A marine ecological assessment system and method based on big data analysis

Abstract

The present application provides a marine ecological assessment system and method based on big data analysis. The system obtains marine biodiversity data and image data of the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators. The system uses an edge computing architecture to stream the image data to obtain a biological activity characteristic map. The system divides the marine monitoring area into grids according to the spatial resolution of the biological activity characteristic map and the historical species distribution data, generates a baseline species distribution density value for each grid cell, and calculates the species distribution density value for each grid cell. The system calculates the negative deviation between the species distribution density value of each grid cell and the corresponding baseline species distribution density value. When the negative deviation is greater than a preset extinction threshold, the corresponding grid cell is determined as a species distribution density attenuation area. The technical solution provided by the present application realizes dynamic assessment and early warning of the health status of the marine ecosystem.

Description

Technical Field

[0001] The present application relates to the technical field of big data analysis, and in particular to a marine ecological assessment system and method based on big data analysis. Background Art

[0002] As human activities and climate change increasingly impact marine ecosystems, there is an urgent need for large-scale, high-frequency, and precise ecological monitoring and assessment methods. In particular, in key ecosystems such as coral reefs and seagrass beds, how to quickly identify changes in species distribution, assess trends in ecological degradation, and provide a dynamic basis for scientific restoration has become a core technical requirement for current ecological conservation efforts.

[0003] To meet the above technical requirements, existing solutions use a combination of multispectral optical remote sensing technology and cloud computing platforms to remotely sense and centrally analyze the ecological characteristics of the ocean surface. Existing solutions use satellites or drones to obtain multispectral images of ocean areas, and combined with historical biodiversity databases, they construct regional ecological health indices in the cloud. Ecological assessment reports are regularly generated to assist management departments in making macro-decision-making. However, existing solutions have some flaws. For example, remote sensing images cannot accurately capture the distribution changes of small or hidden species, and the process of uploading data to the cloud for processing causes delayed assessment results, making it impossible to detect sudden ecological anomalies in a timely manner. Centralized computing architectures are prone to data backlogs and processing bottlenecks when faced with high-frequency monitoring tasks, affecting the timeliness and sophistication of ecological assessments. Summary of the Invention

[0004] This application provides a marine ecological assessment system and method based on big data analysis to solve the problems in existing technologies such as the inability to timely detect sudden ecological anomalies; the proneness to data backlogs and processing bottlenecks; and the lack of timeliness and refinement in ecological assessments.

[0005] First, this application provides a marine ecological assessment method based on big data analysis, including:

[0006] Obtaining marine biodiversity data and image data for the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators;

[0007] Utilizing an edge computing architecture deployed in the ocean monitoring area, the image data is stream-processed to obtain a biological activity feature map;

[0008] Gridding the marine monitoring area based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, generating a baseline species distribution density value for each grid cell, and calculating the species distribution density value for each grid cell;

[0009] Calculate the negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value. When the negative deviation is greater than a preset extinction threshold, the corresponding grid cell is determined as a species distribution density attenuation area.

[0010] Generate marine ecological integrity assessment results based on all species distribution density attenuation areas.

[0011] Optionally, the image data is stream-processed using an edge computing architecture deployed in the ocean monitoring area to obtain a biological activity feature map, including:

[0012] Using the edge computing architecture, the multispectral bands in the image data are separated to obtain reflection intensity data of each spectral channel;

[0013] Enhance the characteristic bands related to biological activities in the reflectance intensity data of all spectral channels to generate enhanced spectral data of each spectral channel;

[0014] The preset biological weight coefficient set and the enhanced spectral data of different spectral channels are weightedly superimposed to generate a preliminary biological activity intensity distribution map;

[0015] Correcting the discontinuous areas in the preliminary biological activity intensity distribution map to generate a corrected biological activity intensity distribution map;

[0016] According to the correlation between the historical species distribution data and the spectral characteristics, the corrected biological activity intensity distribution map is converted into a biological activity characteristic map.

[0017] Optionally, a preset biological weight coefficient set and enhanced spectral data of different spectral channels are weightedly superimposed to generate a preliminary biological activity intensity distribution map, including:

[0018] Determining the ecosystem type to which the marine monitoring area belongs based on the geographic coordinate data of the marine monitoring area, wherein the ecosystem type includes a coral reef ecosystem and a seagrass bed ecosystem;

[0019] Calling a preset biological weight coefficient set corresponding to the ecosystem type, multiplying the enhanced spectral data of each pixel point in the enhanced spectral data of different spectral channels by the biological weight coefficient of the corresponding spectral channel in the preset biological weight coefficient set, to obtain a weighted spectral value of the different spectral channels of each pixel point;

[0020] All weighted spectral values ​​of the same pixel are superimposed to obtain the biological activity intensity value of each pixel;

[0021] The biological activity intensity values ​​of all pixel points are converted into distribution map pixel values ​​to generate a preliminary biological activity intensity distribution map according to the distribution map pixel values.

[0022] Optionally, converting the corrected biological activity intensity distribution map into a biological activity characteristic map according to the correlation between the historical species distribution data and the spectral characteristics includes:

[0023] Grouping the historical species distribution data based on the correlation between the species density of the historical species distribution data and the spectral characteristics, and the ecosystem type, to obtain a grouping result;

[0024] Based on the grouping results, constructing a species density spectral response lookup table, wherein the species density spectral response lookup table includes conversion rules corresponding to different ecosystem types;

[0025] Based on the conversion rule, the biological activity intensity value of each pixel point is converted into a species density characteristic value, so as to generate a biological activity intensity distribution map according to all species density characteristic values.

[0026] Optionally, the marine monitoring area is gridded based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, and a baseline species distribution density value for each grid cell is generated. The species distribution density value for each grid cell is also calculated, including:

[0027] According to the spatial resolution of the biological activity characteristic map, the ocean monitoring area is divided into a plurality of grid cells using a preset grid division rule;

[0028] Extracting historical observation points located within the grid cells from the historical species distribution data, parsing data records of the historical observation points, and obtaining a set of species density measurement values ​​corresponding to each grid cell;

[0029] Sort the species density measurements in each species density measurement set to select the target species density measurement at the median, and use the target species density measurement corresponding to each grid cell as the corresponding benchmark species distribution density value;

[0030] The grid units and the biological activity characteristic map are aligned in coordinate system to extract the biological activity characteristic value set corresponding to each grid unit, and the characteristic mean in each biological activity characteristic value set is used as the species distribution density value of the corresponding grid unit.

