An ecological sensitivity assessment and analysis method and system suitable for highway areas

Abstract

The present invention discloses an ecological sensitivity assessment and analysis method and system suitable for highway areas, specifically relating to the field of highway ecological technology. When comprehensively assessing and managing the ecological environment along the highway, the method identifies and analyzes the distribution of ecological factors of different ecosystems, divides monitoring areas, and extracts characteristic parameters. By constructing a Bayesian network model, the weight of each monitoring area is determined and calculated to obtain an overall ecological environment quality index. Satellite images are used for time series analysis to obtain the spatiotemporal variation of ecological factors. Fuzzy logic is used to analyze the overall environmental quality and spatiotemporal variation to conduct ecological sensitivity assessment. A sensitive area division module divides high, medium, and low sensitive areas according to the assessment results, and feeds the results back to management personnel. Through a systematic and scientific assessment method, the accuracy and efficiency of highway ecological environment management are improved, ensuring the timely protection and reasonable development of sensitive areas.

Description

Technical Field

[0001] The present invention relates to the field of highway ecological technology, and in particular to an ecological sensitivity assessment and analysis method and system suitable for highway areas. Background Art

[0002] Ecological sensitivity assessments for highways involve comprehensive analysis and evaluation of ecosystems along highways and within their impact areas to determine their sensitivity and vulnerability to environmental change. This assessment aims to identify and quantify the potential impacts of highway construction and operation on the ecological environment, including potential threats to biodiversity, soil and water conservation, vegetation cover, and animal habitats. This provides a scientific basis for developing appropriate conservation measures and mitigating environmental impacts.

[0003] Ecological sensitivity assessments can identify key ecologically sensitive areas along expressways and develop corresponding environmental management strategies to minimize damage to the natural environment. This process also involves evaluating various indicators related to ecological protection, such as species diversity, water quality, and soil erosion risk. By comprehensively analyzing these indicators, the current status and carrying capacity of ecosystems can be assessed, guiding expressway planning, design, and construction to ensure that transportation benefits are achieved while maximizing ecological protection.

[0004] The existing technology has the following shortcomings:

[0005] Ecological sensitivity assessments require a large amount of basic data, including information on plants, animals, soils, hydrology, and more. However, ecological data for many regions may be missing or inaccurate. Missing or inaccurate data can lead to underestimation or overestimation of the ecological sensitivity of certain areas. Underestimating ecological sensitivity may lead to neglecting the protection needs of key ecological areas, which in turn leads to damage to the ecosystems in these areas. For example, if there is a lack of accurate data on the habitat of an endangered species, the assessment may conclude that the area is not sensitive, allowing highway construction to destroy its habitat. Conversely, overestimating ecological sensitivity may lead to over-protection, increasing construction costs and difficulty. Summary of the Invention

[0006] The purpose of the present invention is to provide an ecological sensitivity assessment and analysis method and system suitable for highway areas to address the shortcomings of the background technology.

[0007] To achieve the above objectives, the present invention provides the following technical solution: an ecological sensitivity assessment and analysis method suitable for highway areas, comprising the following steps:

[0008] S1: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area;

[0009] Among them, for each delineated ecosystem area, characteristic parameters related to its ecological environment are extracted, including vegetation species complexity and water source distribution area ratio;

[0010] S2: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the weighted average calculation of the weight assignment of each monitoring area is performed to obtain the overall ecological environment quality index;

[0011] The step S2 includes: collecting vegetation type complexity data of n monitoring areas and marking them as ND n , water source distribution area ratio data, marked as HN n , and related environmental factor data, which are marked as E n ;

[0012] Clean and standardize the data and define the nodes in the Bayesian network, including vegetation species complexity, water source distribution area ratio, and environmental factors;

[0013] Determine the structure of the Bayesian network, that is, the causal relationship between nodes, and use the K2 algorithm to construct the network structure. The specific calculation expression is: Among them, G represents the network structure, D represents the observation data of each monitoring area, that is, the current vegetation type complexity and water source distribution area ratio, P(D n ∣Pa(D n ), G) represents node D n The parent node of , q is the total number of monitoring areas; the conditional probability table is learned using maximum likelihood estimation to determine the conditional probability distribution of each node. The calculation expression is: In the formula, COUNT(V n ∣Pa(V n )) indicates V n The joint occurrence count of the node and its parent node;

[0014] Input the observation data of each monitoring area and use the Bayesian inference algorithm to calculate the posterior probability distribution of each node. The specific calculation expression is: Where, P(HN n ∣ND n) is the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area. After determining the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area, the weight assignment of each monitoring area is calculated based on the inference results of the Bayesian network model. The specific calculation expression is: Where W n Assign a weight to each monitoring area, P(HN n ) and P(ND n ) represent the marginal probability of vegetation type complexity and water source distribution area ratio respectively, and the overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area;

[0015] S3: Use satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, perform time series analysis on the ecological factor data to obtain the spatiotemporal changes of the ecological factors.

