Method, device, medium and program product for automated analysis of regional arable land potential

Abstract

This invention discloses an automated method, device, medium, and program product for analyzing regional arable land potential, relating to the field of geographic information. The method includes: acquiring a land information layer of a target area, the land information layer comprising multiple patches with different land use statuses; determining multiple non-arable land patches in the land information layer based on the land use status of the patches, the non-arable land patches including patches whose current land use status is non-arable land; selecting a first potential arable land patch from the non-arable land patches based on a preset first filtering rule; selecting a second potential arable land patch from the first potential arable land patch based on a preset second filtering rule; generating an arable land potential layer based on the second potential arable land patch, the arable land potential layer being used to analyze the arable land potential of the target area. This invention can improve the efficiency and accuracy of analyzing the arable land potential of a target area through automated analysis.

Description

Technical Field

[0001] This invention relates to the field of geographic information technology, and in particular to an automated analysis method, device, medium, and program product for regional arable land potential. Background Technology

[0002] Analyzing regional arable land potential aims to scientifically assess and identify land resources within a region that have the potential to be converted into arable land. This is crucial 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 arable land quality and yield, while simultaneously reducing negative impacts on the ecological environment, ensuring a balance between agricultural production and ecological protection within limited land resources.

[0003] In related technologies, regional arable land potential analysis usually relies on manual field investigation and expert experience, combined with historical land use data, remote sensing images, topographic maps and other relevant map data in geographic information systems (GIS), and assesses factors such as natural conditions, soil fertility, water resources, and topographic slope of the land by manually drawing and classifying map features, thereby identifying 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 the potential of regional arable land. Summary of the Invention

[0005] To address the aforementioned technical problems and deficiencies, the purpose of this invention is to provide an automated analysis method, device, medium, and program product for regional arable land potential, which can improve the efficiency and accuracy of analyzing the arable land potential of a target region through automated analysis.

[0006] To achieve the above objectives, in a first aspect, the present invention provides an automated method for analyzing regional arable land potential, comprising: acquiring a land information layer of a target area, the land information layer including multiple patches with different land use statuses; determining multiple non-arable land patches in the land information layer based on the land use status of the patches, the non-arable land patches including patches whose current land use status is non-arable land; selecting a first potential arable land patch from the non-arable land patches based on a preset first filtering rule; selecting a second potential arable land patch from the first potential arable land patch based on a preset second filtering rule; and generating an arable land potential layer based on the second potential arable land patch, the arable land potential layer being used to analyze the arable land potential of the target area.

[0007] This invention improves the efficiency and accuracy of regional arable land potential assessment through the aforementioned automated analysis process. This embodiment employs automated screening using first and second screening rules, enabling rapid processing of large amounts of land data, reducing human interference, and ensuring the consistency and reliability of the analysis results. Furthermore, this embodiment, through refined screening rules, can more accurately identify land parcels with arable land potential, which helps optimize land resource allocation and improve land use efficiency. Through two screening processes, this embodiment can exclude areas unsuitable or impossible to convert into arable land, thereby ensuring clearer objectives for arable land development projects and more rational resource allocation. This provides strong technical support for land planning and management, and has significant social, economic, and environmental benefits.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of selecting a second potential arable land parcel from the first potential arable land parcel based on a preset second screening rule, the method further includes: obtaining land survey data; verifying the land use status of the second potential arable land parcel based on the land survey data to determine whether the second potential arable land parcel is feasible to be converted into arable land.

[0009] The technical solution adopted in the above embodiments enhances the accuracy and reliability of arable land potential analysis by introducing a verification step for land survey data. This step ensures that the land use status of the second potential arable land parcel is consistent with the latest land survey data, thereby avoiding the risk of making erroneous decisions based on outdated or inaccurate data. Through verification, screening rules can be adjusted and optimized in a timely manner, ensuring the accuracy of subsequent analyses, providing solid data support for land planning and resource management, and ultimately promoting the rational use and protection of land resources.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of verifying the land use status of the second potential arable land parcel based on the land survey data, the method further includes: if the land use status of the second potential arable land parcel does not match the land survey data, then adjusting the first screening rule and / or the second screening rule.

[0011] The technical solution described in the above embodiments proposes a dynamic adjustment mechanism. When a mismatch is found between the current land use status of a second potential arable land parcel and land survey data, the first and / or second screening rules can be adjusted. This flexibility and adaptability are key to improving the robustness of automated analysis methods. It allows the system to continuously optimize screening criteria based on the latest land use information, thereby improving the accuracy of arable land potential assessment. This adjustment mechanism helps to cope with the rapid and complex nature of land use changes, ensuring that the arable land potential analysis results always reflect the latest land conditions.

