Mesoscale vortex detection method based on neural network and sea surface height abnormal data

Abstract

The invention discloses a mesoscale vortex detection method based on a neural network and sea surface height abnormal data. The method comprises the following steps: acquiring sea surface height data of a preset area; extracting a local extreme value in the sea surface height abnormal data from the sea surface height data; performing mesoscale vortex detection on the local extreme value through a contour method to obtain a first mesoscale vortex detection result; inputting the local extreme value into the mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training; and obtaining a mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result. According to the invention, two mesoscale vortex detection results are integrated, and the mesoscale vortex detection accuracy is improved.

Description

Technical Field

[0001] The present application relates to the field of mesoscale vortex detection, and in particular to a mesoscale vortex detection method based on neural network and sea surface height anomaly data. Background Art

[0002] Mesoscale eddies are an important natural phenomenon in the ocean, with diameters usually ranging from tens to hundreds of kilometers, formed by complex interactions of fluid dynamics. These eddies not only have an important impact on the transport of ocean heat, momentum and matter, but also regulate the productivity of marine organisms and the stability of ecosystems, and are crucial to understanding the mechanism of global climate change.

[0003] Accurate detection and identification of mesoscale eddies in the ocean is one of the key tasks in marine science research. Existing mesoscale eddy detection technologies mainly rely on satellite remote sensing, numerical simulation and field observation. However, these methods are susceptible to noise, insufficient feature extraction, slow processing speed and sensitive to outliers, which affect the accuracy of mesoscale eddy detection. Summary of the invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The main purpose of the embodiments of the present disclosure is to propose a mesoscale vortex detection method based on a neural network and sea surface height anomaly data, which can improve the accuracy of mesoscale vortex detection.

[0006] A first aspect of an embodiment of the present application provides a mesoscale vortex detection method based on a neural network and abnormal sea level data, the method comprising:

[0007] Get sea surface height data of a preset area;

[0008] Extracting local extreme values ​​in the sea surface height anomaly data from the sea surface height data;

[0009] Performing mesoscale vortex detection on the local extreme value by using the contour method to obtain a first mesoscale vortex detection result;

[0010] Inputting the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training;

[0011] The mesoscale vortex detection result of the preset area is obtained according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

[0012] The embodiment of the present application provides a mesoscale vortex detection method based on a neural network and sea level height anomaly data, by extracting the local extreme value of the sea level anomaly data in the sea level height data of a preset area, performing mesoscale vortex detection by isoline method according to the local extreme value, obtaining a first mesoscale vortex detection result, and performing mesoscale vortex detection again by a pre-trained mesoscale vortex detection model to obtain a second mesoscale vortex detection result, and finally obtaining a mesoscale vortex detection result of a preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result. It can be seen that the present application combines the two mesoscale vortex detection results to improve the accuracy of mesoscale vortex detection.

[0013] In some embodiments of the present application, before extracting the local extreme value in the sea level height anomaly data from the sea level height data, the method further includes:

[0014] Correcting the sea level height data according to the meteorological environment data of the preset area to obtain the corrected sea level height data;

[0015] The step of extracting the local extreme value in the abnormal sea level data from the sea level data comprises:

[0016] extracting sea surface height anomaly data from the sea surface height data;

[0017] determining local extreme values ​​in the sea surface height anomaly data;

[0018] The sea level height anomaly data is calculated using the following formula:

[0019] SLA(x,y)=H obs (x,y)-H mean (x,y)

[0020] Among them, SLA(x,y) is the sea surface height anomaly data, H obs (x, y) is the corrected sea surface height data, H mean (x, y) is the historical average sea level height data, and x and y represent longitude and latitude.

[0021] In some embodiments of the present application, determining a local extreme value in the sea level height anomaly data includes:

[0022] Dividing the sea surface height anomaly data into a plurality of local windows by a sliding window method;

[0023] The local extreme value of the sea level height anomaly data is determined in each local window, and the local extreme value includes a local minimum value and a local maximum value.

