A method and system for quickly dividing inland shorelines

Abstract

The application discloses a kind of inland river bank line quick division method and system, method includes: according to the land use type in national investigation data, in combination with bank line ecological function and human disturbance characteristics, generate bank line classification rule system;Based on bank line classification rule system, extract river water area range and the land use type map spot of immediate water area from national investigation data, form the basic data layer to be divided;Through GIS model builder concatenation buffer analysis, cutting, erasing, attribute screening and element conversion center line tool, construct river bank line automatic classification and extraction model, output the bank line segment data divided according to type;Bank line segment data is input into bank line merging model and is connected and merged processing, generates the complete inland river bank line achievement data.Using the embodiment of the application, the objectivity, efficiency and spatial continuity of the achievement data of the inland river bank line division can be improved, to provide accurate and reliable data support for land space planning and river and lake ecological protection.

Description

Technical Field

[0001] This invention belongs to the field of surveying and mapping technology, and in particular to a method and system for rapid delineation of inland river shorelines. Background Technology

[0002] Inland river shorelines are crucial areas where water and land meet, serving multiple functions including ecological protection, resource development, and spatial control. With the deepening of territorial spatial planning and river and lake management, the refined survey and classified management of inland river shoreline resources has become an urgent need. Currently, shoreline delineation mainly relies on manual visual interpretation or simple extraction based on a single land use type. This is not only inefficient and highly subjective, but also fails to comprehensively consider multi-dimensional characteristics such as ecological functions and human disturbance. While there have been attempts to extract shorelines using Geographic Information Systems (GIS), these are mostly limited to basic spatial analysis operations, lacking a systematic classification rule system and automated processing flow. This results in deficiencies in shoreline delineation results regarding type definition, spatial continuity, and data consistency, making it difficult to meet the practical needs of refined and dynamic management of shoreline resources in the new era of territorial spatial planning. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for rapid delineation of inland river shorelines, which addresses the shortcomings of existing technologies and improves the objectivity, efficiency, and spatial continuity of the delineation results, providing accurate and reliable data support for land spatial planning and river and lake ecological protection.

[0004] One embodiment of this application provides a method for rapid delineation of inland river shorelines, the method comprising: Based on the land use types in the national land survey data, and combined with the ecological functions and human disturbance characteristics of the shoreline, the inland river shoreline is divided into three categories: natural shoreline, semi-natural shoreline and artificial shoreline, thus generating a shoreline classification rule system. Based on the aforementioned shoreline classification rule system, the river water area and adjacent land use type patches are extracted from the land survey data to form a basic data layer to be divided. By using a GIS model builder to perform buffer analysis, clipping, erasing, attribute filtering, and feature-to-centerline conversion tools, an automatic classification and extraction model for river shorelines is constructed. The basic data layer is iteratively processed to output shoreline segment data classified by type. The shoreline segment data is input into the shoreline merging model for connection and merging processing to generate complete inland river shoreline result data.

[0005] Another embodiment of this application provides a rapid inland river shoreline delineation system, the system comprising: The classification module is used to divide inland river shorelines into three categories—natural shorelines, semi-natural shorelines, and artificial shorelines—based on land use types in national land survey data and in combination with shoreline ecological functions and human disturbance characteristics, thereby generating a shoreline classification rule system. The extraction module is used to extract the river water area and the land use type patches adjacent to the water area from the land survey data based on the shoreline classification rule system, forming a basic data layer to be divided. The construction module is used to construct an automatic classification and extraction model of river shoreline by using the GIS model builder to connect buffer analysis, clipping, erasing, attribute filtering and feature-to-centerline tools, iterate the basic data layer, and output shoreline segment data divided by type. The processing module is used to input the shoreline segment data into the shoreline merging model for connection and merging processing, and generate complete inland river shoreline result data.

[0006] Another embodiment of this application provides a storage medium storing a computer program, wherein the computer program is configured to execute the method described in any of the preceding claims when running.

[0007] Another embodiment of this application provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the method described in any of the preceding claims.

[0008] Compared with existing technologies, the present invention provides a method for rapid delineation of inland river shorelines, which can improve the objectivity, efficiency and spatial continuity of the delineation results, and provide accurate and reliable data support for land spatial planning and river and lake ecological protection. Attached Figure Description

[0009] Figure 1 Hardware structure block diagram of a computer terminal for a method of rapid delineation of inland river shorelines provided in an embodiment of the present invention; Figure 2 A flowchart illustrating a method for rapid delineation of inland river shorelines provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a rapid inland river shoreline delineation system provided in an embodiment of the present invention. Detailed Implementation

[0010] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0011] This invention first provides a method for rapid delineation of inland river shorelines, which can be applied to electronic devices, such as computer terminals, specifically ordinary computers.

[0012] The following detailed explanation uses a computer terminal as an example. Figure 1 This is a hardware structure block diagram of a computer terminal for a method of rapid delineation of inland river shorelines provided in an embodiment of the present invention. (See diagram below.) Figure 1 As shown, the computer device includes a processor, memory, and network interface connected via a system bus, wherein the memory may include non-volatile storage media and internal memory.

[0013] See Figure 2 The present invention provides a method for rapid delineation of inland river shorelines, which may include the following steps: S201, based on land use types in the national land survey data and combined with shoreline ecological functions and human disturbance characteristics, divides inland river shorelines into three categories: natural shorelines, semi-natural shorelines, and artificial shorelines, generating a shoreline classification rule system; Specifically, land use data from the national land survey can be obtained for the study area. This data includes land use code and land use name fields to distinguish land use types and generate the original national land survey dataset. Obtain land use parcel data from the national land survey for the study area. This data includes land use code and land use name fields to distinguish land use types, and generate the original national land survey dataset.

[0014] The core of this step is to acquire standardized and structured basic land survey data within the study area, providing accurate land use type basis for subsequent shoreline classification rules, and ensuring the integrity and validity of the data attributes. The specific implementation method is as follows: Land use parcel data from the national land survey are vector data reflecting the land use types, distribution, and boundaries of the study area. They are the core output of the national land survey. The core attribute fields are land use code and land use name. The land use code is a numeric code that adopts a hierarchical coding rule. The number of digits in the code is set according to the national land survey classification standards, which can accurately distinguish different levels of land use types. The land use name is a textual description that corresponds one-to-one with the land use code, forming a standardized land use type identification system. Together, they serve as the sole basis for distinguishing land use types, avoiding errors caused by identifying a single field.

[0015] The acquisition process uses the administrative boundaries or river basins of the study area as the defining criteria, retrieving the latest land use vector data from the corresponding national land survey. Simultaneously, the data undergoes multi-dimensional verification. First, attribute integrity is verified, eliminating invalid patches with missing land use codes or names. Second, topological consistency is verified, correcting topological errors such as overlapping, broken, and self-intersecting patch boundaries. Third, coordinate system uniformity is verified, converting all data to the commonly used geographic coordinate system of the study area to ensure spatial accuracy. Finally, the verified patches are merged into smaller patches, with smaller patches smaller than a preset threshold of 50 square meters merging into adjacent dominant land use type patches to prevent them from affecting the accuracy of subsequent shoreline classification.

