Environmental monitoring and phenological correlation processing method and system based on GEE

Abstract

The invention discloses a GEE-based environment monitoring and phenological correlation processing method and system, and the method comprises the steps: obtaining environment factors of a to-be-researched region, carrying out the environment monitoring on a GEE platform through employing Landsat 8 remote sensing data according to the environment factors, and obtaining a time-space diagram of the environment factors; determining a time soil adjustment vegetation phenological index from the maximum vegetation index and the minimum vegetation index, taking the time soil adjustment vegetation phenological index as a phenological measurement value for phenological correlation analysis, and analyzing the phenological correlation between the phenological measurement value and an index value corresponding to the surface environment variable based on a support vector regression algorithm. According to the method, the remote sensing data in the GEE is adopted to monitor the environmental change and correlate the environmental change with the phenological data, the wave crest and the wave trough of each parameter in the environmental factors can be identified, the significant correlation between the TSPI and the environmental factors is revealed, the diversified analysis and processing efficiency of the environmental monitoring and the phenological correlation is improved, and the accuracy of the phenological correlation evaluation is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of remote sensing application, and in particular relates to a GEE-based environmental monitoring and phenological correlation processing method and system. Background Art

[0002] Environmental changes over time and space have significant impacts on agriculture, forestry, water management, public health and ecosystems. Understanding and monitoring these fluctuations is essential for making informed decisions. While ground-based environmental monitoring methods provide valuable information on trends in soil moisture, temperature, water resources, air quality and land cover, their scope and coverage are often limited, and the use of satellite-based techniques over a wide range of spatial and temporal scales is essential for ecological research. Environmental monitoring is essential for protecting the planet, maintaining ecological balance and improving the quality of human life, and has traditionally relied on ground-based and meteorological data, for example, using Berlin's Netatmo weather station to collect data on temperature, humidity, air pressure, carbon dioxide levels and noise, which is transmitted every five minutes via Wi-Fi. By juxtaposing this information with reference data, the importance of ground-based stations in urban environmental research is emphasized. Similarly, raster format maps of crop-specific land cover were generated using field data. Researchers have developed an advanced IoT system for comprehensive weather monitoring that provides real-time access to a wide range of environmental data, including temperature, humidity, wind speed, humidity, light intensity, UV radiation, and carbon monoxide levels. The system uses multiple ground sensors to collect data and presents it on a dedicated web page through charts and statistics. This setup enhances accessibility and makes monitoring and reference simple and clear. Although these data can provide valuable insights into trends in soil moisture, temperature, or land cover, they are limited to specific regions and require a significant investment of time, money, and labor. This emphasizes the need for remote sensing satellite data as an effective alternative. Remote sensing sensors can quickly collect comprehensive spectral data across regional and global scales, providing extensive and dynamic observation capabilities.

[0003] Efficient environmental management relies on access to a comprehensive database at a given time. Remote sensing technologies and methods can extract key indicators using various principles that capture the electromagnetic properties of the Earth's surface. This expertise provides a valuable resource for analyzing ecological fluctuations in different areas through indices derived from satellite data. Google Earth Engine (GEE) is a valuable cloud-based remote sensing platform that provides rich data resources and powerful functions for conducting change monitoring studies. The platform has played an important role in many studies and provides diverse analysis and processing capabilities. For example, the use of GEE to monitor changes in the Normalized Difference Vegetation Index (NDVI) for crop mapping revealed growth patterns; similarly, a positive correlation between Land Surface Temperature (LST) and NDVI was established using GEE and Landsat 8 imagery, which aided in the assessment of land degradation and land cover classification; forest degradation monitoring was conducted through time series analysis using GEE, effectively mapping with minimal uncertainty to support conservation efforts; the relationship between LST and forest change within the Paphos forest highlighted the usefulness of NDVI and LST in identifying potential forest decline using GEE; and the use of an integrated model and correlation analysis with Landsat-8 data on GEE to predict LST, an innovative approach that enhances the understanding of the impacts of climate change. However, the use of GEE to study key factors such as vegetation cover, land surface temperature, and soil moisture over different time frames has provided valuable insights into environmental changes. These insights are critical for studying various fields, including ecological events such as floods, public health, and crisis management. Therefore, it is crucial to adopt an interdisciplinary approach that transcends traditional scientific boundaries. In this context, specific overarching concepts such as phenology have relevance in multiple scientific disciplines. Phenology is a bridge between environmental observations and remote sensing, involving the monitoring of periodic biological events and the assessment of ecosystem responses to climate change. In addition to measurements, this framework provides a valuable perspective on ecological dynamics through satellite data. Scholars emphasize the strong correlation between phenology and environmental factors, emphasizing its significance in understanding ecosystem processes.

