A Standardization Method and System for Marine Environmental Data

Abstract

The present invention discloses a method and system for standardizing marine environmental data, which relates to the field of marine environmental monitoring and includes: performing spatial grid processing on the environmental data of the selected target sea area, obtaining multiple target sea area grid division schemes and selecting the optimal grid division data corresponding to the optimal grid division scheme; performing difference analysis on the optimal grid division data to determine the existence of the plane distribution reference paradigm of marine ecological environment impact factors, and constructing the plane distribution reference paradigm of marine ecological environment impact factors; constructing the seasonal change reference paradigm of marine ecological environment impact factors and constructing the interannual change reference paradigm of marine ecological environment impact factors; completing the standardization of marine environmental data in the target sea area by supplementing the missing data in the target sea area according to the three reference paradigms. The present invention can complement the missing marine environmental data on the spatio-temporal scale.

Description

Technical Field

[0001] The present invention relates to the field of marine environment monitoring, and particularly relates to a method and system for standardizing marine environment data. Background Art

[0002] The monitoring, management and application of marine environment data are the keys to the prediction and prevention of marine ecological environment risks. Since the offshore ship cruising and the online buoy water quality monitoring system require a large amount of capital and human resources, the spatial coverage and monthly frequency of the monitoring data are limited, the data of some sea areas are seriously missing, and the existing monitoring data have inconsistent spatio-temporal granularities, making it difficult to comprehensively reflect the environmental conditions such as marine eutrophication. In particular, the spatio-temporal granularities of the original monitoring data are significantly different from those of eutrophication symptoms such as red tides and hypoxia, making it difficult to support the analysis of the environmental process mechanisms of ecological events. Therefore, at present, in scientific research and environmental management such as the simulation, evaluation and prevention and control plan formulation of the eutrophication state in the offshore area, standardized reference data with consistent spatio-temporal granularities are needed as a support, which is of great significance to the prediction and prevention of marine ecological environment risks.

[0003] In the prior art, Yongzhi Liu et al. proposed an improved Cressman interpolation method and applied it to the standardization of the original monitoring data of total nitrogen in the ocean. Rushui Xiao et al. proposed a method for standardizing the spatiotemporal missing data of marine nitrogen and phosphorus nutrients by combining Chebyshev Polynomial Fitting (CPF) and STL (Seasonal-Trend decomposition using LOESS, STL) time series data decomposition and reconstruction. This method first uses spatial interpolation CPF to interpolate the spatially non-uniformly distributed marine nitrogen and phosphorus nutrient monitoring survey statistical data to the same grid as the Copernicus Marine Environment Monitoring Service (CMEMS) product data (1 / 12° horizontal resolution). Then the monitoring data and CMEMS product data are standardized (Minmax normalization). Secondly, STL is used to extract the trend and seasonal signals of the standardized monitoring data and CMEMS product data. Thirdly, the seasonal decomposition of the monitoring data is replaced by the seasonal decomposition of the CMEMS product data (calculated according to the proportion of the original time series). Finally, the monitoring data is decomposed into new seasons, and the trend terms and residual terms are summarized to obtain the completed data. The completed monitoring data retains the trend and detailed fluctuation of the original monitoring data, so that it can more realistically depict the changes in nitrogen and phosphorus nutrients in the target sea area, which is convenient for subsequent analysis. The above data standardization method adopts Chebyshev polynomial fitting when completing spatial data, which realizes the conversion of scattered plane distribution data into grid data covering the entire sea area. This method belongs to statistical interpolation method, which ignores the correlation of complex biogeochemical processes in the ocean with space and time, and can only be applied to spatial data interpolation in a single way. For the standardization of time series data, the above method performs STL decomposition on the same element data from different sources, replaces the seasonal items with each other, and then re-summarizes the items to obtain the completed data. This process not only ignores the important influence of abnormal data on the trend of factor changes, but also relies heavily on exogenous data, which has great limitations in the actual application of data standardization.

[0004] In summary, how to complete the missing marine environmental data in terms of time and space is an important issue that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for standardizing marine environmental data, which can solve the problem in the prior art that missing marine environmental data cannot be supplemented in time and space scales.

[0006] An embodiment of the present invention provides a method for standardizing marine environmental data, including the following steps:

[0007] Using the station coverage rate reflecting the aggregated data after removing outliers in the geographical coverage of the target sea area, the granularity saturation rate measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the distribution balance of monitoring data in different seasons within a year, screen the environmental data of the target sea area and perform gridification;

[0008] Use the hierarchical clustering analysis method to group the gridified data by similarity, and use the radial basis function to model each group of data to obtain the plane distribution reference paradigm of marine ecological environment impact factors;

[0009] Select the environmental data corresponding to the year when the seasonal balance degree reaches the set threshold; according to the distribution pattern of the selected environmental data, determine the corresponding seasonal change reference paradigm of marine ecological environment impact factors;

[0010] Use the seasonal change reference paradigm of marine ecological environment impact factors to obtain the seasonal change standardized data for each year; according to the seasonal change standardized data, use the Fourier series equation to model and obtain the interannual change reference paradigm of marine ecological environment impact factors;

[0011] Use the plane distribution reference paradigm of marine ecological environment impact factors, the seasonal change reference paradigm of marine ecological environment impact factors, and the interannual change reference paradigm of marine ecological environment impact factors to fill in the missing plane distribution data, seasonal change data, and interannual change data of the target sea area respectively, and complete the standardization of marine environmental data in the target sea area.

