Water ecology protection and restoration method based on ecological niche complementation technology

Abstract

The invention relates to the technical field of water ecology restoration, in particular to a water ecology protection and restoration method based on an ecological niche complementation technology. The method comprises the following steps: carrying out image acquisition on a target water area by utilizing an ecological remote sensing technology to obtain a target water area image; performing water body DNA detection on the target water area by using a sensor to obtain water ecological structure data; performing water ecological system analysis on the target water area image according to the water ecological structure data to generate water ecological system feature data; performing water area subdivision on the target water area image based on the water ecosystem feature data to generate a microhabitat; performing regional ecological niche correlation analysis on the microhabitat to generate microhabitat correlation data; and performing ecological compatibility analysis on the water ecosystem characteristic data through the microhabitat associated data to generate ecological compatibility data. According to the invention, high-efficiency and side-effect-free water ecological restoration is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water ecological restoration, and in particular to a water ecological protection and restoration method based on ecological niche complementation technology. Background Art

[0002] Aquatic ecosystems are among the most abundant and complex ecosystems on Earth. They provide important ecological services, including water purification, species diversity maintenance, and fishery resources. However, with the continuous development of urbanization and industrialization, aquatic ecosystems are facing increasing pressure, such as water pollution, overexploitation of water resources, and habitat destruction. These threats have a negative impact on the stability and health of aquatic ecosystems. Traditional methods of water ecological protection and restoration often have problems such as low efficiency and side effects. Therefore, a water ecological protection and restoration method based on niche complementarity technology has emerged. Niche complementarity is a method based on the principle of biodiversity that aims to use biological communities in different niches to synergistically maintain and repair ecosystems. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a water ecological protection and restoration method based on ecological niche complementation technology to solve at least one of the above technical problems.

[0004] To achieve the above object, the present invention provides a method for water ecological protection and restoration based on niche complementation technology, comprising the following steps:

[0005] Step S1: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area; using sensors to detect water body DNA in the target water area to obtain water ecological structure data; performing water ecosystem analysis on the target water area image based on the water ecological structure data to generate water ecosystem characteristic data;

[0006] Step S2: subdividing the target water area image based on the water ecosystem characteristic data to generate microhabitats; performing regional niche association analysis on the microhabitats to generate microhabitat association data;

[0007] Step S3: performing ecological compatibility analysis on the water ecosystem characteristic data through the microhabitat association data to generate ecological compatibility data; performing niche complementarity analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate niche complementarity data;

[0008] Step S4: fitting the complementary map of the niche complementarity data to construct the niche complementarity map; performing complementary strategy analysis on the niche complementarity data through the niche complementarity map to generate an ecological complementarity strategy;

[0009] Step S5: Design an ecological restoration floating bed based on water ecological structure data through an ecological complementarity strategy to construct an ecological complementary restoration floating bed; use numerical control navigation technology to implant the ecological complementary restoration floating bed into a microhabitat orientation, and collect water ecological restoration data;

[0010] Step S6: Use a deep learning algorithm to iteratively optimize the water ecological restoration data to generate water ecological restoration optimization data; perform dilation convolution on the water ecological restoration optimization data to construct a water ecological restoration model to perform water ecological protection and restoration operations.

[0011] The present invention can obtain high-resolution water images by collecting images of target waters through ecological remote sensing technology. These images can provide detailed geographic information and visual features to help understand the morphology, structure and changes of waters. Water ecological structure data can be obtained by performing water body DNA detection on target waters through sensors. Water body DNA detection can identify microbial communities in water, including plants, animals and microorganisms. This provides an understanding of the biodiversity and composition of water ecosystems. Water ecosystem analysis of target water images based on water ecological structure data can reveal the ecological characteristics of waters, such as wetlands, aquatic grass coverage, water quality, etc. of lakes or rivers. This helps to assess the health status and ecological functions of waters. Water segmentation of target water images based on water ecosystem characteristic data can divide waters into microhabitats. Microhabitats are local areas in waters with unique ecological environments and biological communities. Regional niche association analysis of microhabitats can reveal niche relationships between different microhabitats, including resource utilization, competition and interaction. This helps to understand the ecological functions and mutual influences of microhabitats. Through the microhabitat association data, the ecological compatibility analysis of the water ecosystem characteristic data can be used to evaluate the ecological compatibility between microhabitats. Ecological compatibility refers to the complementarity and synergy between different microhabitats to achieve the stability and health of the overall water ecosystem. Based on the ecological compatibility data, the niche complementarity analysis of the water ecosystem characteristic data can identify the niche complementarity relationship between microhabitats. Niche complementarity refers to the complementary relationship between biological groups in different microhabitats in resource utilization and ecological functions. The niche complementarity map can be constructed by fitting the complementary map of the niche complementarity data. The complementary map is a visualization tool that describes the niche complementarity relationship between different microhabitats, which helps to understand and analyze the complementary pattern between microhabitats. The ecological complementarity strategy refers to the formulation of corresponding management and protection strategies for the niche complementarity relationship between different microhabitats to promote the recovery and protection of the water ecosystem. Through the ecological complementarity strategy, the floating bed design of the water ecological structure data can be carried out, and the floating bed structure that conforms to the principle of niche complementarity can be designed for the restoration of the water ecosystem. The floating bed for ecological restoration can provide suitable habitat conditions to promote the colonization and growth of aquatic organisms. The ecological complementary restoration floating bed is implanted in the microhabitat direction using numerical control navigation technology, and water ecological restoration data is collected. These data can include water quality monitoring, aquatic biological monitoring, vegetation growth, etc., which are used to evaluate the effect of ecological restoration and monitor changes in the water ecosystem. The water ecological restoration data can be iteratively optimized using deep learning algorithms to generate water ecological restoration optimization data. Through algorithm optimization, the ecological restoration effect can be improved, and the layout of the restoration floating bed and vegetation can be made more reasonable and effective. The water ecological restoration optimization data can be expanded and convoluted to construct a water ecological restoration model. The water ecological restoration model can simulate the dynamic changes and responses of the water ecosystem, and is used to guide and implement water ecological protection and restoration operations.

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

[0013] Step S11: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area;

[0014] Step S12: using sensors to detect water DNA in the target water area to obtain water DNA data;

[0015] Step S13: performing DNF amplification processing on the water body DNA data to obtain the water body community richness;

[0016] Step S14: performing high-throughput sequencing based on the richness of the water community to generate short DNA sequence fragments;

[0017] Step S15: performing species classification processing on the DNA short sequence fragments to obtain water ecological structure data;

[0018] Step S16: Performing water ecosystem analysis on the target water area image according to the water ecological structure data to generate water ecosystem characteristic data.

[0019] The present invention collects images of target waters through ecological remote sensing technology, and can obtain high-resolution water images. These images provide detailed geographic information and visual features, which are helpful for understanding the morphology, structure and changes of waters. Water DNA data can be obtained by performing water body DNA detection on target waters through sensors. Water body DNA detection can identify microbial communities in water, including plants, animals and microorganisms. This provides an understanding of the biodiversity and composition in water ecosystems. Performing DNF (DNA Next Generation Sequencing) amplification processing on water body DNA data can increase the number of DNA fragments, thereby improving the accuracy and coverage of subsequent analysis. This helps to more comprehensively understand the microbial communities in water ecosystems. Based on water body DNA data, high-throughput sequencing can generate a large number of DNA short sequence fragments. High-throughput sequencing technology can efficiently determine DNA sequences and provide large-scale biological information data. Species classification processing of DNA short sequence fragments can identify and identify different biological species in water ecosystems. Through species classification, information such as the existence, abundance and distribution of various species in waters can be understood. Performing water ecosystem analysis on target water images based on water ecological structure data can reveal the ecological characteristics of waters. This includes wetlands, aquatic plant coverage, water quality, etc. of lakes or rivers. Through water ecosystem analysis, the health status and ecological functions of water bodies can be assessed.

[0020] Preferably, step S16 comprises the following steps:

[0021] Step S161: performing water quality analysis on the target water area image according to the water ecological structure data to generate water quality data of the target water area;

[0022] Step S162: Performing functional zone distribution analysis on the water ecological structure data based on the target water area water quality data to generate water area functional zone distribution data, the water area functional zone distribution data including breeding area, trophic area, diapause area, habitat area and exchange area;

[0023] Step S163: Perform trophic level analysis on the water functional zone distribution data to generate water biological trophic level data;

[0024] Step S164: performing group structure analysis on the water ecological structure data to generate water area group structure data;

[0025] Step S165: Performing water ecosystem analysis on the water community structure data through the water organism trophic level data to generate water ecosystem characteristic data.

[0026] The present invention can evaluate the water quality of a water area by performing water quality analysis on a target water area image according to water ecological structure data. Water quality data include indicators such as dissolved oxygen content, water temperature, pH value, turbidity, ammonia nitrogen, and total phosphorus. Through water quality analysis, the eutrophication degree, pollution degree, and ecological health status of a water area can be understood: functional area distribution analysis of water ecological structure data based on water quality data of the target water area can be performed to divide different functional areas of the water area. Common functional areas include breeding areas, trophic areas, diapause areas, habitat areas, and exchange areas. Functional area distribution data can reveal the distribution patterns and ecological function distribution of different biological groups in the water area. By performing trophic level analysis on the functional area distribution data of the water area, the trophic level of different biological groups in the water area can be determined. The trophic level refers to the position of an organism in a food chain, which is often divided into primary producers, consumers, and decomposers. Through trophic level analysis, the energy flow and material circulation in the water area can be understood, and the ecological balance and stability of the water area can be evaluated. By performing group structure analysis on the water ecological structure data, information such as the number, density, and size distribution of different species in the water area can be understood. The community structure data reflects the composition and population dynamics of biological communities in water bodies, providing a basis for assessing biodiversity, species richness, and the stability of ecosystems. By analyzing the water ecosystem with the community structure data of water bodies through the trophic level data of water bodies, we can gain a deeper understanding of the ecological processes and interactions of water bodies. The water ecosystem analysis can reveal the relationship between food chains and food webs, and assess the stability and sustainability of ecosystems. In addition, it can also identify potential ecological problems and threats such as biological invasions, providing a scientific basis for the protection and restoration of water ecosystems.

