Method and system for calculating single-type vegetation carbon sink, terminal and medium

Abstract

The invention provides a method and system for calculating single-type vegetation carbon sink, a terminal and a medium, and particularly relates to the technical field of forestry carbon sink, and the scheme comprises the steps: obtaining remote sensing data in a target time period and a target region; based on the remote sensing data, determining a land cover distribution map layer and a vegetation index corresponding to the target type of vegetation; and based on the vegetation index and the earth surface coverage distribution map layer, obtaining the carbon sink amount of the target type vegetation in the target time period. According to the scheme, the land cover distribution map layer corresponding to the target type of vegetation and the related vegetation index can be accurately determined, the carbon sink amount of the target region in the set space-time range can be rapidly calculated, and the working efficiency and the calculation precision can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of forestry carbon sinks, and in particular to a method, system, terminal and medium for calculating carbon sinks of a single type of vegetation. Background Art

[0002] As an efficient, wide-area, and continuous means of observation, satellite remote sensing technology has been widely used in the fields of vegetation coverage and ecological environment monitoring. At present, the use of satellite remote sensing data to evaluate vegetation carbon sinks is mainly based on extracting carbon sink characterization data from remote sensing data, and using the carbon sink characterization data to input into a deep neural network model to evaluate the overall carbon sink in a certain region. Although the overall carbon sink can be accurately calculated, the deep neural network model has complex architecture, long calculation time, and high cost. Moreover, the vegetation coverage types in a certain region are usually diverse, and there are few existing technologies that calculate the carbon sink of a certain type of vegetation in a certain region. Summary of the invention

[0003] In view of the above-mentioned deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for calculating the carbon sink of a single type of vegetation, aiming to solve the problem in the prior art of lack of calculation of the carbon sink of a single type of vegetation in an area covered by multiple types of vegetation.

[0004] In order to achieve the above object, the present invention provides a method for calculating carbon sinks of a single type of vegetation in a first aspect, comprising:

[0005] Acquire remote sensing data within the target time period and target area;

[0006] Based on the remote sensing data, determining the surface cover distribution layer and vegetation index corresponding to the target type of vegetation;

[0007] Based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation in the target time period is obtained.

[0008] Optionally, determining the surface cover distribution layer and vegetation index corresponding to the target type vegetation based on the remote sensing data includes:

[0009] Processing the remote sensing data using a trained land cover classification model to obtain a land cover distribution layer corresponding to each type of plant in the target area during the target time period;

[0010] All the land cover distribution layers are screened to determine the land cover distribution layer corresponding to the target type of vegetation.

[0011] Optionally, the process of constructing the land cover classification model includes:

[0012] Collect remote sensing data of several coordinate points in the grid area sample to obtain a training set;

[0013] Labeling and classifying the surface cover type of each coordinate point to obtain several types of surface cover type labels;

[0014] An initial land cover classification model is constructed based on a neural network algorithm, and the initial land cover classification model is iteratively trained using the training set and the land cover type labels to obtain a trained land cover classification model.

[0015] Optionally, obtaining the carbon sequestration amount of the target type of vegetation within the target time period based on the vegetation index and the land cover distribution layer includes:

[0016] Based on the vegetation index and the land cover distribution layer, calculating the carbon sink of the target type of vegetation corresponding to the start and end times of the target time period;

[0017] Based on the carbon sequestration amounts of the target type of vegetation corresponding to the start and end times of the target time period, the carbon sequestration amount of the target type of vegetation within the target time period is obtained.

[0018] Optionally, the calculating, based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation corresponding to the start and end times of the target time period includes:

[0019] Based on the vegetation index and the land cover distribution layer, determine the biomass standardization rate, basic biomass and conversion factor of biomass to carbon sink corresponding to the target type of vegetation in the target area within the target time period;

[0020] The carbon sink of the target type of vegetation is obtained based on the biomass standardization rate, the basic biomass and the conversion factor of the biomass to the carbon sink.

[0021] Optionally, after obtaining the carbon sequestration amount of the target type of vegetation, the method further comprises:

[0022] When there is only one external environmental variable in the external environment where the target type vegetation is located in the target area during the target time period, the degree of influence of the external environmental variable on the carbon sequestration of the target type vegetation is determined based on the carbon sequestration amount of the target type vegetation.

