Layered progressive estimation method for crop harvesting area for large area

Abstract

The invention provides a large-area-oriented crop harvest area layered progressive estimation method, which comprises the following steps of: calculating planting areas in different seasons by utilizing seasonal cultivated land and intensity data in a national scale; performing crop type division on planting areas in different seasons according to phenological characteristics to obtain annual crop planting area spatial distribution data; on the agricultural ecological partition scale, based on the gridding harvesting area data of the reference year, combining with the interannual change characteristics of the planting area, and constructing a space distribution model; according to the model, national scale crop harvest area statistical data of the target year is distributed to each agro-ecological partition; and in a pixel scale, through a weight adjustment model, distributing the total harvest area of crops in the agro-ecological partition to each grid unit. The defect that spatial heterogeneity is neglected in a traditional fixed proportion method can be overcome, deep fusion and multi-scale collaborative estimation of multi-source data are achieved, and the space-time continuity and accuracy of large-area crop harvesting area estimation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural remote sensing monitoring, and particularly relates to a hierarchical progressive estimation method for crop harvested area in a large area. Background Art

[0002] The crop harvested area is the basic data for agricultural production assessment. It itself contains rich agricultural production information such as multiple cropping index and rotation pattern, and is an important indicator for evaluating the regional agricultural planting structure and land use intensity. At present, the existing methods mainly adopt the fixed ratio method, that is, based on the statistical data of the reference year and the grid harvested area data, the estimation is carried out through a simple proportional allocation method. This method assumes that the change of the planting structure within the region is consistent, ignores the spatial heterogeneity of the planting conditions between different grids, and cannot accurately reflect the dynamic change characteristics of the farmland use intensity. Summary of the Invention

[0003] The present invention provides a hierarchical progressive estimation method for crop harvested area in a large area to solve the defect that the traditional fixed ratio method in the prior art ignores the spatial heterogeneity. The present invention fully considers the seasonal change of crop growth and the spatial heterogeneity of the planting structure, and adopts a hierarchical progressive estimation strategy to ensure the accuracy and reliability of the estimation result. The technical solution proposed by the present invention is as follows:

[0004] In the first aspect, the present invention provides a hierarchical progressive estimation method for crop harvested area in a large area, including:

[0005] Obtaining the grid harvested area data of the reference year, the seasonal cultivated land use intensity data of the target year, and the national-scale crop harvested area statistical data;

[0006] At the national scale, calculating the planting area in different seasons by using the seasonal cultivated land use intensity data, and classifying the planting area in different seasons according to the phenological characteristics to obtain the spatial distribution data of the annual crop planting area;

[0007] At the agricultural ecological zoning scale, based on the grid harvested area data of the reference year, combining the inter-annual change characteristics of the planting area, constructing a spatial allocation model; wherein, the inter-annual change characteristics of the planting area are characterized by the spatial distribution data of the annual crop planting area of the target year and the reference year;

[0008] According to the spatial allocation model, allocating the national-scale crop harvested area statistical data of the target year to each agricultural ecological zone to obtain the crop harvested area at the agricultural ecological zoning scale;

[0009] At the pixel scale, through a pre-constructed weight adjustment model, the total harvested area of crops within the agricultural ecological zoning is allocated to each grid cell to obtain the harvested area of crops at the grid scale.

[0010] Optionally, the crop type division of the planting areas in different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planting area includes:

[0011] Obtain the phenological values of crops in different seasons, and determine the set of crop types in each season according to the phenological values of crops in different seasons;

[0012] Use a weight allocation method to divide the planting areas in different seasons to obtain the planting areas of each crop type in the set of crop types;

[0013] For each crop type, accumulate the planting areas of this crop type in each season to obtain the spatial distribution data of the annual crop planting area.

[0014] Optionally, at the agricultural ecological zoning scale, based on the grid-harvested area data of the reference year, combined with the inter-annual change characteristics of the planting area, construct a spatial allocation model, including:

[0015] At the agricultural ecological zoning scale, construct an initial harvested area allocation model based on the grid-harvested area data of the reference year;

[0016] According to the spatial distribution data of the annual crop planting area of the target year and the reference year, respectively determine the change rate of the planting area within the agricultural ecological zoning and the change rate of the planting area at the national scale;

[0017] According to the change rate of the planting area within the agricultural ecological zoning and the change rate of the planting area at the national scale, update the initial harvested area allocation model to obtain the spatial allocation model.

[0018] Optionally, the spatial allocation model is:

[0019]

[0020] where: w j,k,c is the harvested area proportion of crop j in agricultural ecological zoning k of country c in the target year, represents the initial harvested area proportion of crop j in agricultural ecological zoning k of country c, represents the planting area of crop j in grid m within agricultural ecological zoning k in the target year, represents the planting area of crop j in grid m within agricultural ecological zoning k in the reference year, Represents the planted area of crop j in agro - ecological zone n within country c in the target year. Represents the planted area of crop j in agro - ecological zone n within country c in the reference year. j, k, and c respectively represent the numbers of the crop, agro - ecological zone, and country, m represents the number of all grids within agro - ecological zone k, and n represents the number of all agro - ecological zones within country c.

[0021] Optionally, according to the spatial allocation model, allocating the national - scale crop harvest area statistics data of the target year to each agro - ecological zone to obtain the crop harvest area at the agro - ecological zone scale, including:

[0022] Determining the harvest area ratio of the crop in the agro - ecological zone in the target year according to the spatial allocation model;

[0023] Allocating the national - scale crop harvest area statistics data according to the harvest area ratio of the crop in the agro - ecological zone in the target year to obtain the crop harvest area at the agro - ecological zone scale.