[0027] Preferably, step S2 comprises the following steps:

[0028] Step S21: subdividing the target water area image into water areas based on the water ecosystem characteristic data to generate microhabitats;

[0029] Step S22: Calculate the niche width of the microhabitat to generate niche width data;

[0030] Step S23: Calculating the species overlap index of the microhabitat according to the niche width data to generate the species overlap index;

[0031] Step S24: performing ecological function group analysis on the microhabitat through the species overlap index to obtain ecological function group data;

[0032] Step S25: Perform regional niche association analysis on the ecological functional group data to generate microhabitat association data.

[0033] The present invention subdivides the target water area image through the characteristic data of the water ecosystem, and divides the water area into microhabitats. Through the subdivision of the water area, the spatial heterogeneity inside the water area can be taken into account to form a more refined habitat unit, which is helpful to reveal the ecological differences and diversity inside the water area. By calculating the niche width of the microhabitat, the resource utilization range occupied by the biological species in different microhabitats can be evaluated. The niche width reflects the adaptability and resource allocation strategy of the biological population, and can reveal the competition and differentiation between biological species. According to the niche width data, the species overlap index of the microhabitat is calculated to measure the overlap degree of species in different microhabitats. The species overlap index reflects the coexistence and competition relationship between different species, and can reveal the pattern of biodiversity and ecological function distribution. By analyzing the ecological function group of the microhabitat through the species overlap index, the species can be classified and combined according to their ecological function characteristics. The ecological function group refers to a combination of species with similar functions and ecological roles in the ecosystem, such as predators, herbivores, benthic animals, etc. The ecological function group data provides information about the functions and relationships of the ecosystem. Regional niche association analysis of ecological functional group data can reveal the interactions and associations between different microhabitats. Regional niche association data reflect the patterns of resource utilization and species interaction between microhabitats, which helps to understand the overall structure and stability of the ecosystem.

[0034] Preferably, step S3 comprises the following steps:

[0035] Step S31: performing ecological connectivity analysis on the water ecosystem characteristic data through microhabitat association data to generate ecological connectivity data;

[0036] Step S32: performing ecological compatibility analysis on the microhabitat association data according to the ecological connectivity data to generate ecological compatibility data;

[0037] Step S33: performing niche difference analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate species niche difference data;

[0038] Step S34: performing community gap structure identification on the species niche difference data to obtain community gap structure configuration data;

[0039] Step S35: Performing niche complementarity analysis on the water ecosystem characteristic data according to the community vacancy structure configuration data to generate niche complementarity data.

[0040] The present invention performs ecological connectivity analysis on water ecosystem characteristic data through microhabitat association data, and can evaluate the ecological connection and interaction degree between different microhabitats. Ecological connectivity data reflects the connectivity and species migration between microhabitats in water areas, which helps to understand the movement path and population diffusion of organisms. Ecological compatibility analysis is performed on microhabitat association data based on ecological connectivity data, and the ecological compatibility between different microhabitats can be evaluated. Ecological compatibility data reflects the similarity and complementarity between microhabitats, and can reveal the adaptability and migration ability of biological populations between different microhabitats. Based on ecological compatibility data, species niche difference analysis is performed on water ecosystem characteristic data, and the degree of niche difference of species in different microhabitats can be evaluated. Species niche difference data reflects the difference in the utilization of different microhabitat resources by species, which helps to understand the functional differentiation and adaptability of species in different microhabitats. Community vacancy structure identification is performed on species niche difference data, and community vacancies and species missing in microhabitats can be found. Community vacancy structure configuration data provides vacancy information about species distribution, which helps to understand the integrity of species diversity and community structure. The niche complementarity analysis of aquatic ecosystem characteristics based on community vacancy structure configuration data can evaluate the niche complementarity between different microhabitats. Niche complementarity data reflects the degree of functional complementarity of species in different microhabitats, which helps to understand the interdependence between biological populations and the differences in resource utilization.

[0041] Preferably, step S32 includes the following steps:

[0042] Step S321: performing functional group-environment relationship analysis on microhabitat association data according to ecological connectivity data to generate microhabitat functional group-environment relationship data;

[0043] Step S322: performing species compatibility analysis and biological species compatibility analysis on the microhabitat association data according to the microhabitat functional group-environment relationship data;

[0044] Step S323: performing structural compatibility analysis on the microhabitat association data to generate structural compatibility data;

[0045] Step S324: performing energy compatibility analysis on the structural compatibility data according to interspecies compatibility to generate regional energy compatibility data;

[0046] Step S325: Perform ecological compatibility calculation on the energy compatibility data using the regional ecological comprehensive compatibility calculation formula to generate ecological compatibility data.

[0047] The present invention uses ecological connectivity data to perform functional group-environment relationship analysis on microhabitat association data, and can evaluate the relationship between different microhabitat functional groups and environmental conditions. Microhabitat functional group-environment relationship data provides information about the adaptability and environmental preference of functional groups, which helps to understand the distribution and ecological functions of different functional groups under different environmental conditions. According to the microhabitat functional group-environment relationship data, the microhabitat association data is analyzed for species compatibility, and the interaction and coexistence ability between different species can be evaluated. The species compatibility data reflects the degree of mutual adaptation and ecological complementarity between species, which helps to understand species diversity and the stability of the ecosystem. The structural compatibility data reflects the differences in morphological characteristics and spatial distribution between microhabitats, which helps to understand habitat connectivity and the feasibility of species migration. The regional energy compatibility data reflects the effectiveness of energy transfer between different microhabitats and the degree of niche overlap between species, which helps to understand the energy flow and species interdependence in the ecosystem. The ecological compatibility calculation is performed using regional energy compatibility data and the ecological comprehensive compatibility calculation formula, and the ecological compatibility of different microhabitats can be comprehensively evaluated. Ecological compatibility data provide information on the overall compatibility between microhabitats and the comprehensive stability of the ecosystem, which helps guide decision-making and optimal resource allocation for water ecological protection and restoration.

[0048] Preferably, the regional ecological comprehensive compatibility calculation formula in step S325 is specifically:

[0049]

[0050] Among them, C is the regional ecological comprehensive compatibility index, G is the water area, U is the dissolved oxygen concentration in the water area, I is the number of species, T is the species overlap index, B is the complexity of the community structure, h is the number of food chains, W is the number of top predators in the food chain, H is the species environment matching degree, S is the ecological resilience index, D is the regional plankton energy value, R is the water quality index, and A is the degree of species mutual assistance.

[0051] The present invention calculates the natural logarithm of the water area multiplied by the dissolved oxygen concentration in the water area through G·lnU, which represents the ecological environment quality of the water area. A larger area and a higher dissolved oxygen concentration generally mean a better ecological environment. It represents the combined effect of species number, species overlap index and community structure complexity. Higher species number, species overlap index and community structure complexity indicate that there are abundant species and complex ecological networks in the ecosystem, which is conducive to the stability and compatibility of the ecosystem. The combined effect of species-environment matching, the number of top predators in the food chain, and species-environment matching was calculated. A higher species-environment matching and a richer number of top predators in the food chain indicate a higher degree of interrelationship and interdependence among species in the ecosystem. The comprehensive effects of the ecological resilience index, regional plankton energy value, water quality index and species mutual assistance degree are calculated. A higher ecological resilience index and regional plankton energy value indicate that the ecosystem has a stronger adaptability to external disturbances, and a better water quality index and species mutual assistance degree indicate good ecological interaction and synergy of the ecosystem. The formula comprehensively considers multiple factors such as water area, water quality, species quantity, ecological network structure, food chain relationship, species environment matching, ecological resilience and species mutual assistance, and evaluates the comprehensive compatibility of regional ecosystems from different aspects. By calculating the C value, the compatibility of regional ecosystems can be quantitatively evaluated, providing a scientific basis and decision-making support for ecological protection and restoration.

[0052] Preferably, step S4 comprises the following steps:

[0053] Step S41: Calculating the complementarity of the niche complementarity data according to the species overlap index to generate the niche complementarity;

[0054] Step S42: performing complementary network analysis on the niche complementarity data according to the niche complementarity degree to obtain the niche complementarity network;

[0055] Step S43: fitting a complementary map of the niche complementarity network to construct an ecological niche complementarity map;

[0056] Step S44: performing microhabitat complementarity node analysis on the niche complementarity data through the niche complementarity map to obtain microhabitat complementarity nodes;

[0057] Step S45: Perform complementary strategy analysis on the microhabitat complementary nodes to generate an ecological complementary strategy.

[0058] The present invention calculates the complementarity of niche complementarity data through the species overlap index, and can evaluate the degree of niche overlap between different biological species or functional groups. The niche complementarity data provides information about the resource utilization and niche segmentation of species or functional groups, which is helpful to understand the interaction between biological species diversity and different biological groups in the ecosystem. According to the niche complementarity, the niche complementarity data is analyzed by complementary network, which can reveal the complementary relationship and mutual dependence between biological species or functional groups. The complementary network provides information on the connection mode and interaction intensity between species or functional groups, which is helpful to understand the network structure of energy flow and species mutual dependence in the ecosystem. The niche complementarity network is fitted with a complementary map, and a niche complementarity map can be constructed. The niche complementarity map reflects the spatial distribution and characteristics of different biological species or functional groups in resource utilization and niche segmentation, which is helpful to understand the niche complementarity and niche diversity of different regions in the ecosystem. Microhabitat complementary nodes can be determined by performing microhabitat complementary node analysis on the niche complementarity data through the niche complementarity map, and microhabitat nodes with high complementarity can be determined. Microhabitat complementarity nodes provide information about the complementary relationship and niche segmentation between different microhabitats, which helps to understand the microhabitat diversity and distribution of key nodes in the ecosystem. Complementarity strategy analysis of microhabitat complementarity nodes can generate ecological complementarity strategies. Ecological complementarity strategies provide suggestions and guidance on how to optimize microhabitat configuration and resource utilization to promote niche complementarity and ecosystem restoration, which is helpful for decision-making and implementation of water ecological protection and restoration.

