River natural-like assembled treatment planning method

Abstract

The present application belongs to the technical field of river management, and specifically relates to a river quasi-natural assembly type management planning method. The present application obtains river hydrological characteristic parameters through remote sensing images, and combines multi-scale morphological clustering analysis to divide dominant morphological units, thereby realizing accurate identification of river morphological characteristics and division of management units, so as to improve the pertinence and adaptability of the management scheme. Through the matched management scheme in the management module library, assembly type management is implemented to improve the management efficiency and standardization level. Through real-time collection of the management recovery amount and closed-loop adjustment of the backtracking optimization mechanism, dynamic adaptation and accurate regulation of the management process are ensured, the ecological restoration effect of the river is effectively improved, and at the same time, when the management is invalid, an alarm prompt and an abnormal management unit marker are provided to facilitate quick identification and intervention of the management end, and the present application has strong practicability and operability.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of mountain river management, and particularly relates to a river quasi-natural assembly type management planning method. BACKGROUND

[0002] The river hydrological monitoring station network in mountainous areas is sparse, and large-scale river morphology identification and analysis is the basis for carrying out remote sensing-based runoff monitoring in areas lacking data. With the progress of remote sensing technology, large-scale and efficient acquisition of river morphology characteristics and direct use of river morphology characteristics in river hydrodynamic, riverbed evolution, hydrological / water quality, station layout, flood control planning, etc. have become one of the current urgent directions to explore. For rivers in areas lacking data, remote sensing technology provides efficient and wide-area monitoring capabilities, and remote sensing-based runoff monitoring technology has become one of the important research directions.

[0003] At present, remote sensing-based river runoff monitoring technologies such as empirical formula method, multi-station hydraulic geometry method, and Manning formula method have been applied to multiple rivers. However, due to the limitation of the basic principles of river dynamics, the applicability boundary of the methods proposed by the above researches is difficult to determine, resulting in low generalization ability of the methods and difficulty in ensuring accuracy. Therefore, it is necessary to clarify the corresponding relationship between river morphology and remote sensing-based runoff monitoring methods. Based on this, the present scheme proposes a river quasi-natural assembly type management planning method to solve the above problems. SUMMARY

[0004] The purpose of the present application is to provide a river quasi-natural assembly type management planning method, which can effectively improve the scientificity and adaptability of mountain river management planning, and solve the problems of poor applicability and low accuracy of traditional methods in areas lacking data.

[0005] The technical scheme adopted by the present application is as follows:

[0006] A river quasi-natural assembly type management planning method comprises:

[0007] Obtaining remote sensing images of a target river in dry season and flood season, and extracting river hydrological characteristic parameters through band fusion processing;

[0008] Dividing an equidistant cross-section array along the direction of the target river based on the river hydrological characteristic parameters, and determining core morphological parameters, wherein the core morphological parameters include water surface width ratio in dry season and flood season, flood season eccentric distance, and river channel flow symmetry degree;

[0009] Based on the spatial distribution of the core morphological parameters, multi-scale morphological clustering analysis is performed, and the target river is divided into multiple dominant morphological units according to the clustering results;

[0010] According to the morphological characteristics of the dominant morphological unit, the corresponding river section is divided into multiple independent management units, and the corresponding management module is matched from the preset management module library, wherein each management module comprises several management schemes;

[0011] The management recovery amount of each independent management unit in the management process is collected in real time, the management effect of the corresponding independent management unit is evaluated according to the management recovery amount, and when the management is invalid, the backtracking optimization mechanism is triggered to iteratively optimize the management scheme under the management module until the management effective condition is reached.

[0012] In a preferred scheme, the step of acquiring remote sensing images of the target river in dry season and flood season, and extracting river hydrological feature parameters through band fusion processing, comprises:

[0013] The remote sensing images in dry season and flood season are preprocessed to remove cloud and fog interference and geometric distortion to obtain corrected remote sensing images;

[0014] The corrected remote sensing images are fused with panchromatic band and multispectral band to generate fusion data;

[0015] Based on the fusion data, the normalized difference water index is calculated, and the river water body information is extracted by combining threshold segmentation;

[0016] The river boundary and main flow direction line are identified from the river entity information, and the width, curvature and flood season inundation range of the river are determined through the river boundary and main flow direction line;

[0017] The width, curvature and flood season inundation range of the river are recorded as river hydrological feature parameters.

[0018] In a preferred scheme, the step of dividing an equal-interval cross-section array along the direction of the target river based on the river hydrological feature parameters and determining core morphological parameters comprises:

[0019] Based on the river main flow direction line, a plurality of cross-section lines perpendicular to the flow direction are arranged at the center position of the river, wherein the cross-section lines are distributed at equal intervals along the direction of the river;

[0020] The cross-section width is determined through the intersection of each cross-section line and the river boundary, and the water surface width ratio is calculated by combining the water level difference between flood season and dry season;

[0021] The offset distance of the intersection point of the flood season main flow direction line and the cross-section line is calculated and recorded as the flood season eccentric distance;

[0022] The river channel flow direction of the target river is acquired, and the river channel flow symmetry degree is calculated through the included angle between the flow direction and the cross-section line;

[0023] The water surface width ratio, the flood season eccentric distance and the river channel flow symmetry degree are recorded as core morphological parameters.

