Remote sensing evaluation method and device for yield reduction degree of farmland in high groundwater level mining subsidence area

Abstract

The application relates to the technical field of land utilization, in particular to a remote sensing evaluation method and device for the yield reduction degree of cultivated land in a high-water-level coal mining subsidence area, wherein the method comprises the following steps: based on effective remote sensing images, constructing an annual water frequency index time sequence to identify water body pixels, combining a preset algorithm to identify coal mining subsidence water bodies by taking patches as objects, evaluating the yield of cultivated land based on NDVI cumulative values TI-NDVI in a growth period, constructing a spatial gradient model by buffering outward from the center of the coal mining subsidence water bodies, using an exponential function to fit the model and analyze the spatial gradient change rule of TI-NDVI, identifying the boundary of the yield reduction degree based on the spatial gradient change rule, and calculating the grain yield reduction based on the yield reduction degree. Therefore, the problem that in the related art, due to the fact that the grain yield data in a small range and unmanned aerial vehicle remote sensing are mainly used, it is difficult to evaluate the surface subsidence caused by coal mining and the influence on farmland and grain in a regional range is solved.

Description

Technical Field

[0001] This application relates to the field of land use technology, and in particular to a remote sensing assessment method and device for assessing the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels. Background Technology

[0002] Land subsidence and flooding caused by underground mining not only directly inundate large areas of farmland but also affect crop growth in even larger areas, disrupting the synergistic and balancing effects of the ecosystem. The land subsidence and flooding problems caused by underground mining are more insidious than the changes in surface cover caused by open-pit mining, and their negative impacts on the ecological environment and agricultural production are more profound.

[0003] However, research on the impact of mining on agricultural productivity is relatively limited in related technologies. Existing studies are mostly based on yield data and UAV remote sensing within small areas, making it difficult to conduct comprehensive assessments on a large scale. The surface subsidence caused by coal mining and its further impact on farmland and food production have not yet been fully quantified at the regional level and urgently need improvement. Summary of the Invention

[0004] This application provides a remote sensing assessment method and apparatus for assessing the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels. This addresses the problem in related technologies that rely heavily on grain yield data and UAV remote sensing within small areas, making it difficult to assess surface subsidence caused by coal mining and its impact on farmland and grain within a regional scope.

[0005] The first aspect of this application provides a remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, comprising the following steps: based on effective remote sensing images, constructing an annual water frequency index time series to identify water body pixels, and combining a preset algorithm to identify coal mining subsidence water bodies by taking patches as objects; assessing farmland yield based on the cumulative NDVI value (TI-NDVI) during the growing season; constructing a spatial gradient model with the coal mining subsidence water body as the center and buffering outwards, and using an exponential function to fit the model to analyze the spatial gradient change law of TI-NDVI; based on the spatial gradient change law, identifying the boundary of the degree of yield reduction, and calculating the reduction in grain yield according to the degree of yield reduction.

[0006] Through the above technical solution, the embodiments of this application can construct an annual water frequency index time series using effective remote sensing images, identify coal mining subsidence water bodies using a certain algorithm, and then assess arable land yield based on the cumulative NDVI value during the growing season. This method, by constructing a spatial gradient model and using an exponential function to analyze the variation pattern of TI-NDVI, can efficiently and accurately identify the boundaries of yield reduction and quantify grain yield reduction. The advantages of this technical solution lie in its efficiency and accuracy, not only reducing the workload of traditional field surveying methods but also providing a scientific basis for land management and reclamation, thus contributing to sustainable development.

[0007] Optionally, in one embodiment of this application, the step of constructing an annual water frequency index time series to identify water body pixels based on effective remote sensing images, and combining a preset algorithm to identify coal mining subsidence water bodies by taking patches as objects, includes: calculating a vegetation index using the effective remote sensing images to identify water body pixels within the region; calculating the annual water frequency based on the proportion of water body observations in the effective remote sensing images, and constructing an annual water frequency index time series to identify water body pixels based on the water body pixels; and constructing a random forest model to identify the coal mining subsidence water bodies based on the temporal and morphological attributes of the coal mining subsidence water bodies.

[0008] Through the above technical solutions, the embodiments of this application can comprehensively analyze water body pixels by utilizing vegetation indices and water body observation ratios, thereby achieving accurate identification of water bodies. Furthermore, the random forest model constructed based on temporal and morphological features improves the accuracy and reliability of identification, providing a scientific basis for subsequent land management and reclamation, and helping to mitigate the negative impact of coal mining on agricultural production.

[0009] Optionally, in one embodiment of this application, the assessment of farmland yield based on the cumulative NDVI value (TI-NDVI) during the growing season includes: calculating the NDVI index based on the effective remote sensing image, and performing time interpolation on the missing values ​​of the image to perform time weighting on the two adjacent images based on pixel units, thereby obtaining the NDVI time-series image of the target resolution within the study area; performing harmonic fitting on the NDVI time-series image, and selecting data for a specific time period as the NDVI time-series dataset to form the cumulative NDVI value (TI-NDVI) during the growing season of the study area, and assessing the farmland yield within the study area unit based on the TI-NDVI.

[0010] Through the above technical solution, the embodiments of this application can calculate the NDVI index using effective remote sensing images, and perform temporal interpolation and weighting processing on missing values ​​in the images to generate high-resolution NDVI time-series images. By filtering data for specific time periods through harmonic fitting, the cumulative NDVI value TI-NDVI during the growing season is formed, thereby accurately assessing the yield of cultivated land in the study area, improving the timeliness and accuracy of the data, effectively reflecting the crop growth status, and providing a scientific basis for agricultural production.

