A river section form feature recognition method based on remote sensing

Abstract

The present application belongs to the technical field of river section feature recognition, and particularly relates to a river section morphological feature recognition method based on remote sensing. The present application realizes accurate recognition and dynamic monitoring of river morphological features through multi-source remote sensing data fusion analysis, improves the scientificity and efficiency of river management, and provides fine data support for river ecological restoration and management through the construction of river section classification and morphological modules, thereby supporting the intelligentization and dataization needs of river management decisions. Meanwhile, through time sequence analysis of the repair node and the current node, the effective prediction of the river morphological evolution trend is realized, and after the prediction result is output, the confidence is also checked and evaluated, thereby ensuring the reliability and applicability of the prediction result, so that the prediction result can provide corresponding data support for river regulation engineering, can predict the river morphological change trend in advance, and also provides a scientific basis for flood control and disaster reduction and water resource management.

Description

Technical Field

[0001] This invention belongs to the field of river channel and river section feature recognition technology, specifically relating to a method for recognizing the morphological features of river channels and river sections based on remote sensing. Background Technology

[0002] With the increasing demand for water resource management, people's management of rivers is becoming more refined. It is no longer limited to the overall characteristic analysis of rivers, but goes deeper into the identification of morphological features at the river section level. This is to achieve accurate grasp and scientific prediction of the evolution of rivers. Traditional methods of river morphological feature identification mostly rely on manual field measurement, which has problems such as large workload, long cycle and limited coverage. It is difficult to meet the needs of large-scale and high-frequency monitoring. However, with the rapid development of remote sensing technology, new means have been provided for the efficient identification of the morphological features of river sections. This can not only greatly improve the efficiency of data collection, but also effectively reduce labor costs. At the same time, it has strong spatiotemporal coverage capabilities, making dynamic monitoring of the river evolution process possible.

[0003] While some existing technologies exist for river feature identification based on remote sensing data, they generally suffer from insufficient precision in river segment division, incomplete extraction of morphological feature parameters, and inadequate ability to analyze dynamic trends. For example, some technologies simply divide the river into straight segments based on its geometric centerline without fully considering the actual curvature and morphological complexity of the river segment. This results in coarse river segment classification, making it difficult to accurately reflect the true evolution of the river. Furthermore, existing methods often limit the selection of morphological feature parameters to basic indicators such as width and length, lacking effective extraction of higher-order features such as topographic relief and slope changes. This restricts the understanding of the river evolution process, leading to low prediction accuracy and failing to meet the actual needs of river management and governance. Therefore, this paper proposes a remote sensing-based method for river segment morphological feature identification to address the aforementioned problems. Summary of the Invention

[0004] The purpose of this invention is to provide a method for identifying the morphological features of river sections based on remote sensing, which can effectively improve the precision of river section division and the comprehensiveness of morphological feature parameter extraction, thereby more accurately reflecting the evolution pattern of the river.

[0005] The specific technical solution adopted by this invention is as follows:

[0006] A method for identifying the morphological features of river sections based on remote sensing, comprising:

[0007] Acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data;

[0008] Collaborative preprocessing of multi-source remote sensing data yields a standardized remote sensing dataset;

[0009] Based on multi-source remote sensing data, the river boundary line and center line are extracted, and the river is divided into several river segments according to the curvature variation characteristics of the river center line.

[0010] The morphological feature parameters of each river segment are extracted, including the length, width, curvature and bank slope of the river segment. Then, the river segments are classified according to the morphological feature parameters to obtain multiple river segment types. River segments with the same type and adjacent river segments are merged to form a continuous river channel morphology module.

[0011] The restoration nodes of each river segment are obtained, and a sample collection period is constructed between the restoration node and the current node. The morphological feature parameters within the sample collection period are analyzed over time to identify the morphological feature change trend of each river segment. Based on the morphological feature change trend, the river channel morphological feature parameters under future nodes are predicted.

[0012] In a preferred embodiment, the step of acquiring multi-source remote sensing data of the target river channel includes:

[0013] Multiple monitoring points are pre-deployed along the riverbank. Each monitoring point includes acquisition equipment for collecting multi-source remote sensing data, including optical cameras, synthetic aperture radar antennas, and lidar scanners.

[0014] By periodically activating each acquisition device, optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data of the target river channel are acquired synchronously, and the initial remote sensing data is summarized.

[0015] Timestamps and geographic labels are added to the aggregated initial remote sensing data to form multi-source remote sensing data with spatiotemporal identifiers.

[0016] In a preferred embodiment, the step of collaborative preprocessing of multi-source remote sensing data includes:

[0017] Spatial reference unification is performed on optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data, and the optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are registered to a unified coordinate system.

[0018] Multi-temporal image overlay and band reconstruction of optical satellite imagery are used to restore the obscured areas;

[0019] Denoising and geometric correction are performed on synthetic aperture radar images;

[0020] Filtering and elevation normalization are performed on the lidar point cloud data;

[0021] Preprocessed optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are fused together to form a unified information layer, creating a standardized remote sensing dataset with a unified spatial reference.

