A cultivated land and abandoned land full life cycle identification method, device and equipment

Abstract

The application provides a cultivated land and abandoned land full life cycle identification method and device and equipment, wherein the method comprises the following steps: acquiring ground surface vegetation end member time sequence images and ground surface soil end member time sequence images of a target area; analyzing the ground surface vegetation end member time sequence images and the ground surface soil end member time sequence images respectively to obtain optimal fitting curves and corresponding change characteristic parameters of the ground surface vegetation end member time sequence and the ground surface soil end member time sequence; and determining the cultivated land and abandoned land type of the target area based on the optimal fitting curves and the corresponding change characteristic parameters. Through the application, the vegetation-soil end member time sequence representing the ground surface process of cultivated land and abandoned land is used to carry out cultivated land and abandoned land full life cycle modeling and cultivated land and abandoned land scene identification by integrating multi-dimensional end member time sequence interaction information, so that an efficient and high-precision cultivated land and abandoned land full life cycle monitoring method is formed, and technical support is provided for intelligent monitoring and supervision of cultivated land "non-agriculturalization" and "non-foodization" and other natural resources.

Description

Technical Field

[0001] This invention relates to the field of ecological environment monitoring technology, specifically to a method, device, and equipment for identifying the entire life cycle of abandoned farmland. Background Technology

[0002] Farmland abandonment refers to the state of farmland being left idle or underutilized due to farmers' subjective reasons for abandoning cultivation. Scientific and effective monitoring of farmland abandonment is a crucial foundation for ensuring the sustainable use of natural resources and food security. Currently, farmland abandonment monitoring based on multi-year land use cover type classification results is one of the mainstream methods. This method primarily uses annual land use cover type classification results to conduct rule-based farmland abandonment determination. This process requires not only analysis of land use cover types but also using the duration of non-farmland status as a criterion for identifying farmland abandonment areas. This method inevitably suffers from error propagation caused by errors in land use cover classification results, leading to high identification errors in farmland abandonment and a lack of understanding of the entire lifecycle of farmland abandonment. Furthermore, vector analysis based on changes in spectral characteristics or vegetation indices between two consecutive image periods has also been applied to farmland abandonment identification. However, this method struggles to characterize the farmland abandonment process and lacks a comprehensive grasp of the actual path of abandonment status transition, resulting in high uncertainty in the identification results.

[0003] With the continuous development of time series analysis methods, some time series analysis methods based on vegetation indices have also been applied to the identification of farmland abandonment. However, these methods often extract some local features of the time series and then use machine learning and other methods to identify farmland abandonment. They lack monitoring of the entire life cycle of farmland abandonment. At the same time, the information contained in vegetation indices is limited and does not take into account the coordinated changes of other elements such as soil. It is difficult to fully explore the interactive information of landscape elements in farmland abandonment, which limits the accuracy and efficiency of farmland abandonment scene identification. Summary of the Invention

[0004] Therefore, this invention provides a method, device, and equipment for monitoring the entire life cycle of farmland abandonment, aiming to solve the technical problems of accuracy and efficiency in identifying farmland abandonment scenarios in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] According to a first aspect of the present invention, the present invention provides a method for monitoring the entire life cycle of farmland abandonment, the method comprising:

[0007] Acquire time-series images of surface vegetation end-members and surface soil end-members in the target area;

[0008] The time series images of the surface vegetation end-members and the surface soil end-members were analyzed respectively to obtain the optimal fitting curves and corresponding change characteristic parameters of the time series images of the surface vegetation end-members and the surface soil end-members.

[0009] Based on the optimal fitting curve of the target area and the corresponding change characteristic parameters, the type of farmland abandonment in the target area is determined.

[0010] Further, the analysis of the time-series images of the surface vegetation end-members and the surface soil end-members, respectively, to obtain the optimal fitting curves and corresponding variation characteristic parameters of the time-series images of the surface vegetation end-members and the surface soil end-members, includes:

[0011] Adaptive fitting is performed on the time series images of the surface vegetation end-members and the time series images of the surface soil end-members to obtain the optimal fitting curves corresponding to the time series images of the surface vegetation end-members and the time series images of the surface soil end-members.

[0012] The characteristic parameters of the optimal fitting curve are determined using parameter selection rules that match the optimal fitting curve, and are used as the variation characteristic parameters.