[0024] Optionally, the weight adjustment model is constructed in the following manner:

[0025] Determining the initial spatial weight of each grid within the agro - ecological zone based on the gridded harvest area data of the reference year through the following formula:

[0026]

[0027] Where: Represents the initial spatial weight of crop j in grid i within agro - ecological zone k in the reference year. Represents the harvest area of crop j in grid i within agro - ecological zone k in the reference year. Represents the harvest area of crop j in grid m within agro - ecological zone k in the reference year. i, j, and k respectively represent the numbers of the grid, crop, and agro - ecological zone, and m represents the number of all grids within agro - ecological zone k;

[0028] Considering the change in planted area for weight update to obtain the weight adjustment model as follows:

[0029]

[0030] Where, Represents the spatial weight of crop j in grid i within agro - ecological zone k in the target year, r i,j,k Represents the planting area change rate of a single grid, r j,k Represents the planting area change rate of a single agro - ecological zone; Where:

[0031]

[0032]

[0033] Among them, represents the planting area of crop j in grid i within agro - ecological zone k in the target year, represents the planting area of crop j in grid i within agro - ecological zone k in the reference year, represents the planting area of crop j in grid m within agro - ecological zone k in the target year, represents the planting area of crop j in grid m within agro - ecological zone k in the reference year.

[0034] In a second aspect, the present invention also provides a hierarchical progressive estimation device for crop harvesting area for a large region, including the following modules:

[0035] A data acquisition module, configured to acquire the gridded harvesting area data of the reference year, as well as the seasonal cultivated land use intensity data and the national - scale crop harvesting area statistical data of the target year,

[0036] An area calculation module, configured to calculate the planting areas in different seasons at the national scale using the seasonal cultivated land use intensity data, and classify the planting areas in different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planting areas;

[0037] A model construction module, configured to construct a spatial allocation model at the agro - ecological zone scale based on the gridded harvesting area data of the reference year and in combination with the inter - annual change characteristics of the planting area; among them, the inter - annual change characteristics of the planting area are characterized by the spatial distribution data of the annual crop planting areas of the target year and the reference year;

[0038] A first allocation module, configured to allocate the national - scale crop harvesting area statistical data of the target year to each agro - ecological zone according to the spatial allocation model to obtain the crop harvesting area at the agro - ecological zone scale;

[0039] A second allocation module, configured to allocate the total harvesting area of the crops within the agro - ecological zone to each grid cell at the pixel scale through a pre - constructed weight adjustment model to obtain the crop harvesting area at the grid scale.

[0040] In a third aspect, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, it implements the hierarchical progressive estimation method for crop harvesting area for a large region as described in the first aspect above.

[0041] Fourthly, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the hierarchical progressive estimation method for crop harvesting area facing large regions as described in the first aspect above.

[0042] Fifthly, the present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the hierarchical progressive estimation method for crop harvesting area facing large regions as described in the first aspect above.

[0043] Based on the above technical solutions, the beneficial effects of the present invention compared with the prior art are as follows:

[0044] The hierarchical progressive estimation method for crop harvesting area facing large regions provided by the present invention, on the national scale, calculates the planting areas in different seasons by using seasonal cultivated land use intensity data, and divides the planting areas into crop types according to phenological characteristics, fully considering the seasonal changes in crop growth and the spatial heterogeneity of planting structures. Through the division of crop types, the planting areas of crops within different seasons are further refined, thus more accurately reflecting the seasonal changes in planting areas. On the scale of agricultural ecological zoning, based on the grid-based harvesting area data of the reference year and combined with the interannual change characteristics of planting areas, a spatial allocation model is constructed. This step further considers the differences in planting structures within different agricultural ecological zones. Through the seasonal cultivated land use intensity data, this method can capture the seasonal changes in farmland use intensity, thus more accurately reflecting the dynamic characteristics of farmland use intensity. In the construction of the spatial allocation model, the interannual change characteristics of planting areas are also considered, which helps to reflect the long-term change trend of farmland use intensity. This method adopts a hierarchical progressive estimation strategy, gradually refining the estimation results from the national scale to the agricultural ecological zoning scale and then to the pixel scale. At each scale, corresponding data and models are used for estimation to ensure the accuracy and reliability of the estimation results. This systematic hierarchical progressive estimation strategy helps to better understand and grasp the change rules of crop harvesting areas in large regions.

[0045] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0046] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given and described in detail in conjunction with the accompanying drawings. Description of the Drawings

[0047] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0048] Figure 1 It is one of the schematic flowcharts of the method for hierarchically progressive estimation of crop harvesting area for large regions provided by the present invention.

[0049] Figure 2 It is another schematic flowchart of the method for hierarchically progressive estimation of crop harvesting area for large regions provided by the present invention.

[0050] Figure 3 It is a schematic diagram of the spatial distribution of the maize harvesting area of the GAEZ dataset for the reference year (2015) provided by the present invention.

[0051] Figure 4 It is a schematic diagram of the CALF data for the four quarters of the target year (2020) provided by the present invention.

[0052] Figure 5 It is a schematic diagram of the spatial distribution data of the annual crop planting area in 2020 provided by the present invention.

[0053] Figure 6 It is a schematic diagram of the spatial distribution data of the annual harvesting area at the grid scale in 2020 provided by the present invention.

[0054] Figure 7 It is a schematic structural diagram of the device for hierarchically progressive estimation of crop harvesting area for large regions provided by the present invention.

[0055] Figure 8 It is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0056] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0057] The following will describe Figures 1-6 the method for hierarchically progressive estimation of crop harvesting area for large regions of the present invention.

[0058] The core principle of the method of the present invention is a hierarchical progressive estimation strategy based on multi-source data fusion. This method believes that the spatial distribution of crop harvested areas has significant regional heterogeneity, and its changes are affected by multiple factors such as natural conditions and agricultural management methods. Analyses show that there is a significant correlation between Cropped Arable Land Fraction (CALF) data and harvested area data. By introducing seasonal CALF data, the dynamic change characteristics of farmland use can be effectively captured; by dividing Agricultural Ecological Zones (AEZs), the spatial heterogeneity within the region can be better characterized; through multi-scale progressive estimation, the in-depth fusion of statistical data and spatial distribution data can be achieved, thereby improving the accuracy and reliability of the estimation results.