[0022] In a preferred embodiment, the step of extracting the river boundary line and centerline based on multi-source remote sensing data, and dividing the river into several river segments according to the curvature variation characteristics of the river centerline, includes:

[0023] The river water mask is calculated based on the spectral characteristics of optical satellite imagery, and the boundary of the water mask is corrected by combining the microwave reflection characteristics of synthetic aperture radar imagery.

[0024] The topographic elevation information of the river channel is extracted using lidar point cloud data, and the riverbank is determined based on the slope changes;

[0025] The river boundary line is extracted by fusing information from the river water mask and the riverbank, and the river center line is extracted by combining the river boundary line with topographic elevation data.

[0026] The curvature of the river centerline is calculated, and the peak curvature points are marked.

[0027] Feature points whose curvature peaks exceed twice the standard deviation of the overall curvature fluctuation range and whose distance between adjacent curvature peaks is greater than the average width of the river channel are extracted as river segment division nodes.

[0028] The river channel is divided into several independent river segments based on the river segment division nodes, and the boundary range of the corresponding river segment is extracted based on the centerline information of each independent river segment.

[0029] In a preferred embodiment, the step of extracting the morphological feature parameters of each river segment includes:

[0030] The length of a river segment is calculated by accumulating the distances between adjacent coordinate points based on the coordinate sequence of the centerline of each river segment.

[0031] A normal profile line is generated along the centerline of the river section, and the width of the river section is determined based on the distance between the intersections of the river boundary line and the normal profile line.

[0032] Obtain the straight-line distance between the starting and ending points of the river segment's centerline, and calculate the river segment's curvature based on the actual length of the river segment. The curvature is calculated as the ratio of the actual length of the river segment to the straight-line distance between the starting and ending points of the river segment's centerline.

[0033] Elevation points of the slopes on both banks are extracted along the river boundary line. The slope inclination angle is fitted by linear regression, and the average slope of both banks is taken as the slope parameter of the river section.

[0034] The length, width, curvature, and slope of the river section are recorded as morphological characteristic parameters.

[0035] In a preferred embodiment, the step of classifying each river segment based on morphological characteristic parameters to obtain multiple river segment types includes:

[0036] Construct a morphological feature vector that includes parameters such as river length, width, bends, and slope.

[0037] Cluster analysis is performed on the morphological feature vectors to group river segments with similar morphological features into one category, forming multiple river segment types, including straight, meandering, and canyon types.

[0038] Statistical analysis was performed on the morphological characteristic parameters of each type of river segment to obtain the range of morphological characteristic parameters for each type of river segment. The types of river segments were then named and defined in conjunction with the geomorphological features in the remote sensing images.

[0039] In a preferred embodiment, the step of performing time-series analysis on the morphological characteristic parameters during the sample collection period to identify the morphological characteristic change trends of each river segment includes:

[0040] The morphological characteristic parameters of each river section are arranged according to the collection time sequence to form a time series data group;

[0041] The morphological characteristics of the river section were analyzed by time series fitting to determine the rate of change of morphological characteristic parameters.

[0042] The absolute value of the rate of change of morphological feature parameters is processed and output as an evaluation index for recording;

[0043] The evaluation indicators are compared with the preset change thresholds;

[0044] When the evaluation index exceeds the change threshold and continues for N consecutive sampling periods, it is determined that the corresponding river section has a stable morphological change trend. Based on the stable morphological change trend, the type of river section evolution trend is determined, and the corresponding river section evolution characteristic report is output simultaneously.

[0045] In a preferred embodiment, the step of predicting the river channel morphological characteristic parameters at future nodes based on the trend of morphological characteristic changes includes:

[0046] Obtain the demand forecast node and the time interval between the demand forecast node and the current node, and record it as the forecast time window length;

[0047] Obtain the prediction function, and input the morphological feature parameters of the current node, the rate of change of the morphological feature parameters, and the length of the prediction time window into the prediction function, and record the output of the prediction function as the initial prediction parameters;

[0048] All initial prediction parameters are validated for reasonableness. Initial prediction parameter combinations that exceed the reasonable range of morphological feature parameters are removed, and initial prediction parameter combinations that simultaneously meet the reasonable range of morphological feature parameters are retained.

[0049] Confidence assessments are conducted on the initial prediction parameter combinations that meet the reasonable range of morphological characteristic parameters, and the initial prediction parameter combination with the highest confidence is selected as the river channel morphological characteristic parameters under the demand prediction node.

[0050] The present invention also provides a remote sensing-based river section morphology feature recognition system, which uses the above-mentioned remote sensing-based river section morphology feature recognition method, including:

[0051] The data acquisition module is used to acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data.

[0052] The preprocessing module is used to perform collaborative preprocessing on multi-source remote sensing data to obtain a standardized remote sensing dataset;

[0053] The river segment division module is used to extract the river boundary line and center line based on multi-source remote sensing data, and divide the river into several river segments according to the curvature variation characteristics of the river center line.

