A method and device for identifying historical damaged land

Abstract

A method for identifying damaged land left over from history includes: obtaining relevant data of a target area to be identified, the relevant data including remote sensing image data of the target area; determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data based on the remote sensing image data; determining the change trajectory of the land use type represented by each pixel based on the change trajectory of the remote sensing index; determining whether the land represented by each pixel is damaged based on the change trajectory of the land use type; in the case of land damage, determining whether the land is reclaimed; verifying the identified damaged land to determine the final identification result, which includes whether the land is reclaimed and whether the land reclamation is sufficient. This method can realize the objective and accurate identification of damaged land left over from history, avoiding the misjudgment or omission that may be caused by static time point data.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental monitoring, and in particular to a method and device for identifying historical damaged land. Background Art

[0002] In December 2012, the "Implementation Measures for the Land Reclamation Regulations" was issued, which clearly stated that the land damaged by production and construction activities where the land reclamation obligor has disappeared, or the land damaged by production and construction activities before the implementation of the "Land Reclamation Regulations", should be identified as historical damaged land by the local county-level land and resources department. According to the overall deployment and requirements of the investigation and evaluation work of relevant departments, it is urgent to form a technical method for quickly and accurately identifying historical damaged land, so as to serve the subsequent historical damaged land evaluation, reclamation special planning, reclamation implementation and dynamic management. Summary of the invention

[0003] In order to solve the problems existing in the prior art, the embodiments of the present application provide a method, apparatus, computing device, computer storage medium and product including a computer program for identifying historical damaged land, which can achieve objective and accurate identification of historical damaged land and avoid misjudgment or omissions that may be caused by static point-in-time data.

[0004] In a first aspect, an embodiment of the present application provides a method for identifying historical damaged land, including: acquiring relevant data of a target area to be identified, the relevant data including remote sensing image data of the target area; determining, based on the remote sensing image data, a change trajectory of a remote sensing index of each pixel in the remote sensing image data; determining, based on the change trajectory of the remote sensing index, a change trajectory of a land use type of the land represented by each pixel; determining, based on the change trajectory of the land use type, whether the land represented by each pixel is damaged; in the event of land damage, determining whether the land has been reclaimed; in the event of land reclamation, determining whether the land reclamation is sufficient; verifying the identified damaged land to determine a final identification result, the identification result including whether the land has been reclaimed and whether the land reclamation is sufficient.

[0005] In some possible implementations, the remote sensing index includes the normalized vegetation index, the normalized degradation score index, and the normalized difference water index; among them, the normalized vegetation index is used to distinguish vegetation from non-vegetation, the normalized degradation score index is used to distinguish forests from non-forests, and the normalized difference water index is used to distinguish water bodies from non-water bodies.

[0006] In some possible implementations, determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data includes: fitting the harmonic function of the remote sensing index to each pixel in the remote sensing image data, and using the fitted harmonic function as the expression formula of the time series trajectory curve of each pixel; fitting the remote sensing index is performed according to the following formula:

[0007]

[0008] In the formula, i represents the i-th band of the image data, t represents the Julian date, p represents the predicted value, and a 0,i Characterization intercept, s i Characterizes the interannual variation coefficient, a 1,i , b 1,i Characterizes the coefficient of variation within a year, a 2,i , b 2,i Characterizes the annual double peak variation coefficient, a 3,i , b 3,i It represents the coefficient of variation of the three peaks within a year, and T represents the number of days in each year.

[0009] In some possible implementations, determining a change trajectory of a remote sensing index of each pixel in the remote sensing image data includes: taking the maximum value of each remote sensing index in different years as a data point of the change trajectory.

[0010] In some possible implementations, the method further includes: in the event of land damage, recording time information when the land damage occurs.

[0011] In some possible implementations, whether land reclamation is sufficient includes sufficient land reclamation and inadequate land reclamation. Sufficient land reclamation includes that after reclamation, the land reaches the productivity level before damage, and / or is higher than the highest productivity level of the same type of surrounding land.

[0012] In some possible implementations, the method also includes: obtaining map point of interest data and auxiliary information, and verifying historical damaged land based on the map point of interest data and auxiliary information; wherein the auxiliary information includes the production and construction units or personal information that caused the land damage in the target area, the current production and operation status of the production and construction units, and the ownership information of the damaged land.

[0013] In some possible implementations, the final identification results include Type I, Type II, Type III, and Type IV; among them, Type I indicates that the damage occurred in 1988 or before, and no reclamation was implemented after the damage; Type II indicates that the damage occurred in 1988 or before, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved; Type III indicates that the damage occurred in 1989 or later, the person with the obligation to reclaim the land was lost or the responsible entity for land reclamation was the government, and no reclamation was implemented after the damage; Type IV indicates that the damage occurred in 1989 or later, the person with the obligation to reclaim the land was lost or the responsible entity for land reclamation was the government, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved.

[0014] In some possible implementations, the land use types include forest, other vegetation, non-vegetation, and water.