[0011] Optionally, in one embodiment of this application, the calculation formula for assessing arable land yield within the study area unit based on the TI-NDVI is as follows:

[0012] NDVI = (Band) NIR -Band red ) / (Band NIR +Bandred )

[0013] NDVI t =Acos(2πωt)+Bsin(2πωt)+C

[0014] Among them, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A is the cosine coefficient, B is the sine coefficient, C is the intercept coefficient, t is the time point, and ω is the frequency, set to 1.

[0015] Through the above technical solutions, embodiments of this application can provide quantitative analysis of vegetation growth status by utilizing surface reflectance data in the NIR and red bands. By fitting time-series harmonic models, seasonal variations in crop growth are captured, thereby improving the accuracy of yield prediction.

[0016] Optionally, in one embodiment of this application, the step of constructing a spatial gradient model by buffering outwards from the coal mining subsidence water body as the center, and using an exponential function fitting model to analyze the spatial gradient variation law of TI-NDVI, includes: based on the coal mining subsidence water body as the center, buffering outwards at a preset distance based on the water body boundary at a preset interval, and analyzing the law of crop impact caused by mining changing with distance based on the TI-NDVI estimation within each buffer ring.

[0017] Through the above technical solution, the embodiments of this application can effectively analyze the pattern of how the impact of mining activities on crops varies with distance by setting certain intervals outward from the coal mining subsidence water body as the center. This method not only improves the spatial analysis accuracy of the impact on crop yield reduction, but also quantifies crop yield loss at different distances.

[0018] Optionally, in one embodiment of this application, the step of identifying the boundary of the degree of yield reduction based on the spatial gradient change law and calculating the grain yield reduction according to the degree of yield reduction includes: using the spatial gradient model and the spatial gradient change law, determining the impact range of mining disturbance with the location of the preset slope as a threshold, thereby identifying the boundary of the degree of yield reduction; spatially overlaying the grain yield data of a preset year with the yield reduction data of subsidence water body to generate a dataset; and calculating the grain yield reduction based on the dataset according to the degree of change in yield per unit area within a preset time period.

[0019] Through the above technical solutions, the embodiments of this application can accurately determine the impact range of coal mining on farmland by establishing a spatial gradient model and its changing patterns, using a certain slope as a threshold, thereby effectively identifying the boundaries of the degree of yield reduction. Simultaneously, by spatially overlaying grain yield data with yield reduction data from subsidence water bodies, the generated dataset provides a scientific basis for assessing grain yield reduction.

[0020] The second aspect of this application provides a remote sensing assessment device for evaluating the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels. The device includes: an identification module for constructing an annual water frequency index time series to identify water body pixels based on effective remote sensing images, and using a preset algorithm to identify coal mining subsidence water bodies as objects based on patches; an assessment module for assessing farmland yield based on the cumulative NDVI value (TI-NDVI) during the growing season; a construction module for constructing a spatial gradient model with the coal mining subsidence water body as the center and buffering outwards, and using an exponential function to fit the model and analyze the spatial gradient change law of TI-NDVI; and a calculation module for identifying the boundary of the degree of yield reduction based on the spatial gradient change law, and calculating the reduction in grain yield based on the degree of yield reduction.

[0021] Through the above technical solution, the embodiments of this application can construct an annual water frequency index time series using effective remote sensing images, identify coal mining subsidence water bodies using a certain algorithm, and then assess arable land yield based on the cumulative NDVI value during the growing season. This method, by constructing a spatial gradient model and using an exponential function to analyze the variation pattern of TI-NDVI, can efficiently and accurately identify the boundaries of yield reduction and quantify grain yield reduction. The advantages of this technical solution lie in its efficiency and accuracy, not only reducing the workload of traditional field surveying methods but also providing a scientific basis for land management and reclamation, thus contributing to sustainable development.

[0022] Optionally, in one embodiment of this application, the identification module includes: a first identification unit, used to calculate a vegetation index using the effective remote sensing image to identify water body pixels within the region; a first calculation unit, used to calculate the annual water frequency based on the proportion of water body observations in the effective remote sensing image, and combine the water body pixels to construct an annual water frequency index time series to identify water body pixels; and a construction unit, used to construct a random forest model based on the temporal and morphological attributes of the coal mining subsidence water body to identify the coal mining subsidence water body.

[0023] Through the above technical solutions, the embodiments of this application can comprehensively analyze water body pixels by utilizing vegetation indices and water body observation ratios, thereby achieving accurate identification of water bodies. Furthermore, the random forest model constructed based on temporal and morphological features improves the accuracy and reliability of identification, providing a scientific basis for subsequent land management and reclamation, and helping to mitigate the negative impact of coal mining on agricultural production.

[0024] Optionally, in one embodiment of this application, the evaluation module includes: a second calculation unit, configured to calculate the NDVI index based on the effective remote sensing image, and perform time interpolation on the missing values ​​of the image to perform time weighting on the two adjacent images based on pixel units, thereby obtaining the NDVI time-series image of the target resolution within the study area; and an evaluation unit, configured to perform harmonic fitting on the NDVI time-series image, select data for a specific time period as the NDVI time-series dataset, to form the NDVI cumulative value TI-NDVI during the growing season of the study area, and evaluate the cultivated land yield within the study area unit based on the TI-NDVI.

