Typical marine ecological disaster remote sensing monitoring method, device, equipment and medium

Abstract

The invention discloses a typical marine ecological disaster remote sensing monitoring method, device and equipment and a medium, and relates to the technical field of remote sensing monitoring, and the method comprises the steps: obtaining marine algae ecological disaster monitoring data from land-sea multi-source satellite remote sensing data; classifying marine algae ecological disasters in the marine algae ecological disaster monitoring data by using a pre-constructed marine algae ecological disaster recognition algorithm; performing three-dimensional quantitative measurement on the classified marine algae ecological disasters to obtain characteristics and heights of the marine algae ecological disasters; and predicting the offset trajectory of the marine algae ecological disaster according to the characteristics and height of the marine algae ecological disaster. According to the invention, land-sea multi-source satellite remote sensing data are fully utilized to monitor the ecological disasters of the marine algae, and more accurate, intelligent, comprehensive and effective information support can be provided for monitoring and supervision of the ecological disasters of the marine algae.

Description

Technical Field

[0001] This application relates to the field of remote sensing monitoring technology, and particularly to a method, device, equipment and medium for remote sensing monitoring of typical marine ecological disasters. Background Art

[0002] The remote sensing monitoring solutions for marine algal ecological disasters have been continuously improving. From relying on medium-resolution satellite images in the early stage, to gradually adopting high-resolution drone images, and now to processing satellite data based on deep learning models, the application of new technologies has continuously improved the accuracy and production efficiency of marine algal ecological disaster monitoring products. However, there are still problems such as a single data source, limited data coverage, and difficulty in meeting the actual application requirements in terms of data accuracy in the current marine ecological satellite remote sensing intelligent monitoring solutions and information application services. Summary of the Invention

[0003] The main purpose of the embodiments of this application is to propose a method, device, equipment and medium for remote sensing monitoring of typical marine ecological disasters, so as to improve the monitoring accuracy of marine algal ecological disasters.

[0004] To achieve the above purpose, on the one hand, an embodiment of this application proposes a method for remote sensing monitoring of typical marine ecological disasters, and the method includes the following steps: Obtain marine algal ecological disaster monitoring data from multi-source land-sea satellite remote sensing data; Classify the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm; Perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; Predict the offset trajectory of the marine algal ecological disasters according to the characteristics and height of the marine algal ecological disasters.

[0005] In some embodiments, the obtaining marine algal ecological disaster monitoring data from multi-source land-sea satellite remote sensing data includes the following steps: Obtain the first marine algal ecological disaster monitoring data from marine satellite remote sensing data; Obtain the second marine algal ecological disaster monitoring data from the high-resolution image data in the land satellite remote sensing data; Obtain the third marine algal ecological disaster monitoring data from the satellite laser altimetry data in the land satellite remote sensing data.

[0006] In some embodiments, before the classifying the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm, the method further includes the following steps: Fuse the data from different data sources in the monitoring data of marine algal ecological disasters.

[0007] In some embodiments, the steps of pre - constructing the recognition algorithm for marine algal ecological disasters include the following steps: Obtain the prior information of the marine water environment, marine meteorology, satellite spectra and texture information before and after the occurrence of marine algal ecological disaster events; Use the time - series correlation analysis method to obtain target indicative parameters according to the marine water environment, the marine meteorology, the satellite spectra and the texture information; Construct the pixel - by - pixel recognition algorithm for marine algal ecological disasters by combining the target indicative parameters and the XGBOOST machine learning algorithm.

[0008] In some embodiments, the three - dimensional quantitative measurement of the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters includes the following steps: Extract the spectral characteristics and index characteristics of the marine algal ecological disasters classified according to optical data, and extract the first texture characteristics of the marine algal ecological disasters using the first three components of the principal component analysis of the original image; Extract the backscattering coefficient of the marine algal ecological disasters classified according to SAR data and extract the second texture characteristics of the marine algal ecological disasters from the backscattering coefficient; Extract the elevation characteristics of the marine algal ecological disasters classified according to elevation data; Perform feature selection and dimensionality reduction on the spectral characteristics, the index characteristics, the first texture characteristics, the second texture characteristics and the elevation characteristics through the random forest algorithm; Use a laser altimetry satellite to monitor and extract the growth range of the classified marine algal ecological disasters and the sea surface height around them.

[0009] In some embodiments, the prediction of the offset trajectory of the marine algal ecological disaster according to the characteristics and height of the marine algal ecological disaster includes the following steps: Based on marine satellite remote sensing data, establish a trajectory prediction model for marine algal ecological disasters using a mesoscale meteorological model, an unstructured grid near - shore ocean model and Monte Carlo random statistical theory; Use the trajectory prediction model for marine algal ecological disasters based on the drift motion of the marine algal ecological disasters under the action of the marine surface fluid and wind, and calculate the wind - induced drift of the marine algal ecological disasters using the velocity decomposition method; Using the marine algal ecological disaster trajectory prediction model, the Monte Carlo method is applied to predict and generate a statistically significant and time-evolving optimal trajectory region according to a plurality of drifting particles arranged in the region and time period where the marine algal ecological disaster is first observed, as well as various random and uncertain factors during the drifting process; Using the marine algal ecological disaster trajectory prediction model, calculate the candidate shore contact information of the marine algal ecological disaster according to specific marine and meteorological conditions.