[0023] A second aspect of the present invention provides a system for calculating carbon sinks of a single type of vegetation, the system comprising:

[0024] An information acquisition module is used to acquire remote sensing data within a target time period and target area;

[0025] A data processing module, used to determine the surface coverage distribution layer and vegetation index corresponding to the target type of vegetation based on the remote sensing data;

[0026] The carbon sink calculation module is used to obtain the carbon sink of the target type of vegetation within the target time period based on the vegetation index and the land cover distribution layer.

[0027] Optionally, the system also includes a carbon sink impact assessment module, which is used to determine the carbon sink impact of the target type of vegetation based on the carbon sink amount of the target type of vegetation when there is only one external environmental variable in the external environment of the target type of vegetation in the target area during the target time period.

[0028] A third aspect of the present invention provides an intelligent terminal, which includes a memory for storing executable instructions; and a processor for calling and running the executable instructions in the memory to execute any step of the above-mentioned method for calculating carbon sinks of a single type of vegetation.

[0029] A fourth aspect of the present invention provides a computer-readable storage medium having program instructions stored therein. When the program instructions are executed by a processor, any step of the above-mentioned method for calculating carbon sinks of a single type of vegetation is implemented.

[0030] Compared with the prior art, the beneficial effects of this solution are as follows:

[0031] The present invention collects remote sensing data of the target area within a set time and space range, and processes the remote sensing data using a trained land cover classification model, which can accurately determine the land cover distribution layer and related vegetation index corresponding to the target type vegetation, and uses a custom carbon sink estimation model combined with the geographical environment where the target type vegetation is located, which can quickly calculate the carbon sink amount of the target area within the set time and space range, realize automatic data processing flow, avoid manual intervention, and significantly improve work efficiency and calculation accuracy. At the same time, using satellites to collect remote sensing data in real time can improve the timeliness of carbon sink monitoring in the target area. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0033] Figure 1A flow chart of the method for calculating carbon sinks of a single type of vegetation according to the present invention;

[0034] Figure 2 A block diagram for calculating vegetation index distribution, rainfall distribution and land cover distribution of the present invention;

[0035] Figure 3 A block diagram for evaluating the effect of rainfall on vegetation carbon sink of the present invention;

[0036] Figure 4 This is a schematic diagram of the surface coverage marking effect of the present invention;

[0037] Figure 5 This is a schematic diagram of the system module for calculating carbon sinks of a single type of vegetation according to the present invention;

[0038] Figure 6 It is a schematic diagram of the structure of the intelligent terminal of the present invention. DETAILED DESCRIPTION

[0039] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0040] It should be understood that when used in this specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0041] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0042] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0043] As used in this specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0044] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] The present invention is faced with the problem that the existing technology of using satellite remote sensing data to evaluate vegetation carbon sink is mainly based on extracting carbon sink characterization data from remote sensing data, and using the carbon sink characterization data to input into a deep neural network model to evaluate the overall carbon sink in a certain region. Although the overall carbon sink can be accurately calculated, the deep neural network model has the problem of complex architecture, long calculation time and high cost. Moreover, the vegetation coverage types in a certain region are usually diverse, and there is an urgent need for a method that can calculate the carbon sink of a single type of vegetation in a region covered with multiple types of vegetation.

[0047] Based on this, this application proposes a method for calculating the carbon sink of a single type of vegetation, which mainly uses multi-source remote sensing data of the target area to train a landmark coverage distribution model, and uses the landmark coverage distribution model to identify the surface coverage distribution layer and related vegetation index corresponding to the target type of vegetation. The landmark coverage distribution model can identify the cover of each coordinate point, thereby effectively improving the recognition accuracy of the surface coverage distribution layer, which helps to improve the calculation accuracy of the carbon sink in the region; then use a custom single-type vegetation carbon sink calculation model to calculate the carbon sink of the target type of vegetation according to the vegetation index and the landmark coverage distribution layer. The calculation method is simple and efficient, and can improve the timeliness of monitoring the carbon sink changes of a single type of vegetation in the target area. Furthermore, based on the single variable principle, the factors that cause changes in the carbon sink of the target type of vegetation in the target area are analyzed, and the degree of influence of the factors on the carbon sink of the target type of vegetation is analyzed, which can provide strong support for vegetation protection and climate change research.