[0012] Further, the specific steps of screening the environmental data of the target sea area include:

[0013] According to the environmental data of the target sea area, take the station coverage rate, the granularity saturation rate, and the seasonal balance degree as the core criteria for measuring the quality of environmental data;

[0014] According to the environmental data screened by each core criterion, use the standard classification method of equal interval and quantile to divide the environmental data into different levels of high, medium-high, medium, medium-low, and low according to the data quality;

[0015] Take the high-quality environmental data as the environmental data of the screened target sea area.

[0016] Further, the specific steps of performing gridification include:

[0017] Design five grid division schemes for the target sea areas according to high-quality environmental data at different spatial resolutions. The grid division schemes include: 0.25°×0.25°, 0.2°×0.2°, 0.15°×0.15°, 0.1°×0.1°, and 0.05°×0.05°.

[0018] Select the optimal grid division scheme from the five grid division schemes for the target sea areas using the kappa coefficient and relative deviation.

[0019] Further, before using the hierarchical clustering analysis method to perform similarity grouping on the gridded data, it also includes:

[0020] According to the optimal gridded data corresponding to the optimal grid division scheme, select the plane distribution year-on-year data of the influencing factors in the target sea area within different months for one-way analysis of variance.

[0021] If the difference P is greater than 0.05, it is determined that there is a plane distribution reference paradigm for the marine ecological environment influencing factors.

[0022] Further, the specific steps of using the hierarchical clustering analysis method to perform similarity grouping on the gridded data include:

[0023] In the process of hierarchical clustering analysis, adopt the Euclidean distance measurement method and the ward sum of squared deviations clustering merging strategy, and in accordance with the "bottom-up" agglomerative method, gradually merge the data through cyclic iteration and form a clustering structure pedigree diagram.

[0024] Obtain the similar data in the optimal gridded data corresponding to the optimal grid division scheme according to the clustering structure pedigree diagram, and group the similar data.

[0025] Further, the specific steps of obtaining the plane distribution reference paradigm for the marine ecological environment influencing factors include:

[0026] Each group of data after similarity grouping represents a plane distribution pattern. Use the radial basis function to model each group of data to obtain the plane distribution reference paradigm for the marine ecological environment influencing factors. The formula is:

[0027] ;

[0028] Among them, represents the grouped data after similarity analysis, represents the center, is the coefficient term of the model, is the form of the basis function, is the number of radial basis functions, i represents the index variable used to number different radial basis functions.

[0029] Further, according to the distribution pattern of the selected environmental data, determining the corresponding seasonal change benchmark paradigm of the marine ecological environment impact factors, the specific steps include:

[0030] Selecting the environmental data of the year with a seasonal balance degree reaching 100%, and the distribution patterns of the environmental data include "U" type and non-"U" type;

[0031] For the data with a "U" type distribution pattern, using an exponential function for modeling to obtain the seasonal change benchmark paradigm of the marine ecological environment impact factors, and the formula is:

[0032] ;

[0033] Wherein, is the intercept, controlling the position of the curve on the x-axis; is the first-order term coefficient, controlling the slope of the curve; is the second-order term coefficient, controlling the bending degree of the curve, x is the month;

[0034] For the data with a non-"U" type distribution pattern, obtaining the difference between the data with a non-"U" type distribution pattern and the data with a "U" type distribution pattern, and using a sine function to model the difference;

[0035] ;

[0036] Wherein, is the amplitude, controlling the peak value of the sine wave; is the phase, controlling the horizontal translation of the sine wave; is the vertical translation, controlling the vertical offset of the sine wave.

[0037] Further, the interannual change benchmark paradigm of the marine ecological environment impact factors, and the formula is:

[0038] ;

[0039] Wherein, the constant term represents the average value of the data within the entire time range, used to describe the overall offset of the data; the frequency parameter represents the period of each filtering, The larger the value, the shorter the period, and the higher the periodicity of the curve on the abscissa; represents the harmonic order, takes 1 and 2, corresponding to the first harmonic and the second harmonic respectively; the cosine term and the sine term represent the amplitudes of the cosine wave and the sine wave with different frequencies in the data, x represents the year.

[0040] An embodiment of the present invention provides a standardization system for marine environmental data, including:

[0041] A data acquisition module, configured to use the station coverage rate of the aggregated data reflecting the elimination of outliers in the geographical coverage of the target sea area, the granularity saturation rate measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the distribution balance of monitoring data in different seasons within a year to screen the environmental data of the target sea area and perform gridification;

[0042] A planar distribution benchmark paradigm construction module, configured to perform similarity grouping on the gridified data using the hierarchical clustering analysis method, and perform modeling on each group of data using the radial basis function to obtain the planar distribution benchmark paradigm of the marine ecological environment impact factors;

[0043] A seasonal change benchmark paradigm construction module, configured to select the environmental data corresponding to the years when the seasonal balance degree reaches the set threshold; determine the corresponding seasonal change benchmark paradigm of the marine ecological environment impact factors according to the distribution pattern of the selected environmental data;

[0044] An inter-annual change benchmark paradigm construction module, configured to use the seasonal change benchmark paradigm of the marine ecological environment impact factors to obtain the seasonal change benchmarked data for each year; perform modeling using the Fourier series equation according to the seasonal change benchmarked data to obtain the inter-annual change benchmark paradigm of the marine ecological environment impact factors;

[0045] A marine environmental data standardization module, configured to use the planar distribution benchmark paradigm of the marine ecological environment impact factors, the seasonal change benchmark paradigm of the marine ecological environment impact factors, and the inter-annual change benchmark paradigm of the marine ecological environment impact factors to fill in the missing planar distribution data, seasonal change data, and inter-annual change data of the target sea area respectively, and complete the standardization of the marine environmental data in the target sea area.