[0059] In the specific implementation process, this method adopts a "top-down" hierarchical progressive estimation strategy. First, at the national scale, by introducing crop phenological information, the annual scale is subdivided into seasonal scales, the CALF data is used to calculate the planting areas in different seasons, and the crop types are classified according to phenological characteristics, and finally the spatial distribution of the annual crop planting areas is obtained. Second, at the AEZ scale, based on the spatial distribution pattern of the reference year and combined with the inter-annual change characteristics of the planting areas, a spatial allocation model is established to decompose the national statistical data into each AEZ. Finally, at the pixel scale, considering the spatial heterogeneity within the AEZ, through constructing a weight adjustment model, the total harvested area of the AEZ is further allocated to each grid cell, and the reliability of the estimation results is ensured through data consistency verification.

[0060] Refer to Figure 2 As shown, the hierarchical progressive estimation method for crop harvested areas for large regions includes the following:

[0061] Step S110: Obtain the gridded harvested area data of the reference year, as well as the seasonal CALF data and the national-scale crop harvested area statistical data of the target year.

[0062] The present invention establishes a multi-source dataset integration framework, and the specific process is as follows:

[0063] First, collect agricultural statistical data, spatial distribution data, remote sensing monitoring data, crop phenological data, and auxiliary data. Specifically, agricultural statistical data refers to the crop harvested area statistical data of each country in the target year. The crop harvested area statistical data of the target year is collected from the agricultural departments, statistical bureaus, or international organizations of each country. For example, the national-scale crop harvested area statistical data provided by the Food and Agriculture Organization of the United Nations (FAO). Ensure the accuracy and integrity of the data, and process missing or abnormal data. Spatial distribution data refers to the gridded harvested area data of the reference year. The gridded harvested area data is provided by the Global Agro-Ecological Zones (GAEZ) dataset. Perform format conversion and coordinate unification on the data to ensure spatial consistency with other data sources. Remote sensing monitoring data refers to the Cropped Arable Land Fraction (CALF) data, which reflects the arable land use status of each grid in different seasons. These data are usually obtained through satellite remote sensing technology. Perform atmospheric correction, geometric correction, and radiometric correction on the remote sensing data to improve the accuracy of the data. Crop phenological data refers to the phenological information of the main crops in each country collected from agricultural research institutions, universities, or international organizations. Organize the phenological data, including information on key periods such as sowing, growth, maturity, and harvest. Auxiliary data refers to the Agricultural Ecological Zone (AEZ) data, which describes the agricultural ecological conditions in different regions. Classify and code the auxiliary data for correlation analysis with other data sources.

[0064] Preprocess the data obtained above, which includes: performing projection conversion and resampling on all raster data to ensure consistent spatial resolution. Perform data format standardization processing to establish a unified spatial reference system. And complete data quality inspection, including outlier identification and processing.

[0065] Then integrate all the collected data sources into a unified database. Ensure the consistency of data formats, encodings, and coordinate systems.

[0066] Obtain the gridded harvested area data of the reference year, as well as the seasonal cropped arable land fraction data and national-scale crop harvested area statistical data of the target year from the database. The above-mentioned gridded harvested area data of the reference year provides spatial distribution information of the crop harvested area. The above-mentioned seasonal cropped arable land fraction data of the target year reflects the arable land use situation in different seasons. The national-scale crop harvested area statistical data provides information on the total amount of crop harvested area nationwide.

[0067] Step S120: At the national scale, calculate the planting areas in different seasons using the seasonal cultivated land use intensity data, and classify the crop types of the planting areas in different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planting areas.

[0068] Use the seasonal cultivated land use intensity data to calculate the planting areas in different seasons. This helps to understand the growth conditions of crops and the land use situation in different seasons. Classify the crop types of the planting areas in different seasons according to the phenological characteristics of crops (such as growth cycle, key phenological periods, etc.). This can be achieved through methods such as remote sensing monitoring, crop models, or expert systems. Integrate the above information to obtain the spatial distribution data of the annual crop planting areas. These data reflect the spatial distribution and planting areas of crops across the country.

[0069] Step S130: At the agricultural ecological zoning scale, based on the gridded harvested area data of the reference year, combined with the inter-annual change characteristics of the planting area, construct a spatial allocation model; wherein, the inter-annual change characteristics of the planting area are characterized by the spatial distribution data of the annual crop planting areas of the target year and the reference year.

[0070] Based on the gridded harvested area data of the reference year, combined with the inter-annual change characteristics of the planting area (such as change rate, growth trend, fluctuation situation, etc.), construct a spatial allocation model. This model is used to simulate the distribution changes of the crop planting area within different agricultural ecological zones. The inter-annual change characteristics of the planting area can be characterized by comparing the spatial distribution data of the annual crop planting areas of the target year and the reference year.

[0071] Step S140: According to the spatial allocation model, allocate the national-scale crop harvested area statistics data of the target year to each agricultural ecological zone to obtain the crop harvested area at the agricultural ecological zoning scale.

[0072] Use the spatial allocation model to allocate the national-scale crop harvested area statistics data to each agricultural ecological zone. This helps to understand the crop harvested area and distribution situation within different agricultural ecological zones.

[0073] Step S150: At the pixel scale, allocate the total harvested area of crops within the agricultural ecological zone to each grid cell through a pre-constructed weight adjustment model to obtain the crop harvested area at the grid scale.

[0074] At the pixel scale, the total harvested area of crops within the agro-ecological zoning is allocated to each grid cell through a pre-constructed weight adjustment model. This model takes into account various factors such as the distribution of crops within the grid cell, land use types, topography, and so on. The weight adjustment model can be constructed and trained through methods such as remote sensing monitoring, GIS analysis, and machine learning. It can refine the allocation of the crop harvested area according to the characteristics of the grid cell and the growth environment of the crops. Finally, the crop harvested area data at the grid scale are obtained, and these data provide high-resolution distribution information of the crop harvested area in space.