[0024] In some embodiments of the present application, the performing mesoscale vortex detection on the local extreme value by the contour line method to obtain a first mesoscale vortex detection result includes:

[0025] Draw contour maps of the local minimum and local maximum values ​​by contour method;

[0026] Determine whether it is a mesoscale vortex area according to the contour map;

[0027] If it is the mesoscale vortex area, the specific type of the mesoscale vortex area is determined based on the sea surface height anomaly data in the contour map.

[0028] In some embodiments of the present application, the training process of the mesoscale vortex detection model includes:

[0029] Acquire historical sea level height anomaly data and historical remote sensing data of the preset area;

[0030] extracting annotated mesoscale vortex instances from the historical sea surface height anomaly data and the historical remote sensing data;

[0031] Build a neural network-based detection model;

[0032] The detection model is trained according to the labeled mesoscale vortex instances to obtain the trained mesoscale vortex detection model.

[0033] In some embodiments of the present application, the detection model is a ResNet network model.

[0034] In some embodiments of the present application, obtaining the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result includes:

[0035] The first mesoscale vortex detection result and the second mesoscale vortex detection result are weighted and fused by the following formula to obtain the mesoscale vortex detection result of the preset area:

[0036] P final (x,y)=α·P CNN (x,y)+(1-α)·P SLA (x,y)

[0037] Among them, P final is the mesoscale vortex detection result in the prediction area, α is the fusion weight parameter, P CNN is the second mesoscale vortex detection result, P SLA is the first mesoscale vortex detection result, and (x, y) is the longitude and latitude of the preset area.

[0038] A second aspect of an embodiment of the present invention provides a mesoscale vortex detection device based on a neural network and abnormal sea level data, the device comprising:

[0039] A data acquisition module, used to acquire sea surface height data of a preset area;

[0040] A data extraction module, used for extracting local extreme values ​​in the sea level height anomaly data from the sea level height data;

[0041] A first detection module, configured to perform mesoscale vortex detection on the local extreme value by using an isovalue method to obtain a first mesoscale vortex detection result;

[0042] A second detection module is used to input the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training;

[0043] The vortex detection module is used to obtain the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

[0044] A third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the above-mentioned mesoscale vortex detection method based on neural network and sea surface height anomaly data.

[0045] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned mesoscale vortex detection method based on neural network and sea surface height anomaly data.

[0046] It can be understood that the beneficial effects of the second to fourth aspects compared with the related art are the same as the beneficial effects of the first aspect compared with the related art. Please refer to the relevant description in the first aspect, and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0048] Figure 1 It is a flow chart of a method for detecting a mesoscale vortex based on a neural network and abnormal sea level height data provided in an embodiment of the present application;

[0049] Figure 2 It is a vortex map of sea surface height anomaly data provided by an embodiment of the present application, based on a neural network and a mesoscale vortex detection method for sea surface height anomaly data;

[0050] Figure 3 The invention provides a method for detecting mesoscale vortices based on a neural network and abnormal sea surface height data. Figure 2 Schematic diagram of the results of mesoscale vortex detection;

[0051] Figure 4 It is a structural schematic diagram of a mesoscale vortex detection device based on a neural network and sea level height anomaly data provided in an embodiment of the present application;

[0052] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as limiting the present application.

[0054] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0055] In the description of the present application, it should be understood that the descriptions involving orientation, such as the orientation or positional relationship indicated as up, down, etc., are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0056] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0057] Mesoscale eddies are an important phenomenon in the ocean. They are usually tens to hundreds of kilometers in diameter and are formed in the complex interaction of fluid dynamics. These eddies can be caused by factors such as climate change, ocean circulation and terrain influences. Common forms include cyclonic eddies and anticyclonic eddies. Mesoscale eddies not only have an important influence on the transport of ocean heat, momentum and matter, but also can regulate the biological productivity of the ocean and the stability of the ecosystem. Their existence is crucial to understanding the mechanism of global climate change, especially playing an important role in climate patterns and weather forecasts.