[0016] S4: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area, an ecological sensitivity assessment is conducted on the monitoring area of ​​the highway.

[0017] S5: Based on the assessment results, the different monitoring areas of the expressway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

[0018] In a preferred embodiment, the method for obtaining vegetation species complexity is:

[0019] Obtain the visible light band and near-infrared band of high-resolution satellite images in the monitoring area and the plant species in each sample, correct the spectral values ​​in the image to reflect the true ground reflectivity. The ground emissivity represents the vegetation coverage ratio in the monitoring area, and calculate the vegetation reflectivity index. The specific calculation expression is: Where ND is the vegetation reflectance index, NIR is the reflectance of the near-infrared band, and RED is the reflectance of the red band. The vegetation reflectance index and plant species data are combined to form a training data set. The random forest algorithm is used for training. The input is image features and the output is plant species classification. According to the trained random forest model, the target area is classified and the spatial distribution map of each plant species is generated. The monitoring area is divided into several sub-monitoring areas. The plant species and abundance in each sub-monitoring area are counted and the vegetation species complexity is calculated. The specific calculation expression is: Where LM is the complexity of vegetation species, p s is the abundance of the sth species, that is, the ratio of the number of individuals of the sth species to the total number of individuals of all species, and m is the total number of individuals of all species.

[0020] In a preferred embodiment, the method for obtaining the water source distribution area ratio is:

[0021] Use GIS software to vectorize the extracted wetland areas, generate wetland and water body boundaries, calculate the total area Aw of wetlands and water bodies, calculate the total area At of the entire target area using GIS software, calculate the total area Sy of the target area at different spatial scales, analyze the calculation results of the initial wetland and water body area Aw and the target area At, and determine the error range of the initial wetland and water body area Aw;

[0022] The calculated results of wetland and water area Aw and target area At are used as initial sample data, and multiple sampling is performed. Data is randomly extracted from the initial sample each time to form a new sample set. Based on the multiple sampling results, the proportion of water source distribution area is calculated. The calculation expression is: Where HN is the proportion of water source distribution area.

[0023] 4. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 1 is characterized by constructing the ecological factor characteristics of multiple time periods into time series data, and organizing the ecological factor characteristics NDVI of each time period into a time series data set, the data set is: NDVI t1 NDVI t2 , ..., NDVI ti , ..., NDVI tg ; Where i = 1, 2, 3, ..., g, g is a positive integer greater than 0. Arrange the NDVI values ​​of each pixel in chronological order to form a time series, and construct the time series data matrix X, where each row represents a spatial location and each column represents a time point;

[0024] Calculate the mean and standard deviation of the NDVI value at each time point, standardize the NDVI value at each time point, obtain the standardized data matrix Z, and calculate the change vector and change amplitude between each time period, including: ΔNDVI t1，t2 =NDVI t2 -NDVI t1 ; Where, ΔNDVI t1，t2is the change vector, M is the change amplitude, and the spatiotemporal change status of the ecological factors is obtained according to the calculated change vector and change amplitude of the ecological factors in the time series. The change vector and change amplitude data of the ecological factors in the time series are normalized, and the spatiotemporal change index of the ecological factors is calculated through the normalized change vector and change amplitude of the ecological factors in the time series. The spatiotemporal change status of the ecological factors is analyzed according to the spatiotemporal change index of the ecological factors.

[0025] In a preferred embodiment, after analyzing the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area based on fuzzy logic, an ecological sensitivity assessment is conducted on the monitoring area of ​​the highway, specifically:

[0026] Collect the overall ecological environment quality index and spatiotemporal variation index of ecological factors in each monitoring area; use the overall ecological environment quality index and spatiotemporal variation index of ecological factors in the monitoring area as input items, and use the sensitivity value of the monitoring area of ​​the highway as output items;

[0027] Fuzzify the input data and convert it into the corresponding fuzzy set. Use the fuzzy rule base to reason on the fuzzy input and get the fuzzy output.

