A river classification method based on the water ecological environment protection stage of small watersheds

Abstract

The present invention relates to the technical field of water ecological protection, and in particular to a method for river type classification based on the water ecological environment protection stage of a small watershed. The method comprises the following steps: obtaining historical river water area data; obtaining a target watershed image using machine vision technology; performing water flow path analysis on the target watershed image to generate a water flow path network structure; collecting biological samples from the target river and performing genome sequencing processing to generate biological genome data; mining memory information on the biological genome data to obtain watershed memory data; performing environmental change association analysis on the watershed memory data to generate gene-environment evolution data; reconstructing the watershed evolution trajectory of the gene-environment evolution data based on the historical river water area data to construct a watershed evolution trajectory; performing watershed evolution morphological analysis on the water flow path network structure through the watershed evolution trajectory to generate watershed evolution morphological data. The present invention realizes efficient and accurate river division.

Description

Technical Field

[0001] The present invention relates to the technical field of water ecological protection, and in particular to a method for classifying river types based on the water ecological environmental protection stage of a small watershed. Background Art

[0002] In the stage of water ecological environment protection in small watersheds, the classification of river types is one of the key tasks to achieve refined management and effective protection. With the improvement of environmental protection awareness and the advancement of science and technology, the traditional river classification method can no longer meet the refined needs of small watershed water ecological environment. In the traditional river classification method, manual observation and manual measurement are often used to record and analyze river characteristics. This method often has problems such as low work efficiency and inaccurate data analysis. Therefore, a river classification method based on advanced technology is needed to provide more accurate and comprehensive river classification information. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a river type classification method based on the water ecological environment protection stage of a small watershed to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for classifying river types based on the water ecological environment protection stage of a small watershed, comprising the following steps:

[0005] Step S1: Obtain historical river water area data; use machine vision technology to obtain a target watershed image; perform water flow path analysis on the target watershed image to generate a water flow path network structure; collect biological samples from the target river and perform genome sequencing to generate biological genome data;

[0006] Step S2: mining memory information on biological genome data to obtain watershed memory data; performing environmental change association analysis on watershed memory data to generate gene-environment evolution data;

[0007] Step S3: reconstructing the basin evolution trajectory of the gene-environment evolution data based on the historical river water area data to construct the basin evolution trajectory; performing basin evolution morphological analysis on the water flow path network structure through the basin evolution trajectory to generate basin evolution morphological data;

[0008] Step S4: Performing hydrological suppression and regulation analysis on the watershed evolution morphology data to generate hydrological dynamic constraint rules; performing evolution trend prediction on the watershed evolution morphology data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model;

[0009] Step S5: using the evolution trend prediction model to perform water ecological structure analysis on the target watershed image to generate watershed water ecological structure data; performing niche health impairment calculation on the watershed water ecological structure data to generate an ecological niche health impairment index;

[0010] Step S6: Using the preset niche health impairment threshold index to determine the basin health of the niche health impairment index, the river types are divided into damaged rivers, repaired rivers and protected rivers.

[0011] The present invention can provide a historical record of basin evolution by acquiring historical river water data, providing basic data for subsequent analysis and comparison. Using machine vision technology to acquire images of target basins can improve the efficiency and accuracy of data acquisition. Water flow path analysis can help understand the flow of water in the target basin. Biological sample collection and genome sequencing processing can obtain biological genome data in the target river, providing data support for subsequent memory information mining and gene-environment evolution analysis. Memory information mining can identify and extract memory information about basin evolution from biological genome data, providing a basis for subsequent reconstruction of evolution trajectories. Environmental change association analysis can associate basin memory data with environmental factors, revealing the relationship between genes and the environment. The reconstruction of basin evolution trajectories can reveal the historical process of basin evolution and help understand the dynamic changes of basins. Basin evolution morphological data can provide information about basin morphological characteristics, providing a basis for subsequent hydrological inhibition and regulation analysis and evolution trend prediction. Hydrological inhibition and regulation analysis can reveal the impact of hydrological factors on the evolution of the basin, and provide hydrological dynamic constraint rules for subsequent evolution trend predictions. The evolution trend prediction model can predict the basin evolution morphology and gene-environment evolution data based on the hydrological dynamic constraint rules, and provide information on the future development trend of the basin. The water ecological structure analysis can analyze the target basin image through the evolution trend prediction model to understand the composition and structure of the water ecosystem and provide data support for the subsequent niche health impairment calculation. The niche health impairment calculation can evaluate the niche health status of the basin. By analyzing the basin water ecological structure data, the degree of niche impairment can be quantified. The niche health impairment index can be compared with the preset niche health impairment threshold index to judge the health status of the basin and then divide the river types. The division of river types can help evaluate the ecological health status of the river, guide the formulation of relevant management and protection measures, and improve the sustainable development capacity of the basin.

[0012] Preferably, step S1 comprises the following steps:

[0013] Step S11: Acquire historical river water area data;

[0014] Step S12: using machine vision technology to obtain the target watershed image;

[0015] Step S13: performing water flow layering and flow direction identification on the target watershed image to obtain water flow direction data;

[0016] Step S14: performing water flow path analysis on the water flow direction data to obtain water flow path distribution data;

[0017] Step S15: performing flow direction connection processing on the water flow path distribution data to construct a water flow path network structure;

[0018] Step S16: Collect biological samples from the target river and perform genome sequencing to generate biological genome data.

[0019] The present invention provides a record of the past state of the river through historical river water data, including information such as water level, flow rate, and river channel morphology, which can be used to analyze and compare river changes in different time periods. Historical data can also be used as baseline data to evaluate current and future river conditions and formulate relevant management and protection measures. Machine vision technology can obtain image data of the target watershed in an automated manner to improve the efficiency and accuracy of data acquisition. The target watershed image can provide visual information on the spatial distribution and morphological characteristics of the watershed, providing basic data for subsequent analysis and processing. Water flow stratification and direction recognition can identify the water flow in the target watershed image in layers, that is, divide the water flow into different layers according to different water flow depths or speeds. Obtaining water flow direction data can understand the flow direction and path of the water flow at different levels, providing basic information for subsequent flow direction connection processing and water flow path analysis. The analysis can reveal the flow path of water in the target watershed, including the main water flow channels, tributaries, confluence points, etc. Obtaining the water flow path distribution data can help understand the distribution and flow characteristics of water flow, and provide a basis for subsequent flow connection processing and water flow network structure construction. Flow connection processing can connect different water flow paths to establish a water flow network, reflecting the distribution and connectivity of water flow in the entire watershed. Building a water flow network structure can provide an overall understanding of the water flow system in the basin, and provide basic data for subsequent river type classification and watershed analysis. Genome sequencing processing can perform genomic analysis on the collected biological samples to obtain biological genome data, including gene sequence, gene expression and other information. Biological genome data can provide information about the basin's biodiversity, genetic characteristics, and the interaction between organisms and the environment, providing data support for river type classification and basin ecological research.

[0020] Preferably, step S2 comprises the following steps:

[0021] Step S21: performing genome sequencing on the biological genome data to generate genome sequence data;

[0022] Step S22: mining memory information of genome sequence data according to historical river water area data to obtain watershed memory data;

[0023] Step S23: using a neural network algorithm to extract environmental response code table features from the genome sequence data to generate an environmental response feature sequence;

[0024] Step S24: Perform environmental change association analysis on the watershed memory data through the environmental response feature sequence to generate gene-environment evolution data.

[0025] The present invention can sequence genes in biological samples through genome sequencing to obtain genome sequence data, i.e., DNA sequence. Generating genome sequence data can provide genetic information about biological individuals, including genome structure, gene position, sequence variation, etc., and provide a data basis for subsequent memory information mining and environmental response feature extraction. Memory information mining can associate genome sequence data with historical river water data and explore genetic information related to river environmental changes in genome sequences. Obtaining watershed memory data can reveal watershed memory features in genome sequences, i.e., genetic information related to river environmental changes stored in genomes. Neural network algorithms can analyze and pattern recognize genome sequence data and extract features related to environmental responses. Environmental response code table feature extraction can encode environmental response signals in genome sequences into feature sequences, reflecting the genetic responses of biological individuals to river environmental changes. Environmental change association analysis can associate environmental response feature sequences with watershed memory data and reveal the relationship between genomes and river environmental changes. Generating gene-environment evolution data can provide information about the interaction between genomes and river environments, including the degree of association between genes and environmental changes, genome response patterns, etc., and provide genetic ecology data support for river type classification and watershed ecological research.