[0075] Through the hierarchical progressive estimation method, the present invention can comprehensively consider multi-source data and multi-level information, reducing errors and uncertainties in the estimation process. This helps to improve the accuracy of crop harvested area estimation. This method combines various technical means such as remote sensing technology, GIS analysis, and machine learning, and can automatically and quickly estimate the crop harvested area. This enhances the efficiency and practicality of the estimation. By providing high-resolution crop harvested area data, this method can provide a scientific basis and decision-making support for agricultural policy formulation, agricultural resource management, and agricultural production planning. This method helps to understand the spatial distribution and area change of crop planting, providing strong support for the optimal allocation of agricultural resources, the refined management of agricultural production, and the sustainable development of agriculture.

[0076] The traditional fixed ratio method usually estimates the crop harvest area based on a certain preset ratio relationship. This method ignores the spatial heterogeneity, that is, the differences in crop growth and distribution under different regions and ecological conditions. In response to this defect, in the national scale, the present invention calculates the planting area in different seasons using seasonal arable land use intensity data, and classifies the planting area by crop type according to phenological characteristics. This step fully considers the seasonal changes in crop growth and the spatial heterogeneity of the planting structure. Through the classification of crop types, the planting area of crops within different seasons is further refined, thus more accurately reflecting the seasonal changes in the planting area. On the scale of agricultural ecological zoning, based on the gridded harvest area data of the reference year and combined with the interannual change characteristics of the planting area, a spatial allocation model is constructed. This step further considers the differences in the planting structure within different agricultural ecological zones. Through the seasonal arable land use intensity data, this method can capture the seasonal changes in farmland use intensity, thus more accurately reflecting the dynamic characteristics of farmland use intensity. In the construction of the spatial allocation model, the interannual change characteristics of the planting area are also considered, which helps to reflect the long-term change trend of farmland use intensity. This method clearly adopts a hierarchical progressive estimation strategy, from the national scale to the agricultural ecological zoning scale, and then to the pixel scale, gradually refining the estimation results. At each scale, corresponding data and models are used for estimation to ensure the accuracy and reliability of the estimation results. This systematic hierarchical progressive estimation strategy helps to better understand and grasp the change law of the crop harvest area in large regions.

[0077] In the data acquisition stage of the present invention, this method preprocesses and integrates multi-source data to ensure the quality and consistency of the data. For example, geometric correction, radiometric correction, etc. are performed on remote sensing monitoring data, and spatial interpolation, etc. are performed on ground survey data. During the estimation process, this method constructs multiple models, including a spatial allocation model, a weight adjustment model, etc. These models consider factors such as spatial heterogeneity at different scales, the characteristics and interrelationships of data from different sources, and improve the estimation accuracy by optimizing model parameters and structures. This method performs collaborative estimation at different scales. On the national scale, macro data is used for overall grasp; on the agricultural ecological zoning scale, regional characteristics are combined for refined estimation; on the pixel scale, fine-grained allocation is performed through high-resolution data. This multi-scale collaborative method helps to more accurately reflect the growth and distribution of crops.

[0078] This method combines historical data and current data, taking into account the inter-annual variation characteristics of the planting area, so as to maintain continuity in time. At the same time, the spatial data obtained through means such as remote sensing monitoring can also maintain continuity in space. Through methods such as hierarchical estimation, multi-source data fusion, and multi-scale collaboration, this method can more accurately reflect the growth and distribution of crops. In addition, this method also considers various factors such as the phenological characteristics of crops, land use types, topography, etc., further improving the accuracy of estimation.

[0079] The planting areas in different seasons mentioned above can be calculated in the following way:

[0080] CA i,t = CroplandArea i ×CALF i,t

[0081] Where: CA i,t represents the total planting area of grid i in season t, CroplandArea i represents the cropland area of grid i, and CALF i,t represents the cropland planting ratio of grid i in season t.

[0082] In an optional embodiment, the crop type division of the planting areas in different seasons according to the phenological characteristics in step S120 to obtain the spatial distribution data of the annual crop planting area includes:

[0083] S1201. Obtain the phenological values of the crop in different seasons, and determine the crop type set for each season according to the phenological values of the crop in different seasons;

[0084] Through means such as remote sensing monitoring, ground observation, meteorological data, or agricultural statistical materials, collect the phenological information of the crop every 10 days during the entire growth period from sowing to harvesting. These phenological information mainly include key growth indicators such as the growth stage of the crop (such as emergence stage, tillering stage, heading stage, maturity stage, etc.), plant height, coverage, etc. According to the growth habits of the crop and the local climate conditions, determine the length of the growth cycle from sowing to harvesting of the crop. There are differences in the length of the growth cycle of different crops. For example, rice is about 110 - 130 days, corn is about 90 - 120 days, wheat is about 200 - 240 days, etc.

[0085] Integrate the 10-day scale phenological information into the season scale. Summarize or average all the 10-day scale phenological information within each growth season to obtain a season scale phenological value. This can be achieved by calculating the average value, maximum value, minimum value, or median of all the 10-day scale phenological values within the season.

[0086] Define the classification criteria according to the growth characteristics and actual needs of crops. For example, the phenological value is divided into 0 or 1, where 0 represents the non-planting period and 1 represents the planting period. Compare the phenological value at the seasonal scale with the classification criteria. If the phenological value at the seasonal scale reaches or exceeds a certain threshold (such as the average value, median, etc.), then set the phenological value of that season to 1 (planting period). If the phenological value at the seasonal scale is lower than this threshold, then set the phenological value of that season to 0 (non-planting period). According to the above steps, generate a phenological value of 0 or 1 for each growing season.

[0087] Count the number of crops in the planting period within each season, and record how many different crops are growing within each season, so as to determine the set of crop types for each season.

[0088] S1202. Use a weight allocation method to divide the planting areas of different seasons to obtain the planting areas of each crop type in the set of crop types.