[0028] The fuzzy output is converted into clear numerical values ​​to obtain the ecological sensitivity value of each monitoring area.

[0029] In a preferred embodiment, the obtained ecological sensitivity value is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the ecological sensitivity value is compared with the first standard threshold and the second standard threshold respectively;

[0030] If the ecological sensitivity value is greater than the second standard threshold, the monitoring area of ​​the corresponding highway area will be divided into a high-sensitivity area; if the ecological sensitivity value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the monitoring area of ​​the corresponding highway area will be divided into a medium-sensitivity area; if the ecological sensitivity value is less than the first standard threshold, the monitoring area of ​​the corresponding highway area will be divided into a low-sensitivity area.

[0031] The present invention also provides an ecological sensitivity assessment and analysis system suitable for highway areas, including a data acquisition module, an environmental quality analysis module, an ecological factor spatiotemporal analysis module, an ecological sensitivity assessment module, and a sensitive area division module:

[0032] Data acquisition module: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area;

[0033] Environmental quality analysis module: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area;

[0034] Ecological factor spatiotemporal analysis module: uses satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, time series analysis of ecological factor data is performed to obtain the spatiotemporal changes of ecological factors.

[0035] Ecological sensitivity assessment module: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal changes of ecological factors in the monitoring area, the ecological sensitivity of the monitoring area of ​​the highway is assessed;

[0036] Sensitive area division module: Based on the assessment results, different monitoring areas of the highway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

[0037] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0038] 1. This invention utilizes high-resolution satellite imagery, ground-based data, and environmental factor data to construct a Bayesian network model and fuzzy logic system, achieving a comprehensive, scientific, and dynamic ecological sensitivity assessment of ecosystems along highways. By accurately extracting vegetation species complexity and water source distribution area ratios, combining Bayesian network analysis of the Ecological Environment Quality Index with time-series analysis to capture the spatiotemporal variations of ecological factors, the accuracy and reliability of the assessment results are ensured. Fuzzy logic evaluation further addresses data uncertainty, providing flexible and realistic sensitivity assessment results.

[0039] 2. This invention not only improves the scientific nature and accuracy of ecological sensitivity assessments but also enables precise demarcation and differentiated management of high-, medium-, and low-sensitivity areas through categorized management of assessment results. High-sensitivity areas are strictly protected, medium-sensitivity areas are moderately managed, and low-sensitivity areas are permitted reasonable development, effectively preventing resource waste and environmental damage. Prompt feedback of assessment results to relevant management personnel provides a scientific basis for the formulation and adjustment of ecological protection measures, ensuring the sustainable development of the ecological environment and the ecological safety of highway construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0041] Figure 1 Flow chart of the method of the present invention.

[0042] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0044] Example 1

[0045] See also Figure 1 As shown, the ecological sensitivity assessment and analysis method suitable for highway areas described in this embodiment includes the following steps:

[0046] S1: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area;

[0047] S2: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the weighted average calculation of the weight assignment of each monitoring area is performed to obtain the overall ecological environment quality index;

[0048] S3: Use satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, perform time series analysis on the ecological factor data to obtain the spatiotemporal changes of the ecological factors.

[0049] S4: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area, an ecological sensitivity assessment is conducted on the monitoring area of ​​the highway.

[0050] S5: Based on the assessment results, the different monitoring areas of the expressway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

[0051] In S1, different types of ecosystems along the highway are identified, and the distribution of ecological factors of each ecosystem is analyzed. Based on the distribution of different ecosystems and their ecological factors, the highway area is divided into several monitoring areas, and characteristic parameters related to the ecological environment in each monitoring area are extracted. Specifically,

[0052] Identifying different types of ecosystems along highways includes, but is not limited to, conducting preliminary surveys along the highways to identify the main ecosystem types through literature research, government work reports, existing maps, and satellite imagery. Field visits by teams of ecologists and environmental experts will confirm and supplement the preliminary findings. Ecosystem types within the area will be determined based on internationally recognized ecosystem classification standards (such as the U.S. National Land Cover Classification System (NLCD) and the European CORINE system). Examples include forests, wetlands, grasslands, farmland, and urban green spaces.

