Method and device for managing marine spatial data through dynamic remote sensing monitoring

Through dynamic remote sensing monitoring and weighting methods of variation coefficients, the problem of insufficient real-time monitoring in the marine environment is solved, and the dynamic balance between the ecological environment and resource mining of sea area space data management is achieved, ensuring real-time monitoring of sea area conditions and disaster prediction.

CN118657411BActive Publication Date: 2024-11-05SHANDONG PROVINCIAL INST OF LAND & SPACE DATA & REMOTE SENSING TECH (SHANDONG PROVINCIAL SEA AREA DYNAMIC SURVEILLANCE & MONITORING CENT) +2
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411147025.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-21
Publication Date
2024-11-05
Estimated Expiration
2044-08-21

AI Technical Summary

Technical Problem

The existing technology lacks real-time and dynamic monitoring mechanisms in the marine environment, and cannot capture environmental changes in time and make corresponding adjustments, resulting in insufficient balance between ecological environment and resource extraction in sea area spatial data management.

Method used

Dynamic remote sensing monitoring method is adopted to obtain sea area spatial data through multi-remote sensing equipment, integrate and analyze timing characteristics, and use the weighting method of variation coefficients to analyze the correlation between resource mining activities and changes in the marine environment, and formulate targeted sea area regulation and management strategies.

Benefits of technology

It has achieved a dynamic balance between ecological environment and resource exploitation, ensured comprehensive and real-time monitoring of sea areas and disaster prediction, and improved its response to changes in the marine environment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118657411B_ABST
    Figure CN118657411B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and device for managing marine spatial data by dynamic remote sensing monitoring, which relates to the field of marine disaster management. The method includes: extracting the first historical marine disaster time series; performing time series feature analysis; issuing a remote sensing monitoring instruction when the target marine disaster rate reaches a predetermined probability threshold; activating multiple remote sensing devices to perform multi-source remote sensing feature monitoring to obtain a predetermined remote sensing time series; matching the first remote sensing resource and the first remote sensing environment at the first remote sensing time; adjusting the first remote sensing environment by using the first coefficient obtained by weighting the first remote sensing resource with the coefficient of variation as a weight to obtain a first effective remote sensing environment; analyzing and verifying the target marine disaster rate to obtain the target effective marine disaster rate; and performing marine regulation and management. The method solves the technical problem that the existing marine spatial data management is insufficient in terms of the balance between the ecological environment and resource exploitation, and achieves the technical effect of achieving a dynamic balance between the ecological environment and resource exploitation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of marine disaster management, and in particular to a method and device for managing marine spatial data through dynamic remote sensing monitoring. Background Art

[0002] In the marine environment, marine spatial data management is a complex and important task, which is directly related to the rational use of marine resources, the protection of the ecological environment and the effective prevention of natural disasters. With the global climate change and the increase of marine activities, marine natural disasters (such as typhoons, tsunamis, red tides, etc.) occur frequently, posing a serious threat to the safety of life and property of people in coastal areas. In the process of marine resource development and utilization, a core and urgent technical issue is how to maintain the balance of marine ecology while ensuring the effective exploitation of resources and prevent natural disasters caused by resource development. At present, although many methods have been applied to the development of marine resources and the protection of the marine environment, the marine environment is dynamically changing, and the existing methods lack real-time and dynamic monitoring mechanisms, and cannot capture environmental changes in time and make corresponding adjustments.

[0003] Among the current relevant technologies, marine spatial data management has shortcomings in terms of the balance between ecological environment and resource exploitation. Summary of the invention

[0004] The present application provides a method and device for managing marine spatial data through dynamic remote sensing monitoring, and uses multiple remote sensing devices to obtain marine spatial data, including resource data and environmental data. Through fusion analysis, the marine conditions are comprehensively and real-timely grasped. Based on historical disaster data and real-time remote sensing data, time series feature analysis is used to accurately predict marine disasters. The correlation between resource exploitation activities and marine environmental changes is analyzed through the weighted coefficient of variation method. According to the disaster prediction results and ecological and environmental impact analysis, targeted marine regulation and management strategies and other technical means are formulated to ensure that the balance between the ecological environment and resource exploitation is continuously maintained, and the technical effect of achieving a dynamic balance between the ecological environment and resource exploitation is achieved.

[0005] This application provides a method for managing marine spatial data through dynamic remote sensing monitoring, including:

[0006] Extract the first sea area disaster from the natural disasters in the predetermined sea area, and obtain the first historical sea area disaster time series of the first sea area disaster in the predetermined sea area; perform time series feature analysis on the first historical sea area disaster time series based on a predetermined unit period to obtain a target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in a target unit period; when the target sea area disaster rate reaches a predetermined probability threshold, issue a remote sensing monitoring instruction, and call a predetermined remote sensing strategy based on the remote sensing monitoring instruction; activate multiple remote sensing devices according to the predetermined remote sensing strategy to perform multi-source remote sensing feature monitoring on the predetermined sea area, and obtain a predicted sea area disaster rate; The method comprises the steps of: determining a remote sensing timing sequence, wherein the predetermined remote sensing timing sequence includes a predetermined remote sensing resource timing sequence and a predetermined remote sensing environment timing sequence; reading a first remote sensing time, and matching a first remote sensing resource and a first remote sensing environment at the first remote sensing time in the predetermined remote sensing resource timing sequence and the predetermined remote sensing environment timing sequence in turn; adjusting the first remote sensing environment by using a first coefficient obtained by weighting the first remote sensing resource with a coefficient of variation as a weight, and obtaining a first effective remote sensing environment; analyzing and verifying the target sea area disaster rate according to the first effective remote sensing environment, and obtaining a target effective sea area disaster rate; and performing sea area regulation and management on the predetermined sea area according to the target effective sea area disaster rate.

[0007] In a possible implementation, the following processing is performed:

[0008] Based on the predetermined unit period, the first historical sea area disaster time series is divided into time zones to obtain a first time series division result, which includes multiple unit time zones with first sea area disaster frequency identifiers; multi-domain features are collected for the first disaster frequency time series generated based on the multiple unit time zones with first sea area disaster frequency identifiers to obtain a first multi-domain feature set; the first multi-domain feature set is used as input information of a first sea area disaster prediction model to obtain first output information, which includes the target sea area disaster rate; wherein the first sea area disaster prediction model is an intelligent model obtained by supervised learning of the data in the first historical sea area disaster time series.