[0026] Preferably, step S3 comprises the following steps:

[0027] Step S31: performing a dynamic evolution mechanism analysis on the gene-environment evolution data based on historical river water area data to generate watershed dynamic evolution mechanism data;

[0028] Step S32: performing evolution path reverse processing on the water flow path network structure through the basin dynamic evolution mechanism data to construct the evolution path reverse result;

[0029] Step S33: reconstructing the watershed evolution trajectory based on the evolution path inversion result to construct the watershed evolution trajectory;

[0030] Step S34: performing topological structure evolution analysis on the water flow path network structure to generate topological structure evolution data;

[0031] Step S35: performing succession trajectory analysis on the topological structure evolution data through the watershed evolution trajectory to generate deformation trajectory data;

[0032] Step S36: Performing a watershed evolution morphology analysis on the water flow path network structure through the deformation trajectory data to generate watershed evolution morphology data.

[0033] The present invention can associate gene-environment evolution data with historical river water data through dynamic evolution mechanism analysis, revealing the dynamic evolution mechanism between genome and river environmental changes. Generating basin dynamic evolution mechanism data can provide information on the interaction between genome and environment in the evolution of river ecosystem, including the response pattern of genes to environmental changes, the selection pressure of the environment on the genome, etc., providing a genetic ecological basis for the dynamic evolution mechanism for river type classification. The evolution path reverse processing can infer the evolution path of the water flow network structure based on the basin dynamic evolution mechanism data, that is, the change process of the water flow at different time points. Constructing the evolution path reverse result can provide the evolution history information of the water flow network structure, providing a data basis for the subsequent reconstruction of the basin evolution trajectory and the topological structure evolution analysis. The basin evolution trajectory reconstruction can reconstruct the evolution trajectory of the water flow network structure based on the evolution path reverse result, that is, the spatial structure of the basin at different time points. Change process, topological structure evolution analysis can extract and analyze the topological characteristics of water flow network structure, reveal the law of topological structure evolution in river system, and generate topological structure evolution data, which can provide information about the change of topological structure of river system, including river channel connectivity, branch changes, etc. Deformation trajectory analysis can explore the morphological evolution process in river system according to basin evolution trajectory and topological structure evolution data, including spatial distribution and time series of morphological changes. Generating deformation trajectory data can provide information about river morphological changes, including river channel erosion, sedimentation, geomorphic evolution, etc., and provide data basis for basin evolution morphological analysis. Basin evolution morphological analysis can study the evolution morphological characteristics of water flow network structure according to deformation trajectory data, including river morphological type, geomorphic characteristics, etc. Generating basin evolution morphological data can provide information about morphological changes of river system, and provide data support of morphological characteristics for river type classification and basin ecological research.

[0034] Preferably, step S32 includes the following steps:

[0035] Step S321: performing evolution time series analysis on the gene-environment evolution data to generate evolution time series data;

[0036] Step S322: identifying succession nodes of the water flow path network structure through the evolution time series data to generate water flow path succession nodes;

[0037] Step S323: performing succession drive association analysis on water flow path succession nodes through the basin dynamic evolution mechanism data to generate a succession drive association chain;

[0038] Step S324: using the succession driven association chain to analyze the evolution law of the water flow path succession nodes to generate evolution law data;

[0039] Step S325: Perform evolution path reverse processing on the water flow path network structure through the evolution law data to construct an evolution path reverse result.

[0040] The present invention can analyze the changes in gene-environment evolution data in time series through evolutionary time series analysis, revealing the patterns and trends of genome and environmental factors evolving over time. The generated evolutionary time series data can provide time information about genome and environmental evolution, and provide a data basis for subsequent water flow network succession node identification and evolution law analysis. Water flow succession node identification can determine the key nodes in the water flow network structure based on the evolutionary time series data, that is, the position or characteristics of the important change points in the evolution process. The generated water flow succession nodes can provide node information about the changes in the water flow network structure, and provide a data basis for subsequent succession driven association analysis and evolution law analysis. Succession driven association analysis can use the dynamic evolution mechanism data of the watershed to explore the water flow path. The correlation between succession nodes and genome-environment evolution, that is, determining the factors or mechanisms that drive the changes in succession nodes, generating succession-driven association chains can provide correlation information between water path succession nodes and genome-environment evolution, and provide a data basis for subsequent evolution law analysis and evolution path reverse processing. The evolution law analysis can reveal the evolution laws and trends of water path succession nodes based on the succession-driven association chains, including the formation, disappearance, and change frequency of nodes. The evolution path reverse processing can infer the evolution path of the water path network structure based on the evolution law data, that is, the change process of the water path at different time points. The construction of the evolution path reverse result can provide the evolution history information of the water path network structure, and provide a data basis for the classification of river types and the reconstruction of basin evolution trajectories.

[0041] Preferably, step S4 comprises the following steps:

[0042] Step S41: performing a hydrological model quantitative analysis on the basin evolution morphology data to generate hydrological model data;

[0043] Step S42: extracting response rules of the watershed evolution morphology data through hydrological model data to generate constraint response rules;

[0044] Step S43: performing hydrological suppression and regulation analysis on the constraint response law to generate hydrological dynamic constraint rules;

[0045] Step S44: Predict the evolution trend of the watershed evolution morphological data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model.

[0046] The present invention can establish a mathematical model to describe the hydrological process of the basin, including the rainfall-runoff relationship, water level changes, etc., based on the basin evolution morphological data through quantitative analysis of hydrological patterns. The generated hydrological pattern data can provide a quantitative description of the basin hydrological process, and provide a data basis for the subsequent response law extraction and hydrological dynamic constraint rule analysis. The response law extraction can use the hydrological pattern data to analyze the correlation between the basin evolution morphological data and the hydrological process, and find out the change law of the morphological data under different hydrological conditions. The generated constraint response law can provide the response information of the basin evolution morphological data to the change of hydrological conditions. The hydrological inhibition and regulation analysis can explore the inhibitory or regulatory effect of hydrological conditions on the basin evolution morphology based on the constraint response law, that is, determine the constraint rules of hydrological conditions on morphological evolution. The generated hydrological dynamic constraint rules can provide the constraint information of the change of hydrological conditions on the basin evolution morphology. Evolution trend prediction can be based on hydrological dynamic constraint rules, combined with watershed evolution morphology data and gene-environment evolution data, to predict the changing trend of watershed evolution morphology in the future. Constructing an evolution trend prediction model can provide prediction results on the future development of watershed evolution morphology, and provide a reference for river type classification and watershed management decision-making.

[0047] Preferably, step S44 includes the following steps:

[0048] Step S441: Predicting the river basin area trend based on the basin evolution morphology data according to the hydrological dynamic constraint rules to generate basin area trend data;

[0049] Step S442: performing environmental response trend analysis on the gene-environment evolution data to generate environmental change response trend data;

[0050] Step S443: predicting the hydrological environmental deformation of the water flow path network structure according to the hydrological dynamic constraint rules to generate hydrological environmental deformation data;

[0051] Step S444: predicting the gene-environment evolution coupling law for the environmental change response trend data and the hydrological environment deformation data to generate the gene-environment linkage response law;

[0052] Step S445: fitting the evolution model to the watershed area trend data and the watershed evolution morphology data according to the gene-environment linkage response law to construct an evolution trend prediction model.

[0053] The present invention can predict the area trend of a river basin by analyzing and modeling the basin evolution morphological data. This helps to understand the changes in rivers over time, provides prediction information on the evolution of basin area over time, and can classify and divide different rivers based on basin area trend data. Different types of rivers may have different hydrological characteristics and ecological environmental conditions, which is of great significance for scientific research, water resources management and ecological protection. By analyzing the gene-environment evolution data, the impact and response of environmental changes on the genome can be understood. This helps to reveal the role of environmental factors in the evolution and adaptive changes of biological populations, and provides a scientific basis for environmental management and biodiversity protection. By analyzing the environmental response trend, data related to environmental transformation can be generated to describe the trend and pattern of environmental change. These data can provide quantitative analysis of environmental changes, help understand and predict the evolution process of ecosystems, and predict the deformation of the hydrological environment by analyzing and modeling the water flow network structure. This helps to understand the changes in the water flow network, including the evolution trend of hydrological characteristics such as river flow direction, water flow velocity, and water level. By analyzing and modeling the water flow network structure, the deformation of the hydrological environment can be predicted. This helps to understand the changes in the water flow network, including the evolution trend of hydrological characteristics such as river flow direction, water flow velocity, and water level. By analyzing and modeling the environmental change response trend data and hydrological environment deformation data, the interaction and coupling laws between the genome and the environment can be inferred. This helps to understand the adaptive response of biological populations to environmental changes and the impact of the environment on genome evolution.

