Marine Environment Risk Assessment Method and System Based on Multi-Source Data Fusion

Abstract

The present invention relates to the technical field of environmental management, specifically a method and system for marine environmental risk assessment based on multi-source data fusion, including the following steps: Based on multi-source marine environmental monitoring data, evaluate the data integrity, consistency, and timeliness of multiple data sources, calculate the effectiveness scores of multiple data sources, and adjust the contribution ratio of the target data source to generate a multi-source data fusion model. In the present invention, by analyzing the effectiveness of multiple data sources, the adjustment of data source contributions is realized, the dynamic adaptability and flexibility of data fusion are optimized, the accuracy and timeliness of marine environmental risk assessment are improved, the detection and identification of abnormal data of multiple environmental indicators are realized by combining the analysis of water quality-related indicators and temperature data, and by analyzing marine development activity events, a decision-making basis is provided for the adjustment of marine management policies. Combining the prediction of marine biodiversity, the accurate assessment of marine environmental risks is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental management, and particularly to a method and system for marine environmental risk assessment based on multi-source data fusion. Background Art

[0002] The technical field of environmental management aims to predict, monitor, evaluate, and mitigate the impact of environmental problems on the ecosystem and human society through various scientific and technological means, including resource management, pollution control, environmental quality monitoring, ecological protection, disaster prevention and response. By combining big data analysis, environmental simulation prediction, and risk assessment methods, the integration of information technology and environmental science can improve the efficiency and accuracy of environmental management, and promote decision-making support for sustainable development and environmental protection.

[0003] Among them, the marine environmental risk assessment method focuses on identifying and evaluating potential risks in the marine environment, including risk factor identification, risk source assessment, and risk propagation path analysis in the marine ecosystem. By collecting marine environmental data, including water quality, biological community status, and chemical substance concentration, using data fusion technology, through analyzing the collected environmental sample data and comparing with historical data, the severity and possible impact range of various risks are determined, the risk level of the impact of multiple risk factors on the marine ecosystem is evaluated, and the risk factors are quantified to provide a scientific basis for environmental management and policy-making.

[0004] Traditional marine environmental risk assessment methods are often limited by data fragmentation and processing lag in actual operation, relying on a single data source, which restricts the depth and breadth of data analysis, resulting in errors or untimely environmental risk assessment results, making it difficult to accurately capture complex environmental change trends and potential risk points, leading to inaccurate assessment results and affecting the effectiveness of decision-making. The efficiency and accuracy in processing batch and complex data still need to be improved, which is particularly crucial in the rapidly changing marine environment because data timeliness directly affects the timeliness and effectiveness of environmental emergency response. Summary of the Invention

[0005] In order to solve the technical problem that it is difficult to perform fusion processing on multiple data sources in the prior art, the embodiments of the present invention provide a method and system for marine environmental risk assessment based on multi-source data fusion. The technical solutions are as follows:

[0006] On the one hand, a method for marine environmental risk assessment based on multi-source data fusion is provided, and the method includes:

[0007] S1: Based on multi-source marine environmental monitoring data, evaluate the data integrity, consistency, and timeliness of multiple data sources, calculate the efficacy scores of multiple data sources, and adjust the contribution ratio of the target data source to generate a multi-source data fusion model;

[0008] S2: Using the multi-source data fusion model, extract, analyze, and trend analyze and pattern recognize various index data related to water quality, detect and record the outliers of various indexes, and generate marine water quality status information;

[0009] S3: Based on the marine water quality status information, extract and analyze the temperature data of the marine environment, including water temperature and air temperature, analyze the change trend of the marine temperature, detect and identify abnormal fluctuations, and generate a temperature anomaly event record;

[0010] S4: Based on the temperature anomaly event record, analyze multiple marine development activity events, including oil and gas exploitation and coastline changes, evaluate the impact of development activities on the marine environment, and generate development activity impact information;

[0011] S5: According to the development activity impact information, by analyzing the impact of various influencing factors on marine environment indicators, predict the impact of various influencing factors on marine biodiversity, combine the outliers of various indexes, calculate the marine environment risk score, and generate real-time risk assessment information.

[0012] As a further solution of the present invention, the multi-source data fusion model is specifically an effectiveness score list, a data source contribution ratio adjustment record, and a data fusion result. The marine water quality status information includes a water quality trend analysis result, a water quality pattern recognition information, and a water quality outlier record. The temperature anomaly event record specifically refers to water temperature change trend information, air temperature change trend information, and temperature anomaly fluctuation recognition result. The development activity impact information includes development activity type information, development activity impact assessment result, and development activity risk index. The real-time risk assessment information is specifically an influencing factor correlation diagram, a biodiversity impact prediction result, and an environmental risk score.