[0009] In a possible implementation, the following processing is performed:

[0010] The first disaster frequency time series is subjected to time domain feature collection to obtain a first time domain feature set; the first disaster frequency spectrum obtained by converting the first disaster frequency time series is subjected to frequency domain feature collection to obtain a first frequency domain feature set; the first time domain feature set and the first frequency domain feature set constitute the first multi-domain feature set.

[0011] In a possible implementation, the following processing is performed:

[0012] A first effective remote sensing environment time series is generated according to a first mapping relationship between the first remote sensing time and the first effective remote sensing environment; a predictive analysis is performed on the first effective remote sensing environment time series in combination with the target unit period to obtain a first predicted target environment; first prediction data constructed based on the first predicted target environment is used as input information of a second sea area disaster prediction model to obtain second output information, wherein the second output information includes a second target sea area disaster rate; and an average of the target sea area disaster rate and the second target sea area disaster rate is taken as the target effective sea area disaster rate.

[0013] In a possible implementation, the following processing is performed:

[0014] Obtain a first scatter plot of the first effective remote sensing environment time series; perform regression fitting on the first scatter plot using the principle of random sampling consistency to obtain a first fitting formula; analyze the first fitting formula in combination with the target unit period to obtain the second target sea area disaster rate.

[0015] In a possible implementation, the following processing is performed:

[0016] Randomly extract any remote sensing characteristic parameter in the predetermined remote sensing time series, and obtain any sea area coordinates of the arbitrary remote sensing characteristic parameter; obtain the predetermined sea area coordinates of the predetermined sea area, and calculate the spatial distance value between the predetermined sea area coordinates and the arbitrary sea area coordinates; adjust the arbitrary remote sensing characteristic parameter using the spatial distance value as a coefficient.

[0017] In a possible implementation, the following processing is performed:

[0018] Calculate the Euclidean distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; calculate the Manhattan distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; and take the average of the Euclidean distance and the Manhattan distance as the spatial distance value.

[0019] The present application also provides a device for dynamic remote sensing monitoring and marine spatial data management, including:

[0020] A first historical sea area disaster time series extraction module, the first historical sea area disaster time series extraction module is used to extract the first sea area disaster among the natural disasters in the predetermined sea area, and obtain the first historical sea area disaster time series of the first sea area disaster in the predetermined sea area; a target sea area disaster rate acquisition module, the target sea area disaster rate acquisition module is used to perform time series feature analysis on the first historical sea area disaster time series based on a predetermined unit period, and obtain the target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in the target unit period; a predetermined remote sensing strategy calling module, the predetermined remote sensing strategy calling module is used to issue a remote sensing monitoring instruction when the target sea area disaster rate reaches a predetermined probability threshold, and call a predetermined remote sensing strategy based on the remote sensing monitoring instruction; a predetermined remote sensing time series acquisition module, the predetermined remote sensing time series acquisition module is used to activate multiple remote sensing devices to perform multi-source remote sensing feature monitoring on the predetermined sea area according to the predetermined remote sensing strategy, and obtain to a predetermined remote sensing timing, the predetermined remote sensing timing including a predetermined remote sensing resource timing and a predetermined remote sensing environment timing; a first remote sensing time matching module, the first remote sensing time matching module is used to read a first remote sensing time, and sequentially match a first remote sensing resource and a first remote sensing environment under the first remote sensing time in the predetermined remote sensing resource timing and the predetermined remote sensing environment timing; a first effective remote sensing environment acquisition module, the first effective remote sensing environment acquisition module is used to adjust the first remote sensing environment by using a first coefficient obtained by weighting the first remote sensing resource with a coefficient of variation as a weight, and obtain a first effective remote sensing environment; a target effective sea area disaster rate acquisition module, the target effective sea area disaster rate acquisition module is used to analyze and verify the target sea area disaster rate according to the first effective remote sensing environment, and obtain a target effective sea area disaster rate; a sea area regulation and management module, the sea area regulation and management module is used to perform sea area regulation and management on the predetermined sea area according to the target effective sea area disaster rate.

[0021] The method and device for managing marine spatial data through dynamic remote sensing monitoring proposed in the present application first extracts the first marine disaster from the natural disasters in the predetermined marine area, and obtains the first historical marine disaster time series of the first marine disaster in the predetermined marine area, then performs time series feature analysis on the first historical marine disaster time series based on a predetermined unit period, and obtains the target marine disaster rate, wherein the target marine disaster rate refers to the probability of the first marine disaster occurring in the predetermined marine area in the target unit period, and when the target marine disaster rate reaches a predetermined probability threshold, issues a remote sensing monitoring instruction, and calls a predetermined remote sensing strategy based on the remote sensing monitoring instruction, and then activates multiple remote sensing devices according to the predetermined remote sensing strategy to perform multi-source remote sensing feature analysis on the predetermined marine area. The system performs data collection and monitoring to obtain a predetermined remote sensing time series, including a predetermined remote sensing resource time series and a predetermined remote sensing environment time series, and then reads a first remote sensing time, and matches the first remote sensing resource and the first remote sensing environment at the first remote sensing time in the predetermined remote sensing resource time series and the predetermined remote sensing environment time series in turn, and then uses the first coefficient obtained by weighting the first remote sensing resource with the coefficient of variation as a weight to adjust the first remote sensing environment to obtain a first effective remote sensing environment, and then analyzes and verifies the target sea area disaster rate according to the first effective remote sensing environment to obtain the target effective sea area disaster rate, and finally performs sea area regulation and management on the predetermined sea area according to the target effective sea area disaster rate, thereby achieving a technical effect of achieving a dynamic balance between the ecological environment and resource exploitation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A flow chart of a method for managing marine spatial data through dynamic remote sensing monitoring provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of an apparatus for managing marine spatial data through dynamic remote sensing monitoring provided in an embodiment of the present application.