[0054] Preferably, step S5 comprises the following steps:

[0055] Step S51: using the evolution trend prediction model to analyze the type of aquatic biological community on the target watershed image to generate aquatic biological community data;

[0056] Step S52: Perform biodiversity statistics on the water community data to obtain a biodiversity index;

[0057] Step S53: performing community structure analysis on the water biological community data according to the biodiversity index to generate watershed water ecological structure data;

[0058] Step S54: Calculating the niche width of the watershed water ecological structure data to generate a niche width index;

[0059] Step S55: performing ecological overlap analysis on the watershed water ecological structure data based on the niche breadth index to generate an ecological overlap index;

[0060] Step S56: Calculate the ecological niche health impairment of the watershed water ecological structure data using the ecological niche health impairment calculation formula according to the ecological overlap index to generate the ecological niche health impairment index.

[0061] The present invention can determine the distribution of different types of aquatic communities by analyzing the basin image using an evolutionary trend prediction model. This helps to understand the structure and composition of the ecosystem in the basin. Biodiversity statistics can provide information about aquatic biodiversity, including species richness, diversity index, etc. This helps to assess the degree of diversity of the ecosystem in the basin. By analyzing the community structure of aquatic community data, the relationship and distribution pattern between different species can be understood. This helps to understand the structure of the ecosystem in the basin. Niche width calculation can provide information about the functional roles and resource utilization of different species in the ecosystem. Niche width index helps to assess the functional diversity of different species. Ecological overlap analysis allows the identification of the degree of niche overlap between different species, that is, the degree of overlap in their resource utilization. This helps to assess the competition and coexistence relationship between species. Niche health impairment calculation provides an assessment of ecosystem health by comprehensively considering factors such as biodiversity, community structure and niche width. This helps to understand the overall health of the ecosystem in the basin.

[0062] Preferably, the niche health loss calculation formula in step S56 is specifically:

[0063]

[0064] Among them, H is the niche health impairment index, N is the number of existing species in the basin, t is the maximum number of species that the basin can bear, K is the assimilation capacity of the basin ecosystem, r is the species growth rate, g is the average niche width of the species, h is the vegetation coverage rate, and p is the anti-disturbance sensitivity of the basin ecosystem.

[0065] The present invention is achieved by It represents the ratio of the number of existing species in a watershed to the time. It can be used to assess the growth rate of species. A higher value means that the species is relatively large or growing faster, while a lower value means that the species is relatively small or growing slower. Calculate the natural logarithm of the number of species N. By taking the logarithm of the number of species, the impact of extreme values ​​on the niche health impairment index can be weakened, making the index more reflective of the changes in the number of species, and representing the ratio of the species density of the basin to the inverse of the maximum carrying capacity. A smaller density-to-carrying capacity ratio means that the species density is relatively low, and vice versa, it means that the species density is relatively high, (1-e ―rt) is an exponential function of the species growth rate. It describes the growth trend of a species over a given period of time. A higher growth rate will result in an exponential close to 1, while a lower growth rate will result in an exponential close to 0. When the maximum number of species that a watershed can sustain is close to infinity, it corresponds to the long-term stable state of species growth rate, that is, when the number of species in the watershed tends to the maximum value, the stable value of the niche health impairment index takes into account the sensitivity parameter g, stability parameter h and complexity parameter p of the niche. A smaller attenuation function value indicates that the niche has higher stability and complexity, higher resistance to disturbance, can capture the long-term stable state of species growth rate, and help understand the development trend of species number and the stable value of the niche health impairment index.

[0066] Preferably, step S6 comprises the following steps:

[0067] Step S61: when it is determined that the preset ecological niche health impairment threshold index is greater than the ecological niche health impairment index, the river type is classified as a damaged river;

[0068] Step S62: when it is determined that the preset ecological niche health impairment threshold index is equal to the ecological niche health impairment index, the river type is classified as a restoration river;

[0069] Step S63: When it is determined that the preset niche health impairment threshold index is less than the niche health impairment index, the river type is classified as a protected river.

[0070] The present invention classifies a river as a "damaged river" when it determines that the preset niche health impairment threshold index is greater than the niche health impairment index, which indicates that the health of the ecosystem has been seriously damaged. Such classification helps to identify rivers that need urgent protection and restoration so as to take corresponding management and protection measures. Classifying a river as a "repair river" indicates that the health of the ecosystem is close to the threshold but has not yet reached the preset threshold, which helps to identify those rivers that need protection and restoration measures to improve their ecological health. This can also guide managers to take appropriate measures to repair damaged ecosystems. Classifying a river as a "protected river" indicates that the health of the ecosystem is excellent and the health index is higher than the preset threshold. These rivers usually do not require emergency restoration measures, but need to maintain and strengthen management to ensure the long-term health of their ecosystems, which helps to optimize resource allocation and protection policies. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A schematic flow chart of the steps of a method for classifying river types based on the water ecological environment protection stage of a small watershed according to the present invention;

[0072] Figure 2 Detailed implementation flow chart of step S1;

[0073] Figure 3 Detailed implementation flow chart of step S2;

[0074] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0075] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0076] This application example provides a river classification method based on the water ecological environment protection stage of a small watershed. The execution subject of the river classification method based on the water ecological environment protection stage of a small watershed includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of this application, and the data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0077] See also Figures 1 to 4 The present invention provides a method for classifying river types based on the water ecological environment protection stage of a small watershed, the method comprising the following steps:

[0078] Step S1: Obtain historical river water area data; use machine vision technology to obtain a target watershed image; perform water flow path analysis on the target watershed image to generate a water flow path network structure; collect biological samples from the target river and perform genome sequencing to generate biological genome data;

[0079] Step S2: mining memory information on biological genome data to obtain watershed memory data; performing environmental change association analysis on watershed memory data to generate gene-environment evolution data;

[0080] Step S3: reconstructing the basin evolution trajectory of the gene-environment evolution data based on the historical river water area data to construct the basin evolution trajectory; performing basin evolution morphological analysis on the water flow path network structure through the basin evolution trajectory to generate basin evolution morphological data;

[0081] Step S4: Performing hydrological suppression and regulation analysis on the watershed evolution morphology data to generate hydrological dynamic constraint rules; performing evolution trend prediction on the watershed evolution morphology data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model;

[0082] Step S5: using the evolution trend prediction model to perform water ecological structure analysis on the target watershed image to generate watershed water ecological structure data; performing niche health impairment calculation on the watershed water ecological structure data to generate an ecological niche health impairment index;

[0083] Step S6: Using the preset niche health impairment threshold index to determine the basin health of the niche health impairment index, the river types are divided into damaged rivers, repaired rivers and protected rivers.

[0084] The present invention can provide a historical record of basin evolution by acquiring historical river water data, providing basic data for subsequent analysis and comparison. Using machine vision technology to acquire images of target basins can improve the efficiency and accuracy of data acquisition. Water flow path analysis can help understand the flow of water in the target basin. Biological sample collection and genome sequencing processing can obtain biological genome data in the target river, providing data support for subsequent memory information mining and gene-environment evolution analysis. Memory information mining can identify and extract memory information about basin evolution from biological genome data, providing a basis for subsequent reconstruction of evolution trajectories. Environmental change association analysis can associate basin memory data with environmental factors, revealing the relationship between genes and the environment. The reconstruction of basin evolution trajectories can reveal the historical process of basin evolution and help understand the dynamic changes of basins. Basin evolution morphological data can provide information about basin morphological characteristics, providing a basis for subsequent hydrological inhibition and regulation analysis and evolution trend prediction. Hydrological inhibition and regulation analysis can reveal the impact of hydrological factors on the evolution of the basin, and provide hydrological dynamic constraint rules for subsequent evolution trend predictions. The evolution trend prediction model can predict the basin evolution morphology and gene-environment evolution data based on the hydrological dynamic constraint rules, and provide information on the future development trend of the basin. The water ecological structure analysis can analyze the target basin image through the evolution trend prediction model to understand the composition and structure of the water ecosystem and provide data support for the subsequent niche health impairment calculation. The niche health impairment calculation can evaluate the niche health status of the basin. By analyzing the basin water ecological structure data, the degree of niche impairment can be quantified. The niche health impairment index can be compared with the preset niche health impairment threshold index to judge the health status of the basin and then divide the river types. The division of river types can help evaluate the ecological health status of the river, guide the formulation of relevant management and protection measures, and improve the sustainable development capacity of the basin.