[0046] An embodiment of the present invention provides a method and system for standardizing marine environmental data. Compared with the prior art, the beneficial effects are as follows:

[0047] Using the station coverage rate, the granularity saturation rate, and the seasonal balance degree to screen the environmental data of the target sea area and perform gridification; according to the gridified data, obtaining the planar distribution benchmark paradigm of the marine ecological environment impact factors, the seasonal change benchmark paradigm of the marine ecological environment impact factors, and the inter-annual change benchmark paradigm of the marine ecological environment impact factors; through the planar distribution benchmark paradigm of the marine ecological environment impact factors, the seasonal change benchmark paradigm of the marine ecological environment impact factors, and the inter-annual change benchmark paradigm of the marine ecological environment impact factors, it is possible to reflect the regularity of the marine ecological environment impact factors in the target sea area in terms of planar distribution, seasonal change, and inter-annual change, that is, the change law on the spatio-temporal scale, so as to fill in the missing sea area data on the spatio-temporal scale and standardize the data of the target sea area. Description of the Drawings

[0048] Figure 1 This is the overall model architecture of a method for standardizing marine environmental data provided by an embodiment of the present invention;

[0049] Figure 2 This is the backpropagation neural network structure of a method for standardizing marine environmental data provided by an embodiment of the present invention;

[0050] Figure 3 This is the flowchart of a method for standardizing marine environmental data provided by an embodiment of the present invention;

[0051] Figure 4 This is the interannual change benchmark paradigm and standardized data of DIN in the target sea area for a method for standardizing marine environmental data provided by an embodiment of the present invention;

[0052] Figure 5 This is the interannual change benchmark paradigm and standardized data of PO4-P in the target sea area for a method for standardizing marine environmental data provided by an embodiment of the present invention. Detailed Embodiments

[0053] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention is given with reference to the accompanying drawings. Many specific details are set forth in the following description to fully understand the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0054] An embodiment of the present invention provides a method for standardizing marine environmental data, including the following steps:

[0055] Step 1: Use the aggregation data reflecting the elimination of outliers, the station coverage in the geographical coverage area of the target sea area, the granularity saturation measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the distribution balance of monitoring data in different seasons within a year to screen the environmental data of the target sea area and perform gridification.

[0056] Step 2: Use the hierarchical clustering analysis method to group the gridified data by similarity, and use the radial basis function to model each group of data to obtain the plane distribution benchmark paradigm of the marine ecological environment impact factors.

[0057] Step 3: Select the environmental data corresponding to the year when the seasonal balance degree reaches the set threshold; according to the distribution pattern of the selected environmental data, determine the corresponding seasonal change benchmark paradigm of the marine ecological environment impact factors.

[0058] Step 4: Use the seasonal change benchmark paradigm of marine ecological environment impact factors to obtain the seasonal change benchmark data for each year; according to the seasonal change benchmark data, use the Fourier series equation to model and obtain the interannual change benchmark paradigm of marine ecological environment impact factors.

[0059] Step 5: Use the planar distribution benchmark paradigm of marine ecological environment impact factors, the seasonal change benchmark paradigm of marine ecological environment impact factors, and the interannual change benchmark paradigm of marine ecological environment impact factors respectively to supplement the missing planar distribution data, seasonal change data, and interannual change data in the target sea area, and complete the standardization of marine environment data in the target sea area.

[0060] I. The overall model architecture of the present invention is as Figure 1 shown, and it consists of an original data processing module, an aggregated data processing module, and a benchmark data processing module.

[0061] 1. Original data processing module.

[0062] Due to the diversity of monitoring platforms and means, marine environment data are scattered among multiple departments and are not processed according to a unified technical specification, actually forming multiple heterogeneous, autonomous, and distributed data sources, resulting in difficulties in data sharing and common use. The present invention constructs a marine multi-source heterogeneous data fusion framework aiming to overcome the limitations of the spatial sparsity of a single data source. First, the target sea area is subjected to spatial grid processing. Then, according to the nearest neighbor matching principle, the geographical locations of multi-source heterogeneous data are aligned to the standard grid, and a standard grid independent variable matrix is constructed. Finally, at the same resolution grid scale, linear regression data fusion is used for the independent variable matrices from different sources to effectively integrate multi-source heterogeneous data, thereby obtaining more reliable impact factor data on an ideal spatio-temporal scale. The expression is as follows:

[0063] (1).

[0064] In the formula, represents the data sets from different sources, represents the independent variable matrix under the standard grid, represents the resolution of the sea area grid, represents the regression coefficient, represents the error term.

[0065] 2. Aggregated data processing module.