[0089] Based on the number of crops in the planting period within a season, use a weight allocation method to determine the planting areas of each crop type in different seasons. According to the number of crops in the planting period within each season, assign a weight to each crop. The weight can be determined based on historical data of crop quantity, planting area, market demand, or other relevant factors. Use the weight allocation method to calculate the planting area of each crop in each season. This can be achieved by multiplying the total planting area by the weight of each crop, ensuring that the allocation of the planting area is proportional to the number of crops in the planting period within the season.

[0090] S1203. For each crop type, accumulate the planting areas of this crop type in each season to obtain the spatial distribution data of the annual crop planting area.

[0091] For each crop type, accumulate the planting areas of this crop type in each season. The accumulated result is the annual planting area of this crop type. Perform spatial distribution processing on the annual planting areas of all crop types to obtain the spatial distribution data of the annual crop planting area. Specifically, perform spatial distribution processing on the annual planting areas of each crop type according to the geographical location to obtain the spatial distribution data of the annual crop planting area. The area data can be mapped onto the grid or vector layer of a geographic information system (GIS) for visual analysis and application.

[0092] The present invention can more accurately reflect the growth status and distribution characteristics of crops by dividing crop types based on phenological characteristics. Using a weight allocation method to divide the planting areas of different seasons can fully consider factors such as the growth habits of crops and climatic conditions, and improve the accuracy of the division.

[0093] Specifically, by collecting phenological information of crops through means such as remote sensing monitoring, ground observation, meteorological data, or agricultural statistical data every 10 days within a continuous time period (such as one year), the growth status and periodic changes of crops can be more accurately reflected. Integrating the phenological information at a 10-day scale into a seasonal scale makes the representation of crop planting information more macroscopic and easier to analyze. According to the classification criteria defined based on the growth characteristics and actual needs of crops, the crop types in each season can be more accurately judged, thus improving the accuracy of crop planting information.

[0094] Adopting a weight distribution method to divide the planting area in different seasons can fully consider factors such as the number of crops in the planting period and historical data of the planting area within each season, making the distribution of the planting area more reasonable and fair. This method avoids the subjectivity and randomness in traditional planting area distribution and improves the accuracy and scientific nature of the distribution. Summing up the planting area of each crop type in each season to obtain the annual crop planting area helps to understand the annual production situation and spatial distribution characteristics of crops. Performing spatial distribution processing on the annual crop planting area to obtain the spatial distribution data of the annual crop planting area can visually display the planting areas and distribution of crops, providing strong data support for agricultural decision-making.

[0095] In an optional embodiment, the constructing of the spatial allocation model based on the gridded harvested area data of the reference year at the scale of agricultural ecological zoning in the above step S130 includes:

[0096] S1301. At the scale of agricultural ecological zoning, construct an initial harvested area allocation model based on the gridded harvested area data of the reference year.

[0097] At the scale of agricultural ecological zoning, first construct an initial harvested area allocation model based on the gridded harvested area data of the reference year. This model describes the distribution of the harvested area of each grid cell for different crop types within the reference year.

[0098] S1302. According to the spatial distribution data of the annual crop planting area of the target year and the reference year, respectively determine the change rate of the planting area within the agricultural ecological zoning and the change rate of the planting area at the national scale.

[0099] Using the spatial distribution data of the annual crop planting area of the target year and the reference year, respectively calculate the change rate of the planting area within the agricultural ecological zoning and the change rate of the planting area at the national scale. The change rate of the planting area within the agricultural ecological zoning reflects the increase or decrease of the planting area of different crop types within a specific agricultural ecological zoning. The change rate of the planting area at the national scale provides the overall change trend of the crop planting area across the country.

[0100] S1303. Update the initial harvested area allocation model according to the change rate of the planted area within the agricultural ecological zone and the change rate of the planted area at the national scale to obtain the spatial allocation model.

[0101] Update the initial harvested area allocation model according to the calculated change rate of the planted area within the agricultural ecological zone and the change rate of the planted area at the national scale. This step aims to incorporate the inter-annual change characteristics of the planted area into the model, so as to more accurately reflect the crop harvested area of each grid cell in the target year. The updated model is the required spatial allocation model, which can more accurately estimate the crop harvested area in the target year at the scale of the agricultural ecological zone.

[0102] In the present invention, by incorporating the inter-annual change characteristics of the planted area into the spatial allocation model, this method can more accurately reflect the crop harvested area of each grid cell in the target year. This helps to reduce the estimation error caused by ignoring the inter-annual changes and improve the estimation accuracy of the crop harvested area. The initial harvested area allocation model is constructed based on the data of the reference year, while the updated spatial allocation model takes into account the change of the planted area in the target year. This dynamic update mechanism enables the model to adapt to the actual situation of different years and enhances the adaptability and flexibility of the model.

[0103] Specifically, calculate the initial weights of each agricultural ecological zone based on the gridded harvested area data of the reference year, and establish a calculation formula (i.e., the above initial harvested area allocation model):

[0104]

[0105] Where: represents the initial harvested area proportion of crop j in agricultural ecological zone k of country c, represents the harvested area of crop j in grid m within agricultural ecological zone k in the reference year, represents the harvested area of crop j in agricultural ecological zone n of country c in the reference year, ∑ m∈ k represents the summation of all grids within AEZk, ∑ n∈c represents the summation of all grids within country c.

[0106] Introduce the inter-annual change information of the planted area for weight correction, and the above spatial allocation model is obtained as:

[0107]

[0108] Where: w j,k,c is the harvested area proportion of crop j in agricultural ecological zone k of country c in the target year, Represents the initial harvested area proportion of crop j in agro - ecological zone k of country c. Represents the planted area of crop j in grid m within agro - ecological zone k in the target year. Represents the planted area of crop j in grid m within agro - ecological zone k in the reference year. Represents the planted area of crop j in agro - ecological zone n of country c in the target year. Represents the planted area of crop j in agro - ecological zone n of country c in the reference year. Here, j, k, and c represent the numbers of the crop, agro - ecological zone, and country respectively, m represents the number of all grids within agro - ecological zone k, and n represents the number of all agro - ecological zones within country c.