[0010] In some embodiments, the method further includes the following steps: Output monitoring and early warning information according to the deviation trajectory of the marine algal ecological disaster.

[0011] To achieve the above object, on the other hand, an embodiment of the present application provides a remote sensing monitoring device for typical marine ecological disasters, the device includes: A data acquisition unit, configured to acquire marine algal ecological disaster monitoring data from multi-source land and sea satellite remote sensing data; An algae classification unit, configured to classify the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm; An algae measurement unit, configured to perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; A marine algal ecological disaster trajectory prediction unit, configured to predict the deviation trajectory of the marine algal ecological disaster according to the characteristics and height of the marine algal ecological disaster.

[0012] To achieve the above object, on the other hand, an embodiment of the present application provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the above method is implemented.

[0013] To achieve the above object, on the other hand, an embodiment of the present application provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above method is implemented.

[0014] The embodiments of the present application at least include the following beneficial effects: This application can obtain marine algal ecological disaster monitoring data from multi-source satellite remote sensing data on land and sea; classify marine algal ecological disasters in the marine algal ecological disaster monitoring data using a pre-constructed marine algal ecological disaster recognition algorithm; perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; and predict the offset trajectory of the marine algal ecological disasters based on the characteristics and height of the marine algal ecological disasters. This application makes full use of multi-source satellite remote sensing data on land and sea to monitor marine algal ecological disasters, and can provide more accurate, intelligent, comprehensive, and effective information support for the monitoring and supervision of marine algal ecological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of this application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 It is a schematic flowchart of a typical marine ecological disaster remote sensing monitoring method provided by an embodiment of this application; Figure 2 It is an example flowchart of a typical marine ecological disaster remote sensing monitoring method provided by an embodiment of this application; Figure 3 It is a true-color image spatial distribution map of a marine algal ecological disaster provided by an embodiment of this application; Figure 4 It is a distribution map of the scope of a marine algal ecological disaster provided by an embodiment of this application; Figure 5 It is another true-color image spatial distribution map of a marine algal ecological disaster provided by an embodiment of this application; Figure 6 It is a schematic structural diagram of a typical marine ecological disaster remote sensing monitoring device provided by an embodiment of this application; Figure 7 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] In order to make the objectives, technical solutions, and advantages of the present application more clearly understood, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely used to explain the present application and are not intended to limit the present application. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numerals in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods that are consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0018] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if", "when" as used herein may be interpreted as "when...", "while...", or "in response to determining".

[0019] The terms "at least one", "a plurality of", "each", "any one", etc. used in the present application, at least one includes one, two, or more than two, a plurality of includes two or more than two, each refers to each one of the corresponding plurality, and any one refers to any one of the plurality.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0021] Before elaborating on the embodiments of the present application in detail, some related technologies involved in the embodiments of the present application are described as follows:

