Early warning method and system for monitoring maritime information in real time

Abstract

The invention relates to the technical field of marine disaster early warning, and discloses an early warning method and system for monitoring marine information in real time, and the method comprises the steps: obtaining water surface detection data collected by each piece of water surface monitoring equipment in a peripheral echelon in real time, and when the type of a pollutant is determined according to the water surface detection data, carrying out the early warning of the marine information; triggering each water surface monitoring device in the internal echelon to collect water surface detection data; acquiring pollution data of pollutants according to the water surface detection data acquired by the peripheral echelon and the internal echelon; taking the pollution data as an input feature of a pre-configured pollutant prediction model, and obtaining the estimated time when the pollutants arrive at the target sea area by using the pre-configured pollutant prediction model; according to the invention, by predicting the estimated time for the pollutants to reach the target sea area, important decision support can be provided for maintaining the health and sustainability of offshore fishery resources.

Description

Technical Field

[0001] The present invention relates to the field of marine disaster early warning technology, and more specifically, to an early warning method and system for real-time monitoring of marine information. Background Art

[0002] In recent years, with the increasing demand for marine resources, offshore marine aquaculture has been vigorously developed; unlike inland freshwater aquaculture, the water bodies in the offshore area are in direct contact with the water bodies in the offshore area, which makes the water quality of the offshore area easily affected by the water bodies in the offshore area; at the same time, the spread of marine disasters in the offshore area and adjacent offshore areas (such as oil tanker leaks and offshore drilling leaks, etc.) also threatens the safety and production stability of offshore farms; therefore, an efficient and accurate early warning method is needed so that timely measures can be taken to maintain the health and sustainability of offshore fishery resources.

[0003] At present, the existing marine disaster warning methods or systems for offshore areas usually tend to be designed for marine biological disaster warnings in offshore areas, such as red tide warnings for the protection of fishery resources. Although there are some relevant documents for offshore pollution disaster warnings, for example, the Chinese patent with the authorization publication number CN113177183B discloses a seawater pollution monitoring and warning method and system based on marine remote sensing images. Such methods achieve offshore pollution disaster warnings by monitoring the pollution trend of offshore rivers. However, research and practical application of the above methods and existing technologies have found that the above methods and existing technologies have at least the following defects:

[0004] (1) It is impossible to timely predict and warn of pollution incidents from outside the target sea area, which may easily cause the escape or death of organisms in offshore aquaculture areas, making it difficult to provide important decision-making support for maintaining the health and sustainability of offshore fishery resources;

[0005] (2) Monitoring has a lag, and the prediction characteristics and results are easily disturbed, making it difficult to be used for early warning of small-scale seawater pollution incidents. Summary of the invention

[0006] The purpose of the present invention is to provide an early warning method and system for real-time monitoring of marine information to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for early warning of real-time monitoring of marine information, the method relying on a plurality of water surface monitoring devices, the plurality of water surface monitoring devices being deployed in echelons to form a monitoring zone consisting of an outer echelon and an inner echelon, the method comprising:

[0009] Acquire the water surface detection data collected by each water surface monitoring device in the outer echelon in real time, and when the type of pollutant is determined according to the water surface detection data, trigger each water surface monitoring device in the inner echelon to collect water surface detection data; the water surface detection data includes a set of material elements and a water surface image;

[0010] Obtaining the pollution data of pollutants based on the water surface detection data collected at the outer and inner stages; the pollution data includes the flow location of the pollutants, the time of arrival at the flow location, the flow velocity, the flow direction angle and the diffusion coefficient;

[0011] The pollution data is used as the input feature of the preconfigured pollutant prediction model, and the preconfigured pollutant prediction model is used to obtain the estimated time when the pollutants arrive at the target sea area.

[0012] Furthermore, before determining the type of pollutant based on the water surface detection data, it includes:

[0013] Extracting a material element set from the water surface detection data, wherein the material element set includes a plurality of detected material elements;

[0014] Retrieving the pollutant element database, placing each material element in the material element set into the pollutant element database for query traversal to obtain the query result;

[0015] When the query result shows an empty set, it is determined that no marine pollution disaster event has occurred; when the query result shows a non-empty set, it is determined that a marine pollution disaster event has occurred.

[0016] Further, determining the type of pollutant according to the water surface detection data includes:

[0017] The corresponding surface monitoring equipment that detects marine pollution disaster events in the outer echelon is marked as the first target equipment;

[0018] Acquire a set of material elements and a water surface image collected by the first target device, and extract texture features and color features in the water surface image;

[0019] The material element set, texture feature and color feature are combined into a combined feature, and the combined feature is input into a preconfigured pollutant identification model to obtain the pollutant type.

[0020] Furthermore, the generation logic of the preconfigured pollutant identification model is as follows:

[0021] Acquire historical pollutant identification data, and divide the historical pollutant identification data into a pollutant identification training set and a pollutant identification test set; the historical pollutant identification data includes a combination feature and its corresponding annotation label;

[0022] Constructing a classifier, taking the combined features in the pollutant identification training set as input data of the classifier, taking the corresponding annotation labels in the pollutant identification training set as output data of the classifier, training the classifier, and obtaining an initial classification network;

[0023] The input data of the classifier is used to perform model verification on the initial classification network, and the initial classification network with a preset test accuracy is output as a preconfigured pollutant identification model.