[0059] Preferably, step S5 comprises the following steps:

[0060] Step S51: Perform complementary biological population analysis on water ecological structure data through ecological complementarity strategy to obtain ecological complementary populations;

[0061] Step S52: performing a floating bed vegetation spatial distribution analysis on the ecological complementary population to generate vegetation spatial distribution data;

[0062] Step S53: Designing an ecological restoration floating bed for ecological complementary populations based on the vegetation spatial distribution data to construct an ecological complementary restoration floating bed;

[0063] Step S54: extracting the target microhabitat position of the ecological complementarity strategy to generate target microhabitat position parameters;

[0064] Step S55: According to the target microhabitat location parameters, the ecological complementary restoration floating bed is implanted into the microhabitat using numerical control navigation technology, and water ecological restoration data is collected.

[0065] The present invention can identify the situation of species missing or insufficient in the ecosystem by analyzing and simulating the water ecological structure data. Through the ecological complementarity strategy, suitable biological populations can be selected to fill the gaps of species missing to enhance the stability and function of the ecosystem. The introduction of ecological complementary populations can improve biodiversity and promote the recovery and restoration of the ecosystem. By analyzing the spatial distribution of ecological complementary populations on floating bed vegetation, the distribution range, density and structure of different vegetation communities can be understood. Vegetation spatial distribution data can provide information such as coverage, uniformity and diversity of floating bed vegetation. Based on vegetation spatial distribution data, the design and construction of ecological restoration floating beds can be carried out. Ecological restoration floating beds are artificially constructed plant habitats. By reasonably arranging the distribution and density of ecological complementary populations, suitable habitat conditions and resource supply can be provided to promote plant growth and species reproduction. Ecological restoration floating beds can increase biodiversity, improve water quality, provide habitats, and promote the recovery and stability of ecosystems. By analyzing the ecological complementary strategy, the target microhabitat position suitable for ecological restoration can be determined. Using numerical control navigation technology, the ecological complementary restoration floating bed can be precisely implanted into the target microhabitat. By implanting the ecological complementary restoration floating bed, the ecological environment of the water body can be improved, habitats and nutrient sources can be provided, and plant growth and the reproduction of aquatic organisms can be promoted. At the same time, the collection of water ecological restoration data can evaluate the restoration effect and the degree of recovery of the ecosystem, providing a scientific basis and monitoring data for water ecological protection and restoration.

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

[0067] Step S61: Iteratively optimize the water ecological restoration data using a deep learning algorithm to generate water ecological restoration optimization data;

[0068] Step S62: performing convolution preprocessing on the water ecological restoration optimization data to generate a convolution sample set;

[0069] Step S63: performing dilated convolution on the convolution sample set to generate a water ecological restoration convolution network;

[0070] Step S64: performing pooling sampling on the water ecological restoration convolutional network to generate a water ecological restoration convolutional graph;

[0071] Step S65: Perform data mining modeling on the water ecological restoration convolution graph to construct a water ecological restoration model to perform water ecological protection and restoration operations.

[0072] The present invention can improve the accuracy and predictive ability of data by iteratively optimizing water ecological restoration data by applying deep learning algorithms. Deep learning algorithms can learn and extract complex patterns and associations in data, thereby generating more accurate water ecological restoration optimization data. These optimization data can provide a more reliable basis for subsequent analysis and decision-making. Through convolution preprocessing, water ecological restoration optimization data can be converted into a sample set suitable for convolutional neural network (CNN) processing. Convolution preprocessing can extract spatial and temporal features in data, capture local structures and patterns of data, and thus better reveal the laws and trends of water ecological restoration. The generated convolution sample set can be used to train and verify the convolution network model of water ecological restoration. Through dilated convolution, a convolutional neural network for water ecological restoration can be constructed. Dilated convolution can increase the network receptive field, capture a wider spatial range and contextual information, and improve the network's understanding and predictive ability of water ecological restoration data. The water ecological restoration convolution network can learn features and patterns in the data and be used for subsequent image processing and analysis tasks. Through pooled sampling, key features can be extracted from the water ecological restoration convolution network to generate a water ecological restoration convolution map. Pooled sampling can reduce the dimension of data, extract important feature information, and maintain the consistency of spatial relationships. The water ecological restoration convolution map can be used for visualization analysis, feature extraction, and pattern recognition, providing a more intuitive and interpretable data representation for water ecological protection and restoration. By performing data mining modeling on the water ecological restoration convolution map, a water ecological restoration model can be constructed to predict and optimize water ecological protection and restoration operations. Data mining modeling can discover hidden patterns and association laws in the data, and provide predictions and optimization plans for the effects of water ecological restoration. The water ecological restoration model can provide decision support for decision makers and guide the implementation and management of water ecological protection and restoration work. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic diagram of the steps of a water ecological protection and restoration method based on ecological niche complementation technology of the present invention;

[0074] Figure 2 Detailed implementation flow chart of step S1;

[0075] Figure 3 Detailed implementation flow chart of step S2;

[0076] Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0077] 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.

[0078] This application example provides a method for water ecological protection and restoration based on niche complementary technology. The execution subject of the water ecological protection and restoration method based on niche complementary technology includes but is not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload device, 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.

[0079] See also Figures 1 to 4 The present invention provides a method for water ecological protection and restoration based on ecological niche complementation technology, and the method for water ecological protection and restoration based on ecological niche complementation technology comprises the following steps:

[0080] Step S1: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area; using sensors to detect water body DNA in the target water area to obtain water ecological structure data; performing water ecosystem analysis on the target water area image based on the water ecological structure data to generate water ecosystem characteristic data;

[0081] Step S2: subdividing the target water area image based on the water ecosystem characteristic data to generate microhabitats; performing regional niche association analysis on the microhabitats to generate microhabitat association data;

[0082] Step S3: performing ecological compatibility analysis on the water ecosystem characteristic data through the microhabitat association data to generate ecological compatibility data; performing niche complementarity analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate niche complementarity data;

[0083] Step S4: fitting the complementary map of the niche complementarity data to construct the niche complementarity map; performing complementary strategy analysis on the niche complementarity data through the niche complementarity map to generate an ecological complementarity strategy;

[0084] Step S5: Design an ecological restoration floating bed based on water ecological structure data through an ecological complementarity strategy to construct an ecological complementary restoration floating bed; use numerical control navigation technology to implant the ecological complementary restoration floating bed into a microhabitat orientation, and collect water ecological restoration data;

[0085] Step S6: Use a deep learning algorithm to iteratively optimize the water ecological restoration data to generate water ecological restoration optimization data; perform dilation convolution on the water ecological restoration optimization data to construct a water ecological restoration model to perform water ecological protection and restoration operations.

[0086] The present invention can obtain high-resolution water images by collecting images of target waters through ecological remote sensing technology. These images can provide detailed geographic information and visual features to help understand the morphology, structure and changes of waters. Water ecological structure data can be obtained by performing water body DNA detection on target waters through sensors. Water body DNA detection can identify microbial communities in water, including plants, animals and microorganisms. This provides an understanding of the biodiversity and composition of water ecosystems. Water ecosystem analysis of target water images based on water ecological structure data can reveal the ecological characteristics of waters, such as wetlands, aquatic grass coverage, water quality, etc. of lakes or rivers. This helps to assess the health status and ecological functions of waters. Water segmentation of target water images based on water ecosystem characteristic data can divide waters into microhabitats. Microhabitats are local areas in waters with unique ecological environments and biological communities. Regional niche association analysis of microhabitats can reveal niche relationships between different microhabitats, including resource utilization, competition and interaction. This helps to understand the ecological functions and mutual influences of microhabitats. Through the microhabitat association data, the ecological compatibility analysis of the water ecosystem characteristic data can be used to evaluate the ecological compatibility between microhabitats. Ecological compatibility refers to the complementarity and synergy between different microhabitats to achieve the stability and health of the overall water ecosystem. Based on the ecological compatibility data, the niche complementarity analysis of the water ecosystem characteristic data can identify the niche complementarity relationship between microhabitats. Niche complementarity refers to the complementary relationship between biological groups in different microhabitats in resource utilization and ecological functions. The niche complementarity map can be constructed by fitting the complementary map of the niche complementarity data. The complementary map is a visualization tool that describes the niche complementarity relationship between different microhabitats, which helps to understand and analyze the complementary pattern between microhabitats. The ecological complementarity strategy refers to the formulation of corresponding management and protection strategies for the niche complementarity relationship between different microhabitats to promote the recovery and protection of the water ecosystem. Through the ecological complementarity strategy, the floating bed design of the water ecological structure data can be carried out, and the floating bed structure that conforms to the principle of niche complementarity can be designed for the restoration of the water ecosystem. The floating bed for ecological restoration can provide suitable habitat conditions to promote the colonization and growth of aquatic organisms. The ecological complementary restoration floating bed is implanted in the microhabitat direction using numerical control navigation technology, and water ecological restoration data is collected. These data can include water quality monitoring, aquatic biological monitoring, vegetation growth, etc., which are used to evaluate the effect of ecological restoration and monitor changes in the water ecosystem. The water ecological restoration data can be iteratively optimized using deep learning algorithms to generate water ecological restoration optimization data. Through algorithm optimization, the ecological restoration effect can be improved, and the layout of the restoration floating bed and vegetation can be made more reasonable and effective. The water ecological restoration optimization data can be expanded and convoluted to construct a water ecological restoration model. The water ecological restoration model can simulate the dynamic changes and responses of the water ecosystem, and is used to guide and implement water ecological protection and restoration operations.