[0048] The embodiment of the present invention provides a method for calculating the carbon sink of a single type of vegetation, which is deployed on electronic devices such as computers and servers, and is applied to areas covered by a single or multiple types of vegetation. It is aimed at calculating the carbon sink of a single type of vegetation in the area within a target time and space range. The present invention does not limit the type of vegetation. Specifically, Figure 1 and Figure 2 As shown, the steps of the method in this embodiment include:

[0049] Step S100: Acquire remote sensing data within a target time period and a target area.

[0050] Specifically, multi-temporal and multi-spectral remote sensing data within the target time period and target area are obtained through satellite remote sensing platforms (such as Landsat, Sentinel, etc.).

[0051] Furthermore, the quality of remote sensing data is ensured by performing preprocessing such as noise reduction on the collected remote sensing data; the accuracy and consistency of data positioning are ensured by performing preprocessing such as atmospheric correction, geometric correction and image registration on the collected remote sensing data, and data from different phases or different sensors are registered to a unified geographic coordinate system.

[0052] Step S200: Based on the remote sensing data, determine the surface coverage distribution layer and vegetation index corresponding to the target type of vegetation.

[0053] Specifically, the remote sensing data is processed using a trained land cover classification model to obtain a land cover distribution layer corresponding to each type of plant in the target area during the target time period. Specifically, remote sensing images at different time points are compared using a trained land cover classification model to extract surface change information; different band information in multispectral data is extracted using a trained land cover classification model to analyze land cover types, vegetation health status, etc., thereby obtaining land cover distribution layers corresponding to all vegetation types in the target area, that is, one land cover distribution layer for each vegetation type. By constructing multiple layers of land cover distribution layers to characterize the vegetation coverage in the target area, the readability of the coverage of different types of vegetation can be improved. Then, all the land cover distribution layers are screened to determine the land cover distribution layer corresponding to the target type of vegetation. According to the remote sensing reflectance of different bands (such as near-infrared, red, green and blue bands) corresponding to the surface cover distribution layer, the relevant vegetation indices of the target type of vegetation are calculated, such as the Normalized Vegetation Index (NDVI), the Ratio Vegetation Index (RVI), the Difference Vegetation Index (DVI), the soil-adjusted vegetation index (SAVI), the Modified Soil Adjusted Vegetation Index (MSAVI), the Enhanced Vegetation Index (EVI), etc.

[0054] Step S300: Based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation in the target time period is obtained.

[0055] Specifically, in order to improve the accuracy of calculating the carbon sequestration of the target type vegetation, this embodiment limits the time and space scope corresponding to the target type vegetation, that is, the spatial boundary information scope of the study is limited by the target region, and the time information scope of the study is limited by the target time period, and the time information and spatial boundary information can be limited by screening time and space. Once the time and space scope is clear, the carbon sequestration of the target type vegetation corresponding to the start and end times of the target time period can be calculated according to the vegetation index distribution and surface cover distribution layer corresponding to the start time / end time of the target time period; and the carbon sequestration of the target type vegetation in the target time period is obtained by calculating the difference between the carbon sequestration corresponding to the end time and the start time. It is easy to understand that the change of vegetation carbon sequestration is affected by many factors, including vegetation type, geographical growth conditions, climate factors, etc., so the change of vegetation carbon sequestration is the result of the combined effect of various influencing factors.

[0056] In a preferred embodiment, the calculating the carbon sequestration amount of the target type of vegetation corresponding to the start and end times of the target time period based on the vegetation index and the land cover distribution layer includes:

[0057] Based on the vegetation index and the surface cover distribution layer, determine the biomass standardization rate, basic biomass and the conversion factor of biomass to carbon sink corresponding to the target type of vegetation in the target area during the target time period; based on the biomass standardization rate, the basic biomass and the conversion factor of biomass to carbon sink, obtain the carbon sink of the target type of vegetation.

[0058] Specifically, based on the vegetation index and the land cover distribution layer, a biomass estimation model is constructed according to the linear relationship between biomass and vegetation index, namely:

[0059] Biomass = max(0,a×vegetation index+b),

[0060] Among them, the slope parameter a represents the biomass change rate corresponding to the change in the value of the vegetation index; the intercept parameter b represents the basic biomass when the vegetation index is 0; the change in the value of the vegetation index corresponds to the biomass change rate. The values ​​of parameters a and b corresponding to different vegetation types are different, which reflects the unique relationship between biomass and vegetation index of each type of vegetation. It should be stated that the vegetation index selected in this embodiment is NDVI, and the corresponding biomass estimation model can also be constructed by studying the correlation between biomass and other vegetation indices, and the present invention does not make specific limitations on this.