[0016] The study area in this example is the central area of ​​the Three Gorges Reservoir in Chongqing. The data obtained is the land use map data from the 2024 national land survey in this area, with a scale of 1:10000. After verification, more than 100,000 valid map patches were retained. The land use code is a 6-digit code, and the land use name covers more than 100 land use types, including forest land, grassland, cultivated land, and industrial and mining land. All verified vector map patch data were cropped according to the watershed boundary of the study area, retaining only the land use map patches within the reservoir area. Finally, it was integrated into a structured original national land survey dataset containing core attributes such as map patch geometric information, land use code, and land use name. The dataset is in a GIS-recognizable vector layer format and can be directly used for subsequent land use type matching and analysis.

[0017] Based on the ecological function and human disturbance characteristics of the shoreline, the basic principles for shoreline classification are determined. Land use types in a relatively natural state are classified as natural shorelines, land use types mainly used for agricultural production and protective greening are classified as semi-natural shorelines, and land use types whose surfaces are hardened due to human construction activities are classified as artificial shorelines, thus generating a shoreline type classification framework. Based on the ecological functions and human disturbance characteristics of shorelines, the basic principles for shoreline classification are determined. Land use types in a relatively natural state are classified as natural shorelines, land use types mainly used for agricultural production and protective greening are classified as semi-natural shorelines, and land use types whose surfaces have been hardened by human construction activities are classified as artificial shorelines, thus generating a shoreline type classification framework.

[0018] The core of this step is to establish the core basis and basic principles for shoreline classification, and to construct a hierarchical classification framework to provide a unified judgment standard for the accurate matching of subsequent land use types and shoreline categories. The specific implementation method is as follows: The core basis for shoreline classification is ecological function and anthropogenic disturbance characteristics. Ecological function reflects the supporting role of the shoreline in the river and lake ecosystem, mainly including natural ecological service functions such as soil and water conservation, biological habitat, and water purification. The more complete the function, the stronger the natural attributes of the shoreline. Anthropogenic disturbance characteristics reflect the degree of change of the original natural state of the shoreline by human activities. According to the degree of disturbance, it is divided into three levels: no obvious disturbance, slight disturbance, and severe disturbance. The disturbance level is positively correlated with the intensity of human intervention and negatively correlated with the natural attributes of the shoreline.

[0019] Based on two core criteria, the basic principles for classifying shorelines into three categories are established. Natural shorelines are defined as those where the land use type has not been altered by artificial construction, maintaining its original natural form, with minimal human disturbance, intact and unweakened river and lake ecological functions, and capable of fully utilizing natural ecological services such as soil and water conservation and biological habitat. Semi-natural shorelines are defined as those affected by minor human production activities, without altering the natural attributes of the shoreline base, with minor human disturbance, primarily serving agricultural production and ecological protection / greening, with undamaged ecological functions and the possibility of natural restoration through artificial disturbance. Artificial shorelines are defined as those heavily altered by human engineering construction activities, with the shoreline surface hardened, subject to severe human disturbance, significantly weakened natural ecological functions, and primarily serving human production, daily life, engineering construction, and transportation.

[0020] The classification criteria, judgment principles, disturbance levels, and core functions of the three types of shorelines are linked and integrated to form a clearly hierarchical shoreline type classification framework. This framework consists of three levels: the core criteria layer, the judgment principle layer, and the type characteristic layer. The core criteria layer clarifies the core position of ecological functions and human disturbance characteristics; the judgment principle layer defines the specific judgment criteria for each type of shoreline; and the type characteristic layer summarizes the core attribute characteristics of each type of shoreline. The three levels are interconnected and logically unified, providing clear and implementable judgment criteria for subsequent matching of land use types and shoreline categories.

[0021] Based on the shoreline type classification framework, and in accordance with the land use type classification system in the national land survey data, the shoreline category to which each type of land use belongs is clarified one by one. This includes classifying forest land, grassland and wetland as natural shorelines, cultivated land, orchards and ditches as semi-natural shorelines, and industrial and mining land, residential land and hydraulic structures as artificial shorelines. A table of correspondence between land use type and shoreline category is generated. Based on the shoreline type classification framework and in accordance with the land use type classification system in the national land survey data, the shoreline category to which each type of land use belongs is clarified one by one. This includes classifying forest land, grassland and wetlands as natural shorelines, cultivated land, orchards and ditches as semi-natural shorelines, and industrial and mining land, residential land and hydraulic structures as artificial shorelines. A table of correspondence between land use type and shoreline category is generated.

[0022] The core of this step is to accurately match the land use types from the national land survey with the shoreline types, establishing a one-to-one correspondence. This provides the key basis for subsequent automated shoreline delineation attribute selection. The specific implementation method is as follows: First, we sorted out all land use types in the national land survey data, strictly adhering to the land use classification system of the national land survey. We divided the land use types into primary and secondary categories. The primary category is a broad category, including forest land, grassland, cultivated land, commercial and service land, and industrial and mining land. The secondary category is a detailed breakdown of the primary category. For example, the primary category of forest land includes secondary categories such as arbor forest land, shrub forest land, and other forest land. The primary category of grassland includes secondary categories such as natural pasture, artificial pasture, and other grassland. The hierarchical division is consistent with the national land survey classification standards to ensure the standardization of land use type sorting.

[0023] Subsequently, based on the judgment principles and characteristic definitions in the shoreline type classification framework, each type of land use was judged one by one. The judgment process adopted the "core indicator-led method", which takes the level of human disturbance and ecological function of land use type as the core judgment indicators. If the dominant characteristics of land use type meet the judgment principles of a certain type of shoreline, it is directly classified into the corresponding shoreline category without considering secondary characteristics. In the example, land use types such as arbor forests, shrub forests, natural pastures, and marshes and wetlands have no significant human construction intervention, and the level of human disturbance is no significant disturbance. Their ecological functions are intact, and they are directly classified as natural shorelines. Land use types such as paddy fields, dry land, orchards, tea gardens, rural roads, ditches, and facility agricultural land are mainly used for agricultural production or ecological protection and greening. They are only subject to light human production activities, and the level of human disturbance is light disturbance. They are classified as semi-natural shorelines. Land use types such as commercial service land, urban residential land, industrial land, mining land, highway land, and hydraulic engineering land have undergone artificial hardening and construction, and the level of human disturbance is heavy disturbance. Their natural ecological functions are weakened, and they are classified as artificial shorelines.

[0024] For a small number of land use types with overlapping characteristics, supplementary determinations are made based on their actual use functions in the riverbank area. For example, although parks and green spaces have undergone artificial planning intervention, their core function is ecological protection and greening, and they have not changed the natural attributes of the shoreline base; therefore, they are classified as semi-natural shorelines. All determined land use types are matched one by one according to the primary category code, primary category name, secondary category code, secondary category name, land category code, land category name, and the shoreline category to which they belong. This is integrated into a structured table of correspondence between land use types and shoreline categories. All information in the table completely matches the attribute fields of the land survey data, ensuring accurate identification and no mismatches or omissions when the GIS model performs attribute screening in the subsequent process.

[0025] By integrating the shoreline type classification framework and the correspondence table between land use type and shoreline category, a complete document containing classification rule descriptions and land use type mapping relationships is formed, ultimately generating a shoreline classification rule system.

