Automatic analysis method and device for regional cultivated land potential, medium and program product

Abstract

The invention discloses a regional cultivated land potential automatic analysis method and device, a medium and a program product, and relates to the field of geographic information. The method comprises the following steps: acquiring a land information layer of a target area, wherein the land information layer comprises a plurality of pattern spots of different land utilization current situations; according to the current land utilization situation of the pattern spots, multiple non-cultivated land pattern spots are determined in the land information pattern layer, and the non-cultivated land pattern spots comprise pattern spots with the current land utilization situation being non-cultivated land; based on a preset first screening rule, screening out a first potential cultivated land pattern spot from the non-cultivated land pattern spots; based on a preset second screening rule, screening out a second potential cultivated land pattern spot from the first potential cultivated land pattern spots; and generating a cultivated land potential map layer according to the second potential cultivated land map spot, wherein the cultivated land potential map layer is used for analyzing the cultivated land potential of the target area. The method can improve the analysis efficiency and accuracy of the cultivated land potential of the target area through an automatic analysis mode.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and in particular to a method, equipment, medium and program product for automatic analysis of regional cultivated land potential. Background Art

[0002] The purpose of analyzing regional arable land potential is to scientifically evaluate and identify land resources with the potential to be converted into arable land in a region, which is of great significance for ensuring regional food security, optimizing land use structure and promoting sustainable agricultural development. Through arable land potential analysis, land consolidation projects can be rationally planned to improve the quality and yield of arable land, while reducing the negative impact on the ecological environment, ensuring a balance between agricultural production and ecological protection under limited land resources.

[0003] In related technologies, regional arable land potential analysis usually relies on manual field surveys and expert experience, combined with historical land use data, remote sensing images, topographic maps and other relevant map data in the geographic information system (GIS). Through manual drawing and classification of maps, the natural conditions of the land, soil fertility, water conditions, terrain slope and other factors are evaluated to identify areas suitable for development into arable land.

[0004] However, this traditional method is often time-consuming, costly, and greatly affected by human factors, making it difficult to quickly and accurately analyze regional arable land potential. Summary of the invention

[0005] In view of the above-mentioned technical problems and defects, the purpose of the present invention is to provide a method, equipment, medium and program product for automated analysis of regional arable land potential, which can improve the analysis efficiency and accuracy of the arable land potential of the target area through automated analysis.

[0006] To achieve the above-mentioned purpose, in a first aspect, the present invention provides a method for automated analysis of regional cultivated land potential, comprising: obtaining a land information layer of a target area, the land information layer comprising a plurality of patches with different land use status; determining a plurality of non-cultivated patches in the land information layer according to the land use status of the patches, the non-cultivated patches comprising patches with a land use status of non-cultivated land; based on a preset first screening rule, screening out a first potential cultivated land patch from the non-cultivated land patch; based on a preset second screening rule, screening out a second potential cultivated land patch from the first potential cultivated land patch; generating a cultivated land potential layer according to the second potential cultivated land patch, the cultivated land potential layer being used to analyze the cultivated land potential of the target area.

[0007] The present invention improves the efficiency and accuracy of regional arable land potential assessment through the above-mentioned automated analysis process. This embodiment adopts the first screening rule and the second screening rule for automated screening, which can quickly process a large amount of land data, reduce the interference of human factors, and ensure the consistency and reliability of the analysis results. In addition, this embodiment can more accurately identify the map with arable land potential through refined screening rules, which helps to optimize land resource allocation and improve land use efficiency. Through two screenings, this embodiment can exclude those areas that are not suitable or impossible to be converted into arable land, thereby ensuring that the goals of the arable land development project are clearer and the resource investment is more reasonable, providing strong technical support for land planning and management, and having high social, economic and environmental benefits.

[0008] In combination with some embodiments of the first aspect, in some embodiments, after the step of screening out the second potential cultivated land area from the first potential cultivated land area based on a preset second screening rule, it also includes: obtaining land survey data; verifying the land use status of the second potential cultivated land area based on the land survey data to determine whether the second potential cultivated land area is feasible to be converted into cultivated land.

[0009] By adopting the technical solution of the above embodiment, the accuracy and reliability of the cultivated land potential analysis are enhanced by introducing the verification step of land survey data. This step ensures that the land use status of the second potential cultivated land map is consistent with the latest land survey data, thereby avoiding the risk of making wrong decisions based on outdated or inaccurate data. Through verification, the screening rules can be adjusted and optimized in a timely manner to ensure the accuracy of subsequent analysis, provide solid data support for land planning and resource management, and promote the rational use and protection of land resources.

[0010] In combination with some embodiments of the first aspect, in some embodiments, after the step of verifying the land use status of the second potential cultivated land area according to the land survey data, it also includes: if the land use status of the second potential cultivated land area does not match the land survey data, then adjusting the first screening rule and / or the second screening rule.