[0013] Further, the adaptive fitting of the time-series images of the surface vegetation end-members and the surface soil end-members to obtain the optimal fitting curves corresponding to the time-series images of the surface vegetation end-members and the surface soil end-members includes:

[0014] Linear fitting, logical fitting, and double logical fitting are used to fit the time series images of the land surface vegetation end-member and the land surface soil end-member respectively, to obtain linear fitting curves, logical fitting curves, and double logical fitting curves.

[0015] Calculate the root mean square error of the residuals of each fitted curve, and determine the optimal fitted curve based on the calculation results.

[0016] Further, the step of calculating the root mean square error of the residuals of each of the fitted curves and determining the optimal fitted curve based on the calculation results includes:

[0017]

[0018] Model optimal =argmin(RMSE) Linear RMSE Logistic RMSE DoubleLogistic )

[0019] Among them, RMSE Linear The root mean square error (RMSE) of the residuals of the linearly fitted curve. LogisticThe root mean square error (RMSE) of the residuals of the logistic fitting curve. DoubleLogistic The root mean square error of the residuals of the double-logistic fitting curve; Model optimal The optimal fitting curve is defined by β0 and β1, which are the fitting parameters for the linear fitting curve, respectively. L, k, and t0 are the fitting parameters for the logistic fitting curve, respectively. 0,1 and t 0,2 These are the fitting parameters for the double-logic fitting curve; y i and x i These represent the time series values ​​of vegetation / soil endmembers and the year, respectively.

[0020] Further, the step of determining the characteristic parameters of the optimal fitting curve using parameter selection rules that match the optimal fitting curve, as the changing characteristic parameters, includes:

[0021] If the optimal fitting curve is a linear fitting curve, the linear trend of the linear fitting curve is used as the change characteristic parameter;

[0022] If the optimal fitting curve is a logical fitting curve, the inflection start time, inflection end time and curve change amplitude in the logical fitting curve are used as the change feature parameters.

[0023] If the optimal fitting curve is a double logic fitting curve, the turning point start time, the second turning point time, the peak / valley arrival time, the peak / valley duration, and the curve change amplitude in the double logic fitting curve are used as the change characteristic parameters.

[0024] Furthermore, the variation characteristic parameters of the logical fitting curve and the double logical fitting curve are determined by the second derivative;

[0025] The formula for the second derivative is as follows:

[0026]

[0027] Where z = e at-b a and b are the fitting parameters of the logistic fitting curve, respectively; the inflection start time t0 of the logistic fitting curve is the maximum value of the second derivative, and the inflection end time t1 is the minimum value of the second derivative; the inflection start time t0 of the dual logistic fitting curve is the maximum value of the second derivative of the first logistic fitting curve, the peak / valley arrival time t1 is the minimum value of the second derivative of the first logistic fitting curve, and the second inflection time t2 is the maximum value of the second derivative of the second logistic fitting curve.

[0028] And / or,

[0029] The formulas for the curve variation amplitudes of the logic fitting curve and the double logic fitting curve are expressed as follows:

[0030] Mag = f(t1) - f(t0)

[0031] And / or,

[0032] The formula for the peak / valley duration of the double logic fitting curve is as follows:

[0033] Dur = t2 - t1

[0034] Where t0 is the start time of the turning point; t1 is the end time of the turning point or the time when the peak / valley value is reached; and t2 is the time of the second turning point.

[0035] Furthermore, determining the type of farmland abandonment in the target area based on the optimal fitting curve and corresponding variation characteristic parameters of the target area includes:

[0036] If the optimal fitting curve for the target area is a logistic fitting curve, the type of farmland abandonment in the target area is determined using the following formula:

[0037]

[0038] Where K is a positive empirical threshold; 1 represents the target area as abandoned farmland; 0 represents the target area as abandoned non-farmland; Mag v The variation amplitude of the vegetation logical fitting curve in the target area; Mag s The variation range of the soil logical fitting curve for the target area;

[0039] And / or,

[0040] If the optimal fitting curve for the target area is a double-logic fitting curve, the type of farmland abandonment in the target area is determined using the following formula:

[0041]

[0042] Among them, Mag v The variation amplitude of the vegetation double-logic fitting curve in the target area; Mag s The value represents the variation range of the soil double-logistic fitting curve in the target area; 1 represents that the target area is a potential arable land change area; 0 represents that the target area is a non-arable land abandonment area.

[0043] When the target area is a potential area of ​​farmland change, the type of farmland abandonment in the target area is determined using the following formula:

[0044]

[0045] Among them, Dur vDur is the duration of the valley value of the double-logic fitting curve of the vegetation in the target area. s The peak duration of the soil double-logic fitting curve for the target area; T is the preset duration; 1 represents the target area as a potential abandoned area; 0 represents the target area as a fallow area.