[0058] Accurately detecting and identifying mesoscale eddies in the ocean is an important topic in marine science research. The existence and changes of mesoscale eddies directly affect the circulation patterns, heat transfer, material mixing and biological productivity of the ocean. By real-time monitoring and identifying mesoscale eddies, scientists can better understand the ocean dynamics, predict the trend of marine environmental changes, and provide a scientific basis for the development and protection of marine resources. At the same time, the detection data of mesoscale eddies is also an important reference for assessing global climate change, marine disaster warning and the distribution of fishery resources. In addition, mesoscale eddies can affect the distribution of nutrients in the water, thereby affecting the habitat and habitat of marine organisms. Therefore, by accurately identifying and monitoring mesoscale eddies, decision makers can be helped to formulate more scientific marine management strategies.

[0059] Existing mesoscale eddy detection and identification technologies mainly rely on satellite remote sensing, numerical simulation and field observation methods. Satellite remote sensing uses data such as sea surface temperature, salinity and ocean height anomaly to efficiently obtain ocean information over a large area; combined with the development of earth observation technology, sea level anomaly (SLA) data obtained by satellite altimeters is currently a common solution for extracting ocean mesoscale eddies. However, due to satellite orbit parameter deviations, sensor system errors, atmosphere and other factors, SLA data are prone to noise information. The generation of SLA data requires the use of statistical parameters for many years, which is also affected, thereby reducing the accuracy of extracting mesoscale eddies from it. In addition, the deformation radius scale of Rossby waves caused by the rotation of the earth and the change in latitude is similar to that of mesoscale eddies, which further interferes with the identification and extraction of mesoscale eddies.

[0060] Mesoscale vortices are divided into two types: cyclonic vortices (rotating counterclockwise in the Northern Hemisphere, also called "cold vortices") and anticyclonic vortices (rotating counterclockwise in the Southern Hemisphere, also called "warm vortices"). Cyclonic vortices appear as areas of negative extreme values ​​of height anomalies, and anticyclonic vortices appear as areas of positive extreme values ​​of height anomalies. The most intuitive manifestation of mesoscale vortices is closed contour lines of sea surface height anomalies, among which the SLA maximum point corresponds to the anticyclonic vortex, and the SLA minimum point corresponds to the cyclonic vortex.

[0061] For this purpose, refer to Figure 1The embodiment of the present application provides a mesoscale vortex detection method based on a neural network and sea level height anomaly data. The method is applied to a controller. The controller can be a server, an electronic device, or a mobile terminal, etc., which is not specifically limited here. The method includes the following steps S101 to S105.

[0062] Step S101: Acquire sea level height data of a preset area.

[0063] In this step, the preset area is the ocean area where mesoscale vortex detection is to be performed, and the sea surface height data is obtained through satellite remote sensing technology, specifically, the ocean surface height is measured by a satellite radar altimeter.

[0064] Step S102: extracting local extreme values ​​in the sea level height anomaly data from the sea level height data.

[0065] In this step, the meteorological and environmental data of the preset area are first obtained through satellite remote sensing technology, the ocean height data is corrected according to the meteorological and environmental data, the sea surface height anomaly data (SLA data) is calculated based on the corrected ocean height data, and then the local extreme values ​​of the sea surface height anomaly data are determined through the sliding window technology. The local extreme values ​​include the local minimum and the local maximum, so as to eliminate the noise data interference in the sea surface height anomaly data.

[0066] Step S103, performing mesoscale vortex detection on the local extreme value by using the contour method to obtain a first mesoscale vortex detection result.

[0067] In this step, the contour method is a method for extracting lines and surfaces with the same value from a two-dimensional or three-dimensional data field. In this embodiment, the contour method is used to draw contour maps around each local minimum and local maximum, and the closed area of ​​the contour lines is regarded as a possible mesoscale vortex area. The sea surface height anomaly data in the mesoscale vortex area is extracted, and the properties of the mesoscale vortex area are further confirmed in combination with the characteristics of the mesoscale vortex, thereby obtaining the first mesoscale vortex detection result.