[0011] By adopting the technical solution of the above embodiment, a dynamic adjustment mechanism is proposed. When it is found that the land use status of the second potential cultivated land patch does not match the land survey data, the first screening rule and / or the second screening rule can be adjusted. This flexibility and adaptability are the key to improving the robustness of the automated analysis method. It allows the system to continuously optimize the screening criteria according to the latest land use conditions, thereby improving the accuracy of cultivated land potential assessment. This adjustment mechanism helps to cope with the rapidity and complexity of land use changes and ensures that the results of cultivated land potential analysis always reflect the latest land conditions.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the step of generating a cultivated land potential layer based on the second potential cultivated land map patch includes: inputting the remote sensing image of the target area into a preset cultivated land potential prediction model to obtain a cultivated land potential prediction result; generating a cultivated land potential layer based on the cultivated land potential prediction result and the second potential cultivated land map patch.

[0013] By adopting the technical solution of the above embodiment, by combining remote sensing images with the farmland potential prediction model, an intuitive and accurate prediction of farmland potential is achieved. This step uses the surface feature information captured by remote sensing technology, and through the prediction model analysis, directly marks the area with farmland potential on the image. This method not only improves the spatial resolution of the analysis, but also enables decision makers to quickly understand and evaluate the feasibility and priority of farmland development through intuitive image display, so as to make more scientific and reasonable land use planning decisions.

[0014] In combination with some embodiments of the first aspect, in some embodiments, the remote sensing image of the target area is input into a preset arable land potential prediction model to obtain the step of obtaining the arable land potential prediction result, including: marking the areas with arable land potential on the remote sensing image of the target area through the arable land potential prediction model; and using the remote sensing image marked with the arable land potential areas as the arable land potential prediction result.

[0015] By adopting the technical solution of the above embodiment, the transparency and operability of the cultivated land potential analysis are further enhanced by describing in detail the application process of the cultivated land potential prediction model. By directly marking the areas with cultivated land potential on the remote sensing image, this step provides decision makers with an intuitive tool to identify and evaluate cultivated land resources. This method not only improves the efficiency of analysis, but also enables non-professionals to participate in the land planning and decision-making process by converting complex data analysis results into easy-to-understand images, thereby promoting communication and collaboration among multiple stakeholders.

[0016] In combination with some embodiments of the first aspect, in some embodiments, the training process of the arable land potential prediction model includes: acquiring multiple remote sensing image data; marking the areas that are already arable land, non-arable land areas that are feasible to become arable land, and non-arable land areas that are not feasible to become arable land in the multiple remote sensing image data to obtain a training data set; training the selected machine learning model through the training data set to obtain a trained arable land potential prediction model.

[0017] The technical solution of the above embodiment is adopted, and the importance of model accuracy and reliability is emphasized by elaborating the training process of the cultivated land potential prediction model. By acquiring multiple remote sensing image data and accurately marking different types of land use areas in these data, a high-quality training data set is formed. This step ensures that the basic data for model training is representative and diverse, thereby improving the model's adaptability to different land conditions and utilization situations. The high-precision prediction model obtained through training can more accurately predict cultivated land potential and provide strong technical support for land planning and management.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of generating a farmland potential layer according to the second potential farmland map patch, it also includes: generating a farmland potential analysis report of the target area based on the farmland potential layer.

[0019] By adopting the technical solution of the above embodiment, the practicality of the analysis results and the decision-making efficiency are greatly improved by automatically generating the cultivated land potential analysis report. Based on the cultivated land potential layer, this step uses automated tools to integrate key data and analysis results to generate detailed and professional reports. This automated report generation method not only saves a lot of manpower and time, but also ensures the consistency and comparability of information through standardized report formats and content. Automated reports provide decision makers with a comprehensive and accurate land resource assessment tool, which helps to optimize land resource allocation and promote regional sustainable development.

[0020] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation method of the first aspect or the second aspect.

[0021] In a third aspect, the present invention provides a computer-readable storage medium comprising instructions, which, when executed on an electronic device, causes the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0022] In a fourth aspect, the present invention provides a computer program product comprising instructions, which, when executed on an electronic device, enables the electronic device to execute the method described in the first aspect or the second aspect, and any possible implementation of the first aspect or the second aspect.

[0023] It is understandable that the electronic device provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in the present invention. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided by the present invention have at least the following technical effects or advantages: 1. Improve the accuracy and reliability of cultivated land potential analysis: The present invention significantly improves the accuracy and reliability of cultivated land potential analysis by comprehensively using remote sensing image data, GIS technology and automated screening rules. By accurately marking existing cultivated land, potential cultivated land and non-cultivated land areas in multiple remote sensing image data, a high-quality training data set is formed, and then a high-precision cultivated land potential prediction model is trained. The model can directly mark areas with cultivated land potential on new remote sensing images, providing solid data support for land planning and management.

