A vegetation restoration trend evaluation method based on remote sensing data

Abstract

The embodiment of the application discloses a kind of vegetation recovery trend evaluation methods based on remote sensing data, it is related to remote sensing data analysis technical field, the method comprises: obtaining the vegetation index remote sensing image set of the region to be researched, generate the start time grid chart of vegetation growing season, end time grid chart, vegetation growing season length grid chart;The vegetation index trend and vegetation growing season length trend of each pixel unit in preset period are calculated;Vegetation recovery ecological index is calculated based on vegetation index trend and vegetation growing season length trend, and the spatial distribution diagram of the vegetation recovery ecological index of the region to be researched is generated.The application can generate the spatial distribution diagram of vegetation recovery ecological index according to vegetation recovery ecological index and corresponding pixel unit, so as to provide data support for the related research of vegetation recovery effect remarkable area and key repair area, with the advantages of efficient, flexible and accurate, widely used in ecological restoration and environmental protection field.

Description

Technical Field

[0001] This application relates to the field of remote sensing data analysis technology, and in particular to a method for assessing vegetation restoration trends based on remote sensing data. Background Technology

[0002] Vegetation restoration assessment is a core task in ecological environmental protection and restoration, providing a scientific basis for evaluating the effectiveness of ecological engineering projects, formulating ecological restoration strategies, and implementing environmental management. With increasing global climate change and intensified human activities, the urgency of ecological restoration is constantly growing, and the accuracy of vegetation restoration assessment directly affects the scientific validity of ecological protection policies. Remote sensing technology, as an efficient, non-contact monitoring method with spatial resolution advantages, has been widely used in the field of vegetation monitoring. By analyzing remote sensing data, dynamic changes in vegetation cover, greenness, and growth status can be monitored.

[0003] Currently, the Normalized Difference Vegetation Index (NDVI) is commonly used in remote sensing data processing to reflect surface vegetation cover and growth status, and it is widely applied in vegetation monitoring, ecological assessment, and environmental change research. By reflecting the photosynthetic capacity of plants, NDVI can provide information on vegetation growth status at different temporal and spatial scales. Trend analysis of multi-year NDVI time-series data can generate trend maps of vegetation cover change, thereby quantifying the dynamic changes in regional vegetation and providing quantitative evidence for ecological restoration and degradation monitoring.

[0004] However, relying solely on single vegetation indices such as NDVI to analyze vegetation cover changes is insufficient to fully reveal the complexity of vegetation dynamics during ecological restoration, especially regarding the impact of growing season variations on ecosystem recovery. Although many vegetation restoration assessment methods based on remote sensing data exist, most focus on changes in vegetation cover or specific vegetation indices at a single point in time, failing to comprehensively reveal the dynamic characteristics of vegetation during the growing season. Summary of the Invention

[0005] This application provides a method for assessing vegetation restoration trends based on remote sensing data, which addresses the shortcomings of the aforementioned related technologies. The technical solution is as follows:

[0006] In a first aspect, embodiments of this application provide a method for assessing vegetation restoration trends based on remote sensing data, including:

[0007] Acquire a set of vegetation index remote sensing images of the area to be studied; the set of vegetation index remote sensing images includes vegetation index remote sensing images arranged in chronological order within a preset period;

[0008] Based on each vegetation index remote sensing image in the vegetation index remote sensing image set, the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period are calculated, and the start time raster map and end time raster map of the vegetation growth season in the corresponding sub-period are generated.

[0009] Generate a vegetation growth season length raster map for each sub-period based on the start time raster map and end time raster map for each sub-period.

[0010] The vegetation index trend of each pixel unit within the preset period is calculated based on the vegetation index remote sensing image set. The vegetation growth season length trend of each pixel unit within the preset period is calculated based on the start time raster, end time raster and vegetation growth season length raster of each sub-period.

[0011] The vegetation restoration ecological index is calculated based on the vegetation index trend and the vegetation growth season length trend, and a spatial distribution map of the vegetation restoration ecological index of the area to be studied is generated.

[0012] In one alternative embodiment of the first aspect, before calculating the start and end times of the vegetation growing season for each pixel unit based on each vegetation index remote sensing image in the vegetation index remote sensing image set, the method further includes:

[0013] The vegetation index remote sensing images in the vegetation index remote sensing image set are preprocessed by interpolation to fill in missing data, and the region of interest of each vegetation index remote sensing image is cropped. Each vegetation index remote sensing image is processed to a preset temporal resolution, and each vegetation index remote sensing image is processed to a preset spatial resolution by resampling. The preprocessed vegetation index remote sensing image set is then output.