[0109] After obtaining the above w j,k,c Then, in combination with FAO statistical data, area allocation is carried out, and the calculation formula is as follows:

[0110]

[0111] Where: Is the total harvested area of crop j in agro - ecological zone k of country c in the target year. Is the national - scale crop harvested area statistical data provided by FAO in the target year.

[0112] In an optional embodiment, according to the spatial allocation model in step S140, allocating the national - scale crop harvested area statistical data of the target year to each agro - ecological zone to obtain the crop harvested area at the agro - ecological zone scale includes:

[0113] S1401. Determine the harvested area proportion of the crop in the agro - ecological zone in the target year according to the spatial allocation model.

[0114] According to the spatial allocation model, calculate the harvested area proportion of the crop in each agro - ecological zone. This proportion reflects the potential ability of the crop to grow and be harvested in different agro - ecological zones.

[0115] S1402. Allocate the national - scale crop harvested area statistical data according to the harvested area proportion of the crop in the agro - ecological zone in the target year to obtain the crop harvested area at the agro - ecological zone scale.

[0116] For the national - scale crop harvested area (i.e., Figure 1The harvested area of crops in the target year in [ ] is weighted and distributed, that is, according to the calculated proportion of potential harvested area above, the national-scale crop harvested area statistics are distributed to each agro-ecological zone to obtain the harvested area of crops in each agro-ecological zone within the administrative unit in the target year. This can be achieved by multiplying the national-scale harvested area by the proportion of potential harvested area of each agro-ecological zone. Through this distribution method, the harvested area of crops at the scale of each agro-ecological zone can be obtained.

[0117] In the present invention, by distributing the national-scale crop harvested area statistics to each agro-ecological zone, more refined-scale crop harvested area information can be obtained. This helps to more accurately understand the growth and distribution of crops in different regions and provides more reliable data support for agricultural decision-making. According to the harvested area of crops at the agro-ecological zone scale, the allocation of agricultural resources can be optimized more effectively. The harvested area information of crops at the agro-ecological zone scale can provide more refined data support for agricultural management. By real-time monitoring and analyzing the crop growth status, problems can be discovered and solved in a timely manner, improving the efficiency and effectiveness of agricultural management.

[0118] In an optional embodiment, the weight adjustment model in the above step S150 is constructed in the following manner:

[0119] S1501. Determine the initial spatial weight of each grid within the agro-ecological zone according to the gridded harvested area data of the reference year through the following formula:

[0120]

[0121] Where: represents the initial spatial weight of crop j in grid i within agro-ecological zone k in the reference year, represents the harvested area of crop j in grid i within agro-ecological zone k in the reference year, represents the harvested area of crop j in grid m within agro-ecological zone k in the reference year, where i, j, and k respectively represent the numbers of the grid, crop, and agro-ecological zone, and m represents the numbers of all grids within agro-ecological zone k;

[0122] S1502. Consider the change in planting area for weight update to obtain the weight adjustment model as follows:

[0123]

[0124] Where, represents the spatial weight of crop j in grid i within agro-ecological zone k in the target year, r i,j,k represents the planting area change rate of a single grid, r j,kRepresents the change rate of the planting area of a single agro - ecological zone; where:

[0125]

[0126] Where, represents the planting area of crop j in grid i within agro - ecological zone k in the target year, represents the planting area of crop j in grid i within agro - ecological zone k in the reference year, represents the planting area of crop j in grid m within agro - ecological zone k in the target year, represents the planting area of crop j in grid m within agro - ecological zone k in the reference year.

[0127] According to this weight adjustment model, the harvested area calculation at the network scale can be carried out:

[0128]

[0129] Where, is the final harvested area of crop j in grid i within agro - ecological zone k in the target year.

[0130] Summarize the grid - scale results (i.e., the crop harvested areas at the above - mentioned grid scale) to the national scale and compare them with the FAO (Food and Agriculture Organization of the United Nations) statistical data. Compare the summarized data with the FAO statistical data. By calculating the relative error and absolute error, the deviation degree of the data can be understood. If there are data deviations, correction processing is required to ensure the accuracy and consistency of the data. For example, the data can be adjusted according to a certain proportion based on the calculated relative error or absolute error. According to specific situations, other correction methods can also be used, such as linear regression, interpolation, etc. Correct the deviated data one by one to ensure that the corrected data is logically consistent with the original data. Re - verify the corrected data to ensure the accuracy and consistency of the data. It can be compared with the FAO statistical data or other reliable data to evaluate the correction effect.

[0131] Taking the estimation of the maize harvested area in 2020 on a global scale as an example, the hierarchical progressive estimation method for crop harvested areas for large regions provided by the present invention is applied for estimation, and the process is as follows:

[0132] Obtain the spatial distribution data of the maize harvested area in the GAEZ (Global Agro - ecological Zones) dataset in 2015 (such as in the appendix Figure 3)。This dataset provides spatial distribution information on maize cultivation globally and is an important reference for estimating the maize harvested area in the target year. Obtain the maize harvested area data for 2020 from FAO (Food and Agriculture Organization of the United Nations) statistics. FAO statistical data is an internationally recognized authoritative data source for validating and calibrating the estimation results. Obtain the CALF data for the four seasons of 2020 provided by CropWatch (as attached Figure 4 )。These data contain information such as the growth status of crops and the planted area in different seasons, which helps to more accurately estimate the annual harvested area. Collect regional crop phenological data, including information on key growth stages such as the growth status of crops. Integrate and preprocess the above-collected data to ensure consistent data format and reliable quality.

[0133] Using the S120 step provided by the present invention (including obtaining the phenological values of crops in different seasons, determining the set of crop types in each season, and dividing the planted area using a weight allocation method, etc.), calculate the maize planted area at the national scale in 2020. Output the spatial distribution data of the annual crop planted area in 2020, as attached Figure 5 shown. This data shows the spatial distribution of the maize planted area globally.

[0134] According to the division criteria of global agro-ecological zones, the world is divided into different AEZs (agro-ecological zones). Using the S140 step provided by the present invention, allocate the maize planted area at the national scale according to AEZs. This step takes into account the impact of natural conditions such as climate and soil in different AEZs on crop growth.