[0024] Further, after each water surface monitoring device in the internal echelon is triggered to collect water surface detection data, it includes:

[0025] Within the set time range, the corresponding surface monitoring equipment that detects marine pollution disaster events within the inner echelon is marked as the second target equipment;

[0026] Counting the number of second target devices, and comparing the number of second target devices with a preset number threshold;

[0027] If the number of second target devices is less than or equal to the preset number threshold, it is determined that the marine pollution disaster event will not spread to the target sea area; if the number of second target devices is greater than the preset number threshold, it is determined that the marine pollution disaster event will spread to the target sea area.

[0028] Furthermore, the flow position of the pollutant is obtained based on the coordinates of the first target device and the second target device; the time of arriving at the flow position is obtained based on the time determined by the first target device and the second target device according to the marine pollution disaster event.

[0029] Furthermore, the generation logic of the preconfigured pollutant prediction model is as follows:

[0030] Obtaining historical estimated time training data, and dividing the historical estimated time training data into an estimated time training set and an estimated time test set; the historical estimated time training data includes input features and the time when the corresponding pollutants arrive at the target sea area;

[0031] Construct a regression network, use the input features in the estimated time training set as the input data of the regression network, use the time when the pollutants in the estimated time training set arrive at the target sea area as the output data of the regression network, train the regression network, and obtain an initial pollutant prediction network;

[0032] The estimated time test set is used to perform model verification on the initial pollutant prediction network, and the initial pollutant prediction network with a test error less than or equal to the test error is output as the preconfigured pollutant prediction model.

[0033] An early warning system for real-time monitoring of marine information, comprising:

[0034] A data collection module is used to obtain in real time the water surface detection data collected by each water surface monitoring device in the peripheral echelon, and when the type of pollutant is determined according to the water surface detection data, each water surface monitoring device in the internal echelon is triggered to collect water surface detection data; the water surface detection data includes a set of material elements and a water surface image;

[0035] A feature extraction module is used to obtain pollution data of pollutants based on the water surface detection data collected from the peripheral echelon and the internal echelon; the pollution data includes the flow location of the pollutants, the time of arrival at the flow location, the flow velocity, the flow angle and the diffusion coefficient;

[0036] Disaster warning module, which uses pollution data as input features of the pre-configured pollutant prediction model and uses the pre-configured pollutant prediction model to obtain the estimated time when pollutants will arrive at the target sea area

[0037] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the early warning method for real-time monitoring of maritime information as described in any one of the above items is implemented.

[0038] A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, the early warning method for real-time monitoring of marine information as described in any one of the above items is implemented.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present application discloses an early warning method and system for real-time monitoring of marine information, including: real-time acquisition of water surface detection data collected by each water surface monitoring device in an outer echelon, and when the type of pollutant is determined according to the water surface detection data, triggering each water surface monitoring device in an inner echelon to collect water surface detection data; obtaining pollution data of pollutants based on the water surface detection data collected by the outer echelon and the inner echelon; using the pollution data as input features of a pre-configured pollutant prediction model, and using the pre-configured pollutant prediction model to obtain an estimated time for the pollutants to arrive at a target sea area; based on the above process, the present invention is conducive to timely prediction and early warning of pollution events from outside the target sea area, thereby helping to avoid the escape or death of organisms in offshore aquaculture areas, and helping to provide important decision-making support for maintaining the health and sustainability of offshore fishery resources; in addition, compared with the prior art, by deploying gradient monitoring belts, the present invention can be used to warn of small-scale marine pollution disaster events. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic flow chart of an early warning method for real-time monitoring of marine information provided by the present invention;

[0042] Figure 2 A schematic diagram of a module of an early warning system for real-time monitoring of marine information provided by the present invention;

[0043] Figure 3 A schematic diagram of the deployment of water surface monitoring equipment and sea area division provided by the present invention;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided by the present invention;

[0045] Figure 5 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] Example 1

[0048] See also Figure 1 As shown, this embodiment discloses an early warning method for real-time monitoring of marine information. The method relies on multiple water surface monitoring devices, and the multiple water surface monitoring devices are deployed in echelons to form a monitoring belt consisting of an outer echelon and an inner echelon. The method includes:

[0049] S101: acquiring water surface detection data collected by each water surface monitoring device in the peripheral echelon in real time, and when the type of pollutant is determined according to the water surface detection data, triggering each water surface monitoring device in the internal echelon to collect water surface detection data; the water surface detection data includes a material element set and a water surface image;

[0050] It should be noted that the target sea areas are specifically offshore aquaculture waters or offshore fishery resource management waters, while the non-target sea areas are relative to the target sea areas, including offshore sea areas adjacent to the offshore sea areas or the target sea areas. The scope and area of ​​the target sea areas are determined according to the specific conditions of the actual target sea areas.