[0054] The river segment classification module is used to extract the morphological feature parameters of each river segment, including river segment length, width, curvature and bank slope. Then, based on the morphological feature parameters, each river segment is classified to obtain multiple river segment types. River segments with the same type and adjacent river segments are merged to form a continuous river channel morphology module.

[0055] The river segment monitoring module is used to acquire the restoration nodes of each river segment, construct a sample collection period between the restoration node and the current node, perform time-series analysis on the morphological feature parameters within the sample collection period, identify the morphological feature change trend of each river segment, and then predict the river channel morphological feature parameters under future nodes based on the morphological feature change trend.

[0056] And, an electronic device, the electronic device comprising:

[0057] At least one processor;

[0058] and a memory communicatively connected to the at least one processor;

[0059] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the above-described method for identifying the morphological features of river sections based on remote sensing.

[0060] The technical effects achieved by this invention are as follows:

[0061] This invention achieves accurate identification and dynamic monitoring of river morphology characteristics through multi-source remote sensing data fusion analysis, improving the scientific nature and efficiency of river management. By classifying river sections and constructing morphology modules, it provides refined data support for river ecological restoration and management, thus supporting the intelligent and data-driven needs of river management decision-making. Furthermore, through time-series analysis of restoration nodes and current nodes, it effectively predicts the evolution trend of river morphology. After outputting the prediction results, a confidence level verification and evaluation are conducted to ensure the reliability and applicability of the prediction results. This enables the prediction results to provide corresponding data support for river regulation projects, allowing for early prediction of river morphology changes and providing a scientific basis for flood control, disaster reduction, and water resource management. Attached Figure Description

[0062] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0063] Figure 2 This is a schematic diagram of the system modules of the present invention;

[0064] Figure 3 This is a schematic diagram of the electronic device structure of the present invention. Detailed Implementation

[0065] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0066] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0067] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that mutually excludes other embodiments.

[0068] Please see Figure 1 As shown, this invention provides a method for identifying the morphological features of river sections based on remote sensing, including:

[0069] S1. Acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data.

[0070] In step S1, the purpose of monitoring river morphology is primarily to prevent river erosion, siltation, and shoreline changes, ensuring flood control safety and ecological stability. In this embodiment, multi-temporal remote sensing data covering the target river channel is first acquired, including optical satellite images, synthetic aperture radar images, and lidar point cloud data under different seasons and hydrological conditions, to reflect the morphological changes of the river channel under various environments. The step of acquiring multi-source remote sensing data of the target river channel includes:

[0071] Multiple monitoring points are pre-deployed along the riverbank. Each monitoring point includes acquisition equipment for collecting multi-source remote sensing data, including optical cameras, synthetic aperture radar antennas, and lidar scanners.

[0072] By periodically activating each acquisition device, optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data of the target river channel are acquired synchronously, and the initial remote sensing data is summarized.

[0073] Add timestamps and geographic labels to the aggregated initial remote sensing data to form multi-source remote sensing data with spatiotemporal identifiers;

[0074] Specifically, when collecting multi-source remote sensing data, multiple monitoring stations are first pre-deployed along the riverbank. These stations can be evenly distributed or strategically deployed based on the actual topographic features of the river. The density of monitoring points is appropriately increased in areas with frequent morphological changes, such as river bends and confluences, to ensure comprehensive monitoring of the target river. Each monitoring station is equipped with an optical camera, a synthetic aperture radar antenna, and a lidar scanner to capture various morphological changes in the river in real time. Then, through a timed acquisition mechanism, the acquisition equipment of all monitoring stations will start synchronously at a preset time point to quickly capture optical satellite images, synthetic aperture radar images, and lidar point cloud data of the target river, and summarize them into initial remote sensing data for recording. After the initial remote sensing data is collected, timestamps and geographic tags are added to it to form a multi-source remote sensing dataset with spatiotemporal identification. The timestamps record the time of data acquisition, while the geographic tags accurately mark the spatial location of the data, thus providing a corresponding data foundation for subsequent analysis and processing.

[0075] S2. Perform collaborative preprocessing on multi-source remote sensing data to obtain a standardized remote sensing dataset;

[0076] In step S2, after the multi-source remote sensing data is output, collaborative preprocessing is performed on the remote sensing data from each source to eliminate errors and noise caused by factors such as sensor differences, atmospheric interference, and terrain undulations during data acquisition, ensuring data consistency and comparability. The collaborative preprocessing step for the multi-source remote sensing data includes:

[0077] Spatial reference unification is performed on optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data, and the optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are registered to a unified coordinate system.

[0078] Multi-temporal image overlay and band reconstruction of optical satellite imagery are used to restore the obscured areas;

[0079] Denoising and geometric correction are performed on synthetic aperture radar images;

[0080] Filtering and elevation normalization are performed on the lidar point cloud data;

[0081] The preprocessed optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are fused together to form a unified information layer, creating a standardized remote sensing dataset with a unified spatial reference.