[0053] Based on the characteristics of each ecosystem, determine the ecological factors that need to be analyzed, including but not limited to: Plants: plant species, vegetation cover, species diversity, vegetation structure. Animals: animal species, habitats, species diversity, food chain relationships. Soils: soil type, soil texture, soil organic matter content, soil pH, soil erosion risk. Hydrology: water source type (rivers, lakes, wetlands), water quality, water quantity, groundwater level, flood risk. Climate: temperature, precipitation, humidity, wind speed. Human activities: land use type, population density, distribution of transportation infrastructure, degree of human interference.

[0054] Analyze the distribution of ecological factors in each ecosystem, specifically: record the plant species and vegetation coverage in different areas through sample surveys, remote sensing monitoring and plant specimen collection. Obtain information on animal species and habitat distribution through field observations, infrared camera monitoring and capture records. Obtain the physical, chemical and biological properties of the soil through soil sampling and laboratory analysis. Record the distribution and water quality of water sources through water quality sampling, water volume measurement and hydrological monitoring station data. Obtain climate characteristics in the region through meteorological station data and historical meteorological records. Record the impact of human activities through land use maps, demographic data and field surveys. Use GIS technology to spatially process and analyze the collected data to generate ecological factor distribution maps. Analyze the relationship between various ecological factors and their impact on ecosystem health through multivariate statistical analysis. Conduct ecological model simulations to predict future trends in ecological factors under different scenarios (such as climate change and land use change).

[0055] Based on the results of the previous ecosystem identification, the main ecosystem types along the expressway were identified, such as forests, wetlands, grasslands, farmlands, urban green spaces, etc. Utilizing GIS technology, the boundaries of each ecosystem were delineated through the spatial distribution map of ecosystem types, specifically:

[0056] Obtain satellite imagery and aerial photographs to provide high-resolution geographic data. Collect existing ecosystem classification maps, land use maps, and topographic maps. Collect field survey data, including information on flora, fauna, soils, and hydrology.

[0057] Pre-process satellite images, including denoising, radiometric correction, geometric correction, etc. Integrate multi-source data, ensure data format consistency, and import into the GIS platform.

[0058] Use known sample point data for supervised classification, such as maximum likelihood, support vector machine (SVM), and random forest methods, to classify different land cover types. In the absence of sample point data, use unsupervised classification methods, such as K-means clustering, to classify images.

[0059] The classification results were compared with the field survey data to evaluate the classification accuracy. The confusion matrix was used to calculate the overall accuracy, producer accuracy, and user accuracy to ensure the reliability of the classification results.

[0060] Based on the classification results and ecosystem classification standards, different types of ecosystems, such as forests, wetlands, grasslands, and farmland, were identified. GIS software was used for spatial analysis to generate spatial distribution maps of ecosystem types. Spatial filtering and morphological operations (such as dilation, erosion, opening, and closing) were applied to the classification results to remove small patches and isolated pixels and ensure clear boundaries. Using vectorization tools in GIS, the classification results were converted from raster data to vector data to generate ecosystem boundaries. Boundaries were adjusted based on terrain features (such as rivers and mountains) and the impact of human activities (such as roads and cities) to make them more consistent with actual conditions.

[0061] Adjacent small areas with similar ecological characteristics are merged to form larger and continuous ecosystem areas. Based on actual needs, larger ecosystem areas are further subdivided into several monitoring areas, and the ecological characteristics within each monitoring area are as consistent as possible.

[0062] For each designated ecosystem area, characteristic parameters related to its ecological environment are extracted, including vegetation species complexity and water source distribution area ratio.

[0063] Among them, the method for obtaining vegetation type complexity is:

[0064] Obtain the visible light band and near-infrared band of high-resolution satellite images in the monitoring area and the plant species in each sample, correct the spectral values ​​in the image to reflect the true ground reflectivity. The ground emissivity represents the vegetation coverage ratio in the monitoring area, and calculate the vegetation reflectivity index. The specific calculation expression is: Where ND is the vegetation reflectance index, NIR is the reflectance of the near-infrared band, and RED is the reflectance of the red band. The vegetation reflectance index and plant species data are combined to form a training data set. The random forest algorithm is used for training. The input is image features and the output is plant species classification. According to the trained random forest model, the target area is classified and the spatial distribution map of each plant species is generated. The monitoring area is divided into several sub-monitoring areas. The plant species and abundance in each sub-monitoring area are counted and the vegetation species complexity is calculated. The specific calculation expression is: Where LM is the complexity of vegetation species, p s is the relative abundance of the sth species, that is, the ratio of the number of individuals of the sth species to the total number of individuals of all species, and m is the total number of individuals of all species.