[0013] As a further solution of the present invention, based on multi-source marine environment monitoring data, by evaluating the data integrity, consistency, and timeliness of multiple data sources, calculating the effectiveness scores of multiple data sources and adjusting the contribution ratio of the target data source, the steps of generating a multi-source data fusion model are specifically as follows:

[0014] S101: Based on multi-source marine environment monitoring data, perform integrity analysis on the data of multiple data sources, including satellite remote sensing, buoy monitoring, and vessel collection, mark missing data and timestamp errors, and generate a data inspection result;

[0015] S102: Based on the data inspection result, evaluate the consistency and timeliness of the data from multiple sources, calculate the effectiveness scores for multiple data sources, and generate a data source effectiveness score table;

[0016] S103: Based on the data source performance score table, match contribution ratios for multiple data sources according to the performance scores, and construct a multi-source data fusion model.

[0017] As a further solution of the present invention, the specific formula for calculating the performance score for multiple data sources is:

[0018] ;

[0019] where represents the performance score of the th data source, is the weight coefficient of data integrity, is the number of known data points of the th data source, is the total number of data points that the th data source should have theoretically, is the weight coefficient of data consistency, is the number of data points that are consistent between the th data source and other data sources within the same time window, is the total number of data points for consistency comparison of the th data source, is the weight coefficient of data timeliness, is the average data latency of the th data source, represents the index of the data source.

[0020] As a further solution of the present invention, using the multi-source data fusion model, the steps of extracting and analyzing various index data related to water quality, performing trend analysis and pattern recognition on various indexes, detecting and recording outliers of various indexes, and generating marine water quality status information are specifically as follows:

[0021] S201: Based on the multi-source data fusion model, extract various index data related to water quality, including microplastic content, salinity, and dissolved oxygen, and generate a water quality information extraction record;

[0022] S202: Based on the water quality information extraction record, combine with time information, identify the change trends and periodic patterns of multiple water quality indexes, and generate a water quality trend analysis result;

[0023] S203: Based on the water quality trend analysis result, detect and record outliers in multiple index data in real time, and generate marine water quality status information.

[0024] As a further solution of the present invention, based on the marine water quality status information, the steps of extracting and analyzing the temperature data of the marine environment, including water temperature and air temperature, analyzing the changing trend of the marine temperature, detecting and identifying abnormal fluctuations, and generating a temperature anomaly event record are specifically as follows:

[0025] S301: Based on the marine water quality status information, extract the marine temperature data, including water temperature and air temperature information, and generate a temperature data set;

[0026] S302: Based on the temperature data set, by analyzing and predicting the changing trend of the marine temperature data, monitor and record abnormal data points, and generate a temperature anomaly analysis result;

[0027] S303: Based on the temperature anomaly analysis result, by analyzing the amplitude and duration of the fluctuations of multiple abnormal data points, calculate the anomaly degree and mark the abnormal temperature event, and generate a temperature anomaly event record.

[0028] As a further solution of the present invention, based on the temperature anomaly event record, the steps of analyzing multiple marine development activity events, including oil and gas extraction and coastline changes, evaluating the impact of the development activities on the marine environment, and generating development activity impact information are specifically as follows:

[0029] S401: Based on the temperature anomaly event record, extract various information related to the marine development activity events, including the time and geographical location information of the development, and generate a development activity data set;

[0030] S402: Using the development activity data set, combined with the water quality and temperature information of the target location, evaluate the impact of multiple development events on the marine environment, identify and mark the scope of the affected area, including oil and gas extraction and coastline changes, and generate an activity impact analysis result;

[0031] S403: Based on the activity impact analysis result, considering the duration and intensity of the development activities, analyze the impact of multiple development activities on the marine environment, mark the risky development activities, and generate development activity impact information.

[0032] As a further solution of the present invention, according to the development activity impact information, the steps of predicting the impact of various influencing factors on marine biodiversity by analyzing the impact of various influencing factors on marine environment indicators, combining the abnormal values of multiple indicators, calculating the marine environment risk score, and generating real-time risk assessment information are specifically as follows:

[0033] S501: According to the development activity impact information, analyze the impact of various influencing factors on marine environment indicators and quantify the impact degree coefficient, including pollution emissions, human development activities, and meteorological factors, and generate an influencing factor weight list;

[0034] S502: Based on the list of influence factor weights, predict the degree of influence of various influence factors on marine biodiversity according to the influence of various influence factors on marine environmental indicators, and form biodiversity indicators.

[0035] S503: Based on the biodiversity indicators, combined with the outliers of various marine environmental indicators, calculate the marine environmental risk scores of multiple regions, and generate real-time risk assessment information.

[0036] As a further solution of the present invention, the specific formula for calculating the marine environmental risk scores of multiple regions is:

[0037] ;

[0038] Wherein, represents the risk score of the marine environment, is the number of indicators participating in the calculation, is the th weight coefficient of the indicator, is the th outlier of the indicator, is the th anomaly detection threshold of the indicator, represents the total number of indicators involved in the risk score calculation, is the index of the indicator.

[0039] On the other hand, a marine environmental risk assessment system based on multi-source data fusion is provided. This system is applied to the marine environmental risk assessment method based on multi-source data fusion. The system includes:

[0040] The data source processing module, based on multi-source marine environmental monitoring data, adjusts the contribution ratio of the data sources by evaluating the integrity, consistency, and timeliness of the data from multiple data sources, and generates a multi-source data fusion model.