[0082] Specifically, in the collaborative preprocessing of multi-source remote sensing data, the first step is to unify the spatial reference of optical satellite imagery, synthetic aperture radar (SAR) imagery, and lidar point cloud data, registering them to the same coordinate system to ensure spatial consistency between the data and avoid misunderstandings or incorrect conclusions caused by direct comparison or analysis. Then, multi-temporal image overlay and band reconstruction are performed on the optical satellite imagery to restore areas obscured by clouds, shadows, etc. Multi-temporal image overlay utilizes image data from different time points; through comparison and analysis, it identifies obscured areas that were visible at other time points, thereby restoring information about the corresponding areas. Band reconstruction enhances the ability to extract information about specific land features, such as water bodies and vegetation, by adjusting the band combinations of the images. For SAR imagery, the main... The image undergoes denoising and geometric correction. Denoising eliminates speckle noise and improves image clarity, while geometric correction corrects geometric distortions to ensure that the shape, size, and orientation of ground features in the image match reality. LiDAR point cloud data requires filtering and elevation normalization. Filtering removes noise points such as vegetation and buildings to obtain more accurate ground elevation information, while elevation normalization unifies the elevation values ​​of the point cloud data to the same reference plane, facilitating subsequent data analysis and processing. Finally, optical satellite imagery, synthetic aperture radar imagery, and LiDAR point cloud data are fused together into a unified information layer. This integrates remote sensing data from different sources, forming a standardized remote sensing dataset with a unified spatial reference.

[0083] S3. Extract the river boundary line and center line based on multi-source remote sensing data, and divide the river into several river segments according to the curvature change characteristics of the river center line.

[0084] In step S3, after the multi-source remote sensing data is output and preprocessed, the river boundary line and centerline can be extracted based on it, thus providing corresponding preliminary data support for river segment division. The steps of extracting the river boundary line and centerline based on the multi-source remote sensing data and dividing the river into several river segments according to the curvature variation characteristics of the river centerline include:

[0085] The river water mask is calculated based on the spectral characteristics of optical satellite imagery, and the boundary of the water mask is corrected by combining the microwave reflection characteristics of synthetic aperture radar imagery.

[0086] The topographic elevation information of the river channel is extracted using lidar point cloud data, and the riverbank is determined based on the slope changes;

[0087] The river boundary line is extracted by fusing information from the river water mask and the riverbank, and the river center line is extracted by combining the river boundary line with topographic elevation data.

[0088] The curvature of the river centerline is calculated, and the peak curvature points are marked.

[0089] Feature points whose curvature peaks exceed twice the standard deviation of the overall curvature fluctuation range and whose distance between adjacent curvature peaks is greater than the average width of the river channel are extracted as river segment division nodes.

[0090] The river channel is divided into several independent river segments based on the river segment division nodes, and the boundary range of the corresponding river segment is extracted based on the centerline information of each independent river segment.

[0091] Specifically, in the process of delineating river sections, the first step is to extract water bodies from optical satellite imagery based on standardized remote sensing datasets using image processing techniques (common image segmentation algorithms such as U-Net or Mask R-CNN deep learning models, etc.). This yields a preliminary water body mask. Since optical satellite imagery may be affected by factors such as lighting and shadows, leading to inaccurate boundaries for the water body mask, it is necessary to combine the microwave reflection characteristics of synthetic aperture radar (SAR) imagery to correct the water body mask boundaries and improve the accuracy of river boundary line extraction. Next, elevation information from lidar point cloud data is used to determine the elevation range of the riverbank through terrain analysis. The riverbank is the boundary between the river and the land. Then, the water body mask and riverbank information are fused, and a more precise river boundary line is extracted through intersection or fusion processing. Simultaneously, by combining the river boundary line with terrain elevation data, the river centerline can be extracted. The river centerline is the central axis of the river's morphology. Its location and shape reflect the overall direction and curvature of the river channel. Then, the curvature of the river channel centerline is calculated. By calculating the curvature of the river channel centerline, the characteristic points of the river channel's curvature, namely the peak points of curvature, can be identified. By analyzing the peak points of curvature, feature points that exceed twice the standard deviation of the overall curvature fluctuation range and whose distance between adjacent peak points is greater than the average width of the river channel are extracted as nodes for dividing the river segment. Based on this, the river channel is divided into several independent river segments. Finally, based on the centerline information of each independent river segment, the boundary range of the corresponding river segment can be extracted (specifically, the centerline can be smoothed by spatial interpolation methods, and the curvature is calculated based on the smoothed centerline to eliminate the influence of local noise on the identification of peak points of curvature). This provides basic data support for subsequent river segment classification, monitoring, and prediction.

[0092] S4. Extract the morphological feature parameters of each river segment, including river segment length, width, curvature and bank slope. Then classify each river segment according to the morphological feature parameters to obtain multiple river segment types. Merge river segments with the same type and adjacent river segments to form a continuous river channel morphology module.