[0135] Divide the global scope into grids (pixels) of a certain size for easy spatial analysis and visualization. Using the S150 step provided by the present invention, map the maize harvested area at the AEZ scale to the grid scale. Output the spatial distribution data of the grid-scale annual harvested area in 2020, as attached Figure 6 shown. This data shows the spatial distribution of the maize harvested area globally at the grid scale.

[0136] Through the hierarchical progressive estimation method for crop harvested area for large regions provided by the present invention, the maize harvested area in 2020 globally has been successfully estimated. This method combines multiple data sources and advanced estimation techniques, and has high accuracy and reliability. The estimation results can be used in multiple fields such as agricultural decision-making support, food security assessment, and climate change research, providing strong support for the sustainable development of global agriculture.

[0137] The crop harvested area hierarchical progressive estimation device for large regions provided by the present invention will be described below. The crop harvested area hierarchical progressive estimation device for large regions described below can be correspondingly referred to the crop harvested area hierarchical progressive estimation method for large regions described above.

[0138] The main technical route of this method can be summarized as "three stages and four key points". The three stages refer to the hierarchical progressive estimation process from the country to the agro-ecological zone and then to the pixel. This progressive spatial decomposition strategy not only ensures the consistency with statistical data but also realizes the refined expression of spatial distribution. In the first stage, the total amount control is carried out based on the statistical data at the national scale, and the seasonal scale is subdivided by combining phenological information. In the second stage, spatial decomposition is carried out through the intermediate scale of the agro-ecological zone, which takes into account the overall characteristics of the region and lays a foundation for subsequent refined allocation. In the third stage, based on the spatial heterogeneity characteristics at the pixel scale, the final refined spatial allocation is realized.

[0139] The four key points constitute the core technical support of this method. First, the CALF data is used to reflect the dynamic change characteristics of farmland use intensity. The CALF data is obtained by remote sensing means and can timely reflect the cultivated land use status of each grid in different seasons, providing an important basis for capturing the spatio-temporal dynamic changes of farmland use intensity. Secondly, spatial decomposition is carried out based on the agro-ecological zone to improve the regional adaptability of the estimation. As a natural-agricultural composite geographical unit, the agro-ecological zone has similar climatic conditions and agricultural management methods inside, and this zoning method helps to improve the rationality of spatial allocation.

[0140] The third key point is to construct a weight adjustment model considering spatial heterogeneity to improve the accuracy of spatial allocation. Based on the spatial pattern of the reference year, this model dynamically adjusts the spatial weights of the grids by introducing the inter-annual change information of the planting area, so as to more accurately depict the spatial distribution characteristics of the harvested area. This dynamic weight adjustment mechanism not only maintains the relative stability of the spatial distribution but also can reflect the inter-annual dynamic changes. The last key point is to design a data consistency verification mechanism to ensure the coordination of multi-scale estimation results. By establishing a top-down verification system, it is ensured that the estimation results at the pixel scale are consistent with the statistical data when aggregated to the upper scale, thus ensuring the reliability of the entire estimation process.

[0141] Through this systematic technical route, this method realizes the refined dynamic estimation of the crop harvesting area in a large area. These four key points support each other and are organically combined to jointly form a complete technical system. This method has obvious advantages compared with the traditional fixed ratio method: First, the introduction of seasonal CALF data improves the response ability of the method to the dynamic changes in farmland utilization intensity; Second, the adoption of a hierarchical progressive strategy enhances the regional adaptability and the ability to express spatial heterogeneity of the method; Third, the deep integration of multi-source data improves the spatio-temporal continuity and accuracy of the estimation results; Finally, the design of the data consistency verification mechanism ensures the reliability and practicality of the estimation results. These characteristics make this method particularly suitable for the dynamic estimation of the crop harvesting area at the large area scale.

[0142] The hierarchical progressive estimation device for the crop harvesting area facing a large area provided by the present invention, as shown in reference to Figure 7 includes:

[0143] A data acquisition module 210, configured to acquire the gridded harvesting area data of the reference year, as well as the seasonal cultivated land utilization intensity data and the national-scale crop harvesting area statistical data of the target year,

[0144] An area calculation module 220, configured to calculate the planting areas in different seasons at the national scale by using the seasonal cultivated land utilization intensity data, and classify the planting areas in different seasons according to the phenological characteristics to obtain the spatial distribution data of the annual crop planting areas;

[0145] A model construction module 230, configured to construct a spatial allocation model at the agricultural ecological zoning scale based on the gridded harvesting area data of the reference year, in combination with the inter-annual change characteristics of the planting areas; wherein, the inter-annual change characteristics of the planting areas are characterized by the spatial distribution data of the annual crop planting areas of the target year and the reference year;

[0146] A first allocation module 240, configured to allocate the national-scale crop harvesting area statistical data of the target year to each agricultural ecological zone according to the spatial allocation model to obtain the crop harvesting area at the agricultural ecological zoning scale;

[0147] A second allocation module 250, configured to allocate the total harvested area of the crops in the agricultural ecological zone to each grid cell at the pixel scale through a pre-constructed weight adjustment model to obtain the crop harvesting area at the grid scale.

[0148] Figure 8 Illustrates a schematic diagram of the physical structure of an electronic device, such as Figure 8As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 complete communication with each other through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute the hierarchical progressive estimation method for the crop harvesting area in a large area.

[0149] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0150] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the hierarchical progressive estimation method for the crop harvesting area in a large area provided by the above-mentioned various methods.

[0151] On yet another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the hierarchical progressive estimation method for the crop harvesting area in a large area provided by the above-mentioned various methods.