[0061] Then, according to the conversion capacity of different types of vegetation corresponding to biomass to carbon content in the prior art, the conversion factor carbon_factor corresponding to common types of vegetation is determined. The conversion factor represents the conversion factor from biomass to carbon content, which represents the proportion of carbon in the dry weight of vegetation. Based on this, a carbon sink estimation model is constructed, namely:

[0062] Carbon sink = biomass * carbon_factor,

[0063] It is easy to understand that different types of vegetation have different carbon contents, so the carbon_factor will also be different. For example, woody plants (such as trees) usually have higher carbon factors than herbaceous plants, so the carbon_factor value is larger.

[0064] In particular, this embodiment combines the scientific research results disclosed in scientific literature, as well as the geographical environment and vegetation cover types of the actual research area within the real time and space range, selects the vegetation index as NDVI, and sets the preferred parameters a, b and carbon_factor values ​​corresponding to different types of vegetation, as shown in Table 1.

[0065] Table 1:

[0066]

[0067] As can be seen from Table 1, different types of vegetation have different values ​​for the parameters a, b, and carbon_factor. Among them, the tree cover category has the highest a value, reflecting the strong relationship between NDVI and biomass in forests; the lowest b value, reflecting the low biomass that allows accurate prediction in sparse forest areas; and the highest carbon_factor, indicating that the woody biomass has a high carbon content. The shrub cover category has the second highest a and carbon_factor, reflecting the medium woody biomass between trees and herbaceous vegetation; the medium b value, indicating that the shrub base biomass is balanced between trees and grasslands. The crop cover category has a high a value among non-woody vegetation, reflecting the growth under artificial management and the potential high biomass; the medium b value and carbon_factor, indicating that the carbon content is similar to other herbaceous vegetation. The a value of the submerged vegetation cover category is between crops and grasslands, reflecting the adaptation to water-saturated environments; the slightly lower b value than grasslands indicates that the effect of water on NDVI values ​​is taken into account; the standard herbaceous vegetation carbon_factor, indicating that the carbon content is similar to other non-woody vegetation. The grassland cover category has the lowest a value, reflecting the lower biomass compared to woody vegetation and crops; has the smallest absolute negative b value among vegetation, indicating biomass potential even at low NDVI values; and a standard herbaceous vegetation carbon_factor, similar to other non-woody vegetation carbon content. The bare land cover category has very low a and b values, reflecting the minimum vegetation cover in these areas; a slightly lower carbon_factor, indicating that potential sparse vegetation or biological soil crust is taken into account. The values ​​of a, b, and carbon_factor corresponding to water bodies, built-up areas, snow and ice cover types are all zero, indicating that they have no significant vegetation or carbon sequestration potential. It should be noted that negative b values ​​allow the model to predict zero biomass at very low NDVI values, which is more realistic than forcing a positive biomass prediction when NDVI=0. This design can increase the accuracy of the model in areas with low vegetation cover.

[0068] In this embodiment, by collecting remote sensing data of the target area within the set time and space range, and using the trained surface cover classification model to process the remote sensing data, the surface cover distribution layer and related vegetation index corresponding to the target type vegetation can be accurately determined, and the customized carbon sink estimation model can be combined with the geographical environment where the target type vegetation is located to quickly calculate the carbon sink amount of the target area within the set time and space range, realize the automated data processing process, avoid manual intervention, and significantly improve work efficiency and calculation accuracy. At the same time, using satellites to collect remote sensing data in real time can improve the timeliness of carbon sink monitoring in the target area.

[0069] like Figure 3As shown, in a preferred embodiment, the process of constructing the land cover classification model includes:

[0070] Step M100: Collect remote sensing data of several coordinate points in the grid area sample to obtain a training set.

[0071] Specifically, multi-temporal and multi-spectral remote sensing data of regional samples over a period of time are collected by satellite remote sensing platforms (such as Landsat, Sentinel, etc.) using multi-spectral satellites. The remote sensing data consists of full-band remote sensing data consisting of 12 bands as shown in Table 2.