[0025] Explanation of the accompanying drawings: first historical sea area disaster time series extraction module 10, target sea area disaster rate acquisition module 20, predetermined remote sensing strategy calling module 30, predetermined remote sensing time series acquisition module 40, first remote sensing time matching module 50, first effective remote sensing environment acquisition module 60, target effective sea area disaster rate acquisition module 70, sea area regulation and management module 80. DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The present application embodiment provides a method for managing marine spatial data through dynamic remote sensing monitoring, such as Figure 1 As shown, the method includes:

[0030] Step S100, extract the first sea area disaster from the natural disasters in the predetermined sea area, and obtain the first historical sea area disaster time sequence of the first sea area disaster in the predetermined sea area. Specifically, the predetermined sea area refers to the sea area that is pre-demarcated and the monitoring range is determined using the Geographic Information System (GIS), and has geographic coordinates and boundary information. Consult historical meteorological and marine disaster records, combine expert knowledge and literature research, identify the types of natural disasters that may occur in the predetermined sea area, such as typhoons, tsunamis, red tides, etc., and obtain a list of natural disaster types. According to factors such as the severity of the disaster, the frequency of occurrence, and the potential impact on the marine ecology and economy, select one type of natural disaster type to be studied and analyzed from the list of natural disaster types as the first sea area disaster. Use database query, historical archive retrieval, remote sensing image analysis and other means to collect historical data such as the occurrence time, intensity, and impact range of the first sea area disaster in the past years, and obtain a historical data record set of the first sea area disaster. Use time series analysis software (such as the xts package of R language, the pandas library of Python, etc.) to organize the collected historical data in chronological order to form a time series, and obtain the first historical sea disaster time series data set, which contains information such as the timestamp of the disaster, the intensity level, and the impact range. The first historical sea disaster time series is used to analyze the laws and trends of disaster occurrence.

[0031] Step S200, based on a predetermined unit period, the time series characteristics of the first historical sea area disaster time series are analyzed to obtain the target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in the target unit period. Specifically, the predetermined unit period refers to a time unit determined according to monitoring requirements, data availability and disaster occurrence characteristics for analyzing the historical disaster time series and predicting future disaster rates, such as year, quarter, month, etc. The first historical sea area disaster time series data is cleaned to remove outliers and fill missing values ​​to ensure the integrity and accuracy of the data. Time series analysis methods (such as sliding window, Fourier transform, wavelet analysis, etc.) are used to extract key features such as periodicity, trend, seasonality, etc. from the pre-processed historical disaster time series data. According to the extracted time series features, a statistical model (such as an autoregressive model, a time series decomposition model) or a machine learning model (such as a random forest, a neural network, a support vector machine, etc.) is selected to construct a disaster prediction model, which is a mathematical model established based on historical disaster data and used to predict the probability of future disasters. The predetermined unit period is taken as input and the trained disaster prediction model is used to make predictions to obtain the probability of the first sea area disaster occurring within the future predetermined unit period, that is, the target sea area disaster rate.

[0032] In a possible implementation, step S200 further includes step S210, dividing the first historical sea disaster time series into time zones based on the predetermined unit period to obtain a first time series division result, wherein the first time series division result includes multiple unit time zones with a first sea disaster frequency identifier. Specifically, according to the length of the predetermined unit period and the periodic characteristics of the first sea disaster, a specific strategy for time zone division is determined, such as dividing by day, week, month or quarter, to obtain a time zone division strategy. According to the determined time zone division strategy, the first historical sea disaster time series is divided into multiple unit time zones, each unit time zone contains a first sea disaster record within a corresponding time period, and in each unit time zone, the frequency of occurrence of the first sea disaster is counted and used as the identifier of the unit time zone to obtain a set of unit time zones with a first sea disaster frequency identifier. Step S220, multi-domain feature collection is performed on the first disaster frequency time series generated based on the multiple unit time zones with the first sea disaster frequency identifier to obtain a first multi-domain feature set. Specifically, multiple unit time zones with the first sea area disaster frequency identification are arranged in chronological order to generate a first disaster frequency time series, and features of multiple fields are extracted from the first disaster frequency time series, including but not limited to time features (such as season, month), geographical features (such as sea area location, water depth), climate features (such as temperature, humidity, wind speed), etc., to obtain a first multi-domain feature set, and the first multi-domain feature set contains rich feature information for the prediction model. Step S230, using the first multi-domain feature set as input information of the first sea area disaster prediction model to obtain first output information, the first output information includes the target sea area disaster rate, wherein the first sea area disaster prediction model is an intelligent model obtained by supervised learning of the data in the first historical sea area disaster time series. Specifically, a pre-trained first sea area disaster prediction model is loaded, which is obtained by supervised learning based on the data in the first historical sea area disaster time series. The first multi-domain feature set is passed as input information to the first sea area disaster prediction model. The first sea area disaster prediction model performs internal calculations based on the input first multi-domain feature set and outputs prediction results, including the target sea area disaster rate, that is, the probability of the first sea area disaster occurring in the predetermined sea area in the future target unit period. This implementation method decomposes long time series data into smaller and more manageable parts through time zone division, which is convenient for feature extraction and model training. Through multi-domain feature collection, it comprehensively captures the various factors that affect the occurrence of the first sea area disaster, improves the accuracy and robustness of the prediction model, and the supervised learning prediction model utilizes the regularity and patterns in historical data, thereby achieving the technical effect of accurately predicting the probability of future disasters.