[0066] During the data collection process, it is inevitable to encounter problems such as human operation errors, instrument precision limitations, or communication transmission errors. These problems may lead to the appearance of outliers in the monitoring data. The present invention uses Chauvenet's criterion for efficient identification of outliers. This method takes into account the sample size and can give an adaptive discrimination coefficient that varies with the sample size, which makes it particularly suitable for cases where the spatial sample distribution is uneven or the sample size is small. During the process of processing the collected data, it is necessary to implement the annotation of data quality. Therefore, during the calculation of data quality evaluation indicators, the present invention comprehensively considers multiple key factors of marine environmental data in the time and space dimensions. Station Coverage (SC), Granularity Saturation (GS), and Seasonal Balance (SB) are constructed as three core criteria for measuring data quality. These indicators jointly reflect the representativeness and integrity of the original collected data on the time and space scales, providing a comprehensive evaluation framework for data quality.

[0067] First, the station coverage reflects the geographical coverage of the collected data after outlier removal in the target sea area. Specifically, spatial interpolation of the data is performed using Kriging interpolation, and the ratio of the interpolated data coverage area to the total area of the entire target sea area is calculated as the quantitative index of the station coverage. The expression is as follows:

[0068] (2).

[0069] In the formula, is the interpolated area, is the total area of the target sea area.

[0070] Secondly, the granularity saturation measures the density of monitoring stations per unit sea area. This index is determined by comparing the number of stations after outlier processing with the maximum possible number of stations, thereby reflecting the spatial distribution uniformity of the data. The expression is as follows:

[0071] (3).

[0072] In the formula, is the number of monitoring stations, are the sub-sea areas or bays of the target sea area, is the area of a certain sub-sea area or bay.

[0073] Finally, the seasonal balance focuses on the distribution balance of monitoring data in different seasons of a year. This index calculates the monitoring frequency of each season in the four seasons of the whole year and compares this frequency with the total number of times in the whole year to obtain the balance degree of the four-season monitoring. The expression is as follows:

[0074] (4).

[0075] In the formula, is the month to which the data belongs, is the season determination function, is the number of different seasons involved in the given month.

[0076] In order to realize the comprehensive evaluation of data quality, the present invention adopts a standard classification method of equal interval and quantile to divide the quality grade range of the original collected data. The data quality is divided into 5 grades, namely high, medium-high, medium, medium-low, and low, to more precisely describe the different levels of data quality, as shown in Table 1. This systematic data quality management method can ensure the scientific and reasonable distinction and use of data with different quality grades. Among them, the environmental data of high quality grade is used as the research basis to seek the plane distribution benchmark paradigm of marine ecological environment impact factors, the seasonal change benchmark paradigm of marine ecological environment impact factors, and the interannual change benchmark paradigm of marine ecological environment impact factors. However, the data below the high quality grade (medium-high, medium, medium-low, and low) need to be supplemented spatially, seasonally, and interannually based on the spatio-temporal distribution benchmark paradigm due to their poor reliability or missing data. In addition, the comprehensive quality grade of the original collected data depends on the lowest standard value among the 3 sub-indicators, thus ensuring the conservativeness and reliability of the quality control results and avoiding overestimating the comprehensive data quality due to the abnormally high value of a single indicator.

[0077] Table 1 Division of the comprehensive quality grade of the original collected data.

[0078]

[0079] 3. Benchmark data processing module.

[0080] The spatio-temporal distribution benchmark paradigm of the influencing factors of the marine ecological environment is the basis for filling in the spatio-temporal missing data in the target sea area. Therefore, it is first necessary to judge the existence of the benchmark paradigm of the influencing factors. After completing the comprehensive data quality grade assessment, the present invention selects high-quality data for spatial grid processing. According to different spatial resolutions, 5 grid division schemes for the target sea area are given (0.25°×0.25°, 0.2°×0.2°, 0.15°×0.15°, 0.1°×0.1°, 0.05°×0.05°), and the optimal gridded data is determined according to the Kappa coefficient and the relative deviation. Then, by performing a difference analysis on the optimal gridded data, the existence of the planar distribution benchmark paradigm of the influencing factors of the marine ecological environment is judged. According to the actual application requirements, the difference analysis method used is one-way analysis of variance (ANOVA). Based on this method, the difference analysis is performed on the year-on-year data of the planar distribution of the influencing factors in the target sea area in typical months (March, May, August, October), and it is preliminarily judged whether there is a certain law in the planar distribution of this factor. If the difference is too large, there is no benchmark paradigm. Specifically, if the difference P is greater than 0.05, there is a planar distribution benchmark paradigm for the influencing factors of the marine ecological environment; if the difference P is less than 0.05, there is no planar distribution benchmark paradigm for the influencing factors of the marine ecological environment, and there is no need to standardize the marine environment data in the target sea area.

[0081] Among them, determining the optimal gridded data according to the Kappa coefficient and the relative deviation includes: obtaining the environmental data of the target sea area and the Kappa coefficients and relative deviations of various target sea area grid division schemes, and according to the gap between the Kappa coefficient and the relative deviation, selecting the Kappa coefficient and relative deviation with the largest gap, and determining the corresponding target sea area grid division scheme as the optimal grid division scheme.