[0072] Table 2:

[0073]

[0074] The regional sample is divided into grid area samples according to the coordinate points, and each coordinate point corresponds to a grid. Then the remote sensing data corresponding to each coordinate point is extracted according to the grid, and the training set is constructed using the remote sensing data corresponding to all grids in the grid area sample.

[0075] Step M200: label and classify the ground cover type of each coordinate point to obtain several ground cover type labels.

[0076] Specifically, this embodiment uses the three bands R (B4), G (B3), and B (B2) in the remote sensing data to synthesize visible light images as the data to be labeled for the grid area samples. By labeling the data to be labeled with landmarks according to the coordinate points, a surface cover category and a corresponding label number corresponding to each coordinate point are obtained, thereby obtaining several types of surface cover distribution layers corresponding to the entire grid area, and each layer corresponds to a landmark cover category. In this embodiment, the surface cover categories and labels obtained by labeling the grid area samples are shown in Table 3.

[0077] Table 3:

[0078] Coverage Category Label definition water 0 Grid fully covered by water Tree 1 A grid fully covered by trees grassland 2 A grid completely covered with grass Submerged vegetation 3 Rasters completely covered by flooded vegetation crop 4 Grid with complete crop coverage shrub 5 Grid fully covered with shrubs Man-made buildings 6 A grid completely covered by man-made structures Bare Land 7 Bare ground fully covered grid Snow 8 Snow-covered grid

[0079] The surface cover annotation effect diagram obtained by annotation according to Table 3 is as follows Figure 4 As shown in the figure, different colors represent different types of surface cover categories, and the text color is consistent with the surface cover category color.

[0080] Step M300: construct an initial land cover classification model based on a neural network algorithm, and iteratively train the initial land cover classification model using the training set and the land cover type label to obtain a trained land cover classification model.

[0081] Specifically, after preprocessing the training set by noise reduction, atmospheric correction, geometric correction and image registration, an initial land cover classification model is constructed using a neural network such as a convolutional neural network (CNN), a recurrent neural network (RNN) or a fully connected neural network (FCN). The input layer of the initial land cover classification model receives the preprocessed image data; extracts features in the image through multiple convolutional layers; reduces the data dimension through the pooling layer to avoid overfitting; introduces nonlinearity through the activation layer, and commonly used activation functions include ReLU, Sigmoid, etc.; converts features into classification outputs through the fully connected layer; and outputs the probability of each land cover category using the softmax function through the output layer. Then, a loss function such as cross entropy loss is used to measure the difference between the model prediction and the actual label, and an optimization algorithm is used to update the network weights to minimize the loss function. According to this logic, the model is iteratively trained using the training set until the preset number of training times or the preset training accuracy is reached, and a trained land cover classification model is obtained. Then, the trained land cover classification model can accurately identify the vegetation cover type in any region.

[0082] In this embodiment, multi-temporal and multi-spectral remote sensing data are used to iteratively train the neural network model to construct a surface cover classification model. This model can improve the efficiency and accuracy of identifying the vegetation cover type at each coordinate point in the study area, which helps to improve the accuracy of carbon sink calculation in the study area.

[0083] like Figure 2 As shown, in a preferred embodiment, after obtaining the carbon sequestration amount of the target type of vegetation, the following steps are included:

[0084] When there is only one external environmental variable in the external environment where the target type vegetation is located in the target area during the target time period, the degree of influence of the external environmental variable on the carbon sequestration of the target type vegetation is determined based on the carbon sequestration amount of the target type vegetation.

[0085] Specifically, changes in vegetation carbon sinks are usually affected by a variety of factors, including vegetation type, geographical growth conditions, climate factors, etc. Therefore, changes in vegetation carbon sinks are the result of the combined effects of various influencing factors. In order to study the degree of influence of a single environmental variable on the carbon sink of vegetation, this embodiment selects a single external environmental variable that causes changes in the carbon sink of the target type of vegetation within a certain time and space range as a variable to study the degree of influence of the variable on the carbon sink of the target type of vegetation based on the solved carbon sink of the target type of vegetation. This method follows the principle of a single variable and can improve the accuracy of the assessment of the degree of influence of a monitored environmental variable on the carbon sink of the target type of vegetation.