[0033] In a possible implementation, step S220 further includes step S221, collecting time domain features of the first disaster frequency time series to obtain a first time domain feature set. Specifically, the first sea disaster frequency data in each time zone is arranged in chronological order. According to the first disaster frequency time series, determine the time domain features to be extracted, such as the trend (increase, decrease, stability), periodicity (seasonal fluctuations), mutation points (sudden increase or decrease in disaster frequency), etc. of the time series. Apply statistical methods (such as moving average, difference, autocorrelation analysis, etc.) or machine learning algorithms (such as time series decomposition) to extract the time domain features in the first disaster frequency time series, and organize the extracted features into a first time domain feature set, each feature reflects the characteristics of the time series in different time dimensions. Step S222, collect frequency domain features of the first disaster spectrum obtained by converting the first disaster frequency time series to obtain a first frequency domain feature set. Specifically, the first disaster frequency time series is converted from the time domain to the frequency domain by Fourier transform (or other spectrum analysis methods) to obtain the first disaster spectrum, which represents the intensity or energy distribution of different frequency components in the time series. Determine the frequency domain features to be extracted, such as the main frequency (the frequency component with the highest energy), the spectrum width (the degree of spectrum broadening), the spectrum peak (the significant peak in the spectrum), etc. Analyze the first disaster spectrum, extract the defined frequency domain features, and organize the extracted features into a first frequency domain feature set, each of which reflects the characteristics of the time series in the frequency dimension. Step S223, the first time domain feature set and the first frequency domain feature set form the first multi-domain feature set. Specifically, the first time domain feature set obtained in step S221 and the first frequency domain feature set obtained in step S222 are merged to form a first multi-domain feature set, which integrates the characteristics of the time series in both the time domain and the frequency domain, and provides comprehensive information input for the prediction model. This implementation method collects time domain features and frequency domain features at the same time. The time domain features are used to capture intuitive information such as the trend, periodicity and mutation points of the time series over time; the frequency domain features are used to reveal the hidden frequency components and periodic patterns in the time series. By combining the time domain features with the frequency domain features, a comprehensive and accurate prediction model is constructed, achieving the technical effect of improving the accuracy of the prediction of the probability of the first disaster in the predetermined sea area in the future.

[0034] Step S300, when the disaster rate of the target sea area reaches a predetermined probability threshold, a remote sensing monitoring instruction is issued, and a predetermined remote sensing strategy is called based on the remote sensing monitoring instruction. Specifically, the disaster rate of the target sea area is compared with the preset disaster probability threshold to determine whether the disaster rate of the target sea area reaches or exceeds the predetermined probability threshold (a critical value of the probability of disaster occurrence set according to historical data and risk assessment, used to determine whether more in-depth remote sensing monitoring is required). If the comparison result shows that the disaster rate of the target sea area reaches or exceeds the predetermined probability threshold, a remote sensing monitoring instruction is generated and issued through an automated system (such as a monitoring platform, a remote sensing instruction sending system). The remote sensing monitoring instruction is an instruction for guiding the execution of remote sensing monitoring tasks, including sea area information to be monitored, monitoring time, monitoring content, etc. According to the issued remote sensing monitoring instruction, a remote sensing strategy matching the current situation is retrieved and called from a pre-defined remote sensing strategy library, and the remote sensing strategy library contains a variety of remote sensing monitoring schemes for different sea areas and different types of disasters, including monitoring equipment, parameters, data processing methods, etc.

[0035] Step S400, according to the predetermined remote sensing strategy, multiple remote sensing devices are activated to monitor the multi-source remote sensing characteristics of the predetermined sea area, and a predetermined remote sensing time sequence is obtained, wherein the predetermined remote sensing time sequence includes a predetermined remote sensing resource time sequence and a predetermined remote sensing environment time sequence. Specifically, the predetermined remote sensing strategy is parsed to clarify the type of remote sensing devices that need to be activated (devices used to obtain target area information remotely and contactlessly, such as satellite remote sensing, drone remote sensing, ground station remote sensing, etc.), quantity, and respective task allocation. According to the strategy requirements, the parameters of each remote sensing device are configured, such as observation wavelength, resolution, scanning angle, etc., to ensure that they can capture the key features of the predetermined sea area. Through a remote control system or an automated script, the selected multiple remote sensing devices are activated, and specific monitoring task instructions are sent to them. Each remote sensing device performs remote sensing monitoring tasks for the predetermined sea area according to the received instructions, including but not limited to data collection, image capture, signal reception, etc. of resources and environment for the predetermined sea area. During the monitoring process, each remote sensing device generates a large amount of remote sensing data, including image data, spectral data, radar data, etc. These data are transmitted to the data processing center in real time or regularly through satellite communication, wireless transmission, etc. for storage and analysis. The received multi-source remote sensing data is first preprocessed, including denoising, correction, registration and other steps to improve the quality and availability of the data. The preprocessed data is integrated in chronological order to form a predetermined remote sensing time series, which contains remote sensing feature information of the predetermined sea area at different time points, such as resource distribution (sea surface temperature, chlorophyll concentration, suspended matter content, etc.) and environmental conditions (optical properties, thermal infrared properties, radar reflection properties, etc.).

[0036] In a possible implementation, step S400 further includes step S410, randomly extracting any remote sensing characteristic parameter in the predetermined remote sensing time series, and obtaining any sea area coordinates of the arbitrary remote sensing characteristic parameter. Specifically, remote sensing data of one or more time points are randomly selected from the predetermined remote sensing time series using a random number generator or a sampling algorithm. In the selected remote sensing data, one or more remote sensing characteristic parameters (data indicators reflecting specific physical, chemical or biological characteristics of the sea area) are extracted according to the data structure and content. These characteristic parameters include sea surface temperature, chlorophyll concentration, suspended matter content, etc. For each extracted remote sensing characteristic parameter, the corresponding sea area coordinates are determined according to the metadata or coordinate information of the remote sensing data, wherein the sea area coordinates can be expressed in the form of longitude and latitude. Step S420, obtaining the predetermined sea area coordinates of the predetermined sea area, and calculating the spatial distance value between the predetermined sea area coordinates and the arbitrary sea area coordinates. Specifically, according to the pre-set sea area range or boundary, multiple representative point coordinates or boundary coordinates of the predetermined sea area are obtained. The distance calculation function or mathematical algorithm (such as the Haversing formula) in the geographic information system (GIS) is used to calculate the spatial distance value between the predetermined sea area coordinates and the arbitrary sea area coordinates obtained in step S410. The spatial distance refers to the straight-line distance or the shortest path distance between two geographic coordinate points on the surface of the earth. Step S430, the arbitrary remote sensing characteristic parameter is adjusted using the spatial distance value as a coefficient. Specifically, the calculated spatial distance value is used as an adjustment coefficient, which reflects the relative position relationship between the arbitrary sea area coordinates and the predetermined sea area coordinates. According to the adjustment coefficient, the arbitrary remote sensing characteristic parameters extracted in step S410 are weighted or interpolated. The purpose of the adjustment is to make the remote sensing characteristic parameters better reflect the actual conditions in the predetermined sea area, especially when the spatial resolution of the remote sensing data is not sufficient to accurately monitor small-scale sea area characteristics. Due to the limited spatial resolution of remote sensing data, directly using raw remote sensing data sometimes cannot accurately reflect the characteristic changes of small-scale sea areas. This implementation method randomly extracts remote sensing characteristic parameters and calculates their spatial distance from the predetermined sea area, and appropriately adjusts the characteristic parameters according to the distance. This makes up for the problem of insufficient spatial resolution to a certain extent and achieves the technical effect of improving the application accuracy of remote sensing data in marine spatial data management.