[0085] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for classifying river types based on the water ecological environment protection stage of a small watershed according to the present invention. In this example, the steps of the method for classifying river types based on the water ecological environment protection stage of a small watershed include:

[0086] Step S1: Obtain historical river water area data; use machine vision technology to obtain a target watershed image; perform water flow path analysis on the target watershed image to generate a water flow path network structure; collect biological samples from the target river and perform genome sequencing to generate biological genome data;

[0087] In this embodiment, relevant historical river water data, including water velocity, water depth, water quality, water temperature and other information, are collected and obtained, and high-resolution images of the target watershed are obtained using drones, satellite images or other remote sensing technologies. Machine vision technology can help obtain detailed geographic information, including river morphology, vegetation distribution, land use and other target watershed images for water flow path analysis. By identifying river channels, water bodies and nearby terrain features, a water flow path network structure can be generated. This can help understand the direction, distribution and connectivity of rivers, select appropriate sampling points in the target river, collect biological samples, and perform genome sequencing on the collected biological samples. This can be done through modern gene sequencing technologies, such as high-throughput sequencing, to sequence the DNA or RNA in the sample. The sequencing results will provide biological genome data, including information such as species identification, genetic diversity and functional genomes.

[0088] Step S2: mining memory information on biological genome data to obtain watershed memory data; performing environmental change association analysis on watershed memory data to generate gene-environment evolution data;

[0089] In this embodiment, the biological genome data is quality controlled and preprocessed, including removing low-quality sequences, removing contamination and repeated sequences, etc., using the biological genome data for species identification and classification, determining the biological species present in each sample, comparing the genome sequence of the sample with the known reference genome sequence to identify shared gene fragments and genetic variations, and performing association analysis on the biological genome data and environmental factor data to determine the relationship between genes and environmental factors. This can be achieved through methods such as statistical analysis, machine learning or correlation analysis, using methods such as statistical analysis, time series analysis or machine learning to perform pattern recognition and association analysis on watershed memory data and environmental change data to discover potential patterns and trends in gene-environment evolution.

[0090] Step S3: reconstructing the basin evolution trajectory of the gene-environment evolution data based on the historical river water area data to construct the basin evolution trajectory; performing basin evolution morphological analysis on the water flow path network structure through the basin evolution trajectory to generate basin evolution morphological data;

[0091] In this embodiment, the integrated data is modeled using methods such as statistical analysis, time series analysis or machine learning to reconstruct the evolution trajectory of the basin. This can help understand the changing trends and correlations of genes and environmental factors in different time periods, and extract the water flow paths in different time periods based on historical river water data and the reconstructed basin evolution trajectory. The water flow path can be determined by information such as changes in the river channel, the segmentation and connection of the basin, and the morphological parameters of the extracted water flow path are calculated, including the length of the river channel, the number of branches, the width of the river channel, the elevation of the riverbed, etc. This can be used to describe the evolutionary morphology of the water flow path network over time, organize the morphological parameter data of the water flow path network into a format suitable for analysis, and perform statistics and aggregation. This can help understand the changing trends and laws of the basin morphology, and use visualization tools or techniques to display the basin evolution morphological data in the form of charts, images or animations. This can help to more intuitively understand the evolution process and morphological changes of the water flow path network.

[0092] Step S4: Performing hydrological suppression and regulation analysis on the watershed evolution morphology data to generate hydrological dynamic constraint rules; performing evolution trend prediction on the watershed evolution morphology data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model;

[0093] In the present embodiment, according to the basin evolution morphological data, hydrological inhibition adjustment parameters are calculated, such as river capacity, sedimentation rate, water level change, etc. These parameters reflect the inhibition and regulation of the hydrological process to the basin evolution, and based on the calculated hydrological inhibition adjustment parameters, hydrological dynamic constraint rules are generated. These rules can describe the restriction and regulation relationship of the basin evolution morphology under different hydrological conditions, integrate the basin evolution morphological data and gene-environment evolution data, and select relevant features according to the prediction target. Select appropriate prediction model, such as regression model, time series model or machine learning model, and use historical data to carry out model training. This can be used to learn the relationship between basin evolution morphology and gene-environment evolution, and predict future trends. This can help determine the variables and features used for prediction, evaluate the evolution trend prediction model constructed, use suitable evaluation indicators to evaluate model performance, and optimize and adjust the model as needed to improve the accuracy and stability of prediction.

[0094] Step S5: using the evolution trend prediction model to perform water ecological structure analysis on the target watershed image to generate watershed water ecological structure data; performing niche health impairment calculation on the watershed water ecological structure data to generate an ecological niche health impairment index;

[0095] In this embodiment, the preprocessed image is segmented to extract the characteristics of the watershed, such as river length, lake area, wetland distribution, etc. This can help understand the water ecological structure characteristics of the watershed, and use the evolution trend prediction model to predict the water ecological structure of the target watershed. According to the historical data and the relationship learned by the model, the future state of the water ecological structure is predicted, and the niche index is calculated based on the watershed water ecological structure data. The niche index reflects the relationship between the niche capacity and niche utilization of the watershed, and can be used to assess the health of the niche of the watershed. Based on the calculated niche index, the health impairment index is calculated. The health impairment index reflects the health and impairment of the niche of the watershed, and can be used to assess the health of the watershed ecosystem.

[0096] Step S6: Using the preset niche health impairment threshold index to determine the basin health of the niche health impairment index, the river types are divided into damaged rivers, repaired rivers and protected rivers.

[0097] In this embodiment, a niche health impairment threshold index is preset. This threshold index will be used to judge the health of the basin based on the niche health impairment index to divide the river type, and the calculated niche health impairment index will be compared with the preset niche health impairment threshold index. If the niche health impairment index is lower than the threshold index, the basin can be judged as a protected river; if the niche health impairment index is higher than the threshold index, the basin can be judged as a damaged river; if the niche health impairment index is within the threshold index range, the basin can be judged as a repaired river. According to the results of the index comparison, the basin is divided into corresponding river types, including damaged rivers, repaired rivers and protected rivers. In this way, corresponding management and protection measures can be taken for different types of rivers.

[0098] In this embodiment, reference Figure 2 The above is a schematic flow chart of the detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0099] Step S11: Acquire historical river water area data;

[0100] Step S12: using machine vision technology to obtain the target watershed image;

[0101] Step S13: performing water flow layering and flow direction identification on the target watershed image to obtain water flow direction data;

[0102] Step S14: performing water flow path analysis on the water flow direction data to obtain water flow path distribution data;

[0103] Step S15: performing flow direction connection processing on the water flow path distribution data to construct a water flow path network structure;

[0104] Step S16: Collect biological samples from the target river and perform genome sequencing to generate biological genome data.

[0105] The present invention provides a record of the past state of the river through historical river water data, including information such as water level, flow rate, and river channel morphology, which can be used to analyze and compare river changes in different time periods. Historical data can also be used as baseline data to evaluate current and future river conditions and formulate relevant management and protection measures. Machine vision technology can obtain image data of the target watershed in an automated manner to improve the efficiency and accuracy of data acquisition. The target watershed image can provide visual information on the spatial distribution and morphological characteristics of the watershed, providing basic data for subsequent analysis and processing. Water flow stratification and direction recognition can identify the water flow in the target watershed image in layers, that is, divide the water flow into different layers according to different water flow depths or speeds. Obtaining water flow direction data can understand the flow direction and path of the water flow at different levels, providing basic information for subsequent flow direction connection processing and water flow path analysis. The analysis can reveal the flow path of water in the target watershed, including the main water flow channels, tributaries, confluence points, etc. Obtaining the water flow path distribution data can help understand the distribution and flow characteristics of water flow, and provide a basis for subsequent flow connection processing and water flow network structure construction. Flow connection processing can connect different water flow paths to establish a water flow network, reflecting the distribution and connectivity of water flow in the entire watershed. Building a water flow network structure can provide an overall understanding of the water flow system in the basin, and provide basic data for subsequent river type classification and watershed analysis. Genome sequencing processing can perform genomic analysis on the collected biological samples to obtain biological genome data, including gene sequence, gene expression and other information. Biological genome data can provide information about the basin's biodiversity, genetic characteristics, and the interaction between organisms and the environment, providing data support for river type classification and basin ecological research.