[0068] Step S104, inputting the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training.

[0069] In this step, a mesoscale vortex detection model is pre-trained based on a neural network model. The deep features are automatically learned through the mesoscale vortex detection model. The mesoscale vortex detection model can improve the accuracy of ocean image recognition and process data. When the local extreme value of a preset area is obtained, the local extreme value is input into the mesoscale vortex detection model to obtain a second mesoscale vortex detection result.

[0070] Step S105, obtaining a mesoscale vortex detection result of a preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

[0071] In this step, the first mesoscale vortex detection result and the second mesoscale vortex detection result are weightedly fused, and the mesoscale vortex detection result of the preset area is obtained based on the result of the weighted fusion. By combining the two mesoscale vortex detection results, the accuracy of mesoscale vortex detection is further improved.

[0072] Different from the prior art, the embodiment of the present application extracts the local extreme value of the sea surface anomaly data in the sea surface height data of the preset area, performs mesoscale vortex detection by the contour method according to the local extreme value, obtains the first mesoscale vortex detection result, and performs mesoscale vortex detection again by the pre-trained mesoscale vortex detection model to obtain the second mesoscale vortex detection result, and finally obtains the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result. It can be seen that the present application combines the two mesoscale vortex detection results to improve the accuracy of mesoscale vortex detection.

[0073] The specific implementation methods of the above steps are introduced below.

[0074] Before extracting the local extreme value in the sea level height anomaly data from the sea level height data in step S102, the method further includes the following step S201.

[0075] Step S201, correcting the sea level data according to the meteorological environment data of the preset area to obtain corrected sea level data.

[0076] In this embodiment, satellite remote sensing data is acquired through satellite remote sensing technology, and the satellite remote sensing data includes sea surface height data, meteorological and environmental data; wherein the meteorological and environmental data include but are not limited to atmospheric pressure data, wind speed data, and temperature data; the influence of factors such as swells and tides on the sea surface height is calculated through ocean models such as HYCOM (Hybrid Coordinate Ocean Model) and NEMO (Nucleus for European Modelling of the Ocean), and correction is made, and then the meteorological and environmental data in the satellite data are combined with other ground observation data (such as buoys and tidal station data) for data assimilation to enhance the accuracy of the sea surface height data.

[0077] The step of extracting the local extreme value in the abnormal sea level data from the sea level data in step S102 includes the following steps S202 to S203.

[0078] Step S202: extracting sea level height anomaly data from the sea level height data.

[0079] Step S203: Determine the local extreme value in the sea level height anomaly data.

[0080] Among them, the sea surface height anomaly data is calculated by the following formula:

[0081] SLA(x,y)=H obs (x,y)-H mean (x,y)

[0082] Among them, SLA(x,y) is the sea surface height anomaly data, H obs (x, y) is the corrected sea surface height data, H mean (x, y) is the historical average sea level height data, and x and y represent longitude and latitude.

[0083] In this embodiment, the sea level height anomaly data of the preset area is calculated by using the corrected sea level height data and the historical average sea level height data.

[0084] Determining the local extreme value in the sea level height anomaly data in step S203 includes the following steps S301 to S302.

[0085] Step S301: Divide the sea level height anomaly data into multiple local windows by using a sliding window method.

[0086] Step S302: determining the local extreme value of the sea level height anomaly data in each local window, where the local extreme value includes the local minimum value and the local maximum value.

[0087] In this embodiment, the cyclonic vortex appears as a negative extreme value area of ​​the sea surface height anomaly, and the anticyclonic vortex appears as a positive extreme value area of ​​the sea surface height anomaly. The extreme value characteristics of the sea surface height anomaly can be used to effectively identify these vortex areas in the SLA data, which is conducive to improving the accuracy of the preliminary determination of the mesoscale vortex area in the ocean.