[0065] Greater vegetation species complexity generally indicates higher overall ecological and environmental quality. High vegetation species complexity means there are more different plant species in the ecosystem, which increases the redundancy and functional diversity of the ecosystem, making it more sensitive.

[0066] The method for obtaining the proportion of water source distribution area is as follows:

[0067] Use GIS software to vectorize the extracted wetland areas, generate wetland and water body boundaries, calculate the total area Aw of wetlands and water bodies, calculate the total area At of the entire target area using GIS software, calculate the total area Sy of the target area at different spatial scales, analyze the calculation results of the initial wetland and water body area Aw and the target area At, and determine the error range of the initial wetland and water body area Aw;

[0068] The calculated results of wetland and water area Aw and target area At are used as initial sample data, and multiple sampling is performed. Data are randomly extracted from the initial sample each time (duplicates are allowed) to form a new sample set. Based on the multiple sampling results, the proportion of water source distribution area is calculated. The calculation expression is: Where HN is the proportion of water source distribution area.

[0069] A high water source distribution area ratio indicates that there are large areas of wetlands and water bodies within the monitoring area. Large areas of water bodies and wetlands provide rich aquatic ecosystems, which are very sensitive to environmental changes.

[0070] S2: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the weighted average calculation of the weight assignment of each monitoring area is performed to obtain the overall ecological environment quality index;

[0071] Collect vegetation species complexity data of n monitoring areas and mark them as ND n , water source distribution area ratio data, marked as HN n , and related environmental factor data, such as soil health index, precipitation, temperature, etc., which are marked as E n ;

[0072] Clean the data, handle missing values ​​and outliers, and standardize the data to eliminate the impact of different dimensions.

[0073] Define the nodes in the Bayesian network, including vegetation species complexity, water source distribution area ratio, and environmental factors;

[0074] Determine the structure of the Bayesian network, that is, the causal relationship between nodes, and use the K2 algorithm to construct the network structure. The specific calculation expression is: Among them, G represents the network structure, D represents the observation data of each monitoring area, that is, the current vegetation type complexity and water source distribution area ratio, P(D n ∣Pa(D n ), G) represents node D n The parent node of , q is the total number of monitoring areas; the conditional probability table is learned using maximum likelihood estimation to determine the conditional probability distribution of each node. The calculation expression is: In the formula, COUNT(V n ∣Pa(V n )) indicates V n The joint occurrence count of the node and its parent node;

[0075] Input the observation data of each monitoring area and use the Bayesian inference algorithm to calculate the posterior probability distribution of each node. The specific calculation expression is: Where, P(HN n ∣ND n ) is the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area. After determining the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area, the weight assignment of each monitoring area is calculated based on the inference results of the Bayesian network model. The specific calculation expression is: Where W n Assign a weight to each monitoring area, P(HN n ) and P(ND n) represent the marginal probability of vegetation type complexity and water source distribution area ratio respectively. The overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area.

[0076] S3: Use satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, perform time series analysis on the ecological factor data to obtain the spatiotemporal changes of the ecological factors.

[0077] The ecological factor characteristics of multiple time periods are constructed as time series data, and the ecological factor characteristics NDVI of each time period are organized into a time series data set. The data set is: NDVI t1 NDVI t2 , ..., NDVI ti , ..., NDVI tg ; Where i = 1, 2, 3, ..., g, g is a positive integer greater than 0. Arrange the NDVI values ​​of each pixel in chronological order to form a time series, and construct the time series data matrix X, where each row represents a spatial location (pixel) and each column represents a time point; Among them, m is the total number of pixels, NDVI ti (j) represents the NDVI value of the j-th pixel in the i-th time period. The time series data is standardized to eliminate the dimension difference.

[0078] Calculate the mean and standard deviation of the NDVI value at each time point, standardize the NDVI value at each time point, obtain the standardized data matrix Z, and calculate the change vector and change amplitude between each time period, including: ΔNDVI t1，t2 =NDVI t2 -NDVI t1 ; Where, ΔNDVI t1，t2 is the change vector, M is the change amplitude, and the spatiotemporal change status of the ecological factors is obtained according to the calculated change vector and change amplitude of the ecological factors in the time series. The change vector and change amplitude data of the ecological factors in the time series are normalized, and the spatiotemporal change index of the ecological factors is calculated through the normalized change vector and change amplitude of the ecological factors in the time series. The spatiotemporal change status of the ecological factors is analyzed according to the spatiotemporal change index of the ecological factors.