[0025] Through the above technical solution, the embodiments of this application can calculate the NDVI index using effective remote sensing images, and perform temporal interpolation and weighting processing on missing values ​​in the images to generate high-resolution NDVI time-series images. By filtering data for specific time periods through harmonic fitting, the cumulative NDVI value TI-NDVI during the growing season is formed, thereby accurately assessing the yield of cultivated land in the study area, improving the timeliness and accuracy of the data, effectively reflecting the crop growth status, and providing a scientific basis for agricultural production.

[0026] Optionally, in one embodiment of this application, the calculation formula for assessing arable land yield within the study area unit based on the TI-NDVI is as follows:

[0027] NDVI = (Band) NIR -Band red ) / (Band NIR +Band red )

[0028] NDVI t =Acos(2πωt)+Bsin(2πωt)+C

[0029] Among them, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A is the cosine coefficient, B is the sine coefficient, C is the intercept coefficient, t is the time point, and ω is the frequency, set to 1.

[0030] Through the above technical solutions, embodiments of this application can provide quantitative analysis of vegetation growth status by utilizing surface reflectance data in the NIR and red bands. By fitting time-series harmonic models, seasonal variations in crop growth are captured, thereby improving the accuracy of yield prediction.

[0031] Optionally, in one embodiment of this application, the construction module includes: taking the coal mining subsidence water body as the center, buffering a preset distance outward at preset intervals based on the water body boundary, and estimating and analyzing the law of crop impact caused by mining with distance based on TI-NDVI estimation within each buffer ring.

[0032] Through the above technical solution, the embodiments of this application can effectively analyze the pattern of how the impact of mining activities on crops varies with distance by setting certain intervals outward from the coal mining subsidence water body as the center. This method not only improves the spatial analysis accuracy of the impact on crop yield reduction, but also quantifies crop yield loss at different distances.

[0033] Optionally, in one embodiment of this application, the calculation module includes: a second identification unit, used to determine the impact range of mining disturbance by using the spatial gradient model and the spatial gradient change law, with the location of the preset slope as a threshold, thereby identifying the boundary of the degree of production reduction; and a third calculation unit, used to spatially overlay the grain yield data of a preset year with the production reduction data of subsidence water bodies to generate a dataset, and based on the dataset, calculate the grain production reduction according to the degree of change in yield per unit area within a preset time period.

[0034] Through the above technical solutions, the embodiments of this application can accurately determine the impact range of coal mining on farmland by establishing a spatial gradient model and its changing patterns, using a certain slope as a threshold, thereby effectively identifying the boundaries of the degree of yield reduction. Simultaneously, by spatially overlaying grain yield data with yield reduction data from subsidence water bodies, the generated dataset provides a scientific basis for assessing grain yield reduction.

[0035] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels as described in the above embodiments.

[0036] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the remote sensing assessment method for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels, as described above.

[0037] The fifth aspect of this application provides a computer program product, including a computer program, which, when executed, is used to implement the remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, as described above.

[0038] This application's embodiments can utilize effective remote sensing images to construct relevant index time series, analyze water body pixels and vegetation indices, accurately identify water bodies and assess arable land yield, improve accuracy and reliability by constructing models such as spatial gradient models and random forest models, and reduce the workload of traditional field surveying; quantitatively analyze vegetation growth status using band data and capture seasonal changes in crop growth by fitting time series harmonic models to improve yield prediction accuracy; construct a buffer ring centered on coal mining subsidence water bodies to analyze the distance variation law of mining activities' impact on crops, establish a spatial gradient model with slope as a threshold to accurately determine the impact range and yield reduction boundary, and provide a scientific basis for assessing grain yield reduction through data overlay datasets, providing strong support for land management, reclamation and agricultural production, and promoting sustainable development.

[0039] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0040] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0041] Figure 1 This is a flowchart of a remote sensing assessment method for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels, provided according to an embodiment of this application.

[0042] Figure 2 This is a schematic diagram of the technical framework for subsidence water boundary identification and grain loss assessment according to a specific embodiment of this application;

[0043] Figure 3 This is a schematic diagram of the crop loss gradient boundary according to a specific embodiment of this application;

[0044] Figure 4 This is a schematic diagram of the structure of a remote sensing assessment device for assessing the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, provided in accordance with an embodiment of this application.

[0045] Figure 5 This is a structural example diagram of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0046] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0047] The following describes a remote sensing assessment method and apparatus for evaluating the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, based on embodiments of this application, with reference to the accompanying drawings. Addressing the problem mentioned in the background art that many related technologies rely on small-scale grain yield data and UAV remote sensing, making it difficult to assess the impact of coal mining-induced surface subsidence and its effects on farmland and grain within a regional scope, this application provides a remote sensing assessment method for evaluating the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels. This method constructs an annual water frequency index time series using effective remote sensing images, identifies coal mining subsidence water bodies using a specific algorithm, and then assesses farmland yield based on the cumulative NDVI value during the growing season. By constructing a spatial gradient model and using an exponential function to analyze the variation pattern of TI-NDVI, this method can efficiently and accurately identify the boundaries of yield reduction and quantify grain yield reduction. The advantages of this technical solution lie in its efficiency and accuracy, not only reducing the workload of traditional field surveying methods but also providing a scientific basis for land management and reclamation, thus contributing to sustainable development. This solves the problem in related technologies that, due to their reliance on small-scale grain yield data and UAV remote sensing, make it difficult to assess land subsidence caused by coal mining and its impact on farmland and crops within a regional scope.