[0031] Optionally, generate marine ecological integrity assessment results based on all species distribution density decline areas, including:

[0032] Calculate the ratio of the area of ​​the region where the distribution density of all species is attenuated to the marine monitoring area, and use the ratio as the attenuation area ratio value;

[0033] Extract the corresponding negative deviation values ​​from the attenuation areas of all species distribution density, calculate the average value of all negative deviation values, and generate the overall attenuation intensity value;

[0034] Comparing the attenuation area ratio value with a preset health level threshold table to obtain a health level determination result;

[0035] Based on a preset risk index calculation rule, converting the overall attenuation intensity value into a risk index;

[0036] The health grade determination result and the risk index are combined into a marine ecological integrity assessment result.

[0037] Optionally, based on a preset risk index calculation rule, converting the overall attenuation intensity value into a risk index includes:

[0038] Determining a target conversion value interval corresponding to the overall attenuation intensity value according to a preset attenuation intensity risk index mapping table;

[0039] According to the ecosystem type, calling the reference proportional coefficient corresponding to the target conversion value interval in the preset risk index calculation rule, scaling the overall attenuation intensity value to obtain a scaled attenuation intensity value;

[0040] Based on marine biodiversity data, target compensation parameters are selected from the environmental dynamic compensation parameters of the preset risk index calculation rules;

[0041] The scaled attenuation intensity value and the target compensation parameter are superimposed to generate a risk index.

[0042] Secondly, this application provides a marine ecological assessment system based on big data analysis, including:

[0043] An acquisition module, configured to acquire marine biodiversity data and image data of the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators;

[0044] a processing module, configured to perform streaming processing on the image data using an edge computing architecture deployed in the ocean monitoring area to obtain a biological activity feature map;

[0045] a partitioning module, configured to perform grid division on the marine monitoring area based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, generate a baseline species distribution density value for each grid cell, and simultaneously calculate the species distribution density value for each grid cell;

[0046] a determination module, configured to calculate the negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value, and when the negative deviation is greater than a preset extinction threshold, determine the corresponding grid cell as a species distribution density attenuation area;

[0047] The evaluation module is used to generate marine ecological integrity evaluation results based on all species distribution density attenuation areas.

[0048] In a third aspect, an embodiment of the present application provides a computing device comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a marine ecological assessment method based on big data analysis as described in the first aspect above.

[0049] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements a marine ecological assessment method based on big data analysis as described in the first aspect.

[0050] In this application, marine biodiversity data and image data of the marine monitoring area are obtained, and the marine biodiversity data include historical species distribution data and ecological niche indicators; the image data are stream-processed using the edge computing architecture deployed in the marine monitoring area to obtain a biological activity characteristic map; the marine monitoring area is gridded according to the spatial resolution of the biological activity characteristic map and the historical species distribution data, and a baseline species distribution density value for each grid cell is generated, and the species distribution density value for each grid cell is calculated at the same time; the negative deviation between the species distribution density value of each grid cell and the corresponding baseline species distribution density value is calculated, and when the negative deviation is greater than the preset extinction threshold, the corresponding grid cell is determined as a species distribution density attenuation area; based on all species distribution density attenuation areas, a marine ecological integrity assessment result is generated. The technical solution provided in this application obtains marine biodiversity data and image data in the marine monitoring area; uses the edge computing architecture deployed near the monitoring area to stream the image data, thereby improving the real-time and efficiency of data processing and reducing the delay problem caused by traditional centralized processing; the monitoring area is gridded according to the spatial resolution of the biological activity characteristic map and the historical species distribution data, realizing refined modeling and dynamic comparison at the spatial scale; by comparing the negative deviation between the current density value and the baseline value and identifying the declining grid cells, the marine ecological integrity assessment results of all attenuation areas are obtained. Among them, by performing band separation and enhancement processing on multispectral image data, key spectral information related to biological activities is extracted, and weighted superposition is performed in combination with preset biological weight coefficients to form a preliminary biological activity intensity distribution map; then the non-continuous areas in the image are corrected to generate a biological activity feature map with ecological semantics, which improves the extraction accuracy and ecological interpretation ability of biological activity information in remote sensing images, and solves the problem that traditional remote sensing methods are difficult to identify small or hidden species due to insufficient spatial resolution; by completing key image processing tasks at the edge, the processing delay caused by uploading the original image to the cloud is avoided, and the system's response speed to sudden ecological anomalies and the ability to recognize local details are improved, thus breaking through the technical barriers of existing centralized remote sensing monitoring in timeliness and precision.

[0051] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0053] Figure 1 A flow chart of a marine ecological assessment method based on big data analysis provided by this application is shown;

[0054] Figure 2 The following is a schematic diagram of the structure of a marine ecological assessment system based on big data analysis provided by this application;

[0055] Figure 3 A schematic structural diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0057] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0059] Existing technical solutions based on multispectral remote sensing and cloud computing have limitations in response speed, spatial resolution, and processing efficiency, making it difficult to meet the needs of high-frequency and refined monitoring of dynamic changes in species distribution. To address these issues, this application proposes a marine ecological assessment method based on big data analysis. By integrating edge computing and biodiversity data analysis technology, it achieves near-real-time processing of the entire process from data collection to ecological assessment, improving the timeliness and accuracy of ecological anomaly identification and making up for the shortcomings of traditional centralized processing models in dealing with complex and changing marine environments.

[0060] Figure 1A flow chart of a marine ecological assessment method based on big data analysis is provided for the embodiment of this application, such as Figure 1 As shown, the method includes:

[0061] Step 101: Acquire marine biodiversity data and image data of a marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators.

[0062] In this step, marine biodiversity data refers to a data set that reflects the species composition and distribution characteristics of marine ecosystems, including historical species distribution data (such as coral cover and fish abundance) and niche indicators (such as species competition index and habitat fitness score). Image data refers to multispectral ocean surface images obtained by optical remote sensing equipment, which are used to capture plankton chlorophyll concentration, coral symbiotic algae characteristics and seagrass canopy characteristics. Historical species distribution data refers to records of species spatial distribution verified by authoritative institutions, including coordinate location, survey time, and species density values ​​(such as percentage of coral cover and seagrass biomass g / m²). Niche indicators refer to data parameters that quantify the functional status of species in the ecosystem, including trophic level index, niche breadth, and competitive exclusion coefficient, which are calculated through species interactions recorded in historical surveys.