[0022] Marine remote sensing ecological monitoring such as marine algal ecological disasters involves various aspects of work, including the detection, precise measurement, trajectory prediction, and intelligent monitoring information services of algal disasters. Among them, in terms of the detection of marine algal ecological disasters, medium-resolution satellites represented by MODIS, Sentinel-3, HY-1C / D, etc. are one of the most effective means for carrying out marine algal ecological disaster monitoring on a large regional scale due to their more sensitive band responses, larger swath widths, and higher revisit periods. The methods for extracting information on marine algal ecological disasters in the floating state using satellite remote sensing technology mainly include supervised classification method, large phytoplankton index method, sea surface algal bloom index method, floating algae index method, virtual baseline floating algae index method, water color index algorithm, normalized vegetation index method, discriminant index algorithm, marine algal ecological disaster index algorithm, green light algal body index method, single-band extraction method, double-band ratio method, double-band difference method, and the combination method of true color method and band ratio method, etc. Among them, the identification of medium-resolution remote sensing marine algal ecological disasters is basically based on the spectral derivative index threshold segmentation method. For example, Related Technology 1 proposed using the maximum chlorophyll index to identify marine algal ecological disasters in the Gulf of Mexico and the North Atlantic based on MERIS (Medium Resolution Imaging Spectrometer) data, which promoted the subsequent systematic understanding of the development trend of marine algal ecological disasters in this sea area. Related Technology 2 proposed the Enteromorpha prolifera marine algal ecological disaster index and the marine algal ecological disaster index algorithm based on MODIS satellite data to distinguish Enteromorpha prolifera and marine algal ecological disasters. Related Technology 3 extracted the algal spectral curve based on MODIS data and calculated the AFAI index, extracted the spatio-temporal coverage area of marine algal ecological disasters, and plotted their floating paths. In terms of the precise measurement of marine algal ecological disaster monitoring, researchers used data from medium- and low-resolution satellites (such as MODIS, MERIS, etc.) to achieve the extraction of large-scale marine algal ecological disaster blooms in large-scale scenes. However, due to the influence of spatial resolution, it is impossible to effectively detect small patches of marine algal ecological disasters and it is difficult to meet the tracking monitoring of the temporal and sequential changes of marine algal ecological disaster blooms. The emergence of high-spatial-resolution images makes up for the problem of ineffective monitoring of small marine algal ecological disasters. However, high-spatial-resolution images have the problem of insufficient spectral resolution. When multiple large algae appear in the same sea area at the same time, it becomes a difficult point to effectively distinguish marine algal ecological disasters from other large algae. In addition, in terms of the trajectory early warning monitoring of marine algal ecological disasters, researchers used the advanced ROMS model and Lagrangian method to deeply study the characteristics of the Kuroshio path and verified the effectiveness of this method through comparison with various data.Since the 1990s, the Lagrangian method based on high-resolution numerical models has gradually matured and been widely used in the research of phenomena such as ocean circulation, ocean fronts, and pollutant diffusion. Related technology 4 used the ROMS model and the Lagrangian method to study the complete Kuroshio path and its characteristics. Related technology 5 used the Lagrangian method to study the potential risk areas of the occurrence of the Alexandrium toxic bloom in the northern continental shelf of Patagonia, Chile. Related technology 6 compared the results of passive Eulerian tracers and Lagrangian particle trajectories in the drift of cod eggs and larvae. The Lagrangian model allows behavioral characteristics to be parameterized in various ways and has good flexibility. In the research and development of intelligent monitoring products and information application services for marine ecological satellite remote sensing, domestic and foreign research institutions are actively researching and exploring the application value of marine ecological satellite remote sensing monitoring data. By deeply mining and analyzing remote sensing data, the changing laws of the marine environment can be monitored, and problems such as marine pollution and ecological disasters can be discovered and warned in a timely manner. The technology for the research and development of remote sensing monitoring products for marine algal ecological disasters and the like is also continuously progressing. From relying on medium-resolution satellite images in the early stage, to gradually adopting high-resolution drone images, and now to processing satellite data based on deep learning models, the application of new technologies has continuously improved the accuracy and production efficiency of marine algal ecological disaster monitoring products. However, there are still problems such as a single data source, limited data coverage, and difficulty in meeting the actual application requirements of data product accuracy in the research and development of intelligent monitoring products and information application services for marine ecological satellite remote sensing. Through multi-sensor multi-source satellite remote sensing data fusion monitoring, and the application and empowerment of technologies such as big data and artificial intelligence, the potential for mining marine ecological monitoring data by satellite remote sensing can be further stimulated, and more accurate and intelligent marine ecological satellite remote sensing intelligent monitoring products and information application services can be developed and constructed, providing more accurate, intelligent, comprehensive, and effective information support for marine ecological monitoring and supervision.

[0023] However, the existing technologies have technical problems: Technical problem one: Research on the key technologies for the fine identification and monitoring of marine algal ecological disasters.

[0024] Aiming at the problem that the current traditional marine remote sensing satellites are not accurate enough in identifying marine algal ecological disasters and have a relatively high boundary misjudgment rate, research on the key technologies for the fine identification and monitoring of marine algal ecological disasters by medium-resolution satellite remote sensing is carried out for tropical and subtropical marine algal ecological disasters. Specifically, the occurrence processes (formation, development, migration, disappearance) of different marine algal ecological disasters are discussed.

[0025] Relationships with different marine environmental parameters (such as temperature, salinity, nutrient concentration, flow velocity, light, etc.), clarify their internal influence mechanisms, select key influencing parameters, and combine the spectral and texture information carried by ocean satellites to construct an identification algorithm for marine algal ecological disasters. At the same time, carry out research on the refined identification of the boundaries of marine algal ecological disaster areas and the fusion technology of disaster extraction results for multiple regions at multiple time phases in a single day, make the most of the advantages of multi-satellite high-frequency revisit, and achieve the timely identification and discovery of marine algal ecological disasters.

[0026] Technical problem two: Research on the three-dimensional quantitative measurement technology for marine algal ecological disasters.

[0027] Aiming at the problem of relatively large relative spatial scale in the monitoring of marine algal ecological disasters by ocean remote sensing satellites, based on the fine identification of marine algal ecological disasters using medium-resolution ocean satellite remote sensing, carry out research on the accurate identification technology for marine algal ecological disasters by combining multi-source remote sensing images of land high-resolution satellites with feature optimization, further improve the identification fineness of marine algal ecological disasters. Specifically, use multi-source high-resolution remote sensing data to obtain multi-dimensional feature information of marine algal ecological disasters including thickness, texture, and morphological features, then study feature optimization technology for feature information screening and optimization, and study the construction of an identification model for marine algal ecological disasters through machine learning or deep learning models to achieve construction based on the optimal multi-source feature set; in addition, based on the high-precision extraction of marine algal ecological disasters, combine satellite altimetry and ocean dynamics to carry out research on the three-dimensional quantitative calculation technology for marine algal ecological disasters, process and analyze the data obtained by using altimetry technology, establish a three-dimensional distribution model of marine algal ecological disasters, and achieve accurate quantitative calculation of the vertical distribution of marine algal ecological disasters in the water body.