[0014] In one alternative embodiment of the first aspect, the step of calculating the start and end times of the vegetation growth season for each pixel unit in the corresponding sub-period based on each vegetation index remote sensing image in the vegetation index remote sensing image set, and generating a start time raster map and an end time raster map of the vegetation growth season for the corresponding sub-period, includes:

[0015] Extract the vegetation index time series of each pixel unit in the remote sensing image of each sub-time period;

[0016] The first derivative time series of vegetation index for each pixel unit is calculated using the first derivative method based on the vegetation index time series.

[0017] Based on the time series of the first derivative of the vegetation index, the time corresponding to the maximum value of the first derivative is determined, and the start time of the vegetation growth season for each pixel unit is obtained; based on the time series of the first derivative of the vegetation index, the time corresponding to the minimum value of the first derivative is determined, and the end time of the vegetation growth season for each pixel unit is obtained.

[0018] The start time of the vegetation growing season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the start time of each sub-period; the end time of the vegetation growing season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the end time of each sub-period.

[0019] In one alternative embodiment of the first aspect, generating a vegetation growth season length raster map corresponding to each sub-period based on the start time raster map and the end time raster map of each sub-period includes:

[0020] The start and end times of the vegetation growing season for each grid cell are determined based on the start and end time grids of the same sub-period.

[0021] The length of the vegetation growing season for the corresponding grid is calculated by subtracting the start and end times of the vegetation growing season.

[0022] Based on the vegetation growth season length of each grid cell in the area under study in the same sub-period, a vegetation growth season length raster map for the corresponding sub-period is generated.

[0023] In one alternative embodiment of the first aspect, the calculation process for the vegetation index trend and the vegetation growing season length trend includes the following steps:

[0024] Based on the vegetation index remote sensing image set, generate vegetation index time series data for each pixel unit of the area to be studied within the preset period;

[0025] Based on the vegetation growth season length raster map of each sub-period, the time series data of the vegetation growth season length of each pixel unit in the area under study within the preset period is generated.

[0026] The significance parameter of each pixel unit is calculated based on the difference between every two data points in the vegetation index time series data and the vegetation growth season length time series data, respectively. Pixel units with significance parameters greater than a preset threshold are extracted to generate significant change regions.

[0027] The slopes of the vegetation index time series data and the vegetation growth season length time series data for each pixel unit in the significantly changing region are calculated respectively, and the vegetation index trend and vegetation growth season length trend of each pixel unit in the significantly changing region within the preset period are obtained.

[0028] In one alternative embodiment of the first aspect, before calculating the vegetation restoration ecological index based on the vegetation index trend and the vegetation growing season length trend, the method further includes:

[0029] The vegetation index trend and vegetation growing season length trend in the area to be studied were normalized.

[0030] Divide the vegetation index trend of each pixel unit by the maximum absolute value of the vegetation index trend in the area under study, and output the normalized vegetation index trend.

[0031] Divide the vegetation growth season length trend of each pixel unit by the maximum absolute value of the vegetation growth season length trend in the area under study, and output the normalized vegetation index trend.

[0032] In one alternative embodiment of the first aspect, the calculation of the vegetation restoration ecological index based on the vegetation index trend and the vegetation growing season length trend includes:

[0033] Calculate the weighted sum of the vegetation index trend and the vegetation growing season length trend for each pixel unit within the study area, and output the vegetation restoration ecological index for each pixel unit, using the formula:

[0034] VREI =

[0035] w1*NDVI norm +w2*LOS norm ;

[0036] Where VREI is the vegetation restoration ecological index, w1 is the weight of the vegetation index trend, and NDVI norm The trend of vegetation indices is represented by w2, where w2 is the weight of the trend of vegetation growing season length, and LOS is the mean. norm This represents the trend of vegetation growing season length.

[0037] Secondly, embodiments of this application also provide a vegetation restoration trend assessment device based on remote sensing data, comprising:

[0038] The data acquisition module is used to acquire a set of vegetation index remote sensing images of the area to be studied; the set of vegetation index remote sensing images includes vegetation index remote sensing images arranged in chronological order within a preset period.

[0039] The data processing unit is used to calculate the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period based on each vegetation index remote sensing image in the vegetation index remote sensing image set, and is also used to generate a raster map of the start time and the end time of the vegetation growth season in the corresponding sub-period.

[0040] The data processing unit is also used to generate a vegetation growth season length raster map for the corresponding sub-period based on the start time raster map and end time raster map for each sub-period.