[0093] In step S4, after the river segment division is completed, the morphological characteristic parameters of each river segment are extracted, including river segment length, width, curvature, and bank slope. Then, according to preset classification standards, such as length range, curvature level, and bank slope category, each river segment is classified. The purpose of classification is to group river segments with similar morphological characteristics into one category to facilitate subsequent analysis and management. After the river segment classification is completed, adjacent river segments of the same type are merged to form continuous river channel morphology modules, thereby achieving a systematic understanding of the overall river channel structure. The step of extracting the morphological characteristic parameters of each river segment includes:

[0094] The length of a river segment is calculated by accumulating the distances between adjacent coordinate points based on the coordinate sequence of the centerline of each river segment.

[0095] A normal profile line is generated along the centerline of the river section, and the width of the river section is determined based on the distance between the intersections of the river boundary line and the normal profile line.

[0096] Obtain the straight-line distance between the starting and ending points of the river segment's centerline, and calculate the river segment's curvature based on the actual length of the river segment. The curvature is calculated as the ratio of the actual length of the river segment to the straight-line distance between the starting and ending points of the river segment's centerline.

[0097] Elevation points of the slopes on both banks are extracted along the river boundary line. The slope inclination angle is fitted by linear regression, and the average slope of both banks is taken as the slope parameter of the river section.

[0098] The length, width, curvature, and slope of the river section are recorded as morphological characteristic parameters.

[0099] Specifically, when extracting morphological feature parameters of a river segment, the length of the segment is first calculated by accumulating the distances between adjacent coordinate points based on the coordinate sequence of the centerline of each segment. Then, a normal profile line is generated along the centerline of the segment. The distance between the intersection points of the normal profile line and the river boundary line is used to determine the width of the segment, thereby capturing the width variation of the segment at different locations and understanding the morphological features of the river. Next, the straight-line distance between the start and end points of the centerline of the segment is obtained, and the curvature of the segment is calculated by combining it with the actual length of the segment. The curvature is quantified as the ratio of the actual length of the segment to the straight-line distance from the start to the end point of the centerline. The larger the ratio, the higher the curvature of the river. At the same time, the elevation points of the slopes on both banks are extracted along the river boundary line, and the slope angle is fitted by linear regression. Finally, the average slope of both banks is taken as the slope parameter of the segment. Finally, the segment length, width, curvature, and slope parameter are recorded as morphological feature parameters.

[0100] Secondly, the steps of classifying each river segment based on morphological characteristic parameters to obtain multiple river segment types include:

[0101] Construct a morphological feature vector that includes parameters such as river length, width, bends, and slope.

[0102] Cluster analysis is performed on the morphological feature vectors to group river segments with similar morphological features into one category, forming multiple river segment types, including straight, meandering, and canyon types.

[0103] Statistical analysis was performed on the morphological characteristic parameters of each type of river segment to obtain the range of morphological characteristic parameters for each type of river segment. The types of river segments were then named and defined in conjunction with the geomorphological features in the remote sensing images.

[0104] In the above process, when classifying river segments, the morphological features of the river segments, including length, width, curvature, and slope, are first integrated into a morphological feature vector. This vector reflects the geometric and topographical characteristics of the river segment, providing a data foundation for subsequent classification. Then, clustering algorithms, such as K-means or DBSCAN, are used to cluster the morphological feature vector. Clustering analysis automatically groups river segments with similar characteristics into one category without requiring pre-defined classification criteria, thus making the classification results more objective. Through clustering analysis, multiple river segment types can be obtained, such as straight, meandering, and canyon types. Straight river segments typically exhibit characteristics such as a river channel... Straight river sections exhibit minimal changes in width and slope, while meandering river sections display distinct bends with a high degree of curvature. Canyon river sections are located in narrow valleys with steep bank slopes. To more accurately describe and define each type of river section, statistical analysis of the morphological characteristic parameters for each type is conducted to obtain the range of morphological characteristic parameters for each type of river section. Simultaneously, combined with geomorphological features from remote sensing imagery, each type of river section is named and defined. For example, river sections with a straight course and uniform width are named "straight river sections," and river sections with a high degree of curvature and complex morphology are named "complex meandering river sections." This helps to provide a clear understanding and definition of river morphological characteristics.

[0105] S5. Obtain the repair nodes of each river segment, construct a sample collection period between the repair node and the current node, perform time series analysis on the morphological feature parameters within the sample collection period, identify the morphological feature change trend of each river segment, and then predict the river channel morphological feature parameters under future nodes based on the morphological feature change trend.

[0106] In step S5, after the river segment is divided, its morphological characteristic parameters are dynamically monitored. Specifically, the node that underwent the most recent restoration work is selected as the restoration node, and the time period between the restoration node and the current node is defined as the sample collection period. This allows for time-series analysis of the changes in the river segment's morphological characteristic parameters within this period. Through time-series analysis, the changing trends of the river segment's morphological characteristics can be identified, such as the rate of change in river width, the evolution trend of curvature, or the direction of slope adjustment. Based on the identified changing trends, the morphological characteristic parameters of the river segment at a specific future time node are determined, thus providing a basis for subsequent river management and ecological restoration. The step of performing time-series analysis of the morphological characteristic parameters within the sample collection period to identify the changing trends of the morphological characteristics of each river segment includes:

[0107] The morphological characteristic parameters of each river section are arranged according to the collection time sequence to form a time series data group;

[0108] The morphological characteristics of the river section were analyzed by time series fitting to determine the rate of change of morphological characteristic parameters.