[0004] Therefore, there is an urgent need to provide a GEE-based environmental monitoring and phenological correlation processing method and system to solve the above-mentioned technical problems. Summary of the invention

[0005] In view of this, the present invention provides a GEE-based environmental monitoring and phenological correlation processing method and system for improving the efficiency and rationality of environmental monitoring and phenological correlation processing, using Landsat 8 data in the GEE platform to monitor environmental factors and calculate the phenological index, thereby enhancing the usefulness of the phenological index in understanding seasonal changes, which is specifically implemented by the following specific scheme.

[0006] In a first aspect, the present invention provides a method for environmental monitoring and phenological correlation processing based on GEE, comprising the following steps: Acquire environmental factors of the area to be studied, and use Landsat 8 remote sensing data to perform environmental monitoring on the GEE platform based on the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a timeline map corresponding to the surface environmental variables respectively; Determining a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and using the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; The phenological correlation between the phenological measurement values ​​and the index values ​​corresponding to the surface environmental variables is analyzed based on a support vector regression algorithm, wherein the index values ​​include a minimum value, a maximum value, an average value and a difference value.

[0007] As a preferred embodiment of the above technical solution, Landsat 8 is used to extract the surface temperature, including: The digital DN is converted into the TOA radiation value at the top of the atmosphere, and the TOA radiation value at the top of the atmosphere is converted into the brightness temperature BT. The expression for converting the digital DN into the TOA radiation value at the top of the atmosphere is formula (1), and the expression for converting the TOA radiation value at the top of the atmosphere into the brightness temperature BT is formula (2): (1) (2) in, Indicates the radiation value of band 10, Indicates the increased brightness value of radiation band 10, DN indicates the quantized standard product pixel value, It represents the correction value of band 10 and its value is 0.29. , They represent the specific constants of band 10. To convert the land surface temperature LST from Kelvin to Celsius, you need to subtract 273.15; Get vegetation index NDVI and vegetation ratio , based on the vegetation index NDVI and vegetation ratio Calculate the surface emissivity, the corresponding expression is formula (5): (3) (4) (5) in, is the land surface emissivity, Indicates the vegetation ratio used in the formula in the raster calculator. 0.986 is the correction value of the formula. Indicates band 4, Indicates band 5; The surface temperature LST is estimated based on the TOA radiation value at the top of the atmosphere and the surface emissivity, wherein the surface temperature LST is determined according to Planck's law, and formula (6) is derived according to Planck's law: (6) (7) in, Represents the data of band 10 in Landsat 8, represents the wavelength of the emitted radiation, corresponds to Planck's constant and has a value of , represents the Boltzmann constant and its value is , c represents the beam and its value is .

[0008] As a preferred embodiment of the above technical solution, the soil adjusted vegetation index SAVI is calculated according to the vegetation index NDVI to evaluate the presence of green vegetation. The expression for calculating the soil adjusted vegetation index SAVI in Landsat 8 is formula (8): (8) The distribution of L values ​​indicates the level of change in green vegetation. In areas without any green cover, the L value is set to 1; in areas with moderate greening, the L value is 0.5; in areas with dense vegetation, the L value drops to 0. The L value is used to reflect the vegetation index NDVI, which ranges from -1.0 to 1.0.

[0009] As a preferred embodiment of the above technical solution, the soil moisture index is evaluated and calculated using formula (9): (9) in, and Respectively represent the maximum and minimum surface temperature of each image.

[0010] As a preferred embodiment of the above technical solution, the time soil adjusted vegetation phenological index TSPI is used to quantify the difference between the maximum and minimum vegetation activities in the phenological cycle. The calculation expression of TSPI is: (10) in, and They represent the maximum and minimum values ​​of SAVI each year, respectively. TSPI represents the temporal change of land cover, with 0 representing no change and 1 representing the maximum change.

[0011] As a preferred embodiment of the above technical solution, the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable is analyzed based on a support vector regression algorithm, including: The support vector regression algorithm SVR uses a kernel function to map the data to high dimensions to find a hyperplane that best separates the data points. SVR minimizes the error through regularization terms and slack variables, achieving a balance between maximizing the margin and minimizing the error. The minimized loss function is: (11) in, represents the feature importance, represents the offset decision boundary, and Provides flexibility in data fitting, Used to balance error minimization and overfitting prevention, Define the allowed deviation from the true value, n represents the training examples; The R-squared value in SVR is used to measure the extent to which the independent variable explains the variance of the dependent variable. It is a key indicator for evaluating the model fit in regression analysis. The corresponding expression is: (12) in, is the sum of squares of the errors between the observed and predicted values, is the sum of squares and measures the total variance of the dependent variable.

[0012] As a preferred embodiment of the above technical solution, a support vector regression algorithm is used to analyze and compare the meteorological data with the output environmental factors to verify the analysis results corresponding to the phenological correlation, wherein the meteorological data include the monthly average values ​​of temperature, humidity and precipitation in the area to be studied.