[0015] In a second aspect, an embodiment of the present application provides a device for identifying historical damaged land, including: an acquisition module for acquiring relevant data of a target area to be identified, the relevant data including remote sensing image data of the target area; a processing module for determining, based on the remote sensing image data, a change trajectory of a remote sensing index of each pixel in the remote sensing image data; the processing module is also used to determine, based on the change trajectory of the remote sensing index, a change trajectory of a land use type of the land represented by each pixel; the processing module is also used to determine whether the land represented by each pixel is damaged based on the change trajectory of the land use type; the processing module is also used to determine whether the land has been reclaimed if the land has been damaged; if the land has been reclaimed, to determine whether the land has been reclaimed sufficiently; the processing module is also used to verify the identified damaged land to determine a final identification result, the identification result including whether the land has been reclaimed and whether the land has been reclaimed sufficiently.

[0016] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising computer-readable instructions. When a computer reads and executes the computer-readable instructions, the computer executes the method described in any one of the first aspects.

[0017] In a fourth aspect, an embodiment of the present application provides a computing device, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method described in any one of the first aspects is executed.

[0018] In a fifth aspect, an embodiment of the present application provides a product comprising a computer program. When the computer program product runs on a processor, the processor executes the method as described in any one of the first aspects.

[0019] This method can grasp the spatial distribution of historical damaged land in real time and comprehensively, and provide technical reference for scientifically and rationally formulating national land space ecological restoration plans, and quickly, efficiently and benchmarking the ecological restoration of historical damaged land. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0021] Figure 1It is a flow chart of a method for identifying historical damaged land provided in an embodiment of the present application;

[0022] Figure 2 It is a schematic diagram of a data processing result provided in an embodiment of the present application;

[0023] Figure 3 This is a schematic diagram of the historical damaged land identification area and damage year information provided by the embodiment of the present application;

[0024] Figure 4 It is a schematic diagram of the identification result of historical damaged land after verification provided by the embodiment of the present application;

[0025] Figure 5 It is a structural schematic diagram of a device for identifying historical damaged land provided in an embodiment of the present application;

[0026] Figure 6 It is a structural diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] The term "and / or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol " / " in this article indicates that the associated objects are in an or relationship, for example, A / B means A or B.

[0029] The terms "first" and "second" in the specification and claims herein are used to distinguish different objects rather than to describe a specific order of the objects. For example, a first response message and a second response message are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0030] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

[0032] To facilitate the understanding of the embodiments of the present application, the following will further explain and illustrate specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0033] According to the "Research on the Investigation and Utilization of Land Damaged by Historical Relics and Natural Disasters" compiled by the Real Estate Registration Center of the Ministry of Land and Resources (Legal Affairs Center of the Ministry of Land and Resources), the "Appendix 1 National Investigation Procedures for Land Damaged by Historical Relics and Natural Disasters" in the book stipulates that the investigation / identification methods of historical damaged land include the following 6 methods: 1. The existing data extraction method is applicable to areas where historical damaged land investigation has been implemented or relevant data has been accumulated; 2. The image interpretation method is generally applicable to grasslands, deserts or eastern collapsed and waterlogged areas; 3. The GIS spatial analysis method is applicable to situations where the boundary information of historical damaged land has been obtained and the relevant land use information data is relatively complete; 4. The expert experience investigation method is only applicable to areas where management or technical personnel are familiar with the land use status in the jurisdiction; 5. The investigation and inquiry method is applicable to most investigation areas. When applied in the early stage of the investigation, it can obtain general information on historical damaged land, which is helpful for actual measurement and image interpretation. When applied in the later stage of the investigation, it helps to assist in the evaluation of the investigation results; 6. The field investigation and measurement method is applicable to all investigation areas, and the data obtained is relatively objective and accurate.

[0034] Among the existing related methods, the identification methods for historical damaged land include traditional survey methods and satellite remote sensing technology identification methods. However, for traditional survey methods, the existing data extraction methods often have problems such as missing historical data, slow data update speed, poor timeliness of data on whether to repair and the status of repair, and the objectivity, authenticity and accuracy of the previous data also need to be tested and verified; expert experience survey methods or survey and inquiry methods can only obtain general information, with poor accuracy, and the information obtained is somewhat subjective; field survey and measurement methods are time-consuming, require a lot of manpower and material resources, and are difficult to implement in some difficult-to-reach areas. For satellite remote sensing technology, the cost of acquiring image data (especially high spatial resolution images) is high; affected by image resolution, technical conditions, human factors, etc., the recognition accuracy varies greatly, which is easy to cause misjudgment; the existing survey methods only use single-phase image data, or use a few periods of image data for static comparison, compared with the time series remote sensing analysis method, it is easy to cause missed or misjudgment; the existing survey methods are mostly based on the image tone, shadow, shape, texture and relative position characteristics to interpret the historical damaged land patches, ignoring the judgment of factors such as the year of land damage, reclamation and reclamation adequacy.