[0087] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a water ecological protection and restoration method based on ecological niche complementation technology of the present invention. In this example, the steps of the water ecological protection and restoration method based on ecological niche complementation technology include:

[0088] Step S1: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area; using sensors to detect water body DNA in the target water area to obtain water ecological structure data; performing water ecosystem analysis on the target water area image based on the water ecological structure data to generate water ecosystem characteristic data;

[0089] In this embodiment, an appropriate remote sensing data source is selected, such as satellite remote sensing images or drone aerial images, to obtain image data of the target water area. According to actual needs and research purposes, an image acquisition plan is designed to determine parameters such as acquisition area, acquisition time, and acquisition frequency to ensure that comprehensive and continuous image data of the target water area are obtained. An appropriate sensor is selected for water body DNA detection. Commonly used sensors include DNA detection instruments based on PCR (polymerase chain reaction) technology or high-throughput sequencers based on sequencing technology. Representative sampling points are selected in the target water area, and water samples are collected using appropriate methods. Sanitation and quality control during sample collection are ensured to ensure the reliability and accuracy of water body DNA samples. The target water area image is analyzed. Preprocessing is performed, including denoising, geometric correction, edge repair and other operations, to eliminate interference in the image and improve image quality. According to the research purpose and the characteristics of the water ecological structure data, a suitable water ecosystem analysis algorithm is selected. For example, image segmentation algorithms, target extraction algorithms, object recognition algorithms, etc. can be used to analyze and process the image. According to the selected algorithm, the preprocessed target water area image is subjected to water ecosystem analysis. By extracting image features, identifying and classifying water ecological elements (such as lakes, wetlands, vegetation, etc.), water ecosystem characteristic data is generated. The generated water ecosystem characteristic data, including statistical data, spatial distribution data, etc., are sorted out. Through data analysis and visualization methods, the structure, dynamic changes and other characteristics of the water ecosystem are explored.

[0090] Step S2: subdividing the target water area image based on the water ecosystem characteristic data to generate microhabitats; performing regional niche association analysis on the microhabitats to generate microhabitat association data;

[0091] In the present embodiment, according to the research purpose and demand, appropriate water ecosystem features are selected to perform water area segmentation. For example, water body type, vegetation coverage, water quality index, etc. can be selected as the features of segmentation. The target water area image is segmented using the selected algorithm. According to the feature data and algorithm, the target water area is divided into microhabitats, each of which has similar characteristics. According to the research purpose, the niche of each microhabitat is defined. The niche can include environmental factors (such as water temperature, oxygen content), biological community structure (such as plant species, animal species), etc. The selected method is used to perform regional niche association analysis on the microhabitat. By analyzing the niche relationship between different microhabitats, the interactions, dependencies and similarities of the niches between them can be revealed. According to the generated microhabitat association data, the relationship and interaction between different microhabitats are explained. The rules and trends in the niche characteristics, niche distribution, etc. of the microhabitat can be explored through data analysis and professional knowledge.

[0092] Step S3: performing ecological compatibility analysis on the water ecosystem characteristic data through the microhabitat association data to generate ecological compatibility data; performing niche complementarity analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate niche complementarity data;

[0093] In this embodiment, characteristic data of water ecosystems are collected, which may include water quality data, species diversity data of aquatic organisms, hydrological data, etc. Characteristic data of water ecosystems are collected, which may include water quality data, species diversity data of aquatic organisms, hydrological data, etc. Characteristic data of water ecosystems are collected, which may include water quality data, species diversity data of aquatic organisms, hydrological data, etc., and niche complementarity analysis is performed using ecological compatibility data to determine the niche differences and complementarity of aquatic organisms. Niche complementarity analysis is performed using ecological compatibility data to determine the niche differences and complementarity of aquatic organisms. By comparing the niche data of different species, the complementarity between them is determined. Complementarity indicates how different species fill the same or different niches to achieve the stability and function of the ecosystem. Based on the results of the niche complementarity analysis, niche complementarity data are generated, which describe the niche complementarity relationship between different species. This can be a matrix or other form of data set for subsequent ecosystem management and decision-making.

[0094] Step S4: fitting the complementary map of the niche complementarity data to construct the niche complementarity map; performing complementary strategy analysis on the niche complementarity data through the niche complementarity map to generate an ecological complementarity strategy;

[0095] In this embodiment, according to the characteristics of the data and the purpose of the research, a suitable map fitting method is selected. Common methods include cluster analysis, principal component analysis, factor analysis, etc. The selected method is used to fit the niche complementarity data and map the data to a lower dimensional map space. According to the research purpose and the results of the map analysis, the complementary strategies between different microhabitats are defined. The complementary strategies may include collaboration in resource utilization, adjustment of spatial distribution, etc. According to the defined complementary strategies and data types, a suitable analysis method is selected. Common methods include network analysis, association rule mining, spatial distribution models, etc. The selected method is used to analyze the niche complementarity data and the niche complementarity map, explore the complementary relationship, potential interaction and adjustment strategy between microhabitats, organize the results of the complementary strategy analysis, including complementary relationship network, association rules, spatial distribution models, etc., and explain the complementary relationship, strategy and potential ecological effect between different microhabitats according to the generated ecological complementary strategy. Through data analysis and professional knowledge, the laws and trends of complementary potential and resource allocation strategy between microhabitats can be explored.

[0096] Step S5: Design an ecological restoration floating bed based on water ecological structure data through an ecological complementarity strategy to construct an ecological complementary restoration floating bed; use numerical control navigation technology to implant the ecological complementary restoration floating bed into a microhabitat orientation, and collect water ecological restoration data;

[0097] In this embodiment, the water ecological goals that need to be repaired are determined according to the water ecological structure data and the ecological complementarity strategy, such as water quality improvement and biodiversity enhancement. According to the ecological restoration goals and actual conditions, the design principles of the floating bed are formulated, for example, selecting suitable materials, determining the size and shape of the floating bed, considering the adaptability of the floating bed to the water ecological environment, etc. According to the water ecological structure data and the ecological complementarity strategy, the layout and position of the floating bed are determined. Taking into account the complementary relationship and the restoration effect, different types of floating beds are arranged in suitable positions. The equipment and tools required for the numerical control navigation technology are prepared, including a plant directional implantation device and a positioning system. The ecological complementary restoration floating bed is accurately implanted into the water body using the numerical control navigation technology. According to the designed position and layout, the implantation device is controlled to accurately place the floating bed at the target position. After the floating bed is implanted, the water ecological restoration data is collected, including water quality monitoring, biological investigation, growth status monitoring, etc. The restoration effect of the floating bed is evaluated by regularly collecting and recording data, and necessary adjustments and improvements are made.

[0098] Step S6: Iteratively optimize the water ecological restoration data using a deep learning algorithm to generate water ecological restoration optimization data; perform dilation convolution on the water ecological restoration optimization data to construct a water ecological restoration model to perform water ecological protection and restoration operations.

[0099] In this embodiment, according to the optimization goal of water ecological restoration, the optimization goal of the deep learning algorithm is determined, for example, to improve water quality indicators, increase biodiversity, etc., and a suitable deep learning algorithm model is selected, such as convolutional neural network (CNN), recurrent neural network (RNN), etc. The water ecological restoration data of the training set is used to train the model, optimize the model parameters, and use the data of the validation set to evaluate the performance of the model. The model is adjusted and optimized according to the evaluation results. The model architecture, hyperparameters, etc. can be adjusted. The water ecological restoration optimization data is used to perform data expansion operations. For example, the scale of the data set is expanded by interpolation, expansion, etc., and the diversity of samples is increased. The expanded data set is used for convolution operations to construct a water ecological restoration model. A deep learning model such as a dilated convolutional neural network can be used. The dilated convolutional model is used to train and optimize water ecological restoration. According to the actual situation, the model parameters, learning rate, etc. are adjusted to improve the restoration effect. According to the restoration plan generated by the model, the water ecological protection and restoration operation is performed. For example, the position and layout of the floating bed are adjusted, the planting density of plants is increased or decreased, etc., to ensure that the restoration operation is performed according to the optimized data generated by the model.

[0100] 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:

[0101] Step S11: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area;

[0102] Step S12: using sensors to detect water DNA in the target water area to obtain water DNA data;

[0103] Step S13: performing DNF amplification processing on the water body DNA data to obtain the water body community richness;

[0104] Step S14: performing high-throughput sequencing based on the richness of the water community to generate short DNA sequence fragments;

[0105] Step S15: performing species classification processing on the DNA short sequence fragments to obtain water ecological structure data;

[0106] Step S16: Performing water ecosystem analysis on the target water area image according to the water ecological structure data to generate water ecosystem characteristic data.

[0107] The present invention collects images of target waters through ecological remote sensing technology, and can obtain high-resolution water images. These images provide detailed geographic information and visual features, which are helpful for understanding the morphology, structure and changes of waters. Water DNA data can be obtained by performing water body DNA detection on target waters through sensors. Water body DNA detection can identify microbial communities in water, including plants, animals and microorganisms. This provides an understanding of the biodiversity and composition in water ecosystems. Performing DNF (DNA Next Generation Sequencing) amplification processing on water body DNA data can increase the number of DNA fragments, thereby improving the accuracy and coverage of subsequent analysis. This helps to more comprehensively understand the microbial communities in water ecosystems. Based on water body DNA data, high-throughput sequencing can generate a large number of DNA short sequence fragments. High-throughput sequencing technology can efficiently determine DNA sequences and provide large-scale biological information data. Species classification processing of DNA short sequence fragments can identify and identify different biological species in water ecosystems. Through species classification, information such as the existence, abundance and distribution of various species in waters can be understood. Performing water ecosystem analysis on target water images based on water ecological structure data can reveal the ecological characteristics of waters. This includes wetlands, aquatic plant coverage, water quality, etc. of lakes or rivers. Through water ecosystem analysis, the health status and ecological functions of water bodies can be assessed.