[0025] 2. Enhance the dynamic adjustment and adaptability of cultivated land potential analysis: The automated analysis method proposed in the present invention has significant dynamic adjustment and adaptability. When it is found that the land use status of the second potential cultivated land map does not match the land survey data, the system can automatically adjust the screening rules to ensure the accuracy of subsequent analysis. This flexibility and adaptability are the key to improving the robustness of automated analysis methods, helping to cope with the rapidity and complexity of land use changes and ensuring that the results of cultivated land potential analysis always reflect the latest land conditions.

[0026] 3. Realize the full process automation of cultivated land potential analysis: The present invention realizes the full process automation from data acquisition, processing, analysis to report generation, greatly improving the work efficiency of cultivated land potential assessment. Through the integration of key data and analysis results through automated tools, a detailed and professional cultivated land potential analysis report is generated. This automated report generation method not only saves a lot of manpower and time, but also ensures the consistency and comparability of information through standardized report formats and content. The automated analysis report provides decision makers with a comprehensive and accurate land resource assessment tool, which helps to optimize land resource allocation and promote regional sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings herein are incorporated into and constitute a part of the specification, showing embodiments consistent with the present invention, and together with the specification, are used to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1It is a flow chart of a method for automatic analysis of regional cultivated land potential according to an embodiment of the present invention; Figure 2 It is a flow chart of another method for automatic analysis of regional cultivated land potential according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to be limiting of the present invention. As used in the specification of the present invention, the singular expressions "a", "a", "above", "the" and "this" are intended to also include plural expressions, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present invention refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood as implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more.

[0030] It should also be noted that, unless otherwise clearly specified and limited, in the embodiments of the present invention, the terms such as "setting" and "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components; it can be a wired communication connection or a wireless communication connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. The embodiments of the present invention are described in detail below.

[0031] The embodiment of the present invention provides an automated analysis method for regional cultivated land potential, which improves the efficiency and accuracy of regional cultivated land potential assessment through an automated analysis process. This embodiment adopts the first screening rule and the second screening rule for automated screening, which can quickly process a large amount of land data, reduce the interference of human factors, and ensure the consistency and reliability of the analysis results. In addition, this embodiment can more accurately identify the map with cultivated land potential through refined screening rules, which helps to optimize land resource allocation and improve land use efficiency. Through two screenings, this embodiment can exclude areas that are not suitable or impossible to be converted into cultivated land, thereby ensuring that the goals of cultivated land development projects are clearer and resource investment is more reasonable, providing strong technical support for land planning and management, and having high social, economic and environmental benefits.

[0032] The method for automatically analyzing regional cultivated land potential in this embodiment can be performed by electronic equipment to reduce the workload of manual operations. Figure 1 As shown, the method comprises the following steps: Step 101, obtaining the land information layer of the target area.

[0033] Among them, the land information layer includes multiple patches of different land use status. The land information layer is a digital data layer used to represent specific information on the earth's surface in the geographic information system (GIS). It contains detailed attributes and spatial information of the land in the target area, such as land use type, ownership, soil type, etc., and is usually composed of multiple patches. A patch refers to a land area unit with the same attributes in the land information layer. Each patch represents a certain area of ​​land and can be distinguished by its shape, size and location. The collection of patches constitutes the land information layer, which is used for land management and planning analysis.

[0034] This step involves collecting and integrating spatial data from different sources, including using GIS technology to extract information such as land use status, land ownership, soil type, terrain characteristics, etc. from remote sensing satellite images, aerial photography, ground surveys and historical maps, and then using GIS software to process the data and classify the patches, ultimately generating a land information layer for the target area containing multiple patches of different land use status. This process may also require cooperation with local land management departments to ensure the accuracy and update of the data.

[0035] Step 102, according to the land use status of the patches, a plurality of non-cultivated patches are determined in the land information layer, and the non-cultivated patches include patches whose land use status is non-cultivated land.

[0036] The process of identifying multiple non-cultivated patches in the land information layer usually involves a detailed analysis and classification of the land use status of each patch in the layer. First, the land information layer is loaded through the GIS software, which contains rich attribute data, such as land use type, terrain characteristics, soil type, etc. Then, through the attribute query function, filter out those patches whose land use status is marked as non-cultivated land. These non-cultivated patches may include wasteland, forest land, grassland, water area, construction land, etc. In GIS, this step can be automated by setting query parameters and using logical expressions, for example, selecting all patches whose land use type attribute is not equal to "cultivated land".

[0037] In addition, the boundaries, shapes and features of the patches can be verified and corrected by combining remote sensing images and field survey data to ensure the accuracy of the non-cultivated patches. Ultimately, all identified and verified non-cultivated patches will be individually marked and classified to provide a basic data set for subsequent arable land potential analysis. This process not only improves the efficiency of patch recognition, but also provides reliable decision support for land planning and management through accurate patch classification.