[0035] In view of this, the embodiment of the present application provides a method for identifying historical damaged land. Through a remote sensing cloud computing platform, long-term remote sensing image data is obtained, and a continuous change detection and classification (CCDC) algorithm is used to obtain high-quality interannual change trajectories. The information such as the year of pixel damage, reclamation and reclamation sufficiency is integrated to construct a historical damaged land identification process to identify the historical damaged land. This method can be directly used as a technical means for identifying / investigating historical damaged land. For a certain area to be verified, a historical damaged land survey has been carried out in the area, but the historical data of the historical damaged land is missing, or the current status is unclear. On the one hand, this method can verify and update the existing survey results in real time. On the other hand, it can also supplement more information on the basis of the existing survey results, including the time of historical damage, the degree of damage and the degree of reclamation. For a certain historical damaged area, long-term indicator monitoring or comparison can also be carried out to obtain the ecological restoration status of the historical damaged land in real time.

[0036] For example, Figure 1 A method for identifying historical damaged land provided by an embodiment of the present application is shown. Figure 1 As shown, the method for identifying historical damaged land may include the following steps:

[0037] S11: Acquire relevant data of the target area to be measured, where the relevant data includes remote sensing image data of the target area.

[0038] In this embodiment, when confirming whether the land in a target area is historically damaged land, the relevant data of the historically damaged land in the target area can be obtained first. Specifically, when obtaining the remote sensing image data of the target area, all available Landsat TM / ETM data from the start year to the end year in the target area can be obtained in chronological order through relevant satellite data publishing platforms, such as the Google Earth Engine (GEE) platform. + / OLI / OLI-2 and Sentinel-2MSI surface reflectance image data, the processing level of Landsat images is Collection 2Level-2, and the processing level of Sentinel-2 images is Level2A. The image data needs to contain data of each band of blue light, green light, red light, near infrared, shortwave infrared 1 and shortwave infrared 2.

[0039] In some possible embodiments, the acquired remote sensing image data is preprocessed, which may also include time and cloud amount screening, cloud and shadow removal, image cropping and image mosaicking, etc.

[0040] In some possible embodiments, some auxiliary information may also be obtained, such as information related to land reclamation and information related to the obligor of land reclamation. The disappearance of the obligor of land reclamation generally refers to the situation in which, during the land reclamation process, the individual or unit that was originally obliged to carry out land reclamation is unable to continue to perform the reclamation obligation due to death, bankruptcy, relocation, etc. Therefore, it is also possible to count the production and construction units or personal information that caused land damage in the target area to be investigated, the current production and operation situation, and the ownership information of the relevant land.

[0041] S12: Based on the acquired relevant data, determine the change trajectory of the remote sensing index of each pixel in the remote sensing image data.

[0042] In this embodiment, the remote sensing index may include normalized difference vegetation index (NDVI), normalized degradation fraction index (NDFI), and modified normalized difference water index (MNDWI). The remote sensing indexes are obtained based on the acquired remote sensing image data. After obtaining each remote sensing index, each remote sensing index may be fitted, and based on the fitting result, the change trajectory of the remote sensing index is determined.

[0043] Among them, NDVI is an important indicator reflecting the surface vegetation coverage and its production vitality. It is one of the most widely used vegetation indices and has the advantages of high sensitivity in vegetation detection. In the embodiment of this application, it plays a role in distinguishing vegetation from non-vegetation. NDVI is calculated according to the following formula:

[0044] NDVI=(R NIR -R RED ) / (R NIR +R RED )

[0045] In the formula, R NIR Characterizes the reflectance value of the near-infrared band, R RED Characterizes the reflectance value of the red light band.

[0046] NDFI is used in the present embodiment to distinguish forest from non-forest. It is calculated according to the following formula:

[0047]

[0048] In the formula, GV represents the green vegetation component, which is used to indicate the proportion of vegetation that can photosynthesize, Shade represents the shadow component, which is used to indicate the canopy shadow component of green vegetation, NPV represents the non-photosynthetic vegetation component, which is used to indicate the proportion of vegetation that cannot photosynthesize or aging vegetation, and Soil represents the soil component. The NDFI index ranges from -1 to 1. The NDFI value of lush forests is close to 1. When the forest is disturbed (deforestation, coal mining, etc.), the NDFI value decreases. When the forest disappears completely, the NDFI value is close to -1. The four components of GV, NPV, Soil, and Shade are obtained by decomposing the reflectance data of each pixel. The specific matrix coefficients are shown in Table 1 below.

[0049] Table 1

[0050]

[0051] MNDWI is highly sensitive to soil, buildings, and dry lakes, and reduces noise, and can accurately extract water information. It can be calculated according to the following formula:

[0052]

[0053] In the formula, R GREEN Characterizes the reflectance value of the green light band, R SWIR1 Characterizes the reflectance value of the shortwave infrared 1 band.

