Water bird habitat suitability evaluation system

Through the integrated data collection and deep learning modules, a dynamic evaluation index system was established, which solved the shortcomings of traditional aquarium bird habitat evaluation methods, provided scientific and accurate aquarium bird habitat suitability evaluation, promoted the maintenance of water bird reproduction and ecological balance, and achieved the Sustainable protection of waterbird habitats.

CN119026801AInactive Publication Date: 2024-11-26NATIONAL MARINE ENVIRONMENTAL MONITORING CENTRE
View PDF 0 Cites 6 Cited by

Patent Information

Application Number
CN202411129352.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The traditional aquabird habitat suitability evaluation method has poor practicality, insufficient scientificity, single evaluation indicators, lack of data, and limitations in time and space scale, which leads to inaccuracy and one-sidedness of the evaluation results, which is difficult to meet the needs of management practice.

Method used

The data collection module is used to collect factors such as habitat quality, nest site availability, food resource availability, protection management level and human interference, and combine historical ecological environment data, drone image data and deep learning module to establish dynamic evaluation indicators. System, realize centralized processing and visual presentation of data, consider socio-economic factors, and real-time monitoring and adjustment of indicators.

Benefits of technology

It provides a comprehensive, scientific and accurate assessment system for aquatic bird habitat suitability, helps decision makers formulate scientific protection policies, promotes the reproduction of water birds and the maintenance of ecological balance, improves assessment accuracy and efficiency, and achieves sustainable development.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119026801A_ABST
    Figure CN119026801A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of environmental engineering, and discloses a waterfowl habitat suitability evaluation system, which comprises a data collection module, external environmental factors including habitat quality, nest site availability, food resource availability, protection management level and man-made interference degree, and internal biological factors including biological factors including habitat quality, nest site availability, food resource availability, protection management level and man-made interference degree. Comprising bird quantity, bird species, bird breeding, bird migration data and habitat use records; historical ecological environment data collection: collecting and sorting ecological environment data about a certain specific waterfowl habitat in a past period of time; collecting field visit data, and performing field investigation, investigation and recording in the waterfowl habitat; unmanned aerial vehicle image data collection is carried out, and habitat quality evaluation and food resource evaluation are carried out by using an advanced technology so as to improve evaluation precision and efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of environmental engineering, and in particular to a water bird habitat suitability evaluation system. Background Art

[0002] Waterbird habitats refer to specific environments suitable for waterbirds to survive and reproduce, such as coastal zones, lakes, rivers, swamps and other natural waters and their surrounding areas. These habitats not only provide waterbirds with sufficient water sources and abundant food resources, but also provide safe habitats and breeding sites. At the same time, the protection of waterbird habitats is crucial to maintaining ecological balance, protecting biodiversity and promoting harmonious coexistence between man and nature.

[0003] Traditional waterbird habitat suitability evaluation methods may have problems such as lack of practicality, lack of scientificity, single evaluation index, lack of data, time and space scale limitations, and inability to cope with new challenges. These problems may lead to inaccurate and one-sided evaluation results, making it difficult to meet the needs of management practice. Therefore, a waterbird habitat suitability evaluation system is proposed. Summary of the invention

[0004] The purpose of the present invention is to solve the problems that the evaluation method may have poor practicality, insufficient scientificity, single evaluation index, lack of data, and time and space scale limitations, and to propose a water bird habitat suitability evaluation system.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] Data collection module, including external environmental factors, including habitat quality, nest site availability, food resource availability, conservation management level and degree of human disturbance; internal biological factors, including bird numbers, bird species, bird reproduction, bird migration data and habitat use records;

[0007] Historical ecological environment data collection: collecting and collating ecological environment data about a specific waterbird habitat over a period of time;

[0008] Field visit data collection is the process of conducting field visits, surveys, and records within waterbird habitats;

[0009] UAV image data collection, habitat quality assessment and food resource assessment using advanced technology to improve assessment accuracy and efficiency;

[0010] Central data processing, which processes incoming data centrally to enable simple, fast and accurate analysis of data;

[0011] Deep learning modules, including: feature extraction, target detection, classification recognition and time series analysis;

[0012] Establish a dynamic evaluation index system, and continuously update and adjust the indicators in real-time monitoring to cope with data fluctuations caused by environmental changes and changes in waterbird populations;

[0013] Visualize the evaluation results through charts and maps, so that protectors, managers and the public can more intuitively understand the suitability of waterbird habitats;

[0014] Taking into account socio-economic factors, the livelihoods of local residents and industrial development, the protection of waterbird habitats is integrated with the development of local communities to achieve sustainable development.

[0015] The above technical solution further includes:

[0016] The data collection module is mainly used to store and process various data related to waterbird habitats; habitat quality, which evaluates the quality of wetland ecosystems and is directly related to waterbirds' food resources and ability to escape predators; nest site availability, which evaluates locations in wetlands suitable for waterbirds to build nests to ensure the successful reproduction of waterbirds; food resources, which evaluates the richness of food resources in wetlands; protection and management, which evaluates whether wetlands are supported by effective protection and management measures; and the degree of human disturbance, which evaluates the degree of human disturbance in wetlands.

[0017] The field visit data collection usually adopts a series of survey methods and tools to ensure the accuracy and comparability of the data, thereby providing a reliable data basis. The drone image data collection uses advanced technology to conduct habitat quality assessment and food resource assessment to improve assessment accuracy and efficiency.

[0018] The historical ecological and environmental data collection collects and organizes the ecological and environmental data of specific waterbird habitats over a period of time in the past, including information on waterbird species, quantity, distribution, breeding success rate, food resource richness, habitat type and quality, and threatening factors. By collecting and analyzing historical ecological and environmental data, we can understand the changing trends of waterbird habitats in the past, the evolution of the ecological environment, and the correlation between various factors related to waterbird habitats, discover changes in the number of waterbird populations, improvements or deterioration of habitat quality, and potential threatening factors, provide a scientific basis for the protection and management of waterbird habitats, and formulate corresponding protection strategies and management measures.

[0019] The central data processing performs centralized processing on the incoming data to achieve simple, fast and accurate analysis of the data; the deep learning module includes: feature extraction, which extracts various features of water bird habitats, such as water surface color, water body structure, water body area, and vegetation coverage, through learning from wetland image data. These features can help decision makers and managers better understand the situation of water bird habitats and make evaluations and selections; the target detection, which identifies different objects in the image and finds their locations. In wetland images, deep learning can identify different types of water birds and help managers better understand the species composition of water bird habitats; classification and recognition, the model can classify different objects in wetland images by learning from training data, and provide more information to decision makers and managers to help them evaluate and select water bird habitats; time series analysis, which can analyze time series data, analyze and predict water surface fluctuations, vegetation growth, and water bird migration in wetland images, and help decision makers and managers better understand the changes in water bird habitats and formulate corresponding protection and management measures.

[0020] The feature extraction uses principal component analysis as a feature extraction and selection algorithm, a commonly used dimensionality reduction technique, which projects the original data into a new feature space through linear transformation so that the projected features have the largest variance, reduce the dimension of the features, and retain the most important information in the original data. Four features are used for classification and identification of waterbird habitats: humidity, temperature, vegetation coverage, and water area. The covariance matrix between the features is calculated. The element c(i, j) of the covariance matrix C can be calculated by the following formula

[0021] c(i,j)=(1 / n)*Σ((X(i,k)-mean(X(:,i)))*(X(j,k)-mean(X(:,j))))

[0022] Among them, mean(X(:,i)) represents the mean of the i-th feature, and calculates the eigenvector and eigenvalue of the covariance matrix C. The eigenvector represents the direction of the principal component of the covariance matrix, and the eigenvalue represents the importance of the eigenvector. We sort the eigenvectors according to the size of the eigenvalue and select the principal components corresponding to the first two eigenvectors as new features. The two principal components can be obtained by

[0023] new_feature=X*V(:,1:2) where V(:,1:2) represents the matrix composed of the first two eigenvectors in the eigenvalue matrix, and new_feature is the sample feature projected to the new feature space. Through the above steps, the principal component analysis algorithm is used to extract and select appropriate features, and the original four features of humidity, temperature, vegetation coverage and water area are converted into new features of two principal components, which can reduce the dimension of the features and retain the most important feature information, facilitating subsequent classification and recognition tasks.

[0024] The time series analysis considers using the data of water bird population changes over time for evaluation. There is observation data of water bird population in a wetland area over a period of time. We want to evaluate the suitability of the area for water birds through time series analysis. The time series analysis method is seasonal decomposition, which decomposes the time series data into trend terms, seasonal terms and residual terms, so as to help us understand the characteristics and laws of time series data. There is a continuous 12-month observation data of water bird population, represented by y(1), y(2), ..., y(12) respectively. Using seasonal decomposition to evaluate the suitability of the area for water birds, we can calculate the trend of the average number of water birds each month. A simple way is to calculate the 12-month moving average. For each month i, we can calculate

[0025] Trend(i)=(1 / 3)*(y(i-1)+y(i)+y(i+1)) where Trend(i) represents the trend item of the i-th month. The seasonal factor of each month is calculated to represent the impact of seasonal changes. The ratio of the number of waterbirds in each month to the average number of waterbirds throughout the year is calculated as the seasonal factor.

[0026] Seasonal_Factor(i)=y(i) / Average(y(1),y(2),...,y(12))

[0027] Among them, we can calculate the residual term to represent the part that cannot be explained by the trend term and seasonal factor

[0028] Residual(i)=y(i) / (Trend(i)*Seasonal_Factor(i))

[0029] Among them, through such seasonal decomposition, we can obtain trend terms, seasonal factors and residual terms, so as to better understand the changes in the number of waterbirds over time, and evaluate the suitability of the area for waterbirds based on these decomposed data, whether there are obvious seasonal patterns, and whether the residual terms show abnormal fluctuations.

[0030] The aforementioned establishment of a dynamic evaluation index system continuously updates and adjusts the indexes in real-time monitoring to cope with the real-time changes brought about by environmental changes and changes in waterbird populations; the aforementioned visualization of the evaluation results enables protectors, managers and the public to more intuitively understand the suitability of waterbird habitats through charts and maps; the aforementioned consideration of socio-economic factors utilizes the livelihoods of local residents and industrial development to integrate the protection of waterbird habitats with the development of local communities to achieve sustainable development.

[0031] The present invention has the following beneficial effects:

[0032] 1. In the present invention, the comprehensive waterbird habitat suitability evaluation index is used to guide the protection and management of waterbird habitats, and through the evaluation system, it helps decision makers to formulate scientific protection policies to promote the reproduction of waterbirds and the maintenance of ecological balance.

[0033] 2. In the present invention, the deep learning module can quickly and accurately identify different types of water birds, aquatic plants, water body structures and other elements by learning and analyzing a large amount of wetland image data, providing more information for the selection and evaluation of water bird habitats. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is an overall system block diagram of a water bird habitat suitability evaluation system proposed by the present invention;

[0035] Figure 2 This is a partial block diagram of a water bird habitat suitability evaluation system proposed by the present invention. DETAILED DESCRIPTION

[0036] Embodiment 1

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] like Figure 1-2As shown, a waterfowl habitat suitability evaluation system proposed by the present invention includes: a data collection module, wherein the external environmental factors include: habitat quality, nest site availability, food resource availability, protection management level and degree of human disturbance, wherein the internal biological factors include: bird population, bird species, bird reproduction, bird migration data and habitat use records; historical ecological environment data collection, collecting and collating ecological environment data about a specific waterfowl habitat in the past period of time; field visit data collection, the process of conducting field visits, investigations and records in waterfowl habitats; drone image data collection, using advanced technology to evaluate habitat quality and food resources to improve evaluation accuracy and efficiency; central data processing, centralized processing of incoming data to achieve simple, fast and accurate analysis of data;

[0039] The deep learning module includes: feature extraction, target detection, classification recognition and time series analysis; establish a dynamic evaluation index system, continuously update and adjust the index in real-time monitoring to cope with data fluctuations caused by environmental changes and changes in waterbird populations; realize the visualization of evaluation results, through charts and maps, so that protectors, managers and the public can more intuitively understand the suitability of waterbird habitats; consider socio-economic factors, the livelihoods of local residents, and industrial development, integrate the protection of waterbird habitats with the development of local communities, and achieve sustainable development. The data collection module is mainly used to store and process various data related to waterbird habitats, habitat quality, and evaluate the quality of aquatic ecosystems, which is directly related to the food resources of waterbirds;

[0040] and the ability to escape predators, nest site availability, assessing suitable nesting sites for waterbirds in waters to ensure successful breeding of waterbirds, food resources, assessing the abundance of food resources in waters, assessing whether waters are effectively protected, conservation management, assessing whether waters are supported by effective protection and management measures, and estimating the degree of human disturbance in waters. The field visit data collection usually adopts a series of survey methods and tools to ensure the accuracy and comparability of data, thereby providing a reliable data basis. The drone image data collection uses advanced technology to conduct habitat quality assessment and food resource assessment to improve assessment accuracy and efficiency. The historical ecological environment data collection collects and organizes ecological environment data of specific waterbird habitats over a period of time in the past.

[0041] Including information on waterbird species, numbers, distribution, reproductive success rate, abundance of food resources, habitat types and quality. By collecting and analyzing historical ecological and environmental data, we can understand the changing trends of waterbird habitats in the past, the evolution of the ecological environment, and the correlation between various factors related to waterbird habitats. We can also find changes in waterbird populations, improvements or deterioration in habitat quality, and potential threatening factors, so as to provide a scientific basis for the protection and management of waterbird habitats, formulate corresponding protection strategies and management measures, and establish a dynamic evaluation index system.

[0042] Indicators are continuously updated and adjusted during real-time monitoring to cope with real-time changes brought about by environmental changes and changes in waterbird populations. The evaluation results are visualized through charts and maps to allow protectors, managers and the public to more intuitively understand the suitability of waterbird habitats. The consideration of socio-economic factors utilizes the livelihoods of local residents and industrial development to integrate waterbird habitat protection with the development of local communities to achieve sustainable development.

[0043] The data collection module can derive a comprehensive waterbird habitat suitability evaluation index by collecting habitat quality, nest site availability, food resource availability, protection and management level, and degree of human disturbance, which is used to guide the protection and management of waterbird habitats. At the same time, field visits, drone image data collection, and historical ecological environment data collection are used to accurately obtain data on the spot, and the sorted data is transmitted to the central data processing. By centrally processing the incoming data, simple, fast and accurate data analysis is achieved. The deep learning module uses the incoming data for modeling and establishes a dynamic evaluation index system. It continuously updates and adjusts indicators during real-time monitoring to cope with data fluctuations caused by environmental changes and changes in waterbird populations, and realizes the visualization of evaluation results and the consideration of socioeconomic factors, the livelihoods of local residents, and industrial development. It integrates the protection of waterbird habitats with the development of local communities to achieve sustainable development.

[0044] Embodiment 2

[0045] like Figure 1-2As shown, in the embodiment of the present invention, data analysis and early warning, the central data processing, centrally processes the incoming data to achieve simple, fast and accurate analysis of the data, the deep learning module includes: feature extraction, through the study of water image data, extracts various features in the water bird habitat, water surface color, water body structure, vegetation coverage, and through these features can help decision makers and managers better understand the situation of water bird habitats, conduct evaluation and selection, the target detection, identifies different objects in the image and finds their location, in the water image, deep learning can identify different types of water birds, help managers better understand the species composition of water bird habitats, classification recognition, the model can classify different objects in the water image by learning the training data, and provide more information for decision makers and managers;

[0046] Help them evaluate and select waterbird habitats. Time series analysis can analyze time series data, analyze and predict water surface fluctuations, vegetation growth, and waterbird migration in water images, and help decision makers and managers better understand the changes in waterbird habitats and formulate corresponding protection and management measures. The feature extraction uses principal component analysis as a feature extraction and selection algorithm, a commonly used dimensionality reduction technique, which projects the original data into a new feature space through linear transformation, so that the projected features have the largest variance and reduce the dimension of the features.

[0047] And retain the most important information in the original data, and use four features for classification and identification of waterbird habitats: humidity, temperature, vegetation coverage and water area, and calculate the covariance matrix between the features. The element c(i,j) of the covariance matrix C can be calculated by the following formula

[0048] c(i,j)=(1 / n)*Σ((X(i,k)-mean(X(:,i)))*(X(j,k)-mean(X(:,j))))

[0049] Among them, mean(X(:,i)) represents the mean of the i-th feature. Next, we need to calculate the eigenvectors and eigenvalues ​​of the covariance matrix C. The eigenvectors represent the principal component directions of the covariance matrix, and the eigenvalues ​​represent the importance of the eigenvectors. We sort the eigenvectors according to the size of the eigenvalues ​​and select the principal components corresponding to the first two eigenvectors as new features. The two principal components can be obtained by

[0050] new_feature=X*V(:,1:2) where V(:,1:2) represents the matrix composed of the first two eigenvectors in the eigenvalue matrix, and new_feature is the sample feature projected into the new feature space;

[0051] Through the above steps, the principal component analysis algorithm is used to extract and select appropriate features, and the original four features of humidity, temperature, vegetation coverage and water area are converted into new features of two principal components, which can reduce the dimension of the features and retain the most important feature information, which is convenient for subsequent classification and recognition tasks. The time series analysis considers the use of data on the changes in the number of water birds over time for evaluation. There is observation data on the number of water birds in a wetland area over a period of time. We want to evaluate the suitability of the area for water birds through time series analysis. The time series analysis method is seasonal decomposition, which decomposes the time series data into trend terms, seasonal terms and residual terms, so as to help us understand the characteristics and laws of time series data. There is a continuous 12-month observation data on the number of water birds;

[0052] Represented by y(1), y(2), ..., y(12) respectively, seasonal decomposition is used to evaluate the suitability of the area for waterbirds. The trend of the average number of waterbirds per month can be calculated. A simple way is to calculate the moving average of 12 months. For each month i, Trend(i) = (1 / 3) * (y(i-1) + y(i) + y(i+1)) can be calculated, where Trend(i) represents the trend item of the i-th month. The seasonal factor of each month is calculated to represent the impact of seasonal changes, so as to calculate the ratio of the number of waterbirds per month to the average number of waterbirds for the whole year as the seasonal factor.

[0053] Seasonal_Factor(i)=y(i) / Average(y(1),y(2),...,y(12))

[0054] Among them, we can calculate the residual term to represent the part that cannot be explained by the trend term and seasonal factor

[0055] Residual(i)=y(i) / (Trend(i)*Seasonal_Factor(i))Through such seasonal decomposition, we can obtain trend terms, seasonal factors and residual terms, so as to better understand the changes in the number of water birds over time, and based on these decomposed data, evaluate the suitability of the area for water birds, whether there are obvious seasonal patterns, and whether the residual terms show abnormal fluctuations.

[0056] Through feature extraction, deep learning models can extract various features of waterbird habitats by learning from water image data. These features can help decision makers and managers better understand the conditions of waterbird habitats, conduct evaluations and selections, and identify different objects in images through target detection and find their locations. By learning from training data, different objects in water images can be classified to provide decision makers and managers with more information to help them evaluate and select waterbird habitats. Time series data can also be used for analysis to help decision makers and managers better understand changes in waterbird habitats and formulate corresponding protection and management measures.

[0057] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A water bird habitat suitability evaluation system, characterized in that: include: Data collection module, including external environmental factors, including habitat quality, nest site availability, food resource availability, conservation management level and degree of human disturbance; internal biological factors, including bird numbers, bird species, bird reproduction, bird migration data and habitat use records; Historical ecological environment data collection: collecting and collating ecological environment data about a specific waterbird habitat over a period of time; Field visit data collection is the process of conducting field visits, surveys, and records within waterbird habitats; UAV image data collection, habitat quality assessment and food resource assessment using advanced technology to improve assessment accuracy and efficiency; Central data processing, which processes incoming data centrally to enable simple, fast and accurate analysis of data; Deep learning modules, including: feature extraction, target detection, classification recognition and time series analysis; Establish a dynamic evaluation index system, and continuously update and adjust the indicators in real-time monitoring to cope with data fluctuations caused by environmental changes and changes in waterbird populations; Visualize the evaluation results through charts and maps, so that protectors, managers and the public can more intuitively understand the suitability of waterbird habitats; Taking into account socio-economic factors, the livelihoods of local residents and industrial development, the protection of waterbird habitats is integrated with the development of local communities to achieve sustainable development.

2. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The data collection module is mainly used to store and process various data related to waterbird habitats; habitat quality, which evaluates the quality of wetland ecosystems and is directly related to waterbirds' food resources and ability to escape predators; nest site availability, which evaluates locations in wetlands suitable for waterbirds to nest in order to ensure the success of waterbird reproduction; Food resources, assess the richness of food resources in the wetland; protection and management, assess whether the wetland is supported by effective protection and management measures; degree of human disturbance, assess the degree of human disturbance in the wetland.

3. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The field visit data collection usually adopts a series of survey methods and tools to ensure the accuracy and comparability of the data, thereby providing a reliable data basis; the drone image data collection uses advanced technology to conduct habitat quality assessment and food resource assessment to improve assessment accuracy and efficiency.

4. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The historical ecological and environmental data collection collects and organizes the ecological and environmental data of specific waterbird habitats over a period of time in the past, including information on waterbird species, quantity, distribution, breeding success rate, food resource richness, habitat type and quality, and threatening factors. By collecting and analyzing historical ecological and environmental data, we can understand the changing trends of waterbird habitats in the past, the evolution of the ecological environment, and the correlation between various factors related to waterbird habitats, discover changes in the number of waterbird populations, improvements or deterioration in habitat quality, and potential threatening factors, provide a scientific basis for the protection and management of waterbird habitats, and formulate corresponding protection strategies and management measures.

5. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The central data processing performs centralized processing on the incoming data to achieve simple, fast and accurate analysis of the data; the deep learning module includes: feature extraction, which extracts various features of water bird habitats, such as water surface color, water body structure, water body area, and vegetation coverage, through learning from wetland image data. These features can help decision makers and managers better understand the situation of water bird habitats and make evaluations and selections; the target detection, which identifies different objects in the image and finds their locations. In wetland images, deep learning can identify different types of water birds and help managers better understand the species composition of water bird habitats; classification and recognition, the model can classify different objects in wetland images by learning from training data, and provide more information to decision makers and managers to help them evaluate and select water bird habitats; time series analysis, which can analyze time series data, analyze and predict water surface fluctuations, vegetation growth, and water bird migration in wetland images, and help decision makers and managers better understand the changes in water bird habitats and formulate corresponding protection and management measures.

6. A water bird habitat suitability evaluation system according to claim 5, characterized in that: The feature extraction uses principal component analysis as a feature extraction and selection algorithm, a commonly used dimensionality reduction technique, which projects the original data into a new feature space through linear transformation so that the projected features have the largest variance, reduce the dimension of the features, and retain the most important information in the original data. Four features are used for classification and identification of waterbird habitats: humidity, temperature, vegetation coverage, and water area. The covariance matrix between the features is calculated. The element c(i, j) of the covariance matrix C can be calculated by the following formula c(i,j)=(1 / n)*Σ((X(i,k)-mean(X(:,i)))*(X(j,k)-mean(X(:,j)))) Among them, mean(X(:,i)) represents the mean of the i-th feature, and calculates the eigenvector and eigenvalue of the covariance matrix C. The eigenvector represents the direction of the principal component of the covariance matrix, and the eigenvalue represents the importance of the eigenvector. We sort the eigenvectors according to the size of the eigenvalue and select the principal components corresponding to the first two eigenvectors as new features. The two principal components can be obtained by new_feature=X*V(:,1:2) where V(:,1:2) represents the matrix composed of the first two eigenvectors in the eigenvalue matrix, and new_feature is the sample feature projected to the new feature space. Through the above steps, the principal component analysis algorithm is used to extract and select appropriate features, and the original four features of humidity, temperature, vegetation coverage and water area are converted into new features of two principal components, which can reduce the dimension of the features and retain the most important feature information, facilitating subsequent classification and recognition tasks.

7. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The time series analysis considers using the data of water bird population changes over time for evaluation. There is observation data of water bird population in a wetland area over a period of time. We want to evaluate the suitability of the area for water birds through time series analysis. The time series analysis method is seasonal decomposition, which decomposes the time series data into trend terms, seasonal terms and residual terms, so as to help us understand the characteristics and laws of time series data. There is a continuous 12-month observation data of water bird population, represented by y(1), y(2), ..., y(12) respectively. Using seasonal decomposition to evaluate the suitability of the area for water birds, we can calculate the trend of the average number of water birds each month. A simple way is to calculate the 12-month moving average. For each month i, we can calculate Trend(i)=(1 / 3)*(y(i-1)+y(i)+y(i+1)) where Trend(i) represents the trend item of the i-th month. The seasonal factor of each month is calculated to represent the impact of seasonal changes. The ratio of the number of waterbirds in each month to the average number of waterbirds throughout the year is calculated as the seasonal factor. Seasonal_Factor(i)=y(i) / Average(y(1),y(2),...,y(12)) Among them, we can calculate the residual term to represent the part that cannot be explained by the trend term and seasonal factor Residual(i)=y(i) / (Trend(i)*Seasonal_Factor(i)) Among them, through such seasonal decomposition, we can obtain trend terms, seasonal factors and residual terms, so as to better understand the changes in the number of waterbirds over time, and evaluate the suitability of the area for waterbirds based on these decomposed data, whether there are obvious seasonal patterns, and whether the residual terms show abnormal fluctuations.

8. A water bird habitat suitability evaluation system according to claim 1, characterized in that: The aforementioned establishment of a dynamic evaluation index system continuously updates and adjusts the indexes in real-time monitoring to cope with the real-time changes brought about by environmental changes and changes in waterbird populations; the aforementioned visualization of the evaluation results enables protectors, managers and the public to more intuitively understand the suitability of waterbird habitats through charts and maps; the aforementioned consideration of socio-economic factors utilizes the livelihoods of local residents and industrial development to integrate the protection of waterbird habitats with the development of local communities to achieve sustainable development.

Citation Information

Cited By

  • Bird disease analysis management and control method and device in combination with ecological environment data

    CN119273161A

  • Coastal wetland environment and bird inhabitation correlation analysis method

    CN119379518A

  • Automatic habitat wild animal monitoring and analyzing system based on unmanned aerial vehicle airport

    CN119888544A

  • Method for investigating and monitoring esculent swift population and habitat by means of unmanned aerial vehicle

    CN119999602A

  • Water bird habitat ecological data analysis method and system, medium and electronic equipment

    CN120316735A