[0038] Step 103: based on a preset first screening rule, screen out first potential cultivated land patches from non-cultivated land patches.

[0039] Among them, the first screening rule can adopt the positive screening rule, and the positive screening conditions can include but are not limited to: setting an implementation period, linking the increase and decrease of urban and rural construction land, carrying out three-optimization and three-guarantee (i.e. optimizing the urban and rural land structure, optimizing the agricultural land structure, optimizing the construction land structure, protecting cultivated land, protecting the ecological environment, and ensuring food security) remediation projects, and carrying out land remediation projects.

[0040] This step first involves setting a clear implementation period, which defines the time frame for the conversion of the plots into farmland, ensuring that the selected plots are in line with the recent land use planning and development plans. Next, through the GIS system and land management database, identify the plots that have participated in the urban and rural construction land increase and decrease linkage project. Such plots usually have certain infrastructure and development conditions and are more suitable for farmland development. In addition, screen out the plots that have implemented the "three improvements and three guarantees" remediation project. These areas are often planned and remediated and are easier to convert into farmland. Finally, consider those plots that have undergone land remediation. The land conditions of these plots have been improved and are more suitable for agricultural cultivation.

[0041] By integrating these conditions, the first potential cultivated land areas with higher cultivated land potential can be effectively screened out from non-cultivated land areas, providing a scientific basis for further land development and utilization.

[0042] Step 104: based on a preset second screening rule, screen out second potential farmland patches from the first potential farmland patches.

[0043] Among them, the second screening rule can adopt a reverse screening rule, and the reverse screening conditions can include but are not limited to: planning as existing construction land, and the land type is unused land (water area, pond, etc.).

[0044] Specifically, we first focus on excluding those spots that have been designated as current construction land in urban planning. These areas are usually planned for urban development, such as residential areas, commercial areas or industrial areas, and are therefore not suitable for conversion into arable land. In addition, we also need to exclude those spots that are classified as unused land, such as natural wetlands such as water areas and ponds. These areas are not suitable for arable land development due to their special ecological functions and environmental values. Through GIS spatial analysis tools, the first potential arable land spot is compared and analyzed with the urban planning layer and the current land use layer, and the spots that do not meet the conditions for arable land development are automatically identified and excluded, and finally the second potential arable land spot is obtained.

[0045] This step is a key link in ensuring the practicality and feasibility of the results of the arable land potential analysis. By excluding areas that are not suitable for development, the allocation of land resources can be optimized and unnecessary damage to the ecological environment can be avoided. At the same time, it ensures that arable land development projects can proceed smoothly and meet the needs of agricultural production and food security.

[0046] In some embodiments, the first screening rule may also adopt a reverse screening rule, based on the reverse screening condition, exclude some patches from the non-cultivated patches, and leave the first potential cultivated patches. The second screening rule may also adopt a forward screening rule, based on the forward screening condition, retain some patches from the first potential cultivated patches as the second potential cultivated patches.

[0047] Step 105, generating a potential cultivated land layer according to the second potential cultivated land map patch.

[0048] The cultivated land potential layer is used to analyze the cultivated land potential of the target area. After the above screening process, the step of generating the cultivated land potential layer involves spatial integration and visualization of the potential cultivated land patches that have passed the second screening.

[0049] First, using geographic information system (GIS) software, the selected second potential cultivated land patches are merged and classified according to their spatial location and attributes to ensure that the boundaries of each patch are clear and the attribute information is accurate. Then, a potential score or classification level is assigned to each patch based on its cultivated land potential indicators, such as soil quality, proximity to water sources, terrain suitability, etc. These indicators can be obtained through expert scoring, historical data analysis or machine learning model prediction.

[0050] Then, a new layer, namely the arable land potential layer, is created in GIS, and these patches and their potential scores or classification levels are entered and displayed as the attribute information of the layer.

[0051] In addition, different visual symbols or color codes can be set to intuitively represent the arable land potential levels of different map blocks, so that the arable land potential layer is clearly visible on the map, facilitating analysis and decision-making.

[0052] The final arable land potential layer not only intuitively displays the areas with different arable land potentials within the target area, but also provides scientific and accurate spatial data support for land planning, resource management and policy making.

[0053] The embodiment of the present invention realizes a rapid and accurate assessment of regional cultivated land potential by constructing an automated analysis process. The automated process can be based on geographic information system (GIS) technology, and first integrates the land information layer of the target area. Then, through the first screening rule and the second screening rule, non-cultivated land patches with the potential for conversion into cultivated land are automatically identified, and those areas that are not suitable for conversion into cultivated land due to planned use, ecological protection requirements or other restrictions are excluded. Finally, the cultivated land potential layer is automatically generated through GIS technology, and areas with different cultivated land potentials are intuitively displayed, providing a scientific basis for land planning and decision-making. The entire process of the method of this embodiment can be highly automated, reducing manual intervention, improving the efficiency and accuracy of regional cultivated land potential analysis, and ensuring the rational use and effective management of cultivated land resources.