[0046] Furthermore, based on the land use type, the subsequent type of farmland abandonment in the target area is determined using the following formula:

[0047]

[0048] Among them, LU later The target area represents the subsequent land use type; Non_AG ​​represents non-arable land; AG represents arable land; 1 represents the target area as an abandoned area; 0 represents the target area as an abandoned area to be reclaimed.

[0049] According to a second aspect of the present invention, the present invention provides a device for identifying the entire life cycle of abandoned farmland, the device comprising:

[0050] The data acquisition module is used to acquire time-series images of surface vegetation end-members and surface soil end-members of the target area.

[0051] The data analysis module is used to analyze the time series images of the surface vegetation end-members and the time series images of the surface soil end-members, respectively, to obtain the optimal fitting curves and corresponding change characteristic parameters of the time series images of the surface vegetation end-members and the time series images of the surface soil end-members.

[0052] The type identification module is used to determine the type of farmland abandonment in the target area based on the optimal fitting curve of the target area and the corresponding change feature parameters.

[0053] According to a third aspect of the present invention, the present invention provides a computer device, including 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 computer program, it implements the method for identifying the entire life cycle of abandoned farmland as described in any one of the first aspects of the present invention.

[0054] The present invention, by adopting the above technical solution, has at least the following beneficial effects:

[0055] This invention acquires time-series images of surface vegetation and surface soil end-members in a target area. These images are then analyzed to obtain optimal fitting curves and corresponding variation characteristic parameters. Based on these optimal fitting curves and variation characteristic parameters, the type of farmland abandonment in the target area is determined. Thus, by utilizing vegetation-soil end-member time-series data characterizing the surface process of farmland abandonment, a full life-cycle model of farmland abandonment and farmland abandonment scenario identification, integrating multi-dimensional end-member time-series interaction information, is developed. This forms an efficient and high-precision method for monitoring the entire life-cycle of farmland abandonment, providing technical support for intelligent monitoring and supervision of natural resources such as farmland conversion to non-agricultural or non-grain uses.

[0056] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 A flowchart illustrating the whole life cycle identification method for farmland abandonment provided in an embodiment of the present invention is shown.

[0059] Figure 2 A simplified schematic diagram of three optimal fitting curve types provided in an embodiment of the present invention is shown;

[0060] Figure 3 A simplified schematic diagram of the varying characteristic parameters provided in an embodiment of the present invention is shown;

[0061] Figure 4 A simplified schematic diagram of the calculation of the first and second derivatives of the changing characteristic parameters provided in an embodiment of the present invention is shown;

[0062] Figure 5 A schematic diagram of the structure of a farmland abandonment full life cycle identification device provided in an embodiment of the present invention is shown;

[0063] Figure 6 A schematic diagram of the physical structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0064] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0066] This invention provides a method for identifying the entire lifecycle of farmland abandonment, such as... Figure 1 As shown, it may include at least the following steps S101 to S103:

[0067] Step S101: Obtain time-series images of surface vegetation end-members and surface soil end-members in the target area.

[0068] Unlike traditional vegetation indices, endmembers can represent the proportion of different land features in a mixed pixel in a physically meaningful way, which helps to extract multidimensional surface feature information. Therefore, this embodiment of the invention acquires endmember time-series images based on surface vegetation and endmember time-series images of surface soil for subsequent processing of the target area to be identified.

[0069] Step S102: Analyze the time series images of surface vegetation end-members and surface soil end-members respectively to obtain the optimal fitting curves and corresponding change characteristic parameters of the time series images of surface vegetation end-members and surface soil end-members.

[0070] Specifically, adaptive fitting can be performed on the time series images of surface vegetation end-members and surface soil end-members to obtain the optimal fitting curves corresponding to the time series images of surface vegetation end-members and surface soil end-members. Then, the characteristic parameters of the optimal fitting curve can be determined by using the parameter selection rules that match the optimal fitting curve, and these parameters can be used as the variation characteristic parameters.

[0071] This invention provides an optimal curve fitting method for the entire life cycle of farmland abandonment through adaptive time series fitting. It also provides feature parameters for farmland abandonment identification through the analysis of different paths, thus enabling the reconstruction and modeling of the entire farmland abandonment process under different climatic backgrounds (differences in natural vegetation recovery capacity) and human disturbances (reclamation and fallow).