[0024] In a preferred solution, the step of performing multi-scale morphological cluster analysis based on the spatial distribution of the core morphological parameters and dividing the target river into a plurality of dominant morphological units according to the cluster results comprises:

[0025] Taking each cross-section position as a spatial node, the water surface width ratio, the flood season eccentricity and the channel flow symmetry of the corresponding cross-section are combined into a morphological feature vector to form a spatial sequence matrix along the river direction;

[0026] The morphological feature vectors of adjacent spatial positions are analyzed for correlation to identify the morphological feature similarity between adjacent cross-sections, and the cluster intervals are divided according to the similarity degree;

[0027] The morphological feature vectors in each cluster interval are subjected to principal component analysis to extract the principal component scores and record them as comprehensive representation indexes;

[0028] According to the contribution of the comprehensive representation indexes to the river morphological features, the dominant feature types of the river morphology in each cluster interval are determined, and the river reaches with the same dominant feature type are merged into a dominant morphological unit.

[0029] In a preferred solution, the step of determining the dominant feature types of the river morphology in each cluster interval according to the contribution of the comprehensive representation indexes to the river morphological features comprises:

[0030] The variance contribution rates of the principal component analysis in each cluster interval are obtained and calculated item by item to obtain the cumulative variance contribution rates of the principal components;

[0031] The principal component whose cumulative contribution rate first reaches a preset evaluation threshold is selected as a key principal component, and the comprehensive representation index corresponding to the key principal component is marked as a high-contribution index;

[0032] The load coefficients between the high-contribution index and the original morphological feature vector are analyzed, and the morphological feature variable with the largest absolute value of the load coefficient is recorded as a dominant feature factor;

[0033] The appearance frequencies of the dominant feature factors of all high-contribution indexes in each cluster interval are counted, and the dominant feature factor with the highest appearance frequency is determined as the dominant feature type of the river morphology in the corresponding cluster interval.

[0034] In a preferred solution, the step of dividing the corresponding river reach into a plurality of independent management units according to the morphological features of the dominant morphological units comprises:

[0035] The core morphological parameters of the continuous cross-sections in each dominant morphological unit are extracted, and the coefficients of variation of the core morphological parameters in the corresponding dominant morphological unit are calculated;

[0036] When the coefficient of variation is less than or equal to the preset variation threshold, the corresponding whole dominant morphological unit is directly recorded as an initialization management unit;

[0037] When the coefficient of variation is greater than the preset variation threshold, secondary clustering analysis is performed on the corresponding dominant morphological unit to form a subunit partition, and a management unit division point is added at the boundary of the subunit partition, so as to divide the dominant morphological unit into multiple initialization management units;

[0038] The length of each initialization management unit is verified;

[0039] If the length of the initialization management unit is less than or equal to the preset length threshold, the initialization management unit is directly retained as an independent management unit;

[0040] If the length of the initialization management unit is greater than the preset length threshold, the initialization management unit is cut according to the length threshold to form multiple independent management units.

[0041] In a preferred scheme, the step of evaluating the management effect of the corresponding independent management unit according to the management recovery amount comprises:

[0042] A plurality of sample collection nodes are set in the management period, and the management recovery amount under each sample collection node is collected;

[0043] The adjacent management recovery amounts are calculated by difference, and the management recovery rate of the independent management unit is determined according to the difference result;

[0044] The target recovery amount is obtained, and the management completion index is calculated in combination with the management recovery rate, and the management completion index is compared with the preset completion threshold;

[0045] When the management completion index is greater than or equal to the preset completion threshold, it is determined that the management effect of the corresponding independent management unit is effective management;

[0046] When the management completion index is less than the preset completion threshold, it is determined that the management effect of the corresponding independent management unit is invalid management.

[0047] In a preferred scheme, the step of triggering the backtracking optimization mechanism when the management is invalid to iteratively optimize the management scheme under the management module comprises:

[0048] The difference value between the core morphological parameters of the independent management unit under the invalid management and the core morphological parameters of the initial management scheme is extracted and recorded as a parameter deviation amount;

[0049] The morphological control parameters in the initial management scheme are modified according to the parameter deviation amount to form a modified management scheme;

[0050] Re-execute the governance simulation of the independent governance unit combined with the revised governance scheme, and collect the governance recovery amount in the simulation process;

[0051] Recalculate the governance completion index according to the governance recovery amount in the simulation process, and compare the recalculated governance completion index with the preset completion threshold. If the governance completion index is still less than the preset completion threshold, repeat the parameter deviation extraction, governance scheme revision and governance simulation until the governance completion index reaches or exceeds the preset completion threshold, and complete the closed-loop adjustment of the backtracking optimization mechanism;

[0052] If the governance completion threshold is still not reached after continuous N times of parameter revision, an alarm prompt is sent to the management end, and the execution process of the current backtracking optimization mechanism is terminated, and the corresponding independent governance unit is marked as an abnormal governance unit.

[0053] The present application also provides a river quasi-natural assembly type governance planning system using the above-mentioned river quasi-natural assembly type governance planning method, comprising:

[0054] A data acquisition module is configured to obtain remote sensing images of the target river in dry season and flood season, and extract river hydrological feature parameters through band fusion processing;

[0055] A parameter extraction module is configured to divide an equidistant cross-section array along the direction of the target river based on the river hydrological feature parameters, and determine core morphological parameters, wherein the core morphological parameters include water surface width ratio in dry season and flood season, flood season eccentricity, and river channel flow symmetry degree.

[0056] A unit division module is configured to perform multi-scale morphological clustering analysis based on the spatial distribution of the core morphological parameters, and divide the target river into a plurality of dominant morphological units according to the clustering results.

[0057] A scheme matching module is configured to divide the corresponding river section into a plurality of independent governance units according to the morphological characteristics of the dominant morphological units, and match the corresponding governance module from a preset governance module library, wherein each governance module contains several governance schemes.