[0054] For example, Figure 2 Schematic diagram of a data processing result provided by an embodiment of the present application. Figure 2 As shown in Figure 1, remote sensing images of the target area at different dates and years are obtained. Figure 2 As shown in (a) in the figure, a pixel (i.e. Figure 2 The black pixel in the image is selected to obtain the NDVI, NDFI, and MNDWI values ​​of the pixel. The obtained values ​​are integrated into one coordinate axis, with orange representing NDVI, green representing NDFI, and blue representing MNDWI.

[0055] In some possible embodiments, fitting each remote sensing index includes: fitting the harmonic function of the remote sensing index pixel by pixel.

[0056] In this embodiment, the continuous change detection and classification (CCDC) algorithm can be used to fit the harmonic function of the remote sensing index to the time series remote sensing image data pixel by pixel, and the fitted harmonic function is used as the expression formula of the time series trajectory curve of the corresponding pixel. The fitting formula of the harmonic function of the remote sensing index is as follows:

[0057]

[0058] In the formula, i represents the i-th band of the image data, t represents the Julian date, p represents the predicted value, and a 0,i Characterization intercept, s i Characterizes the interannual variation coefficient, a 1,i , b 1,i Characterizes the coefficient of variation within a year, a 2,i , b 2,i Characterizes the annual double peak variation coefficient, a 3,i , b 3,i It represents the coefficient of variation of the three peaks within a year, and T represents the number of days in each year.

[0059] For example, please continue to refer to Figure 2 ,like Figure 2 As shown in (b), after obtaining the NDVI, NDFI, and MNDWI values ​​of the pixels, NDVI, NDFI, and MNDWI are used as remote sensing indicators, and the NDVI, NDFI, and MNDWI values ​​are fitted respectively to obtain the fitted remote sensing index trajectories, which are the orange line, green line, and blue line respectively.

[0060] In some possible embodiments, determining the change trajectory of the remote sensing index based on the fitting result includes: based on the fitted time series trajectory curve, taking the maximum values ​​of each remote sensing index in different years as data points of the change trajectory.

[0061] In this embodiment, after fitting each remote sensing index, the fitting results of each remote sensing index are obtained as a time series trajectory curve. The maximum value of each remote sensing index on the time series trajectory is extracted year by year. The extracted maximum values ​​are connected as the interannual variation trajectory of the remote sensing index. Taking the remote sensing index NDFI as an example, for a certain pixel in the remote sensing image of the target area in the i-th year, the relevant data of all dates in the i-th year are sequentially substituted into the harmonic function of the NDFI time series trajectory curve after the pixel is fitted, and the NDFI index fitting values ​​corresponding to each date are counted, and the maximum value is taken as the NDFI value corresponding to the pixel in the i-th year.

[0062] For example, please continue to refer to Figure 2 ,like Figure 2As shown in (c) in the figure, by connecting the maximum value points of the remote sensing index as the data points of the change trajectory, the interannual change trajectory of each remote sensing indicator (remote sensing index) can be obtained.

[0063] S13: Based on the change trajectory of the remote sensing index, determine the change trajectory of the land use type represented by each pixel.

[0064] In this embodiment, after obtaining the change trajectory of the remote sensing index, the land use type of each data point on the change trajectory of the remote sensing index is determined. By connecting the land use type of each data point, the change trajectory of the land use type of a certain pixel in the target area can be obtained. Land use types may include forests, other vegetation, non-vegetation, and water areas. Among them, other vegetation may include pastures, cultivated land, etc. Non-vegetation may include bare land, industrial and mining land, urban residential construction land, transportation land, etc. The image data is analyzed year by year to determine the threshold Threshold for distinguishing pixels as vegetation or non-vegetation. NDVI , the threshold value of forest or non-forest NDFI , water body or non-water body threshold Threshold MNDWI When obtaining the threshold, the image data can be analyzed year by year, and the NDVI value corresponding to the confidence interval of 5% is taken as the threshold of the vegetation and non-vegetation areas in the corresponding year, and then the obtained annual thresholds are averaged to determine the threshold Threshold NDVI Select an appropriate number of forest and water sample points, extract and analyze the NDFI and MNDWI values ​​corresponding to the sample points each year, and calculate the average value as the threshold NDFI , Threshold MNDWI For pixel i in year j, its NDVI value is recorded as NDVI ij , and record its NDFI value as NDFI ij , and record its MNDWI value as MNDWI ij According to NDVI ij NDFI ij , MNDWI ij And various thresholds, the land use type of pixel i in the jth year can be determined.

[0065] Specifically, when NDVI ij ≤Threshold NDVI And NDFI ij ≥Threshold MNDWI When , the land use type of pixel i in year j is water area.

[0066] When NDVI ij ≤ThresholdNDVI And NDFI ij ≤Threshold MNDWI When , the land use type of pixel i in year j is non-vegetation.

[0067] When NDVI ij ≥Threshold NDVI And NDFI ij ≤Threshold NDF When , the land use type of pixel i in year j is other vegetation.