[0063] In an embodiment of the present application, multispectral optical image data and a historical ecological survey database of the ocean monitoring area are synchronously collected through a satellite remote sensing receiving station and an ocean monitoring buoy network. Marine biodiversity data is obtained by calling the National Marine Species Database, which includes historical species distribution data and ecological niche indicators. Image data is provided by high-resolution satellites and drone aerial photography systems, covering visible light to near-infrared bands.

[0064] Step 102: Utilize the edge computing architecture deployed in the ocean monitoring area to perform streaming processing on the image data to obtain a biological activity feature map.

[0065] In this step, the edge computing architecture refers to a distributed computing system deployed in the ocean monitoring area. It consists of salt-resistant processing nodes and provides four functional modules: spectral decomposition, feature enhancement, data fusion, and spatial optimization. The biological activity feature map is a spatial distribution map that represents the intensity of marine biological activity per unit area. It is generated by converting image data into a matrix of single-channel intensity values.

[0066] In this embodiment, a spectral decomposition module deployed within the edge computing architecture of the ocean monitoring area decomposes image data into independent channels. Marine biosignature enhancement technology is then used to enhance the reflectance intensity of certain bands in coral reefs and seagrass beds. The enhanced multi-channel data is processed by a weighted fusion module, and then a spatial optimization module is used to eliminate wave interference and light gradients, ultimately generating a bioactivity signature map.

[0067] Step 103: Based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, the marine monitoring area is gridded to generate a baseline species distribution density value for each grid cell, and the species distribution density value for each grid cell is calculated.

[0068] In this step, spatial resolution refers to the actual sea surface size corresponding to a single pixel in the biological activity signature map and is used to constrain the grid granularity. The baseline species distribution density value is the statistical aggregation of historical species density measurements within a grid cell. For coral reefs, the median live coral cover is used, while for seagrass beds, the depth-weighted average of leaf biomass is used. The species distribution density value refers to the species density of a grid cell calculated in real time from the biological activity signature map. It is generated by taking the arithmetic mean of the characteristic values ​​of all pixels within the cell. For coral reefs, the value is associated with the reflectance intensity of symbiotic algae, while for seagrass beds, the value is associated with the near-infrared reflectance of the canopy.

[0069] In this embodiment, gridding is performed based on the spatial resolution of the biological activity signature map and historical species distribution data. The grid size is set according to the signature map resolution, and density measurements of the historical species distribution data within each grid cell are extracted. Simultaneously, the arithmetic mean of all pixel feature values ​​for each grid cell is extracted from the biological activity signature map to generate a baseline species distribution density value and a species distribution density value for each grid cell.

[0070] Step 104: Calculate the negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value. When the negative deviation is greater than a preset extinction threshold, determine the corresponding grid cell as a species distribution density attenuation area.

[0071] In this step, negative deviation refers to the relative deviation of the current species distribution density value below the baseline value. The preset extinction threshold is a matrix of critical values ​​used to determine species decline, including coral reef dynamic thresholds and seagrass bed stratification thresholds. The species distribution density decline area refers to the set of grid cells where the negative deviation exceeds the threshold. It contains metadata such as coordinate range, decline intensity, and species type, and is used to generate coral bleaching heat maps or seagrass degradation distribution maps.

[0072] In this embodiment, for each grid cell, the species distribution density value is subtracted from the baseline species distribution density value to calculate the density difference. When the density difference is greater than 0, the ratio of the density difference to the baseline species distribution density value is calculated and this ratio is used as the negative deviation. The negative deviation is compared with a preset extinction threshold. If it exceeds the threshold, the grid cell is marked as a species distribution density attenuation area.

[0073] Step 105: Generate marine ecological integrity assessment results based on all species distribution density attenuation areas.

[0074] In this step, the results of the marine ecological integrity assessment refer to a structured report containing health levels and risk indices, encapsulating parameters such as the proportion of attenuation area, the attenuation rate of core species, and the weight of environmental factors.

[0075] In this example, the ratio of the total area of ​​species density attenuation to the area of ​​the marine monitoring zone is calculated to determine the attenuation area ratio. The negative deviations of all species density attenuation zones are then averaged to form the overall attenuation intensity value. The area ratio values ​​are mapped to health levels using a health level threshold table, and the attenuation intensity values ​​are converted to risk indices using a risk index calculation rule. Finally, the health level and risk index are combined to produce the marine ecological integrity assessment results.

[0076] The embodiments of the present application solve the problem that traditional methods cannot take into account both large-scale monitoring and species-level accuracy, and provide near-real-time ecological risk warnings for marine protected areas.

[0077] This application provides a specific embodiment, step 102, using the edge computing architecture deployed in the ocean monitoring area to stream process the image data to obtain a biological activity feature map, specifically including the following steps:

[0078] Step 201: Utilize the edge computing architecture to separate the multispectral bands in the image data to obtain reflection intensity data of each spectral channel.

[0079] In this step, multispectral bands refer to the spectral intervals in the image data divided by wavelength. The reflectance intensity data of each spectral channel refers to the light reflectance energy dataset of a single band after separation, which is used to quantify the spectral response characteristics of different ground objects.

[0080] In this embodiment of the present application, when using an edge computing architecture to separate multispectral bands in image data, the spectral processing module of the edge node parses the satellite image file and decomposes the composite spectral data into independent spectral channels to generate a matrix of reflectance intensity data for each spectral channel. Each matrix element stores the reflectance intensity data for each spectral channel.

[0081] Step 202: Enhance the characteristic wavebands related to biological activities in the reflection intensity data of all spectral channels to generate enhanced spectral data of each spectral channel.

[0082] In this step, the characteristic bands associated with biological activity refer to the sensitive spectral ranges that characterize biological activity in a specific ecosystem. The enhanced spectral data of each spectral channel refers to the spectral data matrix after radiation enhancement processing, which is achieved through dynamic range expansion and gain amplification.