[0106] In this embodiment, historical river water area data is collected, including relevant data such as water area range, water level, flow rate, water quality, etc. This can be obtained through existing hydrological measurement stations, remote sensing data, historical records, etc., and the collected historical river water area data is sorted and cleaned. Ensure the accuracy and completeness of the data, remove outliers and duplicate data, and use machine vision technologies such as drones and aerial photography to obtain image data of the target basin. Ensure that the image covers the scope of the target basin and ensures image quality and resolution, and pre-process the collected images, including image correction, denoising, image enhancement, etc. This can improve the quality and accuracy of the image, facilitate subsequent water flow stratification and flow direction identification and analysis, and use image processing and computer vision technology to identify the water flow stratification flow direction of the target basin image. This can identify the position and flow direction of different water flow stratifications based on the characteristics of water body color, texture, shape, etc., and extract water flow direction data from the identified water flow stratification image. This can obtain water flow direction information by analyzing the position and direction of water flow stratification, and process and analyze the water flow direction data to obtain water flow path distribution data. This can include calculating the frequency, density, length and other indicators of the water flow direction to describe the distribution of the water flow path, visually displaying the water flow path distribution data, such as drawing flow direction diagrams, heat maps, etc., and performing flow connection processing on the water flow path distribution data to connect adjacent water flow paths to form a water flow path network structure. This can be connected based on the continuity and similarity of the water flow paths, and the water flow path network structure can be constructed based on the connected water flow path data. This can represent the water flow paths as nodes, and the connection relationship between the water flow paths as edges to form a water flow path network.

[0107] In this embodiment, reference Figure 3 The above is a schematic flow chart of the detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0108] Step S21: performing genome sequencing on the biological genome data to generate genome sequence data;

[0109] Step S22: mining memory information of genome sequence data according to historical river water area data to obtain watershed memory data;

[0110] Step S23: using a neural network algorithm to extract environmental response code table features from the genome sequence data to generate an environmental response feature sequence;

[0111] Step S24: Perform environmental change association analysis on the watershed memory data through the environmental response feature sequence to generate gene-environment evolution data.

[0112] The present invention can sequence genes in biological samples through genome sequencing to obtain genome sequence data, i.e., DNA sequence. Generating genome sequence data can provide genetic information about biological individuals, including genome structure, gene position, sequence variation, etc., and provide a data basis for subsequent memory information mining and environmental response feature extraction. Memory information mining can associate genome sequence data with historical river water data and explore genetic information related to river environmental changes in genome sequences. Obtaining watershed memory data can reveal watershed memory features in genome sequences, i.e., genetic information related to river environmental changes stored in genomes. Neural network algorithms can analyze and pattern recognize genome sequence data and extract features related to environmental responses. Environmental response code table feature extraction can encode environmental response signals in genome sequences into feature sequences, reflecting the genetic responses of biological individuals to river environmental changes. Environmental change association analysis can associate environmental response feature sequences with watershed memory data and reveal the relationship between genomes and river environmental changes. Generating gene-environment evolution data can provide information about the interaction between genomes and river environments, including the degree of association between genes and environmental changes, genome response patterns, etc., and provide genetic ecology data support for river type classification and watershed ecological research.

[0113] In this embodiment, a biological sample is prepared, and DNA or RNA is extracted therefrom. This may include extracting biological samples from collected water samples, sediments or aquatic organisms, and performing genome sequencing on the extracted biological samples to obtain genome sequence data. This can be done by using modern gene sequencing technology, such as high-throughput sequencing technology, to sequence DNA or RNA, and using data mining technology, such as association rule mining, time series analysis, etc., to perform association analysis on genome sequence data and historical river water data. This can mine memory information related to water data in genome sequence data, and use a neural network algorithm to build a feature extraction model, which can extract features of environmental response from genome sequence data. This may include convolutional neural networks (CNN), recurrent neural networks (RNN), etc., and use the constructed neural network model to extract features from genome sequence data. The model will learn and capture features related to environmental response in the genome sequence, generate environmental response feature sequences, and use environmental response feature sequences and environmental change data for association analysis. This can use statistical analysis methods, machine learning algorithms, etc. to explore the association between genome sequences and environmental changes, and generate gene-environment evolution data based on the results of environmental change association analysis. These data can describe the relationship between genome sequences and watershed environmental changes, and can be used to study the response and adaptive evolution of the genome to environmental changes.

[0114] In this embodiment, reference Figure 4The above is a schematic flow chart of the detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0115] Step S31: performing a dynamic evolution mechanism analysis on the gene-environment evolution data based on historical river water area data to generate watershed dynamic evolution mechanism data;

[0116] Step S32: performing evolution path reverse processing on the water flow path network structure through the basin dynamic evolution mechanism data to construct the evolution path reverse result;

[0117] Step S33: reconstructing the watershed evolution trajectory based on the evolution path inversion result to construct the watershed evolution trajectory;

[0118] Step S34: performing topological structure evolution analysis on the water flow path network structure to generate topological structure evolution data;

[0119] Step S35: performing succession trajectory analysis on the topological structure evolution data through the watershed evolution trajectory to generate deformation trajectory data;

[0120] Step S36: Performing a watershed evolution morphology analysis on the water flow path network structure through the deformation trajectory data to generate watershed evolution morphology data.

[0121] The present invention can associate gene-environment evolution data with historical river water data through dynamic evolution mechanism analysis, revealing the dynamic evolution mechanism between genome and river environmental changes. Generating basin dynamic evolution mechanism data can provide information on the interaction between genome and environment in the evolution of river ecosystem, including the response pattern of genes to environmental changes, the selection pressure of the environment on the genome, etc., providing a genetic ecological basis for the dynamic evolution mechanism for river type classification. The evolution path reverse processing can infer the evolution path of the water flow network structure based on the basin dynamic evolution mechanism data, that is, the change process of the water flow at different time points. Constructing the evolution path reverse result can provide the evolution history information of the water flow network structure, providing a data basis for the subsequent reconstruction of the basin evolution trajectory and the topological structure evolution analysis. The basin evolution trajectory reconstruction can reconstruct the evolution trajectory of the water flow network structure based on the evolution path reverse result, that is, the spatial structure of the basin at different time points. Change process, topological structure evolution analysis can extract and analyze the topological characteristics of water flow network structure, reveal the law of topological structure evolution in river system, and generate topological structure evolution data, which can provide information about the change of topological structure of river system, including river channel connectivity, branch changes, etc. Deformation trajectory analysis can explore the morphological evolution process in river system according to basin evolution trajectory and topological structure evolution data, including spatial distribution and time series of morphological changes. Generating deformation trajectory data can provide information about river morphological changes, including river channel erosion, sedimentation, geomorphic evolution, etc., and provide data basis for basin evolution morphological analysis. Basin evolution morphological analysis can study the evolution morphological characteristics of water flow network structure according to deformation trajectory data, including river morphological type, geomorphic characteristics, etc. Generating basin evolution morphological data can provide information about morphological changes of river system, and provide data support of morphological characteristics for river type classification and basin ecological research.