[0058] A governance evaluation module is configured to collect the governance recovery amount of each independent governance unit in the governance process in real time, evaluate the governance effect of the corresponding independent governance unit according to the governance recovery amount, and trigger the backtracking optimization mechanism when the governance is invalid to iteratively optimize the governance scheme under the governance module until the governance effective condition is reached.

[0059] An electronic device, comprising:

[0060] At least one processor;

[0061] And a memory connected in communication with the at least one processor.

[0062] The memory stores a computer program executable 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 execute the river quasi-natural assembly type governance planning method.

[0063] The present application achieves the following technical effects:

[0064] The present application obtains river hydrological characteristic parameters through remote sensing images, and combines multi-scale morphological clustering analysis to divide dominant morphological units, so as to realize accurate identification of river morphological characteristics and division of governance units, thereby improving the pertinence and adaptability of the governance scheme, implementing assembly type governance through the matched governance scheme in the governance module library, improving the governance efficiency and standardization level, ensuring dynamic adaptation and accurate regulation of the governance process through real-time collection of governance recovery quantities and closed-loop adjustment of the backtracking optimization mechanism, effectively improving the river ecological restoration effect, and at the same time, when the governance is invalid, the alarm prompt and abnormal governance unit marking are used to facilitate the management end to quickly identify and intervene, so that the present application has strong practicability and operability. BRIEF DESCRIPTION OF DRAWINGS

[0065] Figure 1 is a method flowchart of the present application;

[0066] Figure 2 is a system module schematic diagram of the present application;

[0067] Figure 3 is an electronic device structure schematic diagram of the present application. DETAILED DESCRIPTION

[0068] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0069] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, but the present application can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without departing from the connotation of the present application, therefore the present application is not limited to the specific embodiments disclosed below.

[0070] Secondly, the "one embodiment" or "embodiment" referred to herein means that the specific features, structures or characteristics can be included in at least one implementation of the present application. "In a preferred embodiment" appearing in different places in the specification does not mean the same embodiment, nor is it an independent or alternative embodiment that excludes other embodiments.

[0071] Please refer to Figure 1As shown, the present application provides a river quasi-natural assembly type management planning method, comprising:

[0072] S1, acquiring remote sensing images of the target river in dry season and flood season, and extracting river hydrological characteristic parameters through band fusion processing;

[0073] In the step S1, the river management can not only effectively manage water resources, but also provide necessary support and protection for the ecological system. In this embodiment, when planning the management of the target river, remote sensing image data of the target river is collected, and multi-spectral and thermal infrared bands are combined for fusion analysis to identify the water body boundary, water depth change and water flow speed and other key hydrological characteristic parameters of the river. Among them, the step of acquiring remote sensing images of the target river in dry season and flood season and extracting river hydrological characteristic parameters through band fusion processing comprises:

[0074] Pretreatment is performed on the remote sensing images in dry season and flood season to remove cloud and fog interference and geometric distortion to obtain corrected remote sensing images;

[0075] The corrected remote sensing images are subjected to fusion processing of panchromatic band and multi-spectral band to generate fusion data;

[0076] Based on the fusion data, the normalized difference water body index is calculated, and the river water body information is extracted in combination with threshold segmentation;

[0077] The river boundary and main flow direction line are identified from the river entity information, and the width, curvature and flood season inundation range of the river are determined through the river boundary and main flow direction line;

[0078] The width, curvature and flood season inundation range of the river are recorded as river hydrological characteristic parameters;

[0079] Specifically, in determining the hydrological characteristic parameters of the target river, first, the remote sensing image data of the target river is preprocessed to ensure the accuracy and reliability of the data. The preprocessing operation can remove the cloud and mist interference and geometric distortion in the remote sensing image, so that more clear and accurate corrected remote sensing image can be obtained. On this basis, the fusion processing of the panchromatic band and the multispectral band is further carried out, so that the corresponding fusion data can be generated. In the fusion processing process, first, the green and near-infrared band data with a resolution of 15 m is obtained by fusing the green, near-infrared band and the panchromatic band by using the Gram-Schmidt method. The NDWI of different objects is calculated and counted. After trimming, the NDWI histogram distribution of the river valley range is obtained. Then, the river water surface vector polygon is obtained by using the bimodal threshold method. Finally, after editing and pruning the tributary water surface, the trunk water surface vector file is obtained. After verification, the Kappa coefficient of the extracted dry season river water surface is above 0.83, and the Kappa coefficient of the extracted flood season river water surface is above 0.91. The calculation formula of NDWI is: , wherein, and are the green and near-infrared band remote sensing reflectivity fused with the panchromatic band. In this embodiment, the threshold value of NDWI is automatically identified by using the bimodal method. By counting the distribution characteristics of the NDWI histogram, the water surface and non-water surface regions are effectively distinguished by using the iterative algorithm, so that the river water body information is extracted. After the river water body information is extracted, the river boundary and the main flow direction line are identified, so that the width, curvature and flood season inundation range of the river and other hydrological characteristic parameters can be determined, thereby providing corresponding data support for subsequent management planning.

[0080] S2, based on the river hydrological characteristic parameters, the equal-interval cross-section array along the direction of the target river is divided, and the core morphological parameters are determined, wherein the core morphological parameters include the water surface width ratio in dry season and flood season, the flood season eccentric distance and the river channel flow symmetry degree;

[0081] In the step S2, after the river hydrological characteristic parameters are output, the cross-section array is divided based on the direction of the target river, so that the equal-interval cross-section array is obtained. Each cross-section is perpendicular to the main flow direction line of the river. At the same time, the core morphological parameters such as the water surface width ratio in dry season and flood season, the flood season eccentric distance and the river channel flow symmetry degree are extracted at each cross-section position. The step of dividing the equal-interval cross-section array along the direction of the target river based on the river hydrological characteristic parameters and determining the core morphological parameters comprises:

[0082] Based on the river main flow direction line, a plurality of cross-section lines perpendicular to the flow direction are arranged at the center position of the river. The cross-section lines are distributed at equal intervals along the direction of the river.