[0083] In this example, ecosystem types are first identified, with infrared bands selected for coral reefs and seagrass beds, respectively. Gain amplification technology is then used to linearly increase the reflectance intensity data across all spectral channels, while simultaneously compressing the dynamic range of non-characteristic bands. This enhanced data is then used to generate enhanced spectral data for each spectral channel.

[0084] Step 203: Perform weighted superposition on the preset biological weight coefficient set and the enhanced spectral data of different spectral channels to generate a preliminary biological activity intensity distribution map.

[0085] In this step, the preset biological weight coefficient set refers to the set of spectral fusion parameters preconfigured according to the ecosystem and stored in the local database of the edge node. The preliminary biological activity intensity distribution map refers to the single-channel intensity spatial distribution map generated by weighted superposition.

[0086] In this embodiment, a preset biological weighting coefficient set is used: a red-dominant coefficient set is applied to coral reef areas, and a near-infrared-dominant coefficient set is applied to seagrass beds. This is combined with the enhanced spectral data from different spectral channels to perform a channel-weighted calculation. The formula is to multiply each channel's enhanced spectral data value by the corresponding weighting coefficient, then sum all the channel weightings to generate a biological activity intensity value for that location. Finally, the intensity values ​​for all locations are integrated to produce a preliminary biological activity intensity distribution map.

[0087] Step 204: Correct the discontinuous areas in the preliminary biological activity intensity distribution map to generate a corrected biological activity intensity distribution map.

[0088] In this step, the corrected biological activity intensity distribution map refers to the optimized distribution map after eliminating environmental interference, which is achieved by eliminating wave mutations and radial gradient compensation through median filtering.

[0089] In an embodiment of the present application, the adjacent pixel mutations caused by the fluctuation of waves in the preliminary biological activity intensity distribution map are first detected, and the median filtering of the pixel window is used for smoothing; secondly, a radial brightness compensation model is established for the radiation gradient caused by the change of the solar altitude angle to correct the discontinuous area and generate a corrected biological activity intensity distribution map.

[0090] Step 205: Convert the corrected biological activity intensity distribution map into a biological activity characteristic map based on the correlation between the historical species distribution data and the spectral characteristics.

[0091] In this step, spectral characteristics refer to the correspondence between reflectance and biomass recorded in historical species distribution data, including linear models of red light reflectance and coverage of coral reefs and logarithmic models of near-infrared reflectance and biomass of seagrass beds, which are used to convert intensity values ​​into biological parameters.

[0092] In this example, historical species distribution data and spectral characteristics were used to construct conversion tables for red light intensity and coral cover, and near-infrared light intensity and seagrass biomass. Coordinate matching was performed by substituting the intensity values ​​at each location in the distribution map into the corresponding linear equations in the conversion tables. Finally, the corrected biological activity intensity distribution map was converted into a biological activity signature map.

[0093] The embodiments of the present application realize real-time layered processing of multispectral data through edge computing, breaking through the two major bottlenecks of traditional remote sensing monitoring.

[0094] This application provides a specific embodiment, step 203, which performs weighted superposition of a preset biological weight coefficient set and enhanced spectral data of different spectral channels to generate a preliminary biological activity intensity distribution map, specifically comprising the following steps:

[0095] Step 211: Based on the geographic coordinate data of the ocean monitoring area, determine the ecosystem type to which the ocean monitoring area belongs, where the ecosystem type includes a coral reef ecosystem and a seagrass bed ecosystem.

[0096] In this step, ecosystem type refers to the ecological classification of the marine monitoring area, including coral reef ecosystems and seagrass bed ecosystems. Coral reef ecosystems are ecosystems based on the Scleractinia order, characterized by a three-dimensional reef structure and containing reef-building species such as Acropora and Porites. Seagrass bed ecosystems are ecosystems dominated by plants of the Hydrocharitaceae family, forming banded or patchy meadows.

[0097] In this embodiment, when determining ecosystem types based on geographic coordinate data for a marine monitoring area, the coordinates are matched against a map of coral reef ecosystems and a map of seagrass bed ecosystems by querying a pre-set geographic information database. If the coordinates fall within the spatial boundary of a coral reef, the ecosystem is labeled as a coral reef ecosystem; if they fall within the seagrass bed isobath, the ecosystem is labeled as a seagrass bed ecosystem.

[0098] Step 212: Call the preset biological weight coefficient set corresponding to the ecosystem type, multiply the enhanced spectral data of each pixel point in the enhanced spectral data of different spectral channels by the biological weight coefficient of the corresponding spectral channel in the preset biological weight coefficient set, and obtain the weighted spectral value of the different spectral channels of each pixel point.

[0099] In this step, the enhanced spectral data for each pixel refers to the four-dimensional vector after radiation enhancement processing, and the data format is 32-bit floating point. The biological weight coefficient refers to the weight parameter of spectral fusion. The weighted spectral values ​​of the different spectral channels at each pixel refer to the intermediate data generated by the product operation and are used for subsequent accumulation calculations.

[0100] In this embodiment, when calling the preset biological weight coefficient set corresponding to the ecosystem type, the red-dominant coefficient set is loaded for coral reef ecosystems, and the near-infrared-dominant coefficient set is loaded for seagrass bed ecosystems. A product operation is performed on the enhanced spectral data of each pixel in the enhanced spectral data of different spectral channels. The formula is to multiply each spectral channel value by the corresponding weight coefficient to generate the weighted spectral value of the different spectral channels at that pixel.

[0101] Step 213: Superimpose all weighted spectral values ​​of the same pixel to obtain the biological activity intensity value of each pixel.

[0102] In this step, the biological activity intensity value of each pixel refers to a scalar representing the biological activity.

[0103] In this embodiment, when all weighted spectral values ​​for a given pixel are superimposed, an arithmetic accumulation algorithm is used. The formula is: the biological activity intensity value is equal to the red light weighted value plus the green light weighted value plus the blue light weighted value plus the near-infrared weighted value. The calculation result is stored as the biological activity intensity value for each pixel.

[0104] Step 214: Convert the biological activity intensity values ​​of all pixel points into distribution map pixel values, and generate a preliminary biological activity intensity distribution map according to the distribution map pixel values.

[0105] In this step, the distribution map pixel value refers to the grayscale value of the preliminary biological activity intensity distribution map, which is obtained by linearly mapping the biological activity intensity value to an integer from 0 to 255.