[0026] By integrating the shoreline type classification framework and the correspondence table between land use type and shoreline category, a complete document containing classification rule descriptions and land use type mapping relationships is formed, ultimately generating a shoreline classification rule system.

[0027] The core of this step is to systematically integrate the framework principles of shoreline classification with the matching relationship of land use types, forming a standardized, executable, and implementable classification rule system. This provides a unified standard for manual shoreline determination and a core rule basis for subsequent automated GIS model construction. The specific implementation method is as follows: First, the text of the shoreline type classification framework is standardized and streamlined. The core basis, judgment principle, disturbance level and type characteristics in the framework are standardized and expressed in a hierarchical classification rule description text. The text is clear, well-defined and free of ambiguous words, which ensures that the rules in the subsequent model construction can be quantified and transformed into screening conditions for machine recognition, while also meeting the readability requirements for manual review and judgment.

[0028] Subsequently, the correspondence table between land use type and shoreline category is digitized. The land use code, land use name and shoreline category in the table are mapped one-to-one to form an attribute matching code library that can be recognized by the GIS model. The code library uses the land use code as the unique search key and associates it with the corresponding shoreline category identifier. For example, natural shoreline is identified by Z, semi-natural shoreline by B, and artificial shoreline by R. This enables the GIS model to quickly identify land use type and match shoreline category, while retaining the correspondence between land use type and shoreline category in textual description form, achieving dual adaptation for machine recognition and manual consultation.

[0029] Next, the standardized classification rule description text was integrated with the digitized land use type mapping relationship. At the same time, three supplementary contents were added: the scope of application of the rules, data accuracy requirements, and explanations for the determination of special land use types. The scope of application of the rules is clearly defined as the delineation of inland river shorelines, excluding other types of shorelines such as marine shorelines. The data accuracy requirements are consistent with the accuracy of the land survey data, at a scale of 1:10000, to ensure that the accuracy of shoreline delineation matches the basic data. The explanations for the determination of special land use types provide a detailed explanation of the determination basis and attribution principles for a small number of land use types with overlapping characteristics in the river riparian zone, so as to avoid disputes in subsequent delineation.

[0030] Finally, the integrated classification rules description, land use type mapping relationship, supplementary explanations, and shoreline type division framework are systematically arranged to form a complete structured document. The document is divided into four parts: general rules, core classification rules, land use type mapping relationship, and supplementary explanations. The contents of each part are interconnected and interdependent. The general rules clarify the purpose and scope of application of shoreline classification, the core classification rules define the specific judgment criteria for the three types of shorelines, the land use type mapping relationship provides a precise basis for land use type matching, and the supplementary explanations solve the judgment problems of special cases. Finally, a shoreline classification rule system that can directly guide the construction of GIS models and the practical work of shoreline division is generated. This system ensures the standardization, normalization, and consistency of the entire inland river shoreline division work.

[0031] S202, Based on the shoreline classification rule system, extract the river water area and the land use type patches adjacent to the water area from the land survey data to form the basic data layer to be divided; Specifically, water body land features such as river surfaces, lake surfaces, reservoir surfaces, and pond surfaces can be extracted from the land survey dataset to generate a river water area map. The core of this step is to accurately select relevant water features of inland rivers from standardized land survey data to form a basic water feature layer that defines the scope of shoreline delineation, providing a spatial benchmark for subsequent delineation of shoreline impact areas. The specific implementation method is as follows: The extraction operation uses land use codes and names from the national land survey dataset as the core filtering criteria. These two fields are standardized attributes of the national land survey data, uniquely identifying the land use type of water bodies and avoiding omissions or misselections due to single-field identification. In GIS software, the attribute-based selection tool is used to construct a multi-condition joint filtering expression, filtering all patches whose land use names match river, lake, reservoir, and pond surfaces. Simultaneously, double verification is performed using the water body-specific land use code to ensure the accuracy of the filtering results. After filtering, the water body patches undergo data cleaning. First, small water body patches with an area less than 100 square meters are removed. This threshold is set according to the minimum water body identification standard for inland rivers to avoid small water body elements interfering with the spatial scope of subsequent shoreline delineation. Second, topological errors in the patches are corrected by merging and repairing water body patches with overlapping, broken, or self-intersecting boundaries to ensure the spatial continuity of water body elements. Finally, the filtered and cleaned water body patches are merged, integrating scattered patches from the same river or reservoir into continuous areal elements, eliminating patch fragmentation caused by manual segmentation.

[0032] The study area in this example is the central area of ​​the Three Gorges Reservoir in Chongqing. From the original land survey dataset of the reservoir area, the water features of the main stream of the Yangtze River, the tributaries of the Jialing River and their affiliated reservoirs and lakes within the reservoir area were extracted through dual screening using land category names and codes. After cleaning and fusion, more than 200 small and fragmented pond features were removed, and 15 topological faults were corrected. The final generated river water area layer is a continuous planar vector layer that accurately covers all inland river water areas in the reservoir area and completely defines the water reference range for shoreline delineation.

[0033] Perform buffer analysis on the river water area layer, set an appropriate distance to generate the shoreline influence area adjacent to the water area, and generate the river buffer layer; The core of this step is to use GIS buffer analysis technology to generate a fixed-width polygonal region around the water area layer, accurately defining the research scope of the shoreline adjacent to the water area, and providing spatial boundaries for subsequent extraction of land use types around the shoreline. The specific implementation method is as follows: Buffer analysis is one of the core technologies of GIS spatial analysis. Its principle is to generate an outer polygonal region of a specified width around a planar water feature. This region represents the core influence area of ​​the shoreline. The buffer distance is determined comprehensively based on the ecological influence range of inland riverbanks, shoreline control standards in national land spatial planning, and practical survey experience. For inland river main streams, the buffer distance is set at 50 meters, and for tributaries, it is set at 30 meters. This parameter can be dynamically adjusted according to river classification and watershed ecological characteristics. The 50-meter and 30-meter distance standards can completely cover the shoreline land area adjacent to the water area, avoiding both overly narrow distances that might miss shoreline features and overly wide distances that might introduce irrelevant land use types. In GIS software, the buffer analysis tool is called, using the river water area layer as the input feature. Buffer distances of 50 meters and 30 meters are set according to river classification. The buffer type is set to outer buffer, generating buffers only outside the water features and excluding invalid space within the water area. The fusion type is set to merge all adjacent buffers, eliminating overlapping buffers at river branches and water area connections, forming a continuous and seamless shoreline influence area.

[0034] After the buffer analysis is completed, the generated preliminary buffer layer undergoes spatial verification to check whether the buffer completely matches the water area layer and whether there are any issues such as boundary offsets or omissions. For buffers covering large water areas such as reservoirs and lakes, edge smoothing is performed to avoid excessive polylines that could cause errors in subsequent clipping analysis. In the example, buffer analysis is performed on the river water area layer in the heart of the Three Gorges Reservoir area. Outer buffers are generated at 50-meter intervals for the main stream and 30-meter intervals for tributaries. After merging adjacent overlapping areas, the generated river buffer layer forms a continuous polygonal spatial range, completely covering the adjacent shoreline areas of all rivers in the reservoir area, thus defining precise spatial boundaries for subsequent land use type extraction.