[0109] The absolute value of the rate of change of morphological feature parameters is processed and output as an evaluation index for recording;

[0110] The evaluation indicators are compared with the preset change thresholds;

[0111] When the evaluation index exceeds the change threshold and continues for N consecutive sampling periods, it is determined that the corresponding river section has a stable morphological change trend. Based on the stable morphological change trend, the type of river section evolution trend is determined, and the corresponding river section evolution characteristic report is output simultaneously.

[0112] Specifically, when determining the morphological characteristics and trends of river segments, the morphological parameters of each segment, such as length, width, curvature, and slope, are first arranged according to the time sequence of data collection to form a time-series data set. This reflects the changes in the morphological parameters of the river segment over time. Then, time-series fitting methods, such as ARIMA models or LSTM neural networks, are used to analyze the morphological characteristics and trends of the river segment. By fitting historical data, possible future changes in the morphological parameters of the river segment are predicted, thereby determining the rate of change of the morphological parameters (i.e., the numerical change of the morphological parameters per unit time). This determines the speed and direction of the evolution of the river segment's morphological characteristics. Finally, the absolute value of the rate of change of the morphological parameters is taken to eliminate the influence of the sign on the degree of change. The processed rate of change is recorded as an evaluation indicator for subsequent comparison and analysis. Then, the evaluation indicator is compared with a preset change threshold. The change threshold is set based on factors such as the natural evolution of the river channel and historical restoration experience, and is used to determine whether the changes in the morphological characteristic parameters of the river section are significant. When the evaluation indicator exceeds the change threshold and remains above it for N consecutive sampling periods (N is the preset number of sampling periods, generally between 3 and 5), it is determined that the corresponding river section has a stable morphological change trend. This indicates that the morphological characteristics of the corresponding river section are changing at a certain speed and direction. Finally, the type of river section evolution trend is determined based on the stable morphological change trend, such as river widening trend, increasing curvature trend, or decreasing slope trend, and the corresponding river section evolution characteristic report is output simultaneously.

[0113] Secondly, the steps for predicting river channel morphological characteristic parameters at future nodes based on morphological characteristic change trends include:

[0114] Obtain the demand forecast node and the time interval between the demand forecast node and the current node, and record it as the forecast time window length;

[0115] Obtain the prediction function, and input the morphological feature parameters of the current node, the rate of change of the morphological feature parameters, and the length of the prediction time window into the prediction function, and record the output of the prediction function as the initial prediction parameters;

[0116] All initial prediction parameters are validated for reasonableness. Initial prediction parameter combinations that exceed the reasonable range of morphological feature parameters are removed, and initial prediction parameter combinations that simultaneously meet the reasonable range of morphological feature parameters are retained.

[0117] Confidence assessments are conducted on the initial prediction parameter combinations that meet the reasonable range of morphological characteristic parameters, and the initial prediction parameter combination with the highest confidence is selected as the river channel morphological characteristic parameters under the demand prediction node.

[0118] Specifically, after determining the morphological change trend of a river segment, in order to predict the river channel morphological characteristic parameters at future nodes based on the morphological characteristic change trend, the demand prediction node is first identified. The demand prediction node represents the time point at which the future river channel morphological characteristics need to be predicted. Simultaneously, the time interval between the demand prediction node and the current node is calculated and recorded as the prediction time window length. Then, a pre-defined prediction function is introduced. This function estimates the river channel morphological characteristic parameters at future nodes based on historical data (i.e., the morphological characteristic parameters of the current node and the rate of change of the morphological characteristic parameters) and the prediction time window length. After inputting the relevant data into the prediction function, the output result is the initial prediction parameter. The expression of the prediction function is: Initial prediction parameter = Current morphological characteristic parameter + (Rate of change of morphological characteristic parameter × Prediction time window length). The initial prediction parameter is a preliminary estimate of the future river channel morphological characteristic parameters. However, due to potential errors or uncertainties in the prediction process, all initial prediction parameters need to be validated for reasonableness. The validation standard is the reasonable range of the morphological characteristic parameters, which is based on the river... The prediction parameters are derived from prior knowledge of river morphology and statistical analysis of historical data. By eliminating initial prediction parameter combinations that exceed reasonable ranges, predictions that are more likely to closely approximate the actual situation can be retained. Furthermore, to select the optimal solution from the retained initial prediction parameter combinations, a confidence assessment is conducted. The confidence assessment considers the reliability and accuracy of the prediction results. By comparing the confidence levels of different initial prediction parameter combinations, the combination with the highest confidence level is finally selected as the river morphology characteristic parameter under the demand prediction node. The confidence level assessment method includes a comprehensive consideration of factors such as the historical performance of the prediction model, the stability of parameter changes, and the impact of the prediction time window length. By quantitatively analyzing the confidence levels of multiple prediction parameter combinations (such as linear regression analysis or weighted average method), the initial prediction parameter combinations that are most likely to reflect the actual future river morphology can be effectively identified. This approach not only improves the reliability of the prediction results but also reduces the risk of bias caused by a single prediction method, making the prediction results of river morphology characteristic parameters more accurate, so as to provide a scientific basis for subsequent river management, flood control planning, and ecological protection measures.