[0108] In this embodiment, according to the water ecological information to be obtained and the characteristics of the target water area, a suitable ecological remote sensing technology is selected. For example, satellite remote sensing, drone remote sensing or aerial remote sensing can be used to determine the time, frequency and regional scope of collection, etc., and consider the size and shape of the target water area and the purpose of the study to formulate a reasonable collection plan. According to the collection plan, the corresponding remote sensing platform (such as satellite, drone or aircraft) is used to collect images of the target water area to ensure that the collected images have sufficient spatial resolution and coverage. The water body DNA detection sensor is reasonably installed in the target water area to ensure that the sensor can accurately obtain water body DNA data. The sensor can be a buoy, underwater equipment or other suitable device. The water body is sampled by the sensor to collect DNA samples in the water body. The sensor can collect samples containing DNA such as suspended particles, sediments or plankton in the water body. High-throughput sequencing technology, such as the Illumina sequencing platform, is used to sequence the sample library to obtain a large number of DNA short sequence fragments, the raw data obtained by sequencing are processed by quality control, filtering and removal of low-quality sequences to obtain high-quality DNA short sequence fragments, and the DNA short sequence fragments are compared with known reference databases using appropriate bioinformatics tools, such as BLAST or Bowtie. According to the comparison results, the DNA short sequence fragments are assigned to the corresponding species classification units using classification algorithms and classification systems. This can be achieved through the similarity threshold of the comparison or other classification standards, and the number and abundance information of each species classification unit are recorded. If needed, water ecological structure data such as species diversity index and relative abundance ratio can be calculated. Image processing and analysis methods are used to extract features related to the water ecosystem from the target water image, such as water body color, vegetation cover, water body boundary, etc. The extracted water ecosystem feature data are analyzed and interpreted and inferred according to the research purpose. Statistical methods, machine learning algorithms or professional knowledge can be used to reveal the characteristics and changing trends of the water ecosystem.

[0109] In this embodiment, step S16 includes the following steps:

[0110] Step S161: performing water quality analysis on the target water area image according to the water ecological structure data to generate water quality data of the target water area;

[0111] Step S162: Performing functional zone distribution analysis on the water ecological structure data based on the target water area water quality data to generate water area functional zone distribution data, the water area functional zone distribution data including breeding area, trophic area, diapause area, habitat area and exchange area;

[0112] Step S163: Perform trophic level analysis on the water functional zone distribution data to generate water biological trophic level data;

[0113] Step S164: performing group structure analysis on the water ecological structure data to generate water area group structure data;

[0114] Step S165: Performing water ecosystem analysis on the water community structure data through the water organism trophic level data to generate water ecosystem characteristic data.

[0115] The present invention can evaluate the water quality of a water area by performing water quality analysis on a target water area image according to water ecological structure data. Water quality data include indicators such as dissolved oxygen content, water temperature, pH value, turbidity, ammonia nitrogen, and total phosphorus. Through water quality analysis, the eutrophication degree, pollution degree, and ecological health status of a water area can be understood: functional area distribution analysis of water ecological structure data based on water quality data of the target water area can be performed to divide different functional areas of the water area. Common functional areas include breeding areas, trophic areas, diapause areas, habitat areas, and exchange areas. Functional area distribution data can reveal the distribution patterns and ecological function distribution of different biological groups in the water area. By performing trophic level analysis on the functional area distribution data of the water area, the trophic level of different biological groups in the water area can be determined. The trophic level refers to the position of an organism in a food chain, which is often divided into primary producers, consumers, and decomposers. Through trophic level analysis, the energy flow and material circulation in the water area can be understood, and the ecological balance and stability of the water area can be evaluated. By performing group structure analysis on the water ecological structure data, information such as the number, density, and size distribution of different species in the water area can be understood. The community structure data reflects the composition and population dynamics of biological communities in water bodies, providing a basis for assessing biodiversity, species richness, and the stability of ecosystems. By analyzing the water ecosystem with the community structure data of water bodies through the trophic level data of water bodies, we can gain a deeper understanding of the ecological processes and interactions of water bodies. The water ecosystem analysis can reveal the relationship between food chains and food webs, and assess the stability and sustainability of ecosystems. In addition, it can also identify potential ecological problems and threats such as biological invasions, providing a scientific basis for the protection and restoration of water ecosystems.

[0116] In this embodiment, image processing and analysis methods are used to extract parameters related to water quality from the target water area image. These parameters may include water color, transparency, turbidity, etc. The extracted water quality parameter data are analyzed and interpreted and inferred according to the research purpose. Standard water quality evaluation methods or professional knowledge can be used to evaluate the water quality of the target water area. According to water ecology theory and water quality data, the target water area is divided into different functional areas. Common functional areas include breeding areas (areas suitable for biological reproduction), trophic areas (areas rich in nutrients), diapause areas (areas where nutrient enrichment leads to hypoxia), habitat areas (areas that provide biological habitats), and communication areas (areas where water flows). According to the functional area division, the distribution of water ecological structure data in different functional areas is analyzed. Spatial analysis methods or statistical methods can be used to determine the locations and area proportions of different functional areas. According to the distribution data of water area functional areas and Water quality data, calculate the trophic level of each functional zone. The trophic level is usually estimated based on indicators such as nutrient concentration and photosynthesis intensity. Analyze the trophic level data of different functional zones to understand the nutritional status of organisms in the target waters. Compare the differences in trophic levels of different functional zones and evaluate their impact on the aquatic ecosystem. Analyze the extracted population structure data to understand the composition and distribution of different biological communities in the target waters. Community ecology methods or statistical methods can be used to reveal the characteristics and dynamic changes of community structure. Based on the associated data, water ecosystem analysis can be conducted to explore the relationship between biological trophic level and community structure in water ecosystems, evaluate the stability and function of water ecosystems, and generate characteristic data of water ecosystems based on the results of water ecosystem analysis. These characteristic data can include species diversity index, ecological network structure, niche width, etc., which are used to describe the characteristics and functions of aquatic ecosystems.

[0117] 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:

[0118] Step S21: subdividing the target water area image into water areas based on the water ecosystem characteristic data to generate microhabitats;

[0119] Step S22: Calculate the niche width of the microhabitat to generate niche width data;

[0120] Step S23: Calculating the species overlap index of the microhabitat according to the niche width data to generate the species overlap index;

[0121] Step S24: performing ecological function group analysis on the microhabitat through the species overlap index to obtain ecological function group data;

[0122] Step S25: Perform regional niche association analysis on the ecological functional group data to generate microhabitat association data.

[0123] The present invention subdivides the target water area image through the characteristic data of the water ecosystem, and divides the water area into microhabitats. Through the subdivision of the water area, the spatial heterogeneity inside the water area can be taken into account to form a more refined habitat unit, which is helpful to reveal the ecological differences and diversity inside the water area. By calculating the niche width of the microhabitat, the resource utilization range occupied by the biological species in different microhabitats can be evaluated. The niche width reflects the adaptability and resource allocation strategy of the biological population, and can reveal the competition and differentiation between biological species. According to the niche width data, the species overlap index of the microhabitat is calculated to measure the overlap degree of species in different microhabitats. The species overlap index reflects the coexistence and competition relationship between different species, and can reveal the pattern of biodiversity and ecological function distribution. By analyzing the ecological function group of the microhabitat through the species overlap index, the species can be classified and combined according to their ecological function characteristics. The ecological function group refers to a combination of species with similar functions and ecological roles in the ecosystem, such as predators, herbivores, benthic animals, etc. The ecological function group data provides information about the functions and relationships of the ecosystem. Regional niche association analysis of ecological functional group data can reveal the interactions and associations between different microhabitats. Regional niche association data reflect the patterns of resource utilization and species interaction between microhabitats, which helps to understand the overall structure and stability of the ecosystem.

[0124] In this embodiment, appropriate algorithms and methods are applied to segment the target water area image according to the characteristic data of the water ecosystem. The segmentation can be based on different characteristics, such as habitat type, water body depth, vegetation coverage, etc. According to the water area segmentation results, the target water area is divided into microhabitats. Each microhabitat should have relatively unique ecological characteristics and environmental conditions. The definition and calculation method of niche width are determined. Niche width refers to the resource utilization range occupied by a biological population under specific environmental conditions. Niche data related to each microhabitat, such as habitat type, resource utilization rate, etc., are collected. Based on the collected data, the niche width of each microhabitat is calculated. The calculation method can select appropriate indicators and models according to specific research needs. The species overlap index between each microhabitat is calculated using the collected species information and niche width data. Commonly used indices include Index, Jaccard index, etc. are used to measure the similarity of species coexistence, determine the definition and classification standards of ecological functional groups, which are combinations of species with similar ecological functions and similar responses to the environment. According to the results of the species overlap index, microhabitats are divided into different ecological functional groups, and similar species combinations are classified into the same ecological functional group. The definition and calculation method of regional niche is determined. Regional niche refers to the niche relationship and interaction between different microhabitats in a specific area. The niche association between different microhabitats is analyzed using ecological functional group data. Niche similarity indicators such as the Bray-Curtis similarity index can be calculated to reveal the interaction and association between microhabitats. According to the results of water segmentation, the target water area is divided into microhabitat areas. Each microhabitat area should have relatively unique ecological characteristics and environmental conditions, such as water depth, water flow velocity, vegetation density, etc.

[0125] In this embodiment, reference Figure 4 The 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:

[0126] Step S31: performing ecological connectivity analysis on the water ecosystem characteristic data through microhabitat association data to generate ecological connectivity data;

[0127] Step S32: performing ecological compatibility analysis on the microhabitat association data according to the ecological connectivity data to generate ecological compatibility data;

[0128] Step S33: performing niche difference analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate species niche difference data;

[0129] Step S34: performing community gap structure identification on the species niche difference data to obtain community gap structure configuration data;

[0130] Step S35: Performing niche complementarity analysis on the water ecosystem characteristic data according to the community vacancy structure configuration data to generate niche complementarity data.