[0013] As a preferred embodiment of the above technical solution, the environmental factors of the area to be studied are obtained, including: The remote sensing images corresponding to the environmental factors are subjected to data preprocessing, wherein the preprocessing includes masking clouds and shadows in the remote sensing images, wherein functions cloudMaskL457 and maskL8sr are used to mask low-quality observations, and bit masks are created using pixel quality assessment bands to identify shadows and clouds through bit operations.

[0014] In a second aspect, the present invention further provides a GEE-based environmental monitoring and phenological correlation processing system, which is applied to the above-mentioned GEE-based environmental monitoring and phenological correlation processing method, comprising: An environmental factor acquisition module is used to acquire environmental factors of the area to be studied, and to perform environmental monitoring on the GEE platform using Landsat 8 remote sensing data based on the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a time line map corresponding to the surface environmental variables respectively; A phenological index determination module, for determining a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and using the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; The phenological correlation analysis module is used to analyze the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable based on the support vector regression algorithm, wherein the index value includes the minimum value, the maximum value, the average value and the difference value.

[0015] The invention provides a method and system for processing environmental monitoring and phenological correlation based on GEE. Environmental factors of a research area are obtained, and environmental monitoring is performed on a GEE platform using Landsat 8 remote sensing data according to the environmental factors to obtain a spatiotemporal map of the environmental factors. A temporal soil-adjusted vegetation phenological index is determined from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal map, and the temporal soil-adjusted vegetation phenological index is used as a phenological measurement value for phenological correlation analysis. The phenological correlation between the phenological measurement value and an index value corresponding to the surface environmental variable is analyzed based on a support vector regression algorithm. Remote sensing data in GEE is used to monitor environmental changes and is associated with phenological data. The peaks and troughs of each parameter in the environmental factors can be identified. SVR analysis reveals a significant correlation between TSPI and environmental factors, thereby improving the efficiency of diversified analysis and processing of environmental monitoring and phenological correlation, and improving the accuracy of phenological correlation evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flow chart of the GEE-based environmental monitoring and phenological correlation processing method provided by the present invention; Figure 2The monthly average graph of precipitation, air humidity and temperature in YLYLM Province from 2014 to 2021 provided by the present invention; Figure 3 The TSPI map of YLYLM Province from 2014 to 2021 provided by the present invention; Figure 4 The average TSPI timeline chart of YLYLM Province provided by the present invention (2014-2021); Figure 5 This is a flow chart of the GEE-based environmental monitoring and phenological correlation processing system provided by the present invention. DETAILED DESCRIPTION

[0018] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0019] See also Figure 1 The present invention provides a GEE-based environmental monitoring and phenological correlation processing method, comprising the following steps: S10: Obtain environmental factors of the area to be studied, and use Landsat8 remote sensing data to perform environmental monitoring on the GEE platform according to the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a time line map corresponding to the surface environmental variables respectively; S11: determining a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and using the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; S12: Analyze the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable based on a support vector regression algorithm, wherein the index value includes a minimum value, a maximum value, an average value and a difference value.

[0020] In this example, remote sensing data and Google Earth Engine were used to analyze environmental fluctuations in YLYLM province from 2014 to 2021. We focused on monitoring environmental variables and their correlation with phenology, using support vector regression (SVR) techniques. Landsat 8 satellite data were used to generate time series plots and timelines of land cover, temperature, and soil moisture, using soil adjusted vegetation index (SAVI), land surface temperature (LST) anomalies, and soil moisture index (SMI). Subsequently, the temporal soil adjusted vegetation phenology index (TSPI) was calculated to monitor annual vegetation changes, and the correlation with the specified parameters was analyzed using the R square value in the SVR analysis. The present invention revealed significant changes in environmental attributes and strong correlations with the TSPI index, with soil moisture peaking in late winter and spring but declining in summer, reaching a maximum in 2018, vegetation being most abundant in mid-spring and least in winter, with significant greening in 2019, with the highest temperatures in summer and the lowest in winter, and the least interannual variation. Spatial pattern monitoring showed that surface temperatures continued to rise from the north and east to the south and west, associated with a decreasing trend in vegetation and soil moisture levels. Regression analysis indicated robust associations between TSPI and environmental variables, with R-squared values ​​of 0.84 for LST, 0.91 for SAVI, and 0.79 for SMI. These underscore the effectiveness of remote sensing methods, such as time-series satellite imagery and simplified indices, for large-scale ecological analyses using the GEE platform, highlighting the potential of TSPI as a key indicator for future environmental management studies.

[0021] It should be noted that the ecosystem has a rich diversity of land cover, which is affected by spatial differences and seasonal dynamics. The area to be studied is the YLYLM province, which is an ideal study object due to its diverse climate and landscape. The coordinate range of the YLYLM province is from 33°19' to 35°54'N, and 38°45' to 30°52'E, with an area of ​​20,133 square kilometers and an average altitude of 1,218 meters. The northern and eastern parts of the province are mountainous, dominated by semi-forested areas, with a cold and semi-humid climate, while the western and southern parts are arid deserts with a hot and dry climate. Continuous Landsat 8 remote sensing data were used. These data were chosen because of their reliability and accessibility, as demonstrated by GEE since 2013, as well as their suitable spectral and spatial resolution, which enable continuous monitoring of environmental variables through relevant spectral indices, thus facilitating detailed analysis of surface properties and trends. Detailed resolution information is provided in Appendix 1.