[0048] Specifically, Figure 1 This is a flowchart illustrating a remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, provided in an embodiment of this application.

[0049] like Figure 1 As shown, the remote sensing assessment method for the degree of farmland yield reduction in the coal mining subsidence area with high groundwater level includes the following steps:

[0050] In step S101, based on the effective remote sensing images, an annual water frequency index time series is constructed to identify water body pixels, and a preset algorithm is used to identify coal mining subsidence water bodies by taking patches as objects.

[0051] As we can understand, the annual water frequency index is an indicator used to measure the frequency of water bodies appearing in a given area. It is calculated by analyzing years of remote sensing data to determine the frequency of water bodies appearing at each pixel over those years. For example, if a pixel has been identified as a water body in 6 out of the past 10 years, then its annual water frequency index is 0.6. Arranging these pixel annual water frequency indices in chronological order creates the annual water frequency index time series.

[0052] Optionally, in one embodiment of this application, based on effective remote sensing images, an annual water frequency index time series is constructed to identify water body pixels, and a preset algorithm is used to identify coal mining subsidence water bodies by taking patches as objects. This includes: calculating vegetation indices using effective remote sensing images to identify water body pixels within the region; calculating the annual water frequency based on the proportion of water body observations in the effective remote sensing images, and constructing an annual water frequency index time series to identify water body pixels based on the water body pixels; and constructing a random forest model based on the temporal and morphological attributes of coal mining subsidence water bodies to identify coal mining subsidence water bodies.

[0053] Specifically, using effective Landsat remote sensing imagery data, MNDIWI (Modified Normalized Difference Water Index), EVI (Enhanced Vegetation Index), and NDVI (Normalized Difference Vegetation Index) were calculated to identify water body pixels within the study area. MNDIWI effectively distinguishes water bodies from other land cover types. By calculating reflectance in different bands, MNDIWI improves the identifiability of water bodies; EVI, an indicator assessing vegetation cover and growth status, better reflects vegetation growth, especially in areas with high vegetation cover; NDVI assesses vegetation growth and cover levels, and by comparing reflectance in the near-infrared and red bands, NDVI effectively reflects the health status of vegetation.

[0054] Furthermore, by statistically analyzing water pixels in the imagery, the observed proportion of water bodies in each year is calculated to reflect the water changes in the study area. Based on the annual water observation proportions, a time-series annual water frequency trajectory is constructed to demonstrate the trend of water changes within a specific time frame. After obtaining the water frequency trajectory, the temporal and morphological attributes of the subsided water bodies are further analyzed. These attributes may include, but are not limited to, information such as the area, shape, and distribution of the water bodies. Based on these attributes, a random forest model is constructed to identify mining subsidence water accumulation patches. The random forest model is a powerful machine learning algorithm capable of handling high-dimensional data and improving the accuracy of identification through the ensemble of multiple decision trees.

[0055] This application's embodiments can utilize effective remote sensing image data, combined with multiple vegetation indices (such as MNDIWI, EVI, and NDVI), to comprehensively analyze the frequency of water body occurrence and vegetation status within a region, thereby improving the accuracy of water body identification. By using a random forest model to conduct in-depth analysis of the temporal attributes and morphological characteristics of subsided water bodies, mining subsidence water accumulation patches can be effectively identified, improving identification efficiency.

[0056] In step S102, cultivated land yield is assessed based on the cumulative NDVI value TI-NDVI (Time Normalized Difference Vegetation Index) during the growing season.

[0057] Understandably, TI-NDVI is the cumulative value of NDVI over a specific growth period, used to assess crop growth status and potential yield. By accumulating NDVI values ​​at different points in the growing season, a more comprehensive reflection of crop growth throughout the entire growth cycle can be obtained.

[0058] Optionally, in one embodiment of this application, based on effective remote sensing images, an annual water frequency index time series is constructed to identify water body pixels, and combined with a preset algorithm, coal mining subsidence water bodies are identified by taking patches as objects. This includes: calculating the NDVI index based on effective remote sensing images, and performing time interpolation on the missing values ​​of the images to perform time weighting on the two adjacent images based on pixel units, thereby obtaining the NDVI time series image of the target resolution within the study area; performing harmonic fitting on the NDVI time series image, and selecting data of a specific time period as the NDVI time series dataset to form the NDVI cumulative value TI-NDVI during the growth period of the study area, and evaluating the arable land yield within the study area unit based on TI-NDVI.

[0059] In the actual implementation process, based on the ESA-sentinel-2 (10m resolution) data source, cloud removal preprocessing was performed, the NDVI index was calculated, time interpolation was performed on the image gap values, and time weighting was performed on the two adjacent images based on the pixel unit, thereby obtaining 10m resolution NDVI time-series images of the study area.

[0060] Furthermore, the cumulative NDVI value during the growing season (TI-NDVI) was used as an indicator to predict crop yield during the growing season. Summer crops were selected as the main cultivation period. Based on crop phenological characteristics, a harmonic model was used to fit the NDVI time-series datasets for 60 days before sowing and 180 days after sowing, forming 10-minute data of the cumulative NDVI value during the growing season for the study area, which was used to estimate the cultivated land yield within the unit of this region. The specific formula is as follows:

[0061] NDVI = (Band) NIR -Band red ) / (Band NIR +Band red )

[0062] NDVI t =Acos(2πωt)+Bsin(2πωt)+C

[0063] Among them, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A is the cosine coefficient, B is the sine coefficient, C is the intercept coefficient, t is the time point, and ω is the frequency, set to 1.