[0035] The original land use map data from the national land survey was overlaid with the river buffer layer using a cropping tool. All land use type maps located within the buffer zone were extracted to generate a land use type map layer adjacent to the water area. The core of this step is to extract land use type elements within the shoreline influence area from the nationwide land survey data through GIS clipping and overlay analysis, focusing on the core research object of shoreline delineation. The specific implementation method is as follows: The core principle of clipping and overlay analysis is to use the river buffer layer as a clipping template to spatially clip the original land use type data from the national land survey, retaining only the land use type patches within the template range. Simultaneously, it fully preserves all attribute information of the patches, including land use type codes and names, providing attribute basis for subsequent shoreline type classification. Before operation, it is necessary to ensure that the spatial coordinate system of the original land use type data from the national land survey is consistent with that of the river buffer layer to avoid clipping deviations caused by coordinate system differences. In the GIS software, the clipping tool is invoked, with the original land use type data from the national land survey set as the input feature and the river buffer layer set as the clipping feature. The output feature is set to retain all attribute fields of the input feature, ensuring that the extracted patches can still be identified by land use type codes and names.

[0036] After cropping, the extracted land use type patches undergo post-processing optimization. First, small patches with an area of ​​less than 50 square meters are removed. This threshold is set based on the smallest identification unit of shoreline land use types to avoid small patches interfering with subsequent automatic shoreline classification. Second, adjacent patches with the same land use type are fused to reduce the number of patches and improve the efficiency of subsequent model processing. Finally, the extracted patches undergo attribute verification to remove invalid patches lacking key attributes such as land use codes and names, ensuring that all retained patch attributes are complete and valid. In the example, the river buffer layer of the Three Gorges Reservoir area is used to crop the original land use patch data from the reservoir area's land survey, extracting patches with land use types such as forest land, grassland, cultivated land, industrial and mining land, and hydraulic engineering construction land within the buffer zone. After post-processing, more than 300 small patches are removed, and 120 groups of adjacent patches with the same land use type are merged. The final generated land use type patch layer adjacent to the water area accurately reflects the spatial distribution of land use types around the reservoir shoreline and is the core data for subsequent shoreline type classification.

[0037] The river water area layer is integrated with the land use type patch layer adjacent to the water area, and the coordinate system and data format are unified to finally generate the basic data layer to be divided.

[0038] The core of this step is to standardize and integrate the two types of core layers, eliminating spatial and format differences, and forming a basic data layer with a unified structure and spatial matching. This provides standardized input for the iterative processing of the subsequent shoreline automatic classification and extraction model. The specific implementation method is as follows: First, a unified calibration of the coordinate system is performed. The coordinate system is the core benchmark for geospatial data. Differences in coordinate systems between different layers can lead to spatial location shifts. Therefore, the river and water area layer and the land use type patch layer adjacent to the water area are uniformly converted to the 2000 National Geodetic Coordinate System. This coordinate system is my country's current national basic geospatial coordinate system, suitable for land spatial planning, geographic information data processing, and other related work. It ensures accurate spatial matching between the two types of layers, without offset or misalignment. High-precision geographic projection transformation parameters are used during the coordinate transformation process to ensure that the spatial accuracy of the transformed layers is not reduced, meeting the accuracy requirements for shoreline delineation.

[0039] Secondly, the data format was standardized by converting both types of layers to SHP vector data format. This format is a common vector data format in the GIS field, with strong compatibility and support for all analysis tools in GIS model builders. It can be directly used for subsequent automated model processing. At the same time, this format can completely preserve the geometric and attribute information of features, ensuring that no data information is lost during shoreline delineation. After the format conversion, the two types of layers were loaded into the same GIS data framework, and spatial matching was checked to confirm that the land use type patch layer adjacent to the water area was completely located within the river buffer layer and corresponded one-to-one with the spatial position of the river water area layer, without spatial overlap, offset, or omission issues.

[0040] Finally, the integrated layers undergo overall attribute and spatial validation. This involves checking the completeness of fields such as water area type and river name in the river / water area layer, and the validity of fields such as land use code and name in the land use type mosaic layer adjacent to the water area. Simultaneously, the topological consistency of the two types of layers is checked to ensure there are no issues such as broken or overlapping elements. The two types of layers, after integration and validation, form a unified GIS data layer set, which serves as the basic data layer to be divided. This layer contains two core elements: water area and adjacent land use type. Spatial location is accurately matched, attribute information is complete and valid, and data format and coordinate system are standardized. It can be directly input into subsequent automatic river shoreline classification and extraction models for iterative processing.

[0041] S203, through the GIS model builder, a river shoreline automatic classification and extraction model is constructed by using a series of buffer analysis, clipping, erasing, attribute filtering and feature-to-centerline tools. The basic data layer is iteratively processed to output shoreline segment data divided by type. Specifically, you can create a new model in ArcGIS Pro Model Builder, and then add the Buffer Analysis tool to generate the river buffer area, the Clipping tool to extract the polygons within the buffer, and the Eraser tool to remove duplicate or irrelevant features to generate the basic framework of the model. The core of this step is to build a basic workflow framework for shoreline classification and extraction based on professional GIS modeling tools. By connecting core spatial analysis tools, it achieves automated data processing, laying the workflow foundation for subsequent shoreline type screening and extraction. The specific implementation method is as follows: ArcGIS Pro Model Builder is a visual GIS modeling tool that automates spatial analysis workflows by dragging and dropping tools and setting input / output relationships between them, eliminating the need for manual step-by-step tool operations. First, create a new blank model in the tool, named "Automatic Classification and Extraction Model of River Shoreline." Set the model's workspace to the geographic data storage path of the study area, and unify the output data format of all tools within the model to SHP vector format to ensure data compatibility and consistency in subsequent processing.

[0042] Add three core spatial analysis tools—buffer analysis, clipping, and erasure—to the blank model in sequence. Establish a chain relationship between the tools according to the data processing logic. The output elements of the previous tool are directly used as the input elements of the next tool, forming a standardized processing flow. The input elements for the buffer analysis tool are set to the river water area layer in the base data layer to be divided. The buffer distance is set differently according to the river level: 50 meters for inland river main streams and 30 meters for tributaries. This parameter is determined based on the ecological impact range of inland river riparian zones and shoreline survey specifications. The buffer type is set to outer single buffer, generating a buffer area only outside the water area boundary to avoid including the internal space of the water area. The input elements for the clipping tool are set to the land use type patch layer adjacent to the water area in the base data layer to be divided. The clipping element is the river buffer area output by the buffer analysis tool. After running the tool, it will extract all land use type patches within the buffer, achieving accurate definition of the shoreline research scope. The input elements for the erase tool are the land use patches within the buffer output by the clipping tool. The erase element is set to the river water area layer, and the erase threshold is set to 50 square meters. After running the tool, it will erase the features of the water area itself and small, duplicate patches with an area of ​​less than 50 square meters, eliminating irrelevant features that interfere with subsequent shoreline classification.