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

[0013] The technical solution described in the above embodiments combines remote sensing imagery with a farmland potential prediction model, enabling intuitive and accurate prediction of farmland potential. This step utilizes surface feature information captured by remote sensing technology, analyzes it through a prediction model, and directly marks areas with farmland potential on the imagery. This method not only improves the spatial resolution of the analysis but also, through intuitive image display, allows decision-makers to quickly understand and assess the feasibility and priority of farmland development, thereby making more scientific and rational land use planning decisions.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, the step of inputting the remote sensing image of the target area into a preset arable land potential prediction model to obtain arable land potential prediction results includes: using the arable land potential prediction model to mark areas with arable land potential on the remote sensing image of the target area; and using the remote sensing image of the marked arable land potential areas as arable land potential prediction results.

[0015] By employing the technical solution described above and detailing the application process of the arable land potential prediction model, the transparency and operability of arable land potential analysis are further enhanced. By directly marking areas with arable land potential on remote sensing imagery, this step provides decision-makers with an intuitive tool for identifying and assessing arable land resources. This method not only improves the efficiency of analysis but also, by transforming complex data analysis results into easily understandable images, allows non-experts to participate in land planning and decision-making processes, thereby promoting communication and collaboration among multiple stakeholders.

[0016] In conjunction 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 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 dataset; and training a selected machine learning model using the training dataset to obtain a trained arable land potential prediction model.

[0017] The technical solution described above, through a detailed explanation of the training process of the arable land potential prediction model, emphasizes the importance of model accuracy and reliability. By acquiring multiple remote sensing image datasets and accurately labeling different types of land use areas within these datasets, a high-quality training dataset 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 uses. The high-precision prediction model obtained through training can more accurately predict arable land potential, providing strong technical support for land planning and management.

[0018] In conjunction with some embodiments of the first aspect, in some embodiments, after the step of generating a farmland potential layer based on the second potential farmland patch, the method further includes: generating a farmland potential analysis report for the target area based on the farmland potential layer.

[0019] The technical solution described above significantly improves the practicality of analysis results and decision-making efficiency by automatically generating arable land potential analysis reports. Based on the arable land potential layer, this step utilizes automated tools to integrate key data and analysis results, generating detailed and professional reports. This automated report generation method not only saves considerable manpower and time but also ensures information consistency and comparability through standardized report formats and content. The automated report provides decision-makers with a comprehensive and accurate land resource assessment tool, helping to optimize land resource allocation and promote regional sustainable development.

[0020] In a second aspect, embodiments of the present invention provide an electronic device, including: one or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors calling the computer instructions to cause the electronic device to perform the method described in the first aspect or the second aspect, and any possible implementation thereof.

[0021] Thirdly, the present invention provides a computer-readable storage medium including instructions that, when executed on an electronic device, cause the electronic device to perform the method described in the first aspect or the second aspect, and any possible implementation thereof.

[0022] Fourthly, the present invention provides a computer program product containing instructions that, when the computer program product is run on an electronic device, cause the electronic device to perform the method described in the first aspect or the second aspect, and any possible implementation thereof.

[0023] Understandably, 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 by this invention. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided by this invention have at least the following technical effects or advantages:

[0025] 1. Improving the accuracy and reliability of arable land potential analysis: This invention significantly improves the accuracy and reliability of arable land potential analysis by comprehensively utilizing remote sensing image data, GIS technology, and automated screening rules. By accurately labeling existing arable land, potential arable land, and non-arable land areas in multiple remote sensing image datasets, a high-quality training dataset is formed, which is then used to train a high-precision arable land potential prediction model. This model can directly identify areas with arable land potential on new remote sensing images, providing solid data support for land planning and management.

[0026] 2. Enhanced Dynamic Adjustment and Adaptability of Arable Land Potential Analysis: The automated analysis method proposed in this invention exhibits significant dynamic adjustment and adaptability. When a mismatch is found between the current land use status of a second potential arable land parcel and the land survey data, the system can automatically adjust the screening rules to ensure the accuracy of subsequent analyses. This flexibility and adaptability are key to improving the robustness of the automated analysis method, helping to cope with the rapid and complex nature of land use changes and ensuring that the results of arable land potential analysis always reflect the latest land conditions.