[0088] In this embodiment, the sea surface height anomaly data obtained by the above calculation is divided into multiple local windows using a sliding window method. In each local window, the local minimum and local maximum of the sea surface height anomaly data are found. According to the characteristics of cyclonic vortices and anticyclonic vortices, cyclonic vortices will appear in the local minimum area, and anticyclonic vortices will appear in the local maximum area. Each local minimum and local maximum point is compared with the value of the surrounding area, and a preliminary judgment is made on the vortex properties of the preset area, and the influence of noise data in the sea surface height anomaly data is eliminated, so as to improve the accuracy of subsequent mesoscale vortex detection results in the preset area.

[0089] The step of extracting the local extreme value in the abnormal sea level data from the sea level data in step S202 includes the following steps S401 to S403.

[0090] Step S401: Draw contour maps of local minimum and local maximum values ​​by using the contour method.

[0091] Step S402: determine whether it is a mesoscale vortex area based on the contour map.

[0092] Step S403: If it is a mesoscale vortex area, determine the specific type of the mesoscale vortex area according to the sea surface height anomaly data in the contour map.

[0093] In this embodiment, for each detected local minimum and local maximum, the contour method is further used to accurately define the vortex area, that is, a contour map is drawn around each local minimum and local maximum by the contour method, and the area closed by the contour lines is regarded as a possible mesoscale vortex area, and the sea surface height anomaly data in the mesoscale vortex area is extracted, and then combined with the characteristics of the mesoscale vortex (positive extreme value or negative extreme value) to further confirm the nature of the mesoscale vortex area, and obtain the first mesoscale vortex detection result.

[0094] In some embodiments, the minimum point is taken as the vortex center, and the maximum point is taken as the anti-vortex center. After the vortex center position is detected, the SLA contour method is used to detect the vortex boundary. With a step length of 0.5 cm, the SLA contour is searched from the vortex center position outward; since the measurement error of the altimeter is generally 2 to 3 cm, the SLA contour with a difference greater than 3 cm from the vortex center position and closed is determined as the boundary of the vortex. The height anomaly in the SLA data is used to detect potential mesoscale vortex areas.

[0095] The training process of the mesoscale vortex detection model in step S104 includes the following steps S501 to S504.

[0096] Step S501: Acquire historical sea level height anomaly data and historical remote sensing data of a preset area.

[0097] Step S502: extracting annotated mesoscale vortex instances from historical sea surface height anomaly data and historical remote sensing data.

[0098] Step S503: construct a detection model based on a neural network.

[0099] Step S504: training a detection model according to the annotated mesoscale vortex instances to obtain a trained mesoscale vortex detection model.

[0100] In this embodiment, the historical remote sensing image data comes from optical or multispectral sensors that complement the sea level data, which record the temperature, color, wind field and other information of the ocean surface. In this embodiment, after obtaining the high-resolution historical remote sensing images of the preset area, the historical remote sensing images are standardized to meet the input requirements of the neural network.

[0101] In some embodiments, the standardization of historical remote sensing images is specifically to scale the pixel values ​​of the historical remote sensing images to between 0 and 1 through normalization, or adjust them to a zero mean unit variance form (i.e., subtract the mean and divide by the standard deviation) to eliminate the amplitude, brightness and contrast differences between different historical remote sensing images, so as to improve the training effect of the neural network. In addition, in order to adapt to the fixed-size neural network input, the historical remote sensing images are cropped or resampled to a preset image size, and the preset image size is set to 224×224 pixels. It should be noted that the preset image size can also be set according to specific circumstances.

[0102] In this embodiment, labeled mesoscale vortex instances are extracted from historical sea level height anomaly data and historical remote sensing data, and a mesoscale vortex labeled sample set is constructed through the labeled mesoscale vortex instances. Seventy percent of the mesoscale vortex labeled sample set is used as a training data set for the mesoscale vortex model, and seventy percent of the mesoscale vortex labeled sample set is used as a test data set for the mesoscale vortex model.