[0043] The example builds a basic framework for a model based on the unclassified foundational data layers of the Three Gorges Reservoir area in Chongqing. A buffer analysis tool generates river buffer zones within the reservoir area, with a 50-meter interval for the main stream and a 30-meter interval for tributaries. A cropping tool extracts over 80,000 land use type patches within the buffer zones, and an erasing tool further removes water features and over 2,000 fragmented patches, ultimately outputting clean and effective foundational patches for shoreline classification. After setting the parameters for all tools, the input-output relationships between the tools are saved, forming an automatically executable basic framework for the river shoreline classification and extraction model. The tools within this framework run sequentially according to predetermined logic, without any manual intervention or breakpoints.

[0044] Add an attribute selection tool to the basic model framework. Based on the correspondence table between land use type and shoreline category in the shoreline classification rule system, set selection conditions to filter land use type patches corresponding to natural shoreline, semi-natural shoreline and artificial shoreline, and generate intermediate layers distinguished by category. The core of this step is based on standardized shoreline classification rules. By filtering attributes, it achieves accurate separation of different types of shorelines from the applied map patches. This is the core of automatic shoreline classification, and the specific implementation method is as follows: A selection tool by attribute is added after the eraser tool in the basic model framework. This tool can construct filtering conditions based on the attribute fields of features to achieve accurate extraction of features with specified attributes. To achieve the classification and filtering of three types of shorelines, three selection tools by attribute are added in parallel at the output of the eraser tool, respectively corresponding to the filtering needs of natural shorelines, semi-natural shorelines, and artificial shorelines. The filtering conditions of each selection tool are constructed based on the correspondence table between land use type and shoreline category in the shoreline classification rule system. Using land use code and land use name as dual filtering fields, a multi-condition joint filtering expression is constructed, and the filtering logic relationship is set to "OR" to ensure that all land use type patches corresponding to the shoreline type can be completely extracted.

[0045] For natural shorelines, the attribute selection tool uses a filtering condition that matches the land use code to the exclusive codes of forest land, grassland, and wetland, or that the land use name contains the keywords "forest land," "grassland," or "wetland," ensuring that all land use patches in a relatively natural state are selected. For semi-natural shorelines, the attribute selection tool uses a filtering condition that matches the land use code to the exclusive codes of cultivated land, plantation land, rural roads, and ditches, or that the land use name contains the keywords "cultivated land," "plantation land," "ditch," or "rural road," extracting land use patches mainly used for agricultural production and protective greening. For artificial shorelines, the attribute selection tool uses a filtering condition that matches the land use code to the exclusive codes of industrial and mining land, residential land, and hydraulic engineering land, or that the land use name contains the keywords "industrial and mining," "residential," "hydraulic engineering," or "highway," extracting land use patches whose surfaces have hardened due to human construction activities.

[0046] After setting the filtering criteria, three attribute-based selection tools were run. Each tool output a vector layer containing only map patches of the corresponding shoreline type. These three layers are independent and have no overlapping features, collectively forming an intermediate layer for shoreline classification by category. The layers fully preserve the core attributes of the original map patches, such as land use codes, land use names, and spatial coordinates, providing complete data support for subsequent shoreline feature extraction and attribute assignment. In the example, for map patches within the buffer zone of the Three Gorges Reservoir area, the three attribute-based selection tools respectively filtered out 42,000 natural shoreline map patches, 35,000 semi-natural shoreline map patches, and 3,000 artificial shoreline map patches, accurately achieving the classification and separation of the three types of shorelines for the application map patches.

[0047] Add a feature-to-centerline tool after the intermediate layer categorized by type to convert the polygonal patches into centerline features representing the shoreline location. Also add field addition and field calculation tools to assign corresponding type attributes to each shoreline segment and generate preliminary shoreline segment data categorized by type. The core of this step is to convert the area-like land use patches into linear shoreline centerline features, while assigning standardized shoreline type attributes to the linear features, thus realizing the transformation of the shoreline from land use type to spatial entity. The specific implementation method is as follows: Add a feature-to-centerline tool after each of the three categorized intermediate layers. This tool converts polygonal vector features into linear centerline features that match their geometry, perfectly capturing the physical characteristics of shorelines as linear spaces at the boundary between land and water. The input features for the feature-to-centerline tool are set to the corresponding intermediate layers, and the tool parameters are set to retain all attribute fields of the input features. The geometric precision of the centerline is set to 0.5 meters to ensure that the converted linear features accurately match the spatial position of the original polygonal patches and closely align with the geographical boundaries of the actual shoreline. After running the tool, the original polygonal patches will be converted into linear centerline features. The three types of shorelines correspond to three linear feature layers, and the spatial orientation of the centerlines reflects the distribution orientation of the actual shorelines.

[0048] After each feature is converted to a centerline, a field addition tool and a field calculation tool are added sequentially to standardize the assignment of shoreline type attributes. The input feature for the field addition tool is the converted linear centerline layer. A new field is created and named "Shoreline Type," with the field type set to text and the field length set to 20, sufficient to accommodate the text descriptions of "Natural Shoreline," "Semi-Natural Shoreline," and "Artificial Shoreline." An additional "Land Use Origin" field can be created as needed to record the original land use type corresponding to the shoreline. The input feature for the field calculation tool is the linear layer after adding the new field. A fixed value is assigned to the "Shoreline Type" field for different layer categories: the centerline layer of a natural shoreline is assigned "Natural Shoreline," the centerline layer of a semi-natural shoreline is assigned "Semi-Natural Shoreline," and the centerline layer of an artificial shoreline is assigned "Artificial Shoreline." The assignment process is automated batch processing, eliminating the need for manual editing of each feature individually.

[0049] After attribute assignment, the three types of linear centerline feature layers with clear "shoreline type" attributes constitute the preliminary data for shoreline segments categorized by type. This data retains the attribute information of the original map patches and their precise spatial locations after conversion, while also possessing standardized shoreline type identifiers, achieving a precise association between shoreline type and spatial entities. In the example, the three types of areal map patches in the Three Gorges Reservoir area, after being converted using the feature-to-centerline tool, generate three types of linear features: natural shoreline, semi-natural shoreline, and artificial shoreline. After assignment using the field calculation tool, all shoreline segments have clear type identifiers and can be directly used for subsequent merging and analysis.

[0050] Set the model iteration parameters so that the model can automatically traverse and process multiple river segments or study areas, and finally output shoreline segment data divided by type.

[0051] The core of this step is to add iterative processing capabilities to the model, enabling automated shoreline classification and extraction across large scales, multiple regions, and multiple river segments. This avoids the tedious manual processing of each shoreline individually, improving the model's applicability and processing efficiency. The specific implementation method is as follows: Enable the iterator function in the model builder, select "Iterate by Feature" as the iteration type, and set the iteration feature to the river segment feature in the base data layer to be divided. This feature is divided according to the river name and watershed segment in the study area. Each iteration unit is a river or a river segment, and the iteration fields are set to "River Name" and "Segment Code" to ensure that the model can achieve accurate automated traversal processing by river and segment. Set the model's iteration output rules, naming the output data of each iteration unit in the format of "Shoreline Type_River Name_Segment Code" to achieve standardized management of output data and facilitate subsequent querying and integration.

[0052] Simultaneously, batch processing parameters for the model are set, specifying the unified output path of the model as the storage folder for shoreline results in the study area, and unifying the output data format as SHP vector format, preserving all geometric and attribute information of linear features; a fault tolerance mechanism for the model is set, so that when there are abnormal situations such as missing data or empty features in a certain river segment or study area, the model will automatically skip the iteration unit, and record the abnormal information in the model operation log to ensure that the abnormality of a single iteration unit will not affect the operation of the entire model, thus ensuring the stability of batch processing.