[0054] Combine the following Figure 2 To further introduce the automated analysis method of regional cultivated land potential implemented in this paper, it specifically includes the following steps: Step 201, obtaining the land information layer of the target area.

[0055] This step refers to step 101 and will not be repeated here.

[0056] Step 202, according to the land use status of the patches, a plurality of non-cultivated patches are determined in the land information layer, and the non-cultivated patches include patches whose land use status is non-cultivated land.

[0057] This step refers to step 102 and will not be described in detail here.

[0058] Step 203: based on a preset first screening rule, screen out first potential cultivated land patches from non-cultivated land patches.

[0059] This step refers to step 103 and will not be described again here.

[0060] Step 204: based on a preset second screening rule, screen out second potential farmland patches from the first potential farmland patches.

[0061] This step refers to step 104 and will not be described in detail here.

[0062] Step 205, obtaining land survey data.

[0063] Among them, land survey data is obtained through systematic investigation and measurement of land resources. It records in detail the location, type, area, ownership and utilization status of land. Land survey data can come from the Second National Land Survey (Second National Land Survey) or the Third National Land Survey (Third National Land Survey), which provide an authoritative and comprehensive perspective for assessing the current status and historical changes of land. By integrating these data, the accuracy of analysis and the scientific nature of land resource management can be ensured. Obtaining this data usually involves cooperating with the land management department of the target area, using their databases and survey results, or obtaining the latest land information through modern technical means such as remote sensing technology and field surveys.

[0064] Step 206, verifying the land use status of the second potential cultivated land parcel based on the land survey data to determine whether the second potential cultivated land parcel has the feasibility of being converted into cultivated land.

[0065] This step is a process of detailed verification of the second potential cultivated land area in the present invention. In this step, the land survey data obtained is used to verify the land use status of the second potential cultivated land area that has passed the preliminary screening. This verification process is very important because it can ensure that the selected area really has the potential and feasibility of being converted into cultivated land.

[0066] Specifically, by comparing the detailed information in the land survey data, the current land use type, land conditions, development restrictions and other factors of the map can be verified to assess its possibility of conversion to arable land. For example, if a map is marked as a protected wetland in the land survey data, it is not suitable for conversion to arable land. Through this verification step, those unsuitable or unfeasible maps can be excluded to ensure that the final arable land potential map is highly feasible and practical. This process not only improves the accuracy of the analysis, but also provides solid data support for subsequent land planning and development.

[0067] In some embodiments, if the land use status of the second potential cultivated land patch does not match the land survey data, the first screening rule and / or the second screening rule are adjusted.

[0068] If the current land use status of the second potential cultivated land area is found to be inconsistent with the land survey data, this may mean that the existing screening rules fail to accurately reflect the actual status of the land or that the land use has changed. In order to improve the accuracy and adaptability of the analysis, the first screening rule and / or the second screening rule need to be adjusted accordingly.

[0069] The adjustment process first involves a detailed analysis of the mismatched patches to identify the causes of the mismatch, such as delayed data updates, land use changes, or improper settings of screening rules. Then, based on the analysis results, the specific parameters or conditions in the screening rules are optimized, such as adjusting the screening criteria for land use types, updating the evaluation indicators for soil quality, and redefining the scope of terrain suitability.

[0070] In addition, it may be necessary to introduce new data sources or adopt more advanced data processing technologies to enhance the adaptability and flexibility of the rules. Through this dynamic adjustment mechanism, it can be ensured that the screening rules are always consistent with the land survey data, thereby improving the accuracy and reliability of the cultivated land potential analysis. This process reflects the innovation of this embodiment in the automated analysis method, that is, by continuously iterating and optimizing the screening rules, adapting to the dynamic changes in land use, and ensuring the effectiveness and practicality of the analysis results.

[0071] After adjusting the first screening rule and / or the second screening rule, return to step 203 or step 204 to screen the spots again.

[0072] If the land use status of the second potential cultivated land patch matches the land survey data, the process proceeds to step 207 .

[0073] Step 207, inputting the remote sensing image of the target area into a preset cultivated land potential prediction model to obtain a cultivated land potential prediction result.

[0074] The remote sensing images of the target area are used as key input data to drive the preset arable land potential prediction model, thereby obtaining accurate arable land potential prediction results. Among them, remote sensing images are high-temporal and spatial resolution images that contain rich surface feature information, such as vegetation coverage, land use type, terrain undulation, etc., which are important indicators for evaluating arable land potential.