[0119] Please see Figure 2 A remote sensing-based river section morphology feature recognition system, using the aforementioned remote sensing-based river section morphology feature recognition method, includes:

[0120] The data acquisition module is used to acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data.

[0121] The preprocessing module is used to perform collaborative preprocessing on multi-source remote sensing data to obtain a standardized remote sensing dataset;

[0122] The river segment division module is used to extract the river boundary line and center line based on multi-source remote sensing data, and divide the river into several river segments according to the curvature variation characteristics of the river center line.

[0123] The river segment classification module is used to extract the morphological feature parameters of each river segment, including river segment length, width, curvature and bank slope. Then, based on the morphological feature parameters, each river segment is classified to obtain multiple river segment types. River segments with the same type and adjacent river segments are merged to form a continuous river channel morphology module.

[0124] The river segment monitoring module is used to acquire the restoration nodes of each river segment, construct a sample collection period between the restoration node and the current node, perform time-series analysis on the morphological feature parameters within the sample collection period, identify the morphological feature change trend of each river segment, and then predict the river channel morphological feature parameters under future nodes based on the morphological feature change trend.

[0125] The execution process of this identification system corresponds to the implementation steps of the remote sensing-based river section morphology feature identification method described above, and will not be repeated here.

[0126] Please see Figure 3 An electronic device, comprising:

[0127] At least one processor;

[0128] and memory that is communicatively connected to at least one processor;

[0129] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that at least one processor can execute the above-mentioned method for identifying the morphological features of river sections based on remote sensing.

[0130] The processor of the aforementioned electronic device can be a central processing unit (CPU), a graphics processing unit (GPU), or other computing cores suitable for data processing. The memory can be a storage medium such as random access memory (RAM), read-only memory (ROM), or solid-state drive (SSD). In addition, the electronic device may also include an arithmetic logic unit (ALU), a controller, and input / output interfaces to support the processor's efficient data processing and external communication interaction.

[0131] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0132] The above description is merely a preferred embodiment of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention. Structures, devices, and operating methods not specifically described or explained in this invention are implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A method for identifying the morphological features of river sections based on remote sensing, characterized in that: include: Acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data; Collaborative preprocessing of multi-source remote sensing data yields a standardized remote sensing dataset; The river boundary line and center line are extracted based on the standardized remote sensing dataset, and the river is divided into several river segments according to the curvature variation characteristics of the river center line. The morphological feature parameters of each river segment are extracted, including the length, width, curvature and bank slope of the river segment. Then, the river segments are classified according to the morphological feature parameters to obtain multiple river segment types. River segments with the same type and adjacent river segments are merged to form a continuous river channel morphology module. The node that was last repaired was selected as the repair node. Repair nodes for each river segment were obtained, and a sample collection period was constructed between the repair node and the current node. The morphological feature parameters within the sample collection period were analyzed over time to identify the morphological feature change trend of each river segment. Based on the morphological feature change trend, the river channel morphological feature parameters under future nodes were predicted. The step of performing time-series analysis on morphological feature parameters during the sample collection period to identify the morphological feature change trends of each river segment includes: The morphological characteristic parameters of each river section are arranged according to the collection time sequence to form a time series data group; The morphological characteristics of the river section were analyzed by time series fitting to determine the rate of change of morphological characteristic parameters. The absolute value of the rate of change of morphological feature parameters is processed and output as an evaluation index for recording; The evaluation indicators are compared with the preset change thresholds; When the evaluation index exceeds the change threshold and continues for N sampling periods, it is determined that the corresponding river section has a stable morphological change trend. Based on the stable morphological change trend, the type of river section evolution trend is determined, and the corresponding river section evolution characteristic report is output simultaneously. Here, N is the preset number of sampling periods, which is between 3 and 5. The steps for predicting river morphological feature parameters at future nodes based on morphological feature change trends include: Obtain the demand forecast node and the time interval between the demand forecast node and the current node, and record it as the forecast time window length; Obtain the prediction function, and input the morphological feature parameters of the current node, the rate of change of the morphological feature parameters, and the length of the prediction time window into the prediction function, and record the output of the prediction function as the initial prediction parameters; All initial prediction parameters are validated for reasonableness. Initial prediction parameter combinations that exceed the reasonable range of morphological feature parameters are removed, and initial prediction parameter combinations that simultaneously meet the reasonable range of morphological feature parameters are retained. Confidence assessments are conducted on the initial prediction parameter combinations that meet the reasonable range of morphological characteristic parameters, and the initial prediction parameter combination with the highest confidence is selected as the river channel morphological characteristic parameters under the demand prediction node.