[0022] Table 1: Resolution of Landsat 8

[0023] Meteorological data are incorporated into this embodiment and compared with the output environmental factors through regression analysis to verify the results. The data set includes monthly averages of temperature, humidity and precipitation obtained from weather stations obtained from the Meteorological Bureau. The environmental factors of the area to be studied are obtained by preprocessing the remote sensing images corresponding to the environmental factors, wherein the preprocessing includes masking clouds and shadows in the remote sensing images, wherein functions cloudMaskL457 and maskL8sr are used to mask low-quality observations, and bit masks are created using pixel quality assessment bands to identify shadows and clouds through bit operations. Using the SAVI index, LST anomaly and SMI index, time series graphs and timeline graphs of three key factors were extracted using Landsat 8 data on the GEE platform: land cover, temperature and soil moisture. These maps illustrate the annual trends and spatial patterns of the entire study area by showing the distribution of environmental variables. In addition, the corresponding charts show the temporal fluctuations, highlighting the peaks and lowest points of each parameter in eight consecutive years from 2014 to 2021. In addition, the correlation between these data sets and meteorological data is analyzed to confirm the maps and charts obtained.

[0024] In the subsequent phenological correlation process, TSPI, a phenological measure derived from the SAVI-max and SAVI-min vegetation indices, was analyzed for its correlation with each index value (minimum, maximum, mean, and difference) using support vector regression (SVR).

[0025] It should be understood that by obtaining the environmental factors of the area to be studied, and using Landsat 8 remote sensing data on the GEE platform to conduct environmental monitoring based on the environmental factors, a spatiotemporal map of the environmental factors is obtained, and the temporal soil-adjusted vegetation phenological index is determined from the maximum vegetation index and the minimum vegetation index based on the spatiotemporal map, and the temporal soil-adjusted vegetation phenological index is used as the phenological measurement value for phenological correlation analysis, and the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable is analyzed based on the support vector regression algorithm. The remote sensing data in GEE is used to monitor environmental changes and associate it with the phenological data, and the peaks and troughs of each parameter in the environmental factors can be identified. The SVR analysis reveals the significant correlation between TSPI and environmental factors, improves the efficiency of diversified analysis and processing of environmental monitoring and phenological correlation, and improves the accuracy of phenological correlation assessment.

[0026] Optionally, extract land surface temperature using Landsat 8, including: The digital DN is converted into the TOA radiation value at the top of the atmosphere, and the TOA radiation value at the top of the atmosphere is converted into the brightness temperature BT. The expression for converting the digital DN into the TOA radiation value at the top of the atmosphere is formula (1), and the expression for converting the TOA radiation value at the top of the atmosphere into the brightness temperature BT is formula (2): (1) (2) in, Indicates the radiation value of band 10, Indicates the increased brightness value of radiation band 10, DN indicates the quantized standard product pixel value, It represents the correction value of band 10 and its value is 0.29. , They represent the specific constants of band 10. To convert the land surface temperature LST from Kelvin to Celsius, you need to subtract 273.15; Get vegetation index NDVI and vegetation ratio , based on the vegetation index NDVI and vegetation ratio Calculate the surface emissivity, the corresponding expression is formula (5): (3) (4) (5) in, is the land surface emissivity, Indicates the vegetation ratio used in the formula in the raster calculator. 0.986 is the correction value of the formula. Indicates band 4, Indicates band 5; The surface temperature LST is estimated based on the TOA radiation value at the top of the atmosphere and the surface emissivity, wherein the surface temperature LST is determined according to Planck's law, and formula (6) is derived according to Planck's law: (6) (7) in, Represents the data of band 10 in Landsat 8, represents the wavelength of the emitted radiation, corresponds to Planck's constant and has a value of , represents the Boltzmann constant and its value is , c represents the beam and its value is .

[0027] In this embodiment, LST refers to the heat energy released from the earth's surface and captured in the atmosphere. Landsat 8 OLI / TIRS has a specific band to extract this thermal data anomaly. Top of Atmosphere Reflectivity (TOA): TOA (Top of Atmosphere) reflectivity refers to the reflectivity of satellite remote sensing images when they reach the ground after passing through the atmosphere. It does not consider the effects of the surface and atmosphere on light absorption, scattering and reflection. Therefore, TOA reflectivity is the most basic data obtained by satellite remote sensing images.