[0106] In this example, the biological activity intensity values ​​at all pixels were first linearly scaled to obtain a distribution map pixel value: distribution map pixel value = intensity value ÷ maximum intensity value × A, where A is a constant ranging from 0 to 255. Using a digital elevation model, the geographic coordinates of the coral reef area were projected onto a two-dimensional image grid, and the seagrass bed area was assigned values ​​based on isobaths. This ultimately generated a preliminary biological activity intensity distribution map with the same spatial resolution as the original image.

[0107] The embodiments of the present application break through the triple technical barriers of traditional remote sensing fusion through dynamic loading of weight sets in the ecosystem, pixel-level product operations that retain spatial heterogeneity, and edge node fixed-point number optimization technology.

[0108] This application provides a specific embodiment, step 205, converting the corrected biological activity intensity distribution map into a biological activity characteristic map based on the correlation between the historical species distribution data and the spectral characteristics, specifically comprising the following steps:

[0109] Step 221: Based on the correlation between the species density of the historical species distribution data and the spectral characteristics, and the ecosystem type, the historical species distribution data is grouped to obtain a grouping result.

[0110] In this step, species density refers to the number or coverage ratio of the target species per unit area. This includes the percentage of live coral cover in coral reef areas and the grams of leaf biomass per square meter in seagrass bed areas. The grouping results are structured datasets divided by ecosystem type and spectral intensity range, including coral reef datasets and seagrass bed datasets. Each group includes intensity thresholds, average species density, and sample size.

[0111] In an embodiment of the present application, the species density recorded in the historical species distribution data and the spectral reflectance intensity values ​​of its corresponding spectral characteristics are extracted; the historical species distribution data are divided into independent data sets according to the ecosystem type; and the spectral reflectance intensity values ​​are divided into preset interval groups; and finally, the grouping results containing ecosystem attributes and intensity intervals are output.

[0112] Step 222: Based on the grouping results, construct a species density spectral response lookup table, wherein the species density spectral response lookup table contains transformation rules corresponding to different ecosystem types.

[0113] In this step, the species density spectral response lookup table (SDR) refers to a database storing the mapping between spectral intensity and species density, including entries for coral reef and seagrass bed types. This table is generated based on statistical analysis of grouping results and serves as a guide for pixel-level density conversion. Conversion rules for different ecosystem types refer to ecosystem-specific intensity and density conversion formulas. The coral reef rule multiplies red light intensity by a factor of 0.25 and a constant of 5, while the seagrass bed rule multiplies near-infrared intensity by a factor of 0.3 and a constant of 10.

[0114] In an embodiment of the present application, based on each grouping result, the average value of the measured species density of each group is calculated as the baseline density; a mapping relationship between the intensity interval boundary value and the baseline density is established; the mapping relationship is integrated into a lookup table entry according to the ecosystem type; and finally, a species density spectral response lookup table containing exclusive conversion rules for coral reefs and seagrass beds is generated.

[0115] Step 223: Based on the conversion rule, the biological activity intensity value of each pixel point is converted into a species density characteristic value, so as to generate a biological activity intensity distribution map according to all species density characteristic values.

[0116] In this step, species density eigenvalues ​​are quantitative values ​​representing the density of species per unit area, including the percentage of coral reef pixel coverage and the biomass of seagrass bed pixels. The biomass intensity distribution map is a two-dimensional spatial matrix of geographic distribution, consisting of a grid structure with the same resolution as the original image. Each grid cell stores a species density eigenvalue, which is used to visualize the species distribution heat map.

[0117] In an embodiment of the present application, based on the conversion rule, for each pixel point of the corrected biological activity intensity distribution map, its biological activity intensity value is read; the ecosystem type is determined according to the pixel coordinates; the conversion rule corresponding to the intensity interval is matched from the species density spectral response lookup table; the rule is applied to linearly convert the biological activity intensity value into a species density characteristic value (for example, a biological activity intensity value of 120 is converted into a coral coverage rate of 30%); the species density characteristic values ​​of all pixel points are reorganized according to their original spatial positions to generate a biological activity intensity distribution map.

[0118] The embodiments of the present application achieve precise conversion of pixel-level intensity to species density, solving the core problem that the intensity of biological activity in marine remote sensing monitoring cannot directly reflect the actual species distribution; through differentiated processing of the red light response of coral reefs and the near-infrared response of seagrass beds, the inversion accuracy of coral coverage and seagrass biomass is improved, providing a reliable data basis for ecological evaluation.

[0119] This application provides a specific embodiment, step 103, gridding the marine monitoring area according to the spatial resolution of the biological activity characteristic map and the historical species distribution data, generating a baseline species distribution density value for each grid cell, and calculating the species distribution density value for each grid cell, specifically comprising the following steps:

[0120] Step 301: Divide the ocean monitoring area into a plurality of grid cells according to the spatial resolution of the biological activity characteristic map and using a preset grid division rule.

[0121] In this step, the preset grid division rules refer to grid generation strategies that dynamically adapt to ecosystem characteristics, automatically selected based on a terrain database. Multiple grid cells, consisting of closed polygons with unique geocodes, represent spatial divisions covering the marine monitoring area. Each cell stores boundary coordinates, ecosystem type, and associated data, used to organize density distribution data.

[0122] In an embodiment of the present application, according to the spatial resolution of the biological activity characteristic map, the pixel size of the biological activity characteristic map is read, and a preset grid division rule library is called, and a triangular irregular grid is used for the coral reef ecosystem, and a rectangular grid is used for the seagrass bed ecosystem; the marine monitoring area is cut into specified grids through the geographic information system engine, and multiple grid units covering the entire area are output.

[0123] Step 302: extracting historical observation points located within the grid unit from the historical species distribution data, parsing the data records of the historical observation points, and obtaining a set of species density measurement values ​​corresponding to each grid unit.

[0124] In this step, historical observation points refer to discrete geographic locations recorded during historical surveys, including survey vessel track coordinates and diving observation stations. These points carry timestamps, measured species density, and water depth information, providing a baseline density data source. A species density measurement set refers to the set of density data from all historical observation points within the same grid cell, including a series of percentage cover for coral reef cells or biomass for seagrass beds, used for statistical aggregation.