[0122] In the present embodiment, the gene-environment evolution data is analyzed using statistical analysis methods, machine learning algorithms, etc. This can reveal the dynamic evolution mechanism between genes and environmental changes, and generate basin dynamic evolution mechanism data, design an evolution path inversion algorithm, and the algorithm can reverse the evolution path of the water flow path network structure based on the basin dynamic evolution mechanism data. This can be based on simulated annealing algorithms, genetic algorithms and other optimization algorithms for path search, and the basin dynamic evolution mechanism data is processed using the designed evolution path inversion algorithm to reverse the evolution path of the water flow path network structure. This can generate evolution path inversion results, describe the evolution process of the water flow path network structure, and design an evolution trajectory reconstruction algorithm, which can reconstruct the evolution trajectory of the basin based on the evolution path inversion results. This can involve interpolation methods, curve fitting and other technologies to reconstruct the evolution process of the basin, and the evolution trajectory reconstruction algorithm designed is used to process the evolution path inversion results and reconstruct the evolution trajectory of the basin. This can generate basin evolution trajectories, describe the evolution of basins in different periods, and design topological structure evolution analysis algorithms, which can analyze the evolution of topological structures based on historical data of water flow path network structures. This can involve network analysis, graph theory and other technologies to reveal changes in water flow path network structures. The designed topological structure evolution analysis algorithm is used to process historical data of water flow path network structures and analyze the evolution of topological structures. This can generate topological structure evolution data, describe changes in water flow path network structures, and design deformation trajectory analysis algorithms. This algorithm can analyze the deformation trajectory of topological structures during evolution based on basin evolution trajectories and topological structure evolution data. The designed deformation trajectory analysis algorithm is used to process basin evolution trajectories and topological structure evolution data and analyze the deformation trajectory of topological structures during evolution. This can generate deformation trajectory data, describe the deformation process of water flow path network structures, and design basin evolution morphology analysis algorithms. This algorithm can analyze the evolution morphology of water flow path network structures based on deformation trajectory data. This can involve spatial analysis, terrain analysis and other technologies to describe the morphological changes of the water flow path network structure, and use the designed basin evolution morphological analysis algorithm to process the deformation trajectory data and analyze the evolution of the water flow path network structure. This can generate basin evolution morphological data to describe the morphological changes of the water flow path network structure.

[0123] In this embodiment, step S32 includes the following steps:

[0124] Step S321: performing evolution time series analysis on the gene-environment evolution data to generate evolution time series data;

[0125] Step S322: identifying succession nodes of the water flow path network structure through the evolution time series data to generate water flow path succession nodes;

[0126] Step S323: performing succession drive association analysis on water flow path succession nodes through the basin dynamic evolution mechanism data to generate a succession drive association chain;

[0127] Step S324: using the succession driven association chain to analyze the evolution law of the water flow path succession nodes to generate evolution law data;

[0128] Step S325: Perform evolution path reverse processing on the water flow path network structure through the evolution law data to construct an evolution path reverse result.

[0129] The present invention can analyze the changes in gene-environment evolution data in time series through evolutionary time series analysis, revealing the patterns and trends of genome and environmental factors evolving over time. The generated evolutionary time series data can provide time information about genome and environmental evolution, and provide a data basis for subsequent water flow network succession node identification and evolution law analysis. Water flow succession node identification can determine the key nodes in the water flow network structure based on the evolutionary time series data, that is, the position or characteristics of the important change points in the evolution process. The generated water flow succession nodes can provide node information about the changes in the water flow network structure, and provide a data basis for subsequent succession driven association analysis and evolution law analysis. Succession driven association analysis can use the dynamic evolution mechanism data of the watershed to explore the water flow path. The correlation between succession nodes and genome-environment evolution, that is, determining the factors or mechanisms that drive the changes in succession nodes, generating succession-driven association chains can provide correlation information between water path succession nodes and genome-environment evolution, and provide a data basis for subsequent evolution law analysis and evolution path reverse processing. The evolution law analysis can reveal the evolution laws and trends of water path succession nodes based on the succession-driven association chains, including the formation, disappearance, and change frequency of nodes. The evolution path reverse processing can infer the evolution path of the water path network structure based on the evolution law data, that is, the change process of the water path at different time points. The construction of the evolution path reverse result can provide the evolution history information of the water path network structure, and provide a data basis for the classification of river types and the reconstruction of basin evolution trajectories.

[0130] In this embodiment, a suitable time series analysis method is selected, such as time series analysis, periodic analysis, trend analysis, etc., and a time series analysis is performed on the gene-environment evolution data according to the data characteristics and research purpose. The gene-environment evolution data is analyzed using the selected time series analysis method to generate evolution time series data to describe the temporal change law in the gene-environment evolution process. A suitable succession node identification method is selected, such as mutation point detection, threshold segmentation, etc., and the evolution nodes in the water flow path network structure are identified according to the characteristics of the evolution time series data and background knowledge. The evolution time series data is processed using the selected succession node identification method to identify the succession nodes in the water flow path network structure, that is, the key time points in the evolution process, and a suitable succession driven association analysis method is selected. , such as correlation analysis, causal relationship analysis, etc., according to the characteristics of the basin dynamic evolution mechanism data and the water flow path succession nodes, analyze the correlation between them, process the basin dynamic evolution mechanism data and the water flow path succession nodes, analyze the correlation between them, establish a succession drive association chain, and select appropriate evolution law analysis methods, such as statistical analysis, machine learning algorithms, etc., according to the characteristics of the succession drive association chain and the water flow path succession nodes, analyze the laws and trends between them, process the succession drive association chain and the water flow path succession nodes, analyze the laws and trends between them, generate evolution law data, describe the evolution law of the water flow path network structure, and design an evolution path inversion algorithm, which can inversely infer the evolution path of the water flow path network structure based on the evolution law data. This can be based on the path search of optimization algorithms such as simulated annealing algorithms and genetic algorithms, and construct the evolution path inversion results based on the results of the evolution path inversion processing. This can be a graphical display showing the path changes of the water flow path network structure during the evolution process, or a series of time points and corresponding state descriptions, describing the evolution path of the water flow path network structure.

[0131] In this embodiment, step S4 includes the following steps:

[0132] Step S41: performing a hydrological model quantitative analysis on the basin evolution morphology data to generate hydrological model data;

[0133] Step S42: extracting response rules of the watershed evolution morphology data through hydrological model data to generate constraint response rules;

[0134] Step S43: performing hydrological suppression and regulation analysis on the constraint response law to generate hydrological dynamic constraint rules;

[0135] Step S44: Predict the evolution trend of the watershed evolution morphological data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model.

[0136] The present invention can establish a mathematical model to describe the hydrological process of the basin, including the rainfall-runoff relationship, water level changes, etc., based on the basin evolution morphological data through quantitative analysis of hydrological patterns. The generated hydrological pattern data can provide a quantitative description of the basin hydrological process, and provide a data basis for the subsequent response law extraction and hydrological dynamic constraint rule analysis. The response law extraction can use the hydrological pattern data to analyze the correlation between the basin evolution morphological data and the hydrological process, and find out the change law of the morphological data under different hydrological conditions. The generated constraint response law can provide the response information of the basin evolution morphological data to the change of hydrological conditions. The hydrological inhibition and regulation analysis can explore the inhibitory or regulatory effect of hydrological conditions on the basin evolution morphology based on the constraint response law, that is, determine the constraint rules of hydrological conditions on morphological evolution. The generated hydrological dynamic constraint rules can provide the constraint information of the change of hydrological conditions on the basin evolution morphology. Evolution trend prediction can be based on hydrological dynamic constraint rules, combined with watershed evolution morphology data and gene-environment evolution data, to predict the changing trend of watershed evolution morphology in the future. Constructing an evolution trend prediction model can provide prediction results on the future development of watershed evolution morphology, and provide a reference for river type classification and watershed management decision-making.

[0137] In this embodiment, according to the research purpose and data characteristics, a suitable hydrological model, such as a hydrological cycle model, a hydrological level model, etc., is selected for quantitative analysis of the watershed evolution morphology data. According to the selected hydrological model, corresponding parameters are set, including watershed characteristic parameters, hydrological process parameters, etc., to ensure the accuracy of the model calculation results. The selected hydrological model and the set parameters are used to perform hydrological model calculation on the watershed evolution morphology data to generate hydrological model data to describe the quantitative characteristics of the watershed hydrological process. The selected response law extraction method is used to process the hydrological model data and the watershed evolution morphology data to extract the response law between them, that is, the sensitivity and change trend of the watershed evolution morphology data to the hydrological model. ,According to the constraint response law and the characteristics of the basin evolution morphological data, the inhibition and regulation mechanism in the hydrological process is analyzed, the inhibition and regulation mechanism in the hydrological process is analyzed, and the hydrological dynamic constraint rules are established. The constraint relationship in the hydrological process is described, and suitable evolution trend prediction methods are selected, such as time series analysis, regression analysis, machine learning algorithms, etc. According to the characteristics of the hydrological dynamic constraint rules and the basin evolution morphological data and gene-environment evolution data, their evolution trends are predicted. The hydrological dynamic constraint rules, basin evolution morphological data and gene-environment evolution data are processed to predict their evolution trends. An evolution trend prediction model is constructed to predict the changing trends of basin evolution morphological data and gene-environment evolution data.