[0082] On the premise that the planar distribution benchmark paradigm exists, it can be proved that the influencing factors in the target sea area may have internal laws in typical months. Therefore, it is necessary to further explore the similarity of data distributions in different periods. The present invention uses hierarchical clustering analysis to group the year-on-year data of the planar distribution in typical months. In the process of hierarchical clustering analysis, the Euclidean distance measurement method and the ward sum of squared deviations clustering merger strategy are adopted. According to the "bottom-up" agglomeration method, through cyclic iteration, the data of adjacent years with higher similarity are gradually merged, and a clustering structure dendrogram is formed. The final result of the hierarchical clustering analysis will reveal which years have similar data distribution laws.

[0083] Each group after the similarity analysis can represent a planar distribution pattern. The present invention uses a radial basis function to model and express each group of data. The expression is as follows:

[0084] (5).

[0085] In the formula, represents the grouped data after similarity analysis, represents the center, is a norm operation. In the present invention, the Euclidean norm is adopted, that is, the Euclidean distance between two points is taken. To simplify the input of multiple parameters, the geographical location of the minimum value of the influencing factors in the target sea area is used as the reference coordinate, and the spatial parameters (longitude and latitude) are converted into distance parameters to construct a functional relationship with the distance as the independent variable and the concentration value of the influencing factor as the dependent variable. is the coefficient term of the model, is the form of the basis function, is the number of radial basis functions, i represents the index variable, which is used to number different radial basis functions.

[0086] Meanwhile, in order to test the uncertainty of the radial basis function expressing the benchmark paradigm of the planar distribution, the Monte Carlo method is adopted in the present invention to randomly iteratively sample the input data, and the number of sampling times is greater than 500 times. Then, the relative standard deviation (RSD) is used to characterize the uncertainty caused by the model parameters.

[0087] After completing the benchmarking process of the planar distribution data, the annual data with a seasonal balance degree reaching 100% is selected to establish the benchmark paradigm of the seasonal variation of the marine ecological environment influencing factors. Over the years, there are mainly two main distribution patterns of high-quality seasonal variation data: "U" - shaped and non - "U" - shaped. For the data showing a "U" - shaped distribution, the present invention uses an exponential function for modeling expression. The expression is as follows:

[0088] (6).

[0089] In the formula, is the intercept, which controls the position of the curve on the x - axis; is the coefficient of the first - order term, which controls the slope of the curve; is the coefficient of the second - order term, which controls the degree of curvature of the curve, x is the independent variable, representing different months.

[0090] For the data showing a non - "U" - shaped distribution, the present invention first calculates the difference between it and the typical "U" - shaped distribution data. Subsequently, a sine function is used to model the difference to quantify and express the potential influence of external conditions such as rainfall on the seasonal variation of the influencing factors. Finally, the benchmark paradigm of the seasonal variation of the non - "U" - shaped distribution data can be expressed as the difference between the typical "U" - shaped distribution data and the seasonal variation adjustment value The expression is as follows:

[0091] (7).

[0092] In the formula, is the amplitude, which controls the peak value of the sine wave; is the phase, which controls the horizontal translation of the sine wave; is the vertical translation, which controls the vertical offset of the sine wave. x is the independent variable, representing different months.

[0093] Finally, the present invention integrates the seasonal change reference paradigm of each year to obtain the annual average concentration value of the influencing factors, and uses the Fourier series equation to model and express the interannual change reference paradigm of the marine ecological environment influencing factors. The expression is as follows:

[0094] (8).

[0095] In the formula, the constant term represents the average value of the data over the entire time range, and it can be used to describe the overall offset of the data; the frequency parameter represents the period of each filter. The larger , the shorter the period, and the higher the periodicity of the curve on the abscissa; represents the harmonic order. Here takes 1 and 2, corresponding to the first harmonic and the second harmonic respectively; the cosine term and the sine term x represent the amplitudes of the cosine wave and sine wave of different frequencies in the data.

[0096] 4. Filling in the missing spatio-temporal data.

[0097] After passing through the original data processing module, the aggregated data processing module, and the reference data processing module, the spatio-temporal distribution reference paradigm of the influencing factors in the target sea area can be obtained. Based on the reference paradigm, the spatio-temporal data below high quality can be filled in. Among them, when filling in the planar distribution data below high quality, the key issue lies in determining the applicable planar distribution reference paradigm. Therefore, the present invention adopts a data-driven paradigm determination method, that is, uses a backpropagation neural network to optimize the process of filling in the planar distribution data. On the basis of the optimal grid division, we construct a parallel BP neural network architecture, as shown in Figure 2As shown in the figure, the BPNN is iteratively trained using high-quality planar distribution data to enable it to match the optimal planar distribution benchmark paradigm for new incoming data. According to the selected planar distribution benchmark paradigm, the standardization of the spatial distribution data to be filled is achieved through spatial fitting. And the reliability of the filled data is tested using the kappa coefficient and relative standard deviation. When filling in the data of seasonal changes below high quality, based on the existing monthly data and combined with the minimum deviation method, the applicable seasonal change benchmark paradigm is first determined. Then, according to the selected seasonal change benchmark paradigm, the standardization of the seasonal change data to be filled is achieved through time series fitting. And the relative deviation is used to test the reliability of the seasonal filling result. Finally, after benchmarking the planar distribution and seasonal change data, the missing interannual change data can be directly filled based on the fitting curve of the interannual change benchmark paradigm.