[0028] Optionally, the soil adjusted vegetation index SAVI is calculated based on the vegetation index NDVI to assess the presence of green vegetation. The expression for calculating the soil adjusted vegetation index SAVI in Landsat 8 is formula (8): (8) The distribution of L values ​​indicates the level of change in green vegetation. In areas without any green cover, the L value is set to 1; in areas with moderate greening, the L value is 0.5; in areas with dense vegetation, the L value drops to 0. The L value is used to reflect the vegetation index NDVI, which ranges from -1.0 to 1.0.

[0029] In this embodiment, the soil moisture index is evaluated and calculated using formula (9): (9) in, and denote the maximum and minimum land surface temperatures of each image, respectively. The evaluation of SMI has attracted much attention in previous studies involving remote sensing parameters. A reliable method applied in this context is to utilize LST.

[0030] Optionally, the time soil adjusted vegetation phenology index (TSPI) is used to quantify the difference between the maximum and minimum vegetation activities in the phenological cycle. The calculation expression of TSPI is: (10) in, and Representing the maximum and minimum values ​​of SAVI each year, TSPI represents the temporal change in land cover, with 0 indicating no change and 1 indicating maximum change. Phenological indices are valuable tools for monitoring developments that occur annually or seasonally throughout the growing cycle. It helps track the response of ecosystems to environmental fluctuations using the Temporal SAVI Phenological Index (TSPI), which quantifies the difference between the maximum and minimum vegetation activity during the phenological cycle. This temporal index provides concise insights into phenological changes caused by changes in environmental factors.

[0031] Optionally, analyzing the phenological correlation between the phenological measurement value and the indicator value corresponding to the surface environmental variable based on a support vector regression algorithm includes: The support vector regression algorithm SVR uses a kernel function to map the data to high dimensions to find a hyperplane that best separates the data points. SVR minimizes the error through regularization terms and slack variables, achieving a balance between maximizing the margin and minimizing the error. The minimized loss function is: (11) in, represents the feature importance, represents the offset decision boundary, and Provides flexibility in data fitting, Used to balance error minimization and overfitting prevention, Define the allowed deviation from the true value, n represents the training examples; The R-squared value in SVR is used to measure the extent to which the independent variable explains the variance of the dependent variable. It is a key indicator for evaluating the model fit in regression analysis. The corresponding expression is: (12) in, is the sum of squares of the errors between the observed and predicted values, is the sum of squares and measures the total variance of the dependent variable.

[0032] In this embodiment, a support vector regression algorithm is used to analyze and compare meteorological data with the output environmental factors to verify the analysis results corresponding to the phenological correlation, wherein the meteorological data includes the monthly averages of temperature, humidity and precipitation in the area to be studied. The statistical analysis uses support vector regression (SVR), which effectively investigates the relationship between the encountered variables. SVR uses kernel functions to map data to higher dimensions, aiming to find a hyperplane that best separates data points. It minimizes the error through regularization terms and slack variables, striking a balance between maximizing margin and minimizing error.

[0033] Specifically, environmental factors monitoring included multi-temporal LST based on Landsat 8 data, multi-temporal SAVI based on Landsat 8 data, and multi-temporal SMI based on Landsat 8 data. Maps and timelines of the three key factors (LST, SAVI, and SMI) throughout the measurement period provided insights into their fluctuations and evolution. The results of the correlation study between these factors and TSPI were presented through regression analysis, aiming to clarify the relationship between environment and phenology. This analytical approach enabled us to quantify and explain the correlations between these variables, revealing potential ecological patterns and dynamics.

[0034] Among them, multi-temporal images refer to the characteristics of a set of remote sensing images in a time series, including image data acquired at different times such as satellite remote sensing. These images can be used for dynamic analysis and change detection. LST reaches its highest values ​​in June, July and August, and its lowest levels in December, January and February. The LST chart shows that the fluctuations from different years are minimal, and the annual chart always depicts a very similar and unchanging pattern. At the provincial level, the LST distribution shows an upward trend from the mountainous areas in the north and east to the desert areas in the south and west. The 2021 LST map shows a significant increase in the high temperature area expanding westward, while the 2015 map clearly shows a significant decrease. As shown in Table 2, the highest LST recorded in 2021 is in sharp contrast to the lowest point observed in 2017, and the average levels in 2015 and 2021 are the lowest and highest.

[0035] Table 2: Maximum, minimum, average and difference of LST (℃) in YLYLM Province from 2014 to 2021

[0036] The multi-temporal SAVI based on Landsat 8 data includes: a SAVI timeline for the entire measurement period, an annual average SAVI map, and significant changes in green area cover over the years. These maps show a decreasing trend in green area from the highlands in the northern and eastern regions of the province to the arid and desert areas in the southern and western regions. As shown in Table 3, the monthly fluctuations continue to show higher SAVI values ​​in the spring, while the lowest values ​​are recorded in the winter. The annual map shows the changes, with a significant increase in green area in 2019 and 2020 compared to other years. The lowest average green area level was recorded in 2014. In addition, 2015 had the most annual changes, while 2021 had the least changes.