[0125] In an embodiment of the present application, the geographic boundaries of each grid unit are traversed, and historical observation points whose coordinates fall within the boundaries in the historical species distribution data are screened; the species density field of the historical observation point data records is parsed, and all valid values ​​are summarized into a species density measurement value set corresponding to each grid unit.

[0126] Step 303: Sort the species density measurement values ​​in each species density measurement value set to select a target species density measurement value at the median, and use the target species density measurement value corresponding to each grid cell as the corresponding benchmark species distribution density value.

[0127] In this step, the target species density measurement value refers to the median value of the sorted set of species density measurements, reflecting the typical ecological status of the grid unit.

[0128] In an embodiment of the present application, the set of species density measurement values ​​for each grid unit is arranged in ascending order of value. If the data amount is an odd number, the median value is taken; if it is an even number, the average of the two middle values ​​is taken; the interference of outliers is eliminated, and the target species density measurement value corresponding to each grid unit is obtained as the corresponding benchmark species distribution density value.

[0129] Step 304: Align the coordinate systems of the grid cells and the biological activity characteristic map to extract the biological activity characteristic value set corresponding to each grid cell, and use the characteristic mean in each biological activity characteristic value set as the species distribution density value of the corresponding grid cell.

[0130] In this step, the biological activity feature value set refers to all pixel values ​​in the image area corresponding to the grid cell, including the reflection intensity sequence of pixels in the biological activity feature map, which is used to calculate the real-time density. The feature mean refers to the arithmetic mean of the biological activity feature value set and represents the overall biological activity intensity of the cell.

[0131] In an embodiment of the present application, the grid unit boundary is mapped to the biological activity characteristic map through coordinate system conversion; all biological activity characteristic values ​​within the coverage area of ​​each grid are extracted; the characteristic mean of the pixel value is calculated, and the calculation formula of the characteristic mean is: the sum of all pixel values ​​in the grid divided by the number of pixels, such as (152+168+142) / 3=154, to generate the current species distribution density value.

[0132] The embodiments of the present application achieve spatial alignment of multi-source data through ecosystem-adaptive grid division, use median statistics to eliminate abnormal interference from historical data, and combine pixel mean calculation to accurately quantify real-time species distribution density, thereby solving the data bias problem caused by grid mismatch in traditional methods; the differentiated design of coral reef triangular grids and seagrass bed rectangular grids improves the spatial representation accuracy of coral coverage and seagrass biomass.

[0133] This application provides a specific embodiment, step 105, generating a marine ecological integrity assessment result based on all species distribution density attenuation areas, specifically including the following steps:

[0134] Step 501: Calculate the ratio of the area of ​​the attenuation region of the distribution density of all species to the ocean monitoring area, and use the ratio as the attenuation area ratio value.

[0135] In this step, the ratio of attenuated area refers to a quantitative indicator of the proportion of areas where species are declining, including the percentage of coral reef areas reflecting bleaching areas.

[0136] In an embodiment of the present application, the grid cell areas of all species distribution density attenuation areas are accumulated through a geographic information system, and the accumulated value is divided by the total area of ​​the marine monitoring area to obtain the attenuation area ratio value, that is, the attenuation area ratio value = (total area of ​​attenuation area ÷ total area of ​​monitoring area) %; the coral reef area is calculated based on the three-dimensional surface area of ​​the reef, and the seagrass bed area is calculated based on the isobath-corrected plane area.

[0137] Step 502: extract the corresponding negative deviation values ​​from all species distribution density attenuation areas, calculate the average value of all negative deviation values, and generate an overall attenuation intensity value.

[0138] In this step, negative deviations are the deviations of the real-time density of a grid cell below the historical baseline, including negative deviations in coral cover, and are used to quantify the intensity of decline at a single point. The overall decline intensity is a comprehensive measure of decline across the entire region, consisting of the arithmetic mean of all negative deviations, corrected for tidal phase, for seagrass beds to reflect the overall stress level of the ecosystem.

[0139] In an embodiment of the present application, each attenuation area metadata field is traversed, and pre-stored negative deviation values ​​are read from all species distribution density attenuation areas (such as the symbiotic algae deviation value in the coral reef area and the thallus biomass deviation value in the seagrass bed area); the arithmetic average of all negative deviation values ​​is calculated, and the tidal influence coefficient is additionally introduced into the seagrass bed area for weighting to obtain an overall attenuation intensity value reflecting the overall degree of decline.

[0140] Step 503: Compare the attenuation area ratio value with a preset health level threshold table to obtain a health level determination result.

[0141] In this step, preset health threshold tables refer to ecosystem-specific area ratios and health status mapping standards, including a three-level threshold table for coral reefs and a four-level threshold table for seagrass beds, for objective grading. Health level determination results are qualitative assessments output through threshold comparisons, including textual conclusions such as healthy, degraded, and endangered, using semantic definitions based on International Union for Conservation of Nature standards.

[0142] In the embodiment of the present application, a preset health level threshold table is loaded according to the current ecosystem type, and the attenuation area ratio value is matched to the corresponding interval (if the coral reef ratio is 18%, it is determined to be a degradation level), and the health level determination result is obtained.

[0143] Step 504: Based on a preset risk index calculation rule, convert the overall attenuation intensity value into a risk index.

[0144] In this step, the pre-defined risk index calculation rules define the logic for converting intensity values ​​into risk scores, including linear functions for coral reefs and piecewise functions for seagrass beds. The risk index represents a numerical representation of the degree of ecological risk, using a continuous scale from 0 to 100. Scores above 60 trigger a yellow alert, and scores above 80 trigger a red emergency response.

[0145] In the embodiment of the present application, an ecosystem-specific piecewise linear conversion is performed based on the preset risk index calculation rules. For example, in the coral reef area, the intensity value is multiplied by a coefficient of 100 to generate a basic risk value, and real-time water temperature compensation is superimposed (5 points are added for every 1°C exceeding the benchmark); in the seagrass bed area, the intensity value is multiplied by a coefficient of 80 and then turbidity compensation is added (10 points are added for every 5 NTU exceeding the benchmark), and a quantitative risk index is output.

[0146] Step 505: Combining the health level determination result and the risk index into a marine ecological integrity assessment result.