[0098] When filling in the spatial distribution data, first determine the applicable planar distribution benchmark paradigm for the data to be filled based on the backpropagation neural network. The determined planar distribution benchmark paradigm can reflect the distribution law of influencing factors in different spatial positions within the target sea area. Then, according to the selected planar distribution benchmark paradigm, the standardization of the spatial data to be filled is achieved through spatial fitting. When filling in the seasonal change data, based on the existing monthly data and combined with the minimum deviation method, first determine the applicable seasonal change benchmark paradigm. The determined seasonal change benchmark paradigm can reflect the change pattern of influencing factors in different seasons within the target sea area. Then, according to the selected seasonal change benchmark paradigm, the standardization of the seasonal data to be filled is achieved through time series fitting. When filling in the interannual change data, the interannual change benchmark paradigm can reflect the long-term change trend of influencing factors in different years within the target sea area. Therefore, the standardization of the interannual data to be filled can be directly achieved based on the fitting curve of the interannual change benchmark paradigm.

[0099] Second, the key part of the marine environmental data standardization method proposed in the present invention lies in:

[0100] 1. The present invention fuses and performs outlier tests on multi-source heterogeneous data in the marine environment, comprehensively considers multiple key factors of the monitoring data in the target sea area in terms of time and space dimensions, and constructs three data quality control indicators: station coverage, grain size saturation, and seasonal balance. Based on high-quality data, statistical methods are used to summarize the regularities shown by the influencing factors in the target sea area in terms of planar distribution, seasonal change, and interannual change, and they are respectively modeled and expressed in the form of mathematical equations to construct the spatio-temporal distribution benchmark paradigm of the influencing factors in the target sea area. This can not only elaborate the main change laws of the influencing factors on the marine spatio-temporal scale but also lay a foundation for the filling work of spatio-temporal missing data below high quality.

[0101] 2. In the process of filling in the plane distribution data of elements below high quality in the target sea area, the standardization process of the missing plane distribution data to be filled in is optimized by constructing a backpropagation neural network. Using the constructed data quality control indicators, the high-quality data of influencing elements are filtered and screened according to the minimum value principle. Then, the high-quality plane distribution data is used as the training set to iteratively train the backpropagation neural network, enabling it to have the ability to match the most suitable plane distribution benchmark paradigm for newly incoming data. Furthermore, based on the most suitable plane distribution benchmark paradigm, the plane distribution data below high quality is filled in by means of spatial fitting. For the missing seasonal change data below high quality, based on the existing monthly data and combined with the minimum deviation method, the missing seasonal change data to be filled in is filled in by means of time series fitting. After the benchmarking of the plane distribution data and seasonal change data of influencing elements is completed, the missing interannual change data can be directly filled in based on the fitting curve of the interannual change benchmark paradigm. This progressive spatio-temporal missing data standardization method can ultimately effectively improve and unify the spatio-temporal granularity of influencing elements in the target sea area in terms of plane distribution, seasonal change, and interannual change.

[0102] III. The advantages of the present invention are as follows:

[0103] Marine environmental data usually has certain variation laws in the time and space dimensions. However, due to the limitations of monitoring conditions, relevant data often shows problems such as limited spatial coverage and monthly frequency, serious data loss in some sea areas, and inconsistent spatio-temporal granularity of existing monitoring data. Therefore, the standardization of marine environmental data is crucial for aspects such as the simulation, evaluation, and prevention and control plan formulation of the eutrophication state in coastal waters. The present invention comprehensively considers multiple key factors in the time and space dimensions of marine environmental data, constructs three data quality control sub-indicators, namely station coverage, granularity saturation, and seasonal balance, providing a comprehensive evaluation framework for the data quality of elements in the target sea area. Then, based on high-quality data, the spatio-temporal distribution benchmark paradigm of elements in the target sea area is summarized. This benchmark paradigm provides a clear mathematical equation description of the spatio-temporal distribution characteristics of influencing elements in the target sea area and has high reliability. In addition, when the missing plane distribution data or time series change missing data of influencing elements in the target sea area is input, based on the corresponding benchmark paradigm and combined with a backpropagation neural network, the filling work of marine environmental data can be effectively completed, improving the spatial and time series coverage range of influencing elements in the target sea area and realizing the standardization of marine environmental data in the target sea area. As Figure 3 shown in the flowchart of the present invention.

[0104] An embodiment of the present invention provides a standardization system for marine environmental data, including:

[0105] A data acquisition module, which is used to screen the environmental data of the target sea area and perform gridification by using the station coverage rate reflecting the aggregated data excluding outliers in the geographical coverage range of the target sea area, the granularity saturation rate measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the distribution balance of monitoring data in different seasons within a year.

[0106] A planar distribution benchmark paradigm construction module, which is used to perform similarity grouping on the gridified data by using the hierarchical clustering analysis method, and perform modeling on each group of data by using the radial basis function to obtain the planar distribution benchmark paradigm of the marine ecological environment impact factors.

[0107] A seasonal change benchmark paradigm construction module, which is used to select the environmental data corresponding to the years when the seasonal balance degree reaches the set threshold; determine the corresponding seasonal change benchmark paradigm of the marine ecological environment impact factors according to the distribution pattern of the selected environmental data.