[0068] When NDVI ij ≥Threshold NDVI And NDFI ij ≥Threshold NDFI When , the land use type of pixel i in year j is forest.

[0069] For example, please continue to refer to Figure 2 ,like Figure 2 As shown in (d) in the figure, after obtaining the land use types of the pixels in each year, the land use types are recorded and connected on the coordinate axis, and the land use types are marked with different colors.

[0070] S14: Based on the change trajectory of land use type, determine whether the land represented by each pixel is damaged.

[0071] In this embodiment, after determining the change trajectory of land use type, it can be determined whether each pixel has been damaged. Among them, "forest to other vegetation / non-vegetation / water area", "other vegetation to non-vegetation / water area", "initial state is non-vegetation / water area", "continuous non-vegetation" and "continuous water area" are defined as damage change marks. When any of the above marks exists in the land use type change trajectory of a pixel, it means that the land represented by the corresponding pixel may have been damaged at a certain moment in history, otherwise it means that the land represented by the pixel has not been damaged.

[0072] For example, please continue to refer to Figure 2 ,like Figure 2 As shown in (d) in the figure, the land use type of the land represented by the pixel changes from orange (other vegetation) to red (non-vegetation), indicating that the land represented by the pixel has been damaged.

[0073] In some possible embodiments, when land damage occurs, information on the year in which the land damage occurred may also be recorded.

[0074] Specifically, for the year when land damage occurs, that is, the year when the pixel has a damage change mark, if the pixel has multiple damage change marks during the monitoring period, only the earliest change mark year is selected as the damage year, that is, the first damage year.

[0075] S15: In case of land damage, determine whether the land should be reclaimed.

[0076] In this embodiment, the transformations of "water area transformed into forest / other vegetation", "non-vegetation transformed into forest / other vegetation" and "other vegetation transformed into forest" can be defined as reclamation transformation marks. When any of the above marks exists in the land use type change trajectory of the pixel, and the reclamation transformation mark occurs after the damage transformation mark, it means that the corresponding damaged pixel may have been reclaimed at a certain moment in history, otherwise it means that the damaged pixel has not been reclaimed.

[0077] S16: In the case of land reclamation, determine whether the land reclamation is sufficient.

[0078] In this embodiment, whether land reclamation is sufficient refers to whether the land productivity level after land reclamation has been reached, or the highest productivity level of similar surrounding land. If it has been reached, it indicates that the land reclamation is sufficient. Specifically, in the initial and final stages of the pixel, the land use type is different. When the final land use type of the pixel is better than the initial state, it means that the productivity level of the original land (i.e., the land before the damage) has been reached, or the highest productivity level of similar surrounding land has been reached. The initial stage refers to the period during the entire judgment period (such as Figure 2 In the period from 1986 to 2022 (shown in (d) in the figure), when the land use type changes for the first time, the period from the start time to the first change is called the initial stage. Figure 2 The final stage refers to the duration of the last change in land use type during the entire judgment period, as shown in (d) from 1986 to 2008. Figure 2 2018 to 2022 as shown in (d).

[0079] In some possible embodiments, if the land corresponding to the pixel has the same land use type in the initial and final stages, the following discriminant formula is executed. If the formula is established, it means that the original land productivity level or the highest productivity level of similar surrounding land has been reached.

[0080] Index Start,Max ×95%≤Index End,Mean

[0081] In the formula, Index Start,Max The maximum value of the remote sensing index fitting value during the initial land use state, Index End,MeanThe average value of the remote sensing index fitting value during the period of characterizing the final land use status. It is worth noting that when the initial and final land use types are forests, the Index should select NDFI; when the initial and final land use types are other vegetation, the Index should select NDVI.

[0082] S17: Verify the identified historical damaged land and determine the final identification results, which include the land reclamation situation. The land reclamation situation includes whether the land has been reclaimed and whether the land reclamation is sufficient.

[0083] In this embodiment, the identification of historical damaged land at this time is obtained based on remote sensing data. In order to confirm the identification result, the identification result can be verified. Among them, the verified results may include the following types: Type I indicates that the damage occurred in 1988 or before, and no reclamation was implemented after the damage (including continuous non-vegetated areas); Type II indicates that the damage occurred in 1988 or before, and reclamation was implemented after the damage, but the original (or surrounding similar) land (highest) productivity level was not reached in the end; Type III indicates that the damage occurred in 1989 or later, the land reclamation obligor was lost or the land reclamation responsible entity was the government, and no reclamation was implemented after the damage; Type IV indicates that the damage occurred in 1989 or later, the land reclamation obligor was lost or the land reclamation responsible entity was the government, and reclamation was implemented after the damage, but the original (or surrounding similar) land (highest) productivity level was not reached in the end.

[0084] Specifically, the data of points of interest (POI) on the map can be obtained first. POI data can be obtained through various map software. Field surveys are conducted based on POI data to determine the spatial topological relationship between the target area and POI data. If the target area contains POI data related to urban residential construction land, healthy water bodies or roads, the corresponding target area does not belong to historical damaged land.