[0041] The water quality index analysis module, based on the multi-source data fusion model, extracts various key water quality indicators, including microplastic content, salinity, and dissolved oxygen. Through time series analysis, it identifies the change trend patterns of various indicators and detects the outliers in various indicators, and generates marine water quality status information.

[0042] The real-time temperature monitoring module, based on the marine water quality status information, extracts water temperature and air temperature data and conducts trend analysis, detects and identifies the abnormal fluctuations in the temperature data, and generates temperature anomaly event records.

[0043] The marine activity analysis module, based on the temperature anomaly event records, analyzes the impact of marine development activities on the marine environment, evaluates the environmental sensitivity of various activities, and generates development activity impact information.

[0044] The environmental risk analysis module predicts the impacts of various influencing factors on marine biodiversity based on the development activity impact information, calculates the marine environmental risk score by combining real-time marine environmental monitoring data, and generates real-time risk assessment information.

[0045] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0046] By analyzing the effectiveness of multiple data sources, the adjustment of data source contributions is realized, the dynamic adaptability and flexibility of data fusion are optimized, the accuracy and timeliness of marine environmental risk assessment are improved. By combining the analysis of water quality-related indicators and temperature data, the detection and identification of abnormal data of various environmental indicators are realized. Through the analysis of marine development activity events, a decision-making basis is provided for the adjustment of marine management policies. By combining the prediction of marine biodiversity, the accurate assessment of marine environmental risks is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0048] Figure 1 It is a schematic diagram of the working process of the present invention;

[0049] Figure 2 It is a detailed flowchart of S1 of the present invention;

[0050] Figure 3 It is a detailed flowchart of S2 of the present invention;

[0051] Figure 4 It is a detailed flowchart of S3 of the present invention;

[0052] Figure 5 It is a detailed flowchart of S4 of the present invention;

[0053] Figure 6 It is a detailed flowchart of S5 of the present invention;

[0054] Figure 7 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] The following will describe the technical solutions in the present invention with reference to the drawings.

[0056] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to give examples, illustrations or explanations. Any embodiment or design solution described as an "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of the word "example" is intended to present concepts in a specific manner. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0057] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same. "Of", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meanings they express are the same.

[0058] In the embodiments of the present invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0059] To make the technical problems to be solved, technical solutions and advantages of the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0060] The embodiments of the present invention provide a method for marine environmental risk assessment based on multi-source data fusion, such as Figure 1 The flowchart of the method for marine environmental risk assessment based on multi-source data fusion shown, the processing flow of the method may include the following steps:

[0061] S1: Based on multi-source marine environmental monitoring data, evaluate the data integrity, consistency and timeliness of multiple data sources, calculate the effectiveness scores of multiple data sources and adjust the contribution ratio of the target data source to generate a multi-source data fusion model;

[0062] S2: Use the multi-source data fusion model to extract, analyze and trend analyze and pattern recognize multiple index data related to water quality, detect and record the outliers of multiple indexes to generate marine water quality status information;

[0063] S3: Based on the marine water quality status information, extract and analyze the temperature data of the marine environment, including water temperature and air temperature, analyze the change trend of the marine temperature, detect and identify abnormal fluctuations to generate a temperature anomaly event record;

[0064] S4: Based on the temperature anomaly event record, analyze multiple marine development activity events, including oil and gas exploitation and coastline change, evaluate the impact of development activities on the marine environment to generate development activity impact information;

[0065] S5: Based on the information on the impacts of development activities, by analyzing the impacts of various influencing factors on marine environmental indicators, predicting the impacts of various influencing factors on marine biodiversity, and combining the outliers of various indicators, calculate the marine environmental risk score and generate real-time risk assessment information.

[0066] The multi-source data fusion model specifically includes an effectiveness score list, a record of adjusted contribution ratios of data sources, and data fusion results. The marine water quality status information includes water quality trend analysis results, water quality pattern recognition information, and water quality outlier records. The temperature anomaly event record specifically refers to water temperature change trend information, air temperature change trend information, and temperature anomaly fluctuation recognition results. The information on the impacts of development activities includes development activity type information, development activity impact assessment results, and development activity risk indices. The real-time risk assessment information specifically includes a diagram of the interrelationships between influencing factors, prediction results of biodiversity impacts, and environmental risk scores.

[0067] Please refer to Figure 2 , based on multi-source marine environmental monitoring data, by evaluating the data integrity, consistency, and timeliness of multiple data sources, calculating the effectiveness scores of multiple data sources and adjusting the contribution ratios of target data sources, the steps for generating the multi-source data fusion model are specifically as follows:

[0068] S101: Based on multi-source marine environmental monitoring data, conduct an integrity analysis of the data from multiple data sources, including satellite remote sensing, buoy monitoring, and vessel collection, mark missing data and timestamp errors, and generate data inspection results;

[0069] Review the information provided by each data source, verify the timestamps for each dataset, identify and mark timestamp anomalies caused by synchronization errors or data transmission delays, check data integrity, and determine the specific locations and frequencies of missing data through a threshold setting method. For satellite remote sensing data, analyze its coverage and resolution. For buoy monitoring data, focus on checking for sensor failures or data interruptions. For vessel collection data, verify the continuity and integrity of data collection. The process is carried out using a data quality assessment model, which relies on statistical analysis methods such as standard deviation and mean calculation to identify outliers or data quality issues in the dataset. The process ensures that each data point is verified and calibrated, improving the accuracy and reliability of data analysis. The generated data inspection results include an integrity report for each data source and a timestamp correction record.