[0147] In an embodiment of the present application, a structured data object is created, and the health level determination result and the risk index value are encapsulated as a key-value pair (e.g., the health level is degraded and the risk index is 65), and a spatial distribution heat map link is attached to generate a marine ecological integrity assessment result that can be directly output to the regulatory platform.

[0148] The embodiment of the present application breaks through the limitations of traditional single indicators through a two-dimensional evaluation mechanism of coupling area ratio and recession intensity, combined with an ecosystem dynamic compensation algorithm; the coral reef water temperature compensation and seagrass bed turbidity correction design improve the accuracy of tropical ocean extreme event warnings and provide accurate action priority determination for ecological restoration.

[0149] This application provides a specific embodiment, step 504, converting the overall attenuation intensity value into a risk index based on a preset risk index calculation rule, specifically comprising the following steps:

[0150] Step 511: Determine the target conversion value range corresponding to the overall attenuation intensity value according to a preset attenuation intensity risk index mapping table.

[0151] In this step, the pre-defined attenuation intensity risk index mapping table, a structured standard defining the relationship between intensity intervals and risk levels, includes a three-level interval table for coral reefs and a four-level interval table for seagrass beds. This table is generated based on modeling of historical ecological disaster data. The target conversion value interval is the continuous range of values ​​that the overall attenuation intensity value matches, including closed boundaries with interval identifiers that activate the corresponding calculation rules.

[0152] In an embodiment of the present application, the attenuation intensity risk index mapping table stored in the rule base is called, the overall attenuation intensity value (such as 0.45) is compared with the boundaries of each interval of the preset attenuation intensity risk index mapping table, and the corresponding target conversion value interval is locked, such as 0.45∈[0.3,0.6].

[0153] Step 512: Based on the ecosystem type, call the reference proportional coefficient corresponding to the target conversion value range in the preset risk index calculation rule, scale the overall attenuation intensity value, and obtain the scaled attenuation intensity value.

[0154] In this step, the baseline scaling factor is the multiplier that linearly converts the intensity value to the risk baseline, determined by combining interval and ecosystem matching. The scaled attenuated intensity value is the intermediate result value after processing with the scaling factor, reflecting the base risk level.

[0155] In an embodiment of the present application, a preset risk index calculation rule is loaded according to the current ecosystem type (such as coral reefs and seagrass beds), and the target conversion value interval (such as medium-risk area) is matched to obtain a baseline proportional coefficient (such as 80 for coral reefs and 70 for seagrass beds); the overall attenuation intensity value is multiplied by the baseline proportional coefficient (such as 0.45×80=36 for coral reef areas) to generate a scaled attenuation intensity value.

[0156] Step 513: Based on the marine biodiversity data, a target compensation parameter is selected from the environmental dynamic compensation parameters of the preset risk index calculation rule.

[0157] In this step, the dynamic environmental compensation parameter refers to the adjustment rules for the real-time environmental factors to the risk value, which are dynamically activated based on real-time monitoring data. The target compensation parameter refers to the actual compensation value applied, which is used for the final risk correction.

[0158] In an embodiment of the present application, real-time environmental parameters in marine biodiversity data are analyzed (e.g., surface water temperature for coral reefs and turbidity value for seagrass beds); corresponding parameters are selected from the environmental dynamic compensation parameters of the preset risk index calculation rules according to the ecosystem type and the current risk range (e.g., when the water temperature in the risk area of ​​a coral reef is >28°C, 5 points are added for every 1°C above the limit), and the target compensation parameters are output.

[0159] Step 514: Superimpose the scaled attenuation intensity value and the target compensation parameter to generate a risk index.

[0160] In the embodiment of the present application, an arithmetic addition of the scaled attenuation intensity value and the target compensation parameter is performed (e.g., coral reef area 36 + (29-28) × 5 = 41), and when the result exceeds 100, it is truncated to 100 to generate a final risk index.

[0161] The embodiment of the present application breaks through the limitations of traditional static risk models through a two-layer mechanism of interval intensity mapping and dynamic environmental compensation, providing an accurate quantitative basis for marine protection decision-making.

[0162] Figure 2 The present invention provides a schematic diagram of a marine ecological assessment system based on big data analysis. Figure 2 As shown, the system includes:

[0163] An acquisition module 21 is used to acquire marine biodiversity data and image data of the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators;

[0164] A processing module 22 is configured to utilize an edge computing architecture deployed in the ocean monitoring area to perform streaming processing on the image data to obtain a biological activity feature map;

[0165] a division module 23 for dividing the marine monitoring area into grids based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, generating a baseline species distribution density value for each grid cell, and calculating the species distribution density value for each grid cell;

[0166] a determination module 24 for calculating a negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value, and determining the corresponding grid cell as a species distribution density attenuation area when the negative deviation is greater than a preset extinction threshold;

[0167] The evaluation module 25 is used to generate marine ecological integrity evaluation results based on all species distribution density attenuation areas.

[0168] Figure 2 The marine ecological assessment system based on big data analysis can be performed Figure 1 The implementation principles and technical effects of the marine ecological assessment method based on big data analysis described in the illustrated embodiment are not further described. The specific manner in which each module and unit performs operations in the marine ecological assessment system based on big data analysis in the above embodiment has been described in detail in the embodiments of the method and will not be elaborated on here.

[0169] In one possible design, Figure 2 The marine ecological assessment system based on big data analysis of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0170] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0171] The processing component 32 is used for the above Figure 1 The embodiment provides a marine ecological assessment method based on big data analysis.

[0172] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0173] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0174] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0175] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0176] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0177] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0178] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a marine ecological assessment method based on big data analysis.

[0179] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0180] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0181] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A marine ecological assessment method based on big data analysis, characterized in that: include: Obtaining marine biodiversity data and image data for the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators; Utilizing an edge computing architecture deployed in the ocean monitoring area, the image data is stream-processed to obtain a biological activity feature map; Gridding the marine monitoring area based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, generating a baseline species distribution density value for each grid cell, and calculating the species distribution density value for each grid cell; Calculate the negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value. When the negative deviation is greater than a preset extinction threshold, the corresponding grid cell is determined as a species distribution density attenuation area. Generate marine ecological integrity assessment results based on all species distribution density decline areas; The image data is stream-processed using the edge computing architecture deployed in the ocean monitoring area to obtain a biological activity feature map, including: Using the edge computing architecture, the multispectral bands in the image data are separated to obtain reflection intensity data of each spectral channel; Enhance the characteristic bands related to biological activities in the reflectance intensity data of all spectral channels to generate enhanced spectral data of each spectral channel; The preset biological weight coefficient set and the enhanced spectral data of different spectral channels are weightedly superimposed to generate a preliminary biological activity intensity distribution map; Correcting the discontinuous areas in the preliminary biological activity intensity distribution map to generate a corrected biological activity intensity distribution map; According to the correlation between the historical species distribution data and the spectral characteristics, the corrected biological activity intensity distribution map is converted into a biological activity characteristic map.