[0064] This application's embodiments can assess farmland yield through TI-NDVI, accurately reflecting crop growth and yield by comprehensively considering the cumulative NDVI over the growing season. An annual water frequency index time series is constructed to identify water body pixels and coal mining subsidence water bodies. The NDVI index is calculated from effective remote sensing images, and missing values ​​are processed to obtain high-resolution imagery, improving the accuracy of water body and yield assessment. Cloud removal preprocessing is performed using specific data sources, and the data is fitted with a harmonic model based on crop phenological characteristics to obtain the cumulative NDVI value for the growing season for yield estimation. Fitting band data with a time series harmonic model enhances the accuracy of yield prediction.

[0065] In step S103, a spatial gradient model is constructed by buffering outwards from the coal mining subsidence water body as the center, and the spatial gradient variation law of TI-NDVI is analyzed by fitting the model with an exponential function.

[0066] Understandably, the spatial gradient model is a model used to describe how spatial phenomena change with distance. In the embodiments of this application, the spatial gradient model is used to analyze how the impact of coal mining subsidence water bodies on farmland (especially crop growth) changes with distance.

[0067] Optionally, in one embodiment of this application, a spatial gradient model is constructed by buffering outwards from the coal mining subsidence water body as the center, and the spatial gradient variation law of TI-NDVI is analyzed by fitting the model with an exponential function, including: buffering outwards from the coal mining subsidence water body at a preset distance based on the water body boundary, and analyzing the law of crop impact caused by mining with distance based on the TI-NDVI estimation in each buffer ring.

[0068] Specifically, based on the mining subsidence water body as the center, and buffering outwards for 1080m at 30m intervals along the water body boundary, the TI-NDVI estimation within each buffer ring is used to analyze the variation of crop impact caused by mining with distance. Spatial gradient analysis is performed based on TI-NDVI, and an exponential decay model is proposed to describe the spatial gradient pattern of crop growth caused by mining based on the trend analysis of sample points. The formula is as follows:

[0069] P(x) = -ae -bx +c

[0070] Where P(x) represents the crop growth at a distance x from the subsided water body, and a, b, and c are constants.

[0071] This application embodiment can construct a spatial gradient model through coal mining subsidence water bodies, buffering outwards by 1080 meters at 30-meter intervals from the water body boundary, and using exponential function fitting to analyze the spatial gradient change law of TI-NDVI. The exponential decay model and formula are used to quantify the crop growth at different distances from the water body, which can accurately present the spatial distribution of the impact of mining on farmland crop growth.

[0072] In step S104, based on the spatial gradient change pattern, the boundary of the degree of yield reduction is identified, and the grain yield reduction is calculated according to the degree of yield reduction.

[0073] Understandably, the degree of yield reduction refers to the extent to which crop yields are reduced due to a certain factor (such as coal mining). The boundary, on the other hand, refers to a spatially defined area, indicating the degree of impact of crop yield reduction within that area. For example, crop yield reduction may reach 75% within a specific distance, while there may be no yield reduction outside that distance.

[0074] Optionally, in one embodiment of this application, based on the spatial gradient change law, the boundary of the degree of yield reduction is identified, and the grain yield reduction is calculated according to the degree of yield reduction, including: using a spatial gradient model and the spatial gradient change law, using the location of the preset slope as a threshold to determine the impact range of mining disturbance, thereby identifying the boundary of the degree of yield reduction; spatially overlaying the grain yield data of a preset year with the yield reduction data of subsidence water body to generate a dataset, and based on the dataset, calculating the grain yield reduction according to the degree of change in yield per unit area within a preset time period.

[0075] In actual implementation, based on the spatial gradient model and the actual spatial gradient change pattern, the location with a slope of 0.001 is determined as the threshold to define the impact range of mining disturbance. Areas outside this distance are considered unaffected. The c-value in the fitted model is used as a control group for the normal growth of unaffected crops. Based on this control group as the standard value, the boundaries for determining the degree of impact—reduced yield by 75%, 25%, and 5%—are identified.

[0076] Furthermore, the annual grain yield reduction data is spatially overlaid with subsidence water body data to assess the year-on-year grain yield reduction. For example, using the 2010 FAO (Food and Agriculture Organization of the United Nations) Global Spatially-Disaggregated Crop Production Statistics Data as a basis, six major grain crops are selected, and the annual grain yield reduction is assessed by spatially overlaying the grain yield data with the subsidence water body data. Based on the 2010 crop production potential dataset, the annual grain yield per unit area production potential is adjusted according to the degree of change in China's grain yield per unit area (kg / hectare) from 2000 to 2020, as shown in the following formula:

[0077]

[0078] In the formula, PL y DLP represents the decrease in grain production in year y within the study area. i,y Let DA be the percentage of grain yield reduction for the i-th grid in the damaged area in year y. i,y Let i be the damaged area of ​​the i-th grid in year y. For the production data of the i-th grid in 2010, YF y y represents the adjustment factor for grain yield per unit area in different years compared to the output in 2010, where y is the number of years from 2000 to 2020.

