, supports area zooming in, zooming out, marking and plot selection; Supports data export function. Users can select vegetation ecological indicators, drought index, meteorological factors, etc., and export data according to specified time period and area in TIFF format.

[0054] In summary, the vegetation remote sensing monitoring method based on the geographic information cloud platform provided by the embodiment of the present invention deeply integrates the powerful cloud computing capabilities of the Google Earth Engine platform with the vegetation remote sensing monitoring technology, and this integration is novel in the existing remote sensing monitoring methods. The Google Earth Engine platform can not only meet the needs of data collection, data calculation, data display and other aspects, but also provide an efficient and real-time data processing and analysis environment for vegetation remote sensing monitoring through its powerful cloud computing capabilities. Through automated data screening and processing, the present invention significantly improves the monitoring efficiency and reduces the complexity and error rate of manual operations. In addition, the method has the applicability of a wide range of geographical areas and time ranges, and enhances the universality of vegetation remote sensing monitoring. The integration of multi-source remote sensing data, such as Landsat, MODIS and Sentinel, not only improves the accuracy and comprehensiveness of data processing, but also provides more scientific data support for agricultural production and ecological environment management.

[0055] According to a second aspect of the present invention, a vegetation remote sensing monitoring system based on a geographic information cloud platform is provided. Fig.14 Schematic diagram of a device for dynamic monitoring of vegetation evapotranspiration and identification of driving force according to an embodiment of the present application, Fig.14 As shown, the system comprises: Acquisition module: used to obtain remote sensing image data from the GEE platform, including data sources such as Landsat, MODIS and Sentinel. According to the user-specified time range and plot vector boundary, filter and crop the remote sensing image data that meets the target area; Communication interface: used to interact with GEE server and support data transmission between remote data call and local storage. This interface can realize efficient data request and response, ensuring the real-time and integrity of data acquisition; Processor module: used to process the acquired remote sensing image data, including standardized preprocessing operations such as cloud removal, radiation correction, geometric correction, atmospheric correction and data interpolation; in addition, this module also supports the calculation of vegetation ecological indicators (such as NDVI, kNDVI, LAI, etc.), vegetation drought indicators (such as TVDI) and meteorological factors (such as precipitation, temperature); Display module: used to display the processed monitoring results in a visual form, including spatial distribution diagrams, dynamic time series curves, etc.; supports interactive operations, and users can select the target area to zoom in, zoom out, mark, etc. In addition, the display module provides data export function and supports export to TIFF format or other specified formats.

[0056] Therefore, the vegetation remote sensing monitoring method and system based on the geographic information cloud platform provided by the embodiment of the present invention has the advantages of fast data processing, good visualization effect, simple operation, convenient dissemination, etc., and provides innovative solutions for the fields of vegetation growth monitoring, agricultural management, and ecological environment monitoring. The development of this technology not only helps to promote the research of remote sensing science, but also provides effective tools and methods for resource management and environmental protection in practical applications.

[0057] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vegetation remote sensing monitoring method based on a geographic information cloud platform, characterized in that: The following steps are involved: Determine the time and area of ​​target monitoring, and clarify the geographical boundaries and time range of target monitoring according to user needs; Obtain remote sensing data sources suitable for monitoring needs of the target area, filter remote sensing image data, and crop the filtered remote sensing image data according to the scope of the target area; The cloud removal algorithm is used to process the cloud interference of remote sensing image data and remove the pixels covered by clouds; Performing standardized preprocessing on remote sensing image data, the preprocessing includes: radiation correction, geometric correction, atmospheric correction and data interpolation; Calculate the vegetation ecological index, vegetation drought index and meteorological factors of the target area based on the preprocessed remote sensing image data; The processed vegetation ecological indicators, vegetation drought indicators and meteorological factors are displayed in the form of images on the user interface, and the data can be exported for subsequent analysis.