[0051] It is worth noting that the multiple water surface monitoring devices are arranged in stages, such as Figure 3As shown in (Schematic diagram of water surface monitoring equipment deployment and sea area division), the shaded part in the figure is the target sea area, and the non-shaded part is the non-target sea area. In this schematic diagram, two echelons of water surface monitoring equipment are deployed in the non-target sea area and close to the target sea area (that is, the target sea area is surrounded by two echelons of water surface monitoring equipment), respectively, the outer echelon and the inner echelon, and the outer echelon water surface monitoring equipment includes a number of water surface monitoring equipment; it should be further explained that the echelon farthest from the target sea area (that is, the outermost) is taken as the outer echelon, and the echelon between the outer echelon and the boundary of the target sea area is taken as the inner echelon; it should also be explained that: there is only one outer echelon, while multiple inner echelons can be set, and the echelons are deployed at equal intervals, such as 1 nautical mile, 2 nautical miles, ..., 3 nautical miles or K nautical miles, etc., K is an integer greater than zero; and the water surface monitoring equipment in the echelon is also deployed at equal intervals, such as 100 meters, 200 meters, ..., 300 meters or R meters, etc., R is an integer greater than zero;

[0052] Specifically, the water surface monitoring device is a monitoring buoy or an unmanned monitoring ship, and the water surface monitoring device is provided with at least an electrochemical sensor, an optical sensor, a biosensor, a chemical sensor, a heavy metal sensor, an organic pollutant sensor, and a camera device, etc.;

[0053] It is understandable that: before collecting surface detection data, monitoring buoys are deployed at designated monitoring locations in non-target sea areas, or several monitoring unmanned ships are controlled to arrive at designated monitoring locations in non-target sea areas in advance to form multi-level monitoring belts. When pollutants are detected by any surface monitoring equipment in the outer level, it indicates that a marine pollution disaster event has occurred, and a marine pollution disaster event warning is required to determine the estimated time for pollutants to arrive at the target sea area, so as to take timely measures to maintain the health and sustainability of offshore fishery resources;

[0054] In implementation, before determining the type of pollutant based on water surface detection data, it includes:

[0055] Extracting a material element set from the water surface detection data, wherein the material element set includes a plurality of detected material elements;

[0056] Retrieving the pollutant element database, placing each material element in the material element set into the pollutant element database for query traversal to obtain the query result;

[0057] It should be noted that: a pollutant element database is established in advance, and the identified pollutant elements are included in the pollutant element database in advance, such as organic phosphorus, lead, mercury, cadmium, chromium, sulfur, nitrogen, etc.;

[0058] When the query result shows an empty set, it is determined that no marine pollution disaster event has occurred; when the query result shows a non-empty set, it is determined that a marine pollution disaster event has occurred;

[0059] It can be understood that when the query result shows an empty set, the collected material element set does not contain the polluting elements previously included in the polluting element database, which means that no marine water pollution has occurred; on the contrary, when the query result shows a non-empty set, the collected material element set contains the polluting elements previously included in the polluting element database, which means that marine water pollution has occurred;

[0060] In implementation, the method of determining the type of pollutant based on water surface detection data includes:

[0061] The corresponding surface monitoring equipment that detects marine pollution disaster events in the outer echelon is marked as the first target equipment;

[0062] Acquire a set of material elements and a water surface image collected by the first target device, and extract texture features and color features in the water surface image;

[0063] It should be noted that the texture features and color features in the water surface image are extracted by existing methods such as histogram, convolutional neural network (CNN) or pre-trained models (such as ResNet, VGG, Inception); it can be understood that these models have been trained on large-scale image data and have powerful feature extraction capabilities;

[0064] combining the material element set, the texture feature and the color feature into a combined feature, and inputting the combined feature into a preconfigured pollutant identification model to obtain the pollutant type;

[0065] Specifically, the generation logic of the preconfigured pollutant identification model is as follows:

[0066] Acquire historical pollutant identification data, and divide the historical pollutant identification data into a pollutant identification training set and a pollutant identification test set; the historical pollutant identification data includes a combination feature and its corresponding annotation label;

[0067] Specifically, the label is the type of pollutant, which includes but is not limited to petroleum pollutants, pesticide pollutants, fertilizer pollutants, heavy metal pollutants, and plastic pollutants;

[0068] It should be noted that the labeling is realized by manual labeling or automatic labeling; for example, the material element set of petroleum pollutants includes organic matter, sulfur, nitrogen, oxygen and other elemental components, and the color feature of petroleum pollutants is dark brown or black, and its texture feature is flaky in the water body, so the combination features that meet the above conditions are marked as petroleum pollutants; similarly, the labeling principle of other pollutant types is the same, which will not be described in detail;

[0069] Constructing a classifier, taking the combined features in the pollutant identification training set as input data of the classifier, taking the corresponding annotation labels in the pollutant identification training set as output data of the classifier, training the classifier, and obtaining an initial classification network;