[0079] The following detailed description of this application uses the Huang-Huai-Hai Plain, a region with high groundwater levels in eastern China, as a specific example.

[0080] The Huang-Huai-Hai Plain in eastern China, with its high groundwater levels, is a crucial base for coal and crop production. The region is rich in coal resources, covering an area of ​​1.71 × 10⁶ hectares, accounting for 24.96% of the total area. It also boasts vast farmlands with deep, fertile soil and abundant water resources, providing favorable agricultural conditions. The total farmland area in the study region is 5.13 × 10⁶ hectares, representing 74.89% of the region's area. In 2020, the grain output of the four provinces in the study region was 20,020.9 tons, accounting for 29.11% of the national output; raw coal output was 336.988 million tons, accounting for 8.64% of the national output. This region is a vital national base for grain and coal production.

[0081] The remote sensing assessment method for the degree of farmland yield reduction in this embodiment is as follows: Figure 2 As shown.

[0082] 1. Identify water bodies in coal mining subsidence areas

[0083] Specifically, based on all available images from Landsat 5, 7 and 8 satellite data of the study area from 1989 to 2021, an annual water frequency index time series was constructed to identify water body pixels, and a random forest algorithm was used to identify coal mining subsidence water bodies by patch.

[0084] Valid remote sensing images of the study area collected using satellite data can be used to calculate vegetation indices such as MNDWI, EVI, and NDVI. These indices can effectively distinguish between water bodies and non-water bodies, especially in high-water areas. Furthermore, the calculated vegetation indices are used to identify water body pixels within the study area. Specifically, MNDWI is commonly used for water body identification due to its high sensitivity to water bodies, effectively distinguishing them from other land features. Based on the proportion of water body observations in the valid remote sensing images, the annual water frequency is calculated. This process is pixel-scale; by analyzing images from different years, a time-series annual water frequency trajectory from 1989 to 2021 is constructed, helping to understand water body changes over different time periods.

[0085] Furthermore, based on the temporal and morphological characteristics of the subsidence water body, a random forest model is constructed to determine the coal mining subsidence water body area in the study area.

[0086] 2. Assess arable land yield

[0087] Specifically, using ESA Sentinel-2 data, a T-NDVI index was constructed based on the cumulative NDVI value during the growing season to assess farmland yield. Based on the ESA-sentinel-2 (10m resolution) data source, cloud removal preprocessing was performed, the NDVI index was calculated, time interpolation was performed on image gaps, and time weighting was applied to images from two adjacent periods based on pixel units, thereby obtaining 10m resolution NDVI time-series images of the study area.

[0088] Furthermore, the cumulative NDVI value during the growing season (i.e., TI-NDVI) was used as an indicator to predict crop yield during the growing season. Summer crops were selected as the main cultivation period. Based on crop phenological characteristics, a harmonic model was used to fit the NDVI time-series datasets for 60 days before sowing and 180 days after sowing, forming 10-minute data of the cumulative NDVI value during the growing season for the study area, which was used to estimate the cultivated land yield within the unit of this region. The specific formula is as follows:

[0089] NDVI = (Band) NIR -Band red ) / (Band NIR +Band red )

[0090] NDVI t =Acos(2πωt)+Bsin(2πωt)+C

[0091] In the formula, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A, B, and C are the cosine, sine, and intercept coefficients, t is the time point, and ω is the frequency, set to 1.

[0092] 3. Construct a spatial gradient model

[0093] A spatial gradient model was constructed by buffering outwards from the identified subsidence water body as the center, and the spatial gradient variation law of TI-NDVI was explored by fitting the model with an exponential function.

[0094] Specifically, based on the subsidence water body as the center, and buffering outwards at 30-meter intervals for 1080m based on the water body boundary, the law of crop impact caused by mining changes with distance is analyzed based on the TI-NDVI estimation within each buffer ring. A distance model of mining disturbance is constructed with the subsidence water body as the center and buffered outwards, and the differences in TI-NDVI distribution within each buffer ring are analyzed.

[0095] Based on the above analysis of spatial gradients, an exponential decay model is proposed to describe the spatial gradient pattern of crop growth caused by mining, based on the trend analysis of sample points. The formula is as follows:

[0096] P(x) = -ae -bx +c

[0097] In the formula, P(x) represents the crop growth at a distance x from the subsided water body, and a, b, and c are constants.

[0098] 4. Measuring the reduction in grain production

[0099] Specifically, by using a distance model of mining disturbances, the production reduction boundary is identified and the reduction in grain production is calculated based on the degree of production reduction.

[0100] Based on the fitted model of mining disturbance and the spatial gradient changes of the actual TI-NDVI scatter plot, the location with a slope of 0.001 was determined as the threshold to define the impact range of mining disturbance; areas outside this distance were considered unaffected. The c-value in the fitted model was used as a control group representing the normal growth of unaffected crops. Then, based on this control group as the standard value, the boundaries for determining the degree of impact—reduced yield by 75%, 25%, and 5%—were identified. Figure 3 As shown.