[0037] In a possible implementation, step S420 further includes step S421, calculating the Euclidean distance between the predetermined sea area coordinates and the arbitrary sea area coordinates. Specifically, using the Euclidean distance formula Calculate the straight-line distance between two points, where are the coordinates of the predetermined sea area. is the coordinate of any sea area, and the Euclidean distance is the distance between two points directly connected in Euclidean space, that is, the straight-line distance. Step S422, calculate the Manhattan distance between the predetermined sea area coordinate and the arbitrary sea area coordinate. Specifically, the coordinate values ​​in step S421 are also used, and the Manhattan distance formula is used: Calculate the sum of the absolute wheelbases of the two points in the standard coordinate system. The Manhattan distance represents the shortest path length required for a point to reach another point in the standard coordinate system, where it can only move in the horizontal and vertical directions. Step S423, take the mean of the Euclidean distance and the Manhattan distance as the spatial distance value. Specifically, add the Euclidean distance and the Manhattan distance calculated in steps S421 and S422, and then divide them by 2 to obtain their mean, and use this mean as the spatial distance value in step S420 for the adjustment coefficient in step S430. This implementation method aims to comprehensively evaluate the spatial relationship between the predetermined sea area coordinates and the arbitrary sea area coordinates by considering both the Euclidean distance and the Manhattan distance at the same time. The Euclidean distance reflects the straight-line distance between two points and is suitable for the measurement of continuous space; the Manhattan distance takes into account the directionality of the path, combines the two and takes the mean, and obtains a comprehensive spatial distance value that takes into account both the straight-line distance and the directional influence. This processing method achieves the technical effect of improving the accuracy and robustness of spatial data processing and providing a more reliable spatial distance basis for feature parameter adjustment.

[0038] Step S500, read the first remote sensing time, and match the first remote sensing resource and the first remote sensing environment under the first remote sensing time in the predetermined remote sensing resource time series and the predetermined remote sensing environment time series in turn. Specifically, the first remote sensing time refers to a specific time point selected when performing remote sensing monitoring, which is specified by the system or the user and is used to extract corresponding data from the remote sensing time series data. Through indexing and query operations on time series data (such as SQL query statements or Python's Pandas library), search for data records matching the first remote sensing time in the predetermined remote sensing resource time series. After successful matching, extract the first remote sensing resource data at this time point, such as resource distribution, sea surface temperature, chlorophyll concentration, suspended matter content, etc. Similarly, search for data records matching the first remote sensing time in the predetermined remote sensing environment time series, and extract the first remote sensing environment data at this time point, including environmental parameters observed by remote sensing such as optical, thermal infrared, and radar. Integrate the data matched from the resource time series and the environment time series to ensure that they correspond to the same remote sensing time.

[0039] Step S600, using the first coefficient obtained by weighting the first remote sensing resource with the coefficient of variation as the weight, adjusting the first remote sensing environment to obtain the first effective remote sensing environment. Specifically, the coefficient of variation is a relative indicator to measure the degree of data dispersion, reflecting the degree of difference between the observations. For the first remote sensing resource (such as resource distribution, sea surface temperature, chlorophyll concentration, suspended matter content, etc.), first calculate the coefficient of variation of each resource parameter, and the calculation formula of the coefficient of variation is the ratio of the standard deviation to the mean value. According to the coefficient of variation of each resource parameter, combined with its importance or degree of influence, determine the respective weights, multiply the coefficient of variation of each resource parameter by the corresponding weight, and then perform weighted summation to obtain the first coefficient, which reflects the overall degree of change and importance of the first remote sensing resource. Using the first coefficient as the weight, adjust the first remote sensing environment (such as environmental parameters obtained by remote sensing means such as optics, thermal infrared, radar, etc.), that is, according to the degree of influence of resource changes on the environment, weighted correction is performed on the corresponding environmental parameters. For example, if resource extraction leads to a significant increase in sea surface temperature, then the weight of environmental parameters related to sea surface temperature should be appropriately increased when assessing marine disaster risks. The first remote sensing environment after weighted adjustment is the first effective remote sensing environment, which more accurately reflects the impact of resource extraction on the marine environment and how this impact affects marine disaster risks.

[0040] Step S700, analyze and verify the target sea area disaster rate according to the first effective remote sensing environment to obtain the target effective sea area disaster rate. Specifically, according to the characteristics of the first sea area disaster and the characteristics of the first effective remote sensing environment data, construct or select a suitable analysis model, which can reflect the impact of resource exploitation on the marine environment and how this impact acts on the first sea area disaster risk, wherein the model can be based on statistics (such as regression analysis, time series analysis, etc.) or machine learning (such as neural network, decision tree, etc.). Input the first effective remote sensing environment data and the target sea area disaster rate data into the analysis model to evaluate the disaster risk. During the analysis process, the model will adjust the target sea area disaster rate according to the first effective remote sensing environment data to obtain a more accurate target effective sea area disaster rate. Evaluate the results of the analysis and verification by comparing with historical data, expert review, field verification, etc., check its rationality and accuracy, and if the results are found to be biased or unreasonable, return to the previous steps for correction, such as adjusting model parameters, reselecting the model, etc. After evaluation and confirmation, the target effective sea area disaster rate is output as the final result. The target effective sea area disaster rate more accurately reflects the impact of resource exploitation on the marine environment and the first sea area disaster risk. This result is an important basis for sea area regulation and management.