[0037] Table 3: Maximum, minimum, average and difference of SAVI index values ​​in YLYLM Province from 2014 to 2021

[0038] The multi-temporal SMI based on Landsat 8 data includes: Soil moisture maps show that the highest SMI levels are in November and December, while the lowest values ​​are in July and August, with a comprehensive breakdown of the annual SMI values ​​in Table 4. The SMI map shows a gradual upward trend from the southern and western regions to the central, northern and eastern regions. It is noteworthy that there is a strong correlation between the index and the vegetation levels over the 5-month period. The peaks and troughs in the SAVI map are closely aligned with the highest and lowest values ​​in the SMI map.

[0039] Table 4: Maximum, minimum, average and difference of SMI index in YLYLM province from 2014 to 2021

[0040] Soil Adjusted Vegetation Phenological Index (TSPI): TSPI is calculated by determining the maximum and minimum values ​​of the SAVI index each year. Figure 2 describes the TSPI distribution pattern, and the subsequent Tables 5 and Figure 3 The average values ​​for each year of the study area are shown. In both 2014 and 2021, the TSPI values ​​reached extremes, marking peaks and troughs in greening fluctuations. As shown in the map, there is no obvious pattern in the distribution of this index. Figure 4 A continuous and gradual downward trend in the average annual amounts is depicted, with the exception of 2017, when a significant increase in the index value was recorded.

[0041] Table 5: Average TSPI in YLYLM Province from 2014 to 2021

[0042] Specifically, the statistical analysis included environmental parameters and phenological indices, environmental parameters and ground meteorological data, and environmental parameters and phenological indices included LST and TSPI, SAVI and TSPI, SMI and TSPI. The correlation between the mean values ​​of the specified phenological indices and the three discussed environmental variables (LST, SAVI, and SMI) was examined by SVR analysis, and nonlinear regression was performed using the RBF kernel, with "C=100" set as regularization, "gamma=0.1" set as the influence range, and "epsilon=.1" set as the prediction tolerance. The SVR analysis of different LST indices (minimum, maximum, difference, and average) and the annual average TSPI value showed significant correlation. The R-squared value between TSPI and LST was as small as 0.84 and as large as 0.76, with a difference of 0.79 and an average of 0.67, as shown in Table 6.

[0043] Table 6: Regression analysis results of LST value and TSPI

[0044] Table 7 shows the results of the SVR analysis of the mean values ​​of TSPI and SAVI values ​​for each year, highlighting the strong correlation between these parameters. This alignment strengthens the relationship between phenology and greening index. The R-squared values ​​for the minimum, maximum, difference, and mean SAVI of TSPI were 0.91, 0.62, 0.64, and 0.74, respectively. These values ​​quantify the proportion of variability in TSPI that is explained by each corresponding aspect of SAVI.

[0045] Table 7: Correlation analysis results between SAVI value and TSPI

[0046] Regression analysis showed that there was a moderate correlation between SMI values ​​and TSPI, with an R-squared value of approximately 0.4, as detailed in Table 8. In addition, the peaks on the SMI graph corresponded strongly to the peaks on the SAVI graph within a specific time range. This suggests that there is a significant correlation between SMI and SAVI, with a time lag of approximately five months due to the greening period.

[0047] Table 8: Correlation analysis results between SMI value and TSPI

[0048] See also Figure 5 The present invention also provides a GEE-based environmental monitoring and phenological correlation processing system, which is applied to the above-mentioned GEE-based environmental monitoring and phenological correlation processing method, including: An environmental factor acquisition module is used to acquire environmental factors of the area to be studied, and to perform environmental monitoring on the GEE platform using Landsat 8 remote sensing data based on the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a time line map corresponding to the surface environmental variables respectively; A phenological index determination module, used to determine a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and use the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; The phenological correlation analysis module is used to analyze the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable based on the support vector regression algorithm, wherein the index value includes the minimum value, the maximum value, the average value and the difference value.

[0049] In this example, the correlation between the mean values ​​of the generating parameters (LST, SAVI, SMI) and the meteorological data (monthly mean values ​​of air temperature, humidity and precipitation) was examined using SVR analysis. A strong relationship was found between the ground-based measurements and remote sensing data, specifically, the R-squared values ​​indicated substantial correlations; 0.89 for LST and air temperature, 0.78 for SAVI and air humidity, and 0.72 for SMI and precipitation, which confirmed the reliability of the generating factors. Spatiotemporal maps of environmental factors were generated using advanced remote sensing techniques, which effectively illustrated the dynamics and trends of variables such as temperature, vegetation and soil moisture in YLYLM Province. Spatial analysis using LST, SAVI and SMI maps showed an increasing trend in surface temperature from the mountainous areas in the northeast to the desert areas in the southwest, while green areas and soil moisture showed a decreasing trend. The analysis of greening time depicted by the SAVI timeline map showed that the peak in spring was associated with the optimum air temperature and rainfall, while the minimum in winter was consistent with previous studies. According to the observations, the land surface temperature was consistently highest in summer and lowest in winter, with minimal interannual fluctuations. Assessment of soil moisture through the SMI showed maxima in late winter and spring in contrast to minima in summer, and ground data confirmed these results.