[0108] An inter-annual change benchmark paradigm construction module, which is used to obtain the seasonal change benchmarked data of each year by using the seasonal change benchmark paradigm of the marine ecological environment impact factors; perform modeling by using the Fourier series equation according to the seasonal change benchmarked data to obtain the inter-annual change benchmark paradigm of the marine ecological environment impact factors.

[0109] A marine environmental data standardization module, which is used to complete the standardization of marine environmental data in the target sea area by using the planar distribution benchmark paradigm of the marine ecological environment impact factors, the seasonal change benchmark paradigm of the marine ecological environment impact factors, and the inter-annual change benchmark paradigm of the marine ecological environment impact factors to fill in the missing planar distribution data, seasonal change data, and inter-annual change data in the target sea area respectively.

[0110] A specific embodiment is as follows:

[0111] This embodiment discloses a method for standardizing marine environmental data, and the specific steps are as follows:

[0112] S1. Evaluate the quality of the ecological environment data in a certain sea area.

[0113] Monitoring stations for marine environmental data are usually unevenly distributed in space. Most monitoring stations are distributed in the coastal waters according to administrative divisions, while there are much fewer monitoring stations in the central sea area. The calculation results using formulas (2)-(4) show that there is a certain similarity among the quality control sub-indicators of marine environmental data over the years, all showing a trend of fluctuating in the early stage (from the early 1980s to the early 1990s), rising in the middle stage (from the mid-1990s to the mid-2000s), and stabilizing in the late stage (from the late 2000s to the early 2020s). High-quality data of influencing factors are filtered and selected according to the minimum value principle. Among them, the proportion of data below low quality is as high as 51.66% (DIN) and 57.82% (PO4-P), while the proportion of data above medium and high quality is only 25.17% (DIN) and 23.13% (PO4-P). Therefore, the proportion of low-quality marine environmental data is generally high, and it is urgent to standardize marine environmental data.

[0114] S2. Standardization of ecological environment data in a certain sea area.

[0115] Select high-quality planar distribution data of marine environment in spring, summer, autumn, and winter, and apply the methods of difference analysis and similarity analysis in turn to judge and analyze the planar distribution law of elements in the target sea area. According to the results of difference analysis, the P-values of the planar distribution data in the four seasons are all greater than 0.05, indicating low differences, which shows that the spatial distribution of marine environmental data has seasonal stability and may follow a certain planar distribution pattern. According to the results of similarity analysis, the decadal spatial distribution of influencing factors has obvious clustering characteristics. Among them, the early data in the 1980s have similar planar distribution laws, the mid-term data in the 1990s have similar planar distribution laws, and the recent data in the early 21st century have similar planar distribution laws. Based on this similarity grouping, use formula (5) to construct the benchmark paradigm of the planar distribution of influencing factors, and complete the standardization of planar distribution data in combination with the backpropagation neural network. The relative standard deviations of the standardized data of DIN and PO4-P are 35.62% and 58.44% respectively, and the kappa coefficients are 0.75 and 0.83 respectively, indicating high reliability. Then, use formulas (6)-(7) to construct the benchmark paradigm of the seasonal variation of influencing factors, and complete the standardization of seasonal variation data based on the self-small deviation method. The relative deviations of the standardized data of DIN and PO4-P are 24.39% and 18.81% respectively. Finally, use formula (8) to construct the benchmark paradigm of the interannual variation of influencing factors and complete the standardization of interannual variation data, and the results are as Figure 4 and Figure 5 shown.

[0116] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for standardizing marine environmental data, characterized in that It includes the following steps: Using the station coverage rate reflecting the aggregated data excluding outliers in the geographical coverage of the target sea area, the grain saturation rate measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the balance of distribution of monitoring data in different seasons within a year, screen the environmental data of the target sea area and perform gridification; Use the hierarchical clustering analysis method to group the gridified data by similarity, and use the radial basis function to model each group of data to obtain the plane distribution reference paradigm of the marine ecological environment impact factors; Select the environmental data corresponding to the year when the seasonal balance degree reaches the set threshold; according to the distribution pattern of the selected environmental data, determine the corresponding seasonal change reference paradigm of the marine ecological environment impact factors; Use the seasonal change reference paradigm of the marine ecological environment impact factors to obtain the seasonal change benchmark data for each year; according to the seasonal change benchmark data, use the Fourier series equation to model and obtain the interannual change reference paradigm of the marine ecological environment impact factors; Use the plane distribution reference paradigm of the marine ecological environment impact factors, the seasonal change reference paradigm of the marine ecological environment impact factors, and the interannual change reference paradigm of the marine ecological environment impact factors to fill in the missing plane distribution data, seasonal change data, and interannual change data of the target sea area respectively, and complete the standardization of the marine environmental data in the target sea area.

2. The standardization method for marine environmental data according to claim 1, characterized in that, The specific steps of screening the environmental data of the target sea area include: Based on the environmental data of the target sea area, use the station coverage rate, the grain saturation rate, and the seasonal balance degree as the core criteria for measuring the quality of environmental data; According to the environmental data screened by each core criterion, use the standard classification method of equal interval and quantile to divide the environmental data into different levels of high, medium-high, medium, medium-low, and low according to data quality; Take the high-quality environmental data as the environmental data of the screened target sea area.