[0083] The intersection of each section line and the river boundary determines the section width, and the water surface width ratio is calculated by combining the water level difference between the flood season and the dry season;

[0084] The offset distance of the intersection of the main flow direction line and the section line in the flood season is calculated and recorded as the flood season eccentricity;

[0085] The water flow direction of the river channel is obtained, and the symmetry of the water flow of the river channel is calculated by the angle between the water flow direction and the section line;

[0086] The water surface width ratio, flood season eccentricity and symmetry of the water flow of the river channel are recorded as the core morphological parameters;

[0087] Specifically, when determining the core morphological parameters, first, a plurality of section lines perpendicular to the main flow direction of the river are arranged uniformly at the center position of the river based on the main flow direction line of the river, and the section lines are kept equidistant along the extension direction of the river. The width of each section can be determined by the intersection distance of its two boundaries. Subsequently, the water surface width ratio of the corresponding section is calculated by combining the water level difference between the flood season and the dry season, that is, the water surface width ratio. In addition, the offset distance of the intersection of the main flow direction line and the section line in the flood season relative to the center of the section is calculated, which is recorded as the flood season eccentricity. Then, the angle between the water flow direction and the section line is calculated to evaluate the symmetry of the water flow of the river channel, that is, the symmetry of the water flow of the river channel. The water surface width ratio, flood season eccentricity and symmetry of the water flow of the river channel are integrated as the core morphological parameters, laying a foundation for subsequent management planning of the target river.

[0088] S3, based on the spatial distribution of the core morphological parameters, multi-scale morphological clustering analysis is performed, and the target river is divided into a plurality of dominant morphological units according to the clustering results;

[0089] In the step S3, after the core morphological parameters are determined, multi-scale morphological clustering analysis is performed based on the spatial distribution characteristics, so as to divide the target river into a plurality of river sections with similar morphological characteristics, i.e. dominant morphological units. Based on the spatial distribution of the core morphological parameters, multi-scale morphological clustering analysis is performed, and the target river is divided into a plurality of dominant morphological units according to the clustering results, which comprises:

[0090] Taking each section position as a spatial node, the water surface width ratio, flood season eccentricity and symmetry of the water flow of the corresponding section are combined as a morphological feature vector to form a spatial sequence matrix along the direction of the river;

[0091] The correlation analysis is performed on the morphological feature vectors of adjacent spatial positions, the morphological feature similarity between adjacent sections is identified, and the clustering interval is divided according to the similarity degree;

[0092] The principal component scores are extracted by performing principal component analysis on the morphological feature vectors in each clustering interval, and recorded as the comprehensive representation index;

[0093] According to the contribution degree of the comprehensive representation index to the river morphological characteristics, the dominant characteristic type of the river morphology in each clustering interval is determined, and the river sections with the same dominant characteristic type are merged into a dominant morphological unit;

[0094] Specifically, in the process of dividing the dominant morphological unit, first, the target river is analyzed and divided based on the spatial distribution characteristics of the core morphological parameters. Specifically, taking each cross-section position as a spatial node, the water surface width ratio, the flood season eccentricity and the river channel flow symmetry degree are combined as the morphological characteristic vector, and then the spatial sequence matrix extending along the river direction is constructed. Then, the correlation analysis of the morphological characteristic vectors of adjacent spatial nodes is carried out. By comparing the morphological characteristics between adjacent cross-sections, the similarity is identified, and the clustering interval is defined according to the strength of the similarity. The correlation analysis can be used to quantify the degree of similarity by using Pearson correlation coefficient or Euclidean distance, etc. On this basis, the principal component scores are extracted by principal component analysis (such as K-means clustering algorithm) of the morphological characteristic vectors in each clustering interval, and are recorded as the comprehensive representation index. Then, according to the contribution degree of the comprehensive representation index to the river morphological characteristics, the dominant characteristic type of the river morphology in each clustering interval can be determined, and then the river sections with the same dominant characteristic type are integrated into a dominant morphological unit, thereby providing corresponding data support for the subsequent river management planning.

[0095] It should be noted that the step of determining the dominant characteristic type of the river morphology in each clustering interval according to the contribution degree of the comprehensive representation index to the river morphological characteristics includes:

[0096] Obtaining the variance contribution rate of the principal component analysis in each clustering interval, and performing item-by-item cumulative calculation to obtain the cumulative variance contribution rate of each principal component;

[0097] Selecting the principal component whose cumulative contribution rate first reaches the preset evaluation threshold as the key principal component, and marking the comprehensive representation index corresponding to the key principal component as a high contribution degree index;

[0098] Analyzing the loading coefficient between the high contribution degree index and the original morphological characteristic vector, and recording the morphological characteristic variable with the largest absolute value of the loading coefficient as the dominant characteristic factor;

[0099] Counting the appearance frequency of the dominant characteristic factor of all high contribution degree indexes in each clustering interval, and determining the dominant characteristic factor with the highest appearance frequency as the dominant characteristic type of the river morphology in the corresponding clustering interval;