[0027] 3. Automating the Entire Process of Arable Land Potential Analysis: This invention automates the entire process from data acquisition, processing, and analysis to report generation, significantly improving the efficiency of arable land potential assessment. By integrating key data and analysis results through automated tools, detailed and professional arable land potential analysis reports are generated. This automated report generation method not only saves significant manpower and time but also ensures information consistency and comparability through standardized report formats and content. The automated analysis report provides decision-makers with a comprehensive and accurate land resource assessment tool, helping to optimize land resource allocation and promote regional sustainable development. Attached Figure Description

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0029] Figure 1 This is a flowchart illustrating an automated analysis method for regional arable land potential according to an embodiment of the present invention.

[0030] Figure 2 This is a flowchart illustrating another automated analysis method for regional arable land potential according to an embodiment of the present invention.

[0031] Figure 3 This is a schematic diagram of the architecture of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0032] The terminology used in the following embodiments of the present invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the invention, the singular expressions “a,” “an,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in the invention refers to any or all possible combinations comprising one or more of the listed items.

[0033] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of the present invention, unless otherwise stated, "a plurality of" means two or more.

[0034] It should also be noted that, unless otherwise explicitly specified and limited, the terms "setting" and "connection" in the embodiments of the present invention should be interpreted broadly. 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 a connection within two components; it can be a wired communication connection or a wireless communication connection. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances. The embodiments of the present invention will be described in detail below.

[0035] This invention provides an automated method for analyzing regional arable land potential. Through an automated analysis process, it improves the efficiency and accuracy of regional arable land potential assessment. This embodiment employs a first and second screening rule for automated screening, enabling rapid processing of large amounts of land data, reducing human interference, and ensuring the consistency and reliability of the analysis results. Furthermore, this embodiment, through refined screening rules, can more accurately identify land parcels with arable land potential, which helps optimize land resource allocation and improve land use efficiency. Through two screening processes, this embodiment can exclude areas unsuitable or impossible to convert into arable land, thereby ensuring clearer objectives for arable land development projects and more rational resource allocation. This provides strong technical support for land planning and management, and has significant social, economic, and environmental benefits.

[0036] The automated regional arable land potential analysis method in this embodiment can be executed by electronic devices to reduce the workload of manual operation. For example... Figure 1 As shown, the method includes the following steps:

[0037] Step 101: Obtain the land information layer of the target area.

[0038] The land information layer comprises multiple land parcels representing different land use conditions. In Geographic Information Systems (GIS), the land information layer is a digital data layer used to represent specific information about the Earth's surface. It contains detailed attributes and spatial information of land within a target area, such as land use type, ownership, and soil type, and is typically composed of multiple land parcels. A land parcel is a land area unit with the same attributes within the land information layer. Each parcel represents a certain area of ​​land and can be distinguished by its shape, size, and location. The collection of land parcels constitutes the land information layer, used for land management and planning analysis.

[0039] This step involves collecting and integrating spatial data from various sources, including using GIS technology to extract information such as land use status, land ownership, soil type, and topographic features from remote sensing satellite imagery, aerial photography, ground surveys, and historical maps. Then, GIS software is used for data processing and patch classification, ultimately generating a land information layer for the target area containing multiple patches with different land use statuses. This process may also require collaboration with local land management departments to ensure the accuracy and up-to-dateness of the data.

[0040] Step 102: Based on the current land use status of the map patches, identify multiple non-arable map patches in the land information layer. Non-arable map patches include map patches whose current land use status is non-arable land.

[0041] The process of identifying multiple non-arable land parcels within a land information layer typically involves a detailed analysis and classification of the land use status of each parcel within the layer. First, the land information layer is loaded using GIS software. This layer contains rich attribute data, such as land use type, topographic features, and soil type. Next, the attribute query function is used to filter out parcels whose current land use status is marked as non-arable land. These non-arable land parcels may include wasteland, forest land, grassland, water bodies, and construction land. In GIS, this step can be automated by setting query parameters and using logical expressions; for example, selecting all parcels whose land use type attribute is not equal to "arable land".

[0042] Furthermore, remote sensing imagery and field survey data can be combined to verify and correct the boundaries, shapes, and features of land parcels, ensuring the accuracy of non-arable land parcels. Ultimately, all identified and verified non-arable land parcels will be individually labeled and classified, providing a foundational dataset for subsequent arable land potential analysis. This process not only improves the efficiency of land parcel identification but also provides reliable decision support for land planning and management through accurate parcel classification.

[0043] Step 103: Based on the preset first screening rule, select the first potential cultivated land plots from the non-cultivated land plots.

[0044] Among them, the first screening rule can adopt a positive screening rule, and the positive screening conditions may include, but are not limited to: setting an implementation period, having carried out urban and rural construction land increase-decrease linkage, having carried out the "Three Optimizations and Three Protections" (i.e. optimizing urban and rural land use structure, optimizing agricultural land use structure, optimizing construction land use structure, protecting arable land, protecting the ecological environment, and ensuring food security) improvement projects, and having carried out land consolidation projects.