[0041] In a possible implementation, step S700 further includes step S710, generating a first effective remote sensing environment time series according to a first mapping relationship between the first remote sensing time and the first effective remote sensing environment. Specifically, the time range for generating the first effective remote sensing environment time series is clarified, and this time range is consistent with or includes the target unit cycle. Based on the corresponding relationship between the first remote sensing time and the first effective remote sensing environment, a mapping relationship from time to environment is constructed, and the first effective remote sensing environment data corresponding to each time point is organized in chronological order to form a first effective remote sensing environment time series. Step S720, predictive analysis is performed on the first effective remote sensing environment time series in combination with the target unit cycle to obtain a first predicted target environment. Specifically, a prediction method is selected according to the characteristics of the first effective remote sensing environment time series, such as time series analysis, machine learning algorithm, etc. The target unit cycle is used as a prediction time window and input into the trained model to perform predictive analysis, that is, based on historical data and environmental change trends, future environmental conditions are predicted to obtain a first predicted target environment. Step S730, using the first prediction data formed based on the first prediction target environment as input information of the second sea area disaster prediction model to obtain second output information, wherein the second output information includes the second target sea area disaster rate. Specifically, the first prediction target environment data is sorted into a format suitable for the input of the second sea area disaster prediction model, and the first prediction target environment data is used as input information and sent to the second sea area disaster prediction model, wherein the second sea area disaster prediction model is a model that predicts the probability of occurrence of the first sea area disaster based on environmental data. The second sea area disaster prediction model calculates the second target sea area disaster rate based on the input environmental data, combined with internal algorithms and parameters, and the second target sea area disaster rate is calculated by the second sea area disaster prediction model, and is the probability of occurrence of the first sea area disaster in the predetermined sea area within the target unit period. Step S740, taking the average of the target sea area disaster rate and the second target sea area disaster rate as the target effective sea area disaster rate. Specifically, the target sea area disaster rate and the second target sea area disaster rate are summarized, and the two sea area disaster rates are averaged to obtain the target effective sea area disaster rate. The target effective sea area disaster rate is a combination of historical disaster data, environmental prediction data and model prediction results, and is the probability of the first sea area disaster occurring within the target unit period. This implementation method not only takes into account the actual situation of historical disasters, but also incorporates the prediction information of future environmental changes. By taking the average of the two sea area disaster rates, it balances the impact of historical data and prediction data, achieving the technical effect of obtaining a more comprehensive and accurate disaster risk assessment result.

[0042] In a possible implementation, step S700 further includes step S750, obtaining a first scatter plot of the first effective remote sensing environment time series. Specifically, the time points and corresponding environmental data in the first effective remote sensing environment time series are plotted on a two-dimensional plane as coordinate points, and the graph formed by these coordinate points is the first scatter plot, which intuitively shows the trend of environmental data changing over time. Step S760, regressing and fitting the first scatter plot using the random sampling consistency principle to obtain a first fitting formula. Specifically, a portion of data points are randomly selected from the first scatter plot as a sample set, and different models (such as linear models, polynomial models, etc.) are tried to fit the sample set in an iterative manner, and the number of internal points (i.e., data points that meet the model prediction) corresponding to each model is calculated, and the model with the largest number of internal points and the smallest error is selected as the best fitting model, and its corresponding fitting formula (i.e., the first fitting formula) is determined. The first fitting formula is obtained by the random sampling consistency principle algorithm, and is the mathematical model expression that best represents the distribution law of data points in the first scatter plot. Step S770, analyzing the first fitting formula in combination with the target unit cycle to obtain the second target sea area disaster rate. Specifically, the time point of the target unit cycle is mapped to the first fitting formula to obtain the corresponding environmental data prediction value, and the second target sea area disaster rate is evaluated based on the environmental data prediction value, combined with the law of occurrence of disasters in the predetermined sea area and the empirical formula (or model). This implementation method directly converts the change trend of environmental data into the prediction result of disaster risk by analyzing the first fitting formula in combination with the target unit cycle, avoiding complex model conversion and multiple calculations, and achieving the technical effect of improving prediction efficiency and accuracy.

[0043] Step S800, the predetermined sea area is regulated and managed according to the target effective sea area disaster rate. Specifically, according to the target effective sea area disaster rate, a targeted sea area regulation and management strategy is formulated, including restrictions or adjustments on resource exploitation, protection measures for the marine environment, and improvement of disaster warning and emergency response mechanisms. Among them, for resource exploitation activities, a reasonable exploitation plan and quota are formulated according to the disaster risk and environmental carrying capacity of the first sea area, and the damage and disaster risk to the marine ecosystem are reduced by limiting the intensity of exploitation and optimizing the layout of exploitation; the protection and restoration of the marine environment are strengthened, such as implementing the marine protected area system, carrying out marine ecological restoration projects, etc., strengthening the supervision and control of pollution sources, and reducing the impact of pollutant emissions on the marine environment; improving the marine disaster warning system, improving the accuracy and timeliness of the warning, and formulating a detailed emergency response plan to ensure that response and rescue work can be carried out quickly and effectively when a disaster occurs. The embodiment of the present application uses multiple remote sensing devices to obtain sea area spatial data, including resource data and environmental data. Through fusion analysis, the sea area conditions are comprehensively and real-time grasped. Based on historical disaster data and real-time remote sensing data, time series feature analysis is used to accurately predict sea area disasters. The correlation between resource exploitation activities and marine environmental changes is analyzed through the weighted coefficient of variation method. According to the disaster prediction results and ecological and environmental impact analysis, targeted sea area regulation and management strategies and other technical means are formulated to ensure that the balance between the ecological environment and resource exploitation is continuously maintained, and the technical effect of achieving a dynamic balance between the ecological environment and resource exploitation is achieved.

[0044] In the above, refer to Figure 1 The method for managing marine spatial data by dynamic remote sensing monitoring according to an embodiment of the present invention is described in detail. Figure 2 A device for managing marine spatial data through dynamic remote sensing monitoring according to an embodiment of the present invention is described.

[0045] The device for managing marine spatial data by dynamic remote sensing monitoring according to the embodiment of the present invention is used to solve the technical problem that the existing marine spatial data management is insufficient in terms of the balance between ecological environment and resource exploitation, and achieve the technical effect of achieving a dynamic balance between ecological environment and resource exploitation. The device for managing marine spatial data by dynamic remote sensing monitoring includes: a first historical marine disaster time series extraction module 10, a target marine disaster rate acquisition module 20, a predetermined remote sensing strategy calling module 30, a predetermined remote sensing time series acquisition module 40, a first remote sensing time matching module 50, a first effective remote sensing environment acquisition module 60, a target effective marine disaster rate acquisition module 70, and a marine regulation and management module 80.