[0070] S102: Based on the data inspection results, evaluate the consistency and timeliness of data from multiple sources, calculate effectiveness scores for multiple data sources, and generate a data source effectiveness score table;

[0071] The specific formula for calculating the effectiveness scores for multiple data sources is:

[0072] ;

[0073] Among them, represents the performance score of the th data source, is the weight coefficient of data integrity, is the th number of known data points of the data source, is the total number of data points that the th data source should have in theory, is the weight coefficient of data consistency, is the th number of data points that are consistent between the th data source and other data sources within the same time window, is the total number of data points for consistency comparison of the th data source, is the weight coefficient of data timeliness, is the average data latency time of the th data source,

[0074] Formula:

[0075] ;

[0076] Detailed explanation of the formula and the derivation process of formula calculation:

[0077] The formula is used to evaluate the comprehensive performance of the data source, and the performance score is used to adjust the contribution ratio of each data source to data fusion;

[0078] Meaning and setting values of parameters:

[0079] , , are weight coefficients. Assume , , ;

[0080] is the number of known data points of the data source , assumed to be 800;

[0081] is the total number of data points in theory, assumed to be 1000;

[0082] is the number of data points that are consistent between the data source and other data sources within the same time window, assumed to be 600;

[0083] is the total number of data points for consistency comparison, assumed to be 700;

[0084] is the data source 's average data latency time, assumed to be 2 hours;

[0085] Substitute the parameters into the formula for calculation:

[0086] Calculate the data integrity score:

[0087] ;

[0088] Calculate the data consistency score:

[0089] ;

[0090] Calculate the data timeliness score:

[0091] ;

[0092] Calculate the performance score:

[0093] ;

[0094] The result 0.6336 indicates a relatively high comprehensive performance score for the target data source, reflecting the good overall performance of the data source in terms of integrity, consistency, and timeliness. The score helps determine the weights and usage priorities of multiple data sources during the data fusion process.

[0095] S103: Based on the data source performance score table, match the contribution ratios for multiple data sources according to the performance scores to construct a multi-source data fusion model;

[0096] Apply the linear weighting method to adjust the weight coefficients according to the performance scores, where data sources with high performance obtain higher weights, ensuring that the result of data fusion can reflect the most reliable and up-to-date environmental information. Use the weighted average method to integrate each data source, ensuring that high-performance data dominates in the model, and data with lower performance reduces its influence accordingly. The algorithm combines multiple scoring metrics, including the timeliness of data updates, historical accuracy, and coverage. The multi-source data fusion model constructed by this method improves the efficiency of data processing, enhances the accuracy and credibility of model prediction, and provides a comprehensive risk assessment tool for decision-makers.

[0097] Please refer to Figure 3 , using the multi-source data fusion model, the steps of extracting, analyzing, and detecting various indicator data related to water quality, performing trend analysis and pattern recognition on various indicators, detecting and recording outliers of various indicators, and generating marine water quality status information are as follows:

[0098] S201: Based on the multi-source data fusion model, extract various index data related to water quality, including microplastic content, salinity, and dissolved oxygen, and generate a water quality information extraction record;

[0099] Obtain the latest records of various indicators from the integrated dataset through the set data interface. Each indicator data has undergone preliminary preprocessing and quality control to ensure its accuracy and reliability. For each indicator, apply quantitative analysis methods for precise extraction to ensure that the obtained data can accurately reflect the current water body state. The quantitative analysis methods adopted in the process include linear interpolation method and moving average method to handle possible data discontinuities or missing situations. Automatically adjust the data extraction time window according to the real-time data update frequency of environmental changes to adapt to the dynamics of environmental monitoring and effectively provide real-time water quality information. The generated water quality information extraction record contains real-time data of various indicators, time tags for data acquisition, and source markers, providing basic data for subsequent water quality trend analysis and anomaly monitoring.

[0100] S202: Based on the water quality information extraction record and combined with time information, identify the change trends and periodic patterns of multiple water quality indicators, and generate water quality trend analysis results;

[0101] Use time series analysis methods, such as autoregressive moving average model, to analyze the change laws of each water quality indicator over time, identify the long-term trends, seasonal fluctuations, and sudden events of indicators such as microplastic content, salinity, and dissolved oxygen. Conduct periodic analysis on the data of each indicator to determine the main driving factors of its changes, such as weather conditions, seasonal changes, or human activities. Mark and analyze abnormal data points to track potential environmental problems or equipment failures. The generated water quality trend analysis results provide a scientific basis for environmental management decisions.