[0041] The data processing unit is also used to calculate the vegetation index trend of each pixel unit within the preset period based on the vegetation index remote sensing image set, and is also used to calculate the vegetation growth season length trend of each pixel unit within the preset period based on the start time raster, end time raster and vegetation growth season length raster of each sub-period.

[0042] The data output unit is used to calculate the vegetation restoration ecological index based on the vegetation index trend and the vegetation growth season length trend, and generate a spatial distribution map of the vegetation restoration ecological index of the area to be studied.

[0043] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method provided by the first aspect or any implementation thereof of the embodiments of this application.

[0044] Fourthly, this application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided by the first aspect of the embodiments of this application or any implementation thereof.

[0045] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following:

[0046] This application provides a method for assessing vegetation restoration trends based on remote sensing data. By analyzing the trend of vegetation indices and the length of the vegetation growing season in time-series remote sensing images, it can accurately reveal the long-term changing trends of regional vegetation cover and growing season dynamics. Unlike related technologies that rely solely on vegetation indices, this application incorporates the start, end, and length changes of the vegetation growing season, providing a more comprehensive reflection of the ecological restoration process. It can adapt to differences in vegetation types and regional characteristics, enhancing the scientific rigor and regional adaptability of the assessment. Furthermore, this application can generate a spatial distribution map of the vegetation restoration ecological index based on the corresponding pixel units. This provides data support for research on areas with significant vegetation restoration effects and key restoration areas, offering advantages of efficiency, flexibility, and accuracy, and is widely applicable to the fields of ecological restoration and environmental protection. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating a vegetation restoration trend assessment method based on remote sensing data provided in an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the vegetation index time series and the vegetation index first derivative time series of a vegetation restoration trend assessment method based on remote sensing data provided in an embodiment of this application.

[0050] Figure 3 This is a schematic diagram of the vegetation growth season start time raster, end time raster, and vegetation growth season length raster of a vegetation restoration trend assessment method based on remote sensing data provided in an embodiment of this application.

[0051] Figure 4 This is a schematic diagram showing the distribution of vegetation index trends in a vegetation restoration trend assessment method based on remote sensing data provided in an embodiment of this application.

[0052] Figure 5 This is a schematic diagram showing the distribution of the vegetation growth season length trend in a vegetation restoration trend assessment method based on remote sensing data provided in an embodiment of this application.

[0053] Figure 6 This is a schematic diagram of the structure of a vegetation restoration trend assessment device based on remote sensing data provided in an embodiment of this application;

[0054] Figure 7 This is a schematic diagram of the structure of a vegetation restoration trend assessment device based on remote sensing data provided in an embodiment of this application.

[0055] Figure 8 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0057] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or modules is not limited to the steps or modules listed, but may optionally include steps or modules not listed, or may optionally include other steps or modules inherent to such process, method, product, or apparatus.

[0058] It should be noted that the terms "first" and "second" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that "first" and "second" can be interchanged in a specific order or sequence where permitted. It should be understood that the objects distinguished by "first" and "second" can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in an order other than those described or illustrated herein.

[0059] It should be noted that this application uses parameters such as the start time, end time, and length of the growing season to reflect the dynamic changes in vegetation growing season, and further calculates relevant parameters reflecting ecological restoration. Understandably, an extended growing season generally signifies increased vegetation growth time, prolonged photosynthetic duration, and enhanced ecosystem service functions, making it a key parameter for measuring ecosystem function restoration. This avoids the shortcomings of related technologies that only focus on changes in vegetation cover or specific vegetation indices at a single point in time, and can more comprehensively reveal the dynamic characteristics of the vegetation growing season.

[0060] The present application will now be described in detail with reference to specific embodiments.

[0061] Next, combine Figure 1This paper introduces a method for assessing vegetation restoration trends based on remote sensing data, provided by embodiments of this application. For details, please refer to... Figure 1 , Figure 1 This illustration shows a flowchart of a vegetation restoration trend assessment method based on remote sensing data, provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0062] S101, Obtain the set of remote sensing images of vegetation index of the area to be studied;

[0063] S102, based on each vegetation index remote sensing image in the vegetation index remote sensing image set, calculate the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period, and generate the start time raster map and end time raster map of the vegetation growth season in the corresponding sub-period.

[0064] S103, Generate a vegetation growth season length raster map for the corresponding sub-period based on the start time raster map and end time raster map for each sub-period;

[0065] S104, calculate the vegetation index trend of each pixel unit within the preset period based on the vegetation index remote sensing image set, and calculate the vegetation growth season length trend of each pixel unit within the preset period based on the start time raster map, end time raster map and vegetation growth season length raster map of each sub-period.