[0028] Technical problem three: Research on the trajectory prediction technology for marine algal ecological disasters.

[0029] Aiming at the problem of trajectory drift in the prediction of marine algal ecological disaster trajectories caused by the influence of marine environmental factors such as marine meteorology, sea waves, and flow fields, research and use ocean dynamics and numerical simulation methods, apply Monte Carlo stochastic statistical theory, fully consider the randomness and possible uncertainties in the drift process of drifters, construct a new Lagrangian method for the trajectory prediction model of marine algal ecological disasters, and use this model to provide an important scientific basis for predicting the drift behavior of marine disasters such as marine algal ecological disasters, accurately simulate and predict the drift trajectories and dynamic changes of marine algal ecological disasters, and provide support for relevant marine environmental monitoring and early warning as well as the prevention and control of marine ecological disasters.

[0030] Therefore, the embodiments of the present application provide a method, device, equipment and medium for remotely monitoring typical marine ecological disasters. The technical solution of the present application includes: obtaining marine algae ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea; classifying the marine algae ecological disasters in the marine algae ecological disaster monitoring data by using a pre-constructed marine algae ecological disaster recognition algorithm; performing three-dimensional quantitative measurement on the classified marine algae ecological disasters to obtain the characteristics and height of the marine algae ecological disasters; and predicting the offset trajectory of the marine algae ecological disasters according to the characteristics and height of the marine algae ecological disasters. The present application makes full use of multi-source satellite remote sensing data of land and sea to monitor marine algae ecological disasters, and can provide more accurate, intelligent, comprehensive and effective information support for the monitoring and supervision of marine algae ecological disasters.

[0031] The embodiments of the present application provide a method, device, equipment and medium for remotely monitoring typical marine ecological disasters, which relates to the technical field of remote sensing monitoring. The method, device, equipment and medium for remotely monitoring typical marine ecological disasters provided by the embodiments of the present application can be applied to a terminal, or can be applied to a server, or can also be software running on a terminal or a server. In some embodiments, the terminal may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc., but is not limited thereto; the server side may be configured as an independent physical server, or may be configured as a server cluster or a distributed system composed of multiple physical servers, or may also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server may also be a node server in a blockchain network; the software may be an application implementing a method for remotely monitoring typical marine ecological disasters, etc., but is not limited to the above forms.

[0032] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, hand-held devices or portable devices, tablet-type devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0033] Reference Figure 1 , an embodiment of the present application provides a typical remote sensing monitoring method for marine ecological disasters, which may include but is not limited to S100 to S130, specifically as follows: S100: Obtain marine algal ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea; S110: Classify the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm; S120: Perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; S130: Predict the offset trajectory of the marine algal ecological disasters according to the characteristics and height of the marine algal ecological disasters.

[0034] Optionally, the obtaining of the marine algal ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea includes the following steps: Obtain the first marine algal ecological disaster monitoring data from marine satellite remote sensing data; Obtain the second marine algal ecological disaster monitoring data from the high-resolution image data in the land satellite remote sensing data; Obtain the third marine algal ecological disaster monitoring data from the satellite laser altimetry data in the land satellite remote sensing data.

[0035] Optionally, before the classifying of the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm, the method further includes the following steps: Fuse the data from different data sources in the marine algal ecological disaster monitoring data.

[0036] Optionally, the steps of pre-constructing the marine algal ecological disaster recognition algorithm include the following steps: Obtain the marine water environment, marine meteorology, satellite spectrum and texture information before and after the occurrence of prior marine algal ecological disaster events; Use the time series correlation analysis method to obtain target indicative parameters according to the marine water environment, the marine meteorology, the satellite spectrum and the texture information; Construct the pixel-by-pixel marine algal ecological disaster recognition algorithm by combining the target indicative parameters and the XGBOOST machine learning algorithm.

[0037] Optionally, the performing of the three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters includes the following steps: Extract spectral features and index features for the marine algal ecological disasters classified according to optical data, and extract the first texture feature of the marine algal ecological disasters using the first three components of the principal component analysis of the original image; Extract the backscattering coefficient for the marine algal ecological disasters classified according to SAR data and extract the second texture feature of the marine algal ecological disasters from the backscattering coefficient; Extract the elevation feature of the marine algal ecological disasters classified according to elevation data; Perform feature selection and dimensionality reduction on the spectral features, the index features, the first texture feature, the second texture feature and the elevation feature through the random forest algorithm; Use a laser altimetry satellite to monitor and extract the growth range of the classified marine algal ecological disasters and the sea surface height of the surrounding area.