[0100] In the above, in determining the dominant feature type of the river morphology in each clustering interval, firstly, the variance contribution rate of the principal component analysis in each clustering interval is calculated and counted, so as to measure the contribution degree of each principal component to the river morphology feature. The cumulative variance contribution rate of each principal component is calculated by accumulation. When the cumulative contribution rate of a principal component first reaches the preset evaluation threshold, it is marked as a key principal component, and the corresponding comprehensive representation index is marked as a high contribution index, so as to ensure that the key principal component can accurately reflect the main features of the target river morphology. After the key principal component is determined, the load coefficient between the key principal component and the original morphology feature vector is analyzed. The load coefficient reflects the correlation between the principal component and the original variable. The size of the absolute value of the load coefficient directly reflects the weight of the original variable in the principal component. Based on this, the morphology feature variable with the largest absolute value of the load coefficient is recorded as the dominant feature factor, so as to help to determine the specific morphology feature represented by each key principal component. Finally, the occurrence frequency of the dominant feature factor of all high contribution indexes in each clustering interval is counted. By comparing the frequency of the dominant feature factor in different clustering intervals, the dominant feature factor with the highest frequency is determined as the dominant feature type of the river morphology in the corresponding clustering interval.

[0101] S4, according to the morphology feature of the dominant morphology unit, the corresponding river section is divided into a plurality of independent management units, and the corresponding management module is matched from the preset management module library, wherein each management module comprises a plurality of management schemes;

[0102] In the step S4, after the dominant morphology unit is determined, the corresponding river section is divided into a plurality of independent management units according to the morphology feature, so as to more targetedly implement the management measures on the target river, and the management module most suitable for the morphology feature of each independent management unit is matched from the preset management module library, so as to ensure the effectiveness of the management of the target river. The step of dividing the corresponding river section into a plurality of independent management units according to the morphology feature of the dominant morphology unit comprises:

[0103] Extracting the core morphology parameters of each continuous cross section in the dominant morphology unit, calculating the variation coefficient of each core morphology parameter in the corresponding dominant morphology unit;

[0104] When the variation coefficient is less than or equal to the preset variation threshold, the corresponding entire dominant morphology unit is directly recorded as an initialization management unit;

[0105] When the variation coefficient is greater than the preset variation threshold, the corresponding dominant morphology unit is subjected to secondary clustering analysis to form a sub-unit partition, and a management unit division point is added at the boundary of the sub-unit partition, so as to divide the dominant morphology unit into a plurality of initialization management units;

[0106] Length verification is performed on each initialization management unit;

[0107] If the length of the initialized management unit is less than or equal to the preset length threshold, it is directly reserved as an independent management unit;

[0108] If the length of the initialized management unit is greater than the preset length threshold, the initialized management unit is cut according to the length threshold to form a plurality of independent management units;

[0109] Specifically, in the division of the independent management unit, the core morphological parameters of the continuous cross section in each dominant morphological unit need to be extracted, such as the water surface width ratio, the flood period eccentricity and the river channel flow symmetry, and the variation coefficient of the water surface width ratio, the flood period eccentricity and the river channel flow symmetry in each dominant morphological unit is calculated. The variation coefficient reflects the discrete degree of the core morphological parameters. When the variation coefficient is less than or equal to the preset variation threshold, it indicates that the river morphological characteristics in the corresponding dominant morphological unit are relatively uniform, so the whole dominant morphological unit can be directly recorded as an initialized management unit. When the variation coefficient is greater than the preset variation threshold, it indicates that there is a great change in the river morphological characteristics in the corresponding dominant morphological unit, so secondary clustering analysis is needed to further refine the independent management unit. The secondary clustering analysis can use the same way as the previous multi-scale morphological clustering analysis, by identifying sub-unit partitions and adding management unit segmentation points at the boundaries of the sub-unit partitions, so as to subdivide the dominant morphological unit into a plurality of initialized management units. In the length verification of the initialized management unit, whether it meets the requirements of the independent management unit is judged according to the preset length threshold. If the length of the initialized management unit is less than or equal to the preset length threshold, it indicates that its length is moderate, and it can be directly reserved as an independent management unit for the subsequent implementation of the management measures. If the length of the initialized management unit is greater than the preset length threshold, it indicates that its length is too long, and it needs to be cut according to the length threshold to form a plurality of independent management units with moderate length.

[0110] S5, real-time acquisition of the management recovery amount of each independent management unit in the management process, and evaluation of the management effect of the corresponding independent management unit according to the management recovery amount, and triggering of the backtracking optimization mechanism when the management is invalid to iteratively optimize the management scheme under the management module until the management effective condition is reached;

[0111] After the independent governance units are determined, corresponding governance measures will be implemented for each unit. These measures include engineering measures such as river dredging, embankment reinforcement, and ecological restoration. For example, for canyon sections of the river, rigid revetment structures will be implemented using masonry or concrete slope protection to enhance riverbank stability and prevent collapses caused by water erosion. For the gentle slopes on the right bank, vegetation slope stabilization modules can be used to reduce erosion. By planting erosion-resistant native plants, a stable vegetation cover layer can be formed to improve the slope's resistance to erosion. For concave bank sections of bends, sedimentation dam modules can be used to suppress sedimentation. By setting up flexible or rigid sedimentation structures, the erosion of the concave bank by water flow can be slowed down, inhibiting the evolution of riverbed sedimentation. During the targeted governance process, the amount of governance restoration will be collected in real time, including the amount of river cross-sectional morphology restoration, changes in vegetation cover, and improvements in riverbank stability. The governance effect of the corresponding independent governance unit will be evaluated based on the amount of governance restoration to determine whether the governance measures have achieved the expected results. The steps for evaluating the governance effect of the corresponding independent governance unit based on the amount of governance restoration include:

[0112] Multiple sample collection nodes were set up during the treatment period, and the treatment recovery volume under each sample collection node was collected.