[0066] S105, calculate the vegetation restoration ecological index based on the vegetation index trend and the vegetation growth season length trend, and generate a spatial distribution map of the vegetation restoration ecological index of the area to be studied.

[0067] Specifically, in S101, any city or any area can be selected as the area to be studied. This application embodiment does not limit this. The obtained vegetation index remote sensing image set includes vegetation index remote sensing images arranged in chronological order within a preset period. For example, the area to be studied can be selected as city A, and the preset period can be selected as 2000-2020. Specifically, NDVI images of city A for every 16 days within 2000-2020 can be obtained.

[0068] In some embodiments, before S102, the vegetation index remote sensing images in the vegetation index remote sensing image set can be preprocessed. This involves filling in missing data caused by factors such as cloud shadows through interpolation calculations, cropping the region of interest for each vegetation index remote sensing image, processing each vegetation index remote sensing image to a preset temporal resolution, and resampling each vegetation index remote sensing image to a preset spatial resolution, thus outputting the preprocessed vegetation index remote sensing image set. For example, the preset temporal resolution can be 16 days and the spatial resolution can be 250m.

[0069] Specifically, in S102, the vegetation index time series of each pixel unit in the vegetation index remote sensing image of each sub-time period can be extracted;

[0070] The first derivative time series of vegetation index for each pixel unit is calculated using the first derivative method based on the vegetation index time series.

[0071] Based on the time series of the first derivative of the vegetation index, the time corresponding to the maximum value of the first derivative is determined, and the start time of the vegetation growth season for each pixel unit is obtained; based on the time series of the first derivative of the vegetation index, the time corresponding to the minimum value of the first derivative is determined, and the end time of the vegetation growth season for each pixel unit is obtained.

[0072] For example, taking one year as a sub-period, and taking the change of vegetation index of a certain pixel unit over one year as an example, the vegetation index time series and the calculated vegetation index first derivative time series are as follows: Figure 2 As shown, the horizontal axis represents the number of days in a year (DOY); the number of days in a year corresponding to the maximum value of the first derivative is extracted to obtain the start time of the growing season (SOS) for each pixel unit; the number of days in a year corresponding to the minimum value of the first derivative is extracted to obtain the end time of the growing season (EOS) for each pixel unit.

[0073] Furthermore, the start time of the vegetation growth season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the start time of each sub-period; the end time of the vegetation growth season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the end time of each sub-period.

[0074] For example, the start time SOS raster image and end time EOS raster image of the vegetation growing season in City A from 2000 to 2020 can be calculated, such as... Figure 3 The example shown illustrates the spatial distribution of the start time (SOS), end time (EOS), and length of the growing season (LOS) in City A for 2005, 2010, 2015, and 2020, respectively. Different colors can be used to represent the corresponding times, for example... Figure 3The distribution map of vegetation growth season start time (SOS) in 2005 shows that the red grid indicates that the vegetation growth season starts within the 30th to 90th day of 2005. This application does not limit this.

[0075] Specifically, in S103, the start time and end time of the vegetation growing season for each grid can be determined based on the start time grid and the end time grid of the same sub-period.

[0076] The length of the vegetation growing season for the corresponding grid is calculated by subtracting the start and end times of the vegetation growing season.

[0077] Based on the vegetation growth season length of each grid cell in the area under study in the same sub-period, a vegetation growth season length raster map for the corresponding sub-period is generated.

[0078] For example, Figure 3 The spatial distribution map of vegetation growing season length (LOS) in 2005 shows that orange grids indicate vegetation growing season lengths of 150-180 days within the corresponding grids. This application does not limit this.

[0079] For example, such as Figure 3 As shown, taking 2005, 2010, 2015, and 2020 as examples, the spatial distribution of the start time (SOS), end time (EOS), and length (LOS) of the vegetation growing season in City A is presented. It can be seen that the growing season of vegetation in City A exhibited a clear changing trend from 2000 to 2020. In 2005, most vegetation in City A began growing in mid-to-late April and ended growing in mid-to-late October, lasting mostly 5-7 months. In 2010, 75% of the vegetation in City A began growing in mid-to-late April, 15 days later than in 2005, and the end time of growth was also delayed by 15 days. Therefore, in 2010, the start and end times of vegetation growth in City A (such as woodlands and grasslands in the northwest) were both delayed by half a month, while the duration of the growing season remained concentrated in 6-7 months. In 2015, 60% of the vegetation in City A began to grow in mid-April, and 20% began to sprout and grow before March, a significant increase compared to 2010. The end of vegetation growth remained concentrated between October 16th and November 15th, resulting in a longer growing season, with over 25% of the vegetation growing for more than seven months. In 2020, vegetation in even larger areas showed an earlier growth pattern, with over 80% of the vegetation sprouting and turning green before mid-April, while the end of growth remained around November. This extended the growing season in some areas, with nearly 40% of the vegetation growing for more than seven months, especially in the eastern and southern cultivated land.