[0045] This step first involves setting a clear implementation period, which defines the timeframe for converting land parcels into arable land, ensuring that the selected parcels comply with recent land use planning and development plans. Next, using the GIS system and land management database, parcels that have previously participated in urban-rural construction land linkage projects are identified. These parcels typically already possess certain infrastructure and development conditions, making them more suitable for arable land development. Furthermore, parcels that have already implemented "three optimizations and three protections" improvement projects are selected; these areas have often undergone planning and improvement, making them easier to convert into arable land. Finally, parcels that have undergone land consolidation are considered; the land conditions of these parcels have been improved, making them more suitable for agricultural cultivation.

[0046] By combining these conditions, it is possible to effectively screen out the first potential arable land plots with high arable land potential from non-arable land plots, providing a scientific basis for further land development and utilization.

[0047] Step 104: Based on the preset second screening rule, select the second potential cultivated land patch from the first potential cultivated land patch.

[0048] The second screening rule can adopt a reverse screening rule. The reverse screening conditions may include, but are not limited to: planned as existing construction land, and land use type as unused land (water area, pond, etc.).

[0049] Specifically, the first step is to exclude map features already designated as existing construction land in urban planning. These areas are typically planned for urban development, such as residential, commercial, or industrial zones, and are therefore unsuitable for conversion into arable land. Additionally, map features classified as unused land, such as water bodies and natural wetlands like ponds, need to be excluded. These areas, due to their unique ecological functions and environmental value, are unsuitable for arable land development. Using GIS spatial analysis tools, the first set of potential arable land features are compared and analyzed with the urban planning layer and the current land use layer. This automatically identifies and excludes map features that do not meet the conditions for arable land development, ultimately yielding the second set of potential arable land features.

[0050] This step is crucial in ensuring the practicality and feasibility of the arable land potential analysis results. By eliminating unsuitable areas for development, we can optimize the allocation of land resources, avoid unnecessary damage to the ecological environment, and ensure that arable land development projects can proceed smoothly to meet the needs of agricultural production and food security.

[0051] In some embodiments, the first screening rule may also be a reverse screening rule, which excludes some patches from the non-cultivated patches based on the reverse screening conditions, leaving the first potential cultivated patches. The second screening rule may also be a forward screening rule, which retains some patches from the first potential cultivated patches as the second potential cultivated patches based on the forward screening conditions.

[0052] Step 105: Generate a farmland potential layer based on the second potential farmland patches.

[0053] The arable land potential layer is used to analyze the arable land potential of the target area. After the above screening process, the step of generating the arable land potential layer involves spatial integration and visualization of the potential arable land patches that have passed the second screening.

[0054] First, using Geographic Information System (GIS) software, the selected potential second-tier arable land parcels are merged and classified according to their spatial location and attributes, ensuring that the boundaries of each parcel are clear and the attribute information is accurate. Next, based on the arable land potential indicators of each parcel, such as soil quality, proximity to water sources, and terrain suitability, a potential score or classification level is assigned to each parcel. These indicators can be derived through expert scoring, historical data analysis, or prediction using machine learning models.

[0055] Then, create a new layer in the GIS, namely the arable land potential layer, and input and display these land parcels and their potential scores or classification levels as the layer's attribute information.

[0056] In addition, different visual symbols or color codes can be set to intuitively represent the arable land potential levels of different plots, so that the arable land potential layer is clearly visible on the map, which facilitates analysis and decision-making.

[0057] The resulting arable land potential layer not only visually displays areas with different arable land potential within the target region, but also provides scientific and accurate spatial data support for land planning, resource management, and policy formulation.

[0058] This invention provides an automated analysis process for rapidly and accurately assessing regional arable land potential. Based on Geographic Information System (GIS) technology, this automated process first integrates land information layers for the target area. Then, using first and second filtering rules, it automatically identifies non-arable land parcels with the potential to be converted into arable land, excluding areas unsuitable for conversion due to planned use, ecological protection requirements, or other restrictions. Finally, it automatically generates an arable land potential layer using GIS technology, visually displaying areas with different arable land potentials, providing a scientific basis for land planning and decision-making. The method in this embodiment is highly automated, reducing manual intervention, improving the efficiency and accuracy of regional arable land potential analysis, and ensuring the rational utilization and effective management of arable land resources.

[0059] The following is combined with Figure 2 The following steps will be further introduced to further illustrate the automated analysis method for regional arable land potential implemented in this paper:

[0060] Step 201: Obtain the land information layer of the target area.