[0072] It is understandable that the evolution patterns of vegetation and soil time series in abandoned farmland differ across climatic regions. For example, in arid regions, due to poor natural vegetation recovery, the end-member time series of vegetation and soil in abandoned farmland often exhibit logistic curves; while in humid regions, due to better natural vegetation recovery, the end-member time series of vegetation and soil are often U-shaped. Furthermore, considering that reclamation after farmland abandonment can also be characterized by U-shaped curves of vegetation and soil end-members, this invention, in its embodiment, when adaptively fitting time series images, can set linear fitting, logistic fitting, and double logistic fitting methods to perform pixel-by-pixel fitting on the end-member time series images of surface vegetation and surface soil, respectively, to obtain linear fitting curves, logistic fitting curves, and double logistic fitting curves. Figure 2 The figures shown are simplified diagrams of linear fitting curves, logistic fitting curves, and double logistic fitting curves, respectively. Then, the root mean square error of the residuals for each fitting curve is calculated, and the optimal fitting curve is determined based on the calculation results.

[0073] The root mean square error of the residuals of the linear fitting curve is calculated using the following formula (1):

[0074]

[0075] The root mean square error of the residuals of the logistic fitting curve is calculated using the following formula (2):

[0076]

[0077] The root mean square error of the residuals of the double logic fitting curve is calculated using the following formula (3):

[0078]

[0079] Furthermore, after obtaining the root mean square error of the residuals for each fitted curve, the fitted curve with the smallest root mean square error of the residuals is selected as the optimal fitted curve, as expressed by the following formula (4):

[0080] Model optimal =arg min(RMSE) Linear RMSE Logistic RMSE DoubleLogistic (4)

[0081] Where β0 and β1 are the fitting parameters of the linear fitting curve; L, k, and t0 are the fitting parameters of the logistic fitting curve; L1, L2, k1, k2, and t0 are the fitting parameters of the logistic fitting curve. 0,1 and t 0,2 These are the fitting parameters for the double-logic fitting curve; y i and x i These represent the vegetation / soil end-member time series values ​​and the year, respectively. In this embodiment of the invention, the characteristic parameters of the optimal fitting curve are determined using parameter selection rules that match the optimal fitting curve, serving as variation characteristic parameters. Specifically, the parameter selection rules can be as follows: if the optimal fitting curve is a linear fitting curve, the linear trend of the linear fitting curve is used as the variation characteristic parameter; if the optimal fitting curve is a logistic fitting curve, the inflection start time, inflection end time, and curve change amplitude in the logistic fitting curve are used as variation characteristic parameters; if the optimal fitting curve is a double logistic fitting curve, the inflection start time, re-inflection time, peak / valley arrival time, peak / valley duration, and curve change amplitude in the double logistic fitting curve are used as variation characteristic parameters.

[0082] like Figure 3 The figures shown are simplified schematic diagrams of the changing characteristic parameters in the logistic fitting curve and the double logistic fitting curve, respectively. To obtain these changing characteristic parameters, this embodiment of the invention determines them using the second derivative of the fitting curve, as shown below. Figure 4 The figures shown are simplified diagrams of the first and second derivatives of the fitted curve, respectively. The formula for calculating the first derivative is as follows (5):

[0083]

[0084] The formula for the second derivative is as follows (6):

[0085]

[0086] Where z = e at-b a and b are the fitting parameters of the logic fitting curve, respectively; the inflection start time t0 of the logic fitting curve is the maximum value of the second derivative, and the inflection end time t1 is the minimum value of the second derivative. Therefore, the formula for the curve change amplitude of the logic fitting curve and the double logic fitting curve in the embodiment of the present invention is expressed as follows (7):

[0087] Mag = f(t1) - f(t0) (7)

[0088] The formula for the duration of peak / valley values ​​of the double-logistic fitting curve is expressed as follows (8):

[0089] Dur=t2-t1 (8)

[0090] Where t0 is the inflection start time; t1 is the inflection end time or the peak / trough arrival time; and t2 is the second inflection time. It can be understood that the dual-logic fitting curve consists of two logic curves (the first logic fitting curve and the second logic fitting curve), and its parameter calculation process is consistent with that of the logic curves. Specifically, the inflection start time t0 of the dual-logic fitting curve is the maximum value of the second derivative of the first logic fitting curve, the peak / trough arrival time t1 is the minimum value of the second derivative of the first logic fitting curve, and the second inflection time t2 is the maximum value of the second derivative of the second logic fitting curve.

[0091] Step S103: Based on the optimal fitting curve of the target area and the corresponding change characteristic parameters, determine the type of farmland abandonment in the target area.