[0102] S203: Based on the water quality trend analysis results, real-time detect and record the abnormal points in the multiple indicator data, and generate marine water quality status information;

[0103] In the S203 sub-step, based on the obtained water quality trend analysis results, the system uses an anomaly detection algorithm to real-time monitor and record the abnormal points in the data. Determine the normal fluctuation range of each water quality indicator through trend analysis, and use the statistical threshold method. Through the formula: , identify the data points that exceed the normal range and mark them as abnormal;

[0104] Among them, represents the degree of deviation of the th data point from the average level, is the index of the data point, is the th observation value, representing the specific value of the marine water quality indicator collected in real-time, represents the average value of this water quality indicator in historical data, is the standard deviation of this water quality indicator;

[0105] Detailed explanation of the formula and the derivation process of formula calculation:

[0106] Assume that the average value of the historical data of the target indicator is 0.05, and the standard deviation is 0.01. Calculate the degree of deviation:

[0107] ;

[0108] The calculation result 2 indicates that the observed value is outside the normal fluctuation range, and the obtained marine water quality status information accurately reflects the abnormal state of the current water quality condition, which helps to take timely measures to handle potential water quality problems.

[0109] Please refer to Figure 4 , based on the marine water quality status information, the steps to extract and analyze the temperature data of the marine environment, including water temperature and air temperature, analyze the changing trend of the marine temperature, detect and identify abnormal fluctuations, and generate temperature anomaly event records are as follows:

[0110] S301: Based on the marine water quality status information, extract the marine temperature data, including water temperature and air temperature information, and generate a temperature data set;

[0111] The data is collected from different monitoring stations and sensing devices such as ocean buoys, satellite remote sensing devices, and weather stations. The target temperature data is initially screened and preprocessed to exclude obvious incorrect data caused by equipment failures or external interferences. Data synchronization technology is applied to ensure that all temperature data matches the correct collection time and location. The data is standardized to facilitate comparison and processing of data from different sources on the same analysis platform. After completing the target steps, the integrated temperature data set includes time series data and geographical location information, which is crucial for further trend analysis and pattern recognition.

[0112] S302: Based on the temperature data set, analyze and predict the changing trend of the marine temperature data, monitor and record abnormal data points, and generate a temperature anomaly analysis result;

[0113] Analyze the changing trend of ocean temperature through statistical analysis methods and machine learning techniques. Apply moving average and exponential smoothing techniques to smooth time series data and reduce the impact of accidental fluctuations. Use time series prediction models, such as the seasonal autoregressive integrated moving average model, to predict the trend and periodic changes of temperature data, identify and predict the trend of temperature increase or decrease. Combine statistical process control techniques to monitor and mark abnormal temperature data points that exceed the normal change range in real time, including point anomaly detection and the identification of abnormal trends. The generated temperature anomaly analysis results record the identified abnormal points and trends, providing an important basis for environmental risk assessment.

[0114] S303: Based on the temperature anomaly analysis results, calculate the anomaly degree and mark the abnormal temperature event by analyzing the amplitude and duration of fluctuations of multiple abnormal data points, and generate a temperature anomaly event record;

[0115] In the above content, based on the obtained temperature anomaly analysis results, use the amplitude of the abnormal data points and the duration , apply the weighted average method, according to the formula: , calculate the anomaly degree of the target temperature anomaly event;

[0116] In the formula, represents the anomaly degree index of each temperature anomaly event, represents the amplitude of temperature fluctuations, represents the duration of temperature fluctuations, and are weight coefficients, is the normalization coefficient;

[0117] Detailed explanation of the formula and the derivation process of formula calculation:

[0118] Suppose the amplitude of a certain temperature anomaly , the duration hours, the weight of the amplitude , the weight of the duration , the normalization coefficient , calculate :

[0119] ;

[0120] ;

[0121] ;

[0122] ;

[0123] The calculation results show that the standardized anomaly degree index of this temperature anomaly event is 0.6, which reflects the anomaly severity under the given fluctuation amplitude and duration conditions. The formula is used to assist in managing and responding to temperature anomalies in the marine environment.

[0124] Please refer to Figure 5 , based on the temperature anomaly event records, analyze multiple marine development activity events, including oil and gas extraction and coastline changes, and evaluate the impact of development activities on the marine environment. The steps to generate development activity impact information are as follows:

[0125] S401: Based on the temperature anomaly event records, extract various information related to marine development activity events, including the time and geographical location information of the development, and generate a development activity dataset;

[0126] Extract the key information directly related to marine development activities, including the specific time and exact geographical location of each development activity, such as the coordinates of oil and gas field extraction areas and coastline construction areas. Data extraction relies on geographic information systems for spatial data analysis to ensure the accuracy of the location information of each development event. Perform time series correction on the development time information to synchronize the time stamps of all events and ensure the consistency of the time information. After integrating the target data, form a development activity dataset containing multi-dimensional information, where each piece of data includes information such as time stamps, geographical locations, and event types, providing basic data for evaluating the environmental impact of development activities.