[0070] Using the input data of the classifier to perform model verification on the initial classification network, outputting an initial classification network with a test accuracy greater than or equal to a preset test accuracy as a preconfigured pollutant identification model;

[0071] It should be noted that: the classifier is specifically a RNN recurrent neural network model;

[0072] In an optional implementation, after each water surface monitoring device in the internal echelon is triggered to collect water surface detection data, the method includes:

[0073] Within the set time range, the corresponding surface monitoring equipment that detects marine pollution disaster events within the inner echelon is marked as the second target equipment;

[0074] It should be understood that: how to determine the marine pollution disaster event, and how to mark the corresponding surface monitoring equipment that has detected the marine pollution disaster event in the inner echelon as the second target equipment; the same logic as the above about the marine pollution disaster event and marking the first target equipment, the details can be referred to the above description, and no more elaboration is given;

[0075] It should be noted that the set time range is determined according to the specific experimental results of the technicians, such as 1 hour, 2 hours, ..., 3 hours or W hours, etc., where W is an integer greater than zero;

[0076] Counting the number of second target devices, and comparing the number of second target devices with a preset number threshold;

[0077] If the number of the second target devices is less than or equal to the preset number threshold, it is determined that the marine pollution disaster event will not spread to the target sea area; if the number of the second target devices is greater than the preset number threshold, it is determined that the marine pollution disaster event will spread to the target sea area;

[0078] It can be understood that: through the monitoring belt composed of the outer echelon and the inner echelon, that is, using the multi-echelon equipment deployment form, the steps of this embodiment can make a targeted judgment on whether the marine pollution disaster event will affect the target sea area; further explanation is that by determining whether a certain amount of second target equipment will appear in the inner echelon within a certain period of time, it can be known whether the pollutants will spread to the target sea area, which is conducive to determining whether to trigger or not the early warning mechanism, and is conducive to saving computing resources;

[0079] It should be understood that when it is determined that a marine pollution disaster incident will not spread to the target sea area, the subsequent early warning mechanism will not be triggered, that is, it is assumed that the pollutants will not spread to the target sea area; on the contrary, when it is determined that a marine pollution disaster incident will spread to the target sea area, the subsequent early warning mechanism will be triggered, that is, it is believed that the pollutants will spread to the target sea area, and the estimated time for the pollutants to arrive at the target sea area will be predicted.

[0080] S102: Obtaining pollution data of pollutants based on the water surface detection data collected at the outer and inner stages; the pollution data includes the flow location of the pollutants, the time of arrival at the flow location, the flow velocity, the flow direction angle and the diffusion coefficient;

[0081] Specifically, the flow position of the pollutant is obtained according to the coordinates of the first target device and the second target device; the time of reaching the flow position is obtained according to the time determined by the first target device and the second target device according to the marine pollution disaster event;

[0082] It can be understood that: when the first target device or the second target device is obtained, it means that pollutants have appeared in the area of ​​the corresponding water surface monitoring device, and the coordinates of the corresponding water surface monitoring device are used as the flow position of the pollutants; similarly, when the first target device or the second target device is obtained, it is considered that a marine pollution disaster event has occurred, and the time when the first target device or the second target device has generated the marine pollution disaster event is used as the time of arrival at the flow position;

[0083] It should be noted that the average flow rate of the pollutants is calculated based on each set of calculation data. An exemplary explanation is that, assuming that there are three first target devices in the outer echelon, namely A1, A2 and A3, and two first target devices in the inner echelon, namely B1 and B2, there are six combinations through permutations and combinations, namely (A1, A2)(A1, A3), (A2, A3), (A1, B1), (A1, B2) and (B1, B2), and the flow positions and arrival flow positions of the two target devices in each combination are taken as a set of calculation data; the calculation formula for the average flow rate of the pollutants is: Where: is the average flow velocity of pollutants, V iis the flow rate of the i-th group of pollutants, Q is the total number of calculated data groups, (X 1 ,Y 1 ) and (X 2 ,Y 2 ) are the flow locations of the two pollutants, T 2 -T 1 is the absolute difference between the two arrival times at the flow locations; accordingly, the logic for obtaining the flow angle of the pollutant is also similar, such as using the inverse tangent function to calculate the flow angle of the angle pollutant, for example:

[0084] It should also be noted that: the water surface detection data also includes the concentration value of the pollutant; the diffusion coefficient is calculated based on the concentration value of the pollutant, and its calculation formula is: Where: J is the diffusion flux, which represents the mass of material passing through per unit area per unit time, and the unit is kg / m 2 / s; is the gradient of pollutant concentration C with space X; D is the diffusion coefficient;

[0085] It can be understood that: different from the traditional marine disaster prediction model, this implementation step obtains the flow location, arrival time, flow rate and flow direction angle of the pollutants through the first target device of the outer echelon and the second target device of the inner echelon, which is conducive to eliminating or weakening the variability of parameters such as actual ocean current velocity and wind speed, and improving the accuracy of the final model prediction.