[0061] This step is the same as step 101, and will not be repeated here.

[0062] Step 202: Based on the current land use status of the map patches, determine multiple non-arable map patches in the land information layer. Non-arable map patches include map patches whose current land use status is non-arable land.

[0063] This step is the same as step 102, and will not be repeated here.

[0064] Step 203: Based on the preset first screening rule, select the first potential cultivated land plots from the non-cultivated land plots.

[0065] This step is the same as step 103, and will not be repeated here.

[0066] Step 204: Based on the preset second screening rules, select the second potential cultivated land patches from the first potential cultivated land patches.

[0067] This step is the same as step 104, and will not be repeated here.

[0068] Step 205: Obtain land survey data.

[0069] Land survey data, obtained through systematic investigation and measurement of land resources, records detailed information such as location, type, area, ownership, and utilization status. Land survey data can originate from the Second National Land Survey or the Third National Land Survey, providing an authoritative and comprehensive perspective for assessing the current state and historical changes of land. Integrating this data ensures the accuracy of analysis and the scientific nature of land resource management. Obtaining this data typically involves collaborating with land management departments in the target area, utilizing their databases and survey results, or employing modern technologies such as remote sensing and field surveys to acquire the latest land information.

[0070] Step 206: Verify the current land use status of the second potential arable land parcel based on land survey data to determine whether the second potential arable land parcel is feasible to be converted into arable land.

[0071] This step is the process of detailed verification of the second potential arable land parcels in this invention. In this step, the current land use status of the second potential arable land parcels that have passed the initial screening is verified using the acquired land survey data. This verification process is crucial because it ensures that the selected parcels truly possess the potential and feasibility to be converted into arable land.

[0072] Specifically, by comparing detailed information from land survey data, the current land use type, land conditions, and development restrictions of land parcels can be verified, thereby assessing their potential for conversion into arable land. For example, if a land parcel is marked as a protected wetland in the land survey data, it is not suitable for conversion into arable land. This verification step eliminates unsuitable or infeasible land parcels, ensuring that the final identified arable land potential parcels are 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.

[0073] In some embodiments, if the current land use status of a second potential cultivated land parcel does not match the land survey data, the first screening rule and / or the second screening rule are adjusted.

[0074] If a discrepancy is found between the current land use status of a second potential cultivated land parcel and the land survey data, it may indicate that the existing screening rules have failed to accurately reflect the actual land conditions or that land use has changed. To improve the accuracy and adaptability of the analysis, appropriate adjustments need to be made to the first and / or second screening rules.

[0075] The adjustment process first involves a detailed analysis of mismatched patches to identify the causes of the mismatch, such as data update delays, land use changes, or improper screening rule settings. Then, based on the analysis results, specific parameters or conditions in the screening rules are optimized, such as adjusting the screening criteria for land use types, updating soil quality evaluation indicators, and redefining the scope of topographic suitability.

[0076] Furthermore, 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. This dynamic adjustment mechanism ensures that the screening rules remain consistent with land survey data, thereby improving the accuracy and reliability of arable land potential analysis. This process embodies the innovation of this embodiment in automated analysis methods: by continuously iterating and optimizing the screening rules to adapt to dynamic changes in land use, the effectiveness and practicality of the analysis results are ensured.

[0077] After adjusting the first and / or second filtering rules, return to step 203 or step 204 to filter the image patches again.

[0078] If the current land use status of the second potential arable land parcel matches the land survey data, then proceed to step 207.

[0079] Step 207: Input the remote sensing image of the target area into the preset farmland potential prediction model to obtain the farmland potential prediction result.

[0080] Remote sensing imagery of the target area is used as key input data to drive a pre-defined arable land potential prediction model, thereby obtaining accurate arable land potential prediction results. The remote sensing imagery consists of high spatiotemporal resolution images containing rich surface feature information, such as vegetation cover, land use type, and topographic relief, all of which are important indicators for assessing arable land potential.

[0081] First, key features such as land cover type, vegetation index, and soil moisture of the target area are extracted using remote sensing image processing technology. Then, this feature data is input into a pre-defined arable land potential prediction model. This model employs advanced statistical or machine learning algorithms, such as regression analysis, random forests, or support vector machines, to analyze and learn from the input feature data to identify and predict areas with arable land development potential. After training, the model can automatically process and analyze new remote sensing image data, quickly outputting arable land potential prediction results. These results are displayed in the form of map layers, intuitively identifying areas with different arable land potential levels, providing scientific and intuitive decision support for land planning and resource management. Through this method, the present invention achieves rapid and accurate assessment of regional arable land potential, significantly improving the efficiency and effectiveness of land resource management.