[0085] Secondly, based on data such as the production and construction units or personal information that caused the land damage, current production and operation conditions, ownership information of the relevant land, and on-site investigations, if the individual or legal representative of the unit who was originally obliged to reclaim the land is unable to continue to perform the reclamation obligations due to death, bankruptcy, relocation, etc., then the corresponding area will be classified as historically damaged land.

[0086] Finally, the temperature and precipitation data of the target area, historical mine identification data, etc. can also be obtained. When obtaining the historical mine identification data, the relevant information of the previous historical mine identification results can be obtained and counted according to the actual situation of the county-level administrative unit where the area to be investigated is located. The platform for obtaining the identification results of the previous historical mines is the official website of the government of each county-level administrative unit. The statistical information must include the longitude coordinates of the center point of the map spot, the latitude coordinates of the center point of the map spot and the map spot area. Other information such as the map spot number, degree of damage, and restoration direction can be selectively counted according to the survey needs. Temperature and precipitation data can be obtained from the local meteorological department or meteorological station in the target area, the National Earth System Science Data Center, the National Meteorological Information Center, etc. According to the temperature and precipitation data and field surveys, if the vegetation growth in the area is restricted due to natural factors such as long-term high temperature or scarce precipitation, and there is no land damage caused by human destruction or damage left over from history, the corresponding area does not belong to the historical damaged land.

[0087] The above is an introduction to a method for identifying historical damaged land provided by an embodiment of the present application. By analyzing each pixel in the acquired remote sensing image of the target area, the land use type of the land represented by the pixel is determined. According to the change curve of the land use type, it can be obtained whether the land corresponding to the pixel is damaged. This method selects factors such as the time of land damage under long-term conditions, whether reclamation is implemented, and the adequacy of reclamation as the judgment indicators of historical damaged land, so as to achieve objective and accurate identification of historical damaged land and avoid misjudgment or omissions that may be caused by static time point data. The current spatial distribution status of historical damaged land can be quickly and accurately obtained, the bottom line can be found out, and the basic information such as the distribution location, damaged area, whether to repair, and repair status of historical damaged land can be found out, so as to form real and reliable basic data of historical damaged land, which provides basic data reference for subsequent reclamation suitability evaluation and reclamation benefit analysis. This method can also assist in completing the verification of historical mines and realize long-term tracking monitoring of mine ecological restoration. The corresponding monitoring results can serve as the basis and basis for green mine assessment and selection of historical mine ecological restoration demonstration projects.

[0088] It is understandable that the size of the sequence number of each step in the above-mentioned embodiments does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, in some possible implementations, the steps in the above-mentioned embodiments can be selectively executed according to actual conditions, and can be partially executed or fully executed, which is not limited here. All or part of any feature of any embodiment of the present application can be freely and arbitrarily combined without contradiction. The combined technical solution is also within the scope of the present application.

[0089] In order to verify the feasibility of this plan, a certain township was taken as an example to implement the plan. Figure 3 The identification area of ​​historical damaged land and the year of damage are shown. Figure 4 The results of the verification of the identification of historical damaged land are shown. Figure 3 and Figure 4 , obtain the LandsatTM / ETM data of the township from 1986 to 2022 through the GEE platform + / OLI surface reflectance image data, the processing level is Collection 2Level-2. The original remote sensing image data is preprocessed, including time and cloud coverage screening, cloud removal, image cropping and mosaicking, etc. Among them, the image screening time is from January to December, and there is no limit on the image cloud coverage. The cloud removal is based on the SimpleCloudScore algorithm of the GEE platform, and the image cropping adopts the Quality Mosaic algorithm. Calculate typical remote sensing indexes, and calculate the NDFI, NDVI and MNDWI indexes for each image through the GEE platform. Based on the GEE platform, fit the time series model to obtain high-quality interannual change trajectories. Analyze each pixel and determine that NDVI = 0.5 is the threshold for vegetation / non-vegetation pixels, NDFI = 0.8 is the threshold for forest / non-forest pixels, and MNDWI = 0 is the threshold for water / non-water pixels, thereby determining information such as the year of damage, whether reclamation has been carried out, and whether reclamation is sufficient. Therefore, it can be obtained Figure 3 The historical damaged land identification areas and damage years are shown.