[0101] Based on the 2010 FAO Global Spatially-Disaggregated Crop Production Statistics Data, this study selected six major food crops and spatially overlaid them with data on yield reduction from subsidence water bodies to assess annual food yield reduction. Using the 2010 crop production potential dataset, the annual food yield potential was adjusted according to the degree of change in China's food yield per unit area (kg / hectare) from 2000 to 2020. The formula for the reduction in food yield in year y within the study area is as follows:

[0102]

[0103] In the formula, PL y DLP represents the decrease in grain production in year y within the study area. i,y Let DA be the percentage of grain yield reduction for the i-th grid in the damaged area in year y. i,y Let i be the area of ​​damage to the i-th grid in year y. For the production data of the i-th grid in 2010, YF y y represents the adjustment factor for grain yield per unit area in different years compared to the output in 2010, where y is the number of years from 2000 to 2020.

[0104] The remote sensing assessment method for farmland yield reduction in coal mining subsidence areas with high groundwater levels proposed in this application can construct an annual water frequency index time series from effective remote sensing images, identify coal mining subsidence water bodies using a certain algorithm, and then assess farmland yield based on the cumulative NDVI value during the growing season. This method, by constructing a spatial gradient model and using an exponential function to analyze the variation pattern of TI-NDVI, can efficiently and accurately identify the boundaries of yield reduction and quantify grain yield reduction. The advantages of this technical solution lie in its efficiency and accuracy, which not only reduces the workload of field surveying in traditional methods but also provides a scientific basis for land management and reclamation, contributing to sustainable development.

[0105] Next, referring to the accompanying drawings, a remote sensing assessment device for assessing the degree of farmland reduction in coal mining subsidence areas with high groundwater levels, according to an embodiment of this application, is described.

[0106] Figure 4 This is a block diagram of a remote sensing assessment device for assessing the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, according to an embodiment of this application.

[0107] like Figure 4 As shown, the remote sensing assessment device 10 for assessing the degree of farmland reduction in coal mining subsidence areas with high groundwater levels includes: an identification module 100, an assessment module 200, a construction module 300, and a calculation module 400.

[0108] Specifically, the identification module 100 is used to construct an annual water frequency index time series to identify water body pixels based on effective remote sensing images, and to identify coal mining subsidence water bodies by taking patches as objects in combination with a preset algorithm.

[0109] Assessment module 200 is used to assess farmland yield based on the cumulative NDVI value TI-NDVI during the growing season.

[0110] Module 300 is used to construct a spatial gradient model with the coal mining subsidence water body as the center and buffer outwards. The model is then fitted with an exponential function to analyze the spatial gradient variation law of TI-NDVI.

[0111] The calculation module 400 is used to identify the boundary of the degree of yield reduction based on the spatial gradient change pattern, and to calculate the reduction in grain production based on the degree of yield reduction.

[0112] Optionally, in one embodiment of this application, the identification module 100 includes: a first identification unit, a first calculation unit, and a construction unit.

[0113] The first identification unit is used to calculate the vegetation index using effective remote sensing images in order to identify water pixels within the area.

[0114] The first calculation unit is used to calculate the annual water frequency based on the proportion of water body observations in the effective remote sensing images, and combine the water body pixels to construct an annual water frequency index time series to identify water body pixels.

[0115] The building blocks are used to construct random forest models based on the temporal and morphological attributes of coal mining subsidence water bodies to identify coal mining subsidence water bodies.

[0116] Optionally, in one embodiment of this application, the evaluation module 200 includes a second calculation unit and an evaluation unit.

[0117] The second calculation unit is used to calculate the NDVI index based on the effective remote sensing image and perform time interpolation on the missing values ​​of the image to perform time weighting on the two adjacent images based on the pixel unit, thereby obtaining the NDVI time series image of the target resolution in the study area.

[0118] The evaluation unit is used to perform harmonic fitting on NDVI time-series images, select data from specific time periods as NDVI time-series datasets, and form the cumulative NDVI value TI-NDVI during the growing season of the study area. Based on TI-NDVI, the yield of cultivated land within the study area unit is evaluated.

[0119] Optionally, in one embodiment of this application, the formula for calculating arable land yield within a study area unit based on TI-NDVI assessment is as follows:

[0120] NDVI = (Band)NIR -Band red ) / (Band NIR +Band red )

[0121] NDVI t =Acos(2πωt)+Bsin(2πωt)+C

[0122] Among them, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A is the cosine coefficient, B is the sine coefficient, C is the intercept coefficient, t is the time point, and ω is the frequency, set to 1.

[0123] Optionally, in one embodiment of this application, the construction module 300 includes: based on the coal mining subsidence water body as the center, buffering a preset distance outward at preset intervals based on the water body boundary, and estimating and analyzing the law of crop impact caused by mining with distance based on the TI-NDVI estimation within each buffer ring.

[0124] Optionally, in one embodiment of this application, the measurement module 400 includes: a second identification unit and a third calculation unit.

[0125] The second identification unit is used to determine the impact range of mining disturbance by using the spatial gradient model and the spatial gradient change law, with the location of the preset slope as the threshold, thereby identifying the boundary of the degree of production reduction.

[0126] The third calculation unit is used to spatially overlay the grain yield data of a preset year with the yield reduction data of subsidence water bodies to generate a dataset. Based on the dataset, the grain yield reduction is calculated according to the degree of change in yield per unit area within a preset time period.

[0127] It should be noted that the explanation of the aforementioned remote sensing assessment method embodiment for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels also applies to the remote sensing assessment device for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels in this embodiment, and will not be repeated here.