[0131] The present invention performs ecological connectivity analysis on water ecosystem characteristic data through microhabitat association data, and can evaluate the ecological connection and interaction degree between different microhabitats. Ecological connectivity data reflects the connectivity and species migration between microhabitats in water areas, which helps to understand the movement path and population diffusion of organisms. Ecological compatibility analysis is performed on microhabitat association data based on ecological connectivity data, and the ecological compatibility between different microhabitats can be evaluated. Ecological compatibility data reflects the similarity and complementarity between microhabitats, and can reveal the adaptability and migration ability of biological populations between different microhabitats. Based on ecological compatibility data, species niche difference analysis is performed on water ecosystem characteristic data, and the degree of niche difference of species in different microhabitats can be evaluated. Species niche difference data reflects the difference in the utilization of different microhabitat resources by species, which helps to understand the functional differentiation and adaptability of species in different microhabitats. Community vacancy structure identification is performed on species niche difference data, and community vacancies and species missing in microhabitats can be found. Community vacancy structure configuration data provides vacancy information about species distribution, which helps to understand the integrity of species diversity and community structure. The niche complementarity analysis of aquatic ecosystem characteristics based on community vacancy structure configuration data can evaluate the niche complementarity between different microhabitats. Niche complementarity data reflects the degree of functional complementarity of species in different microhabitats, which helps to understand the interdependence between biological populations and the differences in resource utilization.

[0132] In this embodiment, the definition and calculation method of ecological connectivity are determined. Ecological connectivity refers to the ability of biological populations to communicate and migrate between different microhabitats, reflecting the connectivity and species mobility of the ecosystem. The collected microhabitat association data are used to analyze the ecological connectivity between different microhabitats. Graph theory or network analysis methods can be used to calculate connectivity indicators between microhabitats, such as connectivity degree, network centrality, etc. According to the results of the ecological connectivity analysis, ecological connectivity data containing each microhabitat are generated to describe the degree of connection between microhabitats and the potential for species migration. The ecological connectivity data and microhabitat association data are used to analyze the ecological compatibility between different microhabitats. Based on factors such as species composition and habitat characteristics, compatibility indicators between microhabitats, such as species coexistence index and habitat similarity, can be calculated. According to the results of the ecological compatibility analysis, ecological compatibility data containing each microhabitat are generated to describe the degree of mutual adaptation between microhabitats and the potential for species coexistence. The ecological compatibility data and species niche data are used to analyze the niche differences of different species in different microhabitats. Statistical methods or niche models can be used to calculate the compatibility of different species to different microhabitats. Based on the difference in the degree of utilization of different resources, according to the results of niche difference analysis, the species niche difference data containing each microhabitat are generated, the differences in the niche adaptability of different species in different microhabitats are described, and the definition and identification method of community gap structure are determined. Community gap structure refers to the structural characteristics of the lack of specific species or species combinations in a specific microhabitat. Using species niche difference data, the community gap structure existing in different microhabitats can be identified. Cluster analysis, species diversity index and other methods can be used to identify microhabitats lacking specific species or species combinations. According to the results of community gap structure identification, community gap structure configuration data containing each microhabitat are generated, which describe the characteristics of community gap structure existing in different microhabitats. The niche complementarity relationship between species in different microhabitats is analyzed by using community gap structure configuration data and species niche data. The resource utilization differences and interaction degrees between different species can be calculated based on species coexistence models, niche overlap index and other methods. According to the results of niche complementarity analysis, niche complementarity data containing each microhabitat are generated, which describe the complementarity and symbiotic relationship between species in different microhabitats.

[0133] In this embodiment, step S32 includes the following steps:

[0134] Step S321: performing functional group-environment relationship analysis on microhabitat association data according to ecological connectivity data to generate microhabitat functional group-environment relationship data;

[0135] Step S322: performing species compatibility analysis and biological species compatibility analysis on the microhabitat association data according to the microhabitat functional group-environment relationship data;

[0136] Step S323: performing structural compatibility analysis on the microhabitat association data to generate structural compatibility data;

[0137] Step S324: performing energy compatibility analysis on the structural compatibility data according to interspecies compatibility to generate regional energy compatibility data;

[0138] Step S325: Perform ecological compatibility calculation on the energy compatibility data using the regional ecological comprehensive compatibility calculation formula to generate ecological compatibility data.

[0139] The present invention uses ecological connectivity data to perform functional group-environment relationship analysis on microhabitat association data, and can evaluate the relationship between different microhabitat functional groups and environmental conditions. Microhabitat functional group-environment relationship data provides information about the adaptability and environmental preference of functional groups, which helps to understand the distribution and ecological functions of different functional groups under different environmental conditions. According to the microhabitat functional group-environment relationship data, the microhabitat association data is analyzed for species compatibility, and the interaction and coexistence ability between different species can be evaluated. The species compatibility data reflects the degree of mutual adaptation and ecological complementarity between species, which helps to understand species diversity and the stability of the ecosystem. The structural compatibility data reflects the differences in morphological characteristics and spatial distribution between microhabitats, which helps to understand habitat connectivity and the feasibility of species migration. The regional energy compatibility data reflects the effectiveness of energy transfer between different microhabitats and the degree of niche overlap between species, which helps to understand the energy flow and species interdependence in the ecosystem. The ecological compatibility calculation is performed using regional energy compatibility data and the ecological comprehensive compatibility calculation formula, and the ecological compatibility of different microhabitats can be comprehensively evaluated. Ecological compatibility data provide information on the overall compatibility between microhabitats and the comprehensive stability of the ecosystem, which helps guide decision-making and optimal resource allocation for water ecological protection and restoration.

[0140] In this embodiment, the functional groups in the microhabitat are determined, that is, the species are classified into the same category according to their niche characteristics and functional similarities, each functional group and microhabitat are analyzed, and the relationship between the functional group and the environmental characteristics is explored. Statistical methods or machine learning algorithms, such as regression analysis or decision tree algorithms, can be used to establish an association model between the functional group and the environmental characteristics. According to the results of the functional group-environment relationship analysis, data containing the relationship between each microhabitat and the functional group are generated, describing the response and adaptability of the functional group to the environmental characteristics in different microhabitats. The microhabitat functional group-environment relationship data are used to analyze the compatibility between different species in the same functional group. The resource utilization differences and the degree of interaction between different species can be calculated based on methods such as species coexistence models and niche overlap indexes. According to the results of the interspecies compatibility analysis, species compatibility data containing each microhabitat and the functional group are generated, describing the mutual adaptation degree and symbiotic relationship between different species in the same functional group. The structural compatibility between different microhabitats is analyzed using the microhabitat association data. Cluster analysis, species diversity index and other methods can be used to calculate the similarity of species composition and the consistency of structural characteristics between different microhabitats. According to the structural compatibility The results of the analysis generate structural compatibility data for each microhabitat, which describes the similarity of species composition and structural characteristics between different microhabitats. Energy compatibility refers to the complementarity and synergistic relationship between species in resource utilization and energy transfer. The inter-species compatibility data and structural compatibility data are used to analyze the energy compatibility between different species. The complementarity and synergistic relationship between different species in resource utilization and energy transfer can be calculated based on the functional characteristics of species, niche analysis and other methods. According to the results of the energy compatibility analysis, energy compatibility data for each region are generated, which describes the complementarity and synergistic relationship between different species in resource utilization and energy transfer. Ecological compatibility refers to the overall coordination and stability of ecological functions and interactions between different microhabitats and species in a region. The regional energy compatibility data are used to calculate the ecological compatibility between different microhabitats and species in a region according to the defined ecological compatibility calculation formula. The calculation formula can take into account factors such as species diversity, niche overlap, and relative abundance. According to the results of the ecological compatibility calculation, ecological compatibility data for each region are generated, which describes the overall coordination and stability of ecological functions and interactions between different microhabitats and species in a region.

[0141] In this embodiment, the regional ecological comprehensive compatibility calculation formula in step S325 is specifically:

[0142]

[0143] Among them, C is the regional ecological comprehensive compatibility index, G is the water area, U is the dissolved oxygen concentration in the water area, I is the number of species, T is the species overlap index, B is the complexity of the community structure, h is the number of food chains, W is the number of top predators in the food chain, H is the species environment matching degree, S is the ecological resilience index, D is the regional plankton energy value, R is the water quality index, and A is the degree of species mutual assistance.

[0144] The present invention calculates the natural logarithm of the water area multiplied by the dissolved oxygen concentration in the water area through G·lnU, which represents the ecological environment quality of the water area. A larger area and a higher dissolved oxygen concentration generally mean a better ecological environment. It represents the combined effect of species number, species overlap index and community structure complexity. Higher species number, species overlap index and community structure complexity indicate that there are abundant species and complex ecological networks in the ecosystem, which is conducive to the stability and compatibility of the ecosystem. The combined effect of species-environment matching, the number of top predators in the food chain, and species-environment matching was calculated. A higher species-environment matching and a richer number of top predators in the food chain indicate a higher degree of interrelationship and interdependence among species in the ecosystem. The comprehensive effects of the ecological resilience index, regional plankton energy value, water quality index and species mutual assistance degree are calculated. A higher ecological resilience index and regional plankton energy value indicate that the ecosystem has a stronger adaptability to external disturbances, and a better water quality index and species mutual assistance degree indicate good ecological interaction and synergy of the ecosystem. The formula comprehensively considers multiple factors such as water area, water quality, species quantity, ecological network structure, food chain relationship, species environment matching, ecological resilience and species mutual assistance, and evaluates the comprehensive compatibility of regional ecosystems from different aspects. By calculating the C value, the compatibility of regional ecosystems can be quantitatively evaluated, providing a scientific basis and decision-making support for ecological protection and restoration.

[0145] In this embodiment, step S4 includes the following steps:

[0146] Step S41: Calculating the complementarity of the niche complementarity data according to the species overlap index to generate the niche complementarity;

[0147] Step S42: performing complementary network analysis on the niche complementarity data according to the niche complementarity degree to obtain the niche complementarity network;

[0148] Step S43: fitting a complementary map of the niche complementarity network to construct an ecological niche complementarity map;

[0149] Step S44: performing microhabitat complementarity node analysis on the niche complementarity data through the niche complementarity map to obtain microhabitat complementarity nodes;

[0150] Step S45: Perform complementary strategy analysis on the microhabitat complementary nodes to generate an ecological complementary strategy.