[0113] The difference between adjacent treatment and restoration amounts is calculated, and the treatment and restoration rate of independent treatment units is determined based on the difference results;

[0114] Obtain the target recovery amount, calculate the governance completion index in combination with the governance recovery rate, and compare the governance completion index with the preset completion threshold.

[0115] When the governance completion index is greater than or equal to the preset completion threshold, the governance effect of the corresponding independent governance unit is determined to be effective governance;

[0116] When the governance completion index is less than the preset completion threshold, the governance effect of the corresponding independent governance unit is determined to be invalid governance;

[0117] Specifically, when evaluating the effectiveness of independent governance units, multiple sample collection nodes are first set up during the governance period. These nodes are evenly distributed throughout the period to ensure the comprehensiveness of the collected data. At each node, the corresponding restoration amount is collected. By calculating the difference between adjacent restoration amounts, the restoration rate of the independent governance unit in different time periods can be obtained. The restoration rate reflects the effectiveness of the governance measures and the speed of river ecological restoration. Then, based on the preset target restoration amount and restoration rate, a governance completion index can be further calculated, where the governance completion index = In the formula, Indicates the first The difference in the amount of treatment and restoration under each sample collection node Indicates the first The time interval between each sample collection node and its previous adjacent sample collection node The time decay factor characterizes the degree to which the effectiveness of pollution control diminishes over time. It is determined by combining historical data fitting with empirical parameters. Indicates the first The interval between each sample collection node and the treatment start point This represents the target recovery amount, which is a baseline value set based on the actual needs of the river ecosystem and the goals of river management. This indicates the number of sample collection nodes. The governance completion index is then compared with a preset completion threshold to evaluate the governance effect. If the governance completion index is greater than or equal to the preset completion threshold, it indicates that the governance measures of the corresponding independent governance unit have achieved the expected goals, and it will be judged as effective governance. Conversely, if the governance completion index is lower than the preset completion threshold, it indicates that the current governance measures have failed to achieve the expected results and will be recorded as ineffective governance. In the case of ineffective governance, a backtracking optimization mechanism will be immediately triggered to iteratively optimize the governance plan under the governance module to find a reasonable governance strategy until the effective governance conditions are finally met, ensuring the smooth progress of river governance and the continuous improvement of the river's ecological environment.

[0118] Secondly, when governance proves ineffective, a backtracking optimization mechanism is triggered to iteratively optimize the governance solutions under the governance module, including the following steps:

[0119] Extract the difference between the core morphological parameters of the independent governance unit under ineffective governance and the core morphological parameters of the initial governance scheme, and record it as the parameter deviation.

[0120] Based on the parameter deviation, the morphological control parameters in the initial treatment plan are corrected to form a corrected treatment plan;

[0121] The governance simulation was re-executed for the independent governance units in conjunction with the revised governance scheme, and the amount of governance recovery during the simulation process was collected.

[0122] The governance completion index is recalculated based on the governance recovery amount during the simulation process. The recalculated governance completion index is then compared with the preset completion threshold. If the governance completion index is still less than the preset completion threshold, the parameter deviation extraction, governance scheme correction, and governance simulation are repeated until the governance completion index reaches or exceeds the preset completion threshold, thus completing the closed-loop adjustment of the backtracking optimization mechanism.

[0123] If the governance completion threshold is not reached after N times of parameter correction, an alarm prompt is sent to the management end, the execution process of the current backtracking optimization mechanism is terminated, and the corresponding independent governance unit is marked as an abnormal governance unit;

[0124] In this embodiment, after the backtracking optimization mechanism is triggered, the difference value between the core morphological parameters of the independent governance unit under invalid governance and the core morphological parameters of the initial governance scheme is extracted first. This difference value can directly reflect the degree of mismatch between the governance scheme and the actual river morphology, and is therefore recorded as a parameter deviation. Based on the parameter deviation, the morphological control parameters in the initial governance scheme are adjusted to form a modified governance scheme that is more suitable for the actual river morphology. To ensure the effectiveness of the modified governance scheme, the independent governance unit is re-executed with the modified governance scheme. The governance simulation can simulate the river state after the implementation of the governance measures. During the simulation process, the governance recovery amount is collected in real time, and the governance completion index is recalculated based on the governance recovery amount. By comparing the recalculated governance completion index with the preset completion threshold, it can be determined whether the modified governance scheme achieves the expected effect. If the governance completion index is still less than the preset completion threshold, it means that the modified governance scheme needs to be further optimized. At this time, the processes of parameter deviation extraction, governance scheme modification, and governance simulation are repeated until the governance completion index reaches or exceeds the preset completion threshold, indicating that the closed-loop adjustment of the backtracking optimization mechanism is completed. During this process, if the governance completion threshold is not reached after N times of parameter correction (N≥3), it means that the preset governance strategy cannot effectively adapt to the actual morphology of the independent governance unit. At this time, an alarm prompt is sent to the management end, the execution process of the current backtracking optimization mechanism is terminated, and the corresponding independent governance unit is marked as an abnormal governance unit for subsequent human intervention for investigation and analysis.