2. According to claim 1, a vegetation remote sensing monitoring method based on a geographic information cloud platform is characterized in that: The geographical boundaries and time ranges of target monitoring that are clearly defined based on user needs include: Collect the specific needs of users, including the specific geographical coordinates of the target monitoring area, the monitoring time period, and the specific requirements of users for monitoring results; Mark the target monitoring area on the map according to the geographic coordinates provided by the user, and define the geographic boundaries of the target area by uploading vector data files; Automatically parse the start and end dates based on the time range entered by the user.

3. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 1 is characterized in that: The step of obtaining a remote sensing data source suitable for monitoring the target area and screening remote sensing image data includes: The remote sensing data sources suitable for the monitoring needs of the target area are obtained from the Google Earth Engine platform, and the remote sensing data sources include Landsat, MODIS and Sentinel image data.

4. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 3 is characterized in that: The step of clipping the filtered remote sensing image data according to the target area range comprises the following steps: Receive target monitoring time range and plot vector data; Filter the initial remote sensing image dataset based on the time range; The initial remote sensing image dataset is clipped according to the plot boundaries to generate a remote sensing image dataset that meets the needs of the target area.

5. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 1 is characterized in that: The cloud removal algorithm is used to process the cloud interference of the remote sensing image data, and the pixels covered by clouds are removed, which includes the following steps: Automatically extract preset pixels based on the cloud detection band of the image to generate cloud pixel data; Generate a cloud mask layer based on cloud pixel data; The cloud mask layer is used to perform mask operations on the remote sensing image dataset, remove cloud-covered areas and perform pixel completion to obtain the preset de-clouded remote sensing image dataset.

6. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 1 is characterized in that: The vegetation ecological indicators for the target area are calculated as follows: Based on the remote sensing images of the target area, the normalized vegetation index is calculated and the kernel normalized difference vegetation index is generated to reflect the temporal and spatial variation trend of crop growth in the target plot; Extract the leaf area index of the target area and analyze the growth dynamic characteristics of the crop canopy; Based on remote sensing data and regional meteorological conditions, the vegetation light energy absorption fraction and net primary productivity were calculated to evaluate the light energy utilization efficiency and carbon absorption capacity of the vegetation ecosystem.

7. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 6 is characterized in that: The vegetation drought indicators for the target area are calculated as follows: By combining the surface temperature and vegetation coverage of remote sensing images, a temperature vegetation drought index is constructed to generate a dynamic distribution map of drought conditions in the target area, providing drought monitoring data support for agricultural and ecological management.

8. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 1 is characterized in that: The meteorological factors include precipitation and temperature. Through multi-source remote sensing data and meteorological station observation data, the precipitation and temperature information of the target area are extracted to provide necessary parameters for the calculation of vegetation ecological indicators and drought indicators.

9. The vegetation remote sensing monitoring method based on geographic information cloud platform according to claim 1 is characterized in that: The processing of displaying the processed vegetation ecological index, vegetation drought index and meteorological factor in the form of images on the user interface includes: The user interface displays monitoring data in the form of a spatial distribution map, and provides interactive map functions, supports area zooming in, zooming out, marking and plot selection, supports data export functions, selects vegetation ecological indicators, drought index, meteorological factors, and exports data according to specified time periods and areas.

10. A vegetation remote sensing monitoring system based on a geographic information cloud platform, characterized in that: include: The data acquisition module is used to acquire remote sensing image data and filter and crop the remote sensing image data that meets the target area according to the time range and plot vector boundary specified by the user; Communication interface, used for data interaction with the server, supporting data transmission between remote data calls and local storage; The processor module is used to pre-process the acquired remote sensing image data, including cloud removal, radiation correction, geometric correction, atmospheric correction and data interpolation, and supports the calculation of vegetation ecological indicators, vegetation drought indicators and meteorological factors; The display module is used to display the processed monitoring results in a visual form, including spatial distribution diagrams, dynamic time series curves, supporting interactive operations and providing data export functions.

Images