[0092] It should be noted that the embodiments of the present invention not only use the changes in the time series of vegetation endmembers, but also the changes in the time series of soil endmember data that interact with them for farmland abandonment detection. Therefore, the embodiments of the present invention mainly combine the change feature parameters of the two endmember time series to establish a rule-based farmland abandonment identification process, as follows:

[0093] If the optimal fitting curve for the target area is a logistic fitting curve, the type of farmland abandonment in the target area can be determined using the following formula (9):

[0094]

[0095] Where K is a positive empirical threshold; 1 represents the target area as abandoned farmland; 0 represents the target area as abandoned non-farmland; Mag v The magnitude of the change in the vegetation logistic fitting curve for the target area; Mag s The variation range of the soil logical fitting curve for the target area.

[0096] Understandably, the magnitude of vegetation change is significant. v The value is negative, indicating the magnitude of soil variation (Mag). s A positive value indicates that vegetation degradation and soil exposure have occurred during the process. This embodiment of the invention determines the validity of this change characteristic by setting an empirical threshold (K) where the change magnitude exceeds a certain positive value. Therefore, based on the above characteristics, areas of abandoned farmland can be identified.

[0097] If the optimal fitting curve for the target area is a double-logic fitting curve, the characteristics of farmland evolution are relatively complex, including three types: farmland abandonment, reclamation after abandonment, and farmland fallow. Therefore, in this embodiment of the invention, rules are established and types are classified by combining land use cover type data and end-member time series curves. The specific formula is as follows (10):

[0098]

[0099] Among them, Mag v The magnitude of the variation in the dual-logic fitting curve of vegetation in the target area; Mag s The variation amplitude of the soil double-logic fitting curve in the target area; Mag s >0 indicates that the soil double-logic fitting curve exhibits an inverted U-shape, while >0 indicates a Mag v <0 indicates that the vegetation double logic fitting curve presents a U-shape; 1 indicates that the target area is a potential arable land change area; 0 indicates that the target area is a non-arable land abandonment area. That is to say, according to the preliminary judgment criteria of formula (10), the vegetation end-member abundance is U-shaped and the soil end-member abundance is inverted U-shaped, which characterizes the potential arable land change area.

[0100] Furthermore, when the target area is a potential area of ​​farmland change, the type of farmland abandonment in the target area is determined using the following formula (11):

[0101]

[0102] Among them, Dur v Dur is the duration of the valley value in the double logistic fitting curve of the vegetation in the target area. s The peak duration of the soil double-logic fitting curve for the target area; T is the preset duration; 1 represents the target area as a potential fallow area; 0 represents the target area as a fallow area. It is understood that the criterion for this step is that the duration of the vegetation end-member abundance trough or the soil end-member abundance peak is greater than the preset duration, thus eliminating fallow areas. Preferably, the preset duration can be 2 years.

[0103] Furthermore, embodiments of the present invention can also obtain the land use type of the target area in the later stage, and determine the type of farmland abandonment in the target area in the later stage based on the land use type, as expressed by the following formula (12):

[0104]

[0105] Among them, LU later This represents the subsequent land use type of the target area; Non_AG ​​represents non-arable land; AG represents arable land; 1 indicates the target area is an abandoned area; 0 indicates the target area is an abandoned area that will be reclaimed. The judgment criteria for this step are to determine whether the arable land is abandoned or abandoned + reclaimed based on the subsequent land use type. If the subsequent land use cover is non-arable land, it is determined to be abandoned. If the subsequent land use cover is arable land, it is determined to be abandoned and then reclaimed.

[0106] Based on the above steps, a multi-dimensional information model of the entire process of farmland abandonment is realized, and then multi-dimensional information integration is carried out to identify farmland abandonment, so as to accurately identify whether the target area is an abandoned area or a non-abandoned area. Furthermore, it can further identify the target area as farmland abandonment, farmland reclamation after abandonment, and farmland fallow areas.

[0107] This invention provides a method for identifying the entire lifecycle of farmland abandonment, including acquiring time-series images of surface vegetation and surface soil end-members of a target area; analyzing the time-series images of surface vegetation and surface soil end-members respectively to obtain the optimal fitting curves and corresponding change characteristic parameters of the time-series images of surface vegetation and surface soil end-members; and determining the type of farmland abandonment in the target area based on the optimal fitting curves and corresponding change characteristic parameters of the target area. This invention provides a method for modeling and identifying the entire lifecycle of farmland abandonment by integrating multi-dimensional end-member time-series interactive information. Through farmland abandonment detection based on the interactive mining of end-member time-series information and the full-process modeling of multi-dimensional surface element information time series, it helps to refine the detection of the evolution characteristics of the entire process of farmland abandonment and improve the accuracy of farmland abandonment monitoring.