[0138] In this embodiment, step S44 includes the following steps:

[0139] Step S441: Predicting the river basin area trend based on the basin evolution morphology data according to the hydrological dynamic constraint rules to generate basin area trend data;

[0140] Step S442: performing environmental response trend analysis on the gene-environment evolution data to generate environmental change response trend data;

[0141] Step S443: predicting the hydrological environmental deformation of the water flow path network structure according to the hydrological dynamic constraint rules to generate hydrological environmental deformation data;

[0142] Step S444: predicting the gene-environment evolution coupling law for the environmental change response trend data and the hydrological environment deformation data to generate the gene-environment linkage response law;

[0143] Step S445: fitting the evolution model to the watershed area trend data and the watershed evolution morphology data according to the gene-environment linkage response law to construct an evolution trend prediction model.

[0144] The present invention can predict the area trend of a river basin by analyzing and modeling the basin evolution morphological data. This helps to understand the changes in rivers over time, provides prediction information on the evolution of basin area over time, and can classify and divide different rivers based on basin area trend data. Different types of rivers may have different hydrological characteristics and ecological environmental conditions, which is of great significance for scientific research, water resources management and ecological protection. By analyzing the gene-environment evolution data, the impact and response of environmental changes on the genome can be understood. This helps to reveal the role of environmental factors in the evolution and adaptive changes of biological populations, and provides a scientific basis for environmental management and biodiversity protection. By analyzing the environmental response trend, data related to environmental transformation can be generated to describe the trend and pattern of environmental change. These data can provide quantitative analysis of environmental changes, help understand and predict the evolution process of ecosystems, and predict the deformation of the hydrological environment by analyzing and modeling the water flow network structure. This helps to understand the changes in the water flow network, including the evolution trend of hydrological characteristics such as river flow direction, water flow velocity, and water level. By analyzing and modeling the water flow network structure, the deformation of the hydrological environment can be predicted. This helps to understand the changes in the water flow network, including the evolution trend of hydrological characteristics such as river flow direction, water flow velocity, and water level. By analyzing and modeling the environmental change response trend data and hydrological environment deformation data, the interaction and coupling laws between the genome and the environment can be inferred. This helps to understand the adaptive response of biological populations to environmental changes and the impact of the environment on genome evolution.

[0145] In this embodiment, it is applied to the basin evolution morphology data. According to the constraint relationship described in the rule, the basin evolution morphology data is adjusted and transformed, and the basin evolution morphology data adjusted by the hydrological dynamic constraint rule is processed using the selected basin area trend prediction method to predict the trend of the river basin area and generate basin area trend data. A suitable environmental response trend analysis method is selected, such as statistical analysis, trend analysis, etc., and the gene-environment evolution data is processed using the selected environmental response trend analysis method to analyze the trend of environmental response and generate environmental change response trend data. According to the hydrological dynamic constraint rules and the water flow network structure data, the water flow network is simulated and predicted to generate hydrological environmental deformation data, describe the change trend of the hydrological environment, and convert the environmental change response trend data into the water flow network structure data. Integrate the data of genetics and hydrological environment deformation to ensure the consistency and correspondence of the data, select suitable gene-environment evolution coupling law prediction methods, such as association analysis, model fitting, etc., use the selected method to analyze and model the integrated data, predict the coupling law between genes and environment, generate gene-environment linkage response law, collect and organize basin area trend data, basin evolution morphology data and gene-environment linkage response law data to ensure the integrity and accuracy of the data, select suitable evolution models, such as regression models, machine learning models, etc. according to specific needs and data characteristics, use the selected evolution model to fit and train the basin area trend data and basin evolution morphology data, and establish an evolution trend prediction model.

[0146] In this embodiment, step S5 includes the following steps:

[0147] Step S51: using the evolution trend prediction model to analyze the type of aquatic biological community on the target watershed image to generate aquatic biological community data;

[0148] Step S52: Perform biodiversity statistics on the water community data to obtain a biodiversity index;

[0149] Step S53: performing community structure analysis on the water biological community data according to the biodiversity index to generate watershed water ecological structure data;

[0150] Step S54: Calculating the niche width of the watershed water ecological structure data to generate a niche width index;

[0151] Step S55: performing ecological overlap analysis on the watershed water ecological structure data based on the niche breadth index to generate an ecological overlap index;

[0152] Step S56: Calculate the ecological niche health impairment of the watershed water ecological structure data using the ecological niche health impairment calculation formula according to the ecological overlap index to generate the ecological niche health impairment index.

[0153] The present invention can determine the distribution of different types of aquatic communities by analyzing the basin image using an evolutionary trend prediction model. This helps to understand the structure and composition of the ecosystem in the basin. Biodiversity statistics can provide information about aquatic biodiversity, including species richness, diversity index, etc. This helps to assess the degree of diversity of the ecosystem in the basin. By analyzing the community structure of aquatic community data, the relationship and distribution pattern between different species can be understood. This helps to understand the structure of the ecosystem in the basin. Niche width calculation can provide information about the functional roles and resource utilization of different species in the ecosystem. Niche width index helps to assess the functional diversity of different species. Ecological overlap analysis allows the identification of the degree of niche overlap between different species, that is, the degree of overlap in their resource utilization. This helps to assess the competition and coexistence relationship between species. Niche health impairment calculation provides an assessment of ecosystem health by comprehensively considering factors such as biodiversity, community structure and niche width. This helps to understand the overall health of the ecosystem in the basin.

[0154] In this embodiment, appropriate community structure analysis indicators are selected according to needs, such as relative abundance of species, biomass distribution, etc., and the selected community structure analysis indicators are used to analyze the aquatic community data to reveal the relative abundance, composition structure and distribution characteristics of different species or groups, generate watershed water ecological structure data, select appropriate niche width calculation methods, such as niche models, niche width index, etc., and use the selected niche width calculation method to analyze and calculate the watershed water ecological structure data to obtain the niche width index, which reflects the utilization and distribution range of aquatic organisms in the niche, and select appropriate ecological overlap index calculation methods, such as Index, Jaccard index, etc., use the selected ecological overlap index calculation method to analyze and calculate the watershed water ecological structure data, obtain the degree of ecological overlap between different biological communities, generate the ecological overlap index, which reflects the similarity or overlap between different biological communities, use the selected niche health impairment calculation formula, combine the ecological overlap index data and other relevant data, calculate the watershed water ecological structure data, and obtain the niche health impairment index, which is used to evaluate the health status of the water ecosystem and the stability of the biological community.

[0155] In this embodiment, the niche health loss calculation formula in step S56 is specifically:

[0156]

[0157] Among them, H is the niche health impairment index, N is the number of existing species in the basin, t is the maximum number of species that the basin can bear, K is the assimilation capacity of the basin ecosystem, r is the species growth rate, g is the average niche width of the species, h is the vegetation coverage rate, and p is the anti-disturbance sensitivity of the basin ecosystem.

[0158] The present invention is achieved by It represents the ratio of the number of existing species in a watershed to the time. It can be used to assess the growth rate of species. A higher value means that the species is relatively large or growing faster, while a lower value means that the species is relatively small or growing slower. Calculate the natural logarithm of the number of species N. By taking the logarithm of the number of species, the impact of extreme values ​​on the niche health impairment index can be weakened, making the index more reflective of the changes in the number of species, and representing the ratio of the species density of the basin to the inverse of the maximum carrying capacity. A smaller density-to-carrying capacity ratio means that the species density is relatively low, and vice versa, it means that the species density is relatively high, (1-e ―rt ) is an exponential function of the species growth rate. It describes the growth trend of a species over a given period of time. A higher growth rate will result in an exponential close to 1, while a lower growth rate will result in an exponential close to 0. When the maximum number of species that a watershed can sustain is close to infinity, it corresponds to the long-term stable state of species growth rate, that is, when the number of species in the watershed tends to the maximum value, the stable value of the niche health impairment index takes into account the sensitivity parameter g, stability parameter h and complexity parameter p of the niche. A smaller attenuation function value indicates that the niche has higher stability and complexity, higher resistance to disturbance, can capture the long-term stable state of species growth rate, and help understand the development trend of species number and the stable value of the niche health impairment index.