[0151] The present invention calculates the complementarity of niche complementarity data through the species overlap index, and can evaluate the degree of niche overlap between different biological species or functional groups. The niche complementarity data provides information about the resource utilization and niche segmentation of species or functional groups, which is helpful to understand the interaction between biological species diversity and different biological groups in the ecosystem. According to the niche complementarity, the niche complementarity data is analyzed by complementary network, which can reveal the complementary relationship and mutual dependence between biological species or functional groups. The complementary network provides information on the connection mode and interaction intensity between species or functional groups, which is helpful to understand the network structure of energy flow and species mutual dependence in the ecosystem. The niche complementarity network is fitted with a complementary map, and a niche complementarity map can be constructed. The niche complementarity map reflects the spatial distribution and characteristics of different biological species or functional groups in resource utilization and niche segmentation, which is helpful to understand the niche complementarity and niche diversity of different regions in the ecosystem. Microhabitat complementary nodes can be determined by performing microhabitat complementary node analysis on the niche complementarity data through the niche complementarity map, and microhabitat nodes with high complementarity can be determined. Microhabitat complementarity nodes provide information about the complementary relationship and niche segmentation between different microhabitats, which helps to understand the microhabitat diversity and distribution of key nodes in the ecosystem. Complementarity strategy analysis of microhabitat complementarity nodes can generate ecological complementarity strategies. Ecological complementarity strategies provide suggestions and guidance on how to optimize microhabitat configuration and resource utilization to promote niche complementarity and ecosystem restoration, which is helpful for decision-making and implementation of water ecological protection and restoration.

[0152] In this embodiment, niche complementarity is an indicator to measure the degree of niche overlap between different species, and is used to evaluate their mutual relationship in resource utilization and niche differentiation. Based on the niche complementarity data, the species overlap index between different species is calculated. The species overlap index can be calculated using various methods, such as the Pianka index, the Morisita index, etc., which are used to quantify the degree of niche overlap between species. Based on the calculation result of the species overlap index, niche complementarity data containing each species is generated, which describes the degree of niche overlap between different species. The niche complementarity data is used to construct a niche complementarity network, in which each species represents a node in the network, and the connection between the nodes represents the complementary relationship between them. According to the set threshold or the specified complementarity range, it is determined which species have a complementary relationship and establish a network connection. A binarization method or a weighted connection method based on the complementarity value can be used. According to the complementary relationship and connection information, a niche complementarity network containing species nodes and complementary relationships is generated, which describes the complementary relationship and network topology between different species, and the definition and construction method of the complementary map are determined. The complementary map is the result of fitting the niche complementarity network. Used to reveal the complementary relationship and interaction pattern between species. According to the niche complementarity network, an appropriate fitting algorithm is applied to fit the network. Common fitting algorithms include community discovery algorithm, maximum likelihood estimation, etc., which are used to identify complementary patterns and determine the structure of the complementary map. The constructed niche complementary map is used to perform microhabitat complementary node analysis on the niche complementary data. In each microhabitat, the species node most relevant to the microhabitat is identified according to the contribution or association degree of the species. According to the results of the microhabitat complementary node analysis, the complementary nodes in each microhabitat are determined. These complementary nodes can be species with important functions or key roles in the microhabitat, and play an important role in the stability and ecological function of the microhabitat. The microhabitat complementary nodes are analyzed in detail to understand their niche characteristics, functions and interaction patterns. This can include research on the niche adaptability, resource utilization strategies and niche differentiation degree of species. According to the results of the complementary node analysis, ecological complementary strategies for different microhabitats are generated. These strategies include protecting or increasing the number of complementary nodes, adjusting resource allocation and management strategies, promoting interactions between complementary nodes, etc., so as to improve the stability and ecological function of the ecosystem.

[0153] In this embodiment, step S5 includes the following steps:

[0154] Step S51: Perform complementary biological population analysis on water ecological structure data through ecological complementarity strategy to obtain ecological complementary populations;

[0155] Step S52: performing a floating bed vegetation spatial distribution analysis on the ecological complementary population to generate vegetation spatial distribution data;

[0156] Step S53: Designing an ecological restoration floating bed for ecological complementary populations based on the vegetation spatial distribution data to construct an ecological complementary restoration floating bed;

[0157] Step S54: extracting the target microhabitat position of the ecological complementarity strategy to generate target microhabitat position parameters;

[0158] Step S55: According to the target microhabitat location parameters, the ecological complementary restoration floating bed is implanted into the microhabitat using numerical control navigation technology, and water ecological restoration data is collected.

[0159] The present invention can identify the situation of species missing or insufficient in the ecosystem by analyzing and simulating the water ecological structure data. Through the ecological complementarity strategy, suitable biological populations can be selected to fill the gaps of species missing to enhance the stability and function of the ecosystem. The introduction of ecological complementary populations can improve biodiversity and promote the recovery and restoration of the ecosystem. By analyzing the spatial distribution of ecological complementary populations on floating bed vegetation, the distribution range, density and structure of different vegetation communities can be understood. Vegetation spatial distribution data can provide information such as coverage, uniformity and diversity of floating bed vegetation. Based on vegetation spatial distribution data, the design and construction of ecological restoration floating beds can be carried out. Ecological restoration floating beds are artificially constructed plant habitats. By reasonably arranging the distribution and density of ecological complementary populations, suitable habitat conditions and resource supply can be provided to promote plant growth and species reproduction. Ecological restoration floating beds can increase biodiversity, improve water quality, provide habitats, and promote the recovery and stability of ecosystems. By analyzing the ecological complementary strategy, the target microhabitat position suitable for ecological restoration can be determined. Using numerical control navigation technology, the ecological complementary restoration floating bed can be precisely implanted into the target microhabitat. By implanting the ecological complementary restoration floating bed, the ecological environment of the water body can be improved, habitats and nutrient sources can be provided, and plant growth and the reproduction of aquatic organisms can be promoted. At the same time, the collection of water ecological restoration data can evaluate the restoration effect and the degree of recovery of the ecosystem, providing a scientific basis and monitoring data for water ecological protection and restoration.

[0160] In this embodiment, according to the previously generated ecological complementarity strategy, for a specific aquatic ecosystem, a strategy is applied to select suitable biological populations, according to the ecological complementarity strategy, species with complementary niche characteristics are selected to construct ecological complementary populations, according to the species selected by the ecological complementarity strategy, their population size and spatial distribution are determined, ensuring that the selected species complement and coordinate each other in terms of resource utilization and niche differentiation to improve the stability and function of the aquatic ecosystem, and the vegetation distribution of the ecological complementary population on the floating bed is analyzed. The floating bed is an artificially constructed vegetation platform used to provide an environment for biological habitat and ecological restoration. Surveys and sampling of vegetation on the floating bed are carried out, and information such as vegetation type, quantity, and coverage in each floating bed unit is recorded. Based on the vegetation survey data, the spatial distribution of vegetation is analyzed. Based on the vegetation spatial distribution data and the ecological complementary population, the structure and layout of the ecological restoration floating bed are designed, considering the spatial distribution of vegetation, the complementary relationship of species, and the ecological restoration goals, the size, shape, and location of the floating bed are determined, and the actual floating bed construction is carried out according to the designed ecological restoration floating bed plan, and appropriate materials and tools are selected to build the floating bed according to the design requirements. After the construction of the floating bed is completed, debugging and adjustment work is carried out to check the stability of the floating bed, the growth of vegetation and the interaction with the surrounding environment, and make adjustments to the areas that need improvement or correction. According to the ecological complementarity strategy, analyze and extract key parameters related to the target microhabitat. These parameters include water quality requirements, bottom type, light conditions, etc. According to the extracted parameters, determine the location of the target microhabitat in the aquatic ecosystem, prepare the equipment and tools required for numerical control navigation technology, including navigation systems, ships or submersibles, etc., and use numerical control navigation technology to restore the ecological complementarity floating bed. The bed is accurately positioned to the target microhabitat. According to the target microhabitat location parameters, the ship or submersible is navigated to ensure that the floating bed is accurately placed at the target location. The ecologically complementary populations in the ecologically complementary restoration floating bed are directionally implanted into the target microhabitat. According to the design plan and planting plan, suitable plants or biological populations are placed on the floating bed to achieve the goal of ecological restoration. After implantation, water ecological restoration data is collected, which includes water quality monitoring, plant growth observation, species richness surveys, etc. Through long-term data collection and analysis, the effect of the ecological restoration floating bed and the recovery of the aquatic ecosystem are evaluated.

[0161] In this embodiment, step S6 includes the following steps:

[0162] Step S61: Iteratively optimize the water ecological restoration data using a deep learning algorithm to generate water ecological restoration optimization data;

[0163] Step S62: performing convolution preprocessing on the water ecological restoration optimization data to generate a convolution sample set;

[0164] Step S63: performing dilated convolution on the convolution sample set to generate a water ecological restoration convolution network;

[0165] Step S64: performing pooling sampling on the water ecological restoration convolutional network to generate a water ecological restoration convolutional graph;

[0166] Step S65: Perform data mining modeling on the water ecological restoration convolution graph to construct a water ecological restoration model to perform water ecological protection and restoration operations.

[0167] The present invention can improve the accuracy and predictive ability of data by iteratively optimizing water ecological restoration data by applying deep learning algorithms. Deep learning algorithms can learn and extract complex patterns and associations in data, thereby generating more accurate water ecological restoration optimization data. These optimization data can provide a more reliable basis for subsequent analysis and decision-making. Through convolution preprocessing, water ecological restoration optimization data can be converted into a sample set suitable for convolutional neural network (CNN) processing. Convolution preprocessing can extract spatial and temporal features in data, capture local structures and patterns of data, and thus better reveal the laws and trends of water ecological restoration. The generated convolution sample set can be used to train and verify the convolution network model of water ecological restoration. Through dilated convolution, a convolutional neural network for water ecological restoration can be constructed. Dilated convolution can increase the network receptive field, capture a wider spatial range and contextual information, and improve the network's understanding and predictive ability of water ecological restoration data. The water ecological restoration convolution network can learn features and patterns in the data and be used for subsequent image processing and analysis tasks. Through pooled sampling, key features can be extracted from the water ecological restoration convolution network to generate a water ecological restoration convolution map. Pooled sampling can reduce the dimension of data, extract important feature information, and maintain the consistency of spatial relationships. The water ecological restoration convolution map can be used for visualization analysis, feature extraction, and pattern recognition, providing a more intuitive and interpretable data representation for water ecological protection and restoration. By performing data mining modeling on the water ecological restoration convolution map, a water ecological restoration model can be constructed to predict and optimize water ecological protection and restoration operations. Data mining modeling can discover hidden patterns and association laws in the data, and provide predictions and optimization plans for the effects of water ecological restoration. The water ecological restoration model can provide decision support for decision makers and guide the implementation and management of water ecological protection and restoration work.