[0075] First, through remote sensing image processing technology, key features such as land cover type, vegetation index, soil moisture, etc. of the target area are extracted. Then, these feature data are input into the preset arable land potential prediction model. The model uses advanced statistical or machine learning algorithms, such as regression analysis, random forest or support vector machine, to analyze and learn the input feature data to identify and predict areas with arable land development potential. After the model training is completed, it can automatically process and analyze new remote sensing image data and quickly output the arable land potential prediction results. These results are displayed in the form of map layers, intuitively identifying areas with different arable land potential levels, and providing scientific and intuitive decision support for land planning and resource management. Through this method, the present invention realizes a rapid and accurate assessment of regional arable land potential, greatly improving the efficiency and effectiveness of land resource management.

[0076] In some embodiments, this step may specifically include: Firstly, the cultivated land potential prediction model is used to mark the areas with cultivated land potential on the remote sensing image of the target area; then the remote sensing image marked with the cultivated land potential areas is used as the cultivated land potential prediction result.

[0077] In an embodiment of the present invention, the application of the farmland potential prediction model marks a key step in the automated analysis method. The farmland potential prediction model is specially designed to process and analyze remote sensing images of target areas to identify and mark areas with farmland potential.

[0078] The first step involves inputting high-resolution remote sensing images of the target area into the farmland potential prediction model. The farmland potential prediction model integrates a variety of spatial analysis techniques and algorithms, which can conduct in-depth analysis of remote sensing data and extract features related to farmland potential, such as soil fertility, proximity to water sources, and terrain suitability. Through a comprehensive evaluation of these features, the model can automatically identify areas on remote sensing images that have the conditions to be converted into farmland and mark these areas with specific colors or symbols. The marked areas intuitively show the spatial distribution of farmland potential and provide a clear map of candidate areas for farmland development.

[0079] Subsequently, these remote sensing images processed by the model and marked with potential cultivated land areas were integrated and output as cultivated land potential prediction results, which were presented in the form of map layers, showing in detail the location, scope and potential level of each potential cultivated land area. Such prediction results not only provide a scientific basis for land planning and management, but also enable decision makers to quickly understand and evaluate the feasibility and priority of cultivated land development through intuitive visualization, so as to make more informed land use decisions. This automated prediction process significantly improves the efficiency and accuracy of cultivated land potential analysis, and provides strong technical support for the rational development and sustainable management of land resources.

[0080] In some embodiments, the training process of the cultivated land potential prediction model includes: (1) Obtain multiple remote sensing image data.

[0081] In the process of training the arable land potential prediction model, it is first necessary to obtain multiple remote sensing image data. These remote sensing image data usually come from satellite sensors or aerial photography, which can provide the surface cover and land use of the target area at different time points. These image data contain rich spatial information, such as vegetation index, land cover type, terrain characteristics, etc., which are the basis for arable land potential analysis. Obtaining these data requires coordinating multiple data sources, including remote sensing data released by the government, shared data from scientific research institutions, and commercial remote sensing data providers, to ensure the diversity and coverage of the data to meet the needs of model training.

[0082] (2) In multiple remote sensing image data, areas that are already cultivated land, non-cultivated land areas that are feasible for becoming cultivated land, and non-cultivated land areas that are not feasible for becoming cultivated land are marked to obtain a training data set.

[0083] Specifically, professional geographic information system (GIS) software is first used to load high-resolution remote sensing images, which usually include multispectral data and can show the detailed features of the surface. Then, analysts with expertise in land use and object identification manually draw and mark the areas that are already cultivated land based on the spectral characteristics, texture, shape and contextual information of the image. These areas usually appear as regular field shapes with obvious crop growth characteristics. Subsequently, experts further identify and mark non-cultivated land areas that are feasible for becoming cultivated land, such as land that is currently unused but has suitable soil and terrain conditions. In addition, non-cultivated land areas that are not feasible for becoming cultivated land need to be marked, such as urban built-up areas, ecological protection areas, or areas with steep terrain.

[0084] After all these labeling work is completed, a training data set containing positive samples (existing arable land), potential positive samples (non-arable land with potential), and negative samples (non-arable land without potential) is formed, providing accurate samples and labels for training machine learning models. This process ensures the quality and diversity of the training data set, which is crucial to improving the accuracy of the arable land potential prediction model.

[0085] (3) Train the selected machine learning model using the training data set to obtain a trained arable land potential prediction model.

[0086] The process of training the selected machine learning model with the training data set to obtain the trained arable land potential prediction model first involves importing the prepared training data set into the machine learning algorithm. These training data sets contain samples of labeled arable land, potential arable land, and non-arable land areas, each of which is accompanied by a corresponding label indicating which land use type it belongs to.

[0087] Next, using supervised learning methods, the machine learning model analyzes the characteristics of these samples and the corresponding labels during the training phase, and learns how to distinguish different types of land use areas based on the characteristics of remote sensing images. During this process, the parameters of the model are continuously optimized through algorithms to minimize the difference between the predicted results and the actual labels. Commonly used optimization algorithms include gradient descent, stochastic gradient descent, etc., which help the model achieve a higher accuracy after multiple iterations of training.