[0086] S103: using the pollution data as input features of a preconfigured pollutant prediction model, and using the preconfigured pollutant prediction model to obtain an estimated time for the pollutants to arrive at the target sea area;

[0087] Specifically, the generation logic of the preconfigured pollutant prediction model is as follows:

[0088] Obtaining historical estimated time training data, and dividing the historical estimated time training data into an estimated time training set and an estimated time test set; the historical estimated time training data includes input features and the time when the corresponding pollutants arrive at the target sea area;

[0089] It should be understood that the input features in the historical estimated time training data include the flow location of the pollutant, the time of arrival at the flow location, flow velocity, flow angle and diffusion coefficient; and the time when the corresponding pollutant in the historical estimated time training data arrives at the target sea area is obtained according to the actual situation or experimental records;

[0090] Construct a regression network, use the input features in the estimated time training set as the input data of the regression network, use the time when the pollutants in the estimated time training set arrive at the target sea area as the output data of the regression network, train the regression network, and obtain an initial pollutant prediction network;

[0091] The estimated time test set is used to verify the model of the initial pollutant prediction network, and the initial pollutant prediction network with a test error less than or equal to the test error is output as the preconfigured pollutant prediction model;

[0092] It should be noted that: the regression network is specifically a specific one of the models such as random forest regression, polynomial regression, support vector machine regression or neural network;

[0093] By predicting the estimated time for pollutants to arrive at the target sea area, this embodiment is conducive to providing important decision-making support for maintaining the health and sustainability of offshore fishery resources; in addition, compared with the existing technology, by deploying gradient monitoring belts, the present invention can be used to warn of small-scale marine pollution disaster events.

[0094] Example 2

[0095] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses an early warning system for real-time monitoring of marine information, including:

[0096] The data collection module 210 is used to obtain the water surface detection data collected by each water surface monitoring device in the peripheral echelon in real time, and when the type of pollutant is determined according to the water surface detection data, each water surface monitoring device in the internal echelon is triggered to collect water surface detection data; the water surface detection data includes a set of material elements and a water surface image;

[0097] It should be noted that the target sea areas are specifically offshore aquaculture waters or offshore fishery resource management waters, while the non-target sea areas are relative to the target sea areas, including offshore sea areas adjacent to the offshore sea areas or the target sea areas. The scope and area of ​​the target sea areas are determined according to the specific conditions of the actual target sea areas.

[0098] It is worth noting that the multiple water surface monitoring devices are arranged in stages, such as Figure 3As shown in (Schematic diagram of water surface monitoring equipment deployment and sea area division), the shaded part in the figure is the target sea area, and the non-shaded part is the non-target sea area. In this schematic diagram, two echelons of water surface monitoring equipment are deployed in the non-target sea area and close to the target sea area (that is, the target sea area is surrounded by two echelons of water surface monitoring equipment), respectively, the outer echelon and the inner echelon, and the outer echelon water surface monitoring equipment includes a number of water surface monitoring equipment; it should be further explained that the echelon farthest from the target sea area (that is, the outermost) is taken as the outer echelon, and the echelon between the outer echelon and the boundary of the target sea area is taken as the inner echelon; it should also be explained that: there is only one outer echelon, while multiple inner echelons can be set, and the echelons are deployed at equal intervals, such as 1 nautical mile, 2 nautical miles, ..., 3 nautical miles or K nautical miles, etc., K is an integer greater than zero; and the water surface monitoring equipment in the echelon is also deployed at equal intervals, such as 100 meters, 200 meters, ..., 300 meters or R meters, etc., R is an integer greater than zero;

[0099] Specifically, the water surface monitoring device is a monitoring buoy or an unmanned monitoring ship, and the water surface monitoring device is provided with at least an electrochemical sensor, an optical sensor, a biosensor, a chemical sensor, a heavy metal sensor, an organic pollutant sensor, and a camera device, etc.;

[0100] It is understandable that: before collecting surface detection data, monitoring buoys are deployed at designated monitoring locations in non-target sea areas, or several monitoring unmanned ships are controlled to arrive at designated monitoring locations in non-target sea areas in advance to form multi-level monitoring belts. When pollutants are detected by any surface monitoring equipment in the outer level, it indicates that a marine pollution disaster event has occurred, and a marine pollution disaster event warning is required to determine the estimated time for pollutants to arrive at the target sea area, so as to take timely measures to maintain the health and sustainability of offshore fishery resources;

[0101] In implementation, before determining the type of pollutant based on water surface detection data, it includes:

[0102] Extracting a material element set from the water surface detection data, wherein the material element set includes a plurality of detected material elements;

[0103] Retrieving the pollutant element database, placing each material element in the material element set into the pollutant element database for query traversal to obtain the query result;

[0104] It should be noted that: a pollutant element database is established in advance, and the identified pollutant elements are included in the pollutant element database in advance, such as organic phosphorus, lead, mercury, cadmium, chromium, sulfur, nitrogen, etc.;

[0105] When the query result shows an empty set, it is determined that no marine pollution disaster event has occurred; when the query result shows a non-empty set, it is determined that a marine pollution disaster event has occurred;