[0108] Furthermore, as Figure 1 In specific implementation, embodiments of the present invention provide a device for identifying the entire lifecycle of farmland abandonment, such as... Figure 5 As shown, the device may include: a data acquisition module 510, a data analysis module 520, and a type recognition module 530.

[0109] Data acquisition module 510 can be used to acquire time series images of surface vegetation end-members and surface soil end-members of the target area;

[0110] The data analysis module 520 can be used to analyze the time series images of surface vegetation end-members and surface soil end-members respectively, and obtain the optimal fitting curves and corresponding change characteristic parameters of the time series images of surface vegetation end-members and surface soil end-members.

[0111] The type identification module 530 can be used to determine the type of farmland abandonment in the target area based on the optimal fitting curve of the target area and the corresponding change characteristic parameters.

[0112] Optionally, the data analysis module 520 can also be used to adaptively fit the time series images of surface vegetation end-members and surface soil end-members to obtain the optimal fitting curves corresponding to the time series images of surface vegetation end-members and surface soil end-members.

[0113] The characteristic parameters of the optimal fitting curve are determined by using parameter selection rules that match the optimal fitting curve, and these parameters are used as variable characteristic parameters.

[0114] Optionally, the data analysis module 520 can also be used to set linear fitting, logical fitting and double logical fitting forms to fit the time series images of land surface vegetation end-members and land surface soil end-members respectively, to obtain linear fitting curves, logical fitting curves and double logical fitting curves.

[0115] Calculate the root mean square error of the residuals for each fitted curve, and determine the optimal fitted curve based on the calculation results.

[0116] Optionally, the data analysis module 520 can also be used to determine the optimal fitted curve using the following formula:

[0117]

[0118] Model optimal =argmin(RMSE) Linear RMSE Logistic RMSE DoubleLogistic )

[0119] Among them, RMSE Linear The root mean square error (RMSE) of the residuals of the linearly fitted curve. Logistic The root mean square error (RMSE) of the residuals of the logistic fitting curve. DoubleLogistic The root mean square error of the residuals of the double-logistic fitting curve; Model optimal The optimal fitting curve is defined by β0 and β1, which are the fitting parameters for the linear fitting curve, respectively. L, k, and t0 are the fitting parameters for the logistic fitting curve, respectively. 0,1 and t 0,2 These are the fitting parameters for the double-logic fitting curve; y i and x i These represent the time series values ​​of vegetation / soil endmembers and the year, respectively.

[0120] Optionally, the data analysis module 520 can also be used to use the linear trend of the linear fitting curve as a change characteristic parameter when the optimal fitting curve is a linear fitting curve.

[0121] When the optimal fitting curve is the logical fitting curve, the start time of the inflection, the end time of the inflection, and the magnitude of the curve change in the logical fitting curve are used as the change characteristic parameters.

[0122] When the optimal fitting curve is a double logic fitting curve, the inflection start time, the second inflection time, the peak / valley arrival time, the peak / valley duration, and the curve change amplitude in the double logic fitting curve are used as change characteristic parameters.

[0123] Optionally, the variation characteristic parameters of the logistic fitting curve and the double logistic fitting curve are determined by the second derivative;

[0124] The formula for the second derivative is as follows:

[0125]

[0126] Where z = e at-b ; a and b are the fitting parameters of the logistic fitting curve, respectively; the inflection start time t0 of the logistic fitting curve is the maximum value of the second derivative, and the inflection end time t1 is the minimum value of the second derivative; the inflection start time t0 of the double logistic fitting curve is the maximum value of the second derivative of the first logistic fitting curve, the peak / valley arrival time t1 is the minimum value of the second derivative of the first logistic fitting curve, and the inflection time t2 is the maximum value of the second derivative of the second logistic fitting curve.

[0127] And / or,

[0128] The formulas for the magnitude of change of the logistic fitting curve and the double logistic fitting curve are expressed as follows:

[0129] Mag = f(t1) - f(t0)

[0130] And / or,

[0131] The formula for the duration of peaks / troughs in a double-logistic fitting curve is as follows:

[0132] Dur = t2 - t1

[0133] Where t0 is the start time of the turning point; t1 is the end time of the turning point or the time when the peak / valley value is reached; and t2 is the time of the second turning point.