[0088] In addition, in order to prevent the model from overfitting, cross-validation, regularization and other techniques may be used to improve the generalization ability of the model.

[0089] Ultimately, the fully trained model can accurately identify areas with arable land potential from new remote sensing images, thereby obtaining an efficient and accurate arable land potential prediction model, providing strong technical support for land planning and management.

[0090] Step 208, generating a cultivated land potential layer according to the cultivated land potential prediction result and the second potential cultivated land map patch.

[0091] Specifically, we first use geographic information system (GIS) software to load remote sensing image data. These data have been analyzed through a preset arable land potential prediction model, and the areas with high potential for conversion to arable land identified by the model are clearly marked on the image.

[0092] These predictions were then spatially overlaid with the second potential cultivated land patches identified through the automated screening process to ensure consistency in both geographic location and attribute characteristics. In GIS, each matched patch was assigned corresponding attributes, such as cultivated land potential score, soil quality, proximity to water sources, etc. These attributes reflect the possibility and suitability of each patch to be converted into cultivated land.

[0093] Next, visual expressions are designed for the map blocks based on these attributes, such as different colors or patterns, to intuitively demonstrate the potential of arable land.

[0094] Finally, these patches and their attributes are integrated into a new GIS layer to form a potential arable land layer. This layer not only intuitively displays the spatial distribution of potential arable land in the target area, but also records the arable land potential information of each patch in detail, providing scientific and accurate decision support for land planning and resource management.

[0095] Step 209: Generate a farmland potential analysis report for the target area based on the farmland potential layer.

[0096] Specifically, key spatial data and attribute information are first extracted directly from the farmland potential layer through the automation function of GIS software. A series of analyses can be automatically performed through preset scripts, including calculating the total area of ​​high-potential farmland areas, identifying areas with concentrated farmland, and evaluating the correlation between farmland potential and existing infrastructure.

[0097] Subsequently, these analysis results were used by an automated report generation tool (automated script), combined with natural language generation (NLG) technology, to convert the data into text descriptions and write the various parts of the report, such as the introduction, methodology, results analysis and conclusion recommendations. In addition, the automated script will automatically generate charts and maps to intuitively display the spatial distribution and key indicators of arable land potential.

[0098] Finally, all texts, charts and maps will be automatically compiled into a complete analysis report according to the preset template. This automated process not only improves the efficiency of report generation, but also ensures the accuracy and consistency of information, providing decision makers with a scientific, intuitive and timely arable land potential analysis report.

[0099] In this embodiment, to make an automated script to generate a arable land potential analysis report, it is first necessary to clarify the structure and content requirements of the report, and then select a suitable programming language and automation tool, such as Python combined with ArcGIS's ArcPy library or QGIS's PyQGIS plug-in. Script writing begins with defining the logic of data extraction, including querying the attributes and spatial information of the arable land potential layer from the GIS database. Next, the script should include the automated process of spatial analysis, such as calculating the arable land potential index, identifying high potential areas, etc.

[0100] Subsequently, data processing and visualization libraries (such as Matplotlib or Plotly) are used to automatically generate charts and maps. In addition, the automation script needs to integrate a text generation module, possibly through template filling or NLP (natural language processing) technology, to convert the analysis results into natural language descriptions.

[0101] Finally, the script should include report generation and formatting functionality, such as using the Jinja2 template engine or LaTeX to automatically format text, charts, and maps, and generate reports in PDF or Word document format.

[0102] The writing of the entire script requires GIS expertise, programming skills and a deep understanding of the report content to ensure the accuracy of the automated process and high-quality report output.

[0103] The embodiment of the present invention provides an automated analysis method for regional cultivated land potential, which aims to improve the efficiency and accuracy of cultivated land potential assessment through automation technology. The method starts with obtaining a land information layer through a series of steps, which contains multiple patches of different land use status. Then, multiple non-cultivated patches are determined, and the land use status of these patches is non-cultivated land. Through a preset first screening rule, a first potential cultivated land patch with the possibility of potential cultivated land is screened out from the non-cultivated land patch. Subsequently, using a second screening rule, a second potential cultivated land patch is further screened out from the first potential cultivated land patch, and these patches are more likely to be converted into cultivated land.

[0104] After the screening process, the land survey data is obtained and the land use status of the second potential cultivated land is verified to verify the feasibility of its conversion into cultivated land. If it is found that the land use status does not match the land survey data, the method further includes adjusting the first screening rule and / or the second screening rule to ensure the accuracy of the screening process.