[0103] In this embodiment, the detection model is a ResNet neural network model. ResNet (residual network) is a deep convolutional neural network (CNN). The biggest feature of the ResNet network model is the introduction of the concept of residual learning. By using skip connections (or identity mapping), the gradient vanishing problem in the deep neural network training process is effectively solved, allowing the network to reach an unprecedented depth.

[0104] In this embodiment, the ResNet network model mainly includes a convolutional layer (extracting features from an image to generate a low-dimensional spatial representation), a residual layer (adding the input directly to the output through a jump connection so that the network can learn the residual between the input and the output) and a fully connected layer. The ResNet network model can be expressed by the following formula:

[0105]

[0106] Among them, y represents the output of the ResNet network model, represents the residual function, x is the input, {W i} are trainable parameters in the ResNet network model.

[0107] In this embodiment, the ResNet model is trained by using a training data set, the deviation between the predicted result and the actual result is measured by the cross entropy loss function, and the Adam algorithm is combined with the adjustment of momentum and adaptive learning rate to accelerate the convergence of the model and prevent gradient oscillation, so as to adjust the parameters of the ResNet network model.

[0108] In this embodiment, as shown in the following formula, the ResNet network model is trained for multiple rounds using a training data set. In each round of training, the model parameters of the ResNet network model are adjusted using a back propagation algorithm to minimize the loss value, thereby obtaining a trained mesoscale vortex detection model. The performance of the mesoscale vortex detection model is evaluated using a test data set, and the accuracy of the mesoscale detection model is calculated. If the accuracy is greater than or equal to a preset accuracy, the trained mesoscale vortex detection model is used to perform mesoscale vortex detection. If the accuracy is less than the preset accuracy, the process returns to step S501, and the ResNet network model is retrained until the accuracy meets the requirements. The preset accuracy can be set according to actual conditions, and can also be set to 90%.

[0109]

[0110] Among them, L is the minimized loss function value, N is the number of samples, and y i is the true label, is the predicted probability.

[0111] In this embodiment, by combining a convolutional neural network (ResNet network), the shortcomings of the traditional algorithm in feature extraction are compensated, and the mesoscale vortex detection model can automatically learn deep features, thereby improving the detection accuracy of mesoscale vortices. The deep learning method is used to enhance the robustness to complex data and noise, and reduce the dependence of traditional methods on manual feature design, so that the mesoscale vortex detection model can still maintain good detection capabilities in the face of various environmental changes. By optimizing the structure and algorithm of the ResNet neural network, the computing efficiency is improved so that large-scale SLA data can be processed and real-time or near real-time mesoscale vortex detection can be achieved.

[0112] The step S105 of obtaining the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result includes the following step S601.

[0113] Step S601: weighted fusion of the first mesoscale vortex detection result and the second mesoscale vortex detection result is performed using the following formula to obtain a mesoscale vortex detection result of a preset area:

[0114] P final (x,y)=α·PCNN (x,y)+(1-α)·P SLA (x,y)

[0115] Among them, P final is the mesoscale vortex detection result in the prediction area, α is the fusion weight parameter, P CNN is the second mesoscale vortex detection result, P SLA is the first mesoscale vortex detection result, and (x, y) is the longitude and latitude of the preset area.

[0116] In this embodiment, α can be set according to specific circumstances. This embodiment achieves more accurate and automated mesoscale vortex identification by combining the detection results based on sea surface height anomaly data and the detection results based on the mesoscale vortex detection model.

[0117] In this embodiment, Figure 2 is the vortex diagram of the sea surface height anomaly data, Figure 3 Based on Figure 2 The sea level height anomaly data is obtained by using the technical solution provided in the embodiment of the present application to obtain the mesoscale vortex detection result diagram. It can be seen that the technical solution of the embodiment of the present application can accurately detect the mesoscale vortex.