[0046] The first historical sea area disaster time series extraction module 10 is used to extract the first sea area disaster among the natural disasters in the predetermined sea area, and obtain the first historical sea area disaster time series of the first sea area disaster in the predetermined sea area; the target sea area disaster rate acquisition module 20 is used to perform time series feature analysis on the first historical sea area disaster time series based on a predetermined unit period, and obtain the target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in the target unit period; the predetermined remote sensing strategy calling module 30 is used to issue a remote sensing monitoring instruction when the target sea area disaster rate reaches a predetermined probability threshold, and call a predetermined remote sensing strategy based on the remote sensing monitoring instruction; the predetermined remote sensing time series acquisition module 40 is used to activate multiple remote sensing devices to perform multi-source remote sensing feature monitoring on the predetermined sea area according to the predetermined remote sensing strategy, and obtain A predetermined remote sensing timing sequence, wherein the predetermined remote sensing timing sequence includes a predetermined remote sensing resource timing sequence and a predetermined remote sensing environment timing sequence; a first remote sensing time matching module 50 is used to read a first remote sensing time, and sequentially match a first remote sensing resource and a first remote sensing environment under the first remote sensing time in the predetermined remote sensing resource timing sequence and the predetermined remote sensing environment timing sequence; a first effective remote sensing environment acquisition module 60 is used to adjust the first remote sensing environment by using a first coefficient obtained by weighting the first remote sensing resource with a coefficient of variation as a weight, and obtain a first effective remote sensing environment; a target effective sea area disaster rate acquisition module 70 is used to analyze and verify the target sea area disaster rate according to the first effective remote sensing environment, and obtain a target effective sea area disaster rate; a sea area regulation and management module 80 is used to perform sea area regulation and management on the predetermined sea area according to the target effective sea area disaster rate.

[0047] The specific configuration of the target sea area disaster rate acquisition module 20 will be described in detail below. As described above, the target sea area disaster rate acquisition module 20 may further include: a time zone division unit for performing time zone division on the first historical sea area disaster time series based on the predetermined unit period to obtain a first time series division result, wherein the first time series division result includes a plurality of unit time zones with a first sea area disaster frequency identifier; a multi-domain feature collection unit for performing multi-domain feature collection on the first disaster frequency time series generated based on the plurality of unit time zones with a first sea area disaster frequency identifier to obtain a first multi-domain feature set; a target sea area disaster rate output unit for using the first multi-domain feature set as input information of a first sea area disaster prediction model to obtain first output information, wherein the first sea area disaster prediction model is an intelligent model obtained by supervised learning of the data in the first historical sea area disaster time series.

[0048] Among them, the multi-domain feature collection unit may further include: a time domain feature collection subunit for collecting time domain features of the first disaster frequency time series to obtain a first time domain feature set; a frequency domain feature collection subunit for collecting frequency domain features of the first disaster spectrum obtained by converting the first disaster frequency time series to obtain a first frequency domain feature set; a first multi-domain feature set construction subunit for combining the first time domain feature set and the first frequency domain feature set to form the first multi-domain feature set.

[0049] The specific configuration of the target effective sea area disaster rate acquisition module 70 will be described in detail below. As described above, the target effective sea area disaster rate acquisition module 70 may further include: a first effective remote sensing environment time series generation unit for generating a first effective remote sensing environment time series according to a first mapping relationship between the first remote sensing time and the first effective remote sensing environment; a predictive analysis unit for performing predictive analysis on the first effective remote sensing environment time series in combination with the target unit period to obtain a first predicted target environment; a second target sea area disaster rate output unit for using the first prediction data formed based on the first predicted target environment as input information of a second sea area disaster prediction model to obtain second output information, wherein the second output information includes a second target sea area disaster rate; and a target effective sea area disaster rate calculation unit for taking the average of the target sea area disaster rate and the second target sea area disaster rate as the target effective sea area disaster rate.

[0050] Among them, the target effective sea area disaster rate acquisition module 70 can further include: a first scatter plot acquisition unit is used to obtain a first scatter plot of the first effective remote sensing environment time series; a regression fitting unit is used to perform regression fitting on the first scatter plot using the random sampling consistency principle to obtain a first fitting formula; a first fitting formula analysis unit is used to analyze the first fitting formula in combination with the target unit period to obtain the second target sea area disaster rate.

[0051] The specific configuration of the predetermined remote sensing time series acquisition module 40 will be described in detail below. As described above, the predetermined remote sensing time series acquisition module 40 may further include: an arbitrary sea area coordinate acquisition unit for randomly extracting any remote sensing characteristic parameter in the predetermined remote sensing time series, and obtaining the arbitrary sea area coordinates of the arbitrary remote sensing characteristic parameter; a spatial distance value calculation unit for obtaining the predetermined sea area coordinates of the predetermined sea area, and calculating the spatial distance value between the predetermined sea area coordinates and the arbitrary sea area coordinates; and an arbitrary remote sensing characteristic parameter adjustment unit for adjusting the arbitrary remote sensing characteristic parameter using the spatial distance value as a coefficient.

[0052] Among them, the spatial distance value calculation unit can further include: a Euclidean distance calculation subunit for calculating the Euclidean distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; a Manhattan distance calculation subunit for calculating the Manhattan distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; and a mean calculation subunit for taking the mean of the Euclidean distance and the Manhattan distance as the spatial distance value.