[0152] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0153] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solutions, in essence, or the parts that contribute to the prior art can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0154] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A hierarchical progressive estimation method for crop harvesting area in a large area, characterized in that Comprising: Obtaining gridded harvested area data for the reference year, seasonal cultivated land utilization intensity data for the target year, and national-scale crop harvested area statistical data; At the national scale, calculating the planted areas in different seasons using the seasonal cultivated land utilization intensity data, and classifying the planted areas in different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planted areas; At the agro-ecological zoning scale, based on the gridded harvested area data for the reference year and combined with the inter-annual change characteristics of the planted area, constructing a spatial allocation model; wherein, the inter-annual change characteristics of the planted area are characterized by the spatial distribution data of the annual crop planted areas for the target year and the reference year; According to the spatial allocation model, allocating the national-scale crop harvested area statistical data for the target year to each agro-ecological zone to obtain the crop harvested area at the agro-ecological zoning scale; At the pixel scale, through a pre-constructed weight adjustment model, allocating the total harvested area of the crops within the agro-ecological zone to each grid cell to obtain the crop harvested area at the grid scale.

2. The hierarchical progressive estimation method for crop harvesting areas facing large regions according to claim 1, characterized in that The classifying the planted areas in different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planted areas includes: Obtaining the phenological values of the crops in different seasons, and determining the set of crop types for each season according to the phenological values of the crops in different seasons; Dividing the planted areas in different seasons using a weight allocation method to obtain the planted areas of the respective crop types in the set of crop types; For each crop type, accumulating the planted areas of the crop type in each season to obtain the spatial distribution data of the annual crop planted areas.

3. The method for hierarchical progressive estimation of crop harvesting area for large regions according to claim 1, wherein The constructing a spatial allocation model at the agro-ecological zoning scale, based on the gridded harvested area data for the reference year and combined with the inter-annual change characteristics of the planted area, includes: At the agro-ecological zoning scale, constructing an initial harvested area allocation model based on the gridded harvested area data for the reference year; According to the spatial distribution data of the annual crop planted areas for the target year and the reference year, respectively determining the change rate of the planted area within the agro-ecological zone and the change rate of the planted area at the national scale; According to the change rate of the planted area within the agro-ecological zone and the change rate of the planted area at the national scale, updating the initial harvested area allocation model to obtain the spatial allocation model.

4. The hierarchical progressive estimation method for crop harvesting area facing large areas according to claim 1, characterized in that The spatial allocation model is: ， Wherein: is the harvested area proportion of the crop in the target year in the agricultural ecological zone of the country , representing the initial harvested area proportion of the crop in the agricultural ecological zone of the country ; represents the planted area of the crop in the grid within the agricultural ecological zone in the target year, and represents the planted area of the crop in the grid within the agricultural ecological zone in the reference year; represents the planted area of the crop in the agricultural ecological zone of the country in the target year, and represents the planted area of the crop in the agricultural ecological zone of the country in the reference year; respectively represent the numbers of the crop, the agricultural ecological zone, and the country, represents the number of all grids within the agricultural ecological zone , and represents the number of all agricultural ecological zones within the country.

5. The method for hierarchically and progressively estimating the crop harvesting area facing a large area according to claim 1, wherein The allocating the national-scale crop harvested area statistical data for the target year to each agro-ecological zone according to the spatial allocation model to obtain the crop harvested area at the agro-ecological zoning scale includes: Determining the harvested area proportion of the crops in the agro-ecological zone for the target year according to the spatial allocation model; According to the harvested area proportion of the crops in the agro-ecological zone for the target year, allocating the national-scale crop harvested area statistical data to obtain the crop harvested area at the agro-ecological zoning scale.

6. The method for hierarchically progressive estimation of crop harvesting areas for large regions according to claim 1, characterized in that The weight adjustment model is constructed by the following method: Determining the initial spatial weight of each grid within the agro-ecological zone according to the gridded harvested area data for the reference year by the following formula: Wherein: represents the initial spatial weight of the grid within the agro-ecological zone for the crop in the reference year; represents the harvested area of the grid within the agro-ecological zone for the crop in the reference year; represents the harvested area of the grid within the agro-ecological zone for the crop in the reference year; respectively represent the numbers of the grid, crop, and agro-ecological zone, and represents the numbers of all grids within the agro-ecological zone; The weight is updated considering the change in planting area, and a weight adjustment model as shown in the following formula is obtained: Among them, represents the crop in the target year in the agro-ecological zone within the grid spatial weight, represents the change rate of the planting area of a single grid, represents the change rate of the planting area of a single agro-ecological zone; where: Among them, represents the planting area of the crop in the grid within the agro-ecological zone in the target year, represents the planting area of the crop in the grid within the agro-ecological zone in the reference year, represents the planting area of the crop in the grid within the agro-ecological zone in the target year, represents the planting area of the crop in the grid within the agro-ecological zone in the reference year.

7. A hierarchical progressive estimation method for crop harvesting areas in large regions, characterized in that, Including: A data acquisition module for acquiring gridded harvested area data of a reference year, seasonal cultivated land utilization intensity data of a target year, and national-scale crop harvested area statistical data; An area calculation module for calculating the planting area of different seasons at the national scale using the seasonal cultivated land utilization intensity data, and classifying the planting areas of different seasons according to phenological characteristics to obtain the spatial distribution data of the annual crop planting area; A model construction module for constructing a spatial allocation model at the agricultural ecological zoning scale based on the gridded harvested area data of the reference year in combination with the interannual change characteristics of the planting area; wherein, the interannual change characteristics of the planting area are characterized by the spatial distribution data of the annual crop planting area of the target year and the reference year; A first allocation module for allocating the national-scale crop harvested area statistical data of the target year to each agricultural ecological zone according to the spatial allocation model to obtain the crop harvested area at the agricultural ecological zoning scale; A second allocation module for allocating the total harvested area of crops in the agricultural ecological zone to each grid cell at the pixel scale through a pre-constructed weight adjustment model to obtain the crop harvested area at the grid scale.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the hierarchical progressive estimation method for crop harvested area facing large regions according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the hierarchical progressive estimation method for crop harvested area facing large regions according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the hierarchical progressive estimation method for crop harvested area facing large regions according to any one of claims 1 to 6.

Images