[0038] Optionally, predicting the offset trajectory of the marine algal ecological disasters based on the features and height of the marine algal ecological disasters includes the following steps: Establish a marine algal ecological disaster trajectory prediction model based on mesoscale meteorological models, unstructured grid nearshore ocean models and Monte Carlo random statistical theory using marine satellite remote sensing data; Use the marine algal ecological disaster trajectory prediction model based on the drift movement of the marine algal ecological disasters under the action of the marine surface fluid and wind force, and calculate the wind-induced drift of the marine algal ecological disasters using the velocity decomposition method; Use the marine algal ecological disaster trajectory prediction model to predict and generate a statistically significant and time-evolving optimal trajectory area using the Monte Carlo method based on multiple drift particles arranged in the area and time period when the marine algal ecological disasters are first observed and various randomness and uncertainty factors during the drift process; Use the marine algal ecological disaster trajectory prediction model to calculate the candidate shore contact information of the marine algal ecological disasters according to specific marine and meteorological conditions.

[0039] Optionally, the method further includes the following steps: Output monitoring and warning information according to the offset trajectory of the marine algal ecological disasters.

[0040] Next, the solution of the embodiment of the present application will be introduced and described in detail in combination with specific application examples.

[0041] Exemplarily, this embodiment may include the following technical solutions: Optionally, the marine algal ecological disasters studied in the present application may include Sargassum, and the monitoring of Sargassum may be carried out with reference to the following embodiments.

[0042] Exemplarily, an optional Sargassum monitoring flowchart based on the solution of this embodiment is as Figure 2 shown.

[0043] First, the technical solution studied in this embodiment will be described.

[0044] Research Content 1: Research on key technologies for fine identification and monitoring of Sargassum in ocean remote sensing satellites.

[0045] The research aims to address the Sargassum ocean disaster, consider the complex coupling relationship between multiple environmental factors, and construct an efficient remote sensing identification algorithm based on big data machine learning algorithms to achieve accurate monitoring and timely identification of the disaster. The specific work content includes collecting disaster-related data and integrating data of different environmental factors, designing and implementing a disaster identification algorithm based on the coupling of multiple environmental factors, determining the main disaster impact factors and impact mechanisms, verifying the accuracy and reliability of the algorithm, and forming an optimal extraction method and best parameters for Sargassum disasters.

[0046] Research Content 2: Research on key technologies for three-dimensional quantitative measurement of Sargassum in ocean land satellites.

[0047] The research focuses on the limitations of traditional Sargassum monitoring methods, which are limited to two-dimensional area monitoring, ignore three-dimensional features, and the data redundancy and potential "curse of dimensionality" caused by the fusion of multiple sources and multiple features. It conducts research on multi-source remote sensing precise area calculation and laser altimetry three-dimensional quantitative measurement technology for Sargassum. By analyzing the correlation between different data sources and their characteristics, using feature selection calculation or machine learning methods to determine the optimal feature set, simplify the data processing flow, reduce redundant information, and reduce the calculation cost, improve the accuracy of remote sensing image processing, enhance the classification and recognition performance of remote sensing images, and provide data and technical support for the precise extraction of Sargassum; at the same time, by using remote sensing technology and digital image processing methods, achieve precise calculation and quantitative analysis of the three-dimensional structure of Sargassum, combine laser altimetry data and multi-source remote sensing images, and use three-dimensional reconstruction technology to conduct three-dimensional quantitative calculation of Sargassum, comprehensively and accurately obtain its three-dimensional structure, growth status, and spatial distribution information, and provide fine measurement data information services for the early warning and prevention of Sargassum disasters.

[0048] Research Content 3: Research on key technologies for predicting the monitoring trajectory of ocean Sargassum.

[0049] Study the operating principle of the numerical prediction model, conduct prediction data processing, and through the analysis of historical numerical prediction data, perform necessary preprocessing and calibration on ocean satellite monitoring data. On this basis, conduct research on the application of numerical prediction data in the ocean convection-diffusion equation to provide a kinetic basis for simulating the diffusion of marine disasters such as Sargassum. Then, through research, construct and solve the non-steady ocean convection-diffusion equation, construct a non-steady ocean convection-diffusion equation with a source term to simulate the movement and diffusion process of Sargassum in the ocean, and develop a complete Lagrangian simulation model of Sargassum. Couple and apply the long-term numerical prediction data results of high-precision ocean meteorology, ocean waves, and flow fields to the precise measurement and prediction of the trajectory change of Sargassum, and finally generate a detailed predicted distribution result of Sargassum in the simulation area and analyze the simulation results.

[0050] Next, the specific research methods of this embodiment will be described.

[0051] Research method 1: A refined identification method for Sargassum based on ocean remote sensing satellites.

[0052] Construct a refined identification algorithm for Sargassum of medium-resolution ocean remote sensing satellites. Taking prior Sargassum disaster events as the research object, collect the ocean water environment, ocean meteorology, satellite spectra, and texture information before and after the disaster. Use the time series correlation analysis method to obtain the main indicative parameters, and combine with the XGBOOST machine learning algorithm to construct a pixel-by-pixel Sargassum disaster classification algorithm. At the same time, carry out mixed response decomposition work on the pixels in the disaster boundary area and conduct disaster identification again to obtain a refined disaster classification result.