[0053] Furthermore, the model's running parameters are set to "automatic background operation." After the model starts, it will automatically traverse all river segments or study areas in iteration order, sequentially performing buffer analysis, trimming, erasing, attribute filtering, feature conversion to centerline, and attribute assignment, without manual intervention. After the model runs, it will generate shoreline segment data categorized by type in the specified output path. The data is divided into three types of linear vector layers: natural shoreline, semi-natural shoreline, and artificial shoreline. Each layer contains shoreline segment features of all rivers or segments within the study area. The attribute information of the features includes shoreline type, original land use code, land use name, river to which it belongs, segment code, etc. The spatial location is accurate, and the attribute information is complete, which can be directly used for subsequent shoreline merging and result analysis. The example uses a basic data layer for the core area of ​​the Three Gorges Reservoir, which includes 12 rivers such as the main stream of the Yangtze River, tributaries of the Jialing River and tributaries of the Wujiang River, and 36 segments. After setting the iteration parameters, the model automatically completes the shoreline classification and extraction for the entire reservoir area, and finally outputs three types of shoreline segment data, which contain more than 12,000 linear shoreline segment elements. The entire process is done without human intervention, and the processing efficiency is more than 90% higher than manual segment-by-segment processing.

[0054] S204, Input the shoreline segment data into the shoreline merging model for connection and merging processing to generate complete inland river shoreline result data.

[0055] Specifically, you can create a new shoreline merging model in ArcGIS Pro Model Builder and add a merge tool to stitch together shoreline segment data divided by type to generate preliminary merged shoreline data. The core of this step is to build a specialized shoreline merging model using a GIS model builder. This model uses merging tools to integrate the three types of shoreline segment data, consolidating scattered shoreline segment elements into a unified shoreline data set. This lays the foundation for subsequent topology correction and attribute refinement. The specific implementation method is as follows: First, create a new blank model in ArcGIS Pro Model Builder, named "Shoreline Merging Model." Set the model's workspace to be consistent with the previous automatic river shoreline classification and extraction model to ensure data consistency. Simultaneously, unify the model's output data format to SHP vector format to balance GIS data compatibility and universality, facilitating subsequent accuracy verification and application of results. Add the GIS Core merge tool to the newly created blank model. This tool can seamlessly stitch and merge multiple vector line feature layers of the same type, fully preserving the geometric and attribute information of each feature without data loss or deviation due to stitching.

[0056] The input elements for the merging tool are set to three categories of shoreline segment data: natural shoreline, semi-natural shoreline, and artificial shoreline, output by the automatic river shoreline classification and extraction model. All three types of data are standardized linear vector elements, meeting the input requirements of the merging tool. The merging rule is set to "retain all element attributes," meaning the merged shoreline data fully retains the original shoreline type, land use code, land use origin, and other attribute fields for each segment, ensuring that shoreline type identification is not confused during merging. When the merging tool runs, it automatically identifies the spatial relationships of the three types of shoreline segment data and splices them according to their actual geographical distribution, forming an integrated dataset containing all shoreline segments within the study area. This dataset is the preliminary merged shoreline data, containing all types of shoreline elements and fully retaining all attribute information assigned during the initial processing.

[0057] The example demonstrates the merging of three types of shoreline data from the Three Gorges Reservoir area in Chongqing: natural shoreline, semi-natural shoreline, and artificial shoreline. These three types of data contain a total of 12,000 linear shoreline segment elements. After being spliced ​​and merged by the merging tool, the resulting preliminary merged shoreline data fully preserves the geometric shape and attribute information of all shoreline segments, achieving integrated integration of shoreline data in the reservoir area without any loss of elements or confusion of attributes.

[0058] After the initial merging of shoreline data, a spatial connectivity tool is added to check the connectivity and topological consistency between shoreline segments, handle possible breaks or overlaps, and generate topologically corrected shoreline data. The core of this step is to use spatial connectivity tools to perform topological verification and correction of shoreline data, resolving topological issues such as breaks, overlaps, and hanging points caused by automatic extraction of shoreline segments. This ensures the spatial continuity and topological integrity of the shoreline data, aligning with the actual geographical distribution characteristics of inland river shorelines. The specific implementation method is as follows: In the shoreline merging model, a spatial connection tool is added to the output of the merging tool. This tool can analyze the topological relationships between features through spatial location correlation analysis, and also supports automatic correction of topological errors. It is a core tool for ensuring the spatial integrity of GIS vector data. First, the topology verification parameters of the spatial connection tool are set, with the topology tolerance set to 0.5 meters. This parameter represents the allowable spatial deviation distance between shoreline segments. The 0.5-meter threshold is set based on the accuracy standards of land survey data and shoreline extraction. This effectively identifies minor topological deviations caused by data processing without incorrectly connecting geographically disconnected shorelines.

[0059] The spatial connectivity tool will perform a comprehensive topological consistency check on the initially merged shoreline data according to the set topological tolerance, focusing on identifying three common topological problems: 1) shoreline segment breaks, where shoreline segments of the same river have slight gaps due to spatial deviations, failing to form a continuous line; 2) shoreline segment overlaps, where different shoreline segments overlap spatially; and 3) shoreline overhangs, where the endpoints of shoreline segments are not connected by other features and exceed a reasonable geographical range. For the identified topological problems, the tool will automatically correct them according to preset rules. For shoreline segment breaks with gaps smaller than the topological tolerance, it will automatically connect the endpoints to form a continuous shoreline; for spatially overlapping shoreline segments, it will automatically delete duplicate features, retaining only a single valid shoreline; and for shoreline overhangs exceeding a reasonable range, it will automatically trim them to a reasonable position at the river's water boundary.

[0060] Meanwhile, the spatial connectivity tool retains an operation log for topology correction, recording the number of corrected shoreline segments, the type and location of topology issues, facilitating subsequent manual review. After processing by the tool, shoreline data that originally had topological flaws will achieve spatial continuity, non-overlapping, and no hanging points, generating topology-corrected shoreline data. In the example, topology verification and correction were performed on the initially merged shoreline data of the Three Gorges Reservoir area. The tool identified 82 shoreline segment breaks, 15 shoreline segment overlaps, and 9 shoreline hanging points. After automated correction, all topology issues were resolved, and the generated topology-corrected shoreline data perfectly matches the actual geographical distribution of the rivers in the reservoir area, achieving a spatially continuous representation of the shoreline.