[0053] The device for managing sea area spatial data through dynamic remote sensing monitoring provided in the embodiment of the present invention can execute the method for managing sea area spatial data through dynamic remote sensing monitoring provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0054] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0055] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. Methods of managing marine spatial data through dynamic remote sensing monitoring. It is characterized in that include: Extracting a first sea area disaster from the predetermined sea area natural disasters, and obtaining a first historical sea area disaster time series of the first sea area disaster in the predetermined sea area; Performing a time series characteristic analysis on the first historical sea area disaster time series based on a predetermined unit period to obtain a target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in the target unit period; When the disaster rate of the target sea area reaches a predetermined probability threshold, a remote sensing monitoring instruction is issued, and a predetermined remote sensing strategy is called based on the remote sensing monitoring instruction; activating multiple remote sensing devices according to the predetermined remote sensing strategy to perform multi-source remote sensing feature monitoring on the predetermined sea area to obtain a predetermined remote sensing time sequence, wherein the predetermined remote sensing time sequence includes a predetermined remote sensing resource time sequence and a predetermined remote sensing environment time sequence; Reading a first remote sensing time, and sequentially matching a first remote sensing resource and a first remote sensing environment at the first remote sensing time in the predetermined remote sensing resource timing and the predetermined remote sensing environment timing; The first remote sensing environment is adjusted by using a first coefficient obtained by weighting the first remote sensing resource with a coefficient of variation as a weight to obtain a first effective remote sensing environment, wherein the first coefficient is a weighted sum of the coefficient of variation of each resource parameter in the first remote sensing resource and their respective weights, and the first coefficient reflects the overall degree of change and importance of the first remote sensing resource; Analyze and verify the target sea area disaster rate according to the first effective remote sensing environment to obtain the target effective sea area disaster rate; The predetermined sea area is regulated and managed according to the target effective sea area disaster rate.

2. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 1, It is characterized in that include: Based on the predetermined unit period, the first historical sea area disaster time series is divided into time zones to obtain a first time series division result, wherein the first time series division result includes a plurality of unit time zones with a first sea area disaster frequency identifier; Collecting multi-domain features of the first disaster frequency time series generated based on the multiple unit time zones with the first sea area disaster frequency identifiers to obtain a first multi-domain feature set; Using the first multi-domain feature set as input information of a first marine disaster prediction model to obtain first output information, wherein the first output information includes the target marine disaster rate; Among them, the first sea area disaster prediction model is an intelligent model obtained by supervised learning of the data in the first historical sea area disaster time series.

3. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 2, It is characterized in that include: Collecting time domain features of the first disaster frequency time series to obtain a first time domain feature set; Collecting frequency domain features of a first disaster spectrum obtained by converting the first disaster frequency time series to obtain a first frequency domain feature set; The first time domain feature set and the first frequency domain feature set constitute the first multi-domain feature set.

4. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 1, It is characterized in that include: Generate a first effective remote sensing environment time sequence according to a first mapping relationship between the first remote sensing time and the first effective remote sensing environment; Performing predictive analysis on the first effective remote sensing environment time series in combination with the target unit period to obtain a first predicted target environment; Using the first prediction data formed based on the first prediction target environment as input information of a second sea area disaster prediction model to obtain second output information, wherein the second output information includes a second target sea area disaster rate; The average of the target sea area disaster rate and the second target sea area disaster rate is taken as the target effective sea area disaster rate.

5. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 4, It is characterized in that include: Acquire a first scatter plot of the first effective remote sensing environment time series; Performing regression fitting on the first scatter plot using the random sampling consistency principle to obtain a first fitting formula; The first fitting formula is analyzed in combination with the target unit period to obtain the second target sea area disaster rate.

6. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 1, It is characterized in that Also includes: Randomly extracting any remote sensing characteristic parameter in the predetermined remote sensing time series, and obtaining any sea area coordinates of the arbitrary remote sensing characteristic parameter; Acquire the predetermined sea area coordinates of the predetermined sea area, and calculate the spatial distance value between the predetermined sea area coordinates and the arbitrary sea area coordinates; The arbitrary remote sensing characteristic parameter is adjusted using the spatial distance value as a coefficient.

7. The method for managing marine spatial data by dynamic remote sensing monitoring according to claim 6, It is characterized in that include: Calculating the Euclidean distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; Calculating the Manhattan distance between the predetermined sea area coordinates and the arbitrary sea area coordinates; The average of the Euclidean distance and the Manhattan distance is taken as the spatial distance value.

8. Device for dynamic remote sensing monitoring and management of marine spatial data. It is characterized in that The device is used to implement the method for managing marine spatial data through dynamic remote sensing monitoring as described in any one of claims 1 to 7, and the device comprises: A first historical sea area disaster time series extraction module, the first historical sea area disaster time series extraction module is used to extract a first sea area disaster from a predetermined sea area natural disaster, and obtain a first historical sea area disaster time series of the first sea area disaster in the predetermined sea area; A target sea area disaster rate acquisition module, the target sea area disaster rate acquisition module is used to perform a time series feature analysis on the first historical sea area disaster time series based on a predetermined unit period to obtain a target sea area disaster rate, wherein the target sea area disaster rate refers to the probability of the first sea area disaster occurring in the predetermined sea area in a target unit period; A predetermined remote sensing strategy calling module, wherein the predetermined remote sensing strategy calling module is used to issue a remote sensing monitoring instruction when the disaster rate of the target sea area reaches a predetermined probability threshold, and to call a predetermined remote sensing strategy based on the remote sensing monitoring instruction; A predetermined remote sensing timing acquisition module, the predetermined remote sensing timing acquisition module is used to activate multiple remote sensing devices to perform multi-source remote sensing feature monitoring on the predetermined sea area according to the predetermined remote sensing strategy to obtain a predetermined remote sensing timing, the predetermined remote sensing timing including a predetermined remote sensing resource timing and a predetermined remote sensing environment timing; A first remote sensing time matching module, the first remote sensing time matching module is used to read a first remote sensing time, and sequentially match a first remote sensing resource and a first remote sensing environment at the first remote sensing time in the predetermined remote sensing resource timing and the predetermined remote sensing environment timing; A first effective remote sensing environment acquisition module, the first effective remote sensing environment acquisition module is used to adjust the first remote sensing environment by using a first coefficient obtained by weighting the first remote sensing resource with a coefficient of variation as a weight, so as to obtain a first effective remote sensing environment, wherein the first coefficient is a weighted sum of the coefficient of variation of each resource parameter in the first remote sensing resource and their respective weights, and the first coefficient reflects the overall degree of change and importance of the first remote sensing resource; A target effective sea area disaster rate acquisition module, the target effective sea area disaster rate acquisition module is used to analyze and verify the target sea area disaster rate according to the first effective remote sensing environment to obtain the target effective sea area disaster rate; A sea area regulation and management module is used to perform sea area regulation and management on the predetermined sea area according to the target effective sea area disaster rate.