[0053] Research method 2: A fine measurement method for Sargassum based on multi-source high-resolution remote sensing images of land satellites and satellite laser altimetry data.

[0054] On the one hand, it involves the Sargassum feature extraction and optimization technology of multi-source remote sensing images: In order to better highlight the Sargassum features and reduce data redundancy at the same time, in this embodiment, through the means of feature optimization, quantitatively evaluate the contribution degree of each feature to the Sargassum extraction result. For optical data, extract spectral features and index features, and at the same time use the first three components of the principal component analysis of the original image to extract texture features. For SAR data, extract the backscattering coefficient and the texture features extracted from the backscattering coefficient. For elevation data, extract the Sargassum elevation feature. In order to reduce feature redundancy, avoid the "curse of dimensionality" and optimize multi-source features at the same time, realize the classification of remote sensing images through the random forest algorithm, and at the same time support work such as feature selection and dimensionality reduction to realize the construction of the optimal feature set of multi-source remote sensing images.

[0055] On the other hand, it involves the technology for extracting the height of Sargassum from laser altimetry data: In this embodiment, by using laser altimetry satellites such as GF-7 and ICESat-2, the sea surface height within the growth range of Sargassum and its surrounding areas is monitored and extracted. Among them, the dual-beam laser altimetry system carried by the GF-7 satellite is used to obtain high-precision elevation control points to improve the elevation accuracy of stereo mapping by optical cameras. ICESat-2 is equipped with a photon-counting LiDAR (Light Detection and Ranging) system and an ATLAS (Advanced Topographic Laser Altimeter System). Mainly for sea surface height data, a Gaussian fitting algorithm is designed to identify the peak and valley features of Sargassum.

[0056] Research method three: The method for predicting the trajectory of Sargassum based on ocean remote sensing satellites.

[0057] In this embodiment, a trajectory prediction model system for Sargassum is established based on ocean satellite remote sensing data, using the mesoscale meteorological model WRF (Weather Research and Forecasting Model), the unstructured grid coastal ocean model FVCOM (Finite-Volume Coastal and Ocean Model), and the Monte Carlo stochastic statistical theory. The model mainly considers the drifting motion of Sargassum under the action of ocean surface fluids and wind, and at the same time adopts the method of velocity decomposition, which is different from the wind deflection angle method widely used in existing prediction models to calculate wind-induced drift. In addition, the model design takes into account the complexity and dynamic changes of the motion of drifting objects. By deploying a large number of drifting particles in the area and time period where Sargassum is first observed, various random and uncertain factors during the drifting process are also considered. Applying the Monte Carlo method, the model prediction is realized, and an optimal trajectory area with statistical significance and evolving over time is generated. At the same time, according to specific ocean and meteorological conditions, the shore-touching information of Sargassum candidates is calculated.

[0058] By constructing a complete business process for data processing and application service development of collaborative monitoring of marine ecology by land and sea satellite remote sensing, relying on big data and cloud services, an intelligent information service system for collaborative monitoring of marine ecology by land and sea remote sensing satellites is developed, and a quantitative monitoring plan for Sargassum is constructed.

[0059] Next, the exemplary implementation solutions of this embodiment will be described in conjunction with the exemplary drawings.

[0060] For the tracking and monitoring of the Sargassum outbreak event in Haikou Bay, by applying the Sargassum remote sensing monitoring method of this embodiment, referring to Figure 3 ... it is found by extracting satellite image remote sensing data that there are still large strip-shaped Sargassum floating in the northern waters of Haikou Bay, with a distribution length of about 34 km and the shortest distance from the shore of about 4 km. It is expected that within the next 48 hours, this Sargassum will drift towards Haikou Bay, and a large amount of Sargassum will pile up on the Haikou beach (see Figure 4). By using satellite remote sensing interpretation and analysis, Sargassum is distributed in a strip pattern about 4 km south of a certain place, with a range length of about 8 km and an area of about 0.09 km 2 , initially judged as the source of Sargassum landing in Haikou Bay recently (see Figure 5 ). It is expected that after this round of Sargassum floats ashore, there may not be a large-scale Sargassum landing phenomenon in the future.

[0061] The beneficial effects of this embodiment include: 1. Refined identification of Sargassum disasters by marine remote sensing satellites considering all elements such as the environment and spectrum.

[0062] On the basis of learning from the traditional satellite's own spectral and texture information for disaster identification, introducing various marine environmental parameter information (such as temperature, salinity, nutrient concentration, flow velocity, light, etc.), improving the accuracy of the corresponding Sargassum algorithm identification. Facing the problem of too high misclassification rate of disaster boundaries, using the mixed pixel decomposition technology for the boundary area to improve the accuracy of the disaster boundary extraction range, developing a fusion algorithm for single-day disaster extraction products, forming a standardized output product, and maximizing the application of the high-frequency revisit advantage of medium-resolution satellites to form a high-precision medium-resolution marine remote sensing satellite Sargassum disaster monitoring product.