2. The method according to claim 1, characterized in that The preset biological weight coefficient set and the enhanced spectral data of different spectral channels are weighted superimposed to generate a preliminary biological activity intensity distribution map, including: Determining the ecosystem type to which the marine monitoring area belongs based on the geographic coordinate data of the marine monitoring area, wherein the ecosystem type includes a coral reef ecosystem and a seagrass bed ecosystem; Calling a preset biological weight coefficient set corresponding to the ecosystem type, multiplying the enhanced spectral data of each pixel point in the enhanced spectral data of different spectral channels by the biological weight coefficient of the corresponding spectral channel in the preset biological weight coefficient set, to obtain a weighted spectral value of the different spectral channels of each pixel point; All weighted spectral values ​​of the same pixel are superimposed to obtain the biological activity intensity value of each pixel; The biological activity intensity values ​​of all pixel points are converted into distribution map pixel values ​​to generate a preliminary biological activity intensity distribution map according to the distribution map pixel values.

3. The method according to claim 1, characterized in that According to the correlation between the historical species distribution data and the spectral characteristics, the modified biological activity intensity distribution map is converted into a biological activity characteristic map, including: Grouping the historical species distribution data based on the correlation between the species density of the historical species distribution data and the spectral characteristics, and the ecosystem type, to obtain a grouping result; Based on the grouping results, constructing a species density spectral response lookup table, wherein the species density spectral response lookup table includes conversion rules corresponding to different ecosystem types; Based on the conversion rule, the biological activity intensity value of each pixel point is converted into a species density characteristic value, so as to generate a biological activity intensity distribution map according to all species density characteristic values.

4. The method according to claim 1, wherein The marine monitoring area is gridded based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, and a baseline species distribution density value for each grid cell is generated. The species distribution density value for each grid cell is also calculated, including: According to the spatial resolution of the biological activity characteristic map, the ocean monitoring area is divided into a plurality of grid cells using a preset grid division rule; Extracting historical observation points located within the grid cells from the historical species distribution data, parsing data records of the historical observation points, and obtaining a set of species density measurement values ​​corresponding to each grid cell; Sort the species density measurements in each species density measurement set to select the target species density measurement at the median, and use the target species density measurement corresponding to each grid cell as the corresponding benchmark species distribution density value; The grid units and the biological activity characteristic map are aligned in coordinate system to extract the biological activity characteristic value set corresponding to each grid unit, and the characteristic mean in each biological activity characteristic value set is used as the species distribution density value of the corresponding grid unit.

5. The method according to claim 1, wherein Generate marine ecological integrity assessment results based on all species distribution density decline areas, including: Calculate the ratio of the area of ​​the region where the distribution density of all species is attenuated to the marine monitoring area, and use the ratio as the attenuation area ratio value; Extract the corresponding negative deviation values ​​from the attenuation areas of all species distribution density, calculate the average value of all negative deviation values, and generate the overall attenuation intensity value; Comparing the attenuation area ratio value with a preset health level threshold table to obtain a health level determination result; Based on a preset risk index calculation rule, converting the overall attenuation intensity value into a risk index; The health grade determination result and the risk index are combined into a marine ecological integrity assessment result.

6. The method according to claim 5, characterized in that Based on a preset risk index calculation rule, the overall attenuation intensity value is converted into a risk index, including: Determining a target conversion value interval corresponding to the overall attenuation intensity value according to a preset attenuation intensity risk index mapping table; According to the ecosystem type, calling the reference proportional coefficient corresponding to the target conversion value interval in the preset risk index calculation rule, scaling the overall attenuation intensity value to obtain a scaled attenuation intensity value; Based on marine biodiversity data, target compensation parameters are selected from the environmental dynamic compensation parameters of the preset risk index calculation rules; The scaled attenuation intensity value and the target compensation parameter are superimposed to generate a risk index.

7. A marine ecological assessment system based on big data analysis, characterized in that: include: An acquisition module, configured to acquire marine biodiversity data and image data of the marine monitoring area, wherein the marine biodiversity data includes historical species distribution data and ecological niche indicators; a processing module, configured to perform streaming processing on the image data using an edge computing architecture deployed in the ocean monitoring area to obtain a biological activity feature map; a partitioning module, configured to perform grid division on the marine monitoring area based on the spatial resolution of the biological activity characteristic map and the historical species distribution data, generate a baseline species distribution density value for each grid cell, and simultaneously calculate the species distribution density value for each grid cell; a determination module, configured to calculate the negative deviation between the species distribution density value of each grid cell and the corresponding benchmark species distribution density value, and when the negative deviation is greater than a preset extinction threshold, determine the corresponding grid cell as a species distribution density attenuation area; An assessment module is used to generate marine ecological integrity assessment results based on all species distribution density attenuation areas; The image data is stream-processed using the edge computing architecture deployed in the ocean monitoring area to obtain a biological activity feature map, including: Using the edge computing architecture, the multispectral bands in the image data are separated to obtain reflection intensity data of each spectral channel; Enhance the characteristic bands related to biological activities in the reflectance intensity data of all spectral channels to generate enhanced spectral data of each spectral channel; The preset biological weight coefficient set and the enhanced spectral data of different spectral channels are weightedly superimposed to generate a preliminary biological activity intensity distribution map; Correcting the discontinuous areas in the preliminary biological activity intensity distribution map to generate a corrected biological activity intensity distribution map; According to the correlation between the historical species distribution data and the spectral characteristics, the corrected biological activity intensity distribution map is converted into a biological activity characteristic map.

8. A computing device, characterized in that It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a marine ecological assessment method based on big data analysis as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, a marine ecological assessment method based on big data analysis as described in any one of claims 1 to 6 is implemented.

Images