[0086] For example, when the only variable in the external environmental conditions of the target type of vegetation in the target area during the target time period is rainfall, and the other external environmental conditions remain unchanged, it is obvious that the factor that causes the carbon sink of the target type of vegetation to change during the target time is rainfall. Then, the degree of influence of rainfall on the carbon sink of the target type of vegetation can be judged according to the amount of change in carbon sink during the target time. Among them, the external environmental conditions include climate environment and geographical environment. The climate environment includes but is not limited to temperature, humidity, light, etc., and the geographical environment includes but is not limited to altitude, earth surface structure type, etc. It should be stated that the single environmental variable selected in this example is rainfall. Other types of environmental variables can also be flexibly selected as variables according to actual research needs, and the target vegetation type can be flexibly selected as the dependent variable to analyze the degree of influence of different types of environmental variables on the carbon sink of vegetation.

[0087] In order to verify the effectiveness of the method of the present invention in studying the influence of a single environmental variable on the carbon sink of vegetation, the target area within the real time and space range is used as the research object for experimental verification. Specifically, the rainfall in the target area between January 1, 2021 and June 1, 2024 is collected, and the time period is set to 1 week, 2 weeks, 1 month, 2 months and 3 months, and the values ​​of parameters a, b and carbon_factor are determined, and the correlation coefficient threshold is set. Then, according to these data, the correlation coefficient between the rainfall in the target area and the carbon sink of various types of surface cover in this time period is calculated. A correlation coefficient greater than zero represents a positive correlation, and a correlation coefficient less than zero represents a negative correlation. For example, 0.7 is customized as the correlation coefficient threshold. If the calculated correlation coefficient is greater than 0.7, it means that the rainfall and the carbon sink of this type of vegetation have a strong positive correlation. If the calculated correlation coefficient is less than -0.7, it means that the rainfall and the carbon sink of this type of vegetation have a strong negative correlation. Therefore, the impact of rainfall changes at various time scales on the carbon sink of various types of surface cover vegetation can be evaluated based on the size of the correlation coefficient.

[0088] The results show that most vegetation indicators are positively correlated with rainfall, and the correlation increases with the increase of time scale, which indicates that there is a certain lag effect in the response of vegetation to rainfall. Shrubs and bushes have the highest correlation with rainfall, especially on the time scale of 2 months and 3 months, which suggests that these types of vegetation are most sensitive to precipitation; bare land is negatively correlated with rainfall, and the correlation increases with time, because more bare land is covered by vegetation as rainfall increases; buildings have a low correlation with rainfall, because man-made buildings do not change significantly with rainfall; water bodies and flood vegetation have a high correlation with rainfall in the short term (such as 1-2 weeks), which reflects that rainfall has a direct impact on the storage of surface water. It can be seen that this experiment estimates the impact of rainfall on the carbon sink of different surface covers by designing multiple time scales, and the sensitivity of each type of cover to rainfall can be clearly seen. The research results are in line with reality, and effectively verify the effectiveness and feasibility of the method of the present invention to study the degree of influence of a single environmental variable on the carbon sink of vegetation.

[0089] like Figure 5 As shown, corresponding to the above method for calculating carbon sinks of a single type of vegetation, an embodiment of the present invention further provides a system for calculating carbon sinks of a single type of vegetation, and the system for calculating carbon sinks of a single type of vegetation includes:

[0090] An information acquisition module is used to acquire remote sensing data within a target time period and target area;

[0091] A data processing module, used to determine the surface coverage distribution layer and vegetation index corresponding to the target type vegetation based on the remote sensing data;

[0092] The carbon sink calculation module is used to obtain the carbon sink of the target type of vegetation within the target time period based on the vegetation index and the land cover distribution layer.

[0093] In one embodiment, the system also includes a carbon sink impact assessment module, which is used to determine the carbon sink impact of the target type of vegetation based on the carbon sink amount of the target type of vegetation when there is only one external environmental variable in the external environment of the target type of vegetation in the target area during the target time period.

[0094] Specifically, in this embodiment, the specific functions of the system for calculating the carbon sink of a single type of vegetation can also refer to the corresponding description in the method for calculating the carbon sink of a single type of vegetation, which will not be repeated here.

[0095] Based on the above embodiments, the present invention further provides an intelligent terminal, whose principle block diagram can be shown as follows: Figure 6As shown. The intelligent terminal can be used to execute the method for calculating the carbon sink of a single type of vegetation provided in the above embodiment, which will not be described here for the sake of brevity. The intelligent terminal includes: a processor, the processor is coupled to a memory, the memory is used to store computer programs or instructions, and the processor is used to execute the computer programs or instructions stored in the memory, so that the method in the above method embodiment is executed.