[0118] In this embodiment, by extracting the local extreme value of the sea surface anomaly data in the sea surface height data of the preset area, the mesoscale vortex detection is performed by the contour method according to the local extreme value to obtain the first mesoscale vortex detection result, and the mesoscale vortex detection is performed again by the pre-trained mesoscale vortex detection model to obtain the second mesoscale vortex detection result, and finally the mesoscale vortex detection result of the preset area is obtained according to the first mesoscale vortex detection result and the second mesoscale vortex detection result. The two mesoscale vortex detection results are combined to improve the accuracy of the mesoscale vortex detection.

[0119] like Figure 3 As shown, some embodiments of the present application provide a mesoscale vortex detection device based on a neural network and abnormal sea level data, the device comprising a data acquisition module 1100, a data extraction module 1200, a first detection module 1300, a second detection module 1400, and a vortex detection module 1500, specifically:

[0120] The data acquisition module 1100 is used to acquire sea level height data of a preset area;

[0121] A data extraction module 1200 is used to extract local extreme values ​​in the sea level height anomaly data from the sea level height data;

[0122] The first detection module 1300 is used to perform mesoscale vortex detection on the local extreme value by using the contour method to obtain a first mesoscale vortex detection result;

[0123] The second detection module 1400 is used to input the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training;

[0124] The vortex detection module 1500 is used to obtain a mesoscale vortex detection result of a preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

[0125] It should be noted that the mesoscale vortex detection device based on neural network and sea level abnormality data provided in this embodiment and the above-mentioned mesoscale vortex detection method based on neural network and sea level abnormality data are based on the same inventive concept. Therefore, the relevant content of the above-mentioned mesoscale vortex detection method based on neural network and sea level abnormal data is also applicable to the content of the mesoscale vortex detection device based on neural network and sea level abnormal data. Therefore, it will not be repeated here.

[0126] like Figure 4 The embodiment of the present application further provides an electronic device, the electronic device comprising:

[0127] At least one hydrogen fuel cell;

[0128] at least one memory;

[0129] at least one processor;

[0130] at least one program;

[0131] The program is stored in the memory, and the processor executes at least one program to implement the above-mentioned mesoscale vortex detection method based on neural network and sea surface height anomaly data in the present disclosure.

[0132] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a vehicle-mounted computer, etc.

[0133] The electronic device according to the embodiment of the present application is described in detail below.

[0134] The processor 1600 may be implemented by a general-purpose central processing unit (CPU), 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 disclosure;

[0135] The memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1700 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 1700, and the processor 1600 calls and executes a mesoscale vortex detection method based on a neural network and abnormal sea surface height data in the embodiment of the present disclosure.

[0136] Input / output interface 1800, used to implement information input and output;

[0137] The communication interface 1900 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0138] Bus 2000 , which transmits information between various components of the device (e.g., processor 1600 , memory 1700 , input / output interface 1800 , and communication interface 1900 );

[0139] The processor 1600 , the memory 1700 , the input / output interface 1800 , and the communication interface 1900 are connected to each other in communication within the device via the bus 2000 .

[0140] An embodiment of the present disclosure also provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned mesoscale vortex detection method based on neural network and sea surface height anomaly data.

[0141] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0142] The embodiments described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0143] Those skilled in the art will appreciate that the technical solutions shown in the figures do not limit the embodiments of the present disclosure and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0144] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0145] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0146] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0147] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0148] In the several embodiments provided in the present 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 only schematic. For example, the division of units is only a logical function division. 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.

[0149] 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.

[0150] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] 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 the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store programs.

[0152] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above-mentioned implementation methods. Technical personnel familiar with the field can also make various equivalent modifications or substitutions without violating the spirit of the embodiments of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the embodiments of the present application.