[0106] It can be understood that when the query result shows an empty set, the collected material element set does not contain the polluting elements previously included in the polluting element database, which means that no marine water pollution has occurred; on the contrary, when the query result shows a non-empty set, the collected material element set contains the polluting elements previously included in the polluting element database, which means that marine water pollution has occurred;

[0107] In implementation, the method of determining the type of pollutant based on water surface detection data includes:

[0108] The corresponding surface monitoring equipment that detects marine pollution disaster events in the outer echelon is marked as the first target equipment;

[0109] Acquire a set of material elements and a water surface image collected by the first target device, and extract texture features and color features in the water surface image;

[0110] It should be noted that the texture features and color features in the water surface image are extracted by existing methods such as histogram, convolutional neural network (CNN) or pre-trained models (such as ResNet, VGG, Inception); it can be understood that these models have been trained on large-scale image data and have powerful feature extraction capabilities;

[0111] combining the material element set, the texture feature and the color feature into a combined feature, and inputting the combined feature into a preconfigured pollutant identification model to obtain the pollutant type;

[0112] Specifically, the generation logic of the preconfigured pollutant identification model is as follows:

[0113] Acquire historical pollutant identification data, and divide the historical pollutant identification data into a pollutant identification training set and a pollutant identification test set; the historical pollutant identification data includes a combination feature and its corresponding annotation label;

[0114] Specifically, the label is the type of pollutant, which includes but is not limited to petroleum pollutants, pesticide pollutants, fertilizer pollutants, heavy metal pollutants, and plastic pollutants;

[0115] It should be noted that the labeling is realized by manual labeling or automatic labeling; for example, the material element set of petroleum pollutants includes organic matter, sulfur, nitrogen, oxygen and other elemental components, and the color feature of petroleum pollutants is dark brown or black, and its texture feature is flaky in the water body, so the combination features that meet the above conditions are marked as petroleum pollutants; similarly, the labeling principle of other pollutant types is the same, which will not be described in detail;

[0116] Constructing a classifier, taking the combined features in the pollutant identification training set as input data of the classifier, taking the corresponding annotation labels in the pollutant identification training set as output data of the classifier, training the classifier, and obtaining an initial classification network;

[0117] Using the input data of the classifier to perform model verification on the initial classification network, outputting an initial classification network with a test accuracy greater than or equal to a preset test accuracy as a preconfigured pollutant identification model;

[0118] It should be noted that: the classifier is specifically a RNN recurrent neural network model;

[0119] In an optional implementation, after each water surface monitoring device in the internal echelon is triggered to collect water surface detection data, the method includes:

[0120] Within the set time range, the corresponding surface monitoring equipment that detects marine pollution disaster events within the inner echelon is marked as the second target equipment;

[0121] It should be understood that: how to determine the marine pollution disaster event, and how to mark the corresponding surface monitoring equipment that has detected the marine pollution disaster event in the inner echelon as the second target equipment; the same logic as the above about the marine pollution disaster event and marking the first target equipment, the details can be referred to the above description, and no more elaboration is given;

[0122] It should be noted that the set time range is determined according to the specific experimental results of the technicians, such as 1 hour, 2 hours, ..., 3 hours or W hours, etc., where W is an integer greater than zero;

[0123] Counting the number of second target devices, and comparing the number of second target devices with a preset number threshold;

[0124] If the number of the second target devices is less than or equal to the preset number threshold, it is determined that the marine pollution disaster event will not spread to the target sea area; if the number of the second target devices is greater than the preset number threshold, it is determined that the marine pollution disaster event will spread to the target sea area;

[0125] It can be understood that: through the monitoring belt composed of the outer echelon and the inner echelon, that is, using the multi-echelon equipment deployment form, the steps of this embodiment can make a targeted judgment on whether the marine pollution disaster event will affect the target sea area; further explanation is that by determining whether a certain amount of second target equipment will appear in the inner echelon within a certain period of time, it can be known whether the pollutants will spread to the target sea area, which is conducive to determining whether to trigger or not the early warning mechanism, and is conducive to saving computing resources;

[0126] It should be understood that when it is determined that a marine pollution disaster incident will not spread to the target sea area, the subsequent early warning mechanism will not be triggered, that is, it is assumed that the pollutants will not spread to the target sea area; on the contrary, when it is determined that a marine pollution disaster incident will spread to the target sea area, the subsequent early warning mechanism will be triggered, that is, it is believed that the pollutants will spread to the target sea area, and the estimated time for the pollutants to arrive at the target sea area will be predicted.