[0090] After preliminary verification of POI data, we obtained Figure 4 The identification results of historical damaged land. The identification results include 4 types. Type I represents the damage occurred in 1988 or before, and no reclamation was implemented after the damage (including continuous non-vegetated areas); Type II represents the damage occurred in 1988 or before, and reclamation was implemented after the damage, but the final productivity level of the original (or similar surrounding) land (highest) was not reached; Type III represents the damage occurred in 1989 or later, the land reclamation obligor was lost or the land reclamation responsible entity was the government, and no reclamation was implemented after the damage; Type IV represents the damage occurred in 1989 or later, the land reclamation obligor was lost or the land reclamation responsible entity was the government, and reclamation was implemented after the damage, but the final productivity level of the original (or similar surrounding) land (highest) was not reached. There are 82 historical mine map center points identified in the target area. The specific locations are as follows: Figure 4As shown. After comparison, 70 center points of the spots were effectively identified. According to the current preliminary verification results, Types I and II can be directly identified as historical damaged land, while Types III and IV need to be verified again with auxiliary information (production and construction units or personal information that caused the land damage, current production and operation conditions, ownership information of the relevant land, and field investigation conditions) before they can be identified as historical damaged land.

[0091] After verification of POI data and auxiliary information, accurate identification results of historical damaged land are obtained. Areas that have not been recognized by the government but have been identified as historical damaged land through the above-mentioned technical scheme can be directly supplemented. At the same time, information such as the year of damage and reclamation status (whether reclamation has been implemented and whether the land reclamation is sufficient) of the recognized areas can be supplemented. Areas that have been recognized by the government but have been identified as non-historical damaged land through the above-mentioned technical scheme can be directly verified and updated.

[0092] Based on the method in the above embodiment, the embodiment of the present application also provides a device for identifying historical damaged land.

[0093] For example, Figure 5 A device for identifying damaged land left over from history is shown. Figure 5 As shown, the historical damaged land identification device 500 may include: an acquisition module 501 and a processing module 502.

[0094] Wherein, the acquisition module 501 is used to determine relevant data of the target area to be identified, and the relevant data includes remote sensing image data of the target area;

[0095] A processing module 502 is used to determine a change trajectory of a remote sensing index of each pixel in the remote sensing image data based on the remote sensing image data;

[0096] The processing module 502 is further used to determine the change trajectory of the land use type represented by each pixel based on the change trajectory of the remote sensing index;

[0097] The processing module 502 is further used to determine whether the land represented by each pixel is damaged based on the change trajectory of the land use type;

[0098] The processing module 502 is also used to determine whether the land should be reclaimed when the land is damaged;

[0099] The processing module 502 is also used to verify the identified damaged land and determine the final identification result, which includes the land reclamation situation.

[0100] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method, which will not be repeated here.

[0101] The present application also provides a computing device 600, which may be an FPGA disposed on the aforementioned edge device. Figure 6 As shown, computing device 600 includes: bus 602, processor 604, memory 606 and communication interface 608. Processor 604, memory 606 and communication interface 608 communicate through bus 602. Computing device 600 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in computing device 600.

[0102] The bus 602 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The bus 604 is represented by only one line, but does not mean that there is only one bus or one type of bus. The bus 604 may include a path for transmitting information between various components of the computing device 600 (eg, the memory 606, the processor 604, and the communication interface 608).

[0103] The processor 604 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0104] The memory 606 may include a volatile memory, such as a random access memory (RAM). The processor 604 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0105] The memory 606 stores executable program codes, and the processor 604 executes the executable program codes to respectively implement the functions of the acquisition module 501 and the processing module 502, thereby implementing all or part of the steps of the method in the above embodiment. That is, the memory 606 stores instructions for executing all or part of the steps in the method in the above embodiment.

[0106] Alternatively, the memory 606 stores executable codes, and the processor 604 executes the executable codes to respectively implement the functions of the above-mentioned historical damaged land identification device 500, thereby implementing all or part of the steps in the above-mentioned embodiment method. That is, the memory 606 stores instructions for executing all or part of the steps in the above-mentioned embodiment method.

[0107] The communication interface 608 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 600 and other devices or communication networks.

[0108] Based on the methods in the above embodiments, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a processor, the processor executes the methods in the above embodiments.

[0109] Based on the methods in the above embodiments, an embodiment of the present application provides a computer program product. When the computer program product runs on a processor, the processor executes the methods in the above embodiments.

[0110] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0111] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0112] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0113] It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