[0125] Please refer to Figure 2 A river quasi-natural assembly type governance planning system using the above-mentioned river quasi-natural assembly type governance planning method, comprising:

[0126] A data acquisition module for obtaining remote sensing images of the target river in dry season and flood season, and extracting river hydrological feature parameters through band fusion processing;

[0127] A parameter extraction module for dividing an equidistant cross-section array along the direction of the target river based on the river hydrological feature parameters, and determining core morphological parameters, wherein the core morphological parameters include water surface width ratio in dry season and flood season, flood season eccentricity, and river channel flow symmetry degree;

[0128] A unit division module for performing multi-scale morphological clustering analysis based on the spatial distribution of the core morphological parameters, and dividing the target river into multiple dominant morphological units according to the clustering results.

[0129] The scheme matching module is configured to divide the corresponding river section into a plurality of independent management units according to the morphological characteristics of the dominant morphological unit, and match the corresponding management module from a preset management module library, wherein each management module contains a plurality of management schemes.

[0130] The management evaluation module is configured to collect the management recovery amount of each independent management unit in the management process in real time, evaluate the management effect of the corresponding independent management unit according to the management recovery amount, and trigger a backtracking optimization mechanism when the management is invalid, and iteratively optimize the management scheme under the management module until the management effective condition is reached.

[0131] The execution process of the planning system corresponds to the implementation steps of the river quasi-natural assembly type management planning method described above, and will not be repeatedly described here.

[0132] Please refer to Figure 3 An electronic device, the electronic device comprising:

[0133] At least one processor;

[0134] And a memory connected in communication with the at least one processor;

[0135] The memory stores a computer program executable 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 execute the river quasi-natural assembly type management planning method described above.

[0136] The processor of the electronic device described above can be a central processing unit (CPU), or other forms of processors, such as a graphics processing unit (GPU) or an application-specific integrated circuit (ASIC), and the memory can be a random access memory (RAM), a read-only memory (ROM), a solid state drive (SSD) and other storage media, and the processor and the memory realize data interaction and control signal transmission through an internal bus. In addition, the electronic device can also include an arithmetic logic unit (ALU) and the like for performing specific arithmetic and logical operations, and an input / output device for receiving user operation instructions and input data, such as a keyboard, a mouse, a touch screen, and the like, and an output device for displaying calculation results and system state information, such as a display, a printer, and the like.

[0137] It has to be noted that, as used herein, the terms "includes" and / or "contains", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0138] The above description is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application. The structure, device and operation method not specifically described and explained in the present application, such as no special description and limitation, are implemented according to the conventional means in the art.

Claims

1. A prefabricated, pseudo-natural river management planning method, characterized in that: The method comprises the following steps: acquiring remote sensing images of a target river in dry season and flood season, and extracting river hydrological characteristic parameters through band fusion processing; dividing an equal-interval cross-section array along the direction of the target river based on the river hydrological characteristic parameters, and determining core morphological parameters, wherein the core morphological parameters include water surface width ratio in dry season and flood season, flood season eccentricity, and river channel flow symmetry; performing multi-scale morphological clustering analysis based on the spatial distribution of the core morphological parameters, and dividing the target river into a plurality of dominant morphological units according to the clustering results; dividing the corresponding river section into a plurality of independent management units according to the morphological characteristics of the dominant morphological units, and matching the corresponding management module from a preset management module library, wherein each management module comprises a plurality of management schemes; real-time collection of the management recovery amount of each independent management unit during the management process, evaluation of the management effect of the corresponding independent management unit according to the management recovery amount, and triggering a backtracking optimization mechanism when the management is invalid to iteratively optimize the management scheme under the management module until the management effective condition is reached; wherein the step of dividing the corresponding river section into a plurality of independent management units according to the morphological characteristics of the dominant morphological units comprises: extracting the core morphological parameters of the continuous cross-sections in each dominant morphological unit, and calculating the coefficient of variation of each core morphological parameter in the corresponding dominant morphological unit; when the coefficient of variation is less than or equal to a preset variation threshold, the corresponding entire dominant morphological unit is directly recorded as an initialized management unit; when the coefficient of variation is greater than the preset variation threshold, secondary clustering analysis is performed on the corresponding dominant morphological unit to form sub-unit partitions, and a management unit division point is added at the boundary of the sub-unit partitions to divide the dominant morphological unit into a plurality of initialized management units; length verification of each initialized management unit; if the length of the initialized management unit is less than or equal to a preset length threshold, the initialized management unit is directly retained as an independent management unit; if the length of the initialized management unit is greater than the preset length threshold, the initialized management unit is cut according to the length threshold to form a plurality of independent management units.

2. The method according to claim 1, wherein: The step of acquiring remote sensing images of a target river in dry season and flood season, and extracting river hydrological characteristic parameters through band fusion processing comprises: preprocessing the remote sensing images in dry season and flood season to remove cloud and fog interference and geometric distortion to obtain corrected remote sensing images; performing fusion processing of the panchromatic band and the multispectral band on the corrected remote sensing images to generate fusion data; calculating the normalized difference water index based on the fusion data, and extracting river water information by threshold segmentation; identifying the river boundary and the main flow direction line from the river entity information, and determining the width, curvature and flood season inundation range of the river through the river boundary and the main flow direction line; record the width, curvature and flood season inundation range of the river as the river hydrological characteristic parameters.

3. The method according to claim 2, wherein: The step of dividing an equal-interval cross-section array along the direction of the target river based on the river hydrological characteristic parameters, and determining core morphological parameters comprises: arranging a plurality of cross-section lines perpendicular to the flow direction at the center position of the river main flow direction line, wherein the cross-section lines are distributed at equal intervals along the direction of the river. The cross-section width is determined by the intersection of each section line and the river boundary, and the water surface width ratio is calculated by combining the water level difference between the flood season and the dry season; The offset distance of the intersection point of the main flow direction line and the section line in the flood season is calculated, and recorded as the flood season eccentricity; The river channel flow direction of the target river is obtained, and the river channel flow symmetry is calculated by the angle between the flow direction and the section line; The water surface width ratio, the flood season eccentricity and the river channel flow symmetry are recorded as the core morphological parameters.