[0096] The present invention also provides a computer-readable storage medium on which computer instructions for implementing the method in the above method embodiment are stored.

[0097] For example, when the computer program is executed by a computer, the computer can implement the method in the above method embodiment.

[0098] The embodiment of the present application also provides a computer program product including instructions, which, when executed by a computer, enables the computer to implement the method in the above method embodiment.

[0099] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0100] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0101] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0103] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0104] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A method for calculating carbon sinks of a single type of vegetation, characterized in that: The following steps are involved: Acquire remote sensing data within the target time period and target area; Based on the remote sensing data, determining the surface cover distribution layer and vegetation index corresponding to the target type of vegetation; Based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation in the target time period is obtained.

2. The method for calculating carbon sink of a single type of vegetation according to claim 1, characterized in that: The determining, based on the remote sensing data, a surface coverage distribution layer and a vegetation index corresponding to the target type vegetation includes: Processing the remote sensing data using a trained land cover classification model to obtain a land cover distribution layer corresponding to each type of plant in the target area during the target time period; All the land cover distribution layers are screened to determine the land cover distribution layer corresponding to the target type of vegetation.

3. The method for calculating carbon sink of a single type of vegetation according to claim 2, characterized in that: The process of constructing the land cover classification model includes: Collect remote sensing data of several coordinate points in the grid area sample to obtain a training set; Labeling and classifying the surface cover type of each coordinate point to obtain several types of surface cover type labels; An initial land cover classification model is constructed based on a neural network algorithm, and the initial land cover classification model is iteratively trained using the training set and the land cover type labels to obtain a trained land cover classification model.

4. The method for calculating carbon sink of a single type of vegetation according to claim 1, characterized in that: The obtaining, based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation within the target time period comprises: Based on the vegetation index and the land cover distribution layer, calculating the carbon sink of the target type of vegetation corresponding to the start and end times of the target time period; Based on the carbon sequestration amounts of the target type of vegetation corresponding to the start and end times of the target time period, the carbon sequestration amount of the target type of vegetation within the target time period is obtained.

5. The method for calculating carbon sink of a single type of vegetation according to claim 4, characterized in that: The calculating, based on the vegetation index and the land cover distribution layer, the carbon sequestration amount of the target type of vegetation corresponding to the start and end times of the target time period comprises: Based on the vegetation index and the land cover distribution layer, determine the biomass standardization rate, basic biomass and conversion factor of biomass to carbon sink corresponding to the target type of vegetation in the target area within the target time period; The carbon sink of the target type of vegetation is obtained based on the biomass standardization rate, the basic biomass and the conversion factor of the biomass to the carbon sink.

6. The method for calculating carbon sink of a single type of vegetation according to claim 1, characterized in that: After obtaining the carbon sequestration amount of the target type of vegetation, the method further comprises: When there is only one external environmental variable in the external environment where the target type vegetation is located in the target area during the target time period, the degree of influence of the external environmental variable on the carbon sequestration of the target type vegetation is determined based on the carbon sequestration amount of the target type vegetation.

7. A system for calculating carbon sinks of a single type of vegetation, characterized in that: The system comprises: An information acquisition module is used to acquire remote sensing data within a target time period and target area; A data processing module, used to determine the surface coverage distribution layer and vegetation index corresponding to the target type of vegetation based on the remote sensing data; The carbon sink calculation module is used to obtain the carbon sink of the target type of vegetation within the target time period based on the vegetation index and the land cover distribution layer.

8. The system for calculating carbon sinks of a single type of vegetation according to claim 7, characterized in that: The system also includes a carbon sink impact assessment module, which is used to determine the impact of the external environmental variable on the carbon sink of the target type of vegetation based on the carbon sink amount of the target type of vegetation when there is only one external environmental variable in the external environment of the target type of vegetation in the target area during the target time period.

9. An intelligent terminal, characterized in that: include: A memory for storing executable instructions; A processor is used to call and run the executable instructions in the memory to execute the steps of the method for calculating the carbon sink of a single type of vegetation as described in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, and when the program instructions are executed by a processor, the method for calculating the carbon sink of a single type of vegetation as described in any one of claims 1 to 6 is implemented.

Images