[0082] In some embodiments, this step may specifically include:

[0083] First, the arable land potential prediction model is used to mark areas with arable land potential on remote sensing images of the target area; then, the remote sensing images of the marked areas with arable land potential are used as the arable land potential prediction results.

[0084] In embodiments of the present invention, the application of the arable land potential prediction model marks a key step in automated analysis methods. The arable land potential prediction model is specifically designed to process and analyze remote sensing images of target areas to identify and mark areas with arable land potential.

[0085] The first step involves inputting high-resolution remote sensing imagery of the target area into the arable land potential prediction model. This model integrates various spatial analysis techniques and algorithms, enabling in-depth analysis of remote sensing data to extract features related to arable land potential, such as soil fertility, accessibility to water resources, and terrain suitability. Through a comprehensive evaluation of these features, the model can automatically identify areas on the remote sensing imagery that meet the conditions for conversion to arable land and mark these areas with specific colors or symbols. The marked areas visually demonstrate the spatial distribution of arable land potential, providing a clear map of candidate areas for arable land development.

[0086] Subsequently, these remote sensing images, processed by the model and labeled with areas of arable land potential, are integrated and output as arable land potential prediction results. These results are presented as map layers, detailing the location, extent, and potential level of each potential arable land area. Such predictions not only provide a scientific basis for land planning and management but also, through intuitive visualization, enable decision-makers to quickly understand and assess the feasibility and priority of arable land development, thereby making more informed land use decisions. This automated prediction process significantly improves the efficiency and accuracy of arable land potential analysis, providing strong technical support for the rational development and sustainable management of land resources.

[0087] In some embodiments, the training process for the arable land potential prediction model includes:

[0088] (1) Acquire multiple remote sensing image data.

[0089] Training a farmland potential prediction model first requires acquiring multiple remote sensing image datasets. These datasets, typically sourced from satellite sensors or aerial photography, provide information on land cover and land use in the target area at different points in time. These images contain rich spatial information, such as vegetation indices, land cover types, and topographic features, forming the foundation for farmland potential analysis. Acquiring this data necessitates coordinating multiple data sources, including government-released remote sensing data, shared data from research institutions, and commercial remote sensing data providers, ensuring data diversity and coverage to meet the model's training requirements.

[0090] (2) Mark the areas that are already cultivated land, the non-cultivated land that is feasible to become cultivated land, and the non-cultivated land that is not feasible to become cultivated land in multiple remote sensing image data to obtain the training dataset.

[0091] Specifically, the process begins with loading high-resolution remote sensing imagery using specialized Geographic Information System (GIS) software. This imagery typically includes multispectral data, revealing detailed surface features. Next, analysts with expertise in land use and feature identification manually map and label areas already designated as arable land based on the imagery's spectral characteristics, texture, shape, and contextual information. These areas usually exhibit regular field shapes and clear crop growth characteristics. Subsequently, experts further identify and label non-arable land areas with potential for conversion to arable land, such as currently unused land with suitable soil and topographical conditions. Additionally, non-arable land areas lacking arable land potential, such as urban built-up areas, ecological reserves, or areas with steep terrain, must also be labeled.

[0092] Once all these annotation tasks are completed, a training dataset is formed containing positive samples (existing arable land), potential positive samples (non-arable land with potential), and negative samples (non-arable land without potential), providing accurate samples and labels for training machine learning models. This process ensures the quality and diversity of the training dataset, which is crucial for improving the accuracy of arable land potential prediction models.

[0093] (3) The selected machine learning model is trained using the training dataset to obtain the trained farmland potential prediction model.

[0094] The process of training a selected machine learning model using a training dataset to obtain a trained model for predicting arable land potential first involves importing the prepared training dataset into the machine learning algorithm. These training datasets contain samples of labeled arable land, potential arable land, and non-arable land areas, each sample accompanied by a corresponding label indicating its land use type.

[0095] Next, using supervised learning methods, the machine learning model analyzes the features and corresponding labels of these samples during the training phase, learning how to distinguish different types of land use areas based on the features of remote sensing imagery. During this process, the model's parameters are continuously optimized through algorithms to minimize the difference between the predicted results and the actual labels. Commonly used optimization algorithms include gradient descent and stochastic gradient descent, which help the model achieve high accuracy after multiple iterations of training.

[0096] In addition, to prevent overfitting, techniques such as cross-validation and regularization may be used to improve the model's generalization ability.

[0097] Ultimately, the fully trained model can accurately identify areas with arable land potential from new remote sensing images, thus obtaining an efficient and accurate arable land potential prediction model, providing strong technical support for land planning and management.