[0061] Add field calculation tools to the topology-corrected shoreline data to supplement attribute information including at least shoreline length and the name of the river to which it belongs, and generate shoreline result data with complete attributes; The core of this step is to supplement the topologically corrected shoreline data with key attribute information through field addition and calculation tools, achieving dual completeness of the shoreline data's geometric and attribute characteristics. This meets the practical needs of shoreline resource surveys, statistical analysis, and planning management. The specific implementation method is as follows: In the shoreline merging model, a field addition tool and a field calculation tool are added sequentially to the output of the spatial connection tool. First, the field addition tool is used to create necessary attribute fields for the topologically corrected shoreline data. Then, the field calculation tool assigns precise numerical or textual information to the newly created fields. First, the field addition tool is run to create two core attribute fields: one is "Shoreline Length," with the field type set to floating-point and the numerical precision set to two decimal places. This precision meets the accuracy requirements for shoreline length statistics, and the unit is uniformly set to kilometers, conforming to the scale characteristics of inland river shorelines. The second is "Name of the River," with the field type set to text and the field length set to 50 characters, which can fully accommodate the full name of the river within the study area. Additionally, extended fields such as "Shoreline Segment Code" and "Watershed" can be created as needed to enrich the attribute information of the shoreline data.

[0062] After adding the fields, run the field calculation tool to automatically assign values ​​to the newly created fields. For the "Shoreline Length" field, call the geometric attribute calculation function of the GIS software to automatically calculate the actual geographical length of each linear shoreline segment based on its actual spatial coordinates. The value is output in kilometers with two decimal places to achieve accurate quantification of shoreline length. For the "River Name" field, spatial correlation analysis is used to assign values. The shoreline data is spatially matched with the previously extracted river water area layer. Based on the "River Name" attribute of the river water area element corresponding to the shoreline segment, the corresponding river name is automatically assigned to the shoreline segment, achieving accurate association between the shoreline and its river.

[0063] During field calculation, the tool batch processes all shoreline segments without requiring manual editing of each element. After assignment, the shoreline data will simultaneously contain complete attribute information such as geometric shape, shoreline type, land use origin, shoreline length, and the name of the river to which it belongs, generating shoreline result data with complete attributes. In the example, field supplementation and calculation were performed on the topologically corrected shoreline data of the Three Gorges Reservoir area, calculating the actual length of each of the 12,000 shoreline segments, accurately matching the names of 12 rivers including the Yangtze River main stream, tributaries of the Jialing River, and tributaries of the Wujiang River. The generated shoreline result data with complete attributes can be directly used for the classification, statistics, and spatial analysis of shoreline length in the reservoir area.

[0064] The accuracy of the shoreline data is verified and visualized by overlaying remote sensing images. Once the data is confirmed to be correct, the complete inland river shoreline data is output.

[0065] The core of this step is to verify the accuracy of the shoreline data by overlaying high-precision remote sensing images, while simultaneously visualizing the shoreline data to ensure the accuracy and rationality of shoreline delineation. The final output is standardized inland river shoreline data. The specific implementation method is as follows: First, high-precision remote sensing imagery of the study area was selected as the base map. The resolution of the remote sensing imagery was set to 0.5 meters, which clearly identifies the actual geographical boundaries of the inland river shoreline and the surrounding land use types. This resolution matches the accuracy standards of the land survey data and shoreline extraction, while ensuring that the acquisition time of the remote sensing imagery is consistent with the timeliness of the land survey data to avoid accuracy verification deviations caused by time differences. In ArcGIS Pro software, the high-precision remote sensing imagery was loaded as the base map layer, and then the shoreline data with complete attributes was overlaid on the remote sensing imagery layer to complete the spatial registration between the two. This ensures that the spatial location of the shoreline data perfectly matches the actual riverbank in the remote sensing imagery, without any spatial offset.

[0066] Subsequently, the accuracy of the shoreline data was verified using a dual verification method of visual interpretation and random sampling. First, visual interpretation was conducted to compare the actual riverbank in the remote sensing image with the shoreline in the data segment by segment to check the spatial accuracy and rationality of the shoreline division. Second, random sampling verification was performed, randomly selecting 5% of the shoreline segments from the data as verification samples. Combining remote sensing imagery with actual geographical features, the location accuracy and type classification accuracy of each sample shoreline were verified. A 95% accuracy threshold was set, meaning that the shoreline data was considered accurate when the accuracy of the sampling verification was not lower than 95%. If it was lower than this threshold, the data was returned to the shoreline merging model or classification extraction model for parameter adjustment and data correction until the accuracy met the standard.

[0067] While verifying accuracy, the data on shoreline results are visualized. Differentiated coloring is applied according to shoreline type: natural shorelines are set to green, semi-natural shorelines to yellow, and artificial shorelines to red. The color contrast is striking and can intuitively reflect the spatial distribution characteristics of different types of shorelines. At the same time, statistical charts of shoreline types are generated in GIS, and core statistical indicators such as the total length and proportion of each type of shoreline are automatically calculated, realizing the visualized expression and quantitative statistics of shoreline data.

[0068] After accuracy verification, the shoreline data is output in standardized formats, including SHP vector format and GDB geographic database format. SHP format is suitable for conventional GIS data processing and sharing, while GDB format is suitable for large-scale, high-volume shoreline data storage and management. Shoreline statistical charts, accuracy verification reports, and data are also exported together to form a complete inland river shoreline data package. In the example, shoreline data from the heart of the Three Gorges Reservoir area is overlaid with 0.5-meter resolution remote sensing imagery for accuracy verification. Visual interpretation revealed no significant deviations, and random sampling verification achieved an accuracy rate of 98.2%, far exceeding the 95% passing threshold. Subsequently, visualization was completed by color-coding by type, revealing that natural shoreline accounts for 96.37% of the reservoir area. Finally, inland river shoreline data in both SHP and GDB formats are output, providing accurate data support for ecological protection and restoration work in the reservoir area.

[0069] Another embodiment of the present invention provides a rapid inland river shoreline delineation system, see [link to relevant documentation]. Figure 3 The system may include: The classification module 301 is used to classify inland river shorelines into three categories—natural shorelines, semi-natural shorelines, and artificial shorelines—based on land use types in the national land survey data and in combination with shoreline ecological functions and human disturbance characteristics, thereby generating a shoreline classification rule system. Extraction module 302 is used to extract river water area range and adjacent water area land use type patches from land survey data based on the shoreline classification rule system to form a basic data layer to be divided; Module 303 is used to construct an automatic classification and extraction model of river shoreline by using the GIS model builder to connect buffer analysis, clipping, erasing, attribute filtering and feature-to-centerline tools, iteratively process the basic data layer, and output shoreline segment data divided by type. The processing module 304 is used to input the shoreline segment data into the shoreline merging model for connection and merging processing, and generate complete inland river shoreline result data.

[0070] This invention also provides a storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when running.

[0071] This invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0072] The above description, based on the embodiments shown in the figures, details the structure, features, and effects of the present invention. The above description is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the figures. Any changes made in accordance with the concept of the present invention, or equivalent embodiments modified to have equivalent changes, that do not exceed the spirit covered by the specification and figures, should be within the protection scope of the present invention.

Claims

1. A method for rapid delineation of inland river shorelines, characterized in that, The method includes: Based on the land use types in the national land survey data, and combined with the ecological functions and human disturbance characteristics of the shoreline, the inland river shoreline is divided into three categories: natural shoreline, semi-natural shoreline and artificial shoreline, thus generating a shoreline classification rule system. Based on the aforementioned shoreline classification rule system, the river water area and adjacent land use type patches are extracted from the land survey data to form a basic data layer to be divided. By using a GIS model builder to perform buffer analysis, clipping, erasing, attribute filtering, and feature-to-centerline conversion tools, an automatic classification and extraction model for river shorelines is constructed. The basic data layer is iteratively processed to output shoreline segment data classified by type. The shoreline segment data is input into the shoreline merging model for connection and merging processing to generate complete inland river shoreline result data.