[0105] In addition, this embodiment uses remote sensing images and a preset arable land potential prediction model to predict the arable land potential of the target area. The model marks the area with arable land potential on the remote sensing image and integrates this information into the arable land potential layer. The training process of the prediction model involves obtaining multiple remote sensing image data, and marking the areas that are already arable land, the non-arable land areas that have the feasibility of becoming arable land, and the non-arable land areas that do not have the feasibility of becoming arable land in these data to form a training data set. The selected machine learning model is trained with these data sets to obtain a trained arable land potential prediction model.

[0106] Finally, this embodiment automatically generates a farmland potential analysis report for the target area based on the generated farmland potential layer. The report describes in detail the distribution of farmland potential, the characteristics of potential areas, and development suggestions, providing scientific and intuitive decision support for decision makers, helping to optimize land resource allocation and promote regional sustainable development.

[0107] Overall, the technical solution of this embodiment realizes the automation of the whole process from data acquisition, processing, analysis to report generation through automated processes and advanced analysis technology, greatly improving the work efficiency of arable land potential assessment, while ensuring the scientificity and accuracy of the analysis results. Through this method, potential arable land resources can be more effectively identified and utilized, providing strong technical support for land planning and management.

[0108] The method provided in the above embodiment can be executed by an electronic device. The following describes the electronic device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , is a schematic diagram of a physical device structure of an electronic device in an embodiment of the present invention.

[0109] It should be noted that Figure 3 The structure of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0110] like Figure 3 As shown, the electronic device includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. In RAM 403, various programs and data required for system operation are also stored. CPU 401, ROM 402 and RAM 403 are connected to each other through bus 404. Input / output (I / O) interface 405 is also connected to bus 404.

[0111] The following components are connected to the I / O interface 405: an input section 406 including an audio input device, a button switch, etc.; an output section 407 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0112] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the present invention are performed.

[0113] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0115] Specifically, the electronic device of this embodiment includes a processor and a memory, the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the electronic device to execute the method provided by the above embodiment.

[0116] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the electronic device, the electronic device implements the method provided in the above embodiment.

[0117] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention.

[0118] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0119] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for automated analysis of regional arable land potential, characterized in that: include: Acquire a land information layer of a target area, wherein the land information layer includes a plurality of spots of different land use status; According to the land use status of the map spots, a plurality of non-cultivated map spots are determined in the land information layer, wherein the non-cultivated map spots include maps whose land use status is non-cultivated land; Based on a preset first screening rule, screening out first potential cultivated land patches from the non-cultivated land patches; Based on a preset second screening rule, screening out second potential cultivated land patches from the first potential cultivated land patches; A cultivated land potential layer is generated according to the second potential cultivated land map patch, and the cultivated land potential layer is used to analyze the cultivated land potential of the target area.

2. The method according to claim 1, characterized in that After the step of screening out the second potential cultivated land patches from the first potential cultivated land patches based on the preset second screening rule, the method further includes: Obtaining land survey data; The land use status of the second potential cultivated land parcel is verified based on the land survey data to determine whether the second potential cultivated land parcel is feasible for conversion into cultivated land.

3. The method according to claim 2, characterized in that After the step of verifying the land use status of the second potential cultivated land patch according to the land survey data, the method further includes: If the land use status of the second potential cultivated land patch does not match the land survey data, the first screening rule and / or the second screening rule are adjusted.

4. The method according to claim 1, characterized in that: The step of generating a cultivated land potential layer according to the second potential cultivated land map patch comprises: Inputting the remote sensing image of the target area into a preset cultivated land potential prediction model to obtain a cultivated land potential prediction result; A cultivated land potential layer is generated according to the cultivated land potential prediction result and the second potential cultivated land map patch.

5. The method according to claim 4, characterized in that The step of inputting the remote sensing image of the target area into a preset cultivated land potential prediction model to obtain a cultivated land potential prediction result comprises: Using the arable land potential prediction model, marking areas with arable land potential on the remote sensing image of the target area; The remote sensing images indicating the areas with arable land potential are used as the prediction results of arable land potential.

6. The method according to claim 4, characterized in that The training process of the cultivated land potential prediction model includes: Acquire multiple remote sensing image data; Marking the areas that are already cultivated land, the non-cultivated land areas that are feasible to become cultivated land, and the non-cultivated land areas that are not feasible to become cultivated land in the plurality of remote sensing image data to obtain a training data set; The selected machine learning model is trained using the training data set to obtain a trained arable land potential prediction model.

7. The method according to any one of claims 1 to 6, characterized in that: After the step of generating a cultivated land potential layer according to the second potential cultivated land map patch, the method further includes: Based on the arable land potential layer, a arable land potential analysis report for the target area is generated.

8. An electronic device, characterized in that: including one or more processors and memory; The memory is coupled to the one or more processors, and the memory is used to store computer program codes, wherein the computer program codes include computer instructions, and the one or more processors call the computer instructions to enable the electronic device to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on an electronic device, the electronic device is caused to execute the method as claimed in any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on an electronic device, the electronic device is enabled to execute the method according to any one of claims 1 to 7.

Images