[0127] S402: Using the development activity dataset, combined with the water quality and temperature information of the target location, evaluate the impact of multiple development events on the marine environment, identify and mark the scope of the affected area, including oil and gas extraction and coastline changes, and generate activity impact analysis results;

[0128] Adopt an environmental impact assessment model that considers geospatial data analysis techniques, such as buffer analysis and overlay analysis, to determine the specific area scope affected by development activities. For example, oil and gas extraction affects the water quality of the surrounding sea area, and coastline changes alter the hydrographic conditions and ecosystems of the nearby sea area. By integrating environmental indicators such as water quality and temperature and applying multivariate statistical analysis methods, such as principal component analysis, identify and quantify the main environmental impacts generated by development activities. The environmental impact results of the target area include the degree of impact, duration, and ecological consequences, providing detailed scientific basis for formulating response measures and protection strategies.

[0129] S403: Based on the activity impact analysis results, considering the duration and intensity of the development activities, analyze the impact of multiple development activities on the marine environment, mark the risky development activities, and generate development activity impact information;

[0130] In the above content, considering the specific duration, intensity, and environmental baseline data of the development activities, according to the formula: , calculate the comprehensive impact score of various development activities on the marine environment;

[0131] In the formula, represents the risk score of the target development activity, represents the duration of the development activity, represents the intensity of the development activity, represents the environmental baseline data of the development area, , , are the weight coefficients of the corresponding parameters, used to adjust the influence of different factors in the risk assessment,

[0132] Detailed explanation of the formula and the derivation process of the formula calculation:

[0133] Assume that the duration of the development activity is months, the intensity of the development activity is , the environmental baseline data of the development area is , the weight coefficient is , , , calculate R:

[0134] ;

[0135] ;

[0136] ;

[0137] The results show that considering the duration, intensity of the development and the current environmental conditions, the environmental risk score of the target development activity is 101, and the calculation process is used to identify high-risk development activities that need attention.

[0138] Please refer to Figure 6 , according to the development activity impact information, by analyzing the impact of various influencing factors on marine environmental indicators, predicting the impact of various influencing factors on marine biodiversity, and combining the outliers of various indicators, the steps to calculate the marine environmental risk score and generate real-time risk assessment information are specifically as follows:

[0139] S501: According to the development activity impact information, analyze the impact of various influencing factors on marine environmental indicators and quantify the impact degree coefficient, including pollution emissions, human development activities, and meteorological factors, and generate a list of influencing factor weights;

[0140] Quantify the impact intensity of target factors using statistical analysis methods and environmental assessment models, including pollution emissions such as industrial wastewater and agricultural runoff, human development activities such as seabed mineral mining, and meteorological factors such as temperature and wind speed changes. By constructing a linear regression model, associate the impact degree of each factor with existing environmental data to evaluate its specific impact on marine water quality and ecosystem. Determine the impact weight of pollution emissions by analyzing the correlation between pollution emissions and biodiversity in the nearby sea area in the historical dataset. Determine the impact scope and intensity of human development activities on the ecology of specific sea areas through spatial data analysis. Construct a list containing all evaluation factors and corresponding weights, and the weight coefficient of each factor reflects its impact degree on the marine environment.

[0141] S502: Based on the impact factor weight list, predict the impact degree of multiple impact factors on marine biodiversity according to the impact of multiple impact factors on marine environmental indicators, and form biodiversity indicators;

[0142] Use ecological modeling techniques and species sensitivity indices to predict the impact degree of changes in different environmental variables on biodiversity. The model integrates the weights of each factor obtained from the impact factor weight list, and calculates the comprehensive impact index of each impact through the ecological model. The process includes the response analysis of different species communities, applying generalized additive models combined with time series analysis to predict the trend of biodiversity change caused by environmental factor changes in the next few years. The biodiversity indicators formed by the analysis results provide a scientific basis for formulating subsequent ecological protection and restoration measures to ensure the long-term maintenance of marine biodiversity.

[0143] S503: Based on the biodiversity indicators, combined with the outliers of multiple marine environmental indicators, calculate the marine environmental risk scores of multiple regions to generate real-time risk assessment information;

[0144] The specific formula for calculating the marine environmental risk scores of multiple regions is:

[0145] ;

[0146] Among them, represents the risk score of the marine environment, is the number of indicators participating in the calculation, is the weight coefficient of the th indicator, is the outlier of the th indicator, is the outlier detection threshold of the th indicator, represents the total number of indicators involved in the risk score calculation, is the index of the indicator.

[0147] Formula:

[0148] ;

[0149] Detailed Explanation of the Formula and Derivation Process of Formula Calculation:

[0150] The formula is used to calculate the marine environmental risk score and evaluate the marine environmental risk of the target area;

[0151] Meaning of Parameters and Set Values:

[0152] is the weight coefficient of the th indicator;

[0153] is the actual observed value of the th indicator;

[0154] is the threshold of the th indicator;

[0155] is the total number of indicators;

[0156] Suppose that 4 environmental indicators in the target area are detected to contain abnormal data points, including heavy metal concentration, dissolved oxygen, temperature, and microplastic content. Among them, the heavy metal concentration ppm, the threshold ppm, the weight , the dissolved oxygen mg / L, the threshold mg / L, the weight , the temperature °C, the threshold °C, the weight , the microplastic content , the threshold , the weight ;

[0157] Calculate the risk contribution of each indicator:

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] Total Risk Score:

[0163] ;

[0164] Result Indicates that the comprehensive environmental risk score for this area is , reflecting a relatively high environmental risk in the target area. The data is used to determine whether further environmental monitoring or management measures are required.