[0050] It should be noted that the average values ​​of LST, SAVI and SMI were the highest in 2021, 2019 and 2018, while the lowest values ​​were found in 2015, 2014 and 2020. Temporal vegetation phenology was assessed using the TSPI index, which uses the annual minimum and maximum SAVI values ​​as a reliable indicator. Due to the semi-arid conditions in the study area, SAVI was chosen as the index because it effectively addresses the soil brightness issue by incorporating the L value into the NDVI formula. TSPI provides a precise method to quantify the impact of environmental factors on the phenological cycle, and the corresponding timeline graph shows an overall downward trend, with the most significant greening change in 2014 and the lowest point in 2021, except for 2017. SVR analysis was then conducted to explore the correlation between environmental factors (including maximum, minimum, mean and differential values) and the annual mean values ​​of TSPI, revealing a significant correlation between TSPI and these variables in the specified study area, with SVR R-square values ​​of 0.84 for LST, 0.91 for SAVI and 0.79 for mean SMI.

[0051] A significant correlation was found between SMI and greenness over a five-month timeframe. A peak in soil moisture in late November 2018 coincided with the maximum greenness observed in April 2019. Conversely, a decrease in soil moisture content in 2020 resulted in less greening in the 2021 SAVI map. This correlation is due to favorable temperature conditions that promote plant growth, facilitated by optimal soil moisture. The time lag is a result of the green cycle, which was taken into account when estimating the correlation between the SMI index and TSPI. These results suggest that adequate rainfall and high soil moisture in autumn and winter will lead to a lush spring. Conversely, insufficient rainfall will result in reduced greening. The results were validated by the correlation between the extracted variables and the ground data, with R-squared values ​​showing significant correlations: 0.89 between LST and air temperature, 0.78 between SAVI and air humidity, and 0.72 between SMI and precipitation. The analysis highlights the effectiveness of remote sensing technology for accurate environmental monitoring. Furthermore, the strong correlations between environmental factors and vegetation phenology suggest that the TSPI index has the potential to become a reliable environmental factor for future studies, potentially reducing the need for large datasets in time series analysis.

[0052] It should be understood that remote sensing indices in GEE were used to monitor environmental changes and correlated with phenological data, track the spatiotemporal changes in green cover, temperature, and soil moisture, and analyze time series graphs and charts derived from SAVI, LST, and SMI data. This visualization is able to track the changes in environmental conditions over time, identify the peaks and troughs of each parameter, and reveal spatial trends across the province. Characterized by heterogeneous land cover and weather patterns, different patterns emerged for these environmental parameters. Notably, green and soil moisture increased from the southern and western regions to the northern and eastern regions, while surface temperature decreased, indicating a clear negative correlation between them and temperature. In addition, time series analysis revealed significant fluctuations in land cover and soil moisture over time, while changes in surface temperature were relatively less pronounced. SVR analysis revealed significant correlations between TSPI and environmental factors, effectively tracking changes in vegetation phenology. This provides valuable insights for future ecological studies. TSPI can be used as a key environmental parameter in various algorithms, including those for risk assessment and environmental prediction.

[0053] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0054] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A GEE-based environmental monitoring and phenological correlation processing method, characterized in that: The following steps are involved: Acquire environmental factors of the area to be studied, and use Landsat 8 remote sensing data to perform environmental monitoring on the GEE platform based on the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a timeline map corresponding to the surface environmental variables respectively; Determining a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and using the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; The phenological correlation between the phenological measurement values ​​and the index values ​​corresponding to the surface environmental variables is analyzed based on a support vector regression algorithm, wherein the index values ​​include a minimum value, a maximum value, an average value and a difference value.

2. The GEE-based environmental monitoring and phenological correlation processing method according to claim 1, characterized in that: Using Landsat 8 to extract land surface temperature, including: The digital DN is converted into the TOA radiation value at the top of the atmosphere, and the TOA radiation value at the top of the atmosphere is converted into the brightness temperature BT. The expression for converting the digital DN into the TOA radiation value at the top of the atmosphere is formula (1), and the expression for converting the TOA radiation value at the top of the atmosphere into the brightness temperature BT is formula (2): （1） （2） in, Indicates the radiation value of band 10, Indicates the increased brightness value of radiation band 10, DN indicates the quantized standard product pixel value, It represents the correction value of band 10 and its value is 0.