2. The method according to claim 1, characterized in that, Based on land use types from national land survey data, and combined with shoreline ecological functions and human disturbance characteristics, inland river shorelines are divided into three categories: natural shorelines, semi-natural shorelines, and artificial shorelines. A shoreline classification rule system is generated, including: Obtain land use parcel data from the national land survey for the study area. This data includes land use code and land use name fields to distinguish land use types, and generate the original national land survey dataset. Based on the ecological function and human disturbance characteristics of the shoreline, the basic principles for shoreline classification are determined. Land use types in a relatively natural state are classified as natural shorelines, land use types mainly used for agricultural production and protective greening are classified as semi-natural shorelines, and land use types whose surfaces are hardened due to human construction activities are classified as artificial shorelines, thus generating a shoreline type classification framework. Based on the shoreline type classification framework, and in accordance with the land use type classification system in the national land survey data, the shoreline category to which each type of land use belongs is clarified one by one. This includes forest land, grassland, and wetland being classified as natural shorelines, cultivated land, orchards, and ditches being classified as semi-natural shorelines, and industrial and mining land, residential land, and hydraulic structures being classified as artificial shorelines. A table of correspondence between land use type and shoreline category is generated. By integrating the shoreline type classification framework and the correspondence table between land use type and shoreline category, a complete document containing classification rule descriptions and land use type mapping relationships is formed, ultimately generating a shoreline classification rule system.

3. The method according to claim 2, characterized in that, Based on the shoreline classification rule system, the river water area and adjacent land use type patches are extracted from the land survey data to form a basic data layer to be divided, including: Extract water body land feature patches such as river surface, lake surface, reservoir surface and pond surface from the land survey dataset to generate a river water area range layer; Perform buffer analysis on the river water area layer, set an appropriate distance to generate the shoreline influence area adjacent to the water area, and generate the river buffer layer; The original land use map data from the national land survey was overlaid with the river buffer layer using a cropping tool. All land use type maps located within the buffer zone were extracted to generate a land use type map layer adjacent to the water area. The river water area layer is integrated with the land use type patch layer adjacent to the water area, and the coordinate system and data format are unified to finally generate the basic data layer to be divided.

4. The method according to claim 3, characterized in that, The process involves using a GIS model builder to perform sequential buffer analysis, clipping, erasing, attribute filtering, and feature-to-centerline conversion tools to construct an automatic classification and extraction model for river shorelines. This model iteratively processes the base data layer, outputting shoreline segment data categorized by type, including: Create a new model in ArcGIS Pro Model Builder, and then add the Buffer Analysis tool to generate the river buffer area, the Clipping tool to extract the polygons within the buffer, and the Erasure tool to remove duplicate or irrelevant features to generate the basic framework of the model. Add an attribute selection tool to the basic model framework. Based on the correspondence table between land use type and shoreline category in the shoreline classification rule system, set selection conditions to filter land use type patches corresponding to natural shoreline, semi-natural shoreline and artificial shoreline, and generate intermediate layers distinguished by category. After the intermediate layers are categorized, add the feature-to-centerline tool to convert the polygonal patches into centerline features representing the shoreline locations. Then, use the field addition and field calculation tools to assign corresponding type attributes to each shoreline segment, generating preliminary shoreline segment data categorized by type. Set the model iteration parameters so that the model can automatically traverse and process multiple river segments or study areas, and finally output shoreline segment data divided by type.

5. The method according to claim 4, characterized in that, The process of inputting the shoreline segment data into the shoreline merging model for connection and merging processing to generate complete inland river shoreline result data includes: Create a new shoreline merging model in ArcGIS Pro Model Builder, and add a merge tool to stitch together shoreline segment data divided by type to generate preliminary merged shoreline data. After the initial merging of shoreline data, a spatial connectivity tool is added to check the connectivity and topological consistency between shoreline segments, handle possible breaks or overlaps, and generate topologically corrected shoreline data. Add field calculation tools to the topology-corrected shoreline data to supplement attribute information including at least shoreline length and the name of the river to which it belongs, and generate shoreline result data with complete attributes; The accuracy of the shoreline data is verified and visualized by overlaying remote sensing images. Once the data is confirmed to be correct, the complete inland river shoreline data is output.

6. A rapid inland river shoreline delineation system, characterized in that, The system includes: The classification module is used to divide inland river shorelines into three categories—natural shorelines, semi-natural shorelines, and artificial shorelines—based on land use types in national land survey data and in combination with shoreline ecological functions and human disturbance characteristics, thereby generating a shoreline classification rule system. The extraction module is used to extract the river water area and the land use type patches adjacent to the water area from the land survey data based on the shoreline classification rule system, forming a basic data layer to be divided. The construction module is used to construct an automatic classification and extraction model of river shoreline by using the GIS model builder to connect buffer analysis, clipping, erasing, attribute filtering and feature-to-centerline tools, iterate the basic data layer, and output shoreline segment data divided by type. The processing module is used to input the shoreline segment data into the shoreline merging model for connection and merging processing, and generate complete inland river shoreline result data.

7. The system according to claim 6, characterized in that, The partitioning module is specifically used for: Obtain land use parcel data from the national land survey for the study area. This data includes land use code and land use name fields to distinguish land use types, and generate the original national land survey dataset. Based on the ecological function and human disturbance characteristics of the shoreline, the basic principles for shoreline classification are determined. Land use types in a relatively natural state are classified as natural shorelines, land use types mainly used for agricultural production and protective greening are classified as semi-natural shorelines, and land use types whose surfaces are hardened due to human construction activities are classified as artificial shorelines, thus generating a shoreline type classification framework. Based on the shoreline type classification framework, and in accordance with the land use type classification system in the national land survey data, the shoreline category to which each type of land use belongs is clarified one by one. This includes forest land, grassland, and wetland being classified as natural shorelines, cultivated land, orchards, and ditches being classified as semi-natural shorelines, and industrial and mining land, residential land, and hydraulic structures being classified as artificial shorelines. A table of correspondence between land use type and shoreline category is generated. By integrating the shoreline type classification framework and the correspondence table between land use type and shoreline category, a complete document containing classification rule descriptions and land use type mapping relationships is formed, ultimately generating a shoreline classification rule system.

8. The system according to claim 7, characterized in that, The extraction module is specifically used for: Extract water body land feature patches such as river surface, lake surface, reservoir surface and pond surface from the land survey dataset to generate a river water area range layer; Perform buffer analysis on the river water area layer, set an appropriate distance to generate the shoreline influence area adjacent to the water area, and generate the river buffer layer; The original land use map data from the national land survey was overlaid with the river buffer layer using a cropping tool. All land use type maps located within the buffer zone were extracted to generate a land use type map layer adjacent to the water area. The river water area layer is integrated with the land use type patch layer adjacent to the water area, and the coordinate system and data format are unified to finally generate the basic data layer to be divided.

9. A storage medium, characterized in that, The storage medium stores a computer program, wherein the computer program is configured to execute the method of any one of claims 1-5 when it is run.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method of any one of claims 1-5.

Images