[0128] The remote sensing assessment device for assessing the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, as proposed in this application, can construct an annual water frequency index time series from effective remote sensing images, identify coal mining subsidence water bodies using a certain algorithm, and then assess farmland yield based on the cumulative NDVI value during the growing season. This method, by constructing a spatial gradient model and using an exponential function to analyze the variation pattern of TI-NDVI, can efficiently and accurately identify the boundaries of yield reduction and quantify grain yield reduction. The advantages of this technical solution lie in its efficiency and accuracy; it not only reduces the workload of field surveying in traditional methods but also provides a scientific basis for land management and reclamation, contributing to sustainable development.

[0129] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0130] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0131] When processor 502 executes the program, it implements the remote sensing assessment method for the degree of farmland reduction in coal mining subsidence areas with high water levels provided in the above embodiments.

[0132] Furthermore, electronic devices also include:

[0133] Communication interface 503 is used for communication between memory 501 and processor 502.

[0134] The memory 501 is used to store computer programs that can run on the processor 502.

[0135] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0136] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0137] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0138] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0139] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the remote sensing assessment method for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels, as described above.

[0140] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, as described above.

[0141] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0142] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0143] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0144] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0145] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0146] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0147] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0148] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, characterized in that, Includes the following steps: Based on effective remote sensing images, an annual water frequency index time series is constructed to identify water body pixels, and a preset algorithm is used to identify coal mining subsidence water bodies by taking patches as objects. Assess arable land yield based on the cumulative NDVI value (TI-NDVI) during the growing season; A spatial gradient model was constructed with the coal mining subsidence water body as the center and buffered outwards. The spatial gradient variation law of TI-NDVI was analyzed by using an exponential function fitting model. Based on the spatial gradient change pattern, the boundary of the degree of yield reduction is identified, and the grain yield reduction is calculated according to the degree of yield reduction.

2. The method according to claim 1, characterized in that, The process of constructing an annual water frequency index time series for identifying water body pixels based on effective remote sensing images, and combining this with a preset algorithm to identify coal mining subsidence water bodies by patch type, includes: The vegetation index is calculated using the effective remote sensing images to identify water pixels within the area; The annual water frequency is calculated based on the proportion of water body observations in the effective remote sensing images, and combined with the water body pixels, an annual water frequency index time series is constructed to identify water body pixels. Based on the temporal and morphological attributes of the coal mining subsidence water bodies, a random forest model is constructed to identify the coal mining subsidence water bodies.

3. The method according to claim 1, characterized in that, The assessment of arable land yield based on the cumulative NDVI value (TI-NDVI) during the growing season includes: Based on the effective remote sensing images, the NDVI index is calculated, and the missing values ​​of the images are interpolated over time to perform time weighting on the two adjacent images based on the pixel unit, thereby obtaining the NDVI time series image of the target resolution within the study area. Harmonic fitting is performed on the NDVI time-series images, and data from specific time periods are selected as NDVI time-series datasets to form the cumulative NDVI value TI-NDVI during the growing season of the study area. Based on the TI-NDVI, the arable land yield within the study area unit is evaluated.

4. The method according to claim 1 or 3, characterized in that, The formula for calculating arable land yield within the TI-NDVI-based assessment study area unit is as follows: NDVI=(Band NIR -Band red ) / (Band NIR +Band red ) NDVI t =Acos(2πωt)+Bsin(2πωt)+C Among them, Band NIR For surface reflection in the NIR band, Band red For surface reflection in the red band, NDVI t Here are the fitted NDVI values ​​for the time series harmonic model, where A is the cosine coefficient, B is the sine coefficient, C is the intercept coefficient, t is the time point, and ω is the frequency, set to 1.

5. The method according to claim 1, characterized in that, The process involves constructing a spatial gradient model centered on the coal mining subsidence water body and buffering outwards. An exponential function fitting model is then used to analyze the spatial gradient variation of TI-NDVI, including: Centered on the coal mining subsidence water body, and buffering outwards at preset intervals based on the water body boundary, the pattern of crop impact caused by mining with distance is analyzed based on the TI-NDVI estimation within each buffer ring.

6. The method according to claim 5, characterized in that, The process of identifying the boundary of the degree of yield reduction based on the spatial gradient change pattern, and calculating the grain yield reduction based on the degree of yield reduction, includes: By using the spatial gradient model and the spatial gradient change law, the influence range of mining disturbance is determined with the location of the preset slope as a threshold, thereby identifying the boundary of the degree of production reduction; A dataset is generated by spatially overlaying grain yield data for a preset year with yield reduction data from subsided water bodies. Based on the dataset, the grain yield reduction is calculated according to the degree of change in yield per unit area within a preset time period.

7. A remote sensing assessment device for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, characterized in that, include: The identification module is used to construct an annual water frequency index time series to identify water body pixels based on effective remote sensing images, and to identify coal mining subsidence water bodies by taking patches as objects in combination with a preset algorithm. The assessment module is used to assess farmland yield based on the cumulative NDVI value (TI-NDVI) during the growing season; The module is used to construct a spatial gradient model with the coal mining subsidence water body as the center and buffer outwards, and to use an exponential function to fit the model to analyze the spatial gradient variation law of TI-NDVI. The calculation module is used to identify the boundary of the degree of yield reduction based on the spatial gradient change pattern, and to calculate the reduction in grain production based on the degree of yield reduction.

8. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the remote sensing assessment method for the degree of farmland reduction in coal mining subsidence areas with high groundwater levels as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement a remote sensing assessment method for the degree of farmland yield reduction in coal mining subsidence areas with high groundwater levels, as described in any one of claims 1-6.

Images