[0098] Step 208: Generate a farmland potential layer based on the farmland potential prediction results and the second potential farmland patch.

[0099] Specifically, remote sensing image data is first loaded using Geographic Information System (GIS) software. This data has been analyzed by a pre-set arable land potential prediction model, and areas with high potential to be converted into arable land identified by the model are clearly marked on the image.

[0100] Subsequently, these predictions were spatially overlaid with second potential arable land parcels identified through an automated screening process to ensure consistency in geographical location and attribute characteristics. In GIS, each matching parcel was assigned corresponding attributes, such as arable land potential score, soil quality, and water source proximity, reflecting the likelihood and suitability of each parcel to be converted into arable land.

[0101] Next, based on these attributes, a visual representation of the plots is designed, such as different colors or patterns, to intuitively show the level of arable land potential.

[0102] Finally, these map patches and their attributes are integrated into a new GIS layer to form a farmland potential layer. This layer not only visually displays the spatial distribution of potential farmland within the target area, but also records the farmland potential information of each map patch in detail, providing scientific and accurate decision support for land planning and resource management.

[0103] Step 209: Based on the arable land potential layer, generate an arable land potential analysis report for the target area.

[0104] Specifically, the first step is to use the automation functions of GIS software to directly extract key spatial data and attribute information from the arable land potential layer. A series of analyses can be automatically executed through preset scripts, including calculating the total area of ​​high-potential arable land regions, identifying areas of concentrated arable land, and assessing the correlation between arable land potential and existing infrastructure.

[0105] Subsequently, these analytical results are used by an automated report generation tool (automated script) in conjunction 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 conclusions and recommendations. In addition, the automated script also automatically generates charts and maps to visually display the spatial distribution and key indicators of arable land potential.

[0106] Ultimately, all text, charts, and maps are automatically compiled into a complete analysis report based on a pre-set 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 analysis report on arable land potential.

[0107] In this embodiment, creating an automated script to generate a farmland potential analysis report first requires clarifying the report's structure and content requirements. Then, a suitable programming language and automation tools must be selected, such as Python combined with ArcGIS's ArcPy library or QGIS's PyQGIS plugin. Script writing begins by defining the data extraction logic, including querying the attributes and spatial information of the farmland potential layer from the GIS database. Next, the script should include automated spatial analysis processes, such as calculating the farmland potential index and identifying high-potential areas.

[0108] Subsequently, data processing and visualization libraries (such as Matplotlib or Plotly) are used to automatically generate charts and maps. In addition, the automation scripts need to integrate a text generation module, which may use template filling or NLP (Natural Language Processing) techniques to transform the analysis results into natural language descriptions.

[0109] Finally, the script should include report generation and formatting features, such as automatically formatting text, charts, and maps using the Jinja2 template engine or LaTeX to generate reports in PDF or Word document format.

[0110] 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 the high-quality output of the report.

[0111] This invention provides an automated method for analyzing regional arable land potential, aiming to improve the efficiency and accuracy of arable land potential assessment through automation technology. The method involves a series of steps, starting with acquiring a land information layer containing multiple land parcels with different land use statuses. Next, multiple non-arable land parcels are identified, whose current land use status is non-arable land. Using a preset first screening rule, first potential arable land parcels with the potential to become arable land are selected from the non-arable land parcels. Subsequently, using a second screening rule, second potential arable land parcels are further selected from the first potential arable land parcels; these parcels are more likely to be converted into arable land.

[0112] Following the screening process, land survey data is acquired, and the land use status of the second potential arable land parcels is verified to confirm their feasibility for conversion to arable land. If a mismatch is found between the current land use status and the land survey data, the method also includes adjusting the first and / or second screening rules to ensure the accuracy of the screening process.

[0113] Furthermore, this embodiment utilizes remote sensing imagery and a pre-defined arable land potential prediction model to predict the arable land potential of a target area. The model marks areas with arable land potential on the remote sensing imagery and integrates this information into an arable land potential layer. The training process of this prediction model involves acquiring multiple remote sensing image datasets and marking areas that are already arable land, non-arable land areas with the potential to become arable land, and non-arable land areas without the potential to become arable land, forming a training dataset. A selected machine learning model is trained using these datasets to obtain the trained arable land potential prediction model.

[0114] Finally, based on the generated arable land potential layer, this embodiment automatically generates an arable land potential analysis report for the target area. The report details the distribution of arable land potential, the characteristics of potential areas, and development recommendations, providing decision-makers with scientific and intuitive decision support, helping to optimize land resource allocation and promote regional sustainable development.