[0063] 2. Stereo quantitative monitoring of Sargassum by combining multi-source remote sensing images and lidar data.

[0064] Overcoming the limitations of traditional Sargassum monitoring methods that are limited to two-dimensional area monitoring and ignore the three-dimensional characteristics, as well as the three-dimensional quantitative monitoring technology. By fusing multi-source remote sensing images and satellite remote sensing lidar data, and combining ocean dynamics to construct a three-dimensional height calculation model, breaking through the limitations of traditional monitoring methods and providing a new solution for the three-dimensional quantitative calculation of Sargassum.

[0065] 3. Research on the establishment of a Sargassum regional prediction model and the assimilation processing technology of numerical prediction data.

[0066] Further developing the simulated data of ocean satellite remote sensing numerical prediction, applying the long-term numerical prediction data results of high-precision ocean meteorology, ocean waves, flow fields, etc. to the simulation of Sargassum trajectories. At the same time, innovatively combining the Lagrangian method and the Monte Carlo random statistical theory, simulating the corresponding uncertainties through random sampling, and providing a probabilistic result for evaluating possible trajectory predictions under different conditions.

[0067] Referring to Figure 6 , this application embodiment also provides a typical marine ecological disaster remote sensing monitoring device, which can implement the above-mentioned typical marine ecological disaster remote sensing monitoring method. The device includes: A data acquisition unit for acquiring marine algae ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea; An algal taxon is used to classify marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre - constructed recognition algorithm for marine algal ecological disasters; An algal measurement unit is used to perform three - dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; A marine algal ecological disaster trajectory prediction unit is used to predict the offset trajectory of the marine algal ecological disasters based on the characteristics and height of the marine algal ecological disasters.

[0068] It can be understood that the content in the above - mentioned method embodiments is applicable to the device embodiments. The functions specifically implemented in the device embodiments are the same as those in the above - mentioned method embodiments, and the beneficial effects achieved are also the same as those in the above - mentioned method embodiments.

[0069] An embodiment of the present application also provides an electronic device. The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method of the embodiment of the present application is implemented. The electronic device can be any intelligent terminal including a tablet computer, an in - vehicle computer, etc.

[0070] It can be understood that the content in the above - mentioned method embodiments is applicable to the device embodiments. The functions specifically implemented in the device embodiments are the same as those of the method of the present application, and the beneficial effects achieved are also the same as those of the method of the present application.

[0071] Please refer to Figure 7 , Figure 7 which schematically shows the hardware structure of an electronic device in another embodiment. The electronic device includes: A processor 701, which can be implemented in ways such as a general - purpose CPU (Central Processing Unit), a microprocessor, an application - specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; A memory 702, which can be implemented in forms such as a read - only memory (ROM), a static storage device, a dynamic storage device, or a random - access memory (RAM). The memory 702 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 702, and are called by the processor 701 to execute the method of the embodiments of the present application; An input / output interface 703 for implementing information input and output; A communication interface 704 for implementing communication interaction between this device and other devices, which can implement communication through a wired manner (such as USB, network cable, etc.) or through a wireless manner (such as mobile network, WIFI, Bluetooth, etc.); A bus 705 for transmitting information between various components of the device (such as a processor 701, a memory 702, an input / output interface 703, and a communication interface 704); Among them, the processor 701, the memory 702, the input / output interface 703, and the communication interface 704 are communicatively connected to each other inside the device through the bus 705.

[0072] The embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the method of the present application is implemented.

[0073] It can be understood that the content in the above method embodiments is applicable to the present storage medium embodiment. The functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0074] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory can optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0075] The embodiments described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0076] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or combine some steps, or different steps.

[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0078] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0079] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of this application and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0080] It should be understood that in this application, "at least one (item)" means one or more, and "multiple" means two or more. "And / or" is used to describe the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally means that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or a similar expression means any combination of these items, including any combination of single item (one) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a, b, and c", where a, b, c can be single or multiple.

[0081] In several embodiments provided by this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0082] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be 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.

[0083] In addition, in each embodiment of this application, the functional units 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. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit 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 this application, in essence, or the part that contributes to the prior art, or all or 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 multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of this application. And the foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store programs.

[0085] The preferred embodiments of the embodiments of this application have been described above with reference to the accompanying drawings. However, this does not limit the scope of the rights of the embodiments of this application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of this application shall be within the scope of the rights of the embodiments of this application.