[0134] Optionally, the type recognition module 530 can also be used to determine the type of farmland abandonment in the target area using the following formula when the optimal fitting curve of the target area is a logistic fitting curve:

[0135]

[0136] Where K is a positive empirical threshold; 1 represents the target area as abandoned farmland; 0 represents the target area as abandoned non-farmland; Mag v The magnitude of the change in the vegetation logistic fitting curve for the target area; Mag s The variation range of the soil logical fitting curve for the target area;

[0137] And / or,

[0138] When the optimal fitting curve for the target area is a double-logic fitting curve, the type of farmland abandonment in the target area is determined using the following formula:

[0139]

[0140] Among them, Mag v The magnitude of the variation in the dual-logic fitting curve of vegetation in the target area; Mag s The value represents the variation range of the soil double-logistic fitting curve in the target area; 1 represents the target area as a potential area for arable land change; 0 represents the target area as a non-arable land abandonment area.

[0141] When the target area is a potential area of ​​farmland change, the type of farmland abandonment in the target area is determined using the following formula:

[0142]

[0143] Among them, Dur v Dur is the duration of the valley value in the double logistic fitting curve of the vegetation in the target area. s is the peak duration of the soil double-logic fitting curve for the target area; T is the preset duration; 1 represents the target area as a potential abandoned area; 0 represents the target area as a fallow area.

[0144] Optionally, the type recognition module 530 can also be used to obtain the land use type of the target area in the later stage, and determine the type of farmland abandonment in the target area in the later stage based on the land use type, as shown in the following formula:

[0145]

[0146] Among them, LU later This represents the subsequent land use type of the target area; Non_AG ​​represents non-arable land; AG represents arable land; 1 represents the target area as an abandoned area; 0 represents the target area as an abandoned area that will be reclaimed.

[0147] It should be noted that other corresponding descriptions of the functional modules involved in the farmland abandonment full life cycle identification device provided in this embodiment of the invention can be found in [reference]. Figure 1 The corresponding description of the method shown will not be repeated here.

[0148] Based on the above, Figure 1 The method shown and as Figure 5 The embodiment of the device shown in the invention also provides a physical structure diagram of a computer device, such as... Figure 6 As shown, the computer device may include a communication bus, a processor, a memory, and a communication interface. It may also include input / output interfaces and a display device. The various functional units can communicate with each other via the bus. The memory stores a computer program, and the processor executes the program stored in the memory, performing the steps of the farmland abandonment lifecycle identification method described in the above embodiments.

[0149] Those skilled in the art will clearly understand that the specific working process of the systems, devices, modules and units described above can be referred to the corresponding process in the foregoing method embodiments. For the sake of brevity, it will not be repeated here.

[0150] Furthermore, the functional units in the various embodiments of the present invention can be physically independent of each other, or two or more functional units can be integrated together, or all functional units can be integrated into one processing unit. The integrated functional units described above can be implemented in hardware, or in software or firmware.

[0151] Those skilled in the art will understand that if the integrated functional unit is implemented in software and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or all or part of it, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computing device (e.g., a personal computer, server, or network device) to execute all or part of the steps of the methods described in the embodiments of the present invention when running the instructions. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0152] Alternatively, all or part of the steps of the foregoing method embodiments can be implemented by hardware (such as a computing device, personal computer, server, or network device) related to program instructions. The program instructions can be stored in a computer-readable storage medium. When the program instructions are executed by the processor of the computing device, the computing device executes all or part of the steps of the methods described in the various embodiments of the present invention.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that within the spirit and principles of the present invention, modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein; and these modifications or substitutions do not cause the corresponding technical solutions to depart from the protection scope of the present invention.