[0127] The feature extraction module 220 is used to obtain the pollution data of the pollutants based on the water surface detection data collected by the peripheral echelon and the internal echelon; the pollution data includes the flow position of the pollutants, the time of arrival at the flow position, the flow velocity, the flow angle and the diffusion coefficient;

[0128] Specifically, the flow position of the pollutant is obtained according to the coordinates of the first target device and the second target device; the time of reaching the flow position is obtained according to the time determined by the first target device and the second target device according to the marine pollution disaster event;

[0129] It can be understood that: when the first target device or the second target device is obtained, it means that pollutants have appeared in the area of ​​the corresponding water surface monitoring device, and the coordinates of the corresponding water surface monitoring device are used as the flow position of the pollutants; similarly, when the first target device or the second target device is obtained, it is considered that a marine pollution disaster event has occurred, and the time when the first target device or the second target device has generated the marine pollution disaster event is used as the time of arrival at the flow position;

[0130] It should be noted that the average flow rate of the pollutants is calculated based on each set of calculation data. An exemplary explanation is that, assuming that there are three first target devices in the outer echelon, namely A1, A2 and A3, and two first target devices in the inner echelon, namely B1 and B2, there are six combinations through permutations and combinations, namely (A1, A2)(A1, A3), (A2, A3), (A1, B1), (A1, B2) and (B1, B2), and the flow positions and arrival flow positions of the two target devices in each combination are taken as a set of calculation data; the calculation formula for the average flow rate of the pollutants is: Where: is the average flow velocity of pollutants, V iis the flow rate of the i-th group of pollutants, Q is the total number of calculated data groups, (X 1 ,Y 1 ) and (X 2 ,Y 2 ) are the flow locations of the two pollutants, T 2 -T 1 is the absolute difference between the two arrival times at the flow locations; accordingly, the logic for obtaining the flow angle of the pollutant is also similar, such as using the inverse tangent function to calculate the flow angle of the angle pollutant, for example:

[0131] It should also be noted that: the water surface detection data also includes the concentration value of the pollutant; the diffusion coefficient is calculated based on the concentration value of the pollutant, and its calculation formula is: Where: J is the diffusion flux, which represents the mass of material passing through per unit area per unit time, and the unit is kg / m 2 / s; is the gradient of pollutant concentration C with space X; D is the diffusion coefficient;

[0132] It can be understood that: different from the traditional marine disaster prediction model, this implementation step obtains the flow location, arrival time, flow rate and flow direction angle of the pollutants through the first target device of the outer echelon and the second target device of the inner echelon, which is conducive to eliminating or weakening the variability of parameters such as actual ocean current velocity and wind speed, and improving the accuracy of the final model prediction.

[0133] The disaster warning module 230 is used to use the pollution data as input features of a preconfigured pollutant prediction model, and use the preconfigured pollutant prediction model to obtain an estimated time for the pollutants to arrive at the target sea area;

[0134] Specifically, the generation logic of the preconfigured pollutant prediction model is as follows:

[0135] Obtaining historical estimated time training data, and dividing the historical estimated time training data into an estimated time training set and an estimated time test set; the historical estimated time training data includes input features and the time when the corresponding pollutants arrive at the target sea area;

[0136] It should be understood that the input features in the historical estimated time training data include the flow location of the pollutant, the time of arrival at the flow location, flow velocity, flow angle and diffusion coefficient; and the time when the corresponding pollutant in the historical estimated time training data arrives at the target sea area is obtained according to the actual situation or experimental records;

[0137] Construct a regression network, use the input features in the estimated time training set as the input data of the regression network, use the time when the pollutants in the estimated time training set arrive at the target sea area as the output data of the regression network, train the regression network, and obtain an initial pollutant prediction network;

[0138] The estimated time test set is used to verify the model of the initial pollutant prediction network, and the initial pollutant prediction network with a test error less than or equal to the test error is output as the preconfigured pollutant prediction model;

[0139] It should be noted that: the regression network is specifically a specific one of the models such as random forest regression, polynomial regression, support vector machine regression or neural network;

[0140] By predicting the estimated time for pollutants to arrive at the target sea area, this embodiment is conducive to providing important decision-making support for maintaining the health and sustainability of offshore fishery resources; in addition, compared with the existing technology, by deploying gradient monitoring belts, the present invention can be used to warn of small-scale marine pollution disaster events.

[0141] Example 3

[0142] See also Figure 4 As shown, this embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the early warning method for real-time monitoring of marine information provided by any one of the above methods.

[0143] Since the electronic device introduced in this embodiment is an electronic device used to implement an early warning method for real-time monitoring of maritime information in the embodiment of the present application, based on the early warning method for real-time monitoring of maritime information introduced in the embodiment of the present application, a person skilled in the art can understand the specific implementation of the electronic device of the present embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application is not described in detail here. As long as a person skilled in the art implements an electronic device used in an early warning method for real-time monitoring of maritime information in the embodiment of the present application, it belongs to the scope of protection of the present application.

[0144] Example 4

[0145] See also Figure 5 As shown, this embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, any of the above-mentioned early warning methods for real-time monitoring of maritime information is implemented.