3. The standardization method of marine environmental data according to claim 2, characterized in that, The specific steps of performing gridification include: Design 5 grid division schemes for the target sea area according to the high-quality environmental data at different spatial resolutions. The grid division schemes include: 0.25°×0.25°, 0.2°×0.2°, 0.15°×0.15°, 0.1°×0.1°, and 0.05°×0.05°; Use the Kappa coefficient and relative deviation to select the optimal grid division scheme from the 5 grid division schemes for the target sea area.

4. The standardization method for marine environmental data according to claim 3, characterized in that, Before using the hierarchical clustering analysis method to group the gridified data by similarity, it also includes: According to the optimal gridified data corresponding to the optimal grid division scheme, select the plane distribution year-on-year data of the impact factors in the target sea area in different months for one-way ANOVA; If the difference P is greater than 0.05, it is determined that there is a plane distribution reference paradigm of the marine ecological environment impact factors.

5. The standardization method for marine environmental data according to claim 3, wherein The specific steps of using the hierarchical clustering analysis method to group the gridified data by similarity include: In the process of hierarchical clustering analysis, adopt the Euclidean distance measurement method and the ward sum of squared deviations clustering merging strategy, and in the "bottom-up" agglomeration method, gradually merge the data through cyclic iteration and form a clustering structure dendrogram; Obtain the data with similarity in the optimal gridded data corresponding to the optimal grid division scheme according to the clustering structure dendrogram, and group the data with similarity.

6. The standardization method of marine environmental data according to claim 1, characterized in that, The steps for obtaining the planar distribution reference paradigm of marine ecological environment impact factors specifically include: Each group of data after similarity grouping represents a planar distribution pattern. Use radial basis functions to model each group of data to obtain the planar distribution reference paradigm of marine ecological environment impact factors. The formula is: ； Among them, represents the grouped data after similarity analysis, represents the center, is the coefficient term of the model, is the form of the basis function, is the number of radial basis functions, i represents the index variable used to number different radial basis functions.

7. The standardization method for marine environmental data according to claim 1, characterized in that, According to the selected distribution pattern of environmental data, determine the corresponding seasonal change reference paradigm of marine ecological environment impact factors. The specific steps include: Select the environmental data of the year with a seasonal balance degree reaching 100%. The environmental data has "U"-shaped and non-"U"-shaped distribution patterns; For the data with a "U"-shaped distribution pattern, use an exponential function for modeling to obtain the seasonal change reference paradigm of marine ecological environment impact factors. The formula is: ； Among them, is the intercept, controlling the position of the curve on the x-axis; is the coefficient of the first-order term, controlling the slope of the curve; is the coefficient of the second-order term, controlling the degree of curvature of the curve, x is the month; For the data with a non-"U"-shaped distribution pattern, obtain the difference between the data with a non-"U"-shaped distribution pattern and the data with a "U"-shaped distribution pattern, and use a sine function to model the difference; ； Among them, is the amplitude, which controls the peak value of the sine wave; is the phase, which controls the horizontal translation of the sine wave; is the vertical translation, which controls the vertical offset of the sine wave.

8. The standardization method for marine environmental data according to claim 1, characterized in that The formula for the interannual change reference paradigm of marine ecological environment impact factors is: ； Among them, the constant term represents the average value of the data over the entire time range and is used to describe the overall offset of the data; the frequency parameter represents the period of each filter, the larger it is, the shorter the period, and the higher the periodicity of the curve on the abscissa; represents the harmonic order, taking 1 and 2, corresponding to the fundamental harmonic and the second harmonic respectively; the cosine term and the sine term represent the amplitudes of the cosine wave and the sine wave of different frequencies in the data, x represents the year.

9. A standardization system for marine environmental data, characterized in that, It includes: A data acquisition module, which is used to screen the environmental data of the target sea area and grid it by using the station coverage rate reflecting the collection data excluding outliers in the geographical coverage range of the target sea area, the granularity saturation rate measuring the density of monitoring stations per unit sea area, and the seasonal balance degree reflecting the distribution balance of monitoring data in different seasons within a year; A planar distribution reference paradigm construction module, which is used to group the gridded data by similarity using hierarchical clustering analysis, and use radial basis functions to model each group of data to obtain the planar distribution reference paradigm of marine ecological environment impact factors; A seasonal change reference paradigm construction module, which is used to select the environmental data corresponding to the year with a seasonal balance degree reaching the set threshold; according to the selected distribution pattern of environmental data, determine the corresponding seasonal change reference paradigm of marine ecological environment impact factors; An interannual change reference paradigm construction module, which is used to obtain the seasonal change benchmarked data for each year by using the seasonal change reference paradigm of marine ecological environment impact factors; according to the seasonal change benchmarked data, use the Fourier series equation for modeling to obtain the interannual change reference paradigm of marine ecological environment impact factors; A marine environmental data standardization module, which is used to complete the standardization of marine environmental data in the target sea area by using the planar distribution reference paradigm of marine ecological environment impact factors, the seasonal change reference paradigm of marine ecological environment impact factors, and the interannual change reference paradigm of marine ecological environment impact factors to fill in the missing planar distribution data, seasonal change data, and interannual change data in the target sea area respectively.

Images