[0080] Specifically, in S104, the calculation process of the vegetation index trend and the vegetation growth season length trend includes the following steps:

[0081] Generate the vegetation index time series data of each pixel unit in the area to be studied during the preset period based on the vegetation index remote sensing image set;

[0082] Generate the vegetation growth season length time series data of each pixel unit in the area to be studied during the preset period based on the vegetation growth season length raster map of each sub-period;

[0083] Calculate the significance parameters of each pixel unit respectively based on the difference between every two data in the vegetation index time series data and the vegetation growth season length time series data, and extract the pixel units with significance parameters greater than the preset threshold to generate the significant change area;

[0084] Calculate the slopes of the vegetation index time series data and the vegetation growth season length time series data of each pixel unit in the significant change area respectively, and calculate the vegetation index trend and the vegetation growth season length trend of each pixel unit in the significant change area during the preset period.

[0085] In some embodiments, during the calculation process of the vegetation index trend and the vegetation growth season length trend, the vegetation index time series data and the vegetation growth season length time series data can be expressed as {x1, x2,..., xn}, where n is the time series length. For each pair of data (xi, xj), where 1 ≤ i < j ≤ n, calculate the difference symbol between each pair of data:

[0086] If xj > xi, the difference symbol is +1 (indicating an upward trend);

[0087] If xj < xi, the difference symbol is -1 (indicating a downward trend);

[0088] If xj = xi, the difference symbol is 0 (indicating no trend);

[0089] Calculate the MK statistic S, which is the sum of the trend symbol sequences:

[0090] S = ∑ 1≤i＜j≤n sign(x j - x i );

[0091] Calculate the standardized value Z of the MK statistic S, and Z is also the significance parameter:

[0092]

[0093] The variance Var(S) is calculated using the following formula:

[0094]

[0095] The significance of a trend can be determined based on the Z-value. If |Z| is greater than the critical value under the standard normal distribution (usually 1.96, corresponding to a significance level of 0.05), then the region is considered to have a significant upward or downward trend, thus identifying the significant areas of vegetation change in the corresponding period within the study area.

[0096] In some embodiments, during the calculation of vegetation index trends and vegetation growing season length trends, the slopes of the vegetation index time series data and vegetation growing season length time series data for each pixel unit within the significantly changing region are calculated, specifically including:

[0097] To further quantify the rate of change of trend, the Sen Slope method can be used to calculate the slope Q of time series data. Sen Slope is a median-based trend estimation method suitable for data with irregular fluctuations, providing a quantitative result of trend changes. The formula for calculating Sen Slope is as follows:

[0098]

[0099] Here, Q represents the slope of the time series, indicating the amount of change per unit time. The slope is determined by calculating the difference between each pair of data points and then finding the median of all differences. Using this method, the resulting slope value Q can be used to measure the rate of change in regional vegetation indices and the length of the vegetation growing season.

[0100] If Q>0, it indicates that the time series has an upward trend, i.e., vegetation recovery;

[0101] If Q < 0, it indicates that the time series has a downward trend, i.e., vegetation deterioration;

[0102] If Q = 0, it means that the time series does not have a clear trend.

[0103] In some embodiments, in order to ensure that different indicators are compared on the same scale, before calculating the vegetation restoration ecological index based on the vegetation index trend and the vegetation growth season length trend in S106, the vegetation index trend and the vegetation growth season length trend in the area to be studied can be normalized.

[0104] Divide the vegetation index trend of each pixel unit by the maximum absolute value of the vegetation index trend in the area under study, and output the normalized vegetation index trend.

[0105] Divide the vegetation growth season length trend of each pixel unit by the maximum absolute value of the vegetation growth season length trend in the area under study, and output the normalized vegetation index trend.

[0106] Specifically, by dividing the trend value of each pixel unit by the maximum absolute value within the region under study, the normalized result is within the range of [-1, 1], and the formula is applied:

[0107]

[0108] Where X represents the value of the vegetation index trend or the value of the vegetation growing season length trend. norm This represents the value of the normalized vegetation index trend or the value of the vegetation growing season length trend.