[0153] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. A mesoscale vortex detection method based on neural network and sea level abnormality data, characterized in that: The method comprises: Get sea surface height data of a preset area; Extracting local extreme values ​​in the sea surface height anomaly data from the sea surface height data; Performing mesoscale vortex detection on the local extreme value by using the contour method to obtain a first mesoscale vortex detection result; Inputting the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training; The mesoscale vortex detection result of the preset area is obtained according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

2. The mesoscale vortex detection method based on neural network and sea level abnormal data according to claim 1 is characterized in that: Before extracting the local extreme value in the sea level height anomaly data from the sea level height data, the method further comprises: Correcting the sea level height data according to the meteorological environment data of the preset area to obtain the corrected sea level height data; The step of extracting the local extreme value in the abnormal sea level data from the sea level data comprises: extracting sea surface height anomaly data from the sea surface height data; determining local extreme values ​​in the sea surface height anomaly data; The sea level height anomaly data is calculated using the following formula: SLA(x,y)=H obs (x,y)-H mean (x,y) Among them, SLA(x,y) is the sea surface height anomaly data, H obS (x, y) is the corrected sea surface height data, H mean (x, y) is the historical average sea level height data, and x and y represent longitude and latitude.

3. The mesoscale vortex detection method based on neural network and sea level abnormal data according to claim 2 is characterized in that: Determining the local extreme value in the sea level height anomaly data comprises: Dividing the sea surface height anomaly data into a plurality of local windows by a sliding window method; The local extreme value of the sea level height anomaly data is determined in each local window, and the local extreme value includes a local minimum value and a local maximum value.

4. The mesoscale vortex detection method based on neural network and sea level abnormality data according to claim 3 is characterized in that: The performing mesoscale vortex detection on the local extreme value by the isovalue method to obtain a first mesoscale vortex detection result includes: Draw contour maps of the local minimum and local maximum values ​​by contour method; Determine whether it is a mesoscale vortex area according to the contour map; If it is the mesoscale vortex area, the specific type of the mesoscale vortex area is determined based on the sea surface height anomaly data in the contour map.

5. The mesoscale vortex detection method based on neural network and sea level abnormal data according to claim 1 is characterized in that: The training process of the mesoscale vortex detection model includes: Acquire historical sea level height anomaly data and historical remote sensing data of the preset area; extracting annotated mesoscale vortex instances from the historical sea surface height anomaly data and the historical remote sensing data; Build a neural network-based detection model; The detection model is trained according to the labeled mesoscale vortex instances to obtain the trained mesoscale vortex detection model.

6. The mesoscale vortex detection method based on neural network and sea level abnormality data according to claim 5 is characterized in that: The detection model is a ResNet network model.

7. The mesoscale vortex detection method based on neural network and sea level abnormality data according to claim 1 is characterized in that: The obtaining the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result includes: The first mesoscale vortex detection result and the second mesoscale vortex detection result are weighted and fused by the following formula to obtain the mesoscale vortex detection result of the preset area: P final (x,y)=α·P CNN (x,y)+(1−α)·P SLA (x,y) Among them, P final is the mesoscale vortex detection result in the prediction area, α is the fusion weight parameter, P CNN is the second mesoscale vortex detection result, P SLA is the first mesoscale vortex detection result, and (x, y) is the longitude and latitude of the preset area.

8. A mesoscale vortex detection device based on neural network and sea level abnormality data, characterized in that: The device comprises: A data acquisition module, used to acquire sea surface height data of a preset area; A data extraction module, used for extracting local extreme values ​​in the sea level height anomaly data from the sea level height data; A first detection module, configured to perform mesoscale vortex detection on the local extreme value by using an isovalue method to obtain a first mesoscale vortex detection result; A second detection module is used to input the local extreme value into a mesoscale vortex detection model to obtain a second mesoscale vortex detection result; the mesoscale vortex detection model is obtained based on neural network training; The vortex detection module is used to obtain the mesoscale vortex detection result of the preset area according to the first mesoscale vortex detection result and the second mesoscale vortex detection result.

9. An electronic device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the mesoscale vortex detection method based on a neural network and sea surface height anomaly data as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute a mesoscale vortex detection method based on a neural network and sea surface height anomaly data as described in any one of claims 1 to 7.

Images