29. , They represent the specific constants of band 10. To convert the land surface temperature LST from Kelvin to Celsius, you need to subtract 273.15; Get vegetation index NDVI and vegetation ratio , based on the vegetation index NDVI and vegetation ratio Calculate the surface emissivity, the corresponding expression is formula (5): （3） （4） （5） in, is the land surface emissivity, Indicates the vegetation ratio used in the formula in the raster calculator. 0.986 is the correction value of the formula. Indicates band 4, Indicates band 5; The surface temperature LST is estimated based on the TOA radiation value at the top of the atmosphere and the surface emissivity, wherein the surface temperature LST is determined according to Planck's law, and formula (6) is derived according to Planck's law: （6） （7） in, Represents the data of band 10 in Landsat 8, represents the wavelength of the emitted radiation, corresponds to Planck's constant and has a value of , represents the Boltzmann constant and its value is , c represents the beam and its value is .

3. The GEE-based environmental monitoring and phenological correlation processing method according to claim 2, characterized in that: The soil-adjusted vegetation index (SAVI) is calculated based on the vegetation index NDVI to assess the presence of green vegetation. The expression for calculating the soil-adjusted vegetation index (SAVI) in Landsat 8 is formula (8): （8） The distribution of L values ​​indicates the level of change in green vegetation. In areas without any green cover, the L value is set to 1; in areas with moderate greening, the L value is 0.5; in areas with dense vegetation, the L value drops to 0. The L value is used to reflect the vegetation index NDVI, which ranges from -1.0 to 1.

0.

4. The method for environmental monitoring and phenological correlation processing based on GEE according to claim 3, characterized in that: The soil moisture index is evaluated and calculated using formula (9): （9） in, and Respectively represent the maximum and minimum surface temperature of each image.

5. The method for environmental monitoring and phenological correlation processing based on GEE according to claim 4, characterized in that: The time-adjusted soil vegetation phenology index (TSPI) is used to quantify the difference between the maximum and minimum vegetation activities in the phenological cycle. The calculation expression of TSPI is: （10） in, and They represent the maximum and minimum values ​​of SAVI each year, respectively. TSPI represents the temporal change of land cover, with 0 representing no change and 1 representing the maximum change.

6. The method for environmental monitoring and phenological correlation processing based on GEE according to claim 1, characterized in that: Analyzing the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable based on a support vector regression algorithm includes: The support vector regression algorithm SVR uses a kernel function to map the data to high dimensions to find a hyperplane that best separates the data points. SVR minimizes the error through regularization terms and slack variables, achieving a balance between maximizing the margin and minimizing the error. The minimized loss function is: （11） in, represents the feature importance, represents the offset decision boundary, and Provides flexibility in data fitting, Used to balance error minimization and overfitting prevention, Define the allowed deviation from the true value, n represents the training examples; The R-squared value in SVR is used to measure the extent to which the independent variable explains the variance of the dependent variable. It is a key indicator for evaluating the model fit in regression analysis. The corresponding expression is: （12） in, is the sum of squares of the errors between the observed and predicted values, is the sum of squares and measures the total variance of the dependent variable.

7. The method for environmental monitoring and phenological correlation processing based on GEE according to claim 6, characterized in that: Also includes: The support vector regression algorithm is used to analyze and compare the meteorological data with the output environmental factors to verify the analysis results corresponding to the phenological correlation, wherein the meteorological data includes the monthly average values ​​of temperature, humidity and precipitation in the area to be studied.

8. The method for environmental monitoring and phenological correlation processing based on GEE according to claim 1, characterized in that: Obtain environmental factors of the area to be studied, including: The remote sensing images corresponding to the environmental factors are subjected to data preprocessing, wherein the preprocessing includes masking clouds and shadows in the remote sensing images, wherein functions cloudMaskL457 and maskL8sr are used to mask low-quality observations, and bit masks are created using pixel quality assessment bands to identify shadows and clouds through bit operations.

9. A GEE-based environmental monitoring and phenological correlation processing system, characterized in that: The method for processing environmental monitoring and phenological correlation based on GEE as claimed in any one of claims 1 to 8 comprises: An environmental factor acquisition module is used to acquire environmental factors of the area to be studied, and to perform environmental monitoring on the GEE platform using Landsat 8 remote sensing data based on the environmental factors to obtain a spatiotemporal map of the environmental factors, wherein the environmental factors include meteorological data and surface environmental variables, the surface environmental variables include soil adjusted vegetation index, surface temperature and soil moisture index, and the spatiotemporal map includes a time series map and a time line map corresponding to the surface environmental variables respectively; A phenological index determination module, used to determine a temporal soil-adjusted vegetation phenological index from a maximum vegetation index and a minimum vegetation index according to the spatiotemporal graph, and use the temporal soil-adjusted vegetation phenological index as a phenological measurement value for phenological correlation analysis; The phenological correlation analysis module is used to analyze the phenological correlation between the phenological measurement value and the index value corresponding to the surface environmental variable based on the support vector regression algorithm, wherein the index value includes the minimum value, the maximum value, the average value and the difference value.

Images