[0115] Overall, the technical solution in this embodiment automates the entire process from data acquisition, processing, and analysis to report generation through automated workflows and advanced analytical techniques. This significantly improves the efficiency of arable land potential assessment while ensuring the scientific validity and accuracy of the analysis results. This method allows for more effective identification and utilization of potential arable land resources, providing strong technical support for land planning and management.

[0116] The methods provided in the above embodiments can be executed by an electronic device. The electronic device in the embodiments of the present invention is described below from a hardware processing perspective; please refer to [link to relevant documentation]. Figure 3 This is a schematic diagram of the physical device structure of an electronic device in an embodiment of the present invention.

[0117] It should be noted that, Figure 3 The structure of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0118] like Figure 3As shown, the electronic device includes a Central Processing Unit (CPU) 401, which can perform various appropriate actions and processes based on a program stored in Read-Only Memory (ROM) 402 or a program loaded from storage portion 408 into Random Access Memory (RAM) 403, such as performing the methods described in the above embodiments. The RAM 403 also stores various programs and data required for system operation. The CPU 401, ROM 402, and RAM 403 are interconnected via a bus 404. An Input / Output (I / O) interface 405 is also connected to the bus 404.

[0119] The following components are connected to I / O interface 405: input section 406 including audio input devices, push-button switches, etc.; output section 407 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 408 including a hard disk, etc.; and communication section 409 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 409 performs communication processing via a network such as the Internet. Drive 410 is also connected to I / O interface 405 as needed. Removable media 411, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 410 as needed so that computer programs read from them can be installed into storage section 408 as needed.

[0120] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 409, and / or installed from removable medium 411. When the computer program is executed by central processing unit (CPU) 401, it performs the various functions defined in the present invention.

[0121] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0122] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, program segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0123] Specifically, the electronic device of this embodiment includes a processor and a memory. The memory is coupled to one or more processors and is used to store computer program code. The computer program code includes computer instructions. One or more processors call the computer instructions to cause the electronic device to perform the method provided in the above embodiment.

[0124] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The storage medium carries one or more computer programs that, when executed by a processor of the electronic device, cause the electronic device to implement the methods provided in the above embodiments.

[0125] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0126] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0127] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. An automated method for analyzing regional arable land potential, characterized in that, include: Obtain a land information layer for the target area, wherein the land information layer includes multiple patches with different land use statuses; Based on the current land use status of the map patches, multiple non-arable map patches are determined in the land information layer, including map patches whose current land use status is non-arable land; Based on a preset first screening rule, a first potential cultivated land patch is selected from the non-cultivated land patches; Based on the preset second screening rule, a second potential cultivated land patch is selected from the first potential cultivated land patch; Obtain land survey data; verify the land use status of the second potential arable land parcel based on the land survey data to determine whether the second potential arable land parcel is feasible to be converted into arable land; if the land use status of the second potential arable land parcel does not match the land survey data, adjust the first screening rule and / or the second screening rule. The process of generating a farmland potential layer based on the second potential farmland patch specifically includes: inputting the remote sensing image of the target area into a preset farmland potential prediction model to obtain farmland potential prediction results; A farmland potential layer is generated based on the farmland potential prediction results and the second potential farmland patch; the farmland potential layer is used to analyze the farmland potential of the target area.

2. The method according to claim 1, characterized in that, The step of inputting the remote sensing image of the target area into a preset arable land potential prediction model to obtain arable land potential prediction results includes: The farmland potential prediction model is used to mark areas with farmland potential on remote sensing images of the target area. Remote sensing images that indicate areas with arable land potential are used as the results of arable land potential prediction.

3. The method according to claim 1, characterized in that, The training process of the arable land potential prediction model includes: Acquire multiple remote sensing image data; In the multiple remote sensing image data, areas that are already cultivated land, non-cultivated land that has the potential to become cultivated land, and... The training dataset is obtained from non-arable land areas that are not feasible to be converted into arable land. The selected machine learning model is trained using the training dataset to obtain a trained arable land potential prediction model.

4. The method according to any one of claims 1-3, characterized in that, After the step of generating a arable land potential layer based on the second potential arable land patch, the method further includes: Based on the arable land potential layer, generate an arable land potential analysis report for the target area.

5. An electronic device, characterized in that, Includes one or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in any one of claims 1-4.

6. A computer-readable storage medium storing computer instructions, characterized in that, When the computer instructions are executed on the electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-4.

7. A computer program product, characterized in that, When the computer program product is run on an electronic device, it causes the electronic device to perform the method as described in any one of claims 1-4.

Images