[0165] Please refer to Figure 7 , the marine environmental risk assessment system based on multi-source data fusion. The marine environmental risk assessment system based on multi-source data fusion is used to execute the above-mentioned marine environmental risk assessment method based on multi-source data fusion. The system includes:

[0166] The data source processing module, based on multi-source marine environmental monitoring data, generates a multi-source data fusion model by evaluating the integrity, consistency, and timeliness of data from multiple data sources and adjusting the contribution ratio of the data sources.

[0167] The water quality index analysis module, based on the multi-source data fusion model, extracts various key water quality indexes, including microplastic content, salinity, and dissolved oxygen. Through time series analysis, it identifies the change trend patterns of various indexes and detects outliers in various indexes, generating marine water quality status information.

[0168] The real-time temperature monitoring module, based on the marine water quality status information, extracts water temperature and air temperature data and conducts trend analysis, detects and identifies abnormal fluctuations in the temperature data, generating temperature anomaly event records.

[0169] The marine activity analysis module, based on the temperature anomaly event records, analyzes the impact of marine development activities on the marine environment, evaluates the environmental sensitivity of various activities, and generates development activity impact information.

[0170] The environmental risk analysis module, according to the development activity impact information, predicts the impact of various influencing factors on marine biodiversity, combines the real-time marine environmental monitoring data, calculates the marine environmental risk score, and generates real-time risk assessment information.

[0171] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0172] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood with reference to the context.

[0173] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0174] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0175] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0176] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0177] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in an electrical, mechanical, or other form.

[0178] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0179] In addition, the functional units in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0180] When the above-mentioned function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0181] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A marine environmental risk assessment method based on multi-source data fusion, characterized in that: The method comprises: Based on multi-source marine environment monitoring data, the data integrity, consistency and timeliness of multiple data sources are evaluated, the efficiency scores of multiple data sources are calculated, and the contribution ratio of the target data source is adjusted to generate a multi-source data fusion model; Utilizing the multi-source data fusion model, extracting and analyzing various indicator data related to water quality, performing trend analysis and pattern recognition on the various indicators, detecting and recording abnormal values ​​of the various indicators, and generating ocean water quality status information; Based on the ocean water quality status information, extract and analyze the temperature data of the ocean environment, including water temperature and air temperature, analyze the changing trend of ocean temperature, detect and identify abnormal fluctuations, and generate temperature abnormality event records; Based on the temperature anomaly event records, multiple marine development activity events are analyzed, including oil and gas production and coastline changes, to evaluate the impact of development activities on the marine environment and generate development activity impact information; Based on the impact information of the development activities, by analyzing the impact of various influencing factors on marine environmental indicators, predicting the impact of various influencing factors on marine biodiversity, combining the abnormal values ​​of various indicators, calculating the marine environmental risk score, and generating real-time risk assessment information; Based on multi-source marine environment monitoring data, the data integrity, consistency and timeliness of multiple data sources are evaluated, the performance scores of multiple data sources are calculated and the contribution ratio of the target data source is adjusted. The specific steps for generating a multi-source data fusion model are as follows: Based on multi-source marine environment monitoring data, the integrity analysis of multiple data sources, including satellite remote sensing, buoy monitoring, and ship collection, marks missing data and timestamp errors, and generates data inspection results; Based on the data inspection results, the consistency and timeliness of data from multiple sources are evaluated, performance scores are calculated for multiple data sources, and a data source performance score table is generated; Based on the data source performance rating table, matching contribution ratios of multiple data sources according to performance ratings, and building a multi-source data fusion model; The specific formula for calculating the performance score for multiple data sources is: ； in, Representative The performance rating of each data source, is the weight coefficient of data integrity, It is The number of data points known for each data source, Theoretically, The total number of data points a data source should have, is the weight coefficient of data consistency, It is The number of data points that are consistent between a data source and other data sources in the same time window, It is The total number of data points for consistency comparison of the data sources, is the weight coefficient of data timeliness, It is The average data delay time of each data source, Represents the index of the data source.

2. The marine environmental risk assessment method based on multi-source data fusion according to claim 1 is characterized in that: The multi-source data fusion model specifically includes a performance score list, a data source contribution ratio adjustment record, and a data fusion result. The ocean water quality status information includes water quality trend analysis results, water quality pattern recognition information, and water quality anomaly value records. The temperature anomaly event record specifically refers to water temperature change trend information, air temperature change trend information, and temperature abnormal fluctuation identification results. The development activity impact information includes development activity type information, development activity impact assessment results, and development activity risk index. The real-time risk assessment information specifically includes an influencing factor relationship diagram, biodiversity impact prediction results, and an environmental risk score.