2. The method for identifying river channel morphology features based on remote sensing according to claim 1, characterized in that: The steps for acquiring multi-source remote sensing data of the target river channel include: Multiple monitoring points are pre-deployed along the riverbank. Each monitoring point includes acquisition equipment for collecting multi-source remote sensing data, including optical cameras, synthetic aperture radar antennas, and lidar scanners. By periodically activating each acquisition device, optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data of the target river channel are acquired synchronously, and the initial remote sensing data is summarized. Timestamps and geographic labels are added to the aggregated initial remote sensing data to form multi-source remote sensing data with spatiotemporal identifiers.

3. The method for identifying river channel morphology features based on remote sensing according to claim 1, characterized in that: The steps for collaborative preprocessing of multi-source remote sensing data include: Spatial reference unification is performed on optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data, and the optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are registered to a unified coordinate system. Multi-temporal image overlay and band reconstruction of optical satellite imagery are used to restore the obscured areas; Denoising and geometric correction are performed on synthetic aperture radar images; Filtering and elevation normalization are performed on the lidar point cloud data; Preprocessed optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data are fused together to form a unified information layer, creating a standardized remote sensing dataset with a unified spatial reference.

4. The method for identifying river channel morphology features based on remote sensing according to claim 3, characterized in that: The steps of extracting the river boundary line and centerline based on the standardized remote sensing dataset, and dividing the river into several river segments according to the curvature variation characteristics of the river centerline, include: The river water mask is calculated based on the spectral characteristics of optical satellite imagery, and the boundary of the water mask is corrected by combining the microwave reflection characteristics of synthetic aperture radar imagery. The topographic elevation information of the river channel is extracted using lidar point cloud data, and the riverbank is determined based on the slope changes; The river boundary line is extracted by fusing information from the river water mask and the riverbank, and the river center line is extracted by combining the river boundary line with topographic elevation data. The curvature of the river centerline is calculated, and the peak curvature points are marked. Feature points whose curvature peaks exceed twice the standard deviation of the overall curvature fluctuation range and whose distance between adjacent curvature peaks is greater than the average width of the river channel are extracted as river segment division nodes. The river channel is divided into several independent river segments based on the river segment division nodes, and the boundary range of the corresponding river segment is extracted based on the centerline information of each independent river segment.

5. The method for identifying river channel morphology features based on remote sensing according to claim 1, characterized in that: The step of extracting morphological feature parameters for each river segment includes: The length of a river segment is calculated by accumulating the distances between adjacent coordinate points based on the coordinate sequence of the centerline of each river segment. A normal profile line is generated along the centerline of the river section, and the width of the river section is determined based on the distance between the intersections of the river boundary line and the normal profile line. Obtain the straight-line distance between the starting and ending points of the river segment's centerline, and calculate the river segment's curvature based on the actual length of the river segment. The curvature is calculated as the ratio of the actual length of the river segment to the straight-line distance between the starting and ending points of the river segment's centerline. Elevation points of the slopes on both banks are extracted along the river boundary line. The slope inclination angle is fitted by linear regression, and the average slope of both banks is taken as the slope parameter of the river section. The length, width, curvature, and slope of the river section are recorded as morphological characteristic parameters.

6. The method for identifying river channel morphology features based on remote sensing according to claim 1, characterized in that: The step of classifying each river segment based on morphological feature parameters to obtain multiple river segment types includes: Construct a morphological feature vector that includes parameters such as river length, width, bends, and slope. Cluster analysis is performed on the morphological feature vectors to group river segments with similar morphological features into one category, forming multiple river segment types, including straight, meandering, and canyon types. Statistical analysis was performed on the morphological characteristic parameters of each type of river segment to obtain the range of morphological characteristic parameters for each type of river segment. The types of river segments were then named and defined in conjunction with the geomorphological features in the remote sensing images.

7. A remote sensing-based system for identifying the morphological features of river sections, characterized in that: The method for identifying river channel morphology features based on remote sensing, according to any one of claims 1 to 6, includes: The data acquisition module is used to acquire multi-source remote sensing data of the target river channel, including optical satellite imagery, synthetic aperture radar imagery, and lidar point cloud data. The preprocessing module is used to perform collaborative preprocessing on multi-source remote sensing data to obtain a standardized remote sensing dataset; The river segment division module is used to extract the river boundary line and center line based on multi-source remote sensing data, and divide the river into several river segments according to the curvature variation characteristics of the river center line. The river segment classification module is used to extract the morphological feature parameters of each river segment, including river segment length, width, curvature and bank slope. Then, based on the morphological feature parameters, each river segment is classified to obtain multiple river segment types. River segments with the same type and adjacent river segments are merged to form a continuous river channel morphology module. The river segment monitoring module is used to acquire the restoration nodes of each river segment, construct a sample collection period between the restoration node and the current node, perform time-series analysis on the morphological feature parameters within the sample collection period, identify the morphological feature change trend of each river segment, and then predict the river channel morphological feature parameters under future nodes based on the morphological feature change trend.

8. An electronic device, characterized in that: The electronic device includes: At least one processor; and a memory communicatively connected to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, which is then executed by the at least one processor to enable the at least one processor to perform the remote sensing-based river section morphology feature identification method according to any one of claims 1 to 6.

Images