[0109] For example, the distribution of the calculated vegetation index trend or vegetation growing season length trend is as follows: Figure 4 and Figure 5 As shown, both the vegetation index NDVI and the length of the growing season (LOS) exhibit a significant decreasing trend in the southeastern region of City A, where the vegetation is primarily cultivated land. In contrast, the vegetation index NDVI and LOS of the woodlands and grasslands in the west and north show a significant increasing trend. This indicates that the vegetation in the western and northern parts of City A showed a clear recovery from 2000 to 2020, with significant ecological greening effects. Compared to the trend of NDVI, the length of the growing season (LOS) shows the vegetation greening effect over a wider area, demonstrating that the growing season can provide a more accurate assessment of the ecological effects of vegetation restoration. While NDVI reflects changes in vegetation cover when measuring vegetation restoration, it fails to comprehensively capture the duration of the growing season and the overall state of ecological restoration. LOS, on the other hand, considers not only changes in vegetation cover but also the length of the growing season, directly relating to photosynthetic time, biomass accumulation, and enhanced ecological functions.

[0110] Specifically, in S105, the vegetation restoration ecological index is calculated based on the vegetation index trend and the vegetation growing season length trend, including:

[0111] Calculate the weighted sum of the vegetation index trend and the vegetation growing season length trend for each pixel unit within the study area, and output the vegetation restoration ecological index for each pixel unit, using the formula:

[0112] VREI =

[0113] w1*NDVI norm +w2*LOS norm ;

[0114] Where VREI is the vegetation restoration ecological index, w1 is the weight of the vegetation index trend, and NDVI norm The trend of vegetation indices is represented by w2, where w2 is the weight of the trend of vegetation growing season length, and LOS is the mean. norm This represents the trend of vegetation growing season length.

[0115] For example, the Vegetation Restoration Ecological Index (VREI) can be calculated using Python and then visualized hierarchically and statistically analyzed using ArcGIS. The resulting spatial distribution map of the VREI for the study area is shown below. Figure 6 As shown in the figure, the analysis results indicate that approximately 1.8% of the vegetation restoration ecological index in City A falls within the range of -1 to -0.2, representing a significant deterioration of the vegetation ecosystem in these areas, mainly distributed in the cultivated land areas of southern City A. Furthermore, 4.9% of the vegetation is in a slightly deteriorating stage (vegetation restoration ecological index values ​​between -0.2 and 0), primarily distributed in the cultivated land surrounding the urban area of ​​City A. Meanwhile, approximately 28.2% of the vegetation areas have shown a slight greening trend over the past 20 years, mainly distributed in the woodland areas of northwestern City A. The most significant finding is that 65.1% of the vegetation was in a significant ecological restoration stage between 2000 and 2020, with a vegetation restoration ecological index value exceeding 0.2, mainly concentrated in the eastern and southwestern parts of City A. The vegetation in these areas not only shows a significant increasing trend in NDVI, but also a significantly extended vegetation growing season length (LOS). The extended growing season means more time for vegetation photosynthesis, which promotes the accumulation of plant biomass and the enhancement of ecosystem services, further driving the ecological restoration process in these areas.

[0116] The following are apparatus embodiments of this application, which can be used to execute the method embodiments of this application. For details not disclosed in the apparatus embodiments of this application, please refer to the method embodiments of this application.

[0117] Please see below. Figure 7 This is a schematic diagram of a vegetation restoration trend assessment device based on remote sensing data, provided as an exemplary embodiment of this application. This device can be implemented as all or part of a terminal through software, hardware, or a combination of both, or it can be integrated as an independent module on a server. The vegetation restoration trend assessment device based on remote sensing data in this embodiment can be applied to a terminal or the cloud. The device 70 includes a data acquisition module 701, a data processing unit 702, and a data output unit 703, wherein:

[0118] The data acquisition module 701 is used to acquire a set of vegetation index remote sensing images of the area to be studied; the set of vegetation index remote sensing images includes vegetation index remote sensing images arranged in chronological order within a preset period.

[0119] The data processing unit 702 is used to calculate the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period based on each vegetation index remote sensing image in the vegetation index remote sensing image set, and is also used to generate a raster map of the start time and the end time of the vegetation growth season in the corresponding sub-period.

[0120] The data processing unit 702 is also used to generate a vegetation growth season length raster map for the corresponding sub-period based on the start time raster map and end time raster map of each sub-period.