[0159] In this embodiment, step S6 includes the following steps:

[0160] Step S61: when it is determined that the preset ecological niche health impairment threshold index is greater than the ecological niche health impairment index, the river type is classified as a damaged river;

[0161] Step S62: when it is determined that the preset ecological niche health impairment threshold index is equal to the ecological niche health impairment index, the river type is classified as a restoration river;

[0162] Step S63: When it is determined that the preset niche health impairment threshold index is less than the niche health impairment index, the river type is classified as a protected river.

[0163] The present invention classifies a river as a "damaged river" by determining that a preset niche health impairment threshold index is greater than the niche health impairment index, which indicates that the health of the ecosystem has been seriously damaged. Such classification helps to identify rivers that need urgent protection and restoration so that corresponding management and protection measures can be taken. Classifying a river as a "repairing river" indicates that the health of the ecosystem is close to the threshold but has not yet reached the preset threshold, which helps to identify those rivers that need protection and restoration measures to improve their ecological health. This can also guide managers to take appropriate measures to repair damaged ecosystems. Classifying a river as a "protected river" indicates that the health of the ecosystem is excellent and the health index is higher than the preset threshold. These rivers usually do not require emergency restoration measures, but need to be maintained and strengthened in management to ensure the long-term health of their ecosystems.

[0164] In this embodiment, the calculated niche health impairment index is compared with the preset niche health impairment threshold index. If the calculated niche health impairment index is greater than the preset niche health impairment threshold index, the river is classified as a damaged river type. If the calculated niche health impairment index is equal to the preset niche health impairment threshold index, the river is classified as a repaired river type. If the calculated niche health impairment index is less than the preset niche health impairment threshold index, the river is classified as a protected river type. A damaged river is a river that has suffered severe ecological damage and needs to be focused on and a strategy for reconstruction is formulated. A repaired river is a river that has suffered a moderate degree of ecological damage and needs support from protection policies to avoid becoming a damaged river. A protected river is a river that has suffered a moderate degree of ecological damage and has a relatively good ecological environment and can be focused on to maintain the status quo.

[0165] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0166] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0167] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A river classification method based on the water ecological environment protection stage of a small watershed, characterized in that: The following steps are involved: Step S1: Obtain historical river water area data; Use machine vision technology to obtain target watershed images; Perform water flow path analysis on the target watershed image to generate a water flow path network structure; Collect biological samples from target rivers and perform genome sequencing to generate biological genome data; Step S2: mining memory information on biological genome data to obtain watershed memory data; Conduct environmental change association analysis on watershed memory data to generate gene-environment evolution data; Step S3: reconstructing the basin evolution trajectory of the gene-environment evolution data based on the historical river water area data to construct the basin evolution trajectory; performing basin evolution morphological analysis on the water flow path network structure through the basin evolution trajectory to generate basin evolution morphological data; Step S4: Performing hydrological suppression and regulation analysis on the watershed evolution morphology data to generate hydrological dynamic constraint rules; performing evolution trend prediction on the watershed evolution morphology data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model; Step S5: using the evolution trend prediction model to perform water ecological structure analysis on the target watershed image to generate water ecological structure data of the watershed; performing niche health impairment calculation on the water ecological structure data of the watershed to generate an ecological niche health impairment index; wherein the specific steps of step S5 are: Step S51: using the evolution trend prediction model to analyze the type of aquatic biological community on the target watershed image to generate aquatic biological community data; Step S52: Perform biodiversity statistics on the water community data to obtain a biodiversity index; Step S53: performing community structure analysis on the water biological community data according to the biodiversity index to generate watershed water ecological structure data; Step S54: Calculating the niche width of the watershed water ecological structure data to generate a niche width index; Step S55: performing ecological overlap analysis on the watershed water ecological structure data based on the niche breadth index to generate an ecological overlap index; Step S56: Calculate the ecological niche health loss of the watershed water ecological structure data according to the ecological overlap index using the ecological niche health loss calculation formula to generate the ecological niche health loss index; wherein the ecological niche health loss calculation formula is specifically: ； in, is the niche health impairment index, is the number of existing species in the basin, is the maximum number of species that the basin can sustain, is the absorptive capacity of the watershed ecosystem. is the species growth rate, is the average niche breadth of the species, h is the vegetation coverage rate, for the disturbance sensitivity of the watershed ecosystem; Step S6: Using the preset niche health impairment threshold index to determine the basin health of the niche health impairment index, the river types are divided into damaged rivers, repaired rivers and protected rivers.

2. The method according to claim 1, characterized in that The specific steps of step S1 are: Step S11: Acquire historical river water area data; Step S12: using machine vision technology to obtain the target watershed image; Step S13: performing water flow layering and flow direction identification on the target watershed image to obtain water flow direction data; Step S14: performing water flow path analysis on the water flow direction data to obtain water flow path distribution data; Step S15: performing flow direction connection processing on the water flow path distribution data to construct a water flow path network structure; Step S16: Collect biological samples from the target river and perform genome sequencing to generate biological genome data.

3. The method according to claim 1, characterized in that The specific steps of step S2 are: Step S21: performing genome sequencing on the biological genome data to generate genome sequence data; Step S22: mining memory information of genome sequence data according to historical river water area data to obtain watershed memory data; Step S23: using a neural network algorithm to extract environmental response code table features from the genome sequence data to generate an environmental response feature sequence; Step S24: Perform environmental change association analysis on the watershed memory data through the environmental response feature sequence to generate gene-environment evolution data.

4. The method according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing a dynamic evolution mechanism analysis on the gene-environment evolution data based on historical river water area data to generate watershed dynamic evolution mechanism data; Step S32: performing evolution path reverse processing on the water flow path network structure through the basin dynamic evolution mechanism data to construct the evolution path reverse result; Step S33: reconstructing the watershed evolution trajectory based on the evolution path inversion result to construct the watershed evolution trajectory; Step S34: performing topological structure evolution analysis on the water flow path network structure to generate topological structure evolution data; Step S35: performing succession trajectory analysis on the topological structure evolution data through the watershed evolution trajectory to generate deformation trajectory data; Step S36: Performing a watershed evolution morphology analysis on the water flow path network structure through the deformation trajectory data to generate watershed evolution morphology data.

5. The method according to claim 4, characterized in that The specific steps of step S32 are: Step S321: performing evolution time series analysis on the gene-environment evolution data to generate evolution time series data; Step S322: identifying succession nodes of the water flow path network structure through the evolution time series data to generate water flow path succession nodes; Step S323: performing succession drive association analysis on water flow path succession nodes through the basin dynamic evolution mechanism data to generate a succession drive association chain; Step S324: using the succession driven association chain to analyze the evolution law of the water flow path succession nodes to generate evolution law data; Step S325: Perform evolution path reverse processing on the water flow path network structure through the evolution law data to construct an evolution path reverse result.

6. The method according to claim 1, characterized in that The specific steps of step S4 are: Step S41: performing a hydrological model quantitative analysis on the basin evolution morphology data to generate hydrological model data; Step S42: extracting response rules of the watershed evolution morphology data through hydrological model data to generate constraint response rules; Step S43: performing hydrological suppression and regulation analysis on the constraint response law to generate hydrological dynamic constraint rules; Step S44: Predict the evolution trend of the watershed evolution morphological data and gene-environment evolution data according to the hydrological dynamic constraint rules to construct an evolution trend prediction model.

7. The method according to claim 6, characterized in that The specific steps of step S44 are: Step S441: Predicting the river basin area trend based on the basin evolution morphology data according to the hydrological dynamic constraint rules to generate basin area trend data; Step S442: performing environmental response trend analysis on the gene-environment evolution data to generate environmental change response trend data; Step S443: predicting the hydrological environmental deformation of the water flow path network structure according to the hydrological dynamic constraint rules to generate hydrological environmental deformation data; Step S444: predicting the gene-environment evolution coupling law for the environmental change response trend data and the hydrological environment deformation data to generate the gene-environment linkage response law; Step S445: fitting the evolution model to the watershed area trend data and the watershed evolution morphology data according to the gene-environment linkage response law to construct an evolution trend prediction model.

8. The method according to claim 1, characterized in that The specific steps of step S6 are: Step S61: when it is determined that the preset ecological niche health impairment threshold index is greater than the ecological niche health impairment index, the river type is classified as a damaged river; Step S62: when it is determined that the preset ecological niche health impairment threshold index is equal to the ecological niche health impairment index, the river type is classified as a restoration river; Step S63: When it is determined that the preset niche health impairment threshold index is less than the niche health impairment index, the river type is classified as a protected river.

Images