[0146] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0147] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0148] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0150] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0151] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0152] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0153] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0154] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for early warning of real-time monitoring of marine information, the method relying on multiple water surface monitoring equipment, characterized in that: The plurality of water surface monitoring devices are deployed in stages to form a monitoring zone consisting of an outer stage and an inner stage. The method comprises: Acquire the water surface detection data collected by each water surface monitoring device in the outer echelon in real time, and when the type of pollutant is determined according to the water surface detection data, trigger each water surface monitoring device in the inner echelon to collect water surface detection data; the water surface detection data includes a set of material elements and a water surface image; Obtaining the pollution data of pollutants based on the water surface detection data collected at the outer and inner stages; the pollution data includes the flow location of the pollutants, the time of arrival at the flow location, the flow velocity, the flow direction angle and the diffusion coefficient; The pollution data is used as the input feature of the preconfigured pollutant prediction model, and the preconfigured pollutant prediction model is used to obtain the estimated time when the pollutants arrive at the target sea area.

2. The early warning method for real-time monitoring of marine information according to claim 1 is characterized in that: Before determining the type of contaminant based on water surface detection data, include: Extracting a material element set from the water surface detection data, wherein the material element set includes a plurality of detected material elements; Retrieving the pollutant element database, placing each material element in the material element set into the pollutant element database for query traversal to obtain the query result; When the query result shows an empty set, it is determined that no marine pollution disaster event has occurred; when the query result shows a non-empty set, it is determined that a marine pollution disaster event has occurred.

3. The early warning method for real-time monitoring of marine information according to claim 2 is characterized in that: Determining the type of pollutant according to the water surface detection data includes: The corresponding surface monitoring equipment that detects marine pollution disaster events in the outer echelon is marked as the first target equipment; Acquire a set of material elements and a water surface image collected by the first target device, and extract texture features and color features in the water surface image; The material element set, texture feature and color feature are combined into a combined feature, and the combined feature is input into a preconfigured pollutant identification model to obtain the pollutant type.

4. The early warning method for real-time monitoring of marine information according to claim 3 is characterized in that: The generation logic of the preconfigured pollutant identification model is as follows: Acquire historical pollutant identification data, and divide the historical pollutant identification data into a pollutant identification training set and a pollutant identification test set; the historical pollutant identification data includes a combination feature and its corresponding annotation label; Constructing a classifier, taking the combined features in the pollutant identification training set as input data of the classifier, taking the corresponding annotation labels in the pollutant identification training set as output data of the classifier, training the classifier, and obtaining an initial classification network; The input data of the classifier is used to perform model verification on the initial classification network, and the initial classification network with a preset test accuracy is output as a preconfigured pollutant identification model.

5. The early warning method for real-time monitoring of marine information according to claim 4 is characterized in that: After each water surface monitoring device in the internal echelon is triggered to collect water surface detection data, including: Within the set time range, the corresponding surface monitoring equipment that detects marine pollution disaster events within the inner echelon is marked as the second target equipment; Counting the number of second target devices, and comparing the number of second target devices with a preset number threshold; If the number of second target devices is less than or equal to the preset number threshold, it is determined that the marine pollution disaster event will not spread to the target sea area; if the number of second target devices is greater than the preset number threshold, it is determined that the marine pollution disaster event will spread to the target sea area.

6. The early warning method for real-time monitoring of marine information according to claim 5 is characterized in that: The flow position of the pollutant is obtained according to the coordinate assignment of the first target device and the second target device; The time of arriving at the flow-through position is obtained by assigning a time value determined by the first target device and the second target device according to the marine pollution disaster event.

7. The early warning method for real-time monitoring of marine information according to claim 6 is characterized in that: The generation logic of the preconfigured pollutant prediction model is as follows: Obtaining historical estimated time training data, and dividing the historical estimated time training data into an estimated time training set and an estimated time test set; the historical estimated time training data includes input features and the time when the corresponding pollutants arrive at the target sea area; Construct a regression network, use the input features in the estimated time training set as the input data of the regression network, use the time when the pollutants in the estimated time training set arrive at the target sea area as the output data of the regression network, train the regression network, and obtain an initial pollutant prediction network; The estimated time test set is used to perform model verification on the initial pollutant prediction network, and the initial pollutant prediction network with a test error less than or equal to the test error is output as the preconfigured pollutant prediction model.

8. An early warning system for real-time monitoring of marine information, characterized in that: include: A data collection module is used to obtain in real time the water surface detection data collected by each water surface monitoring device in the peripheral echelon, and when the type of pollutant is determined according to the water surface detection data, each water surface monitoring device in the internal echelon is triggered to collect water surface detection data; the water surface detection data includes a set of material elements and a water surface image; A feature extraction module is used to obtain pollution data of pollutants based on the water surface detection data collected from the peripheral echelon and the internal echelon; the pollution data includes the flow location of the pollutants, the time of arrival at the flow location, the flow velocity, the flow angle and the diffusion coefficient; The disaster warning module is used to use the pollution data as the input feature of the preconfigured pollutant prediction model, and use the preconfigured pollutant prediction model to obtain the estimated time when the pollutants arrive at the target sea area.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the early warning method for real-time monitoring of maritime information as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the early warning method for real-time monitoring of maritime information according to any one of claims 1 to 7 is implemented.

Images