[0121] The data processing unit 702 is also used to calculate the vegetation index trend of each pixel unit within the preset period based on the vegetation index remote sensing image set, and is also used to calculate the vegetation growth season length trend of each pixel unit within the preset period based on the start time raster, end time raster and vegetation growth season length raster of each sub-period.

[0122] The data output unit 703 is used to calculate the vegetation restoration ecological index based on the vegetation index trend and the vegetation growth season length trend, and generate a spatial distribution map of the vegetation restoration ecological index of the area to be studied.

[0123] It should be noted that the device 70 provided in the above embodiments, when executing a vegetation restoration trend assessment method based on remote sensing data, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the device provided in the above embodiments and the embodiment of a vegetation restoration trend assessment method based on remote sensing data belong to the same concept, and its implementation process is detailed in the method embodiment, which will not be repeated here.

[0124] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the methods described above.

[0125] Please see Figure 8 This is a structural block diagram of an electronic device provided in an embodiment of this application.

[0126] like Figure 8 As shown, the electronic device 800 includes a processor 801 and a memory 802.

[0127] In this embodiment, the processor 801 is the control center of the computer system, and can be a processor of a physical machine or a processor of a virtual machine. The processor 801 may include one or more processing cores, such as a 4-core processor or an 8-core processor. The processor 801 can be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array).

[0128] Processor 801 may also include a main processor and a coprocessor. The main processor is the processor used to process data in the wake-up state, also known as the CPU (Central Processing Unit). The coprocessor is a low-power processor used to process data in the standby state.

[0129] Memory 802 may include one or more computer-readable storage media, which may be non-transitory. Memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In some embodiments of this application, the non-transitory computer-readable storage media in memory 802 is used to store at least one instruction, which is executed by processor 801 to implement the method in the embodiments of this application.

[0130] In some embodiments, the electronic device 800 further includes a peripheral device interface 803 and at least one peripheral device 804. The processor 801, memory 802, and peripheral device interface 803 can be connected via a bus or signal line. Each peripheral device 804 can be connected to the peripheral device interface 803 via a bus, signal line, or circuit board. Specifically, the peripheral device 804 includes: a display screen, a camera, and audio circuitry. The peripheral device interface 803 can be used to connect at least one I / O (Input / Output) related peripheral device to the processor 801 and memory 802.

[0131] In some embodiments of this application, the processor 801, memory 802, and peripheral device interface 803 are integrated on the same chip or circuit board; in other embodiments of this application, any one or two of the processor 801, memory 802, and peripheral device interface 803 can be implemented on separate chips or circuit boards. This application does not specifically limit the implementation in this regard.

[0132] The electronic device structural block diagram shown in the embodiments of this application does not constitute a limitation on the electronic device 800. The electronic device 800 may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0133] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the foregoing embodiments. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0134] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of software products. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for assessing vegetation restoration trends based on remote sensing data, characterized in that, include: Obtain a set of remote sensing images of vegetation indices for the area to be studied; The vegetation index remote sensing image set includes vegetation index remote sensing images arranged in chronological order within a preset period. Based on each vegetation index remote sensing image in the vegetation index remote sensing image set, the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period are calculated, and the start time raster map and end time raster map of the vegetation growth season in the corresponding sub-period are generated. Generate a vegetation growth season length raster map for each sub-period based on the start time raster map and end time raster map for each sub-period. The vegetation index trend of each pixel unit within the preset period is calculated based on the vegetation index remote sensing image set. The vegetation growth season length trend of each pixel unit within the preset period is calculated based on the start time raster, end time raster and vegetation growth season length raster of each sub-period. The vegetation restoration ecological index is calculated based on the vegetation index trend and the vegetation growth season length trend, and a spatial distribution map of the vegetation restoration ecological index of the area to be studied is generated.

2. The method according to claim 1, characterized in that, The method further includes calculating the start and end times of the vegetation growth season for each pixel unit in the corresponding sub-time period based on each vegetation index remote sensing image in the vegetation index remote sensing image set. The vegetation index remote sensing images in the vegetation index remote sensing image set are preprocessed by interpolation to fill in missing data, and the region of interest of each vegetation index remote sensing image is cropped. Each vegetation index remote sensing image is processed to a preset temporal resolution, and each vegetation index remote sensing image is processed to a preset spatial resolution by resampling. The preprocessed vegetation index remote sensing image set is then output.