[0168] In this embodiment, a deep learning algorithm suitable for water ecological restoration data optimization is selected. Common algorithms include convolutional neural networks (CNN), recurrent neural networks (RNN) and generative adversarial networks (GAN), etc. According to the specific problem and data type, the most appropriate algorithm is selected, and the selected deep learning algorithm is used to iteratively optimize the water ecological restoration data. By training the model and providing feedback, the data is continuously adjusted and optimized to improve the restoration effect and prediction accuracy. The water ecological restoration optimization data is preprocessed, including data normalization, smoothing, feature extraction, etc., to ensure the consistency and availability of the data before entering the convolutional neural network. Appropriate dilation convolution parameters are selected, including convolution kernel size, dilation rate, step size, etc. These parameters will be adjusted according to the characteristics of the data and the needs of the problem. According to the set dilation convolution parameters, a water ecological restoration convolution network is constructed. The structure of the network may include multiple convolutional layers, pooling layers and fully connected layers to extract and learn the features of the data. Appropriate pooling parameters are selected, such as pooling window size and step size. The pooling operation will The convolution feature map is reduced in dimension and sampled to reduce the number of parameters and computational complexity. According to the set pooling parameters, the output of the water ecological restoration convolutional network is pooled. Common pooling methods include maximum pooling and average pooling. You can choose a method that suits the problem requirements. After pooling sampling, the water ecological restoration convolution map is obtained. These images have the characteristics of reducing dimensions and retaining important features, and can be used for subsequent data mining and modeling. The water ecological restoration convolution map is used for data mining, including feature extraction, pattern recognition, classification and other technologies. According to the results of data mining, a water ecological restoration model is constructed. Machine learning algorithms (such as support vector machines, decision trees, random forests, etc.) or deep learning algorithms (such as neural networks, recurrent neural networks, etc.) can be used to predict and optimize the effect of water ecological restoration. According to the constructed water ecological restoration model, water ecological protection and restoration operations are performed. According to the restoration goals, corresponding restoration plans and measures are formulated and implemented according to the guidance of the model. The restoration operations involve vegetation restoration, water quality improvement, species protection and other aspects.

[0169] 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.

[0170] It should be understood that although the terms "first", "second", etc. are 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, a first unit may be referred to as a second unit, and similarly a second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0171] 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 method for water ecological protection and restoration based on niche complementation technology, characterized in that: The following steps are involved: Step S1: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area; Use sensors to detect water DNA in target waters to obtain water ecological structure data; perform water ecosystem analysis on target water images based on the water ecological structure data to generate water ecosystem characteristic data; Step S2: subdividing the target water area image based on the water ecosystem characteristic data to generate microhabitats; performing regional niche association analysis on the microhabitats to generate microhabitat association data; Step S3: performing ecological compatibility analysis on the water ecosystem characteristic data through the microhabitat association data to generate ecological compatibility data; performing niche complementarity analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate niche complementarity data; Step S4: fitting the complementary map of the niche complementarity data to construct the niche complementarity map; performing complementary strategy analysis on the niche complementarity data through the niche complementarity map to generate an ecological complementarity strategy; Step S5: Designing an ecological restoration floating bed based on water ecological structure data through an ecological complementary strategy to construct an ecological complementary restoration floating bed; Use CNC navigation technology to implant ecological complementary restoration floating beds into microhabitats and collect water ecological restoration data; Step S6: Iteratively optimize the water ecological restoration data using a deep learning algorithm to generate water ecological restoration optimization data; The water ecological restoration optimization data is expanded and convolved to build a water ecological restoration model to perform water ecological protection and restoration operations.

2. The method according to claim 1, characterized in that The specific steps of step S1 are: Step S11: using ecological remote sensing technology to collect images of the target water area to obtain images of the target water area; Step S12: using a sensor to detect water DNA in the target water area to obtain water DNA data; Step S13: performing DNF amplification processing on the water body DNA data to obtain the water body community richness; Step S14: performing high-throughput sequencing based on the richness of the water community to generate short DNA sequence fragments; Step S15: performing species classification processing on the DNA short sequence fragments to obtain water ecological structure data; Step S16: Performing water ecosystem analysis on the target water area image according to the water ecological structure data to generate water ecosystem characteristic data.

3. The method according to claim 2, characterized in that The specific steps of step S16 are: Step S161: performing water quality analysis on the target water area image according to the water ecological structure data to generate water quality data of the target water area; Step S162: Performing functional zone distribution analysis on the water ecological structure data based on the target water area water quality data to generate water area functional zone distribution data, the water area functional zone distribution data including breeding area, trophic area, diapause area, habitat area and exchange area; Step S163: Perform trophic level analysis on the water functional zone distribution data to generate water biological trophic level data; Step S164: performing group structure analysis on the water ecological structure data to generate water area group structure data; Step S165: Performing water ecosystem analysis on the water area population structure data through the water area organism trophic level data to generate water ecosystem characteristic data.

4. The method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: subdividing the target water area image into water areas based on the water ecosystem characteristic data to generate microhabitats; Step S22: Calculate the niche width of the microhabitat to generate niche width data; Step S23: Calculating the species overlap index of the microhabitat according to the niche width data to generate the species overlap index; Step S24: performing ecological function group analysis on the microhabitat through the species overlap index to obtain ecological function group data; Step S25: Perform regional niche association analysis on the ecological functional group data to generate microhabitat association data.

5. The method according to claim 1, characterized in that The specific steps of step S3 are: Step S31: performing ecological connectivity analysis on the water ecosystem characteristic data through microhabitat association data to generate ecological connectivity data; Step S32: performing ecological compatibility analysis on the microhabitat association data according to the ecological connectivity data to generate ecological compatibility data; Step S33: performing niche difference analysis on the water ecosystem characteristic data based on the ecological compatibility data to generate species niche difference data; Step S34: performing community gap structure identification on the species niche difference data to obtain community gap structure configuration data; Step S35: Performing niche complementarity analysis on the water ecosystem characteristic data according to the community vacancy structure configuration data to generate niche complementarity data.

6. The method according to claim 5, characterized in that The ecological compatibility analysis includes species compatibility analysis, structural compatibility analysis, energy compatibility analysis and ecological compatibility calculation. The specific steps of step S32 are: Step S321: performing functional group-environment relationship analysis on microhabitat association data according to ecological connectivity data to generate microhabitat functional group-environment relationship data; Step S322: performing species compatibility analysis and biological species compatibility analysis on the microhabitat association data according to the microhabitat functional group-environment relationship data; Step S323: performing structural compatibility analysis on the microhabitat association data to generate structural compatibility data; Step S324: performing energy compatibility analysis on the structural compatibility data according to interspecies compatibility to generate regional energy compatibility data; Step S325: Perform ecological compatibility calculation on the energy compatibility data using the regional ecological comprehensive compatibility calculation formula to generate ecological compatibility data.

7. The method according to claim 6, characterized in that The regional ecological comprehensive compatibility calculation formula in step S325 is specifically: Among them, C is the regional ecological comprehensive compatibility index, G is the water area, U is the dissolved oxygen concentration in the water area, I is the number of species, T is the species overlap index, B is the complexity of the community structure, h is the number of food chains, W is the number of top predators in the food chain, H is the species environment matching degree, S is the ecological resilience index, D is the regional plankton energy value, R is the water quality index, and A is the degree of species mutual assistance.

8. The method according to claim 1, characterized in that The specific steps of step S4 are: Step S41: Calculating the complementarity of the niche complementarity data according to the species overlap index to generate the niche complementarity; Step S42: performing complementary network analysis on the niche complementarity data according to the niche complementarity degree to obtain the niche complementarity network; Step S43: fitting a complementary map of the niche complementarity network to construct an ecological niche complementarity map; Step S44: performing microhabitat complementarity node analysis on the niche complementarity data through the niche complementarity map to obtain microhabitat complementarity nodes; Step S45: Perform complementary strategy analysis on the microhabitat complementary nodes to generate an ecological complementary strategy.

9. The method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: Perform complementary biological population analysis on water ecological structure data through ecological complementarity strategy to obtain ecological complementary populations; Step S52: performing a floating bed vegetation spatial distribution analysis on the ecological complementary population to generate vegetation spatial distribution data; Step S53: Designing an ecological restoration floating bed for ecological complementary populations based on the vegetation spatial distribution data to construct an ecological complementary restoration floating bed; Step S54: extracting the target microhabitat position of the ecological complementarity strategy to generate target microhabitat position parameters; Step S55: According to the target microhabitat location parameters, the ecological complementary restoration floating bed is implanted into the microhabitat using numerical control navigation technology, and water ecological restoration data is collected.

10. The method according to claim 1, characterized in that The specific steps of step S6 are: Step S61: Iteratively optimize the water ecological restoration data using a deep learning algorithm to generate water ecological restoration optimization data; Step S62: performing convolution preprocessing on the water ecological restoration optimization data to generate a convolution sample set; Step S63: performing dilated convolution on the convolution sample set to generate a water ecological restoration convolution network; Step S64: performing pooling sampling on the water ecological restoration convolutional network to generate a water ecological restoration convolutional graph; Step S65: Perform data mining modeling on the water ecological restoration convolution graph to construct a water ecological restoration model to perform water ecological protection and restoration operations.

Images