3. The marine environmental risk assessment method based on multi-source data fusion according to claim 1 is characterized in that: The steps of using the multi-source data fusion model to extract and analyze various indicator data related to water quality, perform trend analysis and pattern recognition on various indicators, detect and record abnormal values ​​of various indicators, and generate ocean water quality status information are as follows: Based on the multi-source data fusion model, a variety of indicator data related to water quality are extracted, including microplastic content, salinity, and dissolved oxygen, and a water quality information extraction record is generated; Based on the water quality information extraction record, combined with time information, identifying the change trends and periodic patterns of multiple water quality indicators, and generating water quality trend analysis results; Based on the water quality trend analysis results, abnormal points in multiple indicator data are detected and recorded in real time to generate ocean water quality status information.

4. The marine environmental risk assessment method based on multi-source data fusion according to claim 1 is characterized in that: Based on the ocean water quality status information, extract and analyze the temperature data of the ocean environment, including water temperature and air temperature, analyze the change trend of ocean temperature, detect and identify abnormal fluctuations, and generate temperature abnormality event records in the following steps: Based on the ocean water quality status information, extract ocean temperature data, including water temperature and air temperature information, to generate a temperature data set; Based on the temperature data set, by analyzing and predicting the change trend of the ocean temperature data, monitoring and recording abnormal data points, and generating temperature anomaly analysis results; Based on the temperature anomaly analysis result, by analyzing the amplitude and duration of fluctuations of multiple abnormal data points, the degree of anomaly is calculated and abnormal temperature events are marked to generate a temperature anomaly event record.

5. The marine environmental risk assessment method based on multi-source data fusion according to claim 1 is characterized in that: Based on the temperature anomaly event records, multiple marine development activity events are analyzed, including oil and gas exploitation and coastline changes, to evaluate the impact of development activities on the marine environment. The specific steps for generating development activity impact information are as follows: Based on the abnormal temperature event records, extract various information related to marine development activity events, including development time and geographic location information, to generate a development activity data set; Using the development activity dataset, combined with water quality and temperature information at the target location, the impact of multiple development events on the marine environment is evaluated, the scope of the affected area is identified and marked, including oil and gas extraction and coastline changes, and the activity impact analysis results are generated; Based on the results of the activity impact analysis, the duration and intensity of the development activities are taken into consideration, the impact of various development activities on the marine environment is analyzed, risky development activities are marked, and development activity impact information is generated.

6. The marine environmental risk assessment method based on multi-source data fusion according to claim 1 is characterized in that: According to the impact information of the development activities, by analyzing the impact of various factors on marine environmental indicators, predicting the impact of various factors on marine biodiversity, combining the abnormal values ​​of various indicators, calculating the marine environmental risk score, and generating real-time risk assessment information, the specific steps are as follows: Based on the impact information of the development activities, analyze the impact of various factors on marine environmental indicators and quantify the impact coefficients, including pollution emissions, human development activities, and meteorological factors, and generate a weight list of influencing factors; Based on the weight list of influencing factors, according to the impact of various influencing factors on marine environmental indicators, the impact of various influencing factors on marine biodiversity is predicted to form a biodiversity index; Based on the biodiversity indicators and combined with the abnormal values ​​of multiple marine environmental indicators, the marine environmental risk scores of multiple regions are calculated to generate real-time risk assessment information.

7. The marine environmental risk assessment method based on multi-source data fusion according to claim 6 is characterized in that: The specific formula for calculating the marine environmental risk scores of multiple regions is: ； in, represents the risk score of the marine environment, is the number of indicators involved in the calculation, It is The weight coefficient of each indicator is It is The abnormal value of the indicator, It is The anomaly detection threshold of each indicator, Represents the total number of indicators involved in the risk score calculation. is the index of the indicator.

8. The marine environmental risk assessment system based on multi-source data fusion is characterized by: According to any one of claims 1 to 7, the marine environmental risk assessment method based on multi-source data fusion comprises: The data source processing module is based on multi-source marine environment monitoring data. It evaluates the integrity, consistency and timeliness of data from multiple data sources, adjusts the contribution ratio of data sources, and generates a multi-source data fusion model. The water quality index analysis module extracts a variety of key water quality indicators, including microplastic content, salinity and dissolved oxygen, based on the multi-source data fusion model, identifies the change trend patterns of multiple indicators through time series analysis, detects abnormal values ​​in multiple indicators, and generates marine water quality status information; The real-time temperature monitoring module extracts water temperature and air temperature data based on the ocean water quality status information and performs trend analysis, detects and identifies abnormal fluctuations in temperature data, and generates temperature abnormality event records; The marine activity analysis module analyzes the impact of marine development activities on the marine environment based on the abnormal temperature event records, evaluates the environmental sensitivity of various activities, and generates development activity impact information; The environmental risk analysis module predicts the impact of various factors on marine biodiversity based on the impact information of the development activities, calculates the marine environmental risk score in combination with real-time marine environmental monitoring data, and generates real-time risk assessment information.

Images