4. The method according to claim 1, wherein: The step of performing multi-scale morphological clustering analysis based on the spatial distribution of the core morphological parameters, and dividing the target river into a plurality of dominant morphological units according to the clustering results, comprises: Taking each section position as a spatial node, the water surface width ratio, the flood season eccentricity and the river channel flow symmetry of the corresponding section are combined as a morphological feature vector to form a spatial sequence matrix along the river direction; The correlation analysis is performed on the morphological feature vectors of adjacent spatial positions to identify the morphological feature similarity between adjacent sections, and the clustering interval is divided according to the similarity degree; The principal component analysis is performed on the morphological feature vectors in each clustering interval to extract the principal component scores and record them as comprehensive representation indexes; According to the contribution of the comprehensive representation indexes to the river morphological features, the dominant feature type of the river morphology in each clustering interval is determined, and the river reaches with the same dominant feature type are merged into a dominant morphological unit.

5. The method according to claim 4, wherein: The step of determining the dominant feature type of the river morphology in each clustering interval according to the contribution of the comprehensive representation indexes to the river morphological features: The variance contribution rate of the principal component analysis in each clustering interval is obtained, and the cumulative variance contribution rate of each principal component is obtained by item-by-item cumulative calculation; The principal component whose cumulative contribution rate first reaches the preset evaluation threshold is selected as the key principal component, and the comprehensive representation index corresponding to the key principal component is marked as the high contribution index; The load coefficient between the high contribution index and the original morphological feature vector is analyzed, and the morphological feature variable with the largest absolute value of the load coefficient is recorded as the dominant feature factor; The appearance frequency of the dominant feature factor of all high contribution indexes in each clustering interval is counted, and the dominant feature factor with the highest appearance frequency is determined as the dominant feature type of the river morphology in the corresponding clustering interval.

6. The method of claim 1, wherein: The step of evaluating the management effect of the corresponding independent management unit according to the management recovery amount evaluation, comprises: A plurality of sample collection nodes are set in the management period, and the management recovery amount under each sample collection node is collected; The difference value of adjacent management recovery amounts is calculated, and the management recovery rate of the independent management unit is determined according to the difference value result; The target recovery amount is obtained, and the management completion degree index is calculated by combining the management recovery rate, and the management completion degree index is compared with the preset completion degree threshold; When the management completion degree index is greater than or equal to the preset completion degree threshold, it is determined that the management effect of the corresponding independent management unit is effective management; When the management completion degree index is less than the preset completion degree threshold, it is determined that the management effect of the corresponding independent management unit is ineffective management.

7. The method according to claim 1, wherein the method is characterized in that: The step of triggering the backtracking optimization mechanism when the management is ineffective to iteratively optimize the management scheme under the management module, comprises: extract the difference value between the core morphological parameter of the independent governance unit under invalid governance and the core morphological parameter of the initial governance scheme, and record it as a parameter deviation amount; modify the morphological control parameters in the initial governance scheme according to the parameter deviation amount to form a modified governance scheme; re-execute governance simulation on the independent governance unit in combination with the modified governance scheme, and collect the governance recovery amount in the simulation process; re-calculate the governance completion degree index according to the governance recovery amount in the simulation process, and compare the re-calculated governance completion degree index with the preset completion degree threshold value, if the governance completion degree index is still less than the preset completion degree threshold value, then repeat the parameter deviation amount extraction, governance scheme modification and governance simulation until the governance completion degree index reaches or exceeds the preset completion degree threshold value, and complete the closed-loop adjustment of the backtracking optimization mechanism; wherein, if the governance completion degree threshold value is still not reached after continuous N times of parameter modification, an alarm prompt is sent to the management end, and the execution process of the current backtracking optimization mechanism is terminated, and the corresponding independent governance unit is marked as an abnormal governance unit.

8. A river quasi-natural assembled harnessing planning system, characterized in that: The river quasi-natural assembly type governance planning method of any one of claims 1 to 7 comprises: a data acquisition module configured to obtain remote sensing images of a target river in dry season and flood season, and extract river hydrological feature parameters through band fusion processing; a parameter extraction module configured to divide an equal-interval section array along the direction of the target river based on the river hydrological feature parameters, and determine core morphological parameters, wherein the core morphological parameters include water surface width ratios in dry season and flood season, flood season eccentric distances, and river channel flow symmetry degrees; a unit division module configured to perform multi-scale morphological clustering analysis based on the spatial distribution of the core morphological parameters, and divide the target river into a plurality of dominant morphological units according to the clustering results; a scheme matching module configured to divide the corresponding river section into a plurality of independent governance units according to the morphological characteristics of the dominant morphological units, and match the corresponding governance modules from a preset governance module library, wherein each governance module includes a plurality of governance schemes; a governance evaluation module configured to collect the governance recovery amount of each independent governance unit in the governance process in real time, evaluate the governance effect of the corresponding independent governance unit according to the governance recovery amount, and trigger a backtracking optimization mechanism when the governance is invalid to iteratively optimize the governance scheme under the governance module until the governance effective condition is reached.

9. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable 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 execute the river quasi-natural assembly type governance planning method of any one of claims 1 to 7. The electronic device comprises: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable 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 execute the river quasi-natural assembly type governance planning method of any one of claims 1 to 7.

Images