Claims

1. A cultivated land abandoned land full life cycle recognition method, characterized by, The method comprises: acquiring surface vegetation end-member time series images and surface soil end-member time series images of a target region; analyzing the surface vegetation end-member time series images and the surface soil end-member time series images respectively to obtain optimal fitting curves and corresponding change characteristic parameters of the surface vegetation end-member time series and the surface soil end-member time series, including: performing adaptive fitting on the surface vegetation end-member time series images and the surface soil end-member time series images to obtain optimal fitting curves corresponding to the surface vegetation end-member time series and the surface soil end-member time series, including: setting linear fitting, logical fitting and double-logical fitting forms to fit the surface vegetation end-member time series images and the surface soil end-member time series images respectively to obtain linear fitting curves, logical fitting curves and double-logical fitting curves; calculating root mean square errors of residuals of each fitting curve, and determining the optimal fitting curve based on the calculation result; determining characteristic parameters of the optimal fitting curve as the change characteristic parameters using parameter selection rules matched with the optimal fitting curve, including: if the optimal fitting curve is a linear fitting curve, taking a linear trend of the linear fitting curve as the change characteristic parameter; if the optimal fitting curve is a logical fitting curve, taking a turning start time, a turning end time and a curve change amplitude in the logical fitting curve as the change characteristic parameters; if the optimal fitting curve is a double-logical fitting curve, taking a turning start time, a second turning time, a peak / valley value arrival time, a peak / valley value duration and a curve change amplitude in the double-logical fitting curve as the change characteristic parameters; the change characteristic parameters of the logical fitting curve and the double-logical fitting curve are determined by a second derivative; a formula of the second derivative is as follows: wherein ; and are the fitting parameters of the logistic fitting curve; the turning point start time is the maximum of the second derivative, the turning point end time is the minimum of the second derivative; the turning point start time is the maximum of the second derivative of the first logistic fitting curve, the peak / trough value reaching time is the minimum of the second derivative of the first logistic fitting curve, the second turning point time is the maximum of the second derivative of the second logistic fitting curve; and / or, a formula of the curve change amplitude of the logical fitting curve and the double-logical fitting curve is as follows: and / or, a formula of the peak / valley value duration of the double-logical fitting curve is as follows: wherein, is the turning start time; is the turning end time or peak / trough value arrival time; is the re-turning time; based on the optimal fitting curve and the corresponding change characteristic parameters of the target region, determining a cultivated land abandonment type of the target region, including: if the optimal fitting curve of the target region is a logical fitting curve, determining the cultivated land abandonment type of the target region using the following formula: wherein, is a positive empirical threshold value; represents that the target region is a cultivated land abandoned region; represents that the target region is a non-cultivated land abandoned region; is a variation amplitude of a vegetation logical fitting curve of the target region; is a variation amplitude of a soil logical fitting curve of the target region; and / or, if the optimal fitting curve of the target region is a double-logical fitting curve, determining the cultivated land abandonment type of the target region using the following formula: wherein, a variation amplitude of a vegetation double-log fitting curve of the target region; a variation amplitude of a soil double-log fitting curve of the target region; representing that the target region is a potential cultivated land change region; representing that the target region is a non-cultivated land abandoned land region; when the target region is a potential cultivated land change region, determining the cultivated land abandonment type of the target region using the following formula: wherein, a duration of a valley of a double-logistic fitting curve of vegetation of the target area; a duration of a peak of a double-logistic fitting curve of soil of the target area; a preset duration; representing that the target area is a potential abandoned area; representing that the target area is a fallow area.

2. The method of claim 1, wherein, the calculation of the root mean square errors of residuals of each fitting curve and the determination of the optimal fitting curve based on the calculation result include: determining the optimal fitting curve using the following formula: wherein, is the root mean square error of the residuals of the linear fit curve; is the root mean square error of the residuals of the logistic fit curve; is the root mean square error of the residuals of the bi-logistic fit curve; is the optimal fit curve; and are the fit parameters of the linear fit curve, respectively; , are the fit parameters of the logistic fit curve, respectively; , are the fit parameters of the bi-logistic fit curve, respectively; and are the vegetation / soil endmember time series values and year, respectively.

3. The method of claim 1, wherein, The method further comprises: acquiring a land use mode type of the target region in a later period, and determining a cultivated land abandonment type of the target region in the later period based on the land use mode type, which is represented by the following formula: wherein, is a later land use type of the target region; is non-crop land; is crop land; represents that the target region is a fallow land; represents that the target region is a reclamation land after fallow.

4. A cultivated land abandoned land full life cycle recognition device characterized by, The device is applied to the cultivated land abandonment full life cycle identification method in any one of claims 1-3, and the device comprises: a data acquisition module, configured to acquire time-series images of surface vegetation end members and time-series images of surface soil end members in a target area; a data analysis module, configured to analyze the time-series images of surface vegetation end members and the time-series images of surface soil end members respectively, to obtain optimal fitting curves and corresponding variation characteristic parameters of time-series of surface vegetation end members and time-series of surface soil end members; a type identification module, configured to determine a cultivated land abandonment type of the target area based on the optimal fitting curves and the corresponding variation characteristic parameters of the target area.

5. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the cultivated land abandonment full life cycle identification method in any one of claims 1-3.

Images