Claims

1. A typical remote sensing monitoring method for marine ecological disasters, characterized in that, The method includes the following steps: Obtain marine algal ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea; Classify the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm; Perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; the height is the thickness of the marine algae obtained by satellite altimetry; the characteristics include the texture characteristics and morphological characteristics of the marine algae; Predict the offset trajectory of the marine algal ecological disaster according to the characteristics and height of the marine algal ecological disaster; The predicting the offset trajectory of the marine algal ecological disaster according to the characteristics and height of the marine algal ecological disaster includes the following steps: Based on marine satellite remote sensing data, establish a marine algal ecological disaster trajectory prediction model by using a mesoscale meteorological model, an unstructured grid nearshore ocean model, and Monte Carlo stochastic statistical theory; Use the marine algal ecological disaster trajectory prediction model to calculate the wind-induced drift of the marine algal ecological disaster based on the drift movement of the marine algal ecological disaster under the action of the surface ocean fluid and wind, and adopt a velocity decomposition method; Use the marine algal ecological disaster trajectory prediction model to predict and generate a statistically significant and time-evolving optimal trajectory area by applying the Monte Carlo method according to multiple drift particles arranged in the area and time period when the marine algal ecological disaster is first observed and various random and uncertain factors during the drift process; Use the marine algal ecological disaster trajectory prediction model to calculate the candidate shore contact information of the marine algal ecological disaster according to specific ocean and meteorological conditions.

2. A typical marine ecological disaster remote sensing monitoring method according to claim 1, characterized in that, The obtaining the marine algal ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea includes the following steps: Obtain the first marine algal ecological disaster monitoring data from marine satellite remote sensing data; Obtain the second marine algal ecological disaster monitoring data from the high-resolution image data in the land satellite remote sensing data; Obtain the third marine algal ecological disaster monitoring data from the satellite altimetry data in the land satellite remote sensing data.

3. A typical remote sensing monitoring method for marine ecological disasters according to claim 1, characterized in that, Before the classifying the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm, the method further includes the following steps: Fuse the data from different data sources in the marine algal ecological disaster monitoring data.

4. A typical marine ecological disaster remote sensing monitoring method according to claim 1, characterized in that, The steps of pre-constructing the marine algal ecological disaster recognition algorithm include the following steps: Obtain the prior marine water environment, marine meteorology, satellite spectrum, and texture information before and after the occurrence of marine algal ecological disaster events; Use the time series correlation analysis method to obtain target indicative parameters according to the marine water environment, the marine meteorology, the satellite spectrum, and the texture information; Combine the target indicative parameters and the XGBOOST machine learning algorithm to construct the per-pixel marine algal ecological disaster recognition algorithm.

5. A typical remote sensing monitoring method for marine ecological disasters according to claim 1, characterized in that The performing three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters includes the following steps: Extract spectral features and index features for the marine algal ecological disasters classified according to optical data, and extract the first texture feature of the marine algal ecological disasters using the first three components of the principal component analysis of the original image; Extract the backscattering coefficient for the marine algal ecological disasters classified according to SAR data, and extract the second texture feature of the marine algal ecological disasters from the backscattering coefficient; Extract the elevation feature of the marine algal ecological disasters classified according to elevation data; Perform feature selection and dimensionality reduction on the spectral features, the index features, the first texture feature, the second texture feature, and the elevation feature through the random forest algorithm; Use a laser altimetry satellite to monitor and extract the growth range of the classified marine algal ecological disasters and the sea surface height of the surrounding area.

6. A typical marine ecological disaster remote sensing monitoring method according to any one of claims 1 to 5, characterized in that, The method further includes the following steps: Output monitoring and early warning information according to the offset trajectory of the marine algal ecological disasters.

7. A remote sensing monitoring device for typical marine ecological disasters, characterized in that, The device includes: A data acquisition unit, configured to acquire marine algal ecological disaster monitoring data from multi-source satellite remote sensing data of land and sea; An algae classification unit, configured to classify the marine algal ecological disasters in the marine algal ecological disaster monitoring data by using a pre-constructed marine algal ecological disaster recognition algorithm; An algae measurement unit, configured to perform three-dimensional quantitative measurement on the classified marine algal ecological disasters to obtain the characteristics and height of the marine algal ecological disasters; the height is the thickness of the marine algae obtained by satellite laser altimetry; the characteristics include the texture characteristics and morphological characteristics of the marine algae; A marine algal ecological disaster trajectory prediction unit, configured to predict the offset trajectory of the marine algal ecological disasters according to the characteristics and height of the marine algal ecological disasters; The predicting the offset trajectory of the marine algal ecological disasters according to the characteristics and height of the marine algal ecological disasters includes the following steps: Establish a marine algal ecological disaster trajectory prediction model based on the mesoscale meteorological model, the unstructured grid nearshore ocean model, and the Monte Carlo random statistical theory using marine satellite remote sensing data; Use the marine algal ecological disaster trajectory prediction model to calculate the wind-induced drift of the marine algal ecological disasters based on the drift movement of the marine algal ecological disasters under the action of the marine surface fluid and wind, and adopt the velocity decomposition method; Use the marine algal ecological disaster trajectory prediction model to predict and generate a statistically significant and time-evolving optimal trajectory area according to multiple drift particles arranged in the area and time period when the marine algal ecological disasters are first observed and various randomness and uncertainty factors during the drift process by applying the Monte Carlo method; Use the marine algal ecological disaster trajectory prediction model to calculate the candidate shore contact information of the marine algal ecological disasters according to specific marine and meteorological conditions.

8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method according to any one of claims 1 to 6 is implemented.

Images