3. The method according to claim 1 or 2, characterized in that, The method involves calculating the start and end times of the vegetation growth season for each pixel unit in the corresponding sub-time period based on each vegetation index remote sensing image in the vegetation index remote sensing image set, and generating a start time raster map and an end time raster map of the vegetation growth season for the corresponding sub-time period, including: Extract the vegetation index time series of each pixel unit in the remote sensing image of each sub-time period; The first derivative time series of vegetation index for each pixel unit is calculated using the first derivative method based on the vegetation index time series. Based on the time series of the first derivative of the vegetation index, the time corresponding to the maximum value of the first derivative is determined, and the start time of the vegetation growth season for each pixel unit is obtained; based on the time series of the first derivative of the vegetation index, the time corresponding to the minimum value of the first derivative is determined, and the end time of the vegetation growth season for each pixel unit is obtained. The start time of the vegetation growing season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the start time of each sub-period; the end time of the vegetation growing season for each pixel unit in the vegetation index remote sensing image of each sub-period is projected onto the corresponding pixel unit to obtain a raster map of the end time of each sub-period.

4. The method according to claim 3, characterized in that, The process of generating a vegetation growth season length raster map for each sub-period based on the start time raster map and end time raster map includes: The start and end times of the vegetation growing season for each grid cell are determined based on the start and end time grids of the same sub-period. The length of the vegetation growing season for the corresponding grid is calculated by subtracting the start and end times of the vegetation growing season. Based on the vegetation growth season length of each grid cell in the area under study in the same sub-period, a vegetation growth season length raster map for the corresponding sub-period is generated.

5. The method according to claim 1, characterized in that, The calculation process for the vegetation index trend and the vegetation growing season length trend includes the following steps: Based on the vegetation index remote sensing image set, generate vegetation index time series data for each pixel unit of the area to be studied within the preset period; Based on the vegetation growth season length raster map of each sub-period, the time series data of the vegetation growth season length of each pixel unit in the area under study within the preset period is generated. The significance parameter of each pixel unit is calculated based on the difference between every two data points in the vegetation index time series data and the vegetation growth season length time series data, respectively. Pixel units with significance parameters greater than a preset threshold are extracted to generate significant change regions. The slopes of the vegetation index time series data and the vegetation growth season length time series data for each pixel unit in the significantly changing region are calculated respectively, and the vegetation index trend and vegetation growth season length trend of each pixel unit in the significantly changing region within the preset period are obtained.

6. The method according to claim 5, characterized in that, Before calculating the vegetation restoration ecological index based on the vegetation index trend and the vegetation growing season length trend, the method further includes: The vegetation index trend and vegetation growing season length trend in the area to be studied were normalized. Divide the vegetation index trend of each pixel unit by the maximum absolute value of the vegetation index trend in the area under study, and output the normalized vegetation index trend. Divide the vegetation growth season length trend of each pixel unit by the maximum absolute value of the vegetation growth season length trend in the area under study, and output the normalized vegetation index trend.

7. The method according to claim 1, characterized in that, The vegetation restoration ecological index, calculated based on the vegetation index trend and the vegetation growing season length trend, includes: Calculate the weighted sum of the vegetation index trend and the vegetation growing season length trend for each pixel unit within the study area, and output the vegetation restoration ecological index for each pixel unit, using the formula: VREI = w1*NDVI norm +w2*LOS norm ; Where VREI is the vegetation restoration ecological index, w1 is the weight of the vegetation index trend, and NDVI norm The trend of vegetation indices is represented by w2, where w2 is the weight of the trend of vegetation growing season length, and LOS is the mean. norm This represents the trend of vegetation growing season length.

8. A vegetation restoration trend assessment device based on remote sensing data, characterized in that, include: The data acquisition module is used to acquire a set of remote sensing images of vegetation indices for the area under study. The vegetation index remote sensing image set includes vegetation index remote sensing images arranged in chronological order within a preset period. The data processing unit is used to calculate the start time and end time of the vegetation growth season for each pixel unit in the corresponding sub-period based on each vegetation index remote sensing image in the vegetation index remote sensing image set, and is also used to generate a raster map of the start time and the end time of the vegetation growth season in the corresponding sub-period. The data processing unit is also used to generate a vegetation growth season length raster map for the corresponding sub-period based on the start time raster map and end time raster map for each sub-period. The data processing unit is also used to calculate the vegetation index trend of each pixel unit within the preset period based on the vegetation index remote sensing image set, and is also used to calculate the vegetation growth season length trend of each pixel unit within the preset period based on the start time raster, end time raster and vegetation growth season length raster of each sub-period. The data output unit is used to calculate the vegetation restoration ecological index based on the vegetation index trend and the vegetation growth season length trend, and generate a spatial distribution map of the vegetation restoration ecological index of the area to be studied.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images