Claims

1. A method for identifying historical damaged land, characterized in that: The method comprises: Acquire relevant data of the target area to be identified, wherein the relevant data includes remote sensing image data of the target area; Based on the remote sensing image data, determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data; the remote sensing index includes a normalized vegetation index, a normalized degradation fraction index, and a normalized difference water index; wherein the normalized vegetation index is used to distinguish vegetation from non-vegetation, the normalized degradation fraction index is used to distinguish forests from non-forests, and the normalized difference water index is used to distinguish water bodies from non-water bodies; Based on the change trajectory of the remote sensing index, determining the change trajectory of the land use type represented by each pixel; the land use type includes forest, other vegetation, non-vegetation, and water area; Based on the change trajectory of the land use type, determining whether the land represented by each pixel is damaged; In the case of land damage, determine whether the land is reclaimed; in the case of land reclamation, determine whether the land reclamation is sufficient; where the land represented by the pixel has the same land use type at the initial and final stages, execute the following discriminant formula, and if the formula is established, it indicates that the reclamation is sufficient Index Start,Max ×95%≤Index End,Mean In the formula, Index Start,Max The maximum value of the remote sensing index fitting value during the initial land use state, Index End,Mean The average value of the remote sensing index fitting value during the period representing the final land use status; when the initial and final land use types are forests, Index selects NDFI; when the initial and final land use types are other vegetation, Index selects NDVI; The identified damaged land is checked to determine the final identification result, which includes whether the land has been reclaimed and whether the land reclamation is sufficient; the final identification result includes Type I, Type II, Type III, and Type IV; among which, Type I indicates that the damage occurred in 1988 or before, and no reclamation was implemented after the damage; Type II indicates that the damage occurred in 1988 or before, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved; Type III indicates that the damage occurred in 1989 or later, the person with the obligation to reclaim the land is lost or the responsible entity for land reclamation is the government, and no reclamation was implemented after the damage; Type IV indicates that the damage occurred in 1989 or later, the person with the obligation to reclaim the land is lost or the responsible entity for land reclamation is the government, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved.

2. The method according to claim 1, characterized in that Determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data includes: A harmonic function of a remote sensing index is fitted to each pixel in the remote sensing image data, and the fitted harmonic function is used as an expression formula of a time series trajectory curve of each pixel; the fitting remote sensing index is performed according to the following formula: In the formula, i represents the i-th band of the image data, t represents the Julian date, p represents the predicted value, and a 0,i Characterization intercept, s i Characterizes the interannual variation coefficient, a 1,i 、b 1,i Characterizes the coefficient of variation within a year, a 2,i 、b 2,i Characterizes the annual double peak variation coefficient, a 3,i 、b 3,i It represents the coefficient of variation of the three peaks within a year, and T represents the number of days in each year.

3. The method according to claim 2, characterized in that Determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data includes: The maximum values ​​of each remote sensing index in different years are taken as the data points of the change trajectory.

4. The method according to claim 1, characterized in that: The method further includes: when the land is damaged, recording time information of when the land is damaged.

5. The method according to claim 1, characterized in that Whether the land reclamation is sufficient includes sufficient land reclamation and insufficient land reclamation. Sufficient land reclamation includes that after reclamation, the land reaches the productivity level of the land before damage, and / or is higher than the highest productivity level of the same type of land around the land.

6. The method according to claim 1, characterized in that The method also includes: obtaining map point of interest data and auxiliary information, and verifying historical damaged land based on the map point of interest data and the auxiliary information; wherein the auxiliary information includes the production and construction units or personal information that caused the land damage in the target area, the current production and operation status of the production and construction units, and the ownership information of the damaged land.

7. A device for identifying damaged land left over from history, characterized in that: The device comprises: An acquisition module, used for acquiring relevant data of the target area to be identified, wherein the relevant data includes remote sensing image data of the target area; A processing module, for determining the change trajectory of the remote sensing index of each pixel in the remote sensing image data based on the remote sensing image data; the remote sensing index includes a normalized vegetation index, a normalized degradation fraction index, and a normalized difference water index; wherein the normalized vegetation index is used to distinguish vegetation from non-vegetation, the normalized degradation fraction index is used to distinguish forest from non-forest, and the normalized difference water index is used to distinguish water from non-water; The processing module is further used to determine the change trajectory of the land use type of the land represented by each pixel based on the change trajectory of the remote sensing index; the land use type includes forest, other vegetation, non-vegetation, and water area; The processing module is further used to determine whether the land represented by each pixel is damaged based on the change trajectory of the land use type; The processing module is also used to determine whether the land is reclaimed when the land is damaged, and to determine whether the land reclamation is sufficient when the land is reclaimed. In the case where the land represented by the pixel has the same land use type at the initial and final stages, the following discriminant formula is executed. If the formula is established, it indicates that the reclamation is sufficient. Index Start,Max ×95%≤Index End,Mean In the formula, Index Start,Max The maximum value of the remote sensing index fitting value during the initial land use state, Index End,Mean The average value of the remote sensing index fitting value during the period representing the final land use status; when the initial and final land use types are forests, Index selects NDFI; when the initial and final land use types are other vegetation, Index selects NDVI; The processing module is also used to verify the identified damaged land and determine the final identification result, which includes whether the land has been reclaimed and whether the land reclamation is sufficient; the final identification result includes Type I, Type II, Type III, and Type IV; wherein Type I indicates that the damage occurred in 1988 or before, and no reclamation was implemented after the damage; Type II indicates that the damage occurred in 1988 or before, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved; Type III indicates that the damage occurred in 1989 or later, the person who has the obligation to reclaim the land is lost or the responsible entity for the land reclamation is the government, and no reclamation was implemented after the damage; Type IV indicates that the damage occurred in 1989 or later, the person who has the obligation to reclaim the land is lost or the responsible entity for the land reclamation is the government, and reclamation was implemented after the damage, but the land productivity level before the damage was ultimately not achieved.

Images