[0079] S4: After analyzing the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area based on fuzzy logic, an ecological sensitivity assessment is conducted on the monitoring area of ​​the highway.

[0080] Based on fuzzy logic, the overall ecological environment quality index and spatiotemporal variation index of ecological factors in the monitoring area are used as input items, and the sensitivity value of the monitoring area of ​​the highway area is used as the output item. The ecological sensitivity of the monitoring area of ​​the highway area is judged as follows:

[0081] Collect the overall ecological environment quality index and spatiotemporal variation index of ecological factors in each monitoring area;

[0082] Using the overall ecological environment quality index and the spatiotemporal variation index of ecological factors in the monitoring area as input, a fuzzy set of the overall ecological environment quality index, such as low, medium, and high, is defined. A fuzzy set of spatiotemporal variation indexes of ecological factors, such as low, medium, and high, is also defined. Using the sensitivity values ​​of the monitoring areas within the highway area as output, a fuzzy set of ecological sensitivity values, such as low, medium, and high, is defined.

[0083] Determine the membership function for the input variables and output variables. Commonly used membership functions include triangular membership function and trapezoidal membership function.

[0084] Based on historical data, fuzzy rules are formulated. For example, if the overall ecological environment quality index is high and the spatiotemporal variation index of ecological factors is low, then the sensitivity value of the monitoring area is low. If the overall ecological environment quality index is medium and the spatiotemporal variation index of ecological factors is medium, then the sensitivity value of the monitoring area is medium. If the overall ecological environment quality index is low and the spatiotemporal variation index of ecological factors is high, then the sensitivity value of the monitoring area is high.

[0085] Fuzzify the input data and convert it into the corresponding fuzzy set. Use the fuzzy rule base to reason on the fuzzy input and get the fuzzy output.

[0086] The fuzzy output is converted into clear numerical values ​​to obtain the ecological sensitivity value of each monitoring area.

[0087] S5: Based on the assessment results, the different monitoring areas of the expressway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

[0088] Compare the obtained ecological sensitivity value with the sensitivity gradient standard threshold of the highway road monitoring area pre-set in this application. The gradient standard threshold in this application includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold. Compare the ecological sensitivity value with the first standard threshold and the second standard threshold respectively;

[0089] If the ecological sensitivity value is greater than the second standard threshold, the corresponding monitoring area of ​​the expressway will be divided into a high-sensitivity area; strict protection measures will be implemented, environmental monitoring will be strengthened, and environmental problems will be discovered and dealt with in a timely manner.

[0090] If the ecological sensitivity value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the corresponding highway monitoring area will be classified as a moderately sensitive zone. Appropriate management measures will be implemented, emphasizing both rational development and protection. Regularly monitor ecological conditions and adjust management strategies accordingly.

[0091] If the ecological sensitivity value is less than the first standard threshold, the corresponding highway monitoring area will be classified as a low-sensitivity zone; moderate development and utilization can be carried out, but it must ensure that it does not damage the ecological environment. A basic environmental monitoring mechanism needs to be established to prevent the emergence of potential environmental problems.

[0092] Fuzzy logic is used to determine the ecological sensitivity of monitored areas within highways, and zones are divided into high-, medium-, and low-sensitivity areas based on preset thresholds. Based on the characteristics of each sensitive area, appropriate protection, management, and development measures are formulated, and the results are fed back to relevant managers for scientific decision-making and management.

[0093] In this embodiment, the comprehensive assessment and management of the ecological environment along highways involves identifying and analyzing the distribution of ecological factors in different ecosystems, dividing monitoring areas, and extracting characteristic parameters. A Bayesian network model is constructed to determine and calculate the weights of each monitoring area, generating an overall ecological environment quality index. Time series analysis is performed using satellite imagery to determine the spatiotemporal variations of ecological factors. Fuzzy logic is used to analyze overall environmental quality and spatiotemporal variations to assess ecological sensitivity. A sensitive area demarcation module, based on the assessment results, divides areas into high, medium, and low sensitivity zones, and provides feedback to management personnel. This systematic and scientific assessment approach improves the accuracy and efficiency of highway ecological environment management, ensuring the timely protection and rational development of sensitive areas.

[0094] Example 2

[0095] See also Figure 2 As shown, the ecological sensitivity assessment and analysis system suitable for highway areas described in this embodiment includes a data acquisition module, an environmental quality analysis module, an ecological factor spatiotemporal analysis module, an ecological sensitivity assessment module, and a sensitive area division module:

[0096] Data acquisition module: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area;

[0097] Environmental quality analysis module: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area;

[0098] Ecological factor spatiotemporal analysis module: uses satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, time series analysis of ecological factor data is performed to obtain the spatiotemporal changes of ecological factors.

[0099] Ecological sensitivity assessment module: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal changes of ecological factors in the monitoring area, the ecological sensitivity of the monitoring area of ​​the highway is assessed;

[0100] Sensitive area division module: Based on the assessment results, different monitoring areas of the highway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

[0101] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0102] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0103] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0104] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0105] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0106] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for ecological sensitivity assessment and analysis suitable for highway areas, characterized by: The following steps are included: S1: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area; Among them, for each delineated ecosystem area, characteristic parameters related to its ecological environment are extracted, including vegetation species complexity and water source distribution area ratio; S2: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the weighted average calculation of the weight assignment of each monitoring area is performed to obtain the overall ecological environment quality index; The step S2 includes: collecting vegetation type complexity data of n monitoring areas and marking them as ND n , water source distribution area ratio data, marked as HN n , and related environmental factor data, which are marked as E n ; Clean and standardize the data and define the nodes in the Bayesian network, including vegetation species complexity, water source distribution area ratio, and environmental factors; Determine the structure of the Bayesian network, that is, the causal relationship between nodes, and use the K2 algorithm to construct the network structure. The specific calculation expression is: Among them, G represents the network structure, D represents the observation data of each monitoring area, that is, the current vegetation type complexity and water source distribution area ratio, P(D n ∣Pa(D n ), G) represents node D n The parent node of , q is the total number of monitoring areas; the conditional probability table is learned using maximum likelihood estimation to determine the conditional probability distribution of each node. The calculation expression is: In the formula, COUNT(V n ∣Pa(V n )) indicates V n The joint occurrence count of the node and its parent node; Input the observation data of each monitoring area and use the Bayesian inference algorithm to calculate the posterior probability distribution of each node. The specific calculation expression is: Where, P(HN n ∣ND n ) is the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area. After determining the posterior probability distribution of vegetation species complexity and water source distribution area ratio in each monitoring area, the weight assignment of each monitoring area is calculated based on the inference results of the Bayesian network model. The specific calculation expression is: Where W n Assign a weight to each monitoring area, P(HN n ) and P(ND n ) represent the marginal probability of vegetation type complexity and water source distribution area ratio respectively, and the overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area; S3: Use satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, perform time series analysis on the ecological factor data to obtain the spatiotemporal changes of the ecological factors. S4: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area, an ecological sensitivity assessment is conducted on the monitoring area of ​​the highway. S5: Based on the assessment results, the different monitoring areas of the expressway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

2. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 1 is characterized by: The method for obtaining vegetation species complexity is: Obtain the visible light band and near-infrared band of high-resolution satellite images in the monitoring area and the plant species in each sample, correct the spectral values ​​in the image to reflect the true ground reflectivity. The ground emissivity represents the vegetation coverage ratio in the monitoring area, and calculate the vegetation reflectivity index. The specific calculation expression is: Where ND is the vegetation reflectance index, NIR is the reflectance of the near-infrared band, and RED is the reflectance of the red band. The vegetation reflectance index and plant species data are combined to form a training data set. The random forest algorithm is used for training. The input is image features and the output is plant species classification. According to the trained random forest model, the target area is classified and the spatial distribution map of each plant species is generated. The monitoring area is divided into several sub-monitoring areas. The plant species and abundance in each sub-monitoring area are counted and the vegetation species complexity is calculated. The specific calculation expression is: Where LM is the complexity of vegetation species, p s is the abundance of the sth species, that is, the ratio of the number of individuals of the sth species to the total number of individuals of all species, and m is the total number of individuals of all species.

3. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 2 is characterized by: The method for obtaining the proportion of water source distribution area is as follows: Use GIS software to vectorize the extracted wetland areas, generate wetland and water body boundaries, calculate the total area Aw of wetlands and water bodies, calculate the total area At of the entire target area using GIS software, calculate the total area Sy of the target area at different spatial scales, analyze the calculation results of the initial wetland and water body area Aw and the target area At, and determine the error range of the initial wetland and water body area Aw; The calculated results of wetland and water area Aw and target area At are used as initial sample data, and multiple sampling is performed. Data are randomly extracted from the initial sample each time to form a new sample set. Based on the multiple sampling results, the proportion of water source distribution area is calculated.

4. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 1 is characterized by: The ecological factor characteristics of multiple time periods are constructed as time series data, and the ecological factor characteristics NDVI of each time period are organized into a time series data set. The data set is: NDVI t1 NDVI t2 , ..., NDVI ti , ..., NDVI tg ; Where i = 1, 2, 3, ..., g, g is a positive integer greater than 0. Arrange the NDVI values ​​of each pixel in chronological order to form a time series, and construct the time series data matrix X, where each row represents a spatial location and each column represents a time point; Calculate the mean and standard deviation of the NDVI value at each time point, standardize the NDVI value at each time point, obtain the standardized data matrix Z, and calculate the change vector and change amplitude between each time period, including: ΔNDVI t1，t2 =NDVI t2 -NDVI t1 ; Where, ΔNDVI t1，t2 is the change vector, M is the change amplitude, and the spatiotemporal change status of the ecological factors is obtained according to the calculated change vector and change amplitude of the ecological factors in the time series. The change vector and change amplitude data of the ecological factors in the time series are normalized, and the spatiotemporal change index of the ecological factors is calculated through the normalized change vector and change amplitude of the ecological factors in the time series. The spatiotemporal change status of the ecological factors is analyzed according to the spatiotemporal change index of the ecological factors.

5. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 4 is characterized by: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal variation of ecological factors in the monitoring area, an ecological sensitivity assessment was conducted on the monitoring area of ​​the expressway. Specifically: Collect the overall ecological environment quality index and spatiotemporal variation index of ecological factors in each monitoring area; use the overall ecological environment quality index and spatiotemporal variation index of ecological factors in the monitoring area as input items, and use the sensitivity value of the monitoring area of ​​the highway as output items; Fuzzify the input data and convert it into the corresponding fuzzy set. Use the fuzzy rule base to reason on the fuzzy input and get the fuzzy output. The fuzzy output is converted into clear numerical values ​​to obtain the ecological sensitivity value of each monitoring area.

6. The ecological sensitivity assessment and analysis method suitable for highway areas according to claim 5 is characterized by: Comparing the obtained ecological sensitivity value with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the ecological sensitivity value with the first standard threshold and the second standard threshold respectively; If the ecological sensitivity value is greater than the second standard threshold, the corresponding monitoring area of ​​the highway will be divided into a high-sensitivity area; If the ecological sensitivity value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the corresponding monitoring area of ​​the highway is divided into a medium-sensitive area; If the ecological sensitivity value is less than the first standard threshold, the corresponding monitoring area of ​​the highway will be divided into a low-sensitivity area.

7. An ecological sensitivity assessment and analysis system suitable for highway areas, used to implement the ecological sensitivity assessment and analysis method suitable for highway areas according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, environmental quality analysis module, ecological factor spatiotemporal analysis module, ecological sensitivity assessment module and sensitive area division module: Data acquisition module: Identify different types of ecosystems along the highway, analyze the distribution of ecological factors of each ecosystem, divide the highway area into several monitoring areas based on the distribution of different ecosystems and their ecological factors, and extract characteristic parameters related to the ecological environment in each monitoring area; Environmental quality analysis module: By constructing a Bayesian network model and using Bayesian probability theory to analyze the changes in characteristic parameters related to the ecological environment in each monitoring area, the weight assignment of each monitoring area is determined, and the overall ecological environment quality index is obtained by weighted average calculation of the weight assignment of each monitoring area; Ecological factor spatiotemporal analysis module: uses satellite images to obtain ecological factor data over multiple time periods. By regularly acquiring images, time series analysis of ecological factor data is performed to obtain the spatiotemporal changes of ecological factors. Ecological sensitivity assessment module: Based on fuzzy logic analysis of the overall ecological environment quality index and spatiotemporal changes of ecological factors in the monitoring area, the ecological sensitivity of the monitoring area of ​​the highway is assessed; Sensitive area division module: Based on the assessment results, different monitoring areas of the highway are divided into high-sensitivity areas, medium-sensitivity areas and low-sensitivity